*.lzo
*.patch
*.gcno
+*.ll
modules.builtin
Module.symvers
*.dwo
- directory with info on the /proc/sys/* files.
target/
- directory with info on generating TCM v4 fabric .ko modules
+tee.txt
+ - info on the TEE subsystem and drivers
this_cpu_ops.txt
- List rationale behind and the way to use this_cpu operations.
thermal/
rcubarrier.txt
- RCU and Unloadable Modules
rculist_nulls.txt
- - RCU list primitives for use with SLAB_DESTROY_BY_RCU
+ - RCU list primitives for use with SLAB_TYPESAFE_BY_RCU
rcuref.txt
- Reference-count design for elements of lists/arrays protected by RCU
rcu.txt
The <tt>rcu_state</tt> Structure</a>
<li> <a href="#The rcu_node Structure">
The <tt>rcu_node</tt> Structure</a>
+<li> <a href="#The rcu_segcblist Structure">
+ The <tt>rcu_segcblist</tt> Structure</a>
<li> <a href="#The rcu_data Structure">
The <tt>rcu_data</tt> Structure</a>
<li> <a href="#The rcu_dynticks Structure">
Finally, lines 64-66 produce an error if the maximum number of
CPUs is too large for the specified fanout.
+<h3><a name="The rcu_segcblist Structure">
+The <tt>rcu_segcblist</tt> Structure</a></h3>
+
+The <tt>rcu_segcblist</tt> structure maintains a segmented list of
+callbacks as follows:
+
+<pre>
+ 1 #define RCU_DONE_TAIL 0
+ 2 #define RCU_WAIT_TAIL 1
+ 3 #define RCU_NEXT_READY_TAIL 2
+ 4 #define RCU_NEXT_TAIL 3
+ 5 #define RCU_CBLIST_NSEGS 4
+ 6
+ 7 struct rcu_segcblist {
+ 8 struct rcu_head *head;
+ 9 struct rcu_head **tails[RCU_CBLIST_NSEGS];
+10 unsigned long gp_seq[RCU_CBLIST_NSEGS];
+11 long len;
+12 long len_lazy;
+13 };
+</pre>
+
+<p>
+The segments are as follows:
+
+<ol>
+<li> <tt>RCU_DONE_TAIL</tt>: Callbacks whose grace periods have elapsed.
+ These callbacks are ready to be invoked.
+<li> <tt>RCU_WAIT_TAIL</tt>: Callbacks that are waiting for the
+ current grace period.
+ Note that different CPUs can have different ideas about which
+ grace period is current, hence the <tt>->gp_seq</tt> field.
+<li> <tt>RCU_NEXT_READY_TAIL</tt>: Callbacks waiting for the next
+ grace period to start.
+<li> <tt>RCU_NEXT_TAIL</tt>: Callbacks that have not yet been
+ associated with a grace period.
+</ol>
+
+<p>
+The <tt>->head</tt> pointer references the first callback or
+is <tt>NULL</tt> if the list contains no callbacks (which is
+<i>not</i> the same as being empty).
+Each element of the <tt>->tails[]</tt> array references the
+<tt>->next</tt> pointer of the last callback in the corresponding
+segment of the list, or the list's <tt>->head</tt> pointer if
+that segment and all previous segments are empty.
+If the corresponding segment is empty but some previous segment is
+not empty, then the array element is identical to its predecessor.
+Older callbacks are closer to the head of the list, and new callbacks
+are added at the tail.
+This relationship between the <tt>->head</tt> pointer, the
+<tt>->tails[]</tt> array, and the callbacks is shown in this
+diagram:
+
+</p><p><img src="nxtlist.svg" alt="nxtlist.svg" width="40%">
+
+</p><p>In this figure, the <tt>->head</tt> pointer references the
+first
+RCU callback in the list.
+The <tt>->tails[RCU_DONE_TAIL]</tt> array element references
+the <tt>->head</tt> pointer itself, indicating that none
+of the callbacks is ready to invoke.
+The <tt>->tails[RCU_WAIT_TAIL]</tt> array element references callback
+CB 2's <tt>->next</tt> pointer, which indicates that
+CB 1 and CB 2 are both waiting on the current grace period,
+give or take possible disagreements about exactly which grace period
+is the current one.
+The <tt>->tails[RCU_NEXT_READY_TAIL]</tt> array element
+references the same RCU callback that <tt>->tails[RCU_WAIT_TAIL]</tt>
+does, which indicates that there are no callbacks waiting on the next
+RCU grace period.
+The <tt>->tails[RCU_NEXT_TAIL]</tt> array element references
+CB 4's <tt>->next</tt> pointer, indicating that all the
+remaining RCU callbacks have not yet been assigned to an RCU grace
+period.
+Note that the <tt>->tails[RCU_NEXT_TAIL]</tt> array element
+always references the last RCU callback's <tt>->next</tt> pointer
+unless the callback list is empty, in which case it references
+the <tt>->head</tt> pointer.
+
+<p>
+There is one additional important special case for the
+<tt>->tails[RCU_NEXT_TAIL]</tt> array element: It can be <tt>NULL</tt>
+when this list is <i>disabled</i>.
+Lists are disabled when the corresponding CPU is offline or when
+the corresponding CPU's callbacks are offloaded to a kthread,
+both of which are described elsewhere.
+
+</p><p>CPUs advance their callbacks from the
+<tt>RCU_NEXT_TAIL</tt> to the <tt>RCU_NEXT_READY_TAIL</tt> to the
+<tt>RCU_WAIT_TAIL</tt> to the <tt>RCU_DONE_TAIL</tt> list segments
+as grace periods advance.
+
+</p><p>The <tt>->gp_seq[]</tt> array records grace-period
+numbers corresponding to the list segments.
+This is what allows different CPUs to have different ideas as to
+which is the current grace period while still avoiding premature
+invocation of their callbacks.
+In particular, this allows CPUs that go idle for extended periods
+to determine which of their callbacks are ready to be invoked after
+reawakening.
+
+</p><p>The <tt>->len</tt> counter contains the number of
+callbacks in <tt>->head</tt>, and the
+<tt>->len_lazy</tt> contains the number of those callbacks that
+are known to only free memory, and whose invocation can therefore
+be safely deferred.
+
+<p><b>Important note</b>: It is the <tt>->len</tt> field that
+determines whether or not there are callbacks associated with
+this <tt>rcu_segcblist</tt> structure, <i>not</i> the <tt>->head</tt>
+pointer.
+The reason for this is that all the ready-to-invoke callbacks
+(that is, those in the <tt>RCU_DONE_TAIL</tt> segment) are extracted
+all at once at callback-invocation time.
+If callback invocation must be postponed, for example, because a
+high-priority process just woke up on this CPU, then the remaining
+callbacks are placed back on the <tt>RCU_DONE_TAIL</tt> segment.
+Either way, the <tt>->len</tt> and <tt>->len_lazy</tt> counts
+are adjusted after the corresponding callbacks have been invoked, and so
+again it is the <tt>->len</tt> count that accurately reflects whether
+or not there are callbacks associated with this <tt>rcu_segcblist</tt>
+structure.
+Of course, off-CPU sampling of the <tt>->len</tt> count requires
+the use of appropriate synchronization, for example, memory barriers.
+This synchronization can be a bit subtle, particularly in the case
+of <tt>rcu_barrier()</tt>.
+
<h3><a name="The rcu_data Structure">
The <tt>rcu_data</tt> Structure</a></h3>
as follows:
<pre>
- 1 struct rcu_head *nxtlist;
- 2 struct rcu_head **nxttail[RCU_NEXT_SIZE];
- 3 unsigned long nxtcompleted[RCU_NEXT_SIZE];
- 4 long qlen_lazy;
- 5 long qlen;
- 6 long qlen_last_fqs_check;
+ 1 struct rcu_segcblist cblist;
+ 2 long qlen_last_fqs_check;
+ 3 unsigned long n_cbs_invoked;
+ 4 unsigned long n_nocbs_invoked;
+ 5 unsigned long n_cbs_orphaned;
+ 6 unsigned long n_cbs_adopted;
7 unsigned long n_force_qs_snap;
- 8 unsigned long n_cbs_invoked;
- 9 unsigned long n_cbs_orphaned;
-10 unsigned long n_cbs_adopted;
-11 long blimit;
+ 8 long blimit;
</pre>
-<p>The <tt>->nxtlist</tt> pointer and the
-<tt>->nxttail[]</tt> array form a four-segment list with
-older callbacks near the head and newer ones near the tail.
-Each segment contains callbacks with the corresponding relationship
-to the current grace period.
-The pointer out of the end of each of the four segments is referenced
-by the element of the <tt>->nxttail[]</tt> array indexed by
-<tt>RCU_DONE_TAIL</tt> (for callbacks handled by a prior grace period),
-<tt>RCU_WAIT_TAIL</tt> (for callbacks waiting on the current grace period),
-<tt>RCU_NEXT_READY_TAIL</tt> (for callbacks that will wait on the next
-grace period), and
-<tt>RCU_NEXT_TAIL</tt> (for callbacks that are not yet associated
-with a specific grace period)
-respectively, as shown in the following figure.
-
-</p><p><img src="nxtlist.svg" alt="nxtlist.svg" width="40%">
-
-</p><p>In this figure, the <tt>->nxtlist</tt> pointer references the
-first
-RCU callback in the list.
-The <tt>->nxttail[RCU_DONE_TAIL]</tt> array element references
-the <tt>->nxtlist</tt> pointer itself, indicating that none
-of the callbacks is ready to invoke.
-The <tt>->nxttail[RCU_WAIT_TAIL]</tt> array element references callback
-CB 2's <tt>->next</tt> pointer, which indicates that
-CB 1 and CB 2 are both waiting on the current grace period.
-The <tt>->nxttail[RCU_NEXT_READY_TAIL]</tt> array element
-references the same RCU callback that <tt>->nxttail[RCU_WAIT_TAIL]</tt>
-does, which indicates that there are no callbacks waiting on the next
-RCU grace period.
-The <tt>->nxttail[RCU_NEXT_TAIL]</tt> array element references
-CB 4's <tt>->next</tt> pointer, indicating that all the
-remaining RCU callbacks have not yet been assigned to an RCU grace
-period.
-Note that the <tt>->nxttail[RCU_NEXT_TAIL]</tt> array element
-always references the last RCU callback's <tt>->next</tt> pointer
-unless the callback list is empty, in which case it references
-the <tt>->nxtlist</tt> pointer.
-
-</p><p>CPUs advance their callbacks from the
-<tt>RCU_NEXT_TAIL</tt> to the <tt>RCU_NEXT_READY_TAIL</tt> to the
-<tt>RCU_WAIT_TAIL</tt> to the <tt>RCU_DONE_TAIL</tt> list segments
-as grace periods advance.
+<p>The <tt>->cblist</tt> structure is the segmented callback list
+described earlier.
The CPU advances the callbacks in its <tt>rcu_data</tt> structure
whenever it notices that another RCU grace period has completed.
The CPU detects the completion of an RCU grace period by noticing
<tt>->completed</tt> field is updated at the end of each
grace period.
-</p><p>The <tt>->nxtcompleted[]</tt> array records grace-period
-numbers corresponding to the list segments.
-This allows CPUs that go idle for extended periods to determine
-which of their callbacks are ready to be invoked after reawakening.
-
-</p><p>The <tt>->qlen</tt> counter contains the number of
-callbacks in <tt>->nxtlist</tt>, and the
-<tt>->qlen_lazy</tt> contains the number of those callbacks that
-are known to only free memory, and whose invocation can therefore
-be safely deferred.
+<p>
The <tt>->qlen_last_fqs_check</tt> and
<tt>->n_force_qs_snap</tt> coordinate the forcing of quiescent
states from <tt>call_rcu()</tt> and friends when callback
fields count the number of callbacks invoked,
sent to other CPUs when this CPU goes offline,
and received from other CPUs when those other CPUs go offline.
+The <tt>->n_nocbs_invoked</tt> is used when the CPU's callbacks
+are offloaded to a kthread.
+
+<p>
Finally, the <tt>->blimit</tt> counter is the maximum number of
RCU callbacks that may be invoked at a given time.
1 int dynticks_nesting;
2 int dynticks_nmi_nesting;
3 atomic_t dynticks;
+ 4 bool rcu_need_heavy_qs;
+ 5 unsigned long rcu_qs_ctr;
+ 6 bool rcu_urgent_qs;
</pre>
<p>The <tt>->dynticks_nesting</tt> field counts the
field, except that NMIs that interrupt non-dyntick-idle execution
are not counted.
-</p><p>Finally, the <tt>->dynticks</tt> field counts the corresponding
+</p><p>The <tt>->dynticks</tt> field counts the corresponding
CPU's transitions to and from dyntick-idle mode, so that this counter
has an even value when the CPU is in dyntick-idle mode and an odd
value otherwise.
+</p><p>The <tt>->rcu_need_heavy_qs</tt> field is used
+to record the fact that the RCU core code would really like to
+see a quiescent state from the corresponding CPU, so much so that
+it is willing to call for heavy-weight dyntick-counter operations.
+This flag is checked by RCU's context-switch and <tt>cond_resched()</tt>
+code, which provide a momentary idle sojourn in response.
+
+</p><p>The <tt>->rcu_qs_ctr</tt> field is used to record
+quiescent states from <tt>cond_resched()</tt>.
+Because <tt>cond_resched()</tt> can execute quite frequently, this
+must be quite lightweight, as in a non-atomic increment of this
+per-CPU field.
+
+</p><p>Finally, the <tt>->rcu_urgent_qs</tt> field is used to record
+the fact that the RCU core code would really like to see a quiescent
+state from the corresponding CPU, with the various other fields indicating
+just how badly RCU wants this quiescent state.
+This flag is checked by RCU's context-switch and <tt>cond_resched()</tt>
+code, which, if nothing else, non-atomically increment <tt>->rcu_qs_ctr</tt>
+in response.
+
<table>
<tr><th> </th></tr>
<tr><th align="left">Quick Quiz:</th></tr>
id="svg2"
version="1.1"
inkscape:version="0.48.4 r9939"
- sodipodi:docname="nxtlist.fig">
+ sodipodi:docname="segcblist.svg">
<metadata
id="metadata94">
<rdf:RDF>
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
- <dc:title></dc:title>
+ <dc:title />
</cc:Work>
</rdf:RDF>
</metadata>
xml:space="preserve"
x="225"
y="675"
- fill="#000000"
- font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
- text-anchor="start"
- id="text64">nxtlist</text>
+ id="text64"
+ style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->head</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="1800"
- fill="#000000"
- font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
- text-anchor="start"
- id="text66">nxttail[RCU_DONE_TAIL]</text>
+ id="text66"
+ style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->tails[RCU_DONE_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="2925"
- fill="#000000"
- font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
- text-anchor="start"
- id="text68">nxttail[RCU_WAIT_TAIL]</text>
+ id="text68"
+ style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->tails[RCU_WAIT_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="4050"
- fill="#000000"
- font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
- text-anchor="start"
- id="text70">nxttail[RCU_NEXT_READY_TAIL]</text>
+ id="text70"
+ style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->tails[RCU_NEXT_READY_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"
x="225"
y="5175"
- fill="#000000"
- font-family="Courier"
font-style="normal"
font-weight="bold"
font-size="324"
- text-anchor="start"
- id="text72">nxttail[RCU_NEXT_TAIL]</text>
+ id="text72"
+ style="font-size:324px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">->tails[RCU_NEXT_TAIL]</text>
<!-- Text -->
<text
xml:space="preserve"
Funnel locking and wait/wakeup</a>.
<li> <a href="#Use of Workqueues">Use of Workqueues</a>.
<li> <a href="#Stall Warnings">Stall warnings</a>.
+<li> <a href="#Mid-Boot Operation">Mid-boot operation</a>.
</ol>
<h3><a name="Idle-CPU Checks">Idle-CPU Checks</a></h3>
In earlier implementations, the task requesting the expedited
grace period also drove it to completion.
This straightforward approach had the disadvantage of needing to
-account for signals sent to user tasks,
+account for POSIX signals sent to user tasks,
so more recent implemementations use the Linux kernel's
<a href="https://www.kernel.org/doc/Documentation/workqueue.txt">workqueues</a>.
processing, but the task reaching the top of the funnel lock
does a <tt>schedule_work()</tt> (from <tt>_synchronize_rcu_expedited()</tt>
so that a workqueue kthread does the actual grace-period processing.
-Because workqueue kthreads do not accept signals, grace-period-wait
-processing need not allow for signals.
+Because workqueue kthreads do not accept POSIX signals, grace-period-wait
+processing need not allow for POSIX signals.
In addition, this approach allows wakeups for the previous expedited
grace period to be overlapped with processing for the next expedited
Each stall warning results in another pass through the loop, but the
second and subsequent passes use longer stall times.
+<h3><a name="Mid-Boot Operation">Mid-boot operation</a></h3>
+
+<p>
+The use of workqueues has the advantage that the expedited
+grace-period code need not worry about POSIX signals.
+Unfortunately, it has the
+corresponding disadvantage that workqueues cannot be used until
+they are initialized, which does not happen until some time after
+the scheduler spawns the first task.
+Given that there are parts of the kernel that really do want to
+execute grace periods during this mid-boot “dead zone”,
+expedited grace periods must do something else during thie time.
+
+<p>
+What they do is to fall back to the old practice of requiring that the
+requesting task drive the expedited grace period, as was the case
+before the use of workqueues.
+However, the requesting task is only required to drive the grace period
+during the mid-boot dead zone.
+Before mid-boot, a synchronous grace period is a no-op.
+Some time after mid-boot, workqueues are used.
+
+<p>
+Non-expedited non-SRCU synchronous grace periods must also operate
+normally during mid-boot.
+This is handled by causing non-expedited grace periods to take the
+expedited code path during mid-boot.
+
+<p>
+The current code assumes that there are no POSIX signals during
+the mid-boot dead zone.
+However, if an overwhelming need for POSIX signals somehow arises,
+appropriate adjustments can be made to the expedited stall-warning code.
+One such adjustment would reinstate the pre-workqueue stall-warning
+checks, but only during the mid-boot dead zone.
+
+<p>
+With this refinement, synchronous grace periods can now be used from
+task context pretty much any time during the life of the kernel.
+
<h3><a name="Summary">
Summary</a></h3>
In other words, a given instance of <tt>synchronize_rcu()</tt>
can avoid waiting on a given RCU read-side critical section only
if it can prove that <tt>synchronize_rcu()</tt> started first.
+ </font>
- <p>
+ <p><font color="ffffff">
A related question is “When <tt>rcu_read_lock()</tt>
doesn't generate any code, why does it matter how it relates
to a grace period?”
within the critical section, in which case none of the accesses
within the critical section may observe the effects of any
access following the grace period.
+ </font>
- <p>
+ <p><font color="ffffff">
As of late 2016, mathematical models of RCU take this
viewpoint, for example, see slides 62 and 63
of the
In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt>
is permitted to impose modest degradation of real-time latency
on non-idle online CPUs.
-That said, it will likely be necessary to take further steps to reduce this
-degradation, hopefully to roughly that of a scheduling-clock interrupt.
+Here, “modest” means roughly the same latency
+degradation as a scheduling-clock interrupt.
<p>
There are a number of situations where even
but it is also the driving force behind the checks for large numbers
of queued RCU callbacks in the <tt>call_rcu()</tt> code path.
Finally, high update rates should not delay RCU read-side critical
-sections, although some read-side delays can occur when using
+sections, although some small read-side delays can occur when using
<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use
-of <tt>try_stop_cpus()</tt>.
-(In the future, <tt>synchronize_rcu_expedited()</tt> will be
-converted to use lighter-weight inter-processor interrupts (IPIs),
-but this will still disturb readers, though to a much smaller degree.)
+of <tt>smp_call_function_single()</tt>.
<p>
Although all three of these corner cases were understood in the early
<p>
Although <tt>call_rcu()</tt> may be invoked at any
time during boot, callbacks are not guaranteed to be invoked until after
-the scheduler is fully up and running.
+all of RCU's kthreads have been spawned, which occurs at
+<tt>early_initcall()</tt> time.
This delay in callback invocation is due to the fact that RCU does not
invoke callbacks until it is fully initialized, and this full initialization
cannot occur until after the scheduler has initialized itself to the
Perhaps surprisingly, <tt>synchronize_rcu()</tt>,
<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a>
(<a href="#Bottom-Half Flavor">discussed below</a>),
-and
-<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>
+<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>,
+<tt>synchronize_rcu_expedited()</tt>,
+<tt>synchronize_rcu_bh_expedited()</tt>, and
+<tt>synchronize_sched_expedited()</tt>
will all operate normally
during very early boot, the reason being that there is only one CPU
and preemption is disabled.
be a no-op.
<p>
-Both <tt>synchronize_rcu_bh()</tt> and <tt>synchronize_sched()</tt>
-continue to operate normally through the remainder of boot, courtesy
-of the fact that preemption is disabled across their RCU read-side
-critical sections and also courtesy of the fact that there is still
-only one CPU.
-However, once the scheduler starts initializing, preemption is enabled.
-There is still only a single CPU, but the fact that preemption is enabled
-means that the no-op implementation of <tt>synchronize_rcu()</tt> no
-longer works in <tt>CONFIG_PREEMPT=y</tt> kernels.
-Therefore, as soon as the scheduler starts initializing, the early-boot
-fastpath is disabled.
-This means that <tt>synchronize_rcu()</tt> switches to its runtime
-mode of operation where it posts callbacks, which in turn means that
-any call to <tt>synchronize_rcu()</tt> will block until the corresponding
-callback is invoked.
-Unfortunately, the callback cannot be invoked until RCU's runtime
-grace-period machinery is up and running, which cannot happen until
-the scheduler has initialized itself sufficiently to allow RCU's
-kthreads to be spawned.
-Therefore, invoking <tt>synchronize_rcu()</tt> during scheduler
-initialization can result in deadlock.
+However, once the scheduler has spawned its first kthread, this early
+boot trick fails for <tt>synchronize_rcu()</tt> (as well as for
+<tt>synchronize_rcu_expedited()</tt>) in <tt>CONFIG_PREEMPT=y</tt>
+kernels.
+The reason is that an RCU read-side critical section might be preempted,
+which means that a subsequent <tt>synchronize_rcu()</tt> really does have
+to wait for something, as opposed to simply returning immediately.
+Unfortunately, <tt>synchronize_rcu()</tt> can't do this until all of
+its kthreads are spawned, which doesn't happen until some time during
+<tt>early_initcalls()</tt> time.
+But this is no excuse: RCU is nevertheless required to correctly handle
+synchronous grace periods during this time period.
+Once all of its kthreads are up and running, RCU starts running
+normally.
<table>
<tr><th> </th></tr>
<tr><th align="left">Quick Quiz:</th></tr>
<tr><td>
- So what happens with <tt>synchronize_rcu()</tt> during
- scheduler initialization for <tt>CONFIG_PREEMPT=n</tt>
- kernels?
+ How can RCU possibly handle grace periods before all of its
+ kthreads have been spawned???
</td></tr>
<tr><th align="left">Answer:</th></tr>
<tr><td bgcolor="#ffffff"><font color="ffffff">
- In <tt>CONFIG_PREEMPT=n</tt> kernel, <tt>synchronize_rcu()</tt>
- maps directly to <tt>synchronize_sched()</tt>.
- Therefore, <tt>synchronize_rcu()</tt> works normally throughout
- boot in <tt>CONFIG_PREEMPT=n</tt> kernels.
- However, your code must also work in <tt>CONFIG_PREEMPT=y</tt> kernels,
- so it is still necessary to avoid invoking <tt>synchronize_rcu()</tt>
- during scheduler initialization.
+ Very carefully!
+ </font>
+
+ <p><font color="ffffff">
+ During the “dead zone” between the time that the
+ scheduler spawns the first task and the time that all of RCU's
+ kthreads have been spawned, all synchronous grace periods are
+ handled by the expedited grace-period mechanism.
+ At runtime, this expedited mechanism relies on workqueues, but
+ during the dead zone the requesting task itself drives the
+ desired expedited grace period.
+ Because dead-zone execution takes place within task context,
+ everything works.
+ Once the dead zone ends, expedited grace periods go back to
+ using workqueues, as is required to avoid problems that would
+ otherwise occur when a user task received a POSIX signal while
+ driving an expedited grace period.
+ </font>
+
+ <p><font color="ffffff">
+ And yes, this does mean that it is unhelpful to send POSIX
+ signals to random tasks between the time that the scheduler
+ spawns its first kthread and the time that RCU's kthreads
+ have all been spawned.
+ If there ever turns out to be a good reason for sending POSIX
+ signals during that time, appropriate adjustments will be made.
+ (If it turns out that POSIX signals are sent during this time for
+ no good reason, other adjustments will be made, appropriate
+ or otherwise.)
</font></td></tr>
<tr><td> </td></tr>
</table>
The need for <tt>rcu_barrier()</tt> for module unloading became
apparent later.
+<p>
+<b>Important note</b>: The <tt>rcu_barrier()</tt> function is not,
+repeat, <i>not</i>, obligated to wait for a grace period.
+It is instead only required to wait for RCU callbacks that have
+already been posted.
+Therefore, if there are no RCU callbacks posted anywhere in the system,
+<tt>rcu_barrier()</tt> is within its rights to return immediately.
+Even if there are callbacks posted, <tt>rcu_barrier()</tt> does not
+necessarily need to wait for a grace period.
+
+<table>
+<tr><th> </th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+ Wait a minute!
+ Each RCU callbacks must wait for a grace period to complete,
+ and <tt>rcu_barrier()</tt> must wait for each pre-existing
+ callback to be invoked.
+ Doesn't <tt>rcu_barrier()</tt> therefore need to wait for
+ a full grace period if there is even one callback posted anywhere
+ in the system?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+ Absolutely not!!!
+ </font>
+
+ <p><font color="ffffff">
+ Yes, each RCU callbacks must wait for a grace period to complete,
+ but it might well be partly (or even completely) finished waiting
+ by the time <tt>rcu_barrier()</tt> is invoked.
+ In that case, <tt>rcu_barrier()</tt> need only wait for the
+ remaining portion of the grace period to elapse.
+ So even if there are quite a few callbacks posted,
+ <tt>rcu_barrier()</tt> might well return quite quickly.
+ </font>
+
+ <p><font color="ffffff">
+ So if you need to wait for a grace period as well as for all
+ pre-existing callbacks, you will need to invoke both
+ <tt>synchronize_rcu()</tt> and <tt>rcu_barrier()</tt>.
+ If latency is a concern, you can always use workqueues
+ to invoke them concurrently.
+</font></td></tr>
+<tr><td> </td></tr>
+</table>
+
<h3><a name="Hotplug CPU">Hotplug CPU</a></h3>
<p>
The Linux kernel supports CPU hotplug, which means that CPUs
can come and go.
-It is of course illegal to use any RCU API member from an offline CPU.
+It is of course illegal to use any RCU API member from an offline CPU,
+with the exception of <a href="#Sleepable RCU">SRCU</a> read-side
+critical sections.
This requirement was present from day one in DYNIX/ptx, but
on the other hand, the Linux kernel's CPU-hotplug implementation
is “interesting.”
are used to allow the various kernel subsystems (including RCU)
to respond appropriately to a given CPU-hotplug operation.
Most RCU operations may be invoked from CPU-hotplug notifiers,
-including even normal synchronous grace-period operations
-such as <tt>synchronize_rcu()</tt>.
-However, expedited grace-period operations such as
-<tt>synchronize_rcu_expedited()</tt> are not supported,
-due to the fact that current implementations block CPU-hotplug
-operations, which could result in deadlock.
+including even synchronous grace-period operations such as
+<tt>synchronize_rcu()</tt> and <tt>synchronize_rcu_expedited()</tt>.
<p>
-In addition, all-callback-wait operations such as
+However, all-callback-wait operations such as
<tt>rcu_barrier()</tt> are also not supported, due to the
fact that there are phases of CPU-hotplug operations where
the outgoing CPU's callbacks will not be invoked until after
the CPU-hotplug operation ends, which could also result in deadlock.
+Furthermore, <tt>rcu_barrier()</tt> blocks CPU-hotplug operations
+during its execution, which results in another type of deadlock
+when invoked from a CPU-hotplug notifier.
<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3>
API, which, in combination with <tt>srcu_read_unlock()</tt>,
guarantees a full memory barrier.
+<p>
+Also unlike other RCU flavors, SRCU's callbacks-wait function
+<tt>srcu_barrier()</tt> may be invoked from CPU-hotplug notifiers,
+though this is not necessarily a good idea.
+The reason that this is possible is that SRCU is insensitive
+to whether or not a CPU is online, which means that <tt>srcu_barrier()</tt>
+need not exclude CPU-hotplug operations.
+
+<p>
+As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating
+a locking bottleneck present in prior kernel versions.
+Although this will allow users to put much heavier stress on
+<tt>call_srcu()</tt>, it is important to note that SRCU does not
+yet take any special steps to deal with callback flooding.
+So if you are posting (say) 10,000 SRCU callbacks per second per CPU,
+you are probably totally OK, but if you intend to post (say) 1,000,000
+SRCU callbacks per second per CPU, please run some tests first.
+SRCU just might need a few adjustment to deal with that sort of load.
+Of course, your mileage may vary based on the speed of your CPUs and
+the size of your memory.
+
<p>
The
<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a>
<p>
RCU disables CPU hotplug in a few places, perhaps most notably in the
-expedited grace-period and <tt>rcu_barrier()</tt> operations.
-If there is a strong reason to use expedited grace periods in CPU-hotplug
+<tt>rcu_barrier()</tt> operations.
+If there is a strong reason to use <tt>rcu_barrier()</tt> in CPU-hotplug
notifiers, it will be necessary to avoid disabling CPU hotplug.
This would introduce some complexity, so there had better be a <i>very</i>
good reason.
this article human readable, and to Michelle Rankin for her support
of this effort.
Other contributions are acknowledged in the Linux kernel's git archive.
-The cartoon is copyright (c) 2013 by Melissa Broussard,
-and is provided
-under the terms of the Creative Commons Attribution-Share Alike 3.0
-United States license.
</body></html>
This sort of comparison occurs frequently when scanning
RCU-protected circular linked lists.
+ Note that if checks for being within an RCU read-side
+ critical section are not required and the pointer is never
+ dereferenced, rcu_access_pointer() should be used in place
+ of rcu_dereference(). The rcu_access_pointer() primitive
+ does not require an enclosing read-side critical section,
+ and also omits the smp_read_barrier_depends() included in
+ rcu_dereference(), which in turn should provide a small
+ performance gain in some CPUs (e.g., the DEC Alpha).
+
o The comparison is against a pointer that references memory
that was initialized "a long time ago." The reason
this is safe is that even if misordering occurs, the
Using hlist_nulls to protect read-mostly linked lists and
-objects using SLAB_DESTROY_BY_RCU allocations.
+objects using SLAB_TYPESAFE_BY_RCU allocations.
Please read the basics in Documentation/RCU/listRCU.txt
to solve following problem :
A typical RCU linked list managing objects which are
-allocated with SLAB_DESTROY_BY_RCU kmem_cache can
+allocated with SLAB_TYPESAFE_BY_RCU kmem_cache can
use following algos :
1) Lookup algo
3) Remove algo
--------------
Nothing special here, we can use a standard RCU hlist deletion.
-But thanks to SLAB_DESTROY_BY_RCU, beware a deleted object can be reused
+But thanks to SLAB_TYPESAFE_BY_RCU, beware a deleted object can be reused
very very fast (before the end of RCU grace period)
if (put_last_reference_on(obj) {
Using RCU's CPU Stall Detector
-The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
-detector, which detects conditions that unduly delay RCU grace periods.
-This module parameter enables CPU stall detection by default, but
-may be overridden via boot-time parameter or at runtime via sysfs.
+This document first discusses what sorts of issues RCU's CPU stall
+detector can locate, and then discusses kernel parameters and Kconfig
+options that can be used to fine-tune the detector's operation. Finally,
+this document explains the stall detector's "splat" format.
+
+
+What Causes RCU CPU Stall Warnings?
+
+So your kernel printed an RCU CPU stall warning. The next question is
+"What caused it?" The following problems can result in RCU CPU stall
+warnings:
+
+o A CPU looping in an RCU read-side critical section.
+
+o A CPU looping with interrupts disabled.
+
+o A CPU looping with preemption disabled. This condition can
+ result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
+ stalls.
+
+o A CPU looping with bottom halves disabled. This condition can
+ result in RCU-sched and RCU-bh stalls.
+
+o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
+ kernel without invoking schedule(). Note that cond_resched()
+ does not necessarily prevent RCU CPU stall warnings. Therefore,
+ if the looping in the kernel is really expected and desirable
+ behavior, you might need to replace some of the cond_resched()
+ calls with calls to cond_resched_rcu_qs().
+
+o Booting Linux using a console connection that is too slow to
+ keep up with the boot-time console-message rate. For example,
+ a 115Kbaud serial console can be -way- too slow to keep up
+ with boot-time message rates, and will frequently result in
+ RCU CPU stall warning messages. Especially if you have added
+ debug printk()s.
+
+o Anything that prevents RCU's grace-period kthreads from running.
+ This can result in the "All QSes seen" console-log message.
+ This message will include information on when the kthread last
+ ran and how often it should be expected to run.
+
+o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+ happen to preempt a low-priority task in the middle of an RCU
+ read-side critical section. This is especially damaging if
+ that low-priority task is not permitted to run on any other CPU,
+ in which case the next RCU grace period can never complete, which
+ will eventually cause the system to run out of memory and hang.
+ While the system is in the process of running itself out of
+ memory, you might see stall-warning messages.
+
+o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
+ is running at a higher priority than the RCU softirq threads.
+ This will prevent RCU callbacks from ever being invoked,
+ and in a CONFIG_PREEMPT_RCU kernel will further prevent
+ RCU grace periods from ever completing. Either way, the
+ system will eventually run out of memory and hang. In the
+ CONFIG_PREEMPT_RCU case, you might see stall-warning
+ messages.
+
+o A hardware or software issue shuts off the scheduler-clock
+ interrupt on a CPU that is not in dyntick-idle mode. This
+ problem really has happened, and seems to be most likely to
+ result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels.
+
+o A bug in the RCU implementation.
+
+o A hardware failure. This is quite unlikely, but has occurred
+ at least once in real life. A CPU failed in a running system,
+ becoming unresponsive, but not causing an immediate crash.
+ This resulted in a series of RCU CPU stall warnings, eventually
+ leading the realization that the CPU had failed.
+
+The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall
+warning. Note that SRCU does -not- have CPU stall warnings. Please note
+that RCU only detects CPU stalls when there is a grace period in progress.
+No grace period, no CPU stall warnings.
+
+To diagnose the cause of the stall, inspect the stack traces.
+The offending function will usually be near the top of the stack.
+If you have a series of stall warnings from a single extended stall,
+comparing the stack traces can often help determine where the stall
+is occurring, which will usually be in the function nearest the top of
+that portion of the stack which remains the same from trace to trace.
+If you can reliably trigger the stall, ftrace can be quite helpful.
+
+RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE
+and with RCU's event tracing. For information on RCU's event tracing,
+see include/trace/events/rcu.h.
+
+
+Fine-Tuning the RCU CPU Stall Detector
+
+The rcuupdate.rcu_cpu_stall_suppress module parameter disables RCU's
+CPU stall detector, which detects conditions that unduly delay RCU grace
+periods. This module parameter enables CPU stall detection by default,
+but may be overridden via boot-time parameter or at runtime via sysfs.
The stall detector's idea of what constitutes "unduly delayed" is
controlled by a set of kernel configuration variables and cpp macros:
And continues with the output of sched_show_task() for each
task stalling the current RCU-tasks grace period.
+
+Interpreting RCU's CPU Stall-Detector "Splats"
+
For non-RCU-tasks flavors of RCU, when a CPU detects that it is stalling,
it will print a message similar to the following:
It is entirely possible to see stall warnings from normal and from
expedited grace periods at about the same time from the same run.
-
-
-What Causes RCU CPU Stall Warnings?
-
-So your kernel printed an RCU CPU stall warning. The next question is
-"What caused it?" The following problems can result in RCU CPU stall
-warnings:
-
-o A CPU looping in an RCU read-side critical section.
-
-o A CPU looping with interrupts disabled. This condition can
- result in RCU-sched and RCU-bh stalls.
-
-o A CPU looping with preemption disabled. This condition can
- result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
- stalls.
-
-o A CPU looping with bottom halves disabled. This condition can
- result in RCU-sched and RCU-bh stalls.
-
-o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the
- kernel without invoking schedule(). Note that cond_resched()
- does not necessarily prevent RCU CPU stall warnings. Therefore,
- if the looping in the kernel is really expected and desirable
- behavior, you might need to replace some of the cond_resched()
- calls with calls to cond_resched_rcu_qs().
-
-o Booting Linux using a console connection that is too slow to
- keep up with the boot-time console-message rate. For example,
- a 115Kbaud serial console can be -way- too slow to keep up
- with boot-time message rates, and will frequently result in
- RCU CPU stall warning messages. Especially if you have added
- debug printk()s.
-
-o Anything that prevents RCU's grace-period kthreads from running.
- This can result in the "All QSes seen" console-log message.
- This message will include information on when the kthread last
- ran and how often it should be expected to run.
-
-o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
- happen to preempt a low-priority task in the middle of an RCU
- read-side critical section. This is especially damaging if
- that low-priority task is not permitted to run on any other CPU,
- in which case the next RCU grace period can never complete, which
- will eventually cause the system to run out of memory and hang.
- While the system is in the process of running itself out of
- memory, you might see stall-warning messages.
-
-o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
- is running at a higher priority than the RCU softirq threads.
- This will prevent RCU callbacks from ever being invoked,
- and in a CONFIG_PREEMPT_RCU kernel will further prevent
- RCU grace periods from ever completing. Either way, the
- system will eventually run out of memory and hang. In the
- CONFIG_PREEMPT_RCU case, you might see stall-warning
- messages.
-
-o A hardware or software issue shuts off the scheduler-clock
- interrupt on a CPU that is not in dyntick-idle mode. This
- problem really has happened, and seems to be most likely to
- result in RCU CPU stall warnings for CONFIG_NO_HZ_COMMON=n kernels.
-
-o A bug in the RCU implementation.
-
-o A hardware failure. This is quite unlikely, but has occurred
- at least once in real life. A CPU failed in a running system,
- becoming unresponsive, but not causing an immediate crash.
- This resulted in a series of RCU CPU stall warnings, eventually
- leading the realization that the CPU had failed.
-
-The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall
-warning. Note that SRCU does -not- have CPU stall warnings. Please note
-that RCU only detects CPU stalls when there is a grace period in progress.
-No grace period, no CPU stall warnings.
-
-To diagnose the cause of the stall, inspect the stack traces.
-The offending function will usually be near the top of the stack.
-If you have a series of stall warnings from a single extended stall,
-comparing the stack traces can often help determine where the stall
-is occurring, which will usually be in the function nearest the top of
-that portion of the stack which remains the same from trace to trace.
-If you can reliably trigger the stall, ftrace can be quite helpful.
-
-RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE
-and with RCU's event tracing. For information on RCU's event tracing,
-see include/trace/events/rcu.h.
familiar locking primitives. Its overhead makes it a non-starter for
real-life use, as does its lack of scalability. It is also unsuitable
for realtime use, since it allows scheduling latency to "bleed" from
-one read-side critical section to another.
+one read-side critical section to another. It also assumes recursive
+reader-writer locks: If you try this with non-recursive locks, and
+you allow nested rcu_read_lock() calls, you can deadlock.
However, it is probably the easiest implementation to relate to, so is
a good starting point.
write_unlock(&rcu_gp_mutex);
}
-[You can ignore rcu_assign_pointer() and rcu_dereference() without
-missing much. But here they are anyway. And whatever you do, don't
-forget about them when submitting patches making use of RCU!]
+[You can ignore rcu_assign_pointer() and rcu_dereference() without missing
+much. But here are simplified versions anyway. And whatever you do,
+don't forget about them when submitting patches making use of RCU!]
- #define rcu_assign_pointer(p, v) ({ \
- smp_wmb(); \
- (p) = (v); \
- })
+ #define rcu_assign_pointer(p, v) \
+ ({ \
+ smp_store_release(&(p), (v)); \
+ })
- #define rcu_dereference(p) ({ \
- typeof(p) _________p1 = p; \
- smp_read_barrier_depends(); \
- (_________p1); \
- })
+ #define rcu_dereference(p) \
+ ({ \
+ typeof(p) _________p1 = p; \
+ smp_read_barrier_depends(); \
+ (_________p1); \
+ })
The rcu_read_lock() and rcu_read_unlock() primitive read-acquire
e. Is your workload too update-intensive for normal use of
RCU, but inappropriate for other synchronization mechanisms?
- If so, consider SLAB_DESTROY_BY_RCU. But please be careful!
+ If so, consider SLAB_TYPESAFE_BY_RCU (which was originally
+ named SLAB_DESTROY_BY_RCU). But please be careful!
f. Do you need read-side critical sections that are respected
even though they are in the middle of the idle loop, during
extended tables themselves, and also PASID support. With
this option set, extended tables will not be used even
on hardware which claims to support them.
+ tboot_noforce [Default Off]
+ Do not force the Intel IOMMU enabled under tboot.
+ By default, tboot will force Intel IOMMU on, which
+ could harm performance of some high-throughput
+ devices like 40GBit network cards, even if identity
+ mapping is enabled.
+ Note that using this option lowers the security
+ provided by tboot because it makes the system
+ vulnerable to DMA attacks.
intel_idle.max_cstate= [KNL,HW,ACPI,X86]
0 disables intel_idle and fall back on acpi_idle.
nobypass [PPC/POWERNV]
Disable IOMMU bypass, using IOMMU for PCI devices.
+ iommu.passthrough=
+ [ARM64] Configure DMA to bypass the IOMMU by default.
+ Format: { "0" | "1" }
+ 0 - Use IOMMU translation for DMA.
+ 1 - Bypass the IOMMU for DMA.
+ unset - Use IOMMU translation for DMA.
io7= [HW] IO7 for Marvel based alpha systems
See comment before marvel_specify_io7 in
and gids from such clients. This is intended to ease
migration from NFSv2/v3.
- objlayoutdriver.osd_login_prog=
- [NFS] [OBJLAYOUT] sets the pathname to the program which
- is used to automatically discover and login into new
- osd-targets. Please see:
- Documentation/filesystems/pnfs.txt for more explanations
-
nmi_debug= [KNL,SH] Specify one or more actions to take
when a NMI is triggered.
Format: [state][,regs][,debounce][,die]
spia_pedr=
spia_peddr=
+ srcutree.exp_holdoff [KNL]
+ Specifies how many nanoseconds must elapse
+ since the end of the last SRCU grace period for
+ a given srcu_struct until the next normal SRCU
+ grace period will be considered for automatic
+ expediting. Set to zero to disable automatic
+ expediting.
+
stacktrace [FTRACE]
Enabled the stack tracer on boot up.
The kernel configures the translation tables so that translations made
via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of
the virtual address ignored by the translation hardware. This frees up
-this byte for application use, with the following caveats:
+this byte for application use.
- (1) The kernel requires that all user addresses passed to EL1
- are tagged with tag 0x00. This means that any syscall
- parameters containing user virtual addresses *must* have
- their top byte cleared before trapping to the kernel.
- (2) Non-zero tags are not preserved when delivering signals.
- This means that signal handlers in applications making use
- of tags cannot rely on the tag information for user virtual
- addresses being maintained for fields inside siginfo_t.
- One exception to this rule is for signals raised in response
- to watchpoint debug exceptions, where the tag information
- will be preserved.
+Passing tagged addresses to the kernel
+--------------------------------------
- (3) Special care should be taken when using tagged pointers,
- since it is likely that C compilers will not hazard two
- virtual addresses differing only in the upper byte.
+All interpretation of userspace memory addresses by the kernel assumes
+an address tag of 0x00.
+
+This includes, but is not limited to, addresses found in:
+
+ - pointer arguments to system calls, including pointers in structures
+ passed to system calls,
+
+ - the stack pointer (sp), e.g. when interpreting it to deliver a
+ signal,
+
+ - the frame pointer (x29) and frame records, e.g. when interpreting
+ them to generate a backtrace or call graph.
+
+Using non-zero address tags in any of these locations may result in an
+error code being returned, a (fatal) signal being raised, or other modes
+of failure.
+
+For these reasons, passing non-zero address tags to the kernel via
+system calls is forbidden, and using a non-zero address tag for sp is
+strongly discouraged.
+
+Programs maintaining a frame pointer and frame records that use non-zero
+address tags may suffer impaired or inaccurate debug and profiling
+visibility.
+
+
+Preserving tags
+---------------
+
+Non-zero tags are not preserved when delivering signals. This means that
+signal handlers in applications making use of tags cannot rely on the
+tag information for user virtual addresses being maintained for fields
+inside siginfo_t. One exception to this rule is for signals raised in
+response to watchpoint debug exceptions, where the tag information will
+be preserved.
The architecture prevents the use of a tagged PC, so the upper byte will
be set to a sign-extension of bit 55 on exception return.
+
+
+Other considerations
+--------------------
+
+Special care should be taken when using tagged pointers, since it is
+likely that C compilers will not hazard two virtual addresses differing
+only in the upper byte.
groups (switching back to time distribution when needed to keep
throughput high).
+In its default configuration, BFQ privileges latency over
+throughput. So, when needed for achieving a lower latency, BFQ builds
+schedules that may lead to a lower throughput. If your main or only
+goal, for a given device, is to achieve the maximum-possible
+throughput at all times, then do switch off all low-latency heuristics
+for that device, by setting low_latency to 0. Full details in Section 3.
+
On average CPUs, the current version of BFQ can handle devices
performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
reference, 30-50 KIOPS correspond to very high bandwidths with
real-time applications are privileged and experience a lower latency,
as explained in more detail in the description of how BFQ works.
-DO NOT enable this mode if you need full control on bandwidth
+DISABLE this mode if you need full control on bandwidth
distribution. In fact, if it is enabled, then BFQ automatically
increases the bandwidth share of privileged applications, as the main
means to guarantee a lower latency to them.
+In addition, as already highlighted at the beginning of this document,
+DISABLE this mode if your only goal is to achieve a high throughput.
+In fact, privileging the I/O of some application over the rest may
+entail a lower throughput. To achieve the highest-possible throughput
+on a non-rotational device, setting slice_idle to 0 may be needed too
+(at the cost of giving up any strong guarantee on fairness and low
+latency).
+
timeout_sync
------------
--- /dev/null
+OP-TEE Device Tree Bindings
+
+OP-TEE is a piece of software using hardware features to provide a Trusted
+Execution Environment. The security can be provided with ARM TrustZone, but
+also by virtualization or a separate chip.
+
+We're using "linaro" as the first part of the compatible property for
+the reference implementation maintained by Linaro.
+
+* OP-TEE based on ARM TrustZone required properties:
+
+- compatible : should contain "linaro,optee-tz"
+
+- method : The method of calling the OP-TEE Trusted OS. Permitted
+ values are:
+
+ "smc" : SMC #0, with the register assignments specified
+ in drivers/tee/optee/optee_smc.h
+
+ "hvc" : HVC #0, with the register assignments specified
+ in drivers/tee/optee/optee_smc.h
+
+
+
+Example:
+ firmware {
+ optee {
+ compatible = "linaro,optee-tz";
+ method = "smc";
+ };
+ };
- compatible: Should be one of:
- "mediatek,mt2701-apmixedsys"
+ - "mediatek,mt6797-apmixedsys"
- "mediatek,mt8135-apmixedsys"
- "mediatek,mt8173-apmixedsys"
- #clock-cells: Must be 1
- compatible: Should be one of:
- "mediatek,mt2701-imgsys", "syscon"
+ - "mediatek,mt6797-imgsys", "syscon"
- "mediatek,mt8173-imgsys", "syscon"
- #clock-cells: Must be 1
- compatible: Should be one of:
- "mediatek,mt2701-infracfg", "syscon"
+ - "mediatek,mt6797-infracfg", "syscon"
- "mediatek,mt8135-infracfg", "syscon"
- "mediatek,mt8173-infracfg", "syscon"
- #clock-cells: Must be 1
- compatible: Should be one of:
- "mediatek,mt2701-mmsys", "syscon"
+ - "mediatek,mt6797-mmsys", "syscon"
- "mediatek,mt8173-mmsys", "syscon"
- #clock-cells: Must be 1
- compatible: Should be one of:
- "mediatek,mt2701-topckgen"
+ - "mediatek,mt6797-topckgen"
- "mediatek,mt8135-topckgen"
- "mediatek,mt8173-topckgen"
- #clock-cells: Must be 1
- compatible: Should be one of:
- "mediatek,mt2701-vdecsys", "syscon"
+ - "mediatek,mt6797-vdecsys", "syscon"
- "mediatek,mt8173-vdecsys", "syscon"
- #clock-cells: Must be 1
Required Properties:
-- compatible: Should be:
+- compatible: Should be one of:
+ - "mediatek,mt6797-vencsys", "syscon"
- "mediatek,mt8173-vencsys", "syscon"
- #clock-cells: Must be 1
==I2C device node==
Required properties:
-- compatible: shall be one of "idt,5p49v5923" , "idt,5p49v5933".
+- compatible: shall be one of "idt,5p49v5923" , "idt,5p49v5933" ,
+ "idt,5p49v5935".
- reg: i2c device address, shall be 0x68 or 0x6a.
- #clock-cells: from common clock binding; shall be set to 1.
- clocks: from common clock binding; list of parent clock handles,
- 5p49v5923: (required) either or both of XTAL or CLKIN
reference clock.
- - 5p49v5933: (optional) property not present (internal
+ - 5p49v5933 and
+ - 5p49v5935: (optional) property not present (internal
Xtal used) or CLKIN reference
clock.
- clock-names: from common clock binding; clock input names, can be
- 5p49v5923: (required) either or both of "xin", "clkin".
- - 5p49v5933: (optional) property not present or "clkin".
+ - 5p49v5933 and
+ - 5p49v5935: (optional) property not present or "clkin".
==Mapping between clock specifier and physical pins==
1 -- OUT1
2 -- OUT4
+5P49V5935:
+ 0 -- OUT0_SEL_I2CB
+ 1 -- OUT1
+ 2 -- OUT2
+ 3 -- OUT3
+ 4 -- OUT4
+
==Example==
/* 25MHz reference crystal */
-* Rockchip RK1108 Clock and Reset Unit
+* Rockchip RV1108 Clock and Reset Unit
-The RK1108 clock controller generates and supplies clock to various
+The RV1108 clock controller generates and supplies clock to various
controllers within the SoC and also implements a reset controller for SoC
peripherals.
Required Properties:
-- compatible: should be "rockchip,rk1108-cru"
+- compatible: should be "rockchip,rv1108-cru"
- reg: physical base address of the controller and length of memory mapped
region.
- #clock-cells: should be 1.
Each clock is assigned an identifier and client nodes can use this identifier
to specify the clock which they consume. All available clocks are defined as
-preprocessor macros in the dt-bindings/clock/rk1108-cru.h headers and can be
+preprocessor macros in the dt-bindings/clock/rv1108-cru.h headers and can be
used in device tree sources. Similar macros exist for the reset sources in
these files.
Example: Clock controller node:
cru: cru@20200000 {
- compatible = "rockchip,rk1108-cru";
+ compatible = "rockchip,rv1108-cru";
reg = <0x20200000 0x1000>;
rockchip,grf = <&grf>;
controller:
uart0: serial@10230000 {
- compatible = "rockchip,rk1108-uart", "snps,dw-apb-uart";
+ compatible = "rockchip,rv1108-uart", "snps,dw-apb-uart";
reg = <0x10230000 0x100>;
interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
reg-shift = <2>;
- "allwinner,sun8i-a23-ccu"
- "allwinner,sun8i-a33-ccu"
- "allwinner,sun8i-h3-ccu"
+ - "allwinner,sun8i-h3-r-ccu"
- "allwinner,sun8i-v3s-ccu"
- "allwinner,sun9i-a80-ccu"
- "allwinner,sun50i-a64-ccu"
+ - "allwinner,sun50i-a64-r-ccu"
+ - "allwinner,sun50i-h5-ccu"
- reg: Must contain the registers base address and length
- clocks: phandle to the oscillators feeding the CCU. Two are needed:
- #clock-cells : must contain 1
- #reset-cells : must contain 1
-Example:
+For the PRCM CCUs on H3/A64, one more clock is needed:
+- "iosc": the SoC's internal frequency oscillator
+
+Example for generic CCU:
ccu: clock@01c20000 {
compatible = "allwinner,sun8i-h3-ccu";
reg = <0x01c20000 0x400>;
#clock-cells = <1>;
#reset-cells = <1>;
};
+
+Example for PRCM CCU:
+r_ccu: clock@01f01400 {
+ compatible = "allwinner,sun50i-a64-r-ccu";
+ reg = <0x01f01400 0x100>;
+ clocks = <&osc24M>, <&osc32k>, <&iosc>;
+ clock-names = "hosc", "losc", "iosc";
+ #clock-cells = <1>;
+ #reset-cells = <1>;
+};
Additional, the display node has to define properties:
- bits-per-pixel: Bits per pixel
- fsl,pcr: LCDC PCR value
+ A display node may optionally define
+ - fsl,aus-mode: boolean to enable AUS mode (only for imx21)
Optional properties:
- lcd-supply: Regulator for LCD supply voltage.
aliases of secure registers have to be used during
SMMU configuration.
+- stream-match-mask : For SMMUs supporting stream matching and using
+ #iommu-cells = <1>, specifies a mask of bits to ignore
+ when matching stream IDs (e.g. this may be programmed
+ into the SMRn.MASK field of every stream match register
+ used). For cases where it is desirable to ignore some
+ portion of every Stream ID (e.g. for certain MMU-500
+ configurations given globally unique input IDs). This
+ property is not valid for SMMUs using stream indexing,
+ or using stream matching with #iommu-cells = <2>, and
+ may be ignored if present in such cases.
+
** Deprecated properties:
- mmu-masters (deprecated in favour of the generic "iommus" binding) :
master3 {
iommus = <&smmu2 1 0x30>;
};
+
+
+ /* ARM MMU-500 with 10-bit stream ID input configuration */
+ smmu3: iommu {
+ compatible = "arm,mmu-500", "arm,smmu-v2";
+ ...
+ #iommu-cells = <1>;
+ /* always ignore appended 5-bit TBU number */
+ stream-match-mask = 0x7c00;
+ };
+
+ bus {
+ /* bus whose child devices emit one unique 10-bit stream
+ ID each, but may master through multiple SMMU TBUs */
+ iommu-map = <0 &smmu3 0 0x400>;
+ ...
+ };
-Atmel NAND flash
+Atmel NAND flash controller bindings
+
+The NAND flash controller node should be defined under the EBI bus (see
+Documentation/devicetree/bindings/memory-controllers/atmel,ebi.txt).
+One or several NAND devices can be defined under this NAND controller.
+The NAND controller might be connected to an ECC engine.
+
+* NAND controller bindings:
+
+Required properties:
+- compatible: should be one of the following
+ "atmel,at91rm9200-nand-controller"
+ "atmel,at91sam9260-nand-controller"
+ "atmel,at91sam9261-nand-controller"
+ "atmel,at91sam9g45-nand-controller"
+ "atmel,sama5d3-nand-controller"
+- ranges: empty ranges property to forward EBI ranges definitions.
+- #address-cells: should be set to 2.
+- #size-cells: should be set to 1.
+- atmel,nfc-io: phandle to the NFC IO block. Only required for sama5d3
+ controllers.
+- atmel,nfc-sram: phandle to the NFC SRAM block. Only required for sama5d3
+ controllers.
+
+Optional properties:
+- ecc-engine: phandle to the PMECC block. Only meaningful if the SoC embeds
+ a PMECC engine.
+
+* NAND device/chip bindings:
+
+Required properties:
+- reg: describes the CS lines assigned to the NAND device. If the NAND device
+ exposes multiple CS lines (multi-dies chips), your reg property will
+ contain X tuples of 3 entries.
+ 1st entry: the CS line this NAND chip is connected to
+ 2nd entry: the base offset of the memory region assigned to this
+ device (always 0)
+ 3rd entry: the memory region size (always 0x800000)
+
+Optional properties:
+- rb-gpios: the GPIO(s) used to check the Ready/Busy status of the NAND.
+- cs-gpios: the GPIO(s) used to control the CS line.
+- det-gpios: the GPIO used to detect if a Smartmedia Card is present.
+- atmel,rb: an integer identifying the native Ready/Busy pin. Only meaningful
+ on sama5 SoCs.
+
+All generic properties described in
+Documentation/devicetree/bindings/mtd/{common,nand}.txt also apply to the NAND
+device node, and NAND partitions should be defined under the NAND node as
+described in Documentation/devicetree/bindings/mtd/partition.txt.
+
+* ECC engine (PMECC) bindings:
+
+Required properties:
+- compatible: should be one of the following
+ "atmel,at91sam9g45-pmecc"
+ "atmel,sama5d4-pmecc"
+ "atmel,sama5d2-pmecc"
+- reg: should contain 2 register ranges. The first one is pointing to the PMECC
+ block, and the second one to the PMECC_ERRLOC block.
+
+Example:
+
+ pmecc: ecc-engine@ffffc070 {
+ compatible = "atmel,at91sam9g45-pmecc";
+ reg = <0xffffc070 0x490>,
+ <0xffffc500 0x100>;
+ };
+
+ ebi: ebi@10000000 {
+ compatible = "atmel,sama5d3-ebi";
+ #address-cells = <2>;
+ #size-cells = <1>;
+ atmel,smc = <&hsmc>;
+ reg = <0x10000000 0x10000000
+ 0x40000000 0x30000000>;
+ ranges = <0x0 0x0 0x10000000 0x10000000
+ 0x1 0x0 0x40000000 0x10000000
+ 0x2 0x0 0x50000000 0x10000000
+ 0x3 0x0 0x60000000 0x10000000>;
+ clocks = <&mck>;
+
+ nand_controller: nand-controller {
+ compatible = "atmel,sama5d3-nand-controller";
+ atmel,nfc-sram = <&nfc_sram>;
+ atmel,nfc-io = <&nfc_io>;
+ ecc-engine = <&pmecc>;
+ #address-cells = <2>;
+ #size-cells = <1>;
+ ranges;
+
+ nand@3 {
+ reg = <0x3 0x0 0x800000>;
+ atmel,rb = <0>;
+
+ /*
+ * Put generic NAND/MTD properties and
+ * subnodes here.
+ */
+ };
+ };
+ };
+
+-----------------------------------------------------------------------
+
+Deprecated bindings (should not be used in new device trees):
Required properties:
- compatible: The possible values are:
* Denali NAND controller
Required properties:
- - compatible : should be "denali,denali-nand-dt"
+ - compatible : should be one of the following:
+ "altr,socfpga-denali-nand" - for Altera SOCFPGA
- reg : should contain registers location and length for data and reg.
- reg-names: Should contain the reg names "nand_data" and "denali_reg"
- interrupts : The interrupt number.
- - dm-mask : DMA bit mask
The device tree may optionally contain sub-nodes describing partitions of the
address space. See partition.txt for more detail.
nand: nand@ff900000 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "denali,denali-nand-dt";
+ compatible = "altr,socfpga-denali-nand";
reg = <0xff900000 0x100000>, <0xffb80000 0x10000>;
reg-names = "nand_data", "denali_reg";
interrupts = <0 144 4>;
- dma-mask = <0xffffffff>;
};
- #address-cells, #size-cells : Must be present if the device has sub-nodes
representing partitions.
- gpios : Specifies the GPIO pins to control the NAND device. The order of
- GPIO references is: RDY, nCE, ALE, CLE, and an optional nWP.
+ GPIO references is: RDY, nCE, ALE, CLE, and nWP. nCE and nWP are optional.
Optional properties:
- bank-width : Width (in bytes) of the device. If not present, the width
#address-cells = <1>;
#size-cells = <1>;
gpios = <&banka 1 0>, /* RDY */
- <&banka 2 0>, /* nCE */
+ <0>, /* nCE */
<&banka 3 0>, /* ALE */
<&banka 4 0>, /* CLE */
<0>; /* nWP */
--- /dev/null
+* STMicroelectronics Quad Serial Peripheral Interface(QuadSPI)
+
+Required properties:
+- compatible: should be "st,stm32f469-qspi"
+- reg: the first contains the register location and length.
+ the second contains the memory mapping address and length
+- reg-names: should contain the reg names "qspi" "qspi_mm"
+- interrupts: should contain the interrupt for the device
+- clocks: the phandle of the clock needed by the QSPI controller
+- A pinctrl must be defined to set pins in mode of operation for QSPI transfer
+
+Optional properties:
+- resets: must contain the phandle to the reset controller.
+
+A spi flash must be a child of the nor_flash node and could have some
+properties. Also see jedec,spi-nor.txt.
+
+Required properties:
+- reg: chip-Select number (QSPI controller may connect 2 nor flashes)
+- spi-max-frequency: max frequency of spi bus
+
+Optional property:
+- spi-rx-bus-width: see ../spi/spi-bus.txt for the description
+
+Example:
+
+qspi: spi@a0001000 {
+ compatible = "st,stm32f469-qspi";
+ reg = <0xa0001000 0x1000>, <0x90000000 0x10000000>;
+ reg-names = "qspi", "qspi_mm";
+ interrupts = <91>;
+ resets = <&rcc STM32F4_AHB3_RESET(QSPI)>;
+ clocks = <&rcc 0 STM32F4_AHB3_CLOCK(QSPI)>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_qspi0>;
+
+ flash@0 {
+ reg = <0>;
+ spi-rx-bus-width = <4>;
+ spi-max-frequency = <108000000>;
+ ...
+ };
+};
child: power-controller@12341000 {
compatible = "foo,power-controller";
reg = <0x12341000 0x1000>;
- power-domains = <&parent 0>;
+ power-domains = <&parent>;
#power-domain-cells = <0>;
domain-idle-states = <&DOMAIN_PWR_DN>;
};
- compatible: should be one of:
- "atmel,at91sam9rl-pwm"
- "atmel,sama5d3-pwm"
+ - "atmel,sama5d2-pwm"
- reg: physical base address and length of the controller's registers
- #pwm-cells: Should be 3. See pwm.txt in this directory for a
description of the cells format.
- reset-names: Must include the following entries:
- pwm
+Optional properties:
+============================
+In some of the interface like PWM based regulator device, it is required
+to configure the pins differently in different states, especially in suspend
+state of the system. The configuration of pin is provided via the pinctrl
+DT node as detailed in the pinctrl DT binding document
+ Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+
+The PWM node will have following optional properties.
+pinctrl-names: Pin state names. Must be "default" and "sleep".
+pinctrl-0: phandle for the default/active state of pin configurations.
+pinctrl-1: phandle for the sleep state of pin configurations.
+
Example:
pwm: pwm@7000a000 {
resets = <&tegra_car 17>;
reset-names = "pwm";
};
+
+
+Example with the pin configuration for suspend and resume:
+=========================================================
+Suppose pin PE7 (On Tegra210) interfaced with the regulator device and
+it requires PWM output to be tristated when system enters suspend.
+Following will be DT binding to achieve this:
+
+#include <dt-bindings/pinctrl/pinctrl-tegra.h>
+
+ pinmux@700008d4 {
+ pwm_active_state: pwm_active_state {
+ pe7 {
+ nvidia,pins = "pe7";
+ nvidia,tristate = <TEGRA_PIN_DISABLE>;
+ };
+ };
+
+ pwm_sleep_state: pwm_sleep_state {
+ pe7 {
+ nvidia,pins = "pe7";
+ nvidia,tristate = <TEGRA_PIN_ENABLE>;
+ };
+ };
+ };
+
+ pwm@7000a000 {
+ /* Mandatory PWM properties */
+ pinctrl-names = "default", "sleep";
+ pinctrl-0 = <&pwm_active_state>;
+ pinctrl-1 = <&pwm_sleep_state>;
+ };
--- /dev/null
+MediaTek PWM controller
+
+Required properties:
+ - compatible: should be "mediatek,<name>-pwm":
+ - "mediatek,mt7623-pwm": found on mt7623 SoC.
+ - reg: physical base address and length of the controller's registers.
+ - #pwm-cells: must be 2. See pwm.txt in this directory for a description of
+ the cell format.
+ - clocks: phandle and clock specifier of the PWM reference clock.
+ - clock-names: must contain the following:
+ - "top": the top clock generator
+ - "main": clock used by the PWM core
+ - "pwm1-5": the five per PWM clocks
+ - pinctrl-names: Must contain a "default" entry.
+ - pinctrl-0: One property must exist for each entry in pinctrl-names.
+ See pinctrl/pinctrl-bindings.txt for details of the property values.
+
+Example:
+ pwm0: pwm@11006000 {
+ compatible = "mediatek,mt7623-pwm";
+ reg = <0 0x11006000 0 0x1000>;
+ #pwm-cells = <2>;
+ clocks = <&topckgen CLK_TOP_PWM_SEL>,
+ <&pericfg CLK_PERI_PWM>,
+ <&pericfg CLK_PERI_PWM1>,
+ <&pericfg CLK_PERI_PWM2>,
+ <&pericfg CLK_PERI_PWM3>,
+ <&pericfg CLK_PERI_PWM4>,
+ <&pericfg CLK_PERI_PWM5>;
+ clock-names = "top", "main", "pwm1", "pwm2",
+ "pwm3", "pwm4", "pwm5";
+ pinctrl-names = "default";
+ pinctrl-0 = <&pwm0_pins>;
+ };
--- /dev/null
+Motorola CPCAP PMIC RTC
+-----------------------
+
+This module is part of the CPCAP. For more details about the whole
+chip see Documentation/devicetree/bindings/mfd/motorola-cpcap.txt.
+
+Requires node properties:
+- compatible: should contain "motorola,cpcap-rtc"
+- interrupts: An interrupt specifier for alarm and 1 Hz irq
+
+Example:
+
+&cpcap {
+ cpcap_rtc: rtc {
+ compatible = "motorola,cpcap-rtc";
+ interrupts = <39 IRQ_TYPE_NONE>, <26 IRQ_TYPE_NONE>;
+ };
+};
--- /dev/null
+* Real Time Clock for Renesas SH and ARM SoCs
+
+Required properties:
+- compatible: Should be "renesas,r7s72100-rtc" and "renesas,sh-rtc" as a
+ fallback.
+- reg: physical base address and length of memory mapped region.
+- interrupts: 3 interrupts for alarm, period, and carry.
+- interrupt-names: The interrupts should be labeled as "alarm", "period", and
+ "carry".
+- clocks: The functional clock source for the RTC controller must be listed
+ first (if exists). Additionally, potential clock counting sources are to be
+ listed.
+- clock-names: The functional clock must be labeled as "fck". Other clocks
+ may be named in accordance to the SoC hardware manuals.
+
+
+Example:
+rtc: rtc@fcff1000 {
+ compatible = "renesas,r7s72100-rtc", "renesas,sh-rtc";
+ reg = <0xfcff1000 0x2e>;
+ interrupts = <GIC_SPI 276 IRQ_TYPE_EDGE_RISING
+ GIC_SPI 277 IRQ_TYPE_EDGE_RISING
+ GIC_SPI 278 IRQ_TYPE_EDGE_RISING>;
+ interrupt-names = "alarm", "period", "carry";
+ clocks = <&mstp6_clks R7S72100_CLK_RTC>, <&rtc_x1_clk>,
+ <&rtc_x3_clk>, <&extal_clk>;
+ clock-names = "fck", "rtc_x1", "rtc_x3", "extal";
+};
silabs,si7020 Relative Humidity and Temperature Sensors
skyworks,sky81452 Skyworks SKY81452: Six-Channel White LED Driver with Touch Panel Bias Supply
st,24c256 i2c serial eeprom (24cxx)
+st,m41t0 Serial real-time clock (RTC)
st,m41t00 Serial real-time clock (RTC)
st,m41t62 Serial real-time clock (RTC) with alarm
st,m41t80 M41T80 - SERIAL ACCESS RTC WITH ALARMS
- phy-names: Should be "usb-phy"
+ - dmas: specifies the dma channels
+
+ - dma-names: specifies the names of the channels. Use "rxN" for receive
+ and "txN" for transmit endpoints. N specifies the endpoint number.
+
Optional properties:
~~~~~~~~~~~~~~~~~~~~
- vbus-supply: Phandle to a regulator providing the USB bus power.
+DMA
+~~~
+- compatible: ti,da830-cppi41
+- reg: offset and length of the following register spaces: CPPI DMA Controller,
+ CPPI DMA Scheduler, Queue Manager
+- reg-names: "controller", "scheduler", "queuemgr"
+- #dma-cells: should be set to 2. The first number represents the
+ channel number (0 … 3 for endpoints 1 … 4).
+ The second number is 0 for RX and 1 for TX transfers.
+- #dma-channels: should be set to 4 representing the 4 endpoints.
+
Example:
usb_phy: usb-phy {
compatible = "ti,da830-usb-phy";
};
usb0: usb@200000 {
compatible = "ti,da830-musb";
- reg = <0x00200000 0x10000>;
+ reg = <0x00200000 0x1000>;
+ ranges;
+ #address-cells = <1>;
+ #size-cells = <1>;
interrupts = <58>;
interrupt-names = "mc";
phys = <&usb_phy 0>;
phy-names = "usb-phy";
+ dmas = <&cppi41dma 0 0 &cppi41dma 1 0
+ &cppi41dma 2 0 &cppi41dma 3 0
+ &cppi41dma 0 1 &cppi41dma 1 1
+ &cppi41dma 2 1 &cppi41dma 3 1>;
+ dma-names =
+ "rx1", "rx2", "rx3", "rx4",
+ "tx1", "tx2", "tx3", "tx4";
+
status = "okay";
+
+ cppi41dma: dma-controller@201000 {
+ compatible = "ti,da830-cppi41";
+ reg = <0x201000 0x1000
+ 0x202000 0x1000
+ 0x204000 0x4000>;
+ reg-names = "controller", "scheduler", "queuemgr";
+ interrupts = <58>;
+ #dma-cells = <2>;
+ #dma-channels = <4>;
+ };
+
};
lenovo Lenovo Group Ltd.
lg LG Corporation
licheepi Lichee Pi
+linaro Linaro Limited
linux Linux-specific binding
lltc Linear Technology Corporation
lsi LSI Corp. (LSI Logic)
miramems MiraMEMS Sensing Technology Co., Ltd.
mitsubishi Mitsubishi Electric Corporation
mosaixtech Mosaix Technologies, Inc.
+motorola Motorola, Inc.
moxa Moxa
mpl MPL AG
mqmaker mqmaker Inc.
different layout types.
Files-layout-driver code is in: fs/nfs/filelayout/.. directory
-Objects-layout-driver code is in: fs/nfs/objlayout/.. directory
Blocks-layout-driver code is in: fs/nfs/blocklayout/.. directory
Flexfiles-layout-driver code is in: fs/nfs/flexfilelayout/.. directory
-objects-layout setup
---------------------
-
-As part of the full STD implementation the objlayoutdriver.ko needs, at times,
-to automatically login to yet undiscovered iscsi/osd devices. For this the
-driver makes up-calles to a user-mode script called *osd_login*
-
-The path_name of the script to use is by default:
- /sbin/osd_login.
-This name can be overridden by the Kernel module parameter:
- objlayoutdriver.osd_login_prog
-
-If Kernel does not find the osd_login_prog path it will zero it out
-and will not attempt farther logins. An admin can then write new value
-to the objlayoutdriver.osd_login_prog Kernel parameter to re-enable it.
-
-The /sbin/osd_login is part of the nfs-utils package, and should usually
-be installed on distributions that support this Kernel version.
-
-The API to the login script is as follows:
- Usage: $0 -u <URI> -o <OSDNAME> -s <SYSTEMID>
- Options:
- -u target uri e.g. iscsi://<ip>:<port>
- (always exists)
- (More protocols can be defined in the future.
- The client does not interpret this string it is
- passed unchanged as received from the Server)
- -o osdname of the requested target OSD
- (Might be empty)
- (A string which denotes the OSD name, there is a
- limit of 64 chars on this string)
- -s systemid of the requested target OSD
- (Might be empty)
- (This string, if not empty is always an hex
- representation of the 20 bytes osd_system_id)
-
blocks-layout setup
-------------------
This is most obvious from the 'st_dev' field returned by stat(2).
While directories will report an st_dev from the overlay-filesystem,
-all non-directory objects will report an st_dev from the lower or
+non-directory objects may report an st_dev from the lower filesystem or
upper filesystem that is providing the object. Similarly st_ino will
only be unique when combined with st_dev, and both of these can change
over the lifetime of a non-directory object. Many applications and
tools ignore these values and will not be affected.
+In the special case of all overlay layers on the same underlying
+filesystem, all objects will report an st_dev from the overlay
+filesystem and st_ino from the underlying filesystem. This will
+make the overlay mount more compliant with filesystem scanners and
+overlay objects will be distinguishable from the corresponding
+objects in the original filesystem.
+
Upper and Lower
---------------
0xA3 80-8F Port ACL in development:
<mailto:tlewis@mindspring.com>
0xA3 90-9F linux/dtlk.h
+0xA4 00-1F uapi/linux/tee.h Generic TEE subsystem
0xAA 00-3F linux/uapi/linux/userfaultfd.h
0xAB 00-1F linux/nbd.h
0xAC 00-1F linux/raw.h
--- 6.11 Post-link pass
=== 7 Kbuild syntax for exported headers
- --- 7.1 header-y
+ --- 7.1 no-export-headers
--- 7.2 genhdr-y
- --- 7.3 destination-y
- --- 7.4 generic-y
- --- 7.5 generated-y
+ --- 7.3 generic-y
+ --- 7.4 generated-y
+ --- 7.5 mandatory-y
=== 8 Kbuild Variables
=== 9 Makefile language
that may be shared between individual architectures.
The recommended approach how to use a generic header file is
to list the file in the Kbuild file.
- See "7.4 generic-y" for further info on syntax etc.
+ See "7.3 generic-y" for further info on syntax etc.
--- 6.11 Post-link pass
- drop include of compiler.h
- drop all sections that are kernel internal (guarded by ifdef __KERNEL__)
-Each relevant directory contains a file name "Kbuild" which specifies the
-headers to be exported.
-See subsequent chapter for the syntax of the Kbuild file.
-
- --- 7.1 header-y
-
- header-y specifies header files to be exported.
-
- Example:
- #include/linux/Kbuild
- header-y += usb/
- header-y += aio_abi.h
+All headers under include/uapi/, include/generated/uapi/,
+arch/<arch>/include/uapi/ and arch/<arch>/include/generated/uapi/
+are exported.
- The convention is to list one file per line and
- preferably in alphabetic order.
+A Kbuild file may be defined under arch/<arch>/include/uapi/asm/ and
+arch/<arch>/include/asm/ to list asm files coming from asm-generic.
+See subsequent chapter for the syntax of the Kbuild file.
- header-y also specifies which subdirectories to visit.
- A subdirectory is identified by a trailing '/' which
- can be seen in the example above for the usb subdirectory.
+ --- 7.1 no-export-headers
- Subdirectories are visited before their parent directories.
+ no-export-headers is essentially used by include/uapi/linux/Kbuild to
+ avoid exporting specific headers (e.g. kvm.h) on architectures that do
+ not support it. It should be avoided as much as possible.
--- 7.2 genhdr-y
- genhdr-y specifies generated files to be exported.
- Generated files are special as they need to be looked
- up in another directory when doing 'make O=...' builds.
+ genhdr-y specifies asm files to be generated.
Example:
- #include/linux/Kbuild
- genhdr-y += version.h
+ #arch/x86/include/uapi/asm/Kbuild
+ genhdr-y += unistd_32.h
+ genhdr-y += unistd_64.h
+ genhdr-y += unistd_x32.h
- --- 7.3 destination-y
- When an architecture has a set of exported headers that needs to be
- exported to a different directory destination-y is used.
- destination-y specifies the destination directory for all exported
- headers in the file where it is present.
-
- Example:
- #arch/xtensa/platforms/s6105/include/platform/Kbuild
- destination-y := include/linux
-
- In the example above all exported headers in the Kbuild file
- will be located in the directory "include/linux" when exported.
-
- --- 7.4 generic-y
+ --- 7.3 generic-y
If an architecture uses a verbatim copy of a header from
include/asm-generic then this is listed in the file
Example: termios.h
#include <asm-generic/termios.h>
- --- 7.5 generated-y
+ --- 7.4 generated-y
If an architecture generates other header files alongside generic-y
wrappers, and not included in genhdr-y, then generated-y specifies
#arch/x86/include/asm/Kbuild
generated-y += syscalls_32.h
+ --- 7.5 mandatory-y
+
+ mandatory-y is essentially used by include/uapi/asm-generic/Kbuild.asm
+ to define the minimun set of headers that must be exported in
+ include/asm.
+
+ The convention is to list one subdir per line and
+ preferably in alphabetic order.
+
=== 8 Kbuild Variables
The top Makefile exports the following variables:
transform the above code into the following:
q = READ_ONCE(a);
- WRITE_ONCE(b, 1);
+ WRITE_ONCE(b, 2);
do_something_else();
Given this transformation, the CPU is not required to respect the ordering
--- /dev/null
+TEE subsystem
+This document describes the TEE subsystem in Linux.
+
+A TEE (Trusted Execution Environment) is a trusted OS running in some
+secure environment, for example, TrustZone on ARM CPUs, or a separate
+secure co-processor etc. A TEE driver handles the details needed to
+communicate with the TEE.
+
+This subsystem deals with:
+
+- Registration of TEE drivers
+
+- Managing shared memory between Linux and the TEE
+
+- Providing a generic API to the TEE
+
+The TEE interface
+=================
+
+include/uapi/linux/tee.h defines the generic interface to a TEE.
+
+User space (the client) connects to the driver by opening /dev/tee[0-9]* or
+/dev/teepriv[0-9]*.
+
+- TEE_IOC_SHM_ALLOC allocates shared memory and returns a file descriptor
+ which user space can mmap. When user space doesn't need the file
+ descriptor any more, it should be closed. When shared memory isn't needed
+ any longer it should be unmapped with munmap() to allow the reuse of
+ memory.
+
+- TEE_IOC_VERSION lets user space know which TEE this driver handles and
+ the its capabilities.
+
+- TEE_IOC_OPEN_SESSION opens a new session to a Trusted Application.
+
+- TEE_IOC_INVOKE invokes a function in a Trusted Application.
+
+- TEE_IOC_CANCEL may cancel an ongoing TEE_IOC_OPEN_SESSION or TEE_IOC_INVOKE.
+
+- TEE_IOC_CLOSE_SESSION closes a session to a Trusted Application.
+
+There are two classes of clients, normal clients and supplicants. The latter is
+a helper process for the TEE to access resources in Linux, for example file
+system access. A normal client opens /dev/tee[0-9]* and a supplicant opens
+/dev/teepriv[0-9].
+
+Much of the communication between clients and the TEE is opaque to the
+driver. The main job for the driver is to receive requests from the
+clients, forward them to the TEE and send back the results. In the case of
+supplicants the communication goes in the other direction, the TEE sends
+requests to the supplicant which then sends back the result.
+
+OP-TEE driver
+=============
+
+The OP-TEE driver handles OP-TEE [1] based TEEs. Currently it is only the ARM
+TrustZone based OP-TEE solution that is supported.
+
+Lowest level of communication with OP-TEE builds on ARM SMC Calling
+Convention (SMCCC) [2], which is the foundation for OP-TEE's SMC interface
+[3] used internally by the driver. Stacked on top of that is OP-TEE Message
+Protocol [4].
+
+OP-TEE SMC interface provides the basic functions required by SMCCC and some
+additional functions specific for OP-TEE. The most interesting functions are:
+
+- OPTEE_SMC_FUNCID_CALLS_UID (part of SMCCC) returns the version information
+ which is then returned by TEE_IOC_VERSION
+
+- OPTEE_SMC_CALL_GET_OS_UUID returns the particular OP-TEE implementation, used
+ to tell, for instance, a TrustZone OP-TEE apart from an OP-TEE running on a
+ separate secure co-processor.
+
+- OPTEE_SMC_CALL_WITH_ARG drives the OP-TEE message protocol
+
+- OPTEE_SMC_GET_SHM_CONFIG lets the driver and OP-TEE agree on which memory
+ range to used for shared memory between Linux and OP-TEE.
+
+The GlobalPlatform TEE Client API [5] is implemented on top of the generic
+TEE API.
+
+Picture of the relationship between the different components in the
+OP-TEE architecture.
+
+ User space Kernel Secure world
+ ~~~~~~~~~~ ~~~~~~ ~~~~~~~~~~~~
+ +--------+ +-------------+
+ | Client | | Trusted |
+ +--------+ | Application |
+ /\ +-------------+
+ || +----------+ /\
+ || |tee- | ||
+ || |supplicant| \/
+ || +----------+ +-------------+
+ \/ /\ | TEE Internal|
+ +-------+ || | API |
+ + TEE | || +--------+--------+ +-------------+
+ | Client| || | TEE | OP-TEE | | OP-TEE |
+ | API | \/ | subsys | driver | | Trusted OS |
+ +-------+----------------+----+-------+----+-----------+-------------+
+ | Generic TEE API | | OP-TEE MSG |
+ | IOCTL (TEE_IOC_*) | | SMCCC (OPTEE_SMC_CALL_*) |
+ +-----------------------------+ +------------------------------+
+
+RPC (Remote Procedure Call) are requests from secure world to kernel driver
+or tee-supplicant. An RPC is identified by a special range of SMCCC return
+values from OPTEE_SMC_CALL_WITH_ARG. RPC messages which are intended for the
+kernel are handled by the kernel driver. Other RPC messages will be forwarded to
+tee-supplicant without further involvement of the driver, except switching
+shared memory buffer representation.
+
+References:
+[1] https://github.com/OP-TEE/optee_os
+[2] http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
+[3] drivers/tee/optee/optee_smc.h
+[4] drivers/tee/optee/optee_msg.h
+[5] http://www.globalplatform.org/specificationsdevice.asp look for
+ "TEE Client API Specification v1.0" and click download.
KVM_DEV_ARM_VGIC_CTRL_INIT
request the initialization of the ITS, no additional parameter in
kvm_device_attr.addr.
+
+ KVM_DEV_ARM_ITS_SAVE_TABLES
+ save the ITS table data into guest RAM, at the location provisioned
+ by the guest in corresponding registers/table entries.
+
+ The layout of the tables in guest memory defines an ABI. The entries
+ are laid out in little endian format as described in the last paragraph.
+
+ KVM_DEV_ARM_ITS_RESTORE_TABLES
+ restore the ITS tables from guest RAM to ITS internal structures.
+
+ The GICV3 must be restored before the ITS and all ITS registers but
+ the GITS_CTLR must be restored before restoring the ITS tables.
+
+ The GITS_IIDR read-only register must also be restored before
+ calling KVM_DEV_ARM_ITS_RESTORE_TABLES as the IIDR revision field
+ encodes the ABI revision.
+
+ The expected ordering when restoring the GICv3/ITS is described in section
+ "ITS Restore Sequence".
+
Errors:
-ENXIO: ITS not properly configured as required prior to setting
this attribute
-ENOMEM: Memory shortage when allocating ITS internal data
+ -EINVAL: Inconsistent restored data
+ -EFAULT: Invalid guest ram access
+ -EBUSY: One or more VCPUS are running
+
+ KVM_DEV_ARM_VGIC_GRP_ITS_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes the offset of the
+ ITS register, relative to the ITS control frame base address
+ (ITS_base).
+
+ kvm_device_attr.addr points to a __u64 value whatever the width
+ of the addressed register (32/64 bits). 64 bit registers can only
+ be accessed with full length.
+
+ Writes to read-only registers are ignored by the kernel except for:
+ - GITS_CREADR. It must be restored otherwise commands in the queue
+ will be re-executed after restoring CWRITER. GITS_CREADR must be
+ restored before restoring the GITS_CTLR which is likely to enable the
+ ITS. Also it must be restored after GITS_CBASER since a write to
+ GITS_CBASER resets GITS_CREADR.
+ - GITS_IIDR. The Revision field encodes the table layout ABI revision.
+ In the future we might implement direct injection of virtual LPIs.
+ This will require an upgrade of the table layout and an evolution of
+ the ABI. GITS_IIDR must be restored before calling
+ KVM_DEV_ARM_ITS_RESTORE_TABLES.
+
+ For other registers, getting or setting a register has the same
+ effect as reading/writing the register on real hardware.
+ Errors:
+ -ENXIO: Offset does not correspond to any supported register
+ -EFAULT: Invalid user pointer for attr->addr
+ -EINVAL: Offset is not 64-bit aligned
+ -EBUSY: one or more VCPUS are running
+
+ ITS Restore Sequence:
+ -------------------------
+
+The following ordering must be followed when restoring the GIC and the ITS:
+a) restore all guest memory and create vcpus
+b) restore all redistributors
+c) provide the its base address
+ (KVM_DEV_ARM_VGIC_GRP_ADDR)
+d) restore the ITS in the following order:
+ 1. Restore GITS_CBASER
+ 2. Restore all other GITS_ registers, except GITS_CTLR!
+ 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES)
+ 4. Restore GITS_CTLR
+
+Then vcpus can be started.
+
+ ITS Table ABI REV0:
+ -------------------
+
+ Revision 0 of the ABI only supports the features of a virtual GICv3, and does
+ not support a virtual GICv4 with support for direct injection of virtual
+ interrupts for nested hypervisors.
+
+ The device table and ITT are indexed by the DeviceID and EventID,
+ respectively. The collection table is not indexed by CollectionID, and the
+ entries in the collection are listed in no particular order.
+ All entries are 8 bytes.
+
+ Device Table Entry (DTE):
+
+ bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 |
+ values: | V | next | ITT_addr | Size |
+
+ where;
+ - V indicates whether the entry is valid. If not, other fields
+ are not meaningful.
+ - next: equals to 0 if this entry is the last one; otherwise it
+ corresponds to the DeviceID offset to the next DTE, capped by
+ 2^14 -1.
+ - ITT_addr matches bits [51:8] of the ITT address (256 Byte aligned).
+ - Size specifies the supported number of bits for the EventID,
+ minus one
+
+ Collection Table Entry (CTE):
+
+ bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 |
+ values: | V | RES0 | RDBase | ICID |
+
+ where:
+ - V indicates whether the entry is valid. If not, other fields are
+ not meaningful.
+ - RES0: reserved field with Should-Be-Zero-or-Preserved behavior.
+ - RDBase is the PE number (GICR_TYPER.Processor_Number semantic),
+ - ICID is the collection ID
+
+ Interrupt Translation Entry (ITE):
+
+ bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 |
+ values: | next | pINTID | ICID |
+
+ where:
+ - next: equals to 0 if this entry is the last one; otherwise it corresponds
+ to the EventID offset to the next ITE capped by 2^16 -1.
+ - pINTID is the physical LPI ID; if zero, it means the entry is not valid
+ and other fields are not meaningful.
+ - ICID is the collection ID
KVM_DEV_ARM_VGIC_CTRL_INIT
request the initialization of the VGIC, no additional parameter in
kvm_device_attr.addr.
+ KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES
+ save all LPI pending bits into guest RAM pending tables.
+
+ The first kB of the pending table is not altered by this operation.
Errors:
-ENXIO: VGIC not properly configured as required prior to calling
this attribute
-ENODEV: no online VCPU
-ENOMEM: memory shortage when allocating vgic internal data
+ -EFAULT: Invalid guest ram access
+ -EBUSY: One or more VCPUS are running
KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO
# 4) Check for missing system calls
# 5) Generate constants.py (may need bounds.h)
-# Default sed regexp - multiline due to syntax constraints
-define sed-y
- "/^->/{s:->#\(.*\):/* \1 */:; \
- s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:->::; p;}"
-endef
-
-# Use filechk to avoid rebuilds when a header changes, but the resulting file
-# does not
-define filechk_offsets
- (set -e; \
- echo "#ifndef $2"; \
- echo "#define $2"; \
- echo "/*"; \
- echo " * DO NOT MODIFY."; \
- echo " *"; \
- echo " * This file was generated by Kbuild"; \
- echo " */"; \
- echo ""; \
- sed -ne $(sed-y); \
- echo ""; \
- echo "#endif" )
-endef
-
#####
# 1) Generate bounds.h
F: drivers/mmc/host/meson*
N: meson
+ARM/Amlogic Meson SoC CLOCK FRAMEWORK
+M: Neil Armstrong <narmstrong@baylibre.com>
+M: Jerome Brunet <jbrunet@baylibre.com>
+L: linux-amlogic@lists.infradead.org
+S: Maintained
+F: drivers/clk/meson/
+F: include/dt-bindings/clock/meson*
+F: include/dt-bindings/clock/gxbb*
+F: Documentation/devicetree/bindings/clock/amlogic*
+
ARM/Annapurna Labs ALPINE ARCHITECTURE
M: Tsahee Zidenberg <tsahee@annapurnalabs.com>
M: Antoine Tenart <antoine.tenart@free-electrons.com>
M: Josh Wu <rainyfeeling@outlook.com>
L: linux-mtd@lists.infradead.org
S: Supported
-F: drivers/mtd/nand/atmel_nand*
+F: drivers/mtd/nand/atmel/*
ATMEL SDMMC DRIVER
M: Ludovic Desroches <ludovic.desroches@microchip.com>
S: Maintained
F: Documentation/filesystems/btrfs.txt
F: fs/btrfs/
+F: include/linux/btrfs*
+F: include/uapi/linux/btrfs*
BTTV VIDEO4LINUX DRIVER
M: Mauro Carvalho Chehab <mchehab@s-opensource.com>
S: Supported
F: drivers/base/power/domain*.c
F: include/linux/pm_domain.h
+F: Documentation/devicetree/bindings/power/power_domain.txt
GENERIC UIO DRIVER FOR PCI DEVICES
M: "Michael S. Tsirkin" <mst@redhat.com>
M: Boris Brezillon <boris.brezillon@free-electrons.com>
M: Marek Vasut <marek.vasut@gmail.com>
M: Richard Weinberger <richard@nod.at>
-M: Cyrille Pitchen <cyrille.pitchen@atmel.com>
+M: Cyrille Pitchen <cyrille.pitchen@wedev4u.fr>
L: linux-mtd@lists.infradead.org
W: http://www.linux-mtd.infradead.org/
Q: http://patchwork.ozlabs.org/project/linux-mtd/list/
-T: git git://git.infradead.org/linux-mtd.git
-T: git git://git.infradead.org/l2-mtd.git
+T: git git://git.infradead.org/linux-mtd.git master
+T: git git://git.infradead.org/l2-mtd.git master
S: Maintained
F: Documentation/devicetree/bindings/mtd/
F: drivers/mtd/
L: linux-mtd@lists.infradead.org
W: http://www.linux-mtd.infradead.org/
Q: http://patchwork.ozlabs.org/project/linux-mtd/list/
-T: git git://github.com/linux-nand/linux.git
+T: git git://git.infradead.org/linux-mtd.git nand/fixes
+T: git git://git.infradead.org/l2-mtd.git nand/next
S: Maintained
F: drivers/mtd/nand/
F: include/linux/mtd/nand*.h
F: drivers/oprofile/
F: include/linux/oprofile.h
+OP-TEE DRIVER
+M: Jens Wiklander <jens.wiklander@linaro.org>
+S: Maintained
+F: drivers/tee/optee/
+
ORACLE CLUSTER FILESYSTEM 2 (OCFS2)
M: Mark Fasheh <mfasheh@versity.com>
M: Joel Becker <jlbec@evilplan.org>
F: include/linux/stm.h
F: include/uapi/linux/stm.h
+TEE SUBSYSTEM
+M: Jens Wiklander <jens.wiklander@linaro.org>
+S: Maintained
+F: include/linux/tee_drv.h
+F: include/uapi/linux/tee.h
+F: drivers/tee/
+F: Documentation/tee.txt
+
THUNDERBOLT DRIVER
M: Andreas Noever <andreas.noever@gmail.com>
S: Maintained
F: drivers/clk/spear/
SPI NOR SUBSYSTEM
-M: Cyrille Pitchen <cyrille.pitchen@atmel.com>
+M: Cyrille Pitchen <cyrille.pitchen@wedev4u.fr>
M: Marek Vasut <marek.vasut@gmail.com>
L: linux-mtd@lists.infradead.org
W: http://www.linux-mtd.infradead.org/
F: drivers/crypto/virtio/
VIRTIO DRIVERS FOR S390
-M: Christian Borntraeger <borntraeger@de.ibm.com>
M: Cornelia Huck <cornelia.huck@de.ibm.com>
+M: Halil Pasic <pasic@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
L: virtualization@lists.linux-foundation.org
L: kvm@vger.kernel.org
KBUILD_CFLAGS += $(call cc-option,-fno-delete-null-pointer-checks,)
KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
-ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
-KBUILD_CFLAGS += $(call cc-option,-ffunction-sections,)
-KBUILD_CFLAGS += $(call cc-option,-fdata-sections,)
-endif
-
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS += -Os $(call cc-disable-warning,maybe-uninitialized,)
+KBUILD_CFLAGS += $(call cc-option,-Oz,-Os)
+KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,)
else
ifdef CONFIG_PROFILE_ALL_BRANCHES
KBUILD_CFLAGS += -O2 $(call cc-disable-warning,maybe-uninitialized,)
KBUILD_CFLAGS += $(stackp-flag)
ifeq ($(cc-name),clang)
+ifneq ($(CROSS_COMPILE),)
+CLANG_TARGET := -target $(notdir $(CROSS_COMPILE:%-=%))
+GCC_TOOLCHAIN := $(realpath $(dir $(shell which $(LD)))/..)
+endif
+ifneq ($(GCC_TOOLCHAIN),)
+CLANG_GCC_TC := -gcc-toolchain $(GCC_TOOLCHAIN)
+endif
+KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
+KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
-KBUILD_CPPFLAGS += $(call cc-option,-Wno-unknown-warning-option,)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
# See modpost pattern 2
KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
+KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
+KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
else
# These warnings generated too much noise in a regular build.
-# Use make W=1 to enable them (see scripts/Makefile.build)
+# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
endif
KBUILD_CFLAGS += $(call cc-option, -fno-inline-functions-called-once)
endif
+ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
+KBUILD_CFLAGS += $(call cc-option,-ffunction-sections,)
+KBUILD_CFLAGS += $(call cc-option,-fdata-sections,)
+endif
+
# arch Makefile may override CC so keep this after arch Makefile is included
NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include)
CHECKFLAGS += $(NOSTDINC_FLAGS)
# enforce correct pointer usage
KBUILD_CFLAGS += $(call cc-option,-Werror=incompatible-pointer-types)
+# Require designated initializers for all marked structures
+KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init)
+
# use the deterministic mode of AR if available
KBUILD_ARFLAGS := $(call ar-option,D)
KBUILD_CFLAGS += $(ARCH_CFLAGS) $(KCFLAGS)
# Use --build-id when available.
-LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\
+LDFLAGS_BUILD_ID := $(patsubst -Wl$(comma)%,%,\
$(call cc-ldoption, -Wl$(comma)--build-id,))
KBUILD_LDFLAGS_MODULE += $(LDFLAGS_BUILD_ID)
LDFLAGS_vmlinux += $(LDFLAGS_BUILD_ID)
export INSTALL_HDR_PATH = $(objtree)/usr
# If we do an all arch process set dst to asm-$(hdr-arch)
-hdr-dst = $(if $(KBUILD_HEADERS), dst=include/asm-$(hdr-arch), dst=include/asm)
+hdr-dst = $(if $(KBUILD_HEADERS), dst=include/arch-$(hdr-arch), dst=include)
PHONY += archheaders
archheaders:
$(if $(wildcard $(srctree)/arch/$(hdr-arch)/include/uapi/asm/Kbuild),, \
$(error Headers not exportable for the $(SRCARCH) architecture))
$(Q)$(MAKE) $(hdr-inst)=include/uapi
- $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi/asm $(hdr-dst)
+ $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi $(hdr-dst)
PHONY += headers_check_all
headers_check_all: headers_install_all
PHONY += headers_check
headers_check: headers_install
$(Q)$(MAKE) $(hdr-inst)=include/uapi HDRCHECK=1
- $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi/asm $(hdr-dst) HDRCHECK=1
+ $(Q)$(MAKE) $(hdr-inst)=arch/$(hdr-arch)/include/uapi/ $(hdr-dst) HDRCHECK=1
# ---------------------------------------------------------------------------
# Kernel selftest
distclean: mrproper
@find $(srctree) $(RCS_FIND_IGNORE) \
\( -name '*.orig' -o -name '*.rej' -o -name '*~' \
- -o -name '*.bak' -o -name '#*#' -o -name '.*.orig' \
- -o -name '.*.rej' -o -name '*%' -o -name 'core' \) \
+ -o -name '*.bak' -o -name '#*#' -o -name '*%' \
+ -o -name 'core' \) \
-type f -print | xargs rm -f
@echo ' (default: $$(INSTALL_MOD_PATH)/lib/firmware)'
@echo ' dir/ - Build all files in dir and below'
@echo ' dir/file.[ois] - Build specified target only'
+ @echo ' dir/file.ll - Build the LLVM assembly file'
+ @echo ' (requires compiler support for LLVM assembly generation)'
@echo ' dir/file.lst - Build specified mixed source/assembly target only'
@echo ' (requires a recent binutils and recent build (System.map))'
@echo ' dir/file.ko - Build module including final link'
-o -name '*.symtypes' -o -name 'modules.order' \
-o -name modules.builtin -o -name '.tmp_*.o.*' \
-o -name '*.c.[012]*.*' \
+ -o -name '*.ll' \
-o -name '*.gcno' \) -type f -print | xargs rm -f
# Generate tags for editors
$(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
%.symtypes: %.c prepare scripts FORCE
$(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
+%.ll: %.c prepare scripts FORCE
+ $(Q)$(MAKE) $(build)=$(build-dir) $(target-dir)$(notdir $@)
# Modules
/: prepare scripts FORCE
config HAVE_CMPXCHG_DOUBLE
bool
+config ARCH_WEAK_RELEASE_ACQUIRE
+ bool
+
config ARCH_WANT_IPC_PARSE_VERSION
bool
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += a.out.h
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += compiler.h
-header-y += console.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += fpu.h
-header-y += gentrap.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += pal.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += reg.h
-header-y += regdef.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += sysinfo.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
AFLAGS___divlu.o = -DDIV -DINTSIZE
AFLAGS___remlu.o = -DREM -DINTSIZE
-$(obj)/__divqu.o: $(obj)/$(ev6-y)divide.S
- $(cmd_as_o_S)
-$(obj)/__remqu.o: $(obj)/$(ev6-y)divide.S
- $(cmd_as_o_S)
-$(obj)/__divlu.o: $(obj)/$(ev6-y)divide.S
- $(cmd_as_o_S)
-$(obj)/__remlu.o: $(obj)/$(ev6-y)divide.S
- $(cmd_as_o_S)
+$(addprefix $(obj)/,__divqu.o __remqu.o __divlu.o __remlu.o): \
+ $(src)/$(ev6-y)divide.S FORCE
+ $(call if_changed_rule,as_o_S)
boot := arch/arc/boot
#default target for make without any arguments.
-KBUILD_IMAGE := bootpImage
+KBUILD_IMAGE := $(boot)/bootpImage
-all: $(KBUILD_IMAGE)
+all: bootpImage
bootpImage: vmlinux
boot_targets += uImage uImage.bin uImage.gz
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += elf.h
-header-y += page.h
-header-y += cachectl.h
libs-y := arch/arm/lib/ $(libs-y)
# Default target when executing plain make
+boot := arch/arm/boot
ifeq ($(CONFIG_XIP_KERNEL),y)
-KBUILD_IMAGE := xipImage
+KBUILD_IMAGE := $(boot)/xipImage
else
-KBUILD_IMAGE := zImage
+KBUILD_IMAGE := $(boot)/zImage
endif
# Build the DT binary blobs if we have OF configured
KBUILD_DTBS := dtbs
endif
-all: $(KBUILD_IMAGE) $(KBUILD_DTBS)
+all: $(notdir $(KBUILD_IMAGE)) $(KBUILD_DTBS)
-boot := arch/arm/boot
archheaders:
$(Q)$(MAKE) $(build)=arch/arm/tools uapi
#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/interrupt-controller/arm-gic.h>
-#include <dt-bindings/clock/rk1108-cru.h>
+#include <dt-bindings/clock/rv1108-cru.h>
#include <dt-bindings/pinctrl/rockchip.h>
/ {
#address-cells = <1>;
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += auxvec.h
-header-y += byteorder.h
-header-y += fcntl.h
-header-y += hwcap.h
-header-y += ioctls.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += perf_regs.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += setup.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += unistd.h
genhdr-y += unistd-common.h
genhdr-y += unistd-oabi.h
genhdr-y += unistd-eabi.h
#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
#define VGIC_LEVEL_INFO_LINE_LEVEL 0
-#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
/* KVM_IRQ_LINE irq field index values */
#define KVM_ARM_IRQ_TYPE_SHIFT 24
#ifdef CONFIG_MMU
void *module_alloc(unsigned long size)
{
- void *p = __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
- GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+ gfp_t gfp_mask = GFP_KERNEL;
+ void *p;
+
+ /* Silence the initial allocation */
+ if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS))
+ gfp_mask |= __GFP_NOWARN;
+
+ p = __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
+ gfp_mask, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
__builtin_return_address(0));
if (!IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || p)
return p;
kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp/
+
obj-y += kvm-arm.o init.o interrupts.o
-obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
-obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o vgic-v3-coproc.o
+obj-y += handle_exit.o guest.o emulate.o reset.o
+obj-y += coproc.o coproc_a15.o coproc_a7.o vgic-v3-coproc.o
+obj-y += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
+obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
obj-y += $(KVM)/arm/aarch32.o
obj-y += $(KVM)/arm/vgic/vgic.o
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
-/*
- * Tracepoints for entry/exit to guest
- */
-TRACE_EVENT(kvm_entry,
- TP_PROTO(unsigned long vcpu_pc),
- TP_ARGS(vcpu_pc),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- ),
-
- TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
-);
-
-TRACE_EVENT(kvm_exit,
- TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
- TP_ARGS(idx, exit_reason, vcpu_pc),
-
- TP_STRUCT__entry(
- __field( int, idx )
- __field( unsigned int, exit_reason )
- __field( unsigned long, vcpu_pc )
- ),
-
- TP_fast_assign(
- __entry->idx = idx;
- __entry->exit_reason = exit_reason;
- __entry->vcpu_pc = vcpu_pc;
- ),
-
- TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
- __print_symbolic(__entry->idx, kvm_arm_exception_type),
- __entry->exit_reason,
- __print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
- __entry->vcpu_pc)
-);
-
-TRACE_EVENT(kvm_guest_fault,
- TP_PROTO(unsigned long vcpu_pc, unsigned long hsr,
- unsigned long hxfar,
- unsigned long long ipa),
- TP_ARGS(vcpu_pc, hsr, hxfar, ipa),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( unsigned long, hsr )
- __field( unsigned long, hxfar )
- __field( unsigned long long, ipa )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->hsr = hsr;
- __entry->hxfar = hxfar;
- __entry->ipa = ipa;
- ),
-
- TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
- __entry->ipa, __entry->hsr,
- __entry->hxfar, __entry->vcpu_pc)
-);
-
-TRACE_EVENT(kvm_access_fault,
- TP_PROTO(unsigned long ipa),
- TP_ARGS(ipa),
-
- TP_STRUCT__entry(
- __field( unsigned long, ipa )
- ),
-
- TP_fast_assign(
- __entry->ipa = ipa;
- ),
-
- TP_printk("IPA: %lx", __entry->ipa)
-);
-
-TRACE_EVENT(kvm_irq_line,
- TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level),
- TP_ARGS(type, vcpu_idx, irq_num, level),
-
- TP_STRUCT__entry(
- __field( unsigned int, type )
- __field( int, vcpu_idx )
- __field( int, irq_num )
- __field( int, level )
- ),
-
- TP_fast_assign(
- __entry->type = type;
- __entry->vcpu_idx = vcpu_idx;
- __entry->irq_num = irq_num;
- __entry->level = level;
- ),
-
- TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d",
- (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" :
- (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" :
- (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN",
- __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level)
-);
-
-TRACE_EVENT(kvm_mmio_emulate,
- TP_PROTO(unsigned long vcpu_pc, unsigned long instr,
- unsigned long cpsr),
- TP_ARGS(vcpu_pc, instr, cpsr),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( unsigned long, instr )
- __field( unsigned long, cpsr )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->instr = instr;
- __entry->cpsr = cpsr;
- ),
-
- TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
- __entry->vcpu_pc, __entry->instr, __entry->cpsr)
-);
-
/* Architecturally implementation defined CP15 register access */
TRACE_EVENT(kvm_emulate_cp15_imp,
TP_PROTO(unsigned long Op1, unsigned long Rt1, unsigned long CRn,
__entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
);
-TRACE_EVENT(kvm_unmap_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
-
- TP_STRUCT__entry(
- __field( unsigned long, hva )
- ),
-
- TP_fast_assign(
- __entry->hva = hva;
- ),
-
- TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva)
-);
-
-TRACE_EVENT(kvm_unmap_hva_range,
- TP_PROTO(unsigned long start, unsigned long end),
- TP_ARGS(start, end),
-
- TP_STRUCT__entry(
- __field( unsigned long, start )
- __field( unsigned long, end )
- ),
-
- TP_fast_assign(
- __entry->start = start;
- __entry->end = end;
- ),
-
- TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
- __entry->start, __entry->end)
-);
-
-TRACE_EVENT(kvm_set_spte_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
-
- TP_STRUCT__entry(
- __field( unsigned long, hva )
- ),
-
- TP_fast_assign(
- __entry->hva = hva;
- ),
-
- TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
-);
-
-TRACE_EVENT(kvm_age_hva,
- TP_PROTO(unsigned long start, unsigned long end),
- TP_ARGS(start, end),
-
- TP_STRUCT__entry(
- __field( unsigned long, start )
- __field( unsigned long, end )
- ),
-
- TP_fast_assign(
- __entry->start = start;
- __entry->end = end;
- ),
-
- TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
- __entry->start, __entry->end)
-);
-
-TRACE_EVENT(kvm_test_age_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
-
- TP_STRUCT__entry(
- __field( unsigned long, hva )
- ),
-
- TP_fast_assign(
- __entry->hva = hva;
- ),
-
- TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
-);
-
TRACE_EVENT(kvm_hvc,
TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
TP_ARGS(vcpu_pc, r0, imm),
__entry->vcpu_pc, __entry->r0, __entry->imm)
);
-TRACE_EVENT(kvm_set_way_flush,
- TP_PROTO(unsigned long vcpu_pc, bool cache),
- TP_ARGS(vcpu_pc, cache),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( bool, cache )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->cache = cache;
- ),
-
- TP_printk("S/W flush at 0x%016lx (cache %s)",
- __entry->vcpu_pc, __entry->cache ? "on" : "off")
-);
-
-TRACE_EVENT(kvm_toggle_cache,
- TP_PROTO(unsigned long vcpu_pc, bool was, bool now),
- TP_ARGS(vcpu_pc, was, now),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( bool, was )
- __field( bool, now )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->was = was;
- __entry->now = now;
- ),
-
- TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
- __entry->vcpu_pc, __entry->was ? "on" : "off",
- __entry->now ? "on" : "off")
-);
-
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
if (!dd)
return -EINVAL;
- tmpset.cm_clksel1_pll = readl_relaxed(dd->mult_div1_reg);
+ tmpset.cm_clksel1_pll =
+ omap_clk_ll_ops.clk_readl(&dd->mult_div1_reg);
tmpset.cm_clksel1_pll &= ~(dd->mult_mask |
dd->div1_mask);
div = ((curr_prcm_set->xtal_speed / 1000000) - 1);
#define OMAP3PLUS_DPLL_FINT_MIN 32000
#define OMAP3PLUS_DPLL_FINT_MAX 52000000
-static struct ti_clk_ll_ops omap_clk_ll_ops = {
+struct ti_clk_ll_ops omap_clk_ll_ops = {
.clkdm_clk_enable = clkdm_clk_enable,
.clkdm_clk_disable = clkdm_clk_disable,
+ .clkdm_lookup = clkdm_lookup,
.cm_wait_module_ready = omap_cm_wait_module_ready,
.cm_split_idlest_reg = cm_split_idlest_reg,
};
* OMAP2+ specific clock functions
*/
-/* Public functions */
-
-/**
- * omap2_init_clk_clkdm - look up a clockdomain name, store pointer in clk
- * @clk: OMAP clock struct ptr to use
- *
- * Convert a clockdomain name stored in a struct clk 'clk' into a
- * clockdomain pointer, and save it into the struct clk. Intended to be
- * called during clk_register(). No return value.
- */
-void omap2_init_clk_clkdm(struct clk_hw *hw)
-{
- struct clk_hw_omap *clk = to_clk_hw_omap(hw);
- struct clockdomain *clkdm;
- const char *clk_name;
-
- if (!clk->clkdm_name)
- return;
-
- clk_name = __clk_get_name(hw->clk);
-
- clkdm = clkdm_lookup(clk->clkdm_name);
- if (clkdm) {
- pr_debug("clock: associated clk %s to clkdm %s\n",
- clk_name, clk->clkdm_name);
- clk->clkdm = clkdm;
- } else {
- pr_debug("clock: could not associate clk %s to clkdm %s\n",
- clk_name, clk->clkdm_name);
- }
-}
-
/**
* ti_clk_init_features - init clock features struct for the SoC
*
#define OMAP4XXX_EN_DPLL_FRBYPASS 0x6
#define OMAP4XXX_EN_DPLL_LOCKED 0x7
+extern struct ti_clk_ll_ops omap_clk_ll_ops;
+
extern u16 cpu_mask;
extern const struct clkops clkops_omap2_dflt_wait;
#define MAX_MODULE_READY_TIME 2000
# ifndef __ASSEMBLER__
+#include <linux/clk/ti.h>
extern void __iomem *cm_base;
extern void __iomem *cm2_base;
extern void omap2_set_globals_cm(void __iomem *cm, void __iomem *cm2);
* @module_disable: ptr to the SoC CM-specific module_disable impl
*/
struct cm_ll_data {
- int (*split_idlest_reg)(void __iomem *idlest_reg, s16 *prcm_inst,
+ int (*split_idlest_reg)(struct clk_omap_reg *idlest_reg, s16 *prcm_inst,
u8 *idlest_reg_id);
int (*wait_module_ready)(u8 part, s16 prcm_mod, u16 idlest_reg,
u8 idlest_shift);
void (*module_disable)(u8 part, u16 inst, u16 clkctrl_offs);
};
-extern int cm_split_idlest_reg(void __iomem *idlest_reg, s16 *prcm_inst,
+extern int cm_split_idlest_reg(struct clk_omap_reg *idlest_reg, s16 *prcm_inst,
u8 *idlest_reg_id);
int omap_cm_wait_module_ready(u8 part, s16 prcm_mod, u16 idlest_reg,
u8 idlest_shift);
* XXX This function is only needed until absolute register addresses are
* removed from the OMAP struct clk records.
*/
-static int omap2xxx_cm_split_idlest_reg(void __iomem *idlest_reg,
+static int omap2xxx_cm_split_idlest_reg(struct clk_omap_reg *idlest_reg,
s16 *prcm_inst,
u8 *idlest_reg_id)
{
u8 idlest_offs;
int i;
- if (idlest_reg < cm_base || idlest_reg > (cm_base + 0x0fff))
- return -EINVAL;
-
- idlest_offs = (unsigned long)idlest_reg & 0xff;
+ idlest_offs = idlest_reg->offset & 0xff;
for (i = 0; i < ARRAY_SIZE(omap2xxx_cm_idlest_offs); i++) {
if (idlest_offs == omap2xxx_cm_idlest_offs[i]) {
*idlest_reg_id = i + 1;
if (i == ARRAY_SIZE(omap2xxx_cm_idlest_offs))
return -EINVAL;
- offs = idlest_reg - cm_base;
+ offs = idlest_reg->offset;
offs &= 0xff00;
*prcm_inst = offs;
* XXX This function is only needed until absolute register addresses are
* removed from the OMAP struct clk records.
*/
-static int omap3xxx_cm_split_idlest_reg(void __iomem *idlest_reg,
+static int omap3xxx_cm_split_idlest_reg(struct clk_omap_reg *idlest_reg,
s16 *prcm_inst,
u8 *idlest_reg_id)
{
u8 idlest_offs;
int i;
- if (idlest_reg < (cm_base + OMAP3430_IVA2_MOD) ||
- idlest_reg > (cm_base + 0x1ffff))
- return -EINVAL;
-
- idlest_offs = (unsigned long)idlest_reg & 0xff;
+ idlest_offs = idlest_reg->offset & 0xff;
for (i = 0; i < ARRAY_SIZE(omap3xxx_cm_idlest_offs); i++) {
if (idlest_offs == omap3xxx_cm_idlest_offs[i]) {
*idlest_reg_id = i + 1;
if (i == ARRAY_SIZE(omap3xxx_cm_idlest_offs))
return -EINVAL;
- offs = idlest_reg - cm_base;
+ offs = idlest_reg->offset;
offs &= 0xff00;
*prcm_inst = offs;
* or 0 upon success. XXX This function is only needed until absolute
* register addresses are removed from the OMAP struct clk records.
*/
-int cm_split_idlest_reg(void __iomem *idlest_reg, s16 *prcm_inst,
+int cm_split_idlest_reg(struct clk_omap_reg *idlest_reg, s16 *prcm_inst,
u8 *idlest_reg_id)
{
if (!cm_ll_data->split_idlest_reg) {
const struct dma_map_ops *dma_ops;
dev->archdata.dma_coherent = coherent;
+
+ /*
+ * Don't override the dma_ops if they have already been set. Ideally
+ * this should be the only location where dma_ops are set, remove this
+ * check when all other callers of set_dma_ops will have disappeared.
+ */
+ if (dev->dma_ops)
+ return;
+
if (arm_setup_iommu_dma_ops(dev, dma_base, size, iommu))
dma_ops = arm_get_iommu_dma_map_ops(coherent);
else
* published by the Free Software Foundation.
*/
-#include <linux/amba/pl330.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/interrupt.h>
core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
# Default target when executing plain make
-KBUILD_IMAGE := Image.gz
+boot := arch/arm64/boot
+KBUILD_IMAGE := $(boot)/Image.gz
KBUILD_DTBS := dtbs
-all: $(KBUILD_IMAGE) $(KBUILD_DTBS)
+all: Image.gz $(KBUILD_DTBS)
-boot := arch/arm64/boot
Image: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
};
};
};
+
+ firmware {
+ optee {
+ compatible = "linaro,optee-tz";
+ method = "smc";
+ };
+ };
};
&uart2 {
alternative_else_nop_endif
.endm
+/*
+ * Remove the address tag from a virtual address, if present.
+ */
+ .macro clear_address_tag, dst, addr
+ tst \addr, #(1 << 55)
+ bic \dst, \addr, #(0xff << 56)
+ csel \dst, \dst, \addr, eq
+ .endm
+
#endif
#define ATOMIC64_FETCH_OP_AND(name, mb, cl...) \
static inline long atomic64_fetch_and##name(long i, atomic64_t *v) \
{ \
- register long x0 asm ("w0") = i; \
+ register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
#define ATOMIC64_FETCH_OP_SUB(name, mb, cl...) \
static inline long atomic64_fetch_sub##name(long i, atomic64_t *v) \
{ \
- register long x0 asm ("w0") = i; \
+ register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
#define __smp_rmb() dmb(ishld)
#define __smp_wmb() dmb(ishst)
-#define __smp_store_release(p, v) \
+#define __smp_store_release(p, v) \
do { \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
compiletime_assert_atomic_type(*p); \
switch (sizeof(*p)) { \
case 1: \
asm volatile ("stlrb %w1, %0" \
- : "=Q" (*p) : "r" (v) : "memory"); \
+ : "=Q" (*p) \
+ : "r" (*(__u8 *)__u.__c) \
+ : "memory"); \
break; \
case 2: \
asm volatile ("stlrh %w1, %0" \
- : "=Q" (*p) : "r" (v) : "memory"); \
+ : "=Q" (*p) \
+ : "r" (*(__u16 *)__u.__c) \
+ : "memory"); \
break; \
case 4: \
asm volatile ("stlr %w1, %0" \
- : "=Q" (*p) : "r" (v) : "memory"); \
+ : "=Q" (*p) \
+ : "r" (*(__u32 *)__u.__c) \
+ : "memory"); \
break; \
case 8: \
asm volatile ("stlr %1, %0" \
- : "=Q" (*p) : "r" (v) : "memory"); \
+ : "=Q" (*p) \
+ : "r" (*(__u64 *)__u.__c) \
+ : "memory"); \
break; \
} \
} while (0)
" swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \
__nops(3) \
" " #nop_lse) \
- : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) \
+ : "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr) \
: "r" (x) \
: cl); \
\
return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
}
+static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
+{
+ u32 esr = kvm_vcpu_get_hsr(vcpu);
+ return (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+}
+
static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
{
return vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
*/
#define __range_ok(addr, size) \
({ \
+ unsigned long __addr = (unsigned long __force)(addr); \
unsigned long flag, roksum; \
__chk_user_ptr(addr); \
asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls" \
: "=&r" (flag), "=&r" (roksum) \
- : "1" (addr), "Ir" (size), \
+ : "1" (__addr), "Ir" (size), \
"r" (current_thread_info()->addr_limit) \
: "cc"); \
flag; \
})
/*
- * When dealing with data aborts or instruction traps we may end up with
- * a tagged userland pointer. Clear the tag to get a sane pointer to pass
- * on to access_ok(), for instance.
+ * When dealing with data aborts, watchpoints, or instruction traps we may end
+ * up with a tagged userland pointer. Clear the tag to get a sane pointer to
+ * pass on to access_ok(), for instance.
*/
#define untagged_addr(addr) sign_extend64(addr, 55)
(err), ARM64_HAS_UAO); \
break; \
case 8: \
- __get_user_asm("ldr", "ldtr", "%", __gu_val, (ptr), \
+ __get_user_asm("ldr", "ldtr", "%x", __gu_val, (ptr), \
(err), ARM64_HAS_UAO); \
break; \
default: \
(err), ARM64_HAS_UAO); \
break; \
case 8: \
- __put_user_asm("str", "sttr", "%", __pu_val, (ptr), \
+ __put_user_asm("str", "sttr", "%x", __pu_val, (ptr), \
(err), ARM64_HAS_UAO); \
break; \
default: \
include include/uapi/asm-generic/Kbuild.asm
generic-y += kvm_para.h
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += fcntl.h
-header-y += hwcap.h
-header-y += kvm_para.h
-header-y += perf_regs.h
-header-y += param.h
-header-y += ptrace.h
-header-y += setup.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += stat.h
-header-y += statfs.h
-header-y += ucontext.h
-header-y += unistd.h
#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
#define VGIC_LEVEL_INFO_LINE_LEVEL 0
-#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
/* Device Control API on vcpu fd */
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
_ASM_EXTABLE(0b, 4b) \
_ASM_EXTABLE(1b, 4b) \
: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2) \
- : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT), \
+ : "r" ((unsigned long)addr), "i" (-EAGAIN), \
+ "i" (-EFAULT), \
"i" (__SWP_LL_SC_LOOPS) \
: "memory"); \
uaccess_disable(); \
/*
* Data abort handling
*/
- mrs x0, far_el1
+ mrs x3, far_el1
enable_dbg
// re-enable interrupts if they were enabled in the aborted context
tbnz x23, #7, 1f // PSR_I_BIT
enable_irq
1:
+ clear_address_tag x0, x3
mov x2, sp // struct pt_regs
bl do_mem_abort
// enable interrupts before calling the main handler
enable_dbg_and_irq
ct_user_exit
- bic x0, x26, #(0xff << 56)
+ clear_address_tag x0, x26
mov x1, x25
mov x2, sp
bl do_mem_abort
#include <asm/traps.h>
#include <asm/cputype.h>
#include <asm/system_misc.h>
+#include <asm/uaccess.h>
/* Breakpoint currently in use for each BRP. */
static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]);
u64 wp_low, wp_high;
u32 lens, lene;
+ addr = untagged_addr(addr);
+
lens = __ffs(ctrl->len);
lene = __fls(ctrl->len);
void *module_alloc(unsigned long size)
{
+ gfp_t gfp_mask = GFP_KERNEL;
void *p;
+ /* Silence the initial allocation */
+ if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
+ gfp_mask |= __GFP_NOWARN;
+
p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base,
module_alloc_base + MODULES_VSIZE,
- GFP_KERNEL, PAGE_KERNEL_EXEC, 0,
+ gfp_mask, PAGE_KERNEL_EXEC, 0,
NUMA_NO_NODE, __builtin_return_address(0));
if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
}
#define __user_cache_maint(insn, address, res) \
- if (untagged_addr(address) >= user_addr_max()) { \
+ if (address >= user_addr_max()) { \
res = -EFAULT; \
} else { \
uaccess_ttbr0_enable(); \
int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
int ret = 0;
- address = pt_regs_read_reg(regs, rt);
+ address = untagged_addr(pt_regs_read_reg(regs, rt));
switch (crm) {
case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */
CFLAGS_mmu.o := -I.
KVM=../../../virt/kvm
-ARM=../../../arch/arm/kvm
obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp/
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o
kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
{
struct sys_reg_params params;
u32 hsr = kvm_vcpu_get_hsr(vcpu);
- int Rt = (hsr >> 5) & 0xf;
- int Rt2 = (hsr >> 10) & 0xf;
+ int Rt = kvm_vcpu_sys_get_rt(vcpu);
+ int Rt2 = (hsr >> 10) & 0x1f;
params.is_aarch32 = true;
params.is_32bit = false;
{
struct sys_reg_params params;
u32 hsr = kvm_vcpu_get_hsr(vcpu);
- int Rt = (hsr >> 5) & 0xf;
+ int Rt = kvm_vcpu_sys_get_rt(vcpu);
params.is_aarch32 = true;
params.is_32bit = true;
{
struct sys_reg_params params;
unsigned long esr = kvm_vcpu_get_hsr(vcpu);
- int Rt = (esr >> 5) & 0x1f;
+ int Rt = kvm_vcpu_sys_get_rt(vcpu);
int ret;
trace_kvm_handle_sys_reg(esr);
#include <linux/dma-contiguous.h>
#include <linux/vmalloc.h>
#include <linux/swiotlb.h>
+#include <linux/pci.h>
#include <asm/cacheflush.h>
.mapping_error = iommu_dma_mapping_error,
};
-/*
- * TODO: Right now __iommu_setup_dma_ops() gets called too early to do
- * everything it needs to - the device is only partially created and the
- * IOMMU driver hasn't seen it yet, so it can't have a group. Thus we
- * need this delayed attachment dance. Once IOMMU probe ordering is sorted
- * to move the arch_setup_dma_ops() call later, all the notifier bits below
- * become unnecessary, and will go away.
- */
-struct iommu_dma_notifier_data {
- struct list_head list;
- struct device *dev;
- const struct iommu_ops *ops;
- u64 dma_base;
- u64 size;
-};
-static LIST_HEAD(iommu_dma_masters);
-static DEFINE_MUTEX(iommu_dma_notifier_lock);
+static int __init __iommu_dma_init(void)
+{
+ return iommu_dma_init();
+}
+arch_initcall(__iommu_dma_init);
-static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
- u64 dma_base, u64 size)
+static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
+ const struct iommu_ops *ops)
{
- struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+ struct iommu_domain *domain;
+
+ if (!ops)
+ return;
/*
- * If the IOMMU driver has the DMA domain support that we require,
- * then the IOMMU core will have already configured a group for this
- * device, and allocated the default domain for that group.
+ * The IOMMU core code allocates the default DMA domain, which the
+ * underlying IOMMU driver needs to support via the dma-iommu layer.
*/
+ domain = iommu_get_domain_for_dev(dev);
+
if (!domain)
goto out_err;
dev->dma_ops = &iommu_dma_ops;
}
- return true;
+ return;
+
out_err:
- pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+ pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
dev_name(dev));
- return false;
-}
-
-static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops,
- u64 dma_base, u64 size)
-{
- struct iommu_dma_notifier_data *iommudata;
-
- iommudata = kzalloc(sizeof(*iommudata), GFP_KERNEL);
- if (!iommudata)
- return;
-
- iommudata->dev = dev;
- iommudata->ops = ops;
- iommudata->dma_base = dma_base;
- iommudata->size = size;
-
- mutex_lock(&iommu_dma_notifier_lock);
- list_add(&iommudata->list, &iommu_dma_masters);
- mutex_unlock(&iommu_dma_notifier_lock);
-}
-
-static int __iommu_attach_notifier(struct notifier_block *nb,
- unsigned long action, void *data)
-{
- struct iommu_dma_notifier_data *master, *tmp;
-
- if (action != BUS_NOTIFY_BIND_DRIVER)
- return 0;
-
- mutex_lock(&iommu_dma_notifier_lock);
- list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) {
- if (data == master->dev && do_iommu_attach(master->dev,
- master->ops, master->dma_base, master->size)) {
- list_del(&master->list);
- kfree(master);
- break;
- }
- }
- mutex_unlock(&iommu_dma_notifier_lock);
- return 0;
-}
-
-static int __init register_iommu_dma_ops_notifier(struct bus_type *bus)
-{
- struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL);
- int ret;
-
- if (!nb)
- return -ENOMEM;
-
- nb->notifier_call = __iommu_attach_notifier;
-
- ret = bus_register_notifier(bus, nb);
- if (ret) {
- pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n",
- bus->name);
- kfree(nb);
- }
- return ret;
-}
-
-static int __init __iommu_dma_init(void)
-{
- int ret;
-
- ret = iommu_dma_init();
- if (!ret)
- ret = register_iommu_dma_ops_notifier(&platform_bus_type);
- if (!ret)
- ret = register_iommu_dma_ops_notifier(&amba_bustype);
-#ifdef CONFIG_PCI
- if (!ret)
- ret = register_iommu_dma_ops_notifier(&pci_bus_type);
-#endif
- return ret;
-}
-arch_initcall(__iommu_dma_init);
-
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
- const struct iommu_ops *ops)
-{
- struct iommu_group *group;
-
- if (!ops)
- return;
- /*
- * TODO: As a concession to the future, we're ready to handle being
- * called both early and late (i.e. after bus_add_device). Once all
- * the platform bus code is reworked to call us late and the notifier
- * junk above goes away, move the body of do_iommu_attach here.
- */
- group = iommu_group_get(dev);
- if (group) {
- do_iommu_attach(dev, ops, dma_base, size);
- iommu_group_put(group);
- } else {
- queue_iommu_attach(dev, ops, dma_base, size);
- }
}
void arch_teardown_dma_ops(struct device *dev)
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += bfin_sport.h
-header-y += byteorder.h
-header-y += cachectl.h
-header-y += fcntl.h
-header-y += fixed_code.h
-header-y += ioctls.h
-header-y += kvm_para.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += stat.h
-header-y += swab.h
-header-y += unistd.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += kvm_para.h
-
-header-y += byteorder.h
-header-y += kvm_para.h
-header-y += ptrace.h
-header-y += setup.h
-header-y += sigcontext.h
-header-y += swab.h
-header-y += unistd.h
bool "NAND flash support"
depends on ETRAX_ARCH_V32
select MTD_NAND
- select MTD_NAND_IDS
help
This option enables MTD mapping of NAND flash devices. Needed to use
NAND flash memories. If unsure, say Y.
+++ /dev/null
-# CRISv10 arch
+++ /dev/null
-# CRISv32 arch
+++ /dev/null
-# UAPI Header export list
-header-y += sv_addr.agh
-header-y += sv_addr_ag.h
-header-y += svinto.h
-header-y += user.h
+++ /dev/null
-# UAPI Header export list
-header-y += cryptocop.h
-header-y += user.h
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += ../arch-v10/arch/
-header-y += ../arch-v32/arch/
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += elf.h
-header-y += elf_v10.h
-header-y += elf_v32.h
-header-y += errno.h
-header-y += ethernet.h
-header-y += etraxgpio.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += ptrace_v10.h
-header-y += ptrace_v32.h
-header-y += resource.h
-header-y += rs485.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += sync_serial.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += registers.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
#include <asm/thread_info.h>
#include <asm/gdb-stub.h>
-#define DEF_PTREG(sym, reg) \
- asm volatile("\n->" #sym " %0 offsetof(struct pt_regs, " #reg ")" \
- : : "i" (offsetof(struct pt_regs, reg)))
-
-#define DEF_IREG(sym, reg) \
- asm volatile("\n->" #sym " %0 offsetof(struct user_context, " #reg ")" \
- : : "i" (offsetof(struct user_context, reg)))
-
-#define DEF_FREG(sym, reg) \
- asm volatile("\n->" #sym " %0 offsetof(struct user_context, " #reg ")" \
- : : "i" (offsetof(struct user_context, reg)))
-
-#define DEF_0REG(sym, reg) \
- asm volatile("\n->" #sym " %0 offsetof(struct frv_frame0, " #reg ")" \
- : : "i" (offsetof(struct frv_frame0, reg)))
+#define DEF_PTREG(sym, reg) OFFSET(sym, pt_regs, reg)
+#define DEF_IREG(sym, reg) OFFSET(sym, user_context, reg)
+#define DEF_FREG(sym, reg) OFFSET(sym, user_context, reg)
+#define DEF_0REG(sym, reg) OFFSET(sym, frv_frame0, reg)
void foo(void)
{
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += siginfo.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
-#ifndef __ASM_H8300_BITS_PER_LONG
-#define __ASM_H8300_BITS_PER_LONG
+#ifndef _UAPI__ASM_H8300_BITS_PER_LONG
+#define _UAPI__ASM_H8300_BITS_PER_LONG
#include <asm-generic/bitsperlong.h>
typedef long __kernel_ptrdiff_t;
#endif
-#endif /* __ASM_H8300_BITS_PER_LONG */
+#endif /* _UAPI__ASM_H8300_BITS_PER_LONG */
-
-header-y += ucontext.h
-
generic-y += auxvec.h
generic-y += barrier.h
generic-y += bug.h
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += kvm_para.h
-header-y += param.h
-header-y += ptrace.h
-header-y += registers.h
-header-y += setup.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += swab.h
-header-y += unistd.h
-header-y += user.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += kvm_para.h
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += break.h
-header-y += byteorder.h
-header-y += cmpxchg.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += fpu.h
-header-y += gcc_intrin.h
-header-y += ia64regs.h
-header-y += intel_intrin.h
-header-y += intrinsics.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += perfmon.h
-header-y += perfmon_default_smpl.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += ptrace_offsets.h
-header-y += resource.h
-header-y += rse.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += ucontext.h
-header-y += unistd.h
-header-y += ustack.h
# The gate DSO image is built using a special linker script.
include $(src)/Makefile.gate
-# Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
-define sed-y
- "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"
-endef
-quiet_cmd_nr_irqs = GEN $@
-define cmd_nr_irqs
- (set -e; \
- echo "#ifndef __ASM_NR_IRQS_H__"; \
- echo "#define __ASM_NR_IRQS_H__"; \
- echo "/*"; \
- echo " * DO NOT MODIFY."; \
- echo " *"; \
- echo " * This file was generated by Kbuild"; \
- echo " *"; \
- echo " */"; \
- echo ""; \
- sed -ne $(sed-y) $<; \
- echo ""; \
- echo "#endif" ) > $@
-endef
-
# We use internal kbuild rules to avoid the "is up to date" message from make
arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
$(Q)mkdir -p $(dir $@)
$(call if_changed_dep,cc_s_c)
-include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
- $(Q)mkdir -p $(dir $@)
- $(call cmd,nr_irqs)
+include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s FORCE
+ $(call filechk,offsets,__ASM_NR_IRQS_H__)
CPPFLAGS_gate.lds := -P -C -U$(ARCH)
-quiet_cmd_gate = GATE $@
+quiet_cmd_gate = GATE $@
cmd_gate = $(CC) -nostdlib $(GATECFLAGS_$(@F)) -Wl,-T,$(filter-out FORCE,$^) -o $@
GATECFLAGS_gate.so = -shared -s -Wl,-soname=linux-gate.so.1 \
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
generic-y += sockios.h
generic-y += termbits.h
generic-y += termios.h
-
-header-y += a.out.h
-header-y += bootinfo.h
-header-y += bootinfo-amiga.h
-header-y += bootinfo-apollo.h
-header-y += bootinfo-atari.h
-header-y += bootinfo-hp300.h
-header-y += bootinfo-mac.h
-header-y += bootinfo-q40.h
-header-y += bootinfo-vme.h
-header-y += byteorder.h
-header-y += cachectl.h
-header-y += fcntl.h
-header-y += ioctls.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += setup.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += stat.h
-header-y += swab.h
-header-y += unistd.h
#define segment_eq(a, b) ((a).seg == (b).seg)
-#define __kernel_ok (uaccess_kernel())
-/*
- * Explicitly allow NULL pointers here. Parts of the kernel such
- * as readv/writev use access_ok to validate pointers, but want
- * to allow NULL pointers for various reasons. NULL pointers are
- * safe to allow through because the first page is not mappable on
- * Meta.
- *
- * We also wish to avoid letting user code access the system area
- * and the kernel half of the address space.
- */
-#define __user_bad(addr, size) (((addr) > 0 && (addr) < META_MEMORY_BASE) || \
- ((addr) > PAGE_OFFSET && \
- (addr) < LINCORE_BASE))
-
static inline int __access_ok(unsigned long addr, unsigned long size)
{
- return __kernel_ok || !__user_bad(addr, size);
+ /*
+ * Allow access to the user mapped memory area, but not the system area
+ * before it. The check extends to the top of the address space when
+ * kernel access is allowed (there's no real reason to user copy to the
+ * system area in any case).
+ */
+ if (likely(addr >= META_MEMORY_BASE && addr < get_fs().seg &&
+ size <= get_fs().seg - addr))
+ return true;
+ /*
+ * Explicitly allow NULL pointers here. Parts of the kernel such
+ * as readv/writev use access_ok to validate pointers, but want
+ * to allow NULL pointers for various reasons. NULL pointers are
+ * safe to allow through because the first page is not mappable on
+ * Meta.
+ */
+ if (!addr)
+ return true;
+ /* Allow access to core code memory area... */
+ if (addr >= LINCORE_CODE_BASE && addr <= LINCORE_CODE_LIMIT &&
+ size <= LINCORE_CODE_LIMIT + 1 - addr)
+ return true;
+ /* ... but no other areas. */
+ return false;
}
#define access_ok(type, addr, size) __access_ok((unsigned long)(addr), \
#define __get_user_nocheck(x, ptr, size) \
({ \
- long __gu_err, __gu_val; \
+ long __gu_err; \
+ long long __gu_val; \
__get_user_size(__gu_val, (ptr), (size), __gu_err); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
__gu_err; \
#define __get_user_check(x, ptr, size) \
({ \
- long __gu_err = -EFAULT, __gu_val = 0; \
+ long __gu_err = -EFAULT; \
+ long long __gu_val = 0; \
const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \
if (access_ok(VERIFY_READ, __gu_addr, size)) \
__get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
extern unsigned char __get_user_asm_b(const void __user *addr, long *err);
extern unsigned short __get_user_asm_w(const void __user *addr, long *err);
extern unsigned int __get_user_asm_d(const void __user *addr, long *err);
+extern unsigned long long __get_user_asm_l(const void __user *addr, long *err);
#define __get_user_size(x, ptr, size, retval) \
do { \
x = __get_user_asm_w(ptr, &retval); break; \
case 4: \
x = __get_user_asm_d(ptr, &retval); break; \
+ case 8: \
+ x = __get_user_asm_l(ptr, &retval); break; \
default: \
(x) = __get_user_bad(); \
} \
extern long __must_check __strncpy_from_user(char *dst, const char __user *src,
long count);
-#define strncpy_from_user(dst, src, count) __strncpy_from_user(dst, src, count)
-
+static inline long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+ if (!access_ok(VERIFY_READ, src, 1))
+ return -EFAULT;
+ return __strncpy_from_user(dst, src, count);
+}
/*
* Return the size of a string (including the ending 0)
*
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += byteorder.h
-header-y += ech.h
-header-y += ptrace.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += swab.h
-header-y += unistd.h
-
generic-y += mman.h
generic-y += resource.h
generic-y += setup.h
#define __asm_copy_user_64bit_rapf_loop( \
to, from, ret, n, id, FIXUP) \
asm volatile ( \
- ".balign 8\n" \
- "MOV RAPF, %1\n" \
- "MSETL [A0StP++], D0Ar6, D0FrT, D0.5, D0.6, D0.7\n" \
- "MOV D0Ar6, #0\n" \
- "LSR D1Ar5, %3, #6\n" \
- "SUB TXRPT, D1Ar5, #2\n" \
- "MOV RAPF, %1\n" \
+ ".balign 8\n" \
+ " MOV RAPF, %1\n" \
+ " MSETL [A0StP++], D0Ar6, D0FrT, D0.5, D0.6, D0.7\n" \
+ " MOV D0Ar6, #0\n" \
+ " LSR D1Ar5, %3, #6\n" \
+ " SUB TXRPT, D1Ar5, #2\n" \
+ " MOV RAPF, %1\n" \
"$Lloop"id":\n" \
- "ADD RAPF, %1, #64\n" \
- "21:\n" \
- "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "22:\n" \
- "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "23:\n" \
- "SUB %3, %3, #32\n" \
- "24:\n" \
- "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "25:\n" \
- "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "26:\n" \
- "SUB %3, %3, #32\n" \
- "DCACHE [%1+#-64], D0Ar6\n" \
- "BR $Lloop"id"\n" \
+ " ADD RAPF, %1, #64\n" \
+ "21: MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "22: MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "23: SUB %3, %3, #32\n" \
+ "24: MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "25: MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "26: SUB %3, %3, #32\n" \
+ " DCACHE [%1+#-64], D0Ar6\n" \
+ " BR $Lloop"id"\n" \
\
- "MOV RAPF, %1\n" \
- "27:\n" \
- "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "28:\n" \
- "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "29:\n" \
- "SUB %3, %3, #32\n" \
- "30:\n" \
- "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "31:\n" \
- "MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "32:\n" \
- "SUB %0, %0, #8\n" \
- "33:\n" \
- "SETL [%0++], D0.7, D1.7\n" \
- "SUB %3, %3, #32\n" \
- "1:" \
- "DCACHE [%1+#-64], D0Ar6\n" \
- "GETL D0Ar6, D1Ar5, [A0StP+#-40]\n" \
- "GETL D0FrT, D1RtP, [A0StP+#-32]\n" \
- "GETL D0.5, D1.5, [A0StP+#-24]\n" \
- "GETL D0.6, D1.6, [A0StP+#-16]\n" \
- "GETL D0.7, D1.7, [A0StP+#-8]\n" \
- "SUB A0StP, A0StP, #40\n" \
+ " MOV RAPF, %1\n" \
+ "27: MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "28: MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "29: SUB %3, %3, #32\n" \
+ "30: MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "31: MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "32: SETL [%0+#-8], D0.7, D1.7\n" \
+ " SUB %3, %3, #32\n" \
+ "1: DCACHE [%1+#-64], D0Ar6\n" \
+ " GETL D0Ar6, D1Ar5, [A0StP+#-40]\n" \
+ " GETL D0FrT, D1RtP, [A0StP+#-32]\n" \
+ " GETL D0.5, D1.5, [A0StP+#-24]\n" \
+ " GETL D0.6, D1.6, [A0StP+#-16]\n" \
+ " GETL D0.7, D1.7, [A0StP+#-8]\n" \
+ " SUB A0StP, A0StP, #40\n" \
" .section .fixup,\"ax\"\n" \
- "4:\n" \
- " ADD %0, %0, #8\n" \
- "3:\n" \
- " MOV D0Ar2, TXSTATUS\n" \
+ "3: MOV D0Ar2, TXSTATUS\n" \
" MOV D1Ar1, TXSTATUS\n" \
" AND D1Ar1, D1Ar1, #0xFFFFF8FF\n" \
" MOV TXSTATUS, D1Ar1\n" \
FIXUP \
- " MOVT D0Ar2,#HI(1b)\n" \
- " JUMP D0Ar2,#LO(1b)\n" \
+ " MOVT D0Ar2, #HI(1b)\n" \
+ " JUMP D0Ar2, #LO(1b)\n" \
" .previous\n" \
" .section __ex_table,\"a\"\n" \
" .long 21b,3b\n" \
" .long 30b,3b\n" \
" .long 31b,3b\n" \
" .long 32b,3b\n" \
- " .long 33b,4b\n" \
" .previous\n" \
: "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \
: "0" (to), "1" (from), "2" (ret), "3" (n) \
#define __asm_copy_user_32bit_rapf_loop( \
to, from, ret, n, id, FIXUP) \
asm volatile ( \
- ".balign 8\n" \
- "MOV RAPF, %1\n" \
- "MSETL [A0StP++], D0Ar6, D0FrT, D0.5, D0.6, D0.7\n" \
- "MOV D0Ar6, #0\n" \
- "LSR D1Ar5, %3, #6\n" \
- "SUB TXRPT, D1Ar5, #2\n" \
- "MOV RAPF, %1\n" \
- "$Lloop"id":\n" \
- "ADD RAPF, %1, #64\n" \
- "21:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "22:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "23:\n" \
- "SUB %3, %3, #16\n" \
- "24:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "25:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "26:\n" \
- "SUB %3, %3, #16\n" \
- "27:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "28:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "29:\n" \
- "SUB %3, %3, #16\n" \
- "30:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "31:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "32:\n" \
- "SUB %3, %3, #16\n" \
- "DCACHE [%1+#-64], D0Ar6\n" \
- "BR $Lloop"id"\n" \
+ ".balign 8\n" \
+ " MOV RAPF, %1\n" \
+ " MSETL [A0StP++], D0Ar6, D0FrT, D0.5, D0.6, D0.7\n" \
+ " MOV D0Ar6, #0\n" \
+ " LSR D1Ar5, %3, #6\n" \
+ " SUB TXRPT, D1Ar5, #2\n" \
+ " MOV RAPF, %1\n" \
+ "$Lloop"id":\n" \
+ " ADD RAPF, %1, #64\n" \
+ "21: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "22: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "23: SUB %3, %3, #16\n" \
+ "24: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "25: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "26: SUB %3, %3, #16\n" \
+ "27: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "28: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "29: SUB %3, %3, #16\n" \
+ "30: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "31: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "32: SUB %3, %3, #16\n" \
+ " DCACHE [%1+#-64], D0Ar6\n" \
+ " BR $Lloop"id"\n" \
\
- "MOV RAPF, %1\n" \
- "33:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "34:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "35:\n" \
- "SUB %3, %3, #16\n" \
- "36:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "37:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "38:\n" \
- "SUB %3, %3, #16\n" \
- "39:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "40:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "41:\n" \
- "SUB %3, %3, #16\n" \
- "42:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "43:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "44:\n" \
- "SUB %0, %0, #4\n" \
- "45:\n" \
- "SETD [%0++], D0.7\n" \
- "SUB %3, %3, #16\n" \
- "1:" \
- "DCACHE [%1+#-64], D0Ar6\n" \
- "GETL D0Ar6, D1Ar5, [A0StP+#-40]\n" \
- "GETL D0FrT, D1RtP, [A0StP+#-32]\n" \
- "GETL D0.5, D1.5, [A0StP+#-24]\n" \
- "GETL D0.6, D1.6, [A0StP+#-16]\n" \
- "GETL D0.7, D1.7, [A0StP+#-8]\n" \
- "SUB A0StP, A0StP, #40\n" \
+ " MOV RAPF, %1\n" \
+ "33: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "34: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "35: SUB %3, %3, #16\n" \
+ "36: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "37: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "38: SUB %3, %3, #16\n" \
+ "39: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "40: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "41: SUB %3, %3, #16\n" \
+ "42: MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
+ "43: MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "44: SETD [%0+#-4], D0.7\n" \
+ " SUB %3, %3, #16\n" \
+ "1: DCACHE [%1+#-64], D0Ar6\n" \
+ " GETL D0Ar6, D1Ar5, [A0StP+#-40]\n" \
+ " GETL D0FrT, D1RtP, [A0StP+#-32]\n" \
+ " GETL D0.5, D1.5, [A0StP+#-24]\n" \
+ " GETL D0.6, D1.6, [A0StP+#-16]\n" \
+ " GETL D0.7, D1.7, [A0StP+#-8]\n" \
+ " SUB A0StP, A0StP, #40\n" \
" .section .fixup,\"ax\"\n" \
- "4:\n" \
- " ADD %0, %0, #4\n" \
- "3:\n" \
- " MOV D0Ar2, TXSTATUS\n" \
+ "3: MOV D0Ar2, TXSTATUS\n" \
" MOV D1Ar1, TXSTATUS\n" \
" AND D1Ar1, D1Ar1, #0xFFFFF8FF\n" \
" MOV TXSTATUS, D1Ar1\n" \
FIXUP \
- " MOVT D0Ar2,#HI(1b)\n" \
- " JUMP D0Ar2,#LO(1b)\n" \
+ " MOVT D0Ar2, #HI(1b)\n" \
+ " JUMP D0Ar2, #LO(1b)\n" \
" .previous\n" \
" .section __ex_table,\"a\"\n" \
" .long 21b,3b\n" \
" .long 42b,3b\n" \
" .long 43b,3b\n" \
" .long 44b,3b\n" \
- " .long 45b,4b\n" \
" .previous\n" \
: "=r" (to), "=r" (from), "=r" (ret), "=d" (n) \
: "0" (to), "1" (from), "2" (ret), "3" (n) \
}
EXPORT_SYMBOL(__get_user_asm_d);
+unsigned long long __get_user_asm_l(const void __user *addr, long *err)
+{
+ register unsigned long long x asm ("D0Re0") = 0;
+ asm volatile (
+ " GETL %0,%t0,[%2]\n"
+ "1:\n"
+ " GETL %0,%t0,[%2]\n"
+ "2:\n"
+ " .section .fixup,\"ax\"\n"
+ "3: MOV D0FrT,%3\n"
+ " SETD [%1],D0FrT\n"
+ " MOVT D0FrT,#HI(2b)\n"
+ " JUMP D0FrT,#LO(2b)\n"
+ " .previous\n"
+ " .section __ex_table,\"a\"\n"
+ " .long 1b,3b\n"
+ " .previous\n"
+ : "=r" (x)
+ : "r" (err), "r" (addr), "P" (-EFAULT)
+ : "D0FrT");
+ return x;
+}
+EXPORT_SYMBOL(__get_user_asm_l);
+
long __put_user_asm_b(unsigned int x, void __user *addr)
{
register unsigned int err asm ("D0Re0") = 0;
p_swapper_pg_dir++;
addr += PGDIR_SIZE;
- entry++;
}
}
include include/uapi/asm-generic/Kbuild.asm
generic-y += types.h
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += elf.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += unistd.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += ipcbuf.h
-
-header-y += auxvec.h
-header-y += bitfield.h
-header-y += bitsperlong.h
-header-y += break.h
-header-y += byteorder.h
-header-y += cachectl.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += inst.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += sgidefs.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += sysmips.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
+# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += elf.h
-
+generic-y += setup.h
generic-y += ucontext.h
-
-header-y += ucontext.h
-
generic-y += auxvec.h
generic-y += barrier.h
generic-y += bitsperlong.h
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += byteorder.h
-header-y += elf.h
-header-y += kvm_para.h
-header-y += param.h
-header-y += ptrace.h
-header-y += sigcontext.h
-header-y += unistd.h
include include/uapi/asm-generic/Kbuild.asm
generic-y += resource.h
-
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += pdc.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
select ARCH_USE_BUILTIN_BSWAP
select ARCH_USE_CMPXCHG_LOCKREF if PPC64
select ARCH_WANT_IPC_PARSE_VERSION
+ select ARCH_WEAK_RELEASE_ACQUIRE
select BINFMT_ELF
select BUILDTIME_EXTABLE_SORT
select CLONE_BACKWARDS
struct kvm_vcpu *kvm_vcpu;
struct kvmppc_vcore *kvm_vcore;
void __iomem *xics_phys;
+ void __iomem *xive_tima_phys;
+ void __iomem *xive_tima_virt;
u32 saved_xirr;
u64 dabr;
u64 host_mmcr[7]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER */
/* XICS components, defined in book3s_xics.c */
struct kvmppc_xics;
struct kvmppc_icp;
+extern struct kvm_device_ops kvm_xics_ops;
+
+/* XIVE components, defined in book3s_xive.c */
+struct kvmppc_xive;
+struct kvmppc_xive_vcpu;
+extern struct kvm_device_ops kvm_xive_ops;
struct kvmppc_passthru_irqmap;
#endif
#ifdef CONFIG_KVM_XICS
struct kvmppc_xics *xics;
+ struct kvmppc_xive *xive;
struct kvmppc_passthru_irqmap *pimap;
#endif
struct kvmppc_ops *kvm_ops;
#define KVMPPC_IRQ_DEFAULT 0
#define KVMPPC_IRQ_MPIC 1
-#define KVMPPC_IRQ_XICS 2
+#define KVMPPC_IRQ_XICS 2 /* Includes a XIVE option */
#define MMIO_HPTE_CACHE_SIZE 4
struct openpic;
+/* W0 and W1 of a XIVE thread management context */
+union xive_tma_w01 {
+ struct {
+ u8 nsr;
+ u8 cppr;
+ u8 ipb;
+ u8 lsmfb;
+ u8 ack;
+ u8 inc;
+ u8 age;
+ u8 pipr;
+ };
+ __be64 w01;
+};
+
struct kvm_vcpu_arch {
ulong host_stack;
u32 host_pid;
struct openpic *mpic; /* KVM_IRQ_MPIC */
#ifdef CONFIG_KVM_XICS
struct kvmppc_icp *icp; /* XICS presentation controller */
+ struct kvmppc_xive_vcpu *xive_vcpu; /* XIVE virtual CPU data */
+ __be32 xive_cam_word; /* Cooked W2 in proper endian with valid bit */
+ u32 xive_pushed; /* Is the VP pushed on the physical CPU ? */
+ union xive_tma_w01 xive_saved_state; /* W0..1 of XIVE thread state */
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
extern int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp);
extern int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu);
extern void kvmppc_rtas_tokens_free(struct kvm *kvm);
+
extern int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server,
u32 priority);
extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server,
paca[cpu].kvm_hstate.xics_phys = (void __iomem *)addr;
}
+static inline void kvmppc_set_xive_tima(int cpu,
+ unsigned long phys_addr,
+ void __iomem *virt_addr)
+{
+ paca[cpu].kvm_hstate.xive_tima_phys = (void __iomem *)phys_addr;
+ paca[cpu].kvm_hstate.xive_tima_virt = virt_addr;
+}
+
static inline u32 kvmppc_get_xics_latch(void)
{
u32 xirr;
static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
{}
+static inline void kvmppc_set_xive_tima(int cpu,
+ unsigned long phys_addr,
+ void __iomem *virt_addr)
+{}
+
static inline u32 kvmppc_get_xics_latch(void)
{
return 0;
struct kvmppc_irq_map *irq_map,
struct kvmppc_passthru_irqmap *pimap,
bool *again);
+
+extern int kvmppc_xics_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status);
+
extern int h_ipi_redirect;
#else
static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap(
{ return 0; }
#endif
+#ifdef CONFIG_KVM_XIVE
+/*
+ * Below the first "xive" is the "eXternal Interrupt Virtualization Engine"
+ * ie. P9 new interrupt controller, while the second "xive" is the legacy
+ * "eXternal Interrupt Vector Entry" which is the configuration of an
+ * interrupt on the "xics" interrupt controller on P8 and earlier. Those
+ * two function consume or produce a legacy "XIVE" state from the
+ * new "XIVE" interrupt controller.
+ */
+extern int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority);
+extern int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority);
+extern int kvmppc_xive_int_on(struct kvm *kvm, u32 irq);
+extern int kvmppc_xive_int_off(struct kvm *kvm, u32 irq);
+extern void kvmppc_xive_init_module(void);
+extern void kvmppc_xive_exit_module(void);
+
+extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu);
+extern void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu);
+extern int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc);
+extern int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc);
+extern u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu);
+extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
+
+extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status);
+#else
+static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority) { return -1; }
+static inline int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority) { return -1; }
+static inline int kvmppc_xive_int_on(struct kvm *kvm, u32 irq) { return -1; }
+static inline int kvmppc_xive_int_off(struct kvm *kvm, u32 irq) { return -1; }
+static inline void kvmppc_xive_init_module(void) { }
+static inline void kvmppc_xive_exit_module(void) { }
+
+static inline int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
+static inline void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
+static inline int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc) { return -ENODEV; }
+static inline int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc) { return -ENODEV; }
+static inline u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu) { return 0; }
+static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { return -ENOENT; }
+
+static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status) { return -ENODEV; }
+#endif /* CONFIG_KVM_XIVE */
+
/*
* Prototypes for functions called only from assembler code.
* Having prototypes reduces sparse errors.
long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
unsigned long slb_v, unsigned int status, bool data);
unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);
+unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu);
+unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
unsigned long mfrr);
int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
#define XIVE_ESB_SET_PQ_01 0xd00
#define XIVE_ESB_SET_PQ_10 0xe00
#define XIVE_ESB_SET_PQ_11 0xf00
-#define XIVE_ESB_MASK XIVE_ESB_SET_PQ_01
#define XIVE_ESB_VAL_P 0x2
#define XIVE_ESB_VAL_Q 0x1
__be32 *qpage, u32 order, bool can_escalate);
extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
-extern bool __xive_irq_trigger(struct xive_irq_data *xd);
-extern bool __xive_irq_retrigger(struct xive_irq_data *xd);
-extern void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd);
-
+extern void xive_native_sync_source(u32 hw_irq);
extern bool is_xive_irq(struct irq_chip *chip);
+extern int xive_native_enable_vp(u32 vp_id);
+extern int xive_native_disable_vp(u32 vp_id);
+extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
#else
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += bootx.h
-header-y += byteorder.h
-header-y += cputable.h
-header-y += eeh.h
-header-y += elf.h
-header-y += epapr_hcalls.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += nvram.h
-header-y += opal-prd.h
-header-y += param.h
-header-y += perf_event.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ps3fb.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += spu_info.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += tm.h
-header-y += types.h
-header-y += ucontext.h
-header-y += unistd.h
HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
+ HSTATE_FIELD(HSTATE_XIVE_TIMA_PHYS, xive_tima_phys);
+ HSTATE_FIELD(HSTATE_XIVE_TIMA_VIRT, xive_tima_virt);
HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
HSTATE_FIELD(HSTATE_PTID, ptid);
OFFSET(VCPU_HOST_MAS6, kvm_vcpu, arch.host_mas6);
#endif
+#ifdef CONFIG_KVM_XICS
+ DEFINE(VCPU_XIVE_SAVED_STATE, offsetof(struct kvm_vcpu,
+ arch.xive_saved_state));
+ DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu,
+ arch.xive_cam_word));
+ DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed));
+#endif
+
#ifdef CONFIG_KVM_EXIT_TIMING
OFFSET(VCPU_TIMING_EXIT_TBU, kvm_vcpu, arch.timing_exit.tv32.tbu);
OFFSET(VCPU_TIMING_EXIT_TBL, kvm_vcpu, arch.timing_exit.tv32.tbl);
Specification) interrupt controller architecture used on
IBM POWER (pSeries) servers.
+config KVM_XIVE
+ bool
+ default y
+ depends on KVM_XICS && PPC_XIVE_NATIVE && KVM_BOOK3S_HV_POSSIBLE
+
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
book3s_64_mmu_radix.o
kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
- book3s_hv_rm_xics.o
+ book3s_hv_rm_xics.o book3s_hv_rm_xive.o
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
book3s_xics.o
+kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+
kvm-book3s_64-module-objs := \
$(common-objs-y) \
book3s.o \
#include <asm/kvm_book3s.h>
#include <asm/mmu_context.h>
#include <asm/page.h>
+#include <asm/xive.h>
#include "book3s.h"
#include "trace.h"
break;
#ifdef CONFIG_KVM_XICS
case KVM_REG_PPC_ICP_STATE:
- if (!vcpu->arch.icp) {
+ if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
r = -ENXIO;
break;
}
- *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
+ if (xive_enabled())
+ *val = get_reg_val(id, kvmppc_xive_get_icp(vcpu));
+ else
+ *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
break;
#endif /* CONFIG_KVM_XICS */
case KVM_REG_PPC_FSCR:
#endif /* CONFIG_VSX */
#ifdef CONFIG_KVM_XICS
case KVM_REG_PPC_ICP_STATE:
- if (!vcpu->arch.icp) {
+ if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
r = -ENXIO;
break;
}
- r = kvmppc_xics_set_icp(vcpu,
- set_reg_val(id, *val));
+ if (xive_enabled())
+ r = kvmppc_xive_set_icp(vcpu, set_reg_val(id, *val));
+ else
+ r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
break;
#endif /* CONFIG_KVM_XICS */
case KVM_REG_PPC_FSCR:
return kvm->arch.kvm_ops->hcall_implemented(hcall);
}
+#ifdef CONFIG_KVM_XICS
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
+{
+ if (xive_enabled())
+ return kvmppc_xive_set_irq(kvm, irq_source_id, irq, level,
+ line_status);
+ else
+ return kvmppc_xics_set_irq(kvm, irq_source_id, irq, level,
+ line_status);
+}
+
+int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
+ struct kvm *kvm, int irq_source_id,
+ int level, bool line_status)
+{
+ return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
+ level, line_status);
+}
+static int kvmppc_book3s_set_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
+}
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries, int gsi)
+{
+ entries->gsi = gsi;
+ entries->type = KVM_IRQ_ROUTING_IRQCHIP;
+ entries->set = kvmppc_book3s_set_irq;
+ entries->irqchip.irqchip = 0;
+ entries->irqchip.pin = gsi;
+ return 1;
+}
+
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ return pin;
+}
+
+#endif /* CONFIG_KVM_XICS */
+
static int kvmppc_book3s_init(void)
{
int r;
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
r = kvmppc_book3s_init_pr();
#endif
- return r;
+#ifdef CONFIG_KVM_XICS
+#ifdef CONFIG_KVM_XIVE
+ if (xive_enabled()) {
+ kvmppc_xive_init_module();
+ kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
+ } else
+#endif
+ kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
+#endif
+ return r;
}
static void kvmppc_book3s_exit(void)
{
+#ifdef CONFIG_KVM_XICS
+ if (xive_enabled())
+ kvmppc_xive_exit_module();
+#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
kvmppc_book3s_exit_pr();
#endif
#include <asm/mmu.h>
#include <asm/opal.h>
#include <asm/xics.h>
+#include <asm/xive.h>
#include "book3s.h"
case H_IPOLL:
case H_XIRR_X:
if (kvmppc_xics_enabled(vcpu)) {
+ if (xive_enabled()) {
+ ret = H_NOT_AVAILABLE;
+ return RESUME_GUEST;
+ }
ret = kvmppc_xics_hcall(vcpu, req);
break;
}
r = kvmppc_book3s_hv_page_fault(run, vcpu,
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
- } else if (r == RESUME_PASSTHROUGH)
- r = kvmppc_xics_rm_complete(vcpu, 0);
+ } else if (r == RESUME_PASSTHROUGH) {
+ if (WARN_ON(xive_enabled()))
+ r = H_SUCCESS;
+ else
+ r = kvmppc_xics_rm_complete(vcpu, 0);
+ }
} while (is_kvmppc_resume_guest(r));
out:
/*
* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
* Set HVICE bit to enable hypervisor virtualization interrupts.
+ * Set HEIC to prevent OS interrupts to go to hypervisor (should
+ * be unnecessary but better safe than sorry in case we re-enable
+ * EE in HV mode with this LPCR still set)
*/
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
lpcr &= ~LPCR_VPM0;
- lpcr |= LPCR_HVICE;
+ lpcr |= LPCR_HVICE | LPCR_HEIC;
+
+ /*
+ * If xive is enabled, we route 0x500 interrupts directly
+ * to the guest.
+ */
+ if (xive_enabled())
+ lpcr |= LPCR_LPES;
}
/*
struct kvmppc_irq_map *irq_map;
struct kvmppc_passthru_irqmap *pimap;
struct irq_chip *chip;
- int i;
+ int i, rc = 0;
if (!kvm_irq_bypass)
return 1;
/*
* For now, we only support interrupts for which the EOI operation
* is an OPAL call followed by a write to XIRR, since that's
- * what our real-mode EOI code does.
+ * what our real-mode EOI code does, or a XIVE interrupt
*/
chip = irq_data_get_irq_chip(&desc->irq_data);
- if (!chip || !is_pnv_opal_msi(chip)) {
+ if (!chip || !(is_pnv_opal_msi(chip) || is_xive_irq(chip))) {
pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n",
host_irq, guest_gsi);
mutex_unlock(&kvm->lock);
if (i == pimap->n_mapped)
pimap->n_mapped++;
- kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+ if (xive_enabled())
+ rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
+ else
+ kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+ if (rc)
+ irq_map->r_hwirq = 0;
mutex_unlock(&kvm->lock);
{
struct irq_desc *desc;
struct kvmppc_passthru_irqmap *pimap;
- int i;
+ int i, rc = 0;
if (!kvm_irq_bypass)
return 0;
return -ENODEV;
}
- kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
+ if (xive_enabled())
+ rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc);
+ else
+ kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
- /* invalidate the entry */
+ /* invalidate the entry (what do do on error from the above ?) */
pimap->mapped[i].r_hwirq = 0;
/*
*/
unlock:
mutex_unlock(&kvm->lock);
- return 0;
+ return rc;
}
static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons,
* indirectly, via OPAL.
*/
#ifdef CONFIG_SMP
- if (!get_paca()->kvm_hstate.xics_phys) {
+ if (!xive_enabled() && !local_paca->kvm_hstate.xics_phys) {
struct device_node *np;
np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
#define KVM_CMA_CHUNK_ORDER 18
+#include "book3s_xics.h"
+#include "book3s_xive.h"
+
+/*
+ * The XIVE module will populate these when it loads
+ */
+unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
+unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
+int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
+int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_xirr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_ipoll);
+EXPORT_SYMBOL_GPL(__xive_vm_h_ipi);
+EXPORT_SYMBOL_GPL(__xive_vm_h_cppr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_eoi);
+
/*
* Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
* should be power of 2.
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
return;
}
+
/* On POWER8 for IPIs to threads in the same core, use msgsnd. */
if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
cpu_first_thread_sibling(cpu) ==
u8 host_ipi;
int64_t rc;
+ if (xive_enabled())
+ return 1;
+
/* see if a host IPI is pending */
host_ipi = local_paca->kvm_hstate.host_ipi;
if (host_ipi)
return kvmppc_check_passthru(xisr, xirr, again);
}
+
+#ifdef CONFIG_KVM_XICS
+static inline bool is_rm(void)
+{
+ return !(mfmsr() & MSR_DR);
+}
+
+unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_xirr(vcpu);
+ if (unlikely(!__xive_vm_h_xirr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_xirr(vcpu);
+ } else
+ return xics_rm_h_xirr(vcpu);
+}
+
+unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.gpr[5] = get_tb();
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_xirr(vcpu);
+ if (unlikely(!__xive_vm_h_xirr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_xirr(vcpu);
+ } else
+ return xics_rm_h_xirr(vcpu);
+}
+
+unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_ipoll(vcpu, server);
+ if (unlikely(!__xive_vm_h_ipoll))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_ipoll(vcpu, server);
+ } else
+ return H_TOO_HARD;
+}
+
+int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_ipi(vcpu, server, mfrr);
+ if (unlikely(!__xive_vm_h_ipi))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_ipi(vcpu, server, mfrr);
+ } else
+ return xics_rm_h_ipi(vcpu, server, mfrr);
+}
+
+int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_cppr(vcpu, cppr);
+ if (unlikely(!__xive_vm_h_cppr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_cppr(vcpu, cppr);
+ } else
+ return xics_rm_h_cppr(vcpu, cppr);
+}
+
+int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_eoi(vcpu, xirr);
+ if (unlikely(!__xive_vm_h_eoi))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_eoi(vcpu, xirr);
+ } else
+ return xics_rm_h_eoi(vcpu, xirr);
+}
+#endif /* CONFIG_KVM_XICS */
}
-unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
+unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
return check_too_hard(xics, icp);
}
-int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
- unsigned long mfrr)
+int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
return check_too_hard(xics, this_icp);
}
-int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
+int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
return check_too_hard(xics, icp);
}
-int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
+int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
{
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
struct kvmppc_icp *icp = vcpu->arch.icp;
--- /dev/null
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/kernel_stat.h>
+
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xics.h>
+#include <asm/debug.h>
+#include <asm/synch.h>
+#include <asm/cputhreads.h>
+#include <asm/pgtable.h>
+#include <asm/ppc-opcode.h>
+#include <asm/pnv-pci.h>
+#include <asm/opal.h>
+#include <asm/smp.h>
+#include <asm/asm-prototypes.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+
+#include "book3s_xive.h"
+
+/* XXX */
+#include <asm/udbg.h>
+//#define DBG(fmt...) udbg_printf(fmt)
+#define DBG(fmt...) do { } while(0)
+
+static inline void __iomem *get_tima_phys(void)
+{
+ return local_paca->kvm_hstate.xive_tima_phys;
+}
+
+#undef XIVE_RUNTIME_CHECKS
+#define X_PFX xive_rm_
+#define X_STATIC
+#define X_STAT_PFX stat_rm_
+#define __x_tima get_tima_phys()
+#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_page))
+#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_page))
+#define __x_readb __raw_rm_readb
+#define __x_writeb __raw_rm_writeb
+#define __x_readw __raw_rm_readw
+#define __x_readq __raw_rm_readq
+#define __x_writeq __raw_rm_writeq
+
+#include "book3s_xive_template.c"
#include <asm/book3s/64/mmu-hash.h>
#include <asm/tm.h>
#include <asm/opal.h>
+#include <asm/xive-regs.h>
#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
cmpwi r3, 512 /* 1 microsecond */
blt hdec_soon
+#ifdef CONFIG_KVM_XICS
+ /* We are entering the guest on that thread, push VCPU to XIVE */
+ ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
+ cmpldi cr0, r10, r0
+ beq no_xive
+ ld r11, VCPU_XIVE_SAVED_STATE(r4)
+ li r9, TM_QW1_OS
+ stdcix r11,r9,r10
+ eieio
+ lwz r11, VCPU_XIVE_CAM_WORD(r4)
+ li r9, TM_QW1_OS + TM_WORD2
+ stwcix r11,r9,r10
+ li r9, 1
+ stw r9, VCPU_XIVE_PUSHED(r4)
+no_xive:
+#endif /* CONFIG_KVM_XICS */
+
deliver_guest_interrupt:
ld r6, VCPU_CTR(r4)
ld r7, VCPU_XER(r4)
blt deliver_guest_interrupt
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
+#ifdef CONFIG_KVM_XICS
+ /* We are exiting, pull the VP from the XIVE */
+ lwz r0, VCPU_XIVE_PUSHED(r9)
+ cmpwi cr0, r0, 0
+ beq 1f
+ li r7, TM_SPC_PULL_OS_CTX
+ li r6, TM_QW1_OS
+ mfmsr r0
+ andi. r0, r0, MSR_IR /* in real mode? */
+ beq 2f
+ ld r10, HSTATE_XIVE_TIMA_VIRT(r13)
+ cmpldi cr0, r10, 0
+ beq 1f
+ /* First load to pull the context, we ignore the value */
+ lwzx r11, r7, r10
+ eieio
+ /* Second load to recover the context state (Words 0 and 1) */
+ ldx r11, r6, r10
+ b 3f
+2: ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
+ cmpldi cr0, r10, 0
+ beq 1f
+ /* First load to pull the context, we ignore the value */
+ lwzcix r11, r7, r10
+ eieio
+ /* Second load to recover the context state (Words 0 and 1) */
+ ldcix r11, r6, r10
+3: std r11, VCPU_XIVE_SAVED_STATE(r9)
+ /* Fixup some of the state for the next load */
+ li r10, 0
+ li r0, 0xff
+ stw r10, VCPU_XIVE_PUSHED(r9)
+ stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
+ stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
+1:
+#endif /* CONFIG_KVM_XICS */
/* Save more register state */
mfdar r6
mfdsisr r7
.long DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
- .long 0 /* 0x70 - H_IPOLL */
+ .long DOTSYM(kvmppc_rm_h_ipoll) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table
#else
.long 0 /* 0x64 - H_EOI */
.long 0 /* 0x2f0 */
.long 0 /* 0x2f4 */
.long 0 /* 0x2f8 */
- .long 0 /* 0x2fc */
+#ifdef CONFIG_KVM_XICS
+ .long DOTSYM(kvmppc_rm_h_xirr_x) - hcall_real_table
+#else
+ .long 0 /* 0x2fc - H_XIRR_X*/
+#endif
.long DOTSYM(kvmppc_h_random) - hcall_real_table
.globl hcall_real_table_end
hcall_real_table_end:
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/rtas.h>
+#include <asm/xive.h>
#ifdef CONFIG_KVM_XICS
static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
server = be32_to_cpu(args->args[1]);
priority = be32_to_cpu(args->args[2]);
- rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
+ if (xive_enabled())
+ rc = kvmppc_xive_set_xive(vcpu->kvm, irq, server, priority);
+ else
+ rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
if (rc)
rc = -3;
out:
irq = be32_to_cpu(args->args[0]);
server = priority = 0;
- rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
+ if (xive_enabled())
+ rc = kvmppc_xive_get_xive(vcpu->kvm, irq, &server, &priority);
+ else
+ rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
if (rc) {
rc = -3;
goto out;
irq = be32_to_cpu(args->args[0]);
- rc = kvmppc_xics_int_off(vcpu->kvm, irq);
+ if (xive_enabled())
+ rc = kvmppc_xive_int_off(vcpu->kvm, irq);
+ else
+ rc = kvmppc_xics_int_off(vcpu->kvm, irq);
if (rc)
rc = -3;
out:
irq = be32_to_cpu(args->args[0]);
- rc = kvmppc_xics_int_on(vcpu->kvm, irq);
+ if (xive_enabled())
+ rc = kvmppc_xive_int_on(vcpu->kvm, irq);
+ else
+ rc = kvmppc_xics_int_on(vcpu->kvm, irq);
if (rc)
rc = -3;
out:
return 0;
}
-int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
- bool line_status)
+int kvmppc_xics_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
{
struct kvmppc_xics *xics = kvm->arch.xics;
return ics_deliver_irq(xics, irq, level);
}
-int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
- struct kvm *kvm, int irq_source_id,
- int level, bool line_status)
-{
- return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
- level, line_status);
-}
-
static int xics_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
struct kvmppc_xics *xics = dev->private;
vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
}
-static int xics_set_irq(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
-}
-
-int kvm_irq_map_gsi(struct kvm *kvm,
- struct kvm_kernel_irq_routing_entry *entries, int gsi)
-{
- entries->gsi = gsi;
- entries->type = KVM_IRQ_ROUTING_IRQCHIP;
- entries->set = xics_set_irq;
- entries->irqchip.irqchip = 0;
- entries->irqchip.pin = gsi;
- return 1;
-}
-
-int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
- return pin;
-}
-
void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long irq,
unsigned long host_irq)
{
#ifndef _KVM_PPC_BOOK3S_XICS_H
#define _KVM_PPC_BOOK3S_XICS_H
+#ifdef CONFIG_KVM_XICS
/*
* We use a two-level tree to store interrupt source information.
* There are up to 1024 ICS nodes, each of which can represent
return ics;
}
+extern unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu);
+extern int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+#endif /* CONFIG_KVM_XICS */
#endif /* _KVM_PPC_BOOK3S_XICS_H */
--- /dev/null
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "xive-kvm: " fmt
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xics.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/time.h>
+#include <asm/opal.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "book3s_xive.h"
+
+
+/*
+ * Virtual mode variants of the hcalls for use on radix/radix
+ * with AIL. They require the VCPU's VP to be "pushed"
+ *
+ * We still instanciate them here because we use some of the
+ * generated utility functions as well in this file.
+ */
+#define XIVE_RUNTIME_CHECKS
+#define X_PFX xive_vm_
+#define X_STATIC static
+#define X_STAT_PFX stat_vm_
+#define __x_tima xive_tima
+#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_mmio))
+#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_mmio))
+#define __x_readb __raw_readb
+#define __x_writeb __raw_writeb
+#define __x_readw __raw_readw
+#define __x_readq __raw_readq
+#define __x_writeq __raw_writeq
+
+#include "book3s_xive_template.c"
+
+/*
+ * We leave a gap of a couple of interrupts in the queue to
+ * account for the IPI and additional safety guard.
+ */
+#define XIVE_Q_GAP 2
+
+/*
+ * This is a simple trigger for a generic XIVE IRQ. This must
+ * only be called for interrupts that support a trigger page
+ */
+static bool xive_irq_trigger(struct xive_irq_data *xd)
+{
+ /* This should be only for MSIs */
+ if (WARN_ON(xd->flags & XIVE_IRQ_FLAG_LSI))
+ return false;
+
+ /* Those interrupts should always have a trigger page */
+ if (WARN_ON(!xd->trig_mmio))
+ return false;
+
+ out_be64(xd->trig_mmio, 0);
+
+ return true;
+}
+
+static irqreturn_t xive_esc_irq(int irq, void *data)
+{
+ struct kvm_vcpu *vcpu = data;
+
+ /* We use the existing H_PROD mechanism to wake up the target */
+ vcpu->arch.prodded = 1;
+ smp_mb();
+ if (vcpu->arch.ceded)
+ kvmppc_fast_vcpu_kick(vcpu);
+
+ return IRQ_HANDLED;
+}
+
+static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_q *q = &xc->queues[prio];
+ char *name = NULL;
+ int rc;
+
+ /* Already there ? */
+ if (xc->esc_virq[prio])
+ return 0;
+
+ /* Hook up the escalation interrupt */
+ xc->esc_virq[prio] = irq_create_mapping(NULL, q->esc_irq);
+ if (!xc->esc_virq[prio]) {
+ pr_err("Failed to map escalation interrupt for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ return -EIO;
+ }
+
+ /*
+ * Future improvement: start with them disabled
+ * and handle DD2 and later scheme of merged escalation
+ * interrupts
+ */
+ name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
+ vcpu->kvm->arch.lpid, xc->server_num, prio);
+ if (!name) {
+ pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ rc = -ENOMEM;
+ goto error;
+ }
+ rc = request_irq(xc->esc_virq[prio], xive_esc_irq,
+ IRQF_NO_THREAD, name, vcpu);
+ if (rc) {
+ pr_err("Failed to request escalation interrupt for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ goto error;
+ }
+ xc->esc_virq_names[prio] = name;
+ return 0;
+error:
+ irq_dispose_mapping(xc->esc_virq[prio]);
+ xc->esc_virq[prio] = 0;
+ kfree(name);
+ return rc;
+}
+
+static int xive_provision_queue(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = xc->xive;
+ struct xive_q *q = &xc->queues[prio];
+ void *qpage;
+ int rc;
+
+ if (WARN_ON(q->qpage))
+ return 0;
+
+ /* Allocate the queue and retrieve infos on current node for now */
+ qpage = (__be32 *)__get_free_pages(GFP_KERNEL, xive->q_page_order);
+ if (!qpage) {
+ pr_err("Failed to allocate queue %d for VCPU %d\n",
+ prio, xc->server_num);
+ return -ENOMEM;;
+ }
+ memset(qpage, 0, 1 << xive->q_order);
+
+ /*
+ * Reconfigure the queue. This will set q->qpage only once the
+ * queue is fully configured. This is a requirement for prio 0
+ * as we will stop doing EOIs for every IPI as soon as we observe
+ * qpage being non-NULL, and instead will only EOI when we receive
+ * corresponding queue 0 entries
+ */
+ rc = xive_native_configure_queue(xc->vp_id, q, prio, qpage,
+ xive->q_order, true);
+ if (rc)
+ pr_err("Failed to configure queue %d for VCPU %d\n",
+ prio, xc->server_num);
+ return rc;
+}
+
+/* Called with kvm_lock held */
+static int xive_check_provisioning(struct kvm *kvm, u8 prio)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvm_vcpu *vcpu;
+ int i, rc;
+
+ lockdep_assert_held(&kvm->lock);
+
+ /* Already provisioned ? */
+ if (xive->qmap & (1 << prio))
+ return 0;
+
+ pr_devel("Provisioning prio... %d\n", prio);
+
+ /* Provision each VCPU and enable escalations */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!vcpu->arch.xive_vcpu)
+ continue;
+ rc = xive_provision_queue(vcpu, prio);
+ if (rc == 0)
+ xive_attach_escalation(vcpu, prio);
+ if (rc)
+ return rc;
+ }
+
+ /* Order previous stores and mark it as provisioned */
+ mb();
+ xive->qmap |= (1 << prio);
+ return 0;
+}
+
+static void xive_inc_q_pending(struct kvm *kvm, u32 server, u8 prio)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvmppc_xive_vcpu *xc;
+ struct xive_q *q;
+
+ /* Locate target server */
+ vcpu = kvmppc_xive_find_server(kvm, server);
+ if (!vcpu) {
+ pr_warn("%s: Can't find server %d\n", __func__, server);
+ return;
+ }
+ xc = vcpu->arch.xive_vcpu;
+ if (WARN_ON(!xc))
+ return;
+
+ q = &xc->queues[prio];
+ atomic_inc(&q->pending_count);
+}
+
+static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_q *q;
+ u32 max;
+
+ if (WARN_ON(!xc))
+ return -ENXIO;
+ if (!xc->valid)
+ return -ENXIO;
+
+ q = &xc->queues[prio];
+ if (WARN_ON(!q->qpage))
+ return -ENXIO;
+
+ /* Calculate max number of interrupts in that queue. */
+ max = (q->msk + 1) - XIVE_Q_GAP;
+ return atomic_add_unless(&q->count, 1, max) ? 0 : -EBUSY;
+}
+
+static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
+{
+ struct kvm_vcpu *vcpu;
+ int i, rc;
+
+ /* Locate target server */
+ vcpu = kvmppc_xive_find_server(kvm, *server);
+ if (!vcpu) {
+ pr_devel("Can't find server %d\n", *server);
+ return -EINVAL;
+ }
+
+ pr_devel("Finding irq target on 0x%x/%d...\n", *server, prio);
+
+ /* Try pick it */
+ rc = xive_try_pick_queue(vcpu, prio);
+ if (rc == 0)
+ return rc;
+
+ pr_devel(" .. failed, looking up candidate...\n");
+
+ /* Failed, pick another VCPU */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!vcpu->arch.xive_vcpu)
+ continue;
+ rc = xive_try_pick_queue(vcpu, prio);
+ if (rc == 0) {
+ *server = vcpu->arch.xive_vcpu->server_num;
+ pr_devel(" found on 0x%x/%d\n", *server, prio);
+ return rc;
+ }
+ }
+ pr_devel(" no available target !\n");
+
+ /* No available target ! */
+ return -EBUSY;
+}
+
+static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state)
+{
+ struct xive_irq_data *xd;
+ u32 hw_num;
+ u8 old_prio;
+ u64 val;
+
+ /*
+ * Take the lock, set masked, try again if racing
+ * with H_EOI
+ */
+ for (;;) {
+ arch_spin_lock(&sb->lock);
+ old_prio = state->guest_priority;
+ state->guest_priority = MASKED;
+ mb();
+ if (!state->in_eoi)
+ break;
+ state->guest_priority = old_prio;
+ arch_spin_unlock(&sb->lock);
+ }
+
+ /* No change ? Bail */
+ if (old_prio == MASKED)
+ return old_prio;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ /*
+ * If the interrupt is marked as needing masking via
+ * firmware, we do it here. Firmware masking however
+ * is "lossy", it won't return the old p and q bits
+ * and won't set the interrupt to a state where it will
+ * record queued ones. If this is an issue we should do
+ * lazy masking instead.
+ *
+ * For now, we work around this in unmask by forcing
+ * an interrupt whenever we unmask a non-LSI via FW
+ * (if ever).
+ */
+ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
+ xive_native_configure_irq(hw_num,
+ xive->vp_base + state->act_server,
+ MASKED, state->number);
+ /* set old_p so we can track if an H_EOI was done */
+ state->old_p = true;
+ state->old_q = false;
+ } else {
+ /* Set PQ to 10, return old P and old Q and remember them */
+ val = xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_10);
+ state->old_p = !!(val & 2);
+ state->old_q = !!(val & 1);
+
+ /*
+ * Synchronize hardware to sensure the queues are updated
+ * when masking
+ */
+ xive_native_sync_source(hw_num);
+ }
+
+ return old_prio;
+}
+
+static void xive_lock_for_unmask(struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state)
+{
+ /*
+ * Take the lock try again if racing with H_EOI
+ */
+ for (;;) {
+ arch_spin_lock(&sb->lock);
+ if (!state->in_eoi)
+ break;
+ arch_spin_unlock(&sb->lock);
+ }
+}
+
+static void xive_finish_unmask(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state,
+ u8 prio)
+{
+ struct xive_irq_data *xd;
+ u32 hw_num;
+
+ /* If we aren't changing a thing, move on */
+ if (state->guest_priority != MASKED)
+ goto bail;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ /*
+ * See command in xive_lock_and_mask() concerning masking
+ * via firmware.
+ */
+ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
+ xive_native_configure_irq(hw_num,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+ /* If an EOI is needed, do it here */
+ if (!state->old_p)
+ xive_vm_source_eoi(hw_num, xd);
+ /* If this is not an LSI, force a trigger */
+ if (!(xd->flags & OPAL_XIVE_IRQ_LSI))
+ xive_irq_trigger(xd);
+ goto bail;
+ }
+
+ /* Old Q set, set PQ to 11 */
+ if (state->old_q)
+ xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_11);
+
+ /*
+ * If not old P, then perform an "effective" EOI,
+ * on the source. This will handle the cases where
+ * FW EOI is needed.
+ */
+ if (!state->old_p)
+ xive_vm_source_eoi(hw_num, xd);
+
+ /* Synchronize ordering and mark unmasked */
+ mb();
+bail:
+ state->guest_priority = prio;
+}
+
+/*
+ * Target an interrupt to a given server/prio, this will fallback
+ * to another server if necessary and perform the HW targetting
+ * updates as needed
+ *
+ * NOTE: Must be called with the state lock held
+ */
+static int xive_target_interrupt(struct kvm *kvm,
+ struct kvmppc_xive_irq_state *state,
+ u32 server, u8 prio)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ u32 hw_num;
+ int rc;
+
+ /*
+ * This will return a tentative server and actual
+ * priority. The count for that new target will have
+ * already been incremented.
+ */
+ rc = xive_select_target(kvm, &server, prio);
+
+ /*
+ * We failed to find a target ? Not much we can do
+ * at least until we support the GIQ.
+ */
+ if (rc)
+ return rc;
+
+ /*
+ * Increment the old queue pending count if there
+ * was one so that the old queue count gets adjusted later
+ * when observed to be empty.
+ */
+ if (state->act_priority != MASKED)
+ xive_inc_q_pending(kvm,
+ state->act_server,
+ state->act_priority);
+ /*
+ * Update state and HW
+ */
+ state->act_priority = prio;
+ state->act_server = server;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, NULL);
+
+ return xive_native_configure_irq(hw_num,
+ xive->vp_base + server,
+ prio, state->number);
+}
+
+/*
+ * Targetting rules: In order to avoid losing track of
+ * pending interrupts accross mask and unmask, which would
+ * allow queue overflows, we implement the following rules:
+ *
+ * - Unless it was never enabled (or we run out of capacity)
+ * an interrupt is always targetted at a valid server/queue
+ * pair even when "masked" by the guest. This pair tends to
+ * be the last one used but it can be changed under some
+ * circumstances. That allows us to separate targetting
+ * from masking, we only handle accounting during (re)targetting,
+ * this also allows us to let an interrupt drain into its target
+ * queue after masking, avoiding complex schemes to remove
+ * interrupts out of remote processor queues.
+ *
+ * - When masking, we set PQ to 10 and save the previous value
+ * of P and Q.
+ *
+ * - When unmasking, if saved Q was set, we set PQ to 11
+ * otherwise we leave PQ to the HW state which will be either
+ * 10 if nothing happened or 11 if the interrupt fired while
+ * masked. Effectively we are OR'ing the previous Q into the
+ * HW Q.
+ *
+ * Then if saved P is clear, we do an effective EOI (Q->P->Trigger)
+ * which will unmask the interrupt and shoot a new one if Q was
+ * set.
+ *
+ * Otherwise (saved P is set) we leave PQ unchanged (so 10 or 11,
+ * effectively meaning an H_EOI from the guest is still expected
+ * for that interrupt).
+ *
+ * - If H_EOI occurs while masked, we clear the saved P.
+ *
+ * - When changing target, we account on the new target and
+ * increment a separate "pending" counter on the old one.
+ * This pending counter will be used to decrement the old
+ * target's count when its queue has been observed empty.
+ */
+
+int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u8 new_act_prio;
+ int rc = 0;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("set_xive ! irq 0x%x server 0x%x prio %d\n",
+ irq, server, priority);
+
+ /* First, check provisioning of queues */
+ if (priority != MASKED)
+ rc = xive_check_provisioning(xive->kvm,
+ xive_prio_from_guest(priority));
+ if (rc) {
+ pr_devel(" provisioning failure %d !\n", rc);
+ return rc;
+ }
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * We first handle masking/unmasking since the locking
+ * might need to be retried due to EOIs, we'll handle
+ * targetting changes later. These functions will return
+ * with the SB lock held.
+ *
+ * xive_lock_and_mask() will also set state->guest_priority
+ * but won't otherwise change other fields of the state.
+ *
+ * xive_lock_for_unmask will not actually unmask, this will
+ * be done later by xive_finish_unmask() once the targetting
+ * has been done, so we don't try to unmask an interrupt
+ * that hasn't yet been targetted.
+ */
+ if (priority == MASKED)
+ xive_lock_and_mask(xive, sb, state);
+ else
+ xive_lock_for_unmask(sb, state);
+
+
+ /*
+ * Then we handle targetting.
+ *
+ * First calculate a new "actual priority"
+ */
+ new_act_prio = state->act_priority;
+ if (priority != MASKED)
+ new_act_prio = xive_prio_from_guest(priority);
+
+ pr_devel(" new_act_prio=%x act_server=%x act_prio=%x\n",
+ new_act_prio, state->act_server, state->act_priority);
+
+ /*
+ * Then check if we actually need to change anything,
+ *
+ * The condition for re-targetting the interrupt is that
+ * we have a valid new priority (new_act_prio is not 0xff)
+ * and either the server or the priority changed.
+ *
+ * Note: If act_priority was ff and the new priority is
+ * also ff, we don't do anything and leave the interrupt
+ * untargetted. An attempt of doing an int_on on an
+ * untargetted interrupt will fail. If that is a problem
+ * we could initialize interrupts with valid default
+ */
+
+ if (new_act_prio != MASKED &&
+ (state->act_server != server ||
+ state->act_priority != new_act_prio))
+ rc = xive_target_interrupt(kvm, state, server, new_act_prio);
+
+ /*
+ * Perform the final unmasking of the interrupt source
+ * if necessary
+ */
+ if (priority != MASKED)
+ xive_finish_unmask(xive, sb, state, priority);
+
+ /*
+ * Finally Update saved_priority to match. Only int_on/off
+ * set this field to a different value.
+ */
+ state->saved_priority = priority;
+
+ arch_spin_unlock(&sb->lock);
+ return rc;
+}
+
+int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+ arch_spin_lock(&sb->lock);
+ *server = state->guest_server;
+ *priority = state->guest_priority;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+int kvmppc_xive_int_on(struct kvm *kvm, u32 irq)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ pr_devel("int_on(irq=0x%x)\n", irq);
+
+ /*
+ * Check if interrupt was not targetted
+ */
+ if (state->act_priority == MASKED) {
+ pr_devel("int_on on untargetted interrupt\n");
+ return -EINVAL;
+ }
+
+ /* If saved_priority is 0xff, do nothing */
+ if (state->saved_priority == MASKED)
+ return 0;
+
+ /*
+ * Lock and unmask it.
+ */
+ xive_lock_for_unmask(sb, state);
+ xive_finish_unmask(xive, sb, state, state->saved_priority);
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+int kvmppc_xive_int_off(struct kvm *kvm, u32 irq)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ pr_devel("int_off(irq=0x%x)\n", irq);
+
+ /*
+ * Lock and mask
+ */
+ state->saved_priority = xive_lock_and_mask(xive, sb, state);
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+static bool xive_restore_pending_irq(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return false;
+ state = &sb->irq_state[idx];
+ if (!state->valid)
+ return false;
+
+ /*
+ * Trigger the IPI. This assumes we never restore a pass-through
+ * interrupt which should be safe enough
+ */
+ xive_irq_trigger(&state->ipi_data);
+
+ return true;
+}
+
+u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ return 0;
+
+ /* Return the per-cpu state for state saving/migration */
+ return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
+ (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+}
+
+int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+ u8 cppr, mfrr;
+ u32 xisr;
+
+ if (!xc || !xive)
+ return -ENOENT;
+
+ /* Grab individual state fields. We don't use pending_pri */
+ cppr = icpval >> KVM_REG_PPC_ICP_CPPR_SHIFT;
+ xisr = (icpval >> KVM_REG_PPC_ICP_XISR_SHIFT) &
+ KVM_REG_PPC_ICP_XISR_MASK;
+ mfrr = icpval >> KVM_REG_PPC_ICP_MFRR_SHIFT;
+
+ pr_devel("set_icp vcpu %d cppr=0x%x mfrr=0x%x xisr=0x%x\n",
+ xc->server_num, cppr, mfrr, xisr);
+
+ /*
+ * We can't update the state of a "pushed" VCPU, but that
+ * shouldn't happen.
+ */
+ if (WARN_ON(vcpu->arch.xive_pushed))
+ return -EIO;
+
+ /* Update VCPU HW saved state */
+ vcpu->arch.xive_saved_state.cppr = cppr;
+ xc->hw_cppr = xc->cppr = cppr;
+
+ /*
+ * Update MFRR state. If it's not 0xff, we mark the VCPU as
+ * having a pending MFRR change, which will re-evaluate the
+ * target. The VCPU will thus potentially get a spurious
+ * interrupt but that's not a big deal.
+ */
+ xc->mfrr = mfrr;
+ if (mfrr < cppr)
+ xive_irq_trigger(&xc->vp_ipi_data);
+
+ /*
+ * Now saved XIRR is "interesting". It means there's something in
+ * the legacy "1 element" queue... for an IPI we simply ignore it,
+ * as the MFRR restore will handle that. For anything else we need
+ * to force a resend of the source.
+ * However the source may not have been setup yet. If that's the
+ * case, we keep that info and increment a counter in the xive to
+ * tell subsequent xive_set_source() to go look.
+ */
+ if (xisr > XICS_IPI && !xive_restore_pending_irq(xive, xisr)) {
+ xc->delayed_irq = xisr;
+ xive->delayed_irqs++;
+ pr_devel(" xisr restore delayed\n");
+ }
+
+ return 0;
+}
+
+int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ struct irq_data *host_data = irq_desc_get_irq_data(host_desc);
+ unsigned int host_irq = irq_desc_get_irq(host_desc);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(host_data);
+ u16 idx;
+ u8 prio;
+ int rc;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("set_mapped girq 0x%lx host HW irq 0x%x...\n",guest_irq, hw_irq);
+
+ sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * Mark the passed-through interrupt as going to a VCPU,
+ * this will prevent further EOIs and similar operations
+ * from the XIVE code. It will also mask the interrupt
+ * to either PQ=10 or 11 state, the latter if the interrupt
+ * is pending. This will allow us to unmask or retrigger it
+ * after routing it to the guest with a simple EOI.
+ *
+ * The "state" argument is a "token", all it needs is to be
+ * non-NULL to switch to passed-through or NULL for the
+ * other way around. We may not yet have an actual VCPU
+ * target here and we don't really care.
+ */
+ rc = irq_set_vcpu_affinity(host_irq, state);
+ if (rc) {
+ pr_err("Failed to set VCPU affinity for irq %d\n", host_irq);
+ return rc;
+ }
+
+ /*
+ * Mask and read state of IPI. We need to know if its P bit
+ * is set as that means it's potentially already using a
+ * queue entry in the target
+ */
+ prio = xive_lock_and_mask(xive, sb, state);
+ pr_devel(" old IPI prio %02x P:%d Q:%d\n", prio,
+ state->old_p, state->old_q);
+
+ /* Turn the IPI hard off */
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+
+ /* Grab info about irq */
+ state->pt_number = hw_irq;
+ state->pt_data = irq_data_get_irq_handler_data(host_data);
+
+ /*
+ * Configure the IRQ to match the existing configuration of
+ * the IPI if it was already targetted. Otherwise this will
+ * mask the interrupt in a lossy way (act_priority is 0xff)
+ * which is fine for a never started interrupt.
+ */
+ xive_native_configure_irq(hw_irq,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+
+ /*
+ * We do an EOI to enable the interrupt (and retrigger if needed)
+ * if the guest has the interrupt unmasked and the P bit was *not*
+ * set in the IPI. If it was set, we know a slot may still be in
+ * use in the target queue thus we have to wait for a guest
+ * originated EOI
+ */
+ if (prio != MASKED && !state->old_p)
+ xive_vm_source_eoi(hw_irq, state->pt_data);
+
+ /* Clear old_p/old_q as they are no longer relevant */
+ state->old_p = state->old_q = false;
+
+ /* Restore guest prio (unlocks EOI) */
+ mb();
+ state->guest_priority = prio;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_set_mapped);
+
+int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ unsigned int host_irq = irq_desc_get_irq(host_desc);
+ u16 idx;
+ u8 prio;
+ int rc;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("clr_mapped girq 0x%lx...\n", guest_irq);
+
+ sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * Mask and read state of IRQ. We need to know if its P bit
+ * is set as that means it's potentially already using a
+ * queue entry in the target
+ */
+ prio = xive_lock_and_mask(xive, sb, state);
+ pr_devel(" old IRQ prio %02x P:%d Q:%d\n", prio,
+ state->old_p, state->old_q);
+
+ /*
+ * If old_p is set, the interrupt is pending, we switch it to
+ * PQ=11. This will force a resend in the host so the interrupt
+ * isn't lost to whatver host driver may pick it up
+ */
+ if (state->old_p)
+ xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_11);
+
+ /* Release the passed-through interrupt to the host */
+ rc = irq_set_vcpu_affinity(host_irq, NULL);
+ if (rc) {
+ pr_err("Failed to clr VCPU affinity for irq %d\n", host_irq);
+ return rc;
+ }
+
+ /* Forget about the IRQ */
+ state->pt_number = 0;
+ state->pt_data = NULL;
+
+ /* Reconfigure the IPI */
+ xive_native_configure_irq(state->ipi_number,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+
+ /*
+ * If old_p is set (we have a queue entry potentially
+ * occupied) or the interrupt is masked, we set the IPI
+ * to PQ=10 state. Otherwise we just re-enable it (PQ=00).
+ */
+ if (prio == MASKED || state->old_p)
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_10);
+ else
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_00);
+
+ /* Restore guest prio (unlocks EOI) */
+ mb();
+ state->guest_priority = prio;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped);
+
+static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ int i, j;
+
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++) {
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[j];
+
+ if (!state->valid)
+ continue;
+ if (state->act_priority == MASKED)
+ continue;
+ if (state->act_server != xc->server_num)
+ continue;
+
+ /* Clean it up */
+ arch_spin_lock(&sb->lock);
+ state->act_priority = MASKED;
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+ if (state->pt_number) {
+ xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(state->pt_number, 0, MASKED, 0);
+ }
+ arch_spin_unlock(&sb->lock);
+ }
+ }
+}
+
+void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = xc->xive;
+ int i;
+
+ pr_devel("cleanup_vcpu(cpu=%d)\n", xc->server_num);
+
+ /* Ensure no interrupt is still routed to that VP */
+ xc->valid = false;
+ kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+ /* Mask the VP IPI */
+ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01);
+
+ /* Disable the VP */
+ xive_native_disable_vp(xc->vp_id);
+
+ /* Free the queues & associated interrupts */
+ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+ struct xive_q *q = &xc->queues[i];
+
+ /* Free the escalation irq */
+ if (xc->esc_virq[i]) {
+ free_irq(xc->esc_virq[i], vcpu);
+ irq_dispose_mapping(xc->esc_virq[i]);
+ kfree(xc->esc_virq_names[i]);
+ }
+ /* Free the queue */
+ xive_native_disable_queue(xc->vp_id, q, i);
+ if (q->qpage) {
+ free_pages((unsigned long)q->qpage,
+ xive->q_page_order);
+ q->qpage = NULL;
+ }
+ }
+
+ /* Free the IPI */
+ if (xc->vp_ipi) {
+ xive_cleanup_irq_data(&xc->vp_ipi_data);
+ xive_native_free_irq(xc->vp_ipi);
+ }
+ /* Free the VP */
+ kfree(xc);
+}
+
+int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu)
+{
+ struct kvmppc_xive *xive = dev->private;
+ struct kvmppc_xive_vcpu *xc;
+ int i, r = -EBUSY;
+
+ pr_devel("connect_vcpu(cpu=%d)\n", cpu);
+
+ if (dev->ops != &kvm_xive_ops) {
+ pr_devel("Wrong ops !\n");
+ return -EPERM;
+ }
+ if (xive->kvm != vcpu->kvm)
+ return -EPERM;
+ if (vcpu->arch.irq_type)
+ return -EBUSY;
+ if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
+ pr_devel("Duplicate !\n");
+ return -EEXIST;
+ }
+ if (cpu >= KVM_MAX_VCPUS) {
+ pr_devel("Out of bounds !\n");
+ return -EINVAL;
+ }
+ xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+ if (!xc)
+ return -ENOMEM;
+
+ /* We need to synchronize with queue provisioning */
+ mutex_lock(&vcpu->kvm->lock);
+ vcpu->arch.xive_vcpu = xc;
+ xc->xive = xive;
+ xc->vcpu = vcpu;
+ xc->server_num = cpu;
+ xc->vp_id = xive->vp_base + cpu;
+ xc->mfrr = 0xff;
+ xc->valid = true;
+
+ r = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
+ if (r)
+ goto bail;
+
+ /* Configure VCPU fields for use by assembly push/pull */
+ vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
+ vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
+
+ /* Allocate IPI */
+ xc->vp_ipi = xive_native_alloc_irq();
+ if (!xc->vp_ipi) {
+ r = -EIO;
+ goto bail;
+ }
+ pr_devel(" IPI=0x%x\n", xc->vp_ipi);
+
+ r = xive_native_populate_irq_data(xc->vp_ipi, &xc->vp_ipi_data);
+ if (r)
+ goto bail;
+
+ /*
+ * Initialize queues. Initially we set them all for no queueing
+ * and we enable escalation for queue 0 only which we'll use for
+ * our mfrr change notifications. If the VCPU is hot-plugged, we
+ * do handle provisioning however.
+ */
+ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+ struct xive_q *q = &xc->queues[i];
+
+ /* Is queue already enabled ? Provision it */
+ if (xive->qmap & (1 << i)) {
+ r = xive_provision_queue(vcpu, i);
+ if (r == 0)
+ xive_attach_escalation(vcpu, i);
+ if (r)
+ goto bail;
+ } else {
+ r = xive_native_configure_queue(xc->vp_id,
+ q, i, NULL, 0, true);
+ if (r) {
+ pr_err("Failed to configure queue %d for VCPU %d\n",
+ i, cpu);
+ goto bail;
+ }
+ }
+ }
+
+ /* If not done above, attach priority 0 escalation */
+ r = xive_attach_escalation(vcpu, 0);
+ if (r)
+ goto bail;
+
+ /* Enable the VP */
+ r = xive_native_enable_vp(xc->vp_id);
+ if (r)
+ goto bail;
+
+ /* Route the IPI */
+ r = xive_native_configure_irq(xc->vp_ipi, xc->vp_id, 0, XICS_IPI);
+ if (!r)
+ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_00);
+
+bail:
+ mutex_unlock(&vcpu->kvm->lock);
+ if (r) {
+ kvmppc_xive_cleanup_vcpu(vcpu);
+ return r;
+ }
+
+ vcpu->arch.irq_type = KVMPPC_IRQ_XICS;
+ return 0;
+}
+
+/*
+ * Scanning of queues before/after migration save
+ */
+static void xive_pre_save_set_queued(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return;
+
+ state = &sb->irq_state[idx];
+
+ /* Some sanity checking */
+ if (!state->valid) {
+ pr_err("invalid irq 0x%x in cpu queue!\n", irq);
+ return;
+ }
+
+ /*
+ * If the interrupt is in a queue it should have P set.
+ * We warn so that gets reported. A backtrace isn't useful
+ * so no need to use a WARN_ON.
+ */
+ if (!state->saved_p)
+ pr_err("Interrupt 0x%x is marked in a queue but P not set !\n", irq);
+
+ /* Set flag */
+ state->in_queue = true;
+}
+
+static void xive_pre_save_mask_irq(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ u32 irq)
+{
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[irq];
+
+ if (!state->valid)
+ return;
+
+ /* Mask and save state, this will also sync HW queues */
+ state->saved_scan_prio = xive_lock_and_mask(xive, sb, state);
+
+ /* Transfer P and Q */
+ state->saved_p = state->old_p;
+ state->saved_q = state->old_q;
+
+ /* Unlock */
+ arch_spin_unlock(&sb->lock);
+}
+
+static void xive_pre_save_unmask_irq(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ u32 irq)
+{
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[irq];
+
+ if (!state->valid)
+ return;
+
+ /*
+ * Lock / exclude EOI (not technically necessary if the
+ * guest isn't running concurrently. If this becomes a
+ * performance issue we can probably remove the lock.
+ */
+ xive_lock_for_unmask(sb, state);
+
+ /* Restore mask/prio if it wasn't masked */
+ if (state->saved_scan_prio != MASKED)
+ xive_finish_unmask(xive, sb, state, state->saved_scan_prio);
+
+ /* Unlock */
+ arch_spin_unlock(&sb->lock);
+}
+
+static void xive_pre_save_queue(struct kvmppc_xive *xive, struct xive_q *q)
+{
+ u32 idx = q->idx;
+ u32 toggle = q->toggle;
+ u32 irq;
+
+ do {
+ irq = __xive_read_eq(q->qpage, q->msk, &idx, &toggle);
+ if (irq > XICS_IPI)
+ xive_pre_save_set_queued(xive, irq);
+ } while(irq);
+}
+
+static void xive_pre_save_scan(struct kvmppc_xive *xive)
+{
+ struct kvm_vcpu *vcpu = NULL;
+ int i, j;
+
+ /*
+ * See comment in xive_get_source() about how this
+ * work. Collect a stable state for all interrupts
+ */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ xive_pre_save_mask_irq(xive, sb, j);
+ }
+
+ /* Then scan the queues and update the "in_queue" flag */
+ kvm_for_each_vcpu(i, vcpu, xive->kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ if (!xc)
+ continue;
+ for (j = 0; j < KVMPPC_XIVE_Q_COUNT; j++) {
+ if (xc->queues[i].qpage)
+ xive_pre_save_queue(xive, &xc->queues[i]);
+ }
+ }
+
+ /* Finally restore interrupt states */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ xive_pre_save_unmask_irq(xive, sb, j);
+ }
+}
+
+static void xive_post_save_scan(struct kvmppc_xive *xive)
+{
+ u32 i, j;
+
+ /* Clear all the in_queue flags */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ sb->irq_state[j].in_queue = false;
+ }
+
+ /* Next get_source() will do a new scan */
+ xive->saved_src_count = 0;
+}
+
+/*
+ * This returns the source configuration and state to user space.
+ */
+static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u64 __user *ubufp = (u64 __user *) addr;
+ u64 val, prio;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -ENOENT;
+
+ state = &sb->irq_state[idx];
+
+ if (!state->valid)
+ return -ENOENT;
+
+ pr_devel("get_source(%ld)...\n", irq);
+
+ /*
+ * So to properly save the state into something that looks like a
+ * XICS migration stream we cannot treat interrupts individually.
+ *
+ * We need, instead, mask them all (& save their previous PQ state)
+ * to get a stable state in the HW, then sync them to ensure that
+ * any interrupt that had already fired hits its queue, and finally
+ * scan all the queues to collect which interrupts are still present
+ * in the queues, so we can set the "pending" flag on them and
+ * they can be resent on restore.
+ *
+ * So we do it all when the "first" interrupt gets saved, all the
+ * state is collected at that point, the rest of xive_get_source()
+ * will merely collect and convert that state to the expected
+ * userspace bit mask.
+ */
+ if (xive->saved_src_count == 0)
+ xive_pre_save_scan(xive);
+ xive->saved_src_count++;
+
+ /* Convert saved state into something compatible with xics */
+ val = state->guest_server;
+ prio = state->saved_scan_prio;
+
+ if (prio == MASKED) {
+ val |= KVM_XICS_MASKED;
+ prio = state->saved_priority;
+ }
+ val |= prio << KVM_XICS_PRIORITY_SHIFT;
+ if (state->lsi) {
+ val |= KVM_XICS_LEVEL_SENSITIVE;
+ if (state->saved_p)
+ val |= KVM_XICS_PENDING;
+ } else {
+ if (state->saved_p)
+ val |= KVM_XICS_PRESENTED;
+
+ if (state->saved_q)
+ val |= KVM_XICS_QUEUED;
+
+ /*
+ * We mark it pending (which will attempt a re-delivery)
+ * if we are in a queue *or* we were masked and had
+ * Q set which is equivalent to the XICS "masked pending"
+ * state
+ */
+ if (state->in_queue || (prio == MASKED && state->saved_q))
+ val |= KVM_XICS_PENDING;
+ }
+
+ /*
+ * If that was the last interrupt saved, reset the
+ * in_queue flags
+ */
+ if (xive->saved_src_count == xive->src_count)
+ xive_post_save_scan(xive);
+
+ /* Copy the result to userspace */
+ if (put_user(val, ubufp))
+ return -EFAULT;
+
+ return 0;
+}
+
+static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *xive,
+ int irq)
+{
+ struct kvm *kvm = xive->kvm;
+ struct kvmppc_xive_src_block *sb;
+ int i, bid;
+
+ bid = irq >> KVMPPC_XICS_ICS_SHIFT;
+
+ mutex_lock(&kvm->lock);
+
+ /* block already exists - somebody else got here first */
+ if (xive->src_blocks[bid])
+ goto out;
+
+ /* Create the ICS */
+ sb = kzalloc(sizeof(*sb), GFP_KERNEL);
+ if (!sb)
+ goto out;
+
+ sb->id = bid;
+
+ for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+ sb->irq_state[i].number = (bid << KVMPPC_XICS_ICS_SHIFT) | i;
+ sb->irq_state[i].guest_priority = MASKED;
+ sb->irq_state[i].saved_priority = MASKED;
+ sb->irq_state[i].act_priority = MASKED;
+ }
+ smp_wmb();
+ xive->src_blocks[bid] = sb;
+
+ if (bid > xive->max_sbid)
+ xive->max_sbid = bid;
+
+out:
+ mutex_unlock(&kvm->lock);
+ return xive->src_blocks[bid];
+}
+
+static bool xive_check_delayed_irq(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvm *kvm = xive->kvm;
+ struct kvm_vcpu *vcpu = NULL;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ continue;
+
+ if (xc->delayed_irq == irq) {
+ xc->delayed_irq = 0;
+ xive->delayed_irqs--;
+ return true;
+ }
+ }
+ return false;
+}
+
+static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u64 __user *ubufp = (u64 __user *) addr;
+ u16 idx;
+ u64 val;
+ u8 act_prio, guest_prio;
+ u32 server;
+ int rc = 0;
+
+ if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS)
+ return -ENOENT;
+
+ pr_devel("set_source(irq=0x%lx)\n", irq);
+
+ /* Find the source */
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb) {
+ pr_devel("No source, creating source block...\n");
+ sb = xive_create_src_block(xive, irq);
+ if (!sb) {
+ pr_devel("Failed to create block...\n");
+ return -ENOMEM;
+ }
+ }
+ state = &sb->irq_state[idx];
+
+ /* Read user passed data */
+ if (get_user(val, ubufp)) {
+ pr_devel("fault getting user info !\n");
+ return -EFAULT;
+ }
+
+ server = val & KVM_XICS_DESTINATION_MASK;
+ guest_prio = val >> KVM_XICS_PRIORITY_SHIFT;
+
+ pr_devel(" val=0x016%llx (server=0x%x, guest_prio=%d)\n",
+ val, server, guest_prio);
+ /*
+ * If the source doesn't already have an IPI, allocate
+ * one and get the corresponding data
+ */
+ if (!state->ipi_number) {
+ state->ipi_number = xive_native_alloc_irq();
+ if (state->ipi_number == 0) {
+ pr_devel("Failed to allocate IPI !\n");
+ return -ENOMEM;
+ }
+ xive_native_populate_irq_data(state->ipi_number, &state->ipi_data);
+ pr_devel(" src_ipi=0x%x\n", state->ipi_number);
+ }
+
+ /*
+ * We use lock_and_mask() to set us in the right masked
+ * state. We will override that state from the saved state
+ * further down, but this will handle the cases of interrupts
+ * that need FW masking. We set the initial guest_priority to
+ * 0 before calling it to ensure it actually performs the masking.
+ */
+ state->guest_priority = 0;
+ xive_lock_and_mask(xive, sb, state);
+
+ /*
+ * Now, we select a target if we have one. If we don't we
+ * leave the interrupt untargetted. It means that an interrupt
+ * can become "untargetted" accross migration if it was masked
+ * by set_xive() but there is little we can do about it.
+ */
+
+ /* First convert prio and mark interrupt as untargetted */
+ act_prio = xive_prio_from_guest(guest_prio);
+ state->act_priority = MASKED;
+ state->guest_server = server;
+
+ /*
+ * We need to drop the lock due to the mutex below. Hopefully
+ * nothing is touching that interrupt yet since it hasn't been
+ * advertized to a running guest yet
+ */
+ arch_spin_unlock(&sb->lock);
+
+ /* If we have a priority target the interrupt */
+ if (act_prio != MASKED) {
+ /* First, check provisioning of queues */
+ mutex_lock(&xive->kvm->lock);
+ rc = xive_check_provisioning(xive->kvm, act_prio);
+ mutex_unlock(&xive->kvm->lock);
+
+ /* Target interrupt */
+ if (rc == 0)
+ rc = xive_target_interrupt(xive->kvm, state,
+ server, act_prio);
+ /*
+ * If provisioning or targetting failed, leave it
+ * alone and masked. It will remain disabled until
+ * the guest re-targets it.
+ */
+ }
+
+ /*
+ * Find out if this was a delayed irq stashed in an ICP,
+ * in which case, treat it as pending
+ */
+ if (xive->delayed_irqs && xive_check_delayed_irq(xive, irq)) {
+ val |= KVM_XICS_PENDING;
+ pr_devel(" Found delayed ! forcing PENDING !\n");
+ }
+
+ /* Cleanup the SW state */
+ state->old_p = false;
+ state->old_q = false;
+ state->lsi = false;
+ state->asserted = false;
+
+ /* Restore LSI state */
+ if (val & KVM_XICS_LEVEL_SENSITIVE) {
+ state->lsi = true;
+ if (val & KVM_XICS_PENDING)
+ state->asserted = true;
+ pr_devel(" LSI ! Asserted=%d\n", state->asserted);
+ }
+
+ /*
+ * Restore P and Q. If the interrupt was pending, we
+ * force both P and Q, which will trigger a resend.
+ *
+ * That means that a guest that had both an interrupt
+ * pending (queued) and Q set will restore with only
+ * one instance of that interrupt instead of 2, but that
+ * is perfectly fine as coalescing interrupts that haven't
+ * been presented yet is always allowed.
+ */
+ if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+ state->old_p = true;
+ if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
+ state->old_q = true;
+
+ pr_devel(" P=%d, Q=%d\n", state->old_p, state->old_q);
+
+ /*
+ * If the interrupt was unmasked, update guest priority and
+ * perform the appropriate state transition and do a
+ * re-trigger if necessary.
+ */
+ if (val & KVM_XICS_MASKED) {
+ pr_devel(" masked, saving prio\n");
+ state->guest_priority = MASKED;
+ state->saved_priority = guest_prio;
+ } else {
+ pr_devel(" unmasked, restoring to prio %d\n", guest_prio);
+ xive_finish_unmask(xive, sb, state, guest_prio);
+ state->saved_priority = guest_prio;
+ }
+
+ /* Increment the number of valid sources and mark this one valid */
+ if (!state->valid)
+ xive->src_count++;
+ state->valid = true;
+
+ return 0;
+}
+
+int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+
+ /* Perform locklessly .... (we need to do some RCUisms here...) */
+ state = &sb->irq_state[idx];
+ if (!state->valid)
+ return -EINVAL;
+
+ /* We don't allow a trigger on a passed-through interrupt */
+ if (state->pt_number)
+ return -EINVAL;
+
+ if ((level == 1 && state->lsi) || level == KVM_INTERRUPT_SET_LEVEL)
+ state->asserted = 1;
+ else if (level == 0 || level == KVM_INTERRUPT_UNSET) {
+ state->asserted = 0;
+ return 0;
+ }
+
+ /* Trigger the IPI */
+ xive_irq_trigger(&state->ipi_data);
+
+ return 0;
+}
+
+static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ struct kvmppc_xive *xive = dev->private;
+
+ /* We honor the existing XICS ioctl */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ return xive_set_source(xive, attr->attr, attr->addr);
+ }
+ return -ENXIO;
+}
+
+static int xive_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ struct kvmppc_xive *xive = dev->private;
+
+ /* We honor the existing XICS ioctl */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ return xive_get_source(xive, attr->attr, attr->addr);
+ }
+ return -ENXIO;
+}
+
+static int xive_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ /* We honor the same limits as XICS, at least for now */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ if (attr->attr >= KVMPPC_XICS_FIRST_IRQ &&
+ attr->attr < KVMPPC_XICS_NR_IRQS)
+ return 0;
+ break;
+ }
+ return -ENXIO;
+}
+
+static void kvmppc_xive_cleanup_irq(u32 hw_num, struct xive_irq_data *xd)
+{
+ xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(hw_num, 0, MASKED, 0);
+ xive_cleanup_irq_data(xd);
+}
+
+static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
+{
+ int i;
+
+ for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
+
+ if (!state->valid)
+ continue;
+
+ kvmppc_xive_cleanup_irq(state->ipi_number, &state->ipi_data);
+ xive_native_free_irq(state->ipi_number);
+
+ /* Pass-through, cleanup too */
+ if (state->pt_number)
+ kvmppc_xive_cleanup_irq(state->pt_number, state->pt_data);
+
+ state->valid = false;
+ }
+}
+
+static void kvmppc_xive_free(struct kvm_device *dev)
+{
+ struct kvmppc_xive *xive = dev->private;
+ struct kvm *kvm = xive->kvm;
+ int i;
+
+ debugfs_remove(xive->dentry);
+
+ if (kvm)
+ kvm->arch.xive = NULL;
+
+ /* Mask and free interrupts */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ if (xive->src_blocks[i])
+ kvmppc_xive_free_sources(xive->src_blocks[i]);
+ kfree(xive->src_blocks[i]);
+ xive->src_blocks[i] = NULL;
+ }
+
+ if (xive->vp_base != XIVE_INVALID_VP)
+ xive_native_free_vp_block(xive->vp_base);
+
+
+ kfree(xive);
+ kfree(dev);
+}
+
+static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
+{
+ struct kvmppc_xive *xive;
+ struct kvm *kvm = dev->kvm;
+ int ret = 0;
+
+ pr_devel("Creating xive for partition\n");
+
+ xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+ if (!xive)
+ return -ENOMEM;
+
+ dev->private = xive;
+ xive->dev = dev;
+ xive->kvm = kvm;
+
+ /* Already there ? */
+ if (kvm->arch.xive)
+ ret = -EEXIST;
+ else
+ kvm->arch.xive = xive;
+
+ /* We use the default queue size set by the host */
+ xive->q_order = xive_native_default_eq_shift();
+ if (xive->q_order < PAGE_SHIFT)
+ xive->q_page_order = 0;
+ else
+ xive->q_page_order = xive->q_order - PAGE_SHIFT;
+
+ /* Allocate a bunch of VPs */
+ xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
+ pr_devel("VP_Base=%x\n", xive->vp_base);
+
+ if (xive->vp_base == XIVE_INVALID_VP)
+ ret = -ENOMEM;
+
+ if (ret) {
+ kfree(xive);
+ return ret;
+ }
+
+ return 0;
+}
+
+
+static int xive_debug_show(struct seq_file *m, void *private)
+{
+ struct kvmppc_xive *xive = m->private;
+ struct kvm *kvm = xive->kvm;
+ struct kvm_vcpu *vcpu;
+ u64 t_rm_h_xirr = 0;
+ u64 t_rm_h_ipoll = 0;
+ u64 t_rm_h_cppr = 0;
+ u64 t_rm_h_eoi = 0;
+ u64 t_rm_h_ipi = 0;
+ u64 t_vm_h_xirr = 0;
+ u64 t_vm_h_ipoll = 0;
+ u64 t_vm_h_cppr = 0;
+ u64 t_vm_h_eoi = 0;
+ u64 t_vm_h_ipi = 0;
+ unsigned int i;
+
+ if (!kvm)
+ return 0;
+
+ seq_printf(m, "=========\nVCPU state\n=========\n");
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ continue;
+
+ seq_printf(m, "cpu server %#x CPPR:%#x HWCPPR:%#x"
+ " MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n",
+ xc->server_num, xc->cppr, xc->hw_cppr,
+ xc->mfrr, xc->pending,
+ xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
+
+ t_rm_h_xirr += xc->stat_rm_h_xirr;
+ t_rm_h_ipoll += xc->stat_rm_h_ipoll;
+ t_rm_h_cppr += xc->stat_rm_h_cppr;
+ t_rm_h_eoi += xc->stat_rm_h_eoi;
+ t_rm_h_ipi += xc->stat_rm_h_ipi;
+ t_vm_h_xirr += xc->stat_vm_h_xirr;
+ t_vm_h_ipoll += xc->stat_vm_h_ipoll;
+ t_vm_h_cppr += xc->stat_vm_h_cppr;
+ t_vm_h_eoi += xc->stat_vm_h_eoi;
+ t_vm_h_ipi += xc->stat_vm_h_ipi;
+ }
+
+ seq_printf(m, "Hcalls totals\n");
+ seq_printf(m, " H_XIRR R=%10lld V=%10lld\n", t_rm_h_xirr, t_vm_h_xirr);
+ seq_printf(m, " H_IPOLL R=%10lld V=%10lld\n", t_rm_h_ipoll, t_vm_h_ipoll);
+ seq_printf(m, " H_CPPR R=%10lld V=%10lld\n", t_rm_h_cppr, t_vm_h_cppr);
+ seq_printf(m, " H_EOI R=%10lld V=%10lld\n", t_rm_h_eoi, t_vm_h_eoi);
+ seq_printf(m, " H_IPI R=%10lld V=%10lld\n", t_rm_h_ipi, t_vm_h_ipi);
+
+ return 0;
+}
+
+static int xive_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, xive_debug_show, inode->i_private);
+}
+
+static const struct file_operations xive_debug_fops = {
+ .open = xive_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void xive_debugfs_init(struct kvmppc_xive *xive)
+{
+ char *name;
+
+ name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive);
+ if (!name) {
+ pr_err("%s: no memory for name\n", __func__);
+ return;
+ }
+
+ xive->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root,
+ xive, &xive_debug_fops);
+
+ pr_debug("%s: created %s\n", __func__, name);
+ kfree(name);
+}
+
+static void kvmppc_xive_init(struct kvm_device *dev)
+{
+ struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private;
+
+ /* Register some debug interfaces */
+ xive_debugfs_init(xive);
+}
+
+struct kvm_device_ops kvm_xive_ops = {
+ .name = "kvm-xive",
+ .create = kvmppc_xive_create,
+ .init = kvmppc_xive_init,
+ .destroy = kvmppc_xive_free,
+ .set_attr = xive_set_attr,
+ .get_attr = xive_get_attr,
+ .has_attr = xive_has_attr,
+};
+
+void kvmppc_xive_init_module(void)
+{
+ __xive_vm_h_xirr = xive_vm_h_xirr;
+ __xive_vm_h_ipoll = xive_vm_h_ipoll;
+ __xive_vm_h_ipi = xive_vm_h_ipi;
+ __xive_vm_h_cppr = xive_vm_h_cppr;
+ __xive_vm_h_eoi = xive_vm_h_eoi;
+}
+
+void kvmppc_xive_exit_module(void)
+{
+ __xive_vm_h_xirr = NULL;
+ __xive_vm_h_ipoll = NULL;
+ __xive_vm_h_ipi = NULL;
+ __xive_vm_h_cppr = NULL;
+ __xive_vm_h_eoi = NULL;
+}
--- /dev/null
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _KVM_PPC_BOOK3S_XIVE_H
+#define _KVM_PPC_BOOK3S_XIVE_H
+
+#ifdef CONFIG_KVM_XICS
+#include "book3s_xics.h"
+
+/*
+ * State for one guest irq source.
+ *
+ * For each guest source we allocate a HW interrupt in the XIVE
+ * which we use for all SW triggers. It will be unused for
+ * pass-through but it's easier to keep around as the same
+ * guest interrupt can alternatively be emulated or pass-through
+ * if a physical device is hot unplugged and replaced with an
+ * emulated one.
+ *
+ * This state structure is very similar to the XICS one with
+ * additional XIVE specific tracking.
+ */
+struct kvmppc_xive_irq_state {
+ bool valid; /* Interrupt entry is valid */
+
+ u32 number; /* Guest IRQ number */
+ u32 ipi_number; /* XIVE IPI HW number */
+ struct xive_irq_data ipi_data; /* XIVE IPI associated data */
+ u32 pt_number; /* XIVE Pass-through number if any */
+ struct xive_irq_data *pt_data; /* XIVE Pass-through associated data */
+
+ /* Targetting as set by guest */
+ u32 guest_server; /* Current guest selected target */
+ u8 guest_priority; /* Guest set priority */
+ u8 saved_priority; /* Saved priority when masking */
+
+ /* Actual targetting */
+ u32 act_server; /* Actual server */
+ u8 act_priority; /* Actual priority */
+
+ /* Various state bits */
+ bool in_eoi; /* Synchronize with H_EOI */
+ bool old_p; /* P bit state when masking */
+ bool old_q; /* Q bit state when masking */
+ bool lsi; /* level-sensitive interrupt */
+ bool asserted; /* Only for emulated LSI: current state */
+
+ /* Saved for migration state */
+ bool in_queue;
+ bool saved_p;
+ bool saved_q;
+ u8 saved_scan_prio;
+};
+
+/* Select the "right" interrupt (IPI vs. passthrough) */
+static inline void kvmppc_xive_select_irq(struct kvmppc_xive_irq_state *state,
+ u32 *out_hw_irq,
+ struct xive_irq_data **out_xd)
+{
+ if (state->pt_number) {
+ if (out_hw_irq)
+ *out_hw_irq = state->pt_number;
+ if (out_xd)
+ *out_xd = state->pt_data;
+ } else {
+ if (out_hw_irq)
+ *out_hw_irq = state->ipi_number;
+ if (out_xd)
+ *out_xd = &state->ipi_data;
+ }
+}
+
+/*
+ * This corresponds to an "ICS" in XICS terminology, we use it
+ * as a mean to break up source information into multiple structures.
+ */
+struct kvmppc_xive_src_block {
+ arch_spinlock_t lock;
+ u16 id;
+ struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
+};
+
+
+struct kvmppc_xive {
+ struct kvm *kvm;
+ struct kvm_device *dev;
+ struct dentry *dentry;
+
+ /* VP block associated with the VM */
+ u32 vp_base;
+
+ /* Blocks of sources */
+ struct kvmppc_xive_src_block *src_blocks[KVMPPC_XICS_MAX_ICS_ID + 1];
+ u32 max_sbid;
+
+ /*
+ * For state save, we lazily scan the queues on the first interrupt
+ * being migrated. We don't have a clean way to reset that flags
+ * so we keep track of the number of valid sources and how many of
+ * them were migrated so we can reset when all of them have been
+ * processed.
+ */
+ u32 src_count;
+ u32 saved_src_count;
+
+ /*
+ * Some irqs are delayed on restore until the source is created,
+ * keep track here of how many of them
+ */
+ u32 delayed_irqs;
+
+ /* Which queues (priorities) are in use by the guest */
+ u8 qmap;
+
+ /* Queue orders */
+ u32 q_order;
+ u32 q_page_order;
+
+};
+
+#define KVMPPC_XIVE_Q_COUNT 8
+
+struct kvmppc_xive_vcpu {
+ struct kvmppc_xive *xive;
+ struct kvm_vcpu *vcpu;
+ bool valid;
+
+ /* Server number. This is the HW CPU ID from a guest perspective */
+ u32 server_num;
+
+ /*
+ * HW VP corresponding to this VCPU. This is the base of the VP
+ * block plus the server number.
+ */
+ u32 vp_id;
+ u32 vp_chip_id;
+ u32 vp_cam;
+
+ /* IPI used for sending ... IPIs */
+ u32 vp_ipi;
+ struct xive_irq_data vp_ipi_data;
+
+ /* Local emulation state */
+ uint8_t cppr; /* guest CPPR */
+ uint8_t hw_cppr;/* Hardware CPPR */
+ uint8_t mfrr;
+ uint8_t pending;
+
+ /* Each VP has 8 queues though we only provision some */
+ struct xive_q queues[KVMPPC_XIVE_Q_COUNT];
+ u32 esc_virq[KVMPPC_XIVE_Q_COUNT];
+ char *esc_virq_names[KVMPPC_XIVE_Q_COUNT];
+
+ /* Stash a delayed irq on restore from migration (see set_icp) */
+ u32 delayed_irq;
+
+ /* Stats */
+ u64 stat_rm_h_xirr;
+ u64 stat_rm_h_ipoll;
+ u64 stat_rm_h_cppr;
+ u64 stat_rm_h_eoi;
+ u64 stat_rm_h_ipi;
+ u64 stat_vm_h_xirr;
+ u64 stat_vm_h_ipoll;
+ u64 stat_vm_h_cppr;
+ u64 stat_vm_h_eoi;
+ u64 stat_vm_h_ipi;
+};
+
+static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr)
+{
+ struct kvm_vcpu *vcpu = NULL;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num)
+ return vcpu;
+ }
+ return NULL;
+}
+
+static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmppc_xive *xive,
+ u32 irq, u16 *source)
+{
+ u32 bid = irq >> KVMPPC_XICS_ICS_SHIFT;
+ u16 src = irq & KVMPPC_XICS_SRC_MASK;
+
+ if (source)
+ *source = src;
+ if (bid > KVMPPC_XICS_MAX_ICS_ID)
+ return NULL;
+ return xive->src_blocks[bid];
+}
+
+/*
+ * Mapping between guest priorities and host priorities
+ * is as follow.
+ *
+ * Guest request for 0...6 are honored. Guest request for anything
+ * higher results in a priority of 7 being applied.
+ *
+ * However, when XIRR is returned via H_XIRR, 7 is translated to 0xb
+ * in order to match AIX expectations
+ *
+ * Similar mapping is done for CPPR values
+ */
+static inline u8 xive_prio_from_guest(u8 prio)
+{
+ if (prio == 0xff || prio < 8)
+ return prio;
+ return 7;
+}
+
+static inline u8 xive_prio_to_guest(u8 prio)
+{
+ if (prio == 0xff || prio < 7)
+ return prio;
+ return 0xb;
+}
+
+static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle)
+{
+ u32 cur;
+
+ if (!qpage)
+ return 0;
+ cur = be32_to_cpup(qpage + *idx);
+ if ((cur >> 31) == *toggle)
+ return 0;
+ *idx = (*idx + 1) & msk;
+ if (*idx == 0)
+ (*toggle) ^= 1;
+ return cur & 0x7fffffff;
+}
+
+extern unsigned long xive_rm_h_xirr(struct kvm_vcpu *vcpu);
+extern unsigned long xive_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
+extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+
+extern unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
+extern unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
+extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
+
+#endif /* CONFIG_KVM_XICS */
+#endif /* _KVM_PPC_BOOK3S_XICS_H */
--- /dev/null
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+/* File to be included by other .c files */
+
+#define XGLUE(a,b) a##b
+#define GLUE(a,b) XGLUE(a,b)
+
+static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
+{
+ u8 cppr;
+ u16 ack;
+
+ /* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */
+
+ /* Perform the acknowledge OS to register cycle. */
+ ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
+
+ /* Synchronize subsequent queue accesses */
+ mb();
+
+ /* XXX Check grouping level */
+
+ /* Anything ? */
+ if (!((ack >> 8) & TM_QW1_NSR_EO))
+ return;
+
+ /* Grab CPPR of the most favored pending interrupt */
+ cppr = ack & 0xff;
+ if (cppr < 8)
+ xc->pending |= 1 << cppr;
+
+#ifdef XIVE_RUNTIME_CHECKS
+ /* Check consistency */
+ if (cppr >= xc->hw_cppr)
+ pr_warn("KVM-XIVE: CPU %d odd ack CPPR, got %d at %d\n",
+ smp_processor_id(), cppr, xc->hw_cppr);
+#endif
+
+ /*
+ * Update our image of the HW CPPR. We don't yet modify
+ * xc->cppr, this will be done as we scan for interrupts
+ * in the queues.
+ */
+ xc->hw_cppr = cppr;
+}
+
+static u8 GLUE(X_PFX,esb_load)(struct xive_irq_data *xd, u32 offset)
+{
+ u64 val;
+
+ if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
+ offset |= offset << 4;
+
+ val =__x_readq(__x_eoi_page(xd) + offset);
+#ifdef __LITTLE_ENDIAN__
+ val >>= 64-8;
+#endif
+ return (u8)val;
+}
+
+
+static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
+{
+ /* If the XIVE supports the new "store EOI facility, use it */
+ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
+ __x_writeq(0, __x_eoi_page(xd));
+ else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
+ opal_int_eoi(hw_irq);
+ } else {
+ uint64_t eoi_val;
+
+ /*
+ * Otherwise for EOI, we use the special MMIO that does
+ * a clear of both P and Q and returns the old Q,
+ * except for LSIs where we use the "EOI cycle" special
+ * load.
+ *
+ * This allows us to then do a re-trigger if Q was set
+ * rather than synthetizing an interrupt in software
+ *
+ * For LSIs, using the HW EOI cycle works around a problem
+ * on P9 DD1 PHBs where the other ESB accesses don't work
+ * properly.
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_LSI)
+ __x_readq(__x_eoi_page(xd));
+ else {
+ eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00);
+
+ /* Re-trigger if needed */
+ if ((eoi_val & 1) && __x_trig_page(xd))
+ __x_writeq(0, __x_trig_page(xd));
+ }
+ }
+}
+
+enum {
+ scan_fetch,
+ scan_poll,
+ scan_eoi,
+};
+
+static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
+ u8 pending, int scan_type)
+{
+ u32 hirq = 0;
+ u8 prio = 0xff;
+
+ /* Find highest pending priority */
+ while ((xc->mfrr != 0xff || pending != 0) && hirq == 0) {
+ struct xive_q *q;
+ u32 idx, toggle;
+ __be32 *qpage;
+
+ /*
+ * If pending is 0 this will return 0xff which is what
+ * we want
+ */
+ prio = ffs(pending) - 1;
+
+ /*
+ * If the most favoured prio we found pending is less
+ * favored (or equal) than a pending IPI, we return
+ * the IPI instead.
+ *
+ * Note: If pending was 0 and mfrr is 0xff, we will
+ * not spurriously take an IPI because mfrr cannot
+ * then be smaller than cppr.
+ */
+ if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
+ prio = xc->mfrr;
+ hirq = XICS_IPI;
+ break;
+ }
+
+ /* Don't scan past the guest cppr */
+ if (prio >= xc->cppr || prio > 7)
+ break;
+
+ /* Grab queue and pointers */
+ q = &xc->queues[prio];
+ idx = q->idx;
+ toggle = q->toggle;
+
+ /*
+ * Snapshot the queue page. The test further down for EOI
+ * must use the same "copy" that was used by __xive_read_eq
+ * since qpage can be set concurrently and we don't want
+ * to miss an EOI.
+ */
+ qpage = READ_ONCE(q->qpage);
+
+skip_ipi:
+ /*
+ * Try to fetch from the queue. Will return 0 for a
+ * non-queueing priority (ie, qpage = 0).
+ */
+ hirq = __xive_read_eq(qpage, q->msk, &idx, &toggle);
+
+ /*
+ * If this was a signal for an MFFR change done by
+ * H_IPI we skip it. Additionally, if we were fetching
+ * we EOI it now, thus re-enabling reception of a new
+ * such signal.
+ *
+ * We also need to do that if prio is 0 and we had no
+ * page for the queue. In this case, we have non-queued
+ * IPI that needs to be EOId.
+ *
+ * This is safe because if we have another pending MFRR
+ * change that wasn't observed above, the Q bit will have
+ * been set and another occurrence of the IPI will trigger.
+ */
+ if (hirq == XICS_IPI || (prio == 0 && !qpage)) {
+ if (scan_type == scan_fetch)
+ GLUE(X_PFX,source_eoi)(xc->vp_ipi,
+ &xc->vp_ipi_data);
+ /* Loop back on same queue with updated idx/toggle */
+#ifdef XIVE_RUNTIME_CHECKS
+ WARN_ON(hirq && hirq != XICS_IPI);
+#endif
+ if (hirq)
+ goto skip_ipi;
+ }
+
+ /* If fetching, update queue pointers */
+ if (scan_type == scan_fetch) {
+ q->idx = idx;
+ q->toggle = toggle;
+ }
+
+ /* Something found, stop searching */
+ if (hirq)
+ break;
+
+ /* Clear the pending bit on the now empty queue */
+ pending &= ~(1 << prio);
+
+ /*
+ * Check if the queue count needs adjusting due to
+ * interrupts being moved away.
+ */
+ if (atomic_read(&q->pending_count)) {
+ int p = atomic_xchg(&q->pending_count, 0);
+ if (p) {
+#ifdef XIVE_RUNTIME_CHECKS
+ WARN_ON(p > atomic_read(&q->count));
+#endif
+ atomic_sub(p, &q->count);
+ }
+ }
+ }
+
+ /* If we are just taking a "peek", do nothing else */
+ if (scan_type == scan_poll)
+ return hirq;
+
+ /* Update the pending bits */
+ xc->pending = pending;
+
+ /*
+ * If this is an EOI that's it, no CPPR adjustment done here,
+ * all we needed was cleanup the stale pending bits and check
+ * if there's anything left.
+ */
+ if (scan_type == scan_eoi)
+ return hirq;
+
+ /*
+ * If we found an interrupt, adjust what the guest CPPR should
+ * be as if we had just fetched that interrupt from HW.
+ */
+ if (hirq)
+ xc->cppr = prio;
+ /*
+ * If it was an IPI the HW CPPR might have been lowered too much
+ * as the HW interrupt we use for IPIs is routed to priority 0.
+ *
+ * We re-sync it here.
+ */
+ if (xc->cppr != xc->hw_cppr) {
+ xc->hw_cppr = xc->cppr;
+ __x_writeb(xc->cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+ }
+
+ return hirq;
+}
+
+X_STATIC unsigned long GLUE(X_PFX,h_xirr)(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 old_cppr;
+ u32 hirq;
+
+ pr_devel("H_XIRR\n");
+
+ xc->GLUE(X_STAT_PFX,h_xirr)++;
+
+ /* First collect pending bits from HW */
+ GLUE(X_PFX,ack_pending)(xc);
+
+ /*
+ * Cleanup the old-style bits if needed (they may have been
+ * set by pull or an escalation interrupts).
+ */
+ if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions))
+ clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
+ &vcpu->arch.pending_exceptions);
+
+ pr_devel(" new pending=0x%02x hw_cppr=%d cppr=%d\n",
+ xc->pending, xc->hw_cppr, xc->cppr);
+
+ /* Grab previous CPPR and reverse map it */
+ old_cppr = xive_prio_to_guest(xc->cppr);
+
+ /* Scan for actual interrupts */
+ hirq = GLUE(X_PFX,scan_interrupts)(xc, xc->pending, scan_fetch);
+
+ pr_devel(" got hirq=0x%x hw_cppr=%d cppr=%d\n",
+ hirq, xc->hw_cppr, xc->cppr);
+
+#ifdef XIVE_RUNTIME_CHECKS
+ /* That should never hit */
+ if (hirq & 0xff000000)
+ pr_warn("XIVE: Weird guest interrupt number 0x%08x\n", hirq);
+#endif
+
+ /*
+ * XXX We could check if the interrupt is masked here and
+ * filter it. If we chose to do so, we would need to do:
+ *
+ * if (masked) {
+ * lock();
+ * if (masked) {
+ * old_Q = true;
+ * hirq = 0;
+ * }
+ * unlock();
+ * }
+ */
+
+ /* Return interrupt and old CPPR in GPR4 */
+ vcpu->arch.gpr[4] = hirq | (old_cppr << 24);
+
+ return H_SUCCESS;
+}
+
+X_STATIC unsigned long GLUE(X_PFX,h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 pending = xc->pending;
+ u32 hirq;
+ u8 pipr;
+
+ pr_devel("H_IPOLL(server=%ld)\n", server);
+
+ xc->GLUE(X_STAT_PFX,h_ipoll)++;
+
+ /* Grab the target VCPU if not the current one */
+ if (xc->server_num != server) {
+ vcpu = kvmppc_xive_find_server(vcpu->kvm, server);
+ if (!vcpu)
+ return H_PARAMETER;
+ xc = vcpu->arch.xive_vcpu;
+
+ /* Scan all priorities */
+ pending = 0xff;
+ } else {
+ /* Grab pending interrupt if any */
+ pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR);
+ if (pipr < 8)
+ pending |= 1 << pipr;
+ }
+
+ hirq = GLUE(X_PFX,scan_interrupts)(xc, pending, scan_poll);
+
+ /* Return interrupt and old CPPR in GPR4 */
+ vcpu->arch.gpr[4] = hirq | (xc->cppr << 24);
+
+ return H_SUCCESS;
+}
+
+static void GLUE(X_PFX,push_pending_to_hw)(struct kvmppc_xive_vcpu *xc)
+{
+ u8 pending, prio;
+
+ pending = xc->pending;
+ if (xc->mfrr != 0xff) {
+ if (xc->mfrr < 8)
+ pending |= 1 << xc->mfrr;
+ else
+ pending |= 0x80;
+ }
+ if (!pending)
+ return;
+ prio = ffs(pending) - 1;
+
+ __x_writeb(prio, __x_tima + TM_SPC_SET_OS_PENDING);
+}
+
+X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 old_cppr;
+
+ pr_devel("H_CPPR(cppr=%ld)\n", cppr);
+
+ xc->GLUE(X_STAT_PFX,h_cppr)++;
+
+ /* Map CPPR */
+ cppr = xive_prio_from_guest(cppr);
+
+ /* Remember old and update SW state */
+ old_cppr = xc->cppr;
+ xc->cppr = cppr;
+
+ /*
+ * We are masking less, we need to look for pending things
+ * to deliver and set VP pending bits accordingly to trigger
+ * a new interrupt otherwise we might miss MFRR changes for
+ * which we have optimized out sending an IPI signal.
+ */
+ if (cppr > old_cppr)
+ GLUE(X_PFX,push_pending_to_hw)(xc);
+
+ /* Apply new CPPR */
+ xc->hw_cppr = cppr;
+ __x_writeb(cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+
+ return H_SUCCESS;
+}
+
+X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr)
+{
+ struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_irq_data *xd;
+ u8 new_cppr = xirr >> 24;
+ u32 irq = xirr & 0x00ffffff, hw_num;
+ u16 src;
+ int rc = 0;
+
+ pr_devel("H_EOI(xirr=%08lx)\n", xirr);
+
+ xc->GLUE(X_STAT_PFX,h_eoi)++;
+
+ xc->cppr = xive_prio_from_guest(new_cppr);
+
+ /*
+ * IPIs are synthetized from MFRR and thus don't need
+ * any special EOI handling. The underlying interrupt
+ * used to signal MFRR changes is EOId when fetched from
+ * the queue.
+ */
+ if (irq == XICS_IPI || irq == 0)
+ goto bail;
+
+ /* Find interrupt source */
+ sb = kvmppc_xive_find_source(xive, irq, &src);
+ if (!sb) {
+ pr_devel(" source not found !\n");
+ rc = H_PARAMETER;
+ goto bail;
+ }
+ state = &sb->irq_state[src];
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ state->in_eoi = true;
+ mb();
+
+again:
+ if (state->guest_priority == MASKED) {
+ arch_spin_lock(&sb->lock);
+ if (state->guest_priority != MASKED) {
+ arch_spin_unlock(&sb->lock);
+ goto again;
+ }
+ pr_devel(" EOI on saved P...\n");
+
+ /* Clear old_p, that will cause unmask to perform an EOI */
+ state->old_p = false;
+
+ arch_spin_unlock(&sb->lock);
+ } else {
+ pr_devel(" EOI on source...\n");
+
+ /* Perform EOI on the source */
+ GLUE(X_PFX,source_eoi)(hw_num, xd);
+
+ /* If it's an emulated LSI, check level and resend */
+ if (state->lsi && state->asserted)
+ __x_writeq(0, __x_trig_page(xd));
+
+ }
+
+ mb();
+ state->in_eoi = false;
+bail:
+
+ /* Re-evaluate pending IRQs and update HW */
+ GLUE(X_PFX,scan_interrupts)(xc, xc->pending, scan_eoi);
+ GLUE(X_PFX,push_pending_to_hw)(xc);
+ pr_devel(" after scan pending=%02x\n", xc->pending);
+
+ /* Apply new CPPR */
+ xc->hw_cppr = xc->cppr;
+ __x_writeb(xc->cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+
+ return rc;
+}
+
+X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ pr_devel("H_IPI(server=%08lx,mfrr=%ld)\n", server, mfrr);
+
+ xc->GLUE(X_STAT_PFX,h_ipi)++;
+
+ /* Find target */
+ vcpu = kvmppc_xive_find_server(vcpu->kvm, server);
+ if (!vcpu)
+ return H_PARAMETER;
+ xc = vcpu->arch.xive_vcpu;
+
+ /* Locklessly write over MFRR */
+ xc->mfrr = mfrr;
+
+ /* Shoot the IPI if most favored than target cppr */
+ if (mfrr < xc->cppr)
+ __x_writeq(0, __x_trig_page(&xc->vp_ipi_data));
+
+ return H_SUCCESS;
+}
#endif
#ifdef CONFIG_KVM_XICS
ret = ret || (kvm->arch.xics != NULL);
+ ret = ret || (kvm->arch.xive != NULL);
#endif
smp_rmb();
return ret;
#include <asm/irqflags.h>
#include <asm/iommu.h>
#include <asm/switch_to.h>
+#include <asm/xive.h>
+
#include "timing.h"
#include "irq.h"
#include "../mm/mmu_decl.h"
kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
break;
case KVMPPC_IRQ_XICS:
- kvmppc_xics_free_icp(vcpu);
+ if (xive_enabled())
+ kvmppc_xive_cleanup_vcpu(vcpu);
+ else
+ kvmppc_xics_free_icp(vcpu);
break;
}
r = -EPERM;
dev = kvm_device_from_filp(f.file);
- if (dev)
- r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
+ if (dev) {
+ if (xive_enabled())
+ r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]);
+ else
+ r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
+ }
fdput(f);
break;
return true;
#endif
#ifdef CONFIG_KVM_XICS
- if (kvm->arch.xics)
+ if (kvm->arch.xics || kvm->arch.xive)
return true;
#endif
return false;
EXPORT_SYMBOL_GPL(opal_write_oppanel_async);
/* Export this for KVM */
EXPORT_SYMBOL_GPL(opal_int_set_mfrr);
+EXPORT_SYMBOL_GPL(opal_int_eoi);
#endif
bool __xive_enabled;
+EXPORT_SYMBOL_GPL(__xive_enabled);
bool xive_cmdline_disabled;
/* We use only one priority for now */
static u8 xive_irq_priority;
-/* TIMA */
+/* TIMA exported to KVM */
void __iomem *xive_tima;
+EXPORT_SYMBOL_GPL(xive_tima);
u32 xive_tima_offset;
/* Backend ops */
DBG_VERBOSE("eoi_irq: irq=%d [0x%lx] pending=%02x\n",
d->irq, irqd_to_hwirq(d), xc->pending_prio);
- /* EOI the source if it hasn't been disabled */
- if (!irqd_irq_disabled(d))
+ /*
+ * EOI the source if it hasn't been disabled and hasn't
+ * been passed-through to a KVM guest
+ */
+ if (!irqd_irq_disabled(d) && !irqd_is_forwarded_to_vcpu(d))
xive_do_source_eoi(irqd_to_hwirq(d), xd);
/*
old_target = xd->target;
- rc = xive_ops->configure_irq(hw_irq,
- get_hard_smp_processor_id(target),
- xive_irq_priority, d->irq);
+ /*
+ * Only configure the irq if it's not currently passed-through to
+ * a KVM guest
+ */
+ if (!irqd_is_forwarded_to_vcpu(d))
+ rc = xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(target),
+ xive_irq_priority, d->irq);
if (rc < 0) {
pr_err("Error %d reconfiguring irq %d\n", rc, d->irq);
return rc;
return 1;
}
+static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ int rc;
+ u8 pq;
+
+ /*
+ * We only support this on interrupts that do not require
+ * firmware calls for masking and unmasking
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_MASK_FW)
+ return -EIO;
+
+ /*
+ * This is called by KVM with state non-NULL for enabling
+ * pass-through or NULL for disabling it
+ */
+ if (state) {
+ irqd_set_forwarded_to_vcpu(d);
+
+ /* Set it to PQ=10 state to prevent further sends */
+ pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_10);
+
+ /* No target ? nothing to do */
+ if (xd->target == XIVE_INVALID_TARGET) {
+ /*
+ * An untargetted interrupt should have been
+ * also masked at the source
+ */
+ WARN_ON(pq & 2);
+
+ return 0;
+ }
+
+ /*
+ * If P was set, adjust state to PQ=11 to indicate
+ * that a resend is needed for the interrupt to reach
+ * the guest. Also remember the value of P.
+ *
+ * This also tells us that it's in flight to a host queue
+ * or has already been fetched but hasn't been EOIed yet
+ * by the host. This it's potentially using up a host
+ * queue slot. This is important to know because as long
+ * as this is the case, we must not hard-unmask it when
+ * "returning" that interrupt to the host.
+ *
+ * This saved_p is cleared by the host EOI, when we know
+ * for sure the queue slot is no longer in use.
+ */
+ if (pq & 2) {
+ pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_11);
+ xd->saved_p = true;
+
+ /*
+ * Sync the XIVE source HW to ensure the interrupt
+ * has gone through the EAS before we change its
+ * target to the guest. That should guarantee us
+ * that we *will* eventually get an EOI for it on
+ * the host. Otherwise there would be a small window
+ * for P to be seen here but the interrupt going
+ * to the guest queue.
+ */
+ if (xive_ops->sync_source)
+ xive_ops->sync_source(hw_irq);
+ } else
+ xd->saved_p = false;
+ } else {
+ irqd_clr_forwarded_to_vcpu(d);
+
+ /* No host target ? hard mask and return */
+ if (xd->target == XIVE_INVALID_TARGET) {
+ xive_do_source_set_mask(xd, true);
+ return 0;
+ }
+
+ /*
+ * Sync the XIVE source HW to ensure the interrupt
+ * has gone through the EAS before we change its
+ * target to the host.
+ */
+ if (xive_ops->sync_source)
+ xive_ops->sync_source(hw_irq);
+
+ /*
+ * By convention we are called with the interrupt in
+ * a PQ=10 or PQ=11 state, ie, it won't fire and will
+ * have latched in Q whether there's a pending HW
+ * interrupt or not.
+ *
+ * First reconfigure the target.
+ */
+ rc = xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(xd->target),
+ xive_irq_priority, d->irq);
+ if (rc)
+ return rc;
+
+ /*
+ * Then if saved_p is not set, effectively re-enable the
+ * interrupt with an EOI. If it is set, we know there is
+ * still a message in a host queue somewhere that will be
+ * EOId eventually.
+ *
+ * Note: We don't check irqd_irq_disabled(). Effectively,
+ * we *will* let the irq get through even if masked if the
+ * HW is still firing it in order to deal with the whole
+ * saved_p business properly. If the interrupt triggers
+ * while masked, the generic code will re-mask it anyway.
+ */
+ if (!xd->saved_p)
+ xive_do_source_eoi(hw_irq, xd);
+
+ }
+ return 0;
+}
+
static struct irq_chip xive_irq_chip = {
.name = "XIVE-IRQ",
.irq_startup = xive_irq_startup,
.irq_set_affinity = xive_irq_set_affinity,
.irq_set_type = xive_irq_set_type,
.irq_retrigger = xive_irq_retrigger,
+ .irq_set_vcpu_affinity = xive_irq_set_vcpu_affinity,
};
bool is_xive_irq(struct irq_chip *chip)
{
return chip == &xive_irq_chip;
}
+EXPORT_SYMBOL_GPL(is_xive_irq);
void xive_cleanup_irq_data(struct xive_irq_data *xd)
{
xd->trig_mmio = NULL;
}
}
+EXPORT_SYMBOL_GPL(xive_cleanup_irq_data);
static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
{
#include <asm/xive.h>
#include <asm/xive-regs.h>
#include <asm/opal.h>
+#include <asm/kvm_ppc.h>
#include "xive-internal.h"
}
return 0;
}
+EXPORT_SYMBOL_GPL(xive_native_populate_irq_data);
int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq)
{
}
return rc == 0 ? 0 : -ENXIO;
}
+EXPORT_SYMBOL_GPL(xive_native_configure_irq);
+
/* This can be called multiple time to change a queue configuration */
int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
fail:
return rc;
}
+EXPORT_SYMBOL_GPL(xive_native_configure_queue);
static void __xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio)
{
{
__xive_native_disable_queue(vp_id, q, prio);
}
+EXPORT_SYMBOL_GPL(xive_native_disable_queue);
static int xive_native_setup_queue(unsigned int cpu, struct xive_cpu *xc, u8 prio)
{
}
return 0;
}
+#endif /* CONFIG_SMP */
u32 xive_native_alloc_irq(void)
{
return 0;
return rc;
}
+EXPORT_SYMBOL_GPL(xive_native_alloc_irq);
void xive_native_free_irq(u32 irq)
{
msleep(1);
}
}
+EXPORT_SYMBOL_GPL(xive_native_free_irq);
+#ifdef CONFIG_SMP
static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc)
{
s64 rc;
return;
/* Enable the pool VP */
- vp = xive_pool_vps + get_hard_smp_processor_id(cpu);
+ vp = xive_pool_vps + cpu;
pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp);
for (;;) {
rc = opal_xive_set_vp_info(vp, OPAL_XIVE_VP_ENABLED, 0);
in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
/* Disable it */
- vp = xive_pool_vps + get_hard_smp_processor_id(cpu);
+ vp = xive_pool_vps + cpu;
for (;;) {
rc = opal_xive_set_vp_info(vp, 0, 0);
if (rc != OPAL_BUSY)
}
}
-static void xive_native_sync_source(u32 hw_irq)
+void xive_native_sync_source(u32 hw_irq)
{
opal_xive_sync(XIVE_SYNC_EAS, hw_irq);
}
+EXPORT_SYMBOL_GPL(xive_native_sync_source);
static const struct xive_ops xive_native_ops = {
.populate_irq_data = xive_native_populate_irq_data,
return true;
}
+static void xive_native_setup_pools(void)
+{
+ /* Allocate a pool big enough */
+ pr_debug("XIVE: Allocating VP block for pool size %d\n", nr_cpu_ids);
+
+ xive_pool_vps = xive_native_alloc_vp_block(nr_cpu_ids);
+ if (WARN_ON(xive_pool_vps == XIVE_INVALID_VP))
+ pr_err("XIVE: Failed to allocate pool VP, KVM might not function\n");
+
+ pr_debug("XIVE: Pool VPs allocated at 0x%x for %d max CPUs\n",
+ xive_pool_vps, nr_cpu_ids);
+}
+
u32 xive_native_default_eq_shift(void)
{
return xive_queue_shift;
}
+EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
bool xive_native_init(void)
{
struct property *prop;
u8 max_prio = 7;
const __be32 *p;
- u32 val;
+ u32 val, cpu;
s64 rc;
if (xive_cmdline_disabled)
break;
}
- /* Grab size of provisioning pages */
+ /* Configure Thread Management areas for KVM */
+ for_each_possible_cpu(cpu)
+ kvmppc_set_xive_tima(cpu, r.start, tima);
+
+ /* Grab size of provisionning pages */
xive_parse_provisioning(np);
/* Switch the XIVE to exploitation mode */
return false;
}
+ /* Setup some dummy HV pool VPs */
+ xive_native_setup_pools();
+
/* Initialize XIVE core with our backend */
if (!xive_core_init(&xive_native_ops, tima, TM_QW3_HV_PHYS,
max_prio)) {
pr_warn("OPAL error %lld freeing VP block\n", rc);
}
EXPORT_SYMBOL_GPL(xive_native_free_vp_block);
+
+int xive_native_enable_vp(u32 vp_id)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp_id, OPAL_XIVE_VP_ENABLED, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_enable_vp);
+
+int xive_native_disable_vp(u32 vp_id)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp_id, 0, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_disable_vp);
+
+int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id)
+{
+ __be64 vp_cam_be;
+ __be32 vp_chip_id_be;
+ s64 rc;
+
+ rc = opal_xive_get_vp_info(vp_id, NULL, &vp_cam_be, NULL, &vp_chip_id_be);
+ if (rc)
+ return -EIO;
+ *out_cam_id = be64_to_cpu(vp_cam_be) & 0xffffffffu;
+ *out_chip_id = be32_to_cpu(vp_chip_id_be);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_info);
generic-y += resource.h
generic-y += sockios.h
generic-y += termbits.h
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += chpid.h
-header-y += chsc.h
-header-y += clp.h
-header-y += cmb.h
-header-y += dasd.h
-header-y += debug.h
-header-y += errno.h
-header-y += guarded_storage.h
-header-y += hypfs.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm.h
-header-y += kvm_para.h
-header-y += kvm_perf.h
-header-y += kvm_virtio.h
-header-y += monwriter.h
-header-y += msgbuf.h
-header-y += pkey.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += qeth.h
-header-y += schid.h
-header-y += sclp_ctl.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sie.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += tape390.h
-header-y += termios.h
-header-y += types.h
-header-y += ucontext.h
-header-y += unistd.h
-header-y += virtio-ccw.h
-header-y += vtoc.h
-header-y += zcrypt.h
-
-header-y +=
-
generic-y += barrier.h
generic-y += clkdev.h
generic-y += current.h
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
defaultimage-$(CONFIG_SH_7619_SOLUTION_ENGINE) := vmlinux
# Set some sensible Kbuild defaults
-KBUILD_IMAGE := $(defaultimage-y)
+boot := arch/sh/boot
+KBUILD_IMAGE := $(boot)/$(defaultimage-y)
#
# Choosing incompatible machines durings configuration will result in
drivers-y += arch/sh/drivers/
drivers-$(CONFIG_OPROFILE) += arch/sh/oprofile/
-boot := arch/sh/boot
-
cflags-y += $(foreach d, $(cpuincdir-y), -Iarch/sh/include/$(d)) \
$(foreach d, $(machdir-y), -Iarch/sh/include/$(d))
romImage
PHONY += $(BOOT_TARGETS)
-all: $(KBUILD_IMAGE)
+all: $(notdir $(KBUILD_IMAGE))
$(BOOT_TARGETS): vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += byteorder.h
-header-y += cachectl.h
-header-y += cpu-features.h
-header-y += hw_breakpoint.h
-header-y += ioctls.h
-header-y += posix_types.h
-header-y += posix_types_32.h
-header-y += posix_types_64.h
-header-y += ptrace.h
-header-y += ptrace_32.h
-header-y += ptrace_64.h
-header-y += setup.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += sockios.h
-header-y += stat.h
-header-y += swab.h
-header-y += types.h
-header-y += unistd.h
-header-y += unistd_32.h
-header-y += unistd_64.h
# UAPI Header export list
-# User exported sparc header files
-
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += apc.h
-header-y += asi.h
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += display7seg.h
-header-y += envctrl.h
-header-y += errno.h
-header-y += fbio.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += jsflash.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += openpromio.h
-header-y += param.h
-header-y += perfctr.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += psr.h
-header-y += psrcompat.h
-header-y += pstate.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += traps.h
-header-y += uctx.h
-header-y += unistd.h
-header-y += utrap.h
-header-y += watchdog.h
retl
mov %o1, %o0
ENDPROC(__retl_o1)
+
+ENTRY(__retl_o1_asi)
+ wr %o5, 0x0, %asi
+ retl
+ mov %o1, %o0
+ENDPROC(__retl_o1_asi)
if (count > LED_MAX_LENGTH)
count = LED_MAX_LENGTH;
- buf = kmalloc(sizeof(char) * (count + 1), GFP_KERNEL);
- if (!buf)
- return -ENOMEM;
-
- if (copy_from_user(buf, buffer, count)) {
- kfree(buf);
- return -EFAULT;
- }
-
- buf[count] = '\0';
+ buf = memdup_user_nul(buffer, count);
+ if (IS_ERR(buf))
+ return PTR_ERR(buf);
/* work around \n when echo'ing into proc */
if (buf[count - 1] == '\n')
{
while (*commands) {
/* Move to the start of the next "argument". */
- while (*commands && *commands == ' ')
+ while (*commands == ' ')
commands++;
/* Process any command switches, otherwise skip it. */
{
while (*commands) {
/* Move to the start of the next "argument". */
- while (*commands && *commands == ' ')
+ while (*commands == ' ')
commands++;
/* Process any command switches, otherwise skip it. */
98: x,y; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_o1; \
+ .word 98b, __retl_o1_asi;\
.text; \
.align 4;
98: x,y; \
.section __ex_table,"a";\
.align 4; \
- .word 98b, __retl_o1; \
+ .word 98b, __retl_o1_asi;\
.text; \
.align 4;
+++ /dev/null
-# Tile arch headers
-
-header-y += ../arch/
-
generic-y += bug.h
generic-y += bugs.h
generic-y += clkdev.h
+++ /dev/null
-# UAPI Header export list
-header-y += abi.h
-header-y += chip.h
-header-y += chip_tilegx.h
-header-y += chip_tilepro.h
-header-y += icache.h
-header-y += interrupts.h
-header-y += interrupts_32.h
-header-y += interrupts_64.h
-header-y += opcode.h
-header-y += opcode_tilegx.h
-header-y += opcode_tilepro.h
-header-y += sim.h
-header-y += sim_def.h
-header-y += spr_def.h
-header-y += spr_def_32.h
-header-y += spr_def_64.h
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += cachectl.h
-header-y += hardwall.h
-header-y += kvm_para.h
-header-y += mman.h
-header-y += ptrace.h
-header-y += setup.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += stat.h
-header-y += swab.h
-header-y += ucontext.h
-header-y += unistd.h
-
generic-y += ucontext.h
# Default defconfig and target when executing plain make
KBUILD_DEFCONFIG := $(ARCH)_defconfig
-KBUILD_IMAGE := zImage
+KBUILD_IMAGE := $(boot)/zImage
-all: $(KBUILD_IMAGE)
+all: zImage
zImage Image uImage: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-header-y += byteorder.h
-header-y += kvm_para.h
-header-y += ptrace.h
-header-y += sigcontext.h
-header-y += unistd.h
-
generic-y += kvm_para.h
void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t offset, unsigned long mask);
+ int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+
/* pmu operations of sub-arch */
const struct kvm_pmu_ops *pmu_ops;
genhdr-y += unistd_32.h
genhdr-y += unistd_64.h
genhdr-y += unistd_x32.h
-header-y += a.out.h
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += boot.h
-header-y += bootparam.h
-header-y += byteorder.h
-header-y += debugreg.h
-header-y += e820.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += hw_breakpoint.h
-header-y += hyperv.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += ist.h
-header-y += kvm.h
-header-y += kvm_para.h
-header-y += kvm_perf.h
-header-y += ldt.h
-header-y += mce.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += msr-index.h
-header-y += msr.h
-header-y += mtrr.h
-header-y += param.h
-header-y += perf_regs.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += posix_types_32.h
-header-y += posix_types_64.h
-header-y += posix_types_x32.h
-header-y += prctl.h
-header-y += processor-flags.h
-header-y += ptrace-abi.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += sigcontext32.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += svm.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += ucontext.h
-header-y += unistd.h
-header-y += vm86.h
-header-y += vmx.h
-header-y += vsyscall.h
};
struct legacy_pic *legacy_pic = &default_legacy_pic;
+EXPORT_SYMBOL(legacy_pic);
static int __init i8259A_init_ops(void)
{
if (!tboot_enabled())
return 0;
+ if (!intel_iommu_tboot_noforce)
+ return 1;
+
if (no_iommu || swiotlb || dmar_disabled)
pr_warning("Forcing Intel-IOMMU to enabled\n");
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
+/**
+ * kvm_arch_write_log_dirty - emulate dirty page logging
+ * @vcpu: Guest mode vcpu
+ *
+ * Emulate arch specific page modification logging for the
+ * nested hypervisor
+ */
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+{
+ if (kvm_x86_ops->write_log_dirty)
+ return kvm_x86_ops->write_log_dirty(vcpu);
+
+ return 0;
+}
+
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn)
{
void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
#endif
if (level == walker->level && write_fault &&
!(pte & PT_GUEST_DIRTY_MASK)) {
trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
+#if PTTYPE == PTTYPE_EPT
+ if (kvm_arch_write_log_dirty(vcpu))
+ return -EINVAL;
+#endif
pte |= PT_GUEST_DIRTY_MASK;
}
if (pte == orig_pte)
u64 xss_exit_bitmap;
u64 guest_physical_address;
u64 vmcs_link_pointer;
+ u64 pml_address;
u64 guest_ia32_debugctl;
u64 guest_ia32_pat;
u64 guest_ia32_efer;
u16 guest_ldtr_selector;
u16 guest_tr_selector;
u16 guest_intr_status;
+ u16 guest_pml_index;
u16 host_es_selector;
u16 host_cs_selector;
u16 host_ss_selector;
/* Has the level1 guest done vmxon? */
bool vmxon;
gpa_t vmxon_ptr;
+ bool pml_full;
/* The guest-physical address of the current VMCS L1 keeps for L2 */
gpa_t current_vmptr;
FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector),
FIELD(GUEST_TR_SELECTOR, guest_tr_selector),
FIELD(GUEST_INTR_STATUS, guest_intr_status),
+ FIELD(GUEST_PML_INDEX, guest_pml_index),
FIELD(HOST_ES_SELECTOR, host_es_selector),
FIELD(HOST_CS_SELECTOR, host_cs_selector),
FIELD(HOST_SS_SELECTOR, host_ss_selector),
FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
+ FIELD64(PML_ADDRESS, pml_address),
FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
return flexpriority_enabled;
}
+static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
+{
+ return vmx_misc_cr3_count(to_vmx(vcpu)->nested.nested_vmx_misc_low);
+}
+
static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
return vmcs12->cpu_based_vm_exec_control & bit;
vmx_xsaves_supported();
}
+static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML);
+}
+
static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
{
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT |
VMX_EPT_1GB_PAGE_BIT;
- if (enable_ept_ad_bits)
+ if (enable_ept_ad_bits) {
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_PML;
vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT;
+ }
} else
vmx->nested.nested_vmx_ept_caps = 0;
case EXIT_REASON_PREEMPTION_TIMER:
return false;
case EXIT_REASON_PML_FULL:
- /* We don't expose PML support to L1. */
+ /* We emulate PML support to L1. */
return false;
default:
return true;
struct x86_exception *fault)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exit_reason;
+ unsigned long exit_qualification = vcpu->arch.exit_qualification;
- if (fault->error_code & PFERR_RSVD_MASK)
+ if (vmx->nested.pml_full) {
+ exit_reason = EXIT_REASON_PML_FULL;
+ vmx->nested.pml_full = false;
+ exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+ } else if (fault->error_code & PFERR_RSVD_MASK)
exit_reason = EXIT_REASON_EPT_MISCONFIG;
else
exit_reason = EXIT_REASON_EPT_VIOLATION;
- nested_vmx_vmexit(vcpu, exit_reason, 0, vcpu->arch.exit_qualification);
+
+ nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
vmcs12->guest_physical_address = fault->address;
}
return 0;
}
+static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ u64 address = vmcs12->pml_address;
+ int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML)) {
+ if (!nested_cpu_has_ept(vmcs12) ||
+ !IS_ALIGNED(address, 4096) ||
+ address >> maxphyaddr)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
struct vmx_msr_entry *e)
{
bool from_vmentry, u32 *entry_failure_code)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 exec_control;
+ u32 exec_control, vmcs12_exec_ctrl;
vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_APIC_REGISTER_VIRT);
if (nested_cpu_has(vmcs12,
- CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
- exec_control |= vmcs12->secondary_vm_exec_control;
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
+ vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
+ ~SECONDARY_EXEC_ENABLE_PML;
+ exec_control |= vmcs12_exec_ctrl;
+ }
if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) {
vmcs_write64(EOI_EXIT_BITMAP0,
if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_vmx_check_pml_controls(vcpu, vmcs12))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
vmx->nested.nested_vmx_procbased_ctls_low,
vmx->nested.nested_vmx_procbased_ctls_high) ||
vmx->nested.nested_vmx_entry_ctls_high))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) ||
!nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
!nested_cr3_valid(vcpu, vmcs12->host_cr3))
kvm_flush_pml_buffers(kvm);
}
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ gpa_t gpa;
+ struct page *page = NULL;
+ u64 *pml_address;
+
+ if (is_guest_mode(vcpu)) {
+ WARN_ON_ONCE(vmx->nested.pml_full);
+
+ /*
+ * Check if PML is enabled for the nested guest.
+ * Whether eptp bit 6 is set is already checked
+ * as part of A/D emulation.
+ */
+ vmcs12 = get_vmcs12(vcpu);
+ if (!nested_cpu_has_pml(vmcs12))
+ return 0;
+
+ if (vmcs12->guest_pml_index > PML_ENTITY_NUM) {
+ vmx->nested.pml_full = true;
+ return 1;
+ }
+
+ gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+
+ page = nested_get_page(vcpu, vmcs12->pml_address);
+ if (!page)
+ return 0;
+
+ pml_address = kmap(page);
+ pml_address[vmcs12->guest_pml_index--] = gpa;
+ kunmap(page);
+ nested_release_page_clean(page);
+ }
+
+ return 0;
+}
+
static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *memslot,
gfn_t offset, unsigned long mask)
.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
.flush_log_dirty = vmx_flush_log_dirty,
.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
+ .write_log_dirty = vmx_write_pml_buffer,
.pre_block = vmx_pre_block,
.post_block = vmx_post_block,
#include <linux/mmiotrace.h>
static unsigned long mmio_address;
-module_param(mmio_address, ulong, 0);
+module_param_hw(mmio_address, ulong, iomem, 0);
MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB "
"(or 8 MB if read_far is non-zero).");
# UAPI Header export list
include include/uapi/asm-generic/Kbuild.asm
-
-header-y += auxvec.h
-header-y += byteorder.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += swab.h
-header-y += termbits.h
-header-y += types.h
-header-y += unistd.h
* rotational or flash-based devices, and to get the job done quickly
* for applications consisting in many I/O-bound processes.
*
+ * NOTE: if the main or only goal, with a given device, is to achieve
+ * the maximum-possible throughput at all times, then do switch off
+ * all low-latency heuristics for that device, by setting low_latency
+ * to 0.
+ *
* BFQ is described in [1], where also a reference to the initial, more
* theoretical paper on BFQ can be found. The interested reader can find
* in the latter paper full details on the main algorithm, as well as
bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
{
struct bfq_sched_data *sd = entity->sched_data;
- struct bfq_service_tree *st = bfq_entity_service_tree(entity);
- int is_in_service = entity == sd->in_service_entity;
+ struct bfq_service_tree *st;
+ bool is_in_service;
if (!entity->on_st) /* entity never activated, or already inactive */
return false;
+ /*
+ * If we get here, then entity is active, which implies that
+ * bfq_group_set_parent has already been invoked for the group
+ * represented by entity. Therefore, the field
+ * entity->sched_data has been set, and we can safely use it.
+ */
+ st = bfq_entity_service_tree(entity);
+ is_in_service = entity == sd->in_service_entity;
+
if (is_in_service)
bfq_calc_finish(entity, entity->service);
return false;
}
- WARN_ON_ONCE(req->rq_flags & RQF_SPECIAL_PAYLOAD);
-
req->__data_len -= total_bytes;
/* update sector only for requests with clear definition of sector */
req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK;
}
- /*
- * If total number of sectors is less than the first segment
- * size, something has gone terribly wrong.
- */
- if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
- blk_dump_rq_flags(req, "request botched");
- req->__data_len = blk_rq_cur_bytes(req);
- }
+ if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) {
+ /*
+ * If total number of sectors is less than the first segment
+ * size, something has gone terribly wrong.
+ */
+ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
+ blk_dump_rq_flags(req, "request botched");
+ req->__data_len = blk_rq_cur_bytes(req);
+ }
- /* recalculate the number of segments */
- blk_recalc_rq_segments(req);
+ /* recalculate the number of segments */
+ blk_recalc_rq_segments(req);
+ }
return true;
}
}
EXPORT_SYMBOL(blk_mq_stop_hw_queue);
-void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
+static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
{
struct blk_mq_hw_ctx *hctx;
int i;
blk_queue_bounce(q, &bio);
+ blk_queue_split(q, &bio, q->bio_split);
+
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
bio_io_error(bio);
return BLK_QC_T_NONE;
}
- blk_queue_split(q, &bio, q->bio_split);
-
if (!is_flush_fua && !blk_queue_nomerges(q) &&
blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
return BLK_QC_T_NONE;
blk_mq_init_cpu_queues(q, set->nr_hw_queues);
- mutex_lock(&all_q_mutex);
get_online_cpus();
+ mutex_lock(&all_q_mutex);
list_add_tail(&q->all_q_node, &all_q_list);
blk_mq_add_queue_tag_set(set, q);
blk_mq_map_swqueue(q, cpu_online_mask);
- put_online_cpus();
mutex_unlock(&all_q_mutex);
+ put_online_cpus();
if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
int ret;
rcu_read_lock();
list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
- if (blk_stat_is_active(cb)) {
- bucket = cb->bucket_fn(rq);
- if (bucket < 0)
- continue;
- stat = &this_cpu_ptr(cb->cpu_stat)[bucket];
- __blk_stat_add(stat, value);
- }
+ if (!blk_stat_is_active(cb))
+ continue;
+
+ bucket = cb->bucket_fn(rq);
+ if (bucket < 0)
+ continue;
+
+ stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
+ __blk_stat_add(stat, value);
+ put_cpu_ptr(cb->cpu_stat);
}
rcu_read_unlock();
}
strlcpy(elevator_name, name, sizeof(elevator_name));
e = elevator_get(strstrip(elevator_name), true);
- if (!e) {
- printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
+ if (!e)
return -EINVAL;
- }
if (q->elevator &&
!strcmp(elevator_name, q->elevator->type->elevator_name)) {
if (!ret)
return count;
- printk(KERN_ERR "elevator: switch to %s failed\n", name);
return ret;
}
source "drivers/fsi/Kconfig"
+source "drivers/tee/Kconfig"
+
endmenu
obj-$(CONFIG_NVMEM) += nvmem/
obj-$(CONFIG_FPGA) += fpga/
obj-$(CONFIG_FSI) += fsi/
+obj-$(CONFIG_TEE) += tee/
acpi-y += sysfs.o
acpi-y += property.o
acpi-$(CONFIG_X86) += acpi_cmos_rtc.o
+acpi-$(CONFIG_X86) += x86/utils.o
acpi-$(CONFIG_DEBUG_FS) += debugfs.o
acpi-$(CONFIG_ACPI_NUMA) += numa.o
acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
.setup = acpi_apd_setup,
.fixed_clk_rate = 133000000,
};
+
+static const struct apd_device_desc hip07_i2c_desc = {
+ .setup = acpi_apd_setup,
+ .fixed_clk_rate = 200000000,
+};
+
+static const struct apd_device_desc hip08_i2c_desc = {
+ .setup = acpi_apd_setup,
+ .fixed_clk_rate = 250000000,
+};
#endif
#else
{ "APMC0D0F", APD_ADDR(xgene_i2c_desc) },
{ "BRCM900D", APD_ADDR(vulcan_spi_desc) },
{ "CAV900D", APD_ADDR(vulcan_spi_desc) },
+ { "HISI0A21", APD_ADDR(hip07_i2c_desc) },
+ { "HISI0A22", APD_ADDR(hip08_i2c_desc) },
#endif
{ }
};
writel(val, pdata->mmio_base + offset);
}
+/*
+ * BYT PWM used for backlight control by the i915 driver on systems without
+ * the Crystal Cove PMIC.
+ */
+static struct pwm_lookup byt_pwm_lookup[] = {
+ PWM_LOOKUP_WITH_MODULE("80860F09:00", 0, "0000:00:02.0",
+ "pwm_backlight", 0, PWM_POLARITY_NORMAL,
+ "pwm-lpss-platform"),
+};
+
+static void byt_pwm_setup(struct lpss_private_data *pdata)
+{
+ if (!acpi_dev_present("INT33FD", NULL, -1))
+ pwm_add_table(byt_pwm_lookup, ARRAY_SIZE(byt_pwm_lookup));
+}
+
#define LPSS_I2C_ENABLE 0x6c
static void byt_i2c_setup(struct lpss_private_data *pdata)
static const struct lpss_device_desc byt_pwm_dev_desc = {
.flags = LPSS_SAVE_CTX,
+ .setup = byt_pwm_setup,
};
static const struct lpss_device_desc bsw_pwm_dev_desc = {
# Makefile for ACPICA Core interpreter
#
-ccflags-y := -Os -DBUILDING_ACPICA
+ccflags-y := -Os -D_LINUX -DBUILDING_ACPICA
ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT
# use acpi.o to put all files here into acpi.o modparam namespace
--- /dev/null
+/******************************************************************************
+ *
+ * Module Name: acapps - common include for ACPI applications/tools
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2017, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions, and the following disclaimer,
+ * without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ * substantially similar to the "NO WARRANTY" disclaimer below
+ * ("Disclaimer") and any redistribution must be conditioned upon
+ * including a substantially similar Disclaimer requirement for further
+ * binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ * of any contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#ifndef _ACCONVERT
+#define _ACCONVERT
+
+/* Definitions for comment state */
+
+#define ASL_COMMENT_STANDARD 1
+#define ASLCOMMENT_INLINE 2
+#define ASL_COMMENT_OPEN_PAREN 3
+#define ASL_COMMENT_CLOSE_PAREN 4
+#define ASL_COMMENT_CLOSE_BRACE 5
+
+/* Definitions for comment print function*/
+
+#define AML_COMMENT_STANDARD 1
+#define AMLCOMMENT_INLINE 2
+#define AML_COMMENT_END_NODE 3
+#define AML_NAMECOMMENT 4
+#define AML_COMMENT_CLOSE_BRACE 5
+#define AML_COMMENT_ENDBLK 6
+#define AML_COMMENT_INCLUDE 7
+
+#ifdef ACPI_ASL_COMPILER
+/*
+ * cvcompiler
+ */
+void
+cv_process_comment(struct asl_comment_state current_state,
+ char *string_buffer, int c1);
+
+void
+cv_process_comment_type2(struct asl_comment_state current_state,
+ char *string_buffer);
+
+u32 cv_calculate_comment_lengths(union acpi_parse_object *op);
+
+void cv_process_comment_state(char input);
+
+char *cv_append_inline_comment(char *inline_comment, char *to_add);
+
+void cv_add_to_comment_list(char *to_add);
+
+void cv_place_comment(u8 type, char *comment_string);
+
+u32 cv_parse_op_block_type(union acpi_parse_object *op);
+
+struct acpi_comment_node *cv_comment_node_calloc(void);
+
+void cg_write_aml_def_block_comment(union acpi_parse_object *op);
+
+void
+cg_write_one_aml_comment(union acpi_parse_object *op,
+ char *comment_to_print, u8 input_option);
+
+void cg_write_aml_comment(union acpi_parse_object *op);
+
+/*
+ * cvparser
+ */
+void
+cv_init_file_tree(struct acpi_table_header *table,
+ u8 *aml_start, u32 aml_length);
+
+void cv_clear_op_comments(union acpi_parse_object *op);
+
+struct acpi_file_node *cv_filename_exists(char *filename,
+ struct acpi_file_node *head);
+
+void cv_label_file_node(union acpi_parse_object *op);
+
+void
+cv_capture_list_comments(struct acpi_parse_state *parser_state,
+ struct acpi_comment_node *list_head,
+ struct acpi_comment_node *list_tail);
+
+void cv_capture_comments_only(struct acpi_parse_state *parser_state);
+
+void cv_capture_comments(struct acpi_walk_state *walk_state);
+
+void cv_transfer_comments(union acpi_parse_object *op);
+
+/*
+ * cvdisasm
+ */
+void cv_switch_files(u32 level, union acpi_parse_object *op);
+
+u8 cv_file_has_switched(union acpi_parse_object *op);
+
+void cv_close_paren_write_comment(union acpi_parse_object *op, u32 level);
+
+void cv_close_brace_write_comment(union acpi_parse_object *op, u32 level);
+
+void
+cv_print_one_comment_list(struct acpi_comment_node *comment_list, u32 level);
+
+void
+cv_print_one_comment_type(union acpi_parse_object *op,
+ u8 comment_type, char *end_str, u32 level);
+
+#endif
+
+#endif /* _ACCONVERT */
#endif
+/*
+ * Meant for the -ca option.
+ */
+ACPI_INIT_GLOBAL(char *, acpi_gbl_current_inline_comment, NULL);
+ACPI_INIT_GLOBAL(char *, acpi_gbl_current_end_node_comment, NULL);
+ACPI_INIT_GLOBAL(char *, acpi_gbl_current_open_brace_comment, NULL);
+ACPI_INIT_GLOBAL(char *, acpi_gbl_current_close_brace_comment, NULL);
+
+ACPI_INIT_GLOBAL(char *, acpi_gbl_root_filename, NULL);
+ACPI_INIT_GLOBAL(char *, acpi_gbl_current_filename, NULL);
+ACPI_INIT_GLOBAL(char *, acpi_gbl_current_parent_filename, NULL);
+ACPI_INIT_GLOBAL(char *, acpi_gbl_current_include_filename, NULL);
+
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_last_list_head, NULL);
+
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_def_blk_comment_list_head,
+ NULL);
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_def_blk_comment_list_tail,
+ NULL);
+
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_reg_comment_list_head,
+ NULL);
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_reg_comment_list_tail,
+ NULL);
+
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_inc_comment_list_head,
+ NULL);
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_inc_comment_list_tail,
+ NULL);
+
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_end_blk_comment_list_head,
+ NULL);
+ACPI_INIT_GLOBAL(struct acpi_comment_node, *acpi_gbl_end_blk_comment_list_tail,
+ NULL);
+
+ACPI_INIT_GLOBAL(struct acpi_comment_addr_node,
+ *acpi_gbl_comment_addr_list_head, NULL);
+
+ACPI_INIT_GLOBAL(union acpi_parse_object, *acpi_gbl_current_scope, NULL);
+
+ACPI_INIT_GLOBAL(struct acpi_file_node, *acpi_gbl_file_tree_root, NULL);
+
+ACPI_GLOBAL(acpi_cache_t *, acpi_gbl_reg_comment_cache);
+ACPI_GLOBAL(acpi_cache_t *, acpi_gbl_comment_addr_cache);
+ACPI_GLOBAL(acpi_cache_t *, acpi_gbl_file_cache);
+
+ACPI_INIT_GLOBAL(u8, gbl_capture_comments, FALSE);
+
+ACPI_INIT_GLOBAL(u8, acpi_gbl_debug_asl_conversion, FALSE);
+ACPI_INIT_GLOBAL(ACPI_FILE, acpi_gbl_conv_debug_file, NULL);
+
+ACPI_GLOBAL(char, acpi_gbl_table_sig[4]);
+
/*****************************************************************************
*
* Application globals
/* Total number of aml opcodes defined */
-#define AML_NUM_OPCODES 0x82
+#define AML_NUM_OPCODES 0x83
/* Forward declarations */
#define ACPI_DISASM_ONLY_MEMBERS(a)
#endif
+#if defined(ACPI_ASL_COMPILER)
+#define ACPI_CONVERTER_ONLY_MEMBERS(a) a;
+#else
+#define ACPI_CONVERTER_ONLY_MEMBERS(a)
+#endif
+
#define ACPI_PARSE_COMMON \
- union acpi_parse_object *parent; /* Parent op */\
- u8 descriptor_type; /* To differentiate various internal objs */\
- u8 flags; /* Type of Op */\
- u16 aml_opcode; /* AML opcode */\
- u8 *aml; /* Address of declaration in AML */\
- union acpi_parse_object *next; /* Next op */\
- struct acpi_namespace_node *node; /* For use by interpreter */\
- union acpi_parse_value value; /* Value or args associated with the opcode */\
- u8 arg_list_length; /* Number of elements in the arg list */\
- ACPI_DISASM_ONLY_MEMBERS (\
- u16 disasm_flags; /* Used during AML disassembly */\
- u8 disasm_opcode; /* Subtype used for disassembly */\
- char *operator_symbol;/* Used for C-style operator name strings */\
- char aml_op_name[16]) /* Op name (debug only) */
+ union acpi_parse_object *parent; /* Parent op */\
+ u8 descriptor_type; /* To differentiate various internal objs */\
+ u8 flags; /* Type of Op */\
+ u16 aml_opcode; /* AML opcode */\
+ u8 *aml; /* Address of declaration in AML */\
+ union acpi_parse_object *next; /* Next op */\
+ struct acpi_namespace_node *node; /* For use by interpreter */\
+ union acpi_parse_value value; /* Value or args associated with the opcode */\
+ u8 arg_list_length; /* Number of elements in the arg list */\
+ ACPI_DISASM_ONLY_MEMBERS (\
+ u16 disasm_flags; /* Used during AML disassembly */\
+ u8 disasm_opcode; /* Subtype used for disassembly */\
+ char *operator_symbol; /* Used for C-style operator name strings */\
+ char aml_op_name[16]) /* Op name (debug only) */\
+ ACPI_CONVERTER_ONLY_MEMBERS (\
+ char *inline_comment; /* Inline comment */\
+ char *end_node_comment; /* End of node comment */\
+ char *name_comment; /* Comment associated with the first parameter of the name node */\
+ char *close_brace_comment; /* Comments that come after } on the same as } */\
+ struct acpi_comment_node *comment_list; /* comments that appears before this node */\
+ struct acpi_comment_node *end_blk_comment; /* comments that at the end of a block but before ) or } */\
+ char *cv_filename; /* Filename associated with this node. Used for ASL/ASL+ converter */\
+ char *cv_parent_filename) /* Parent filename associated with this node. Used for ASL/ASL+ converter */
+
+/* categories of comments */
+
+typedef enum {
+ STANDARD_COMMENT = 1,
+ INLINE_COMMENT,
+ ENDNODE_COMMENT,
+ OPENBRACE_COMMENT,
+ CLOSE_BRACE_COMMENT,
+ STD_DEFBLK_COMMENT,
+ END_DEFBLK_COMMENT,
+ FILENAME_COMMENT,
+ PARENTFILENAME_COMMENT,
+ ENDBLK_COMMENT,
+ INCLUDE_COMMENT
+} asl_comment_types;
/* Internal opcodes for disasm_opcode field above */
#define ACPI_DASM_LNOT_SUFFIX 0x09 /* End of a Lnot_equal (etc.) pair of opcodes */
#define ACPI_DASM_HID_STRING 0x0A /* String is a _HID or _CID */
#define ACPI_DASM_IGNORE_SINGLE 0x0B /* Ignore the opcode but not it's children */
-#define ACPI_DASM_SWITCH_PREDICATE 0x0C /* Object is a predicate for a Switch or Case block */
-#define ACPI_DASM_CASE 0x0D /* If/Else is a Case in a Switch/Case block */
-#define ACPI_DASM_DEFAULT 0x0E /* Else is a Default in a Switch/Case block */
+#define ACPI_DASM_SWITCH 0x0C /* While is a Switch */
+#define ACPI_DASM_SWITCH_PREDICATE 0x0D /* Object is a predicate for a Switch or Case block */
+#define ACPI_DASM_CASE 0x0E /* If/Else is a Case in a Switch/Case block */
+#define ACPI_DASM_DEFAULT 0x0F /* Else is a Default in a Switch/Case block */
+
+/*
+ * List struct used in the -ca option
+ */
+struct acpi_comment_node {
+ char *comment;
+ struct acpi_comment_node *next;
+};
+
+struct acpi_comment_addr_node {
+ u8 *addr;
+ struct acpi_comment_addr_node *next;
+};
+
+/*
+ * File node - used for "Include" operator file stack and
+ * depdendency tree for the -ca option
+ */
+struct acpi_file_node {
+ void *file;
+ char *filename;
+ char *file_start; /* Points to AML and indicates when the AML for this particular file starts. */
+ char *file_end; /* Points to AML and indicates when the AML for this particular file ends. */
+ struct acpi_file_node *next;
+ struct acpi_file_node *parent;
+ u8 include_written;
+ struct acpi_comment_node *include_comment;
+};
/*
* Generic operation (for example: If, While, Store)
ACPI_PARSE_COMMON union acpi_parse_object *child;
union acpi_parse_object *parent_method;
char *filename;
+ u8 file_changed;
+ char *parent_filename;
char *external_name;
char *namepath;
char name_seg[4];
struct acpi_parse_obj_asl asl;
};
+struct asl_comment_state {
+ u8 comment_type;
+ u32 spaces_before;
+ union acpi_parse_object *latest_parse_node;
+ union acpi_parse_object *parsing_paren_brace_node;
+ u8 capture_comments;
+};
+
/*
* Parse state - one state per parser invocation and each control
* method.
#define ACPI_IS_OCTAL_DIGIT(d) (((char)(d) >= '0') && ((char)(d) <= '7'))
+/*
+ * Macors used for the ASL-/ASL+ converter utility
+ */
+#ifdef ACPI_ASL_COMPILER
+
+#define ASL_CV_LABEL_FILENODE(a) cv_label_file_node(a);
+#define ASL_CV_CAPTURE_COMMENTS_ONLY(a) cv_capture_comments_only (a);
+#define ASL_CV_CAPTURE_COMMENTS(a) cv_capture_comments (a);
+#define ASL_CV_TRANSFER_COMMENTS(a) cv_transfer_comments (a);
+#define ASL_CV_CLOSE_PAREN(a,b) cv_close_paren_write_comment(a,b);
+#define ASL_CV_CLOSE_BRACE(a,b) cv_close_brace_write_comment(a,b);
+#define ASL_CV_SWITCH_FILES(a,b) cv_switch_files(a,b);
+#define ASL_CV_CLEAR_OP_COMMENTS(a) cv_clear_op_comments(a);
+#define ASL_CV_PRINT_ONE_COMMENT(a,b,c,d) cv_print_one_comment_type (a,b,c,d);
+#define ASL_CV_PRINT_ONE_COMMENT_LIST(a,b) cv_print_one_comment_list (a,b);
+#define ASL_CV_FILE_HAS_SWITCHED(a) cv_file_has_switched(a)
+#define ASL_CV_INIT_FILETREE(a,b,c) cv_init_file_tree(a,b,c);
+
+#else
+
+#define ASL_CV_LABEL_FILENODE(a)
+#define ASL_CV_CAPTURE_COMMENTS_ONLY(a)
+#define ASL_CV_CAPTURE_COMMENTS(a)
+#define ASL_CV_TRANSFER_COMMENTS(a)
+#define ASL_CV_CLOSE_PAREN(a,b) acpi_os_printf (")");
+#define ASL_CV_CLOSE_BRACE(a,b) acpi_os_printf ("}");
+#define ASL_CV_SWITCH_FILES(a,b)
+#define ASL_CV_CLEAR_OP_COMMENTS(a)
+#define ASL_CV_PRINT_ONE_COMMENT(a,b,c,d)
+#define ASL_CV_PRINT_ONE_COMMENT_LIST(a,b)
+#define ASL_CV_FILE_HAS_SWITCHED(a) 0
+#define ASL_CV_INIT_FILETREE(a,b,c)
+
+#endif
+
#endif /* ACMACROS_H */
#define ARGP_BUFFER_OP ARGP_LIST3 (ARGP_PKGLENGTH, ARGP_TERMARG, ARGP_BYTELIST)
#define ARGP_BYTE_OP ARGP_LIST1 (ARGP_BYTEDATA)
#define ARGP_BYTELIST_OP ARGP_LIST1 (ARGP_NAMESTRING)
+#define ARGP_COMMENT_OP ARGP_LIST2 (ARGP_BYTEDATA, ARGP_COMMENT)
#define ARGP_CONCAT_OP ARGP_LIST3 (ARGP_TERMARG, ARGP_TERMARG, ARGP_TARGET)
#define ARGP_CONCAT_RES_OP ARGP_LIST3 (ARGP_TERMARG, ARGP_TERMARG, ARGP_TARGET)
#define ARGP_COND_REF_OF_OP ARGP_LIST2 (ARGP_SIMPLENAME, ARGP_TARGET)
#define ARGI_BUFFER_OP ARGI_LIST1 (ARGI_INTEGER)
#define ARGI_BYTE_OP ARGI_INVALID_OPCODE
#define ARGI_BYTELIST_OP ARGI_INVALID_OPCODE
+#define ARGI_COMMENT_OP ARGI_INVALID_OPCODE
#define ARGI_CONCAT_OP ARGI_LIST3 (ARGI_ANYTYPE, ARGI_ANYTYPE, ARGI_TARGETREF)
#define ARGI_CONCAT_RES_OP ARGI_LIST3 (ARGI_BUFFER, ARGI_BUFFER, ARGI_TARGETREF)
#define ARGI_COND_REF_OF_OP ARGI_LIST2 (ARGI_OBJECT_REF, ARGI_TARGETREF)
/* primary opcodes */
-#define AML_NULL_CHAR (u16) 0x00
-
#define AML_ZERO_OP (u16) 0x00
#define AML_ONE_OP (u16) 0x01
-#define AML_UNASSIGNED (u16) 0x02
#define AML_ALIAS_OP (u16) 0x06
#define AML_NAME_OP (u16) 0x08
#define AML_BYTE_OP (u16) 0x0a
#define AML_SCOPE_OP (u16) 0x10
#define AML_BUFFER_OP (u16) 0x11
#define AML_PACKAGE_OP (u16) 0x12
-#define AML_VAR_PACKAGE_OP (u16) 0x13 /* ACPI 2.0 */
+#define AML_VARIABLE_PACKAGE_OP (u16) 0x13 /* ACPI 2.0 */
#define AML_METHOD_OP (u16) 0x14
#define AML_EXTERNAL_OP (u16) 0x15 /* ACPI 6.0 */
#define AML_DUAL_NAME_PREFIX (u16) 0x2e
-#define AML_MULTI_NAME_PREFIX_OP (u16) 0x2f
-#define AML_NAME_CHAR_SUBSEQ (u16) 0x30
-#define AML_NAME_CHAR_FIRST (u16) 0x41
-#define AML_EXTENDED_OP_PREFIX (u16) 0x5b
+#define AML_MULTI_NAME_PREFIX (u16) 0x2f
+#define AML_EXTENDED_PREFIX (u16) 0x5b
#define AML_ROOT_PREFIX (u16) 0x5c
#define AML_PARENT_PREFIX (u16) 0x5e
-#define AML_LOCAL_OP (u16) 0x60
+#define AML_FIRST_LOCAL_OP (u16) 0x60 /* Used for Local op # calculations */
#define AML_LOCAL0 (u16) 0x60
#define AML_LOCAL1 (u16) 0x61
#define AML_LOCAL2 (u16) 0x62
#define AML_LOCAL5 (u16) 0x65
#define AML_LOCAL6 (u16) 0x66
#define AML_LOCAL7 (u16) 0x67
-#define AML_ARG_OP (u16) 0x68
+#define AML_FIRST_ARG_OP (u16) 0x68 /* Used for Arg op # calculations */
#define AML_ARG0 (u16) 0x68
#define AML_ARG1 (u16) 0x69
#define AML_ARG2 (u16) 0x6a
#define AML_STORE_OP (u16) 0x70
#define AML_REF_OF_OP (u16) 0x71
#define AML_ADD_OP (u16) 0x72
-#define AML_CONCAT_OP (u16) 0x73
+#define AML_CONCATENATE_OP (u16) 0x73
#define AML_SUBTRACT_OP (u16) 0x74
#define AML_INCREMENT_OP (u16) 0x75
#define AML_DECREMENT_OP (u16) 0x76
#define AML_FIND_SET_LEFT_BIT_OP (u16) 0x81
#define AML_FIND_SET_RIGHT_BIT_OP (u16) 0x82
#define AML_DEREF_OF_OP (u16) 0x83
-#define AML_CONCAT_RES_OP (u16) 0x84 /* ACPI 2.0 */
+#define AML_CONCATENATE_TEMPLATE_OP (u16) 0x84 /* ACPI 2.0 */
#define AML_MOD_OP (u16) 0x85 /* ACPI 2.0 */
#define AML_NOTIFY_OP (u16) 0x86
#define AML_SIZE_OF_OP (u16) 0x87
#define AML_CREATE_BIT_FIELD_OP (u16) 0x8d
#define AML_OBJECT_TYPE_OP (u16) 0x8e
#define AML_CREATE_QWORD_FIELD_OP (u16) 0x8f /* ACPI 2.0 */
-#define AML_LAND_OP (u16) 0x90
-#define AML_LOR_OP (u16) 0x91
-#define AML_LNOT_OP (u16) 0x92
-#define AML_LEQUAL_OP (u16) 0x93
-#define AML_LGREATER_OP (u16) 0x94
-#define AML_LLESS_OP (u16) 0x95
+#define AML_LOGICAL_AND_OP (u16) 0x90
+#define AML_LOGICAL_OR_OP (u16) 0x91
+#define AML_LOGICAL_NOT_OP (u16) 0x92
+#define AML_LOGICAL_EQUAL_OP (u16) 0x93
+#define AML_LOGICAL_GREATER_OP (u16) 0x94
+#define AML_LOGICAL_LESS_OP (u16) 0x95
#define AML_TO_BUFFER_OP (u16) 0x96 /* ACPI 2.0 */
-#define AML_TO_DECSTRING_OP (u16) 0x97 /* ACPI 2.0 */
-#define AML_TO_HEXSTRING_OP (u16) 0x98 /* ACPI 2.0 */
+#define AML_TO_DECIMAL_STRING_OP (u16) 0x97 /* ACPI 2.0 */
+#define AML_TO_HEX_STRING_OP (u16) 0x98 /* ACPI 2.0 */
#define AML_TO_INTEGER_OP (u16) 0x99 /* ACPI 2.0 */
#define AML_TO_STRING_OP (u16) 0x9c /* ACPI 2.0 */
-#define AML_COPY_OP (u16) 0x9d /* ACPI 2.0 */
+#define AML_COPY_OBJECT_OP (u16) 0x9d /* ACPI 2.0 */
#define AML_MID_OP (u16) 0x9e /* ACPI 2.0 */
#define AML_CONTINUE_OP (u16) 0x9f /* ACPI 2.0 */
#define AML_IF_OP (u16) 0xa0
#define AML_NOOP_OP (u16) 0xa3
#define AML_RETURN_OP (u16) 0xa4
#define AML_BREAK_OP (u16) 0xa5
-#define AML_BREAK_POINT_OP (u16) 0xcc
+#define AML_COMMENT_OP (u16) 0xa9
+#define AML_BREAKPOINT_OP (u16) 0xcc
#define AML_ONES_OP (u16) 0xff
-/* prefixed opcodes */
+/*
+ * Combination opcodes (actually two one-byte opcodes)
+ * Used by the disassembler and iASL compiler
+ */
+#define AML_LOGICAL_GREATER_EQUAL_OP (u16) 0x9295 /* LNot (LLess) */
+#define AML_LOGICAL_LESS_EQUAL_OP (u16) 0x9294 /* LNot (LGreater) */
+#define AML_LOGICAL_NOT_EQUAL_OP (u16) 0x9293 /* LNot (LEqual) */
+
+/* Prefixed (2-byte) opcodes (with AML_EXTENDED_PREFIX) */
-#define AML_EXTENDED_OPCODE (u16) 0x5b00 /* prefix for 2-byte opcodes */
+#define AML_EXTENDED_OPCODE (u16) 0x5b00 /* Prefix for 2-byte opcodes */
#define AML_MUTEX_OP (u16) 0x5b01
#define AML_EVENT_OP (u16) 0x5b02
-#define AML_SHIFT_RIGHT_BIT_OP (u16) 0x5b10
-#define AML_SHIFT_LEFT_BIT_OP (u16) 0x5b11
-#define AML_COND_REF_OF_OP (u16) 0x5b12
+#define AML_SHIFT_RIGHT_BIT_OP (u16) 0x5b10 /* Obsolete, not in ACPI spec */
+#define AML_SHIFT_LEFT_BIT_OP (u16) 0x5b11 /* Obsolete, not in ACPI spec */
+#define AML_CONDITIONAL_REF_OF_OP (u16) 0x5b12
#define AML_CREATE_FIELD_OP (u16) 0x5b13
#define AML_LOAD_TABLE_OP (u16) 0x5b1f /* ACPI 2.0 */
#define AML_LOAD_OP (u16) 0x5b20
#define AML_FIELD_OP (u16) 0x5b81
#define AML_DEVICE_OP (u16) 0x5b82
#define AML_PROCESSOR_OP (u16) 0x5b83
-#define AML_POWER_RES_OP (u16) 0x5b84
+#define AML_POWER_RESOURCE_OP (u16) 0x5b84
#define AML_THERMAL_ZONE_OP (u16) 0x5b85
#define AML_INDEX_FIELD_OP (u16) 0x5b86
#define AML_BANK_FIELD_OP (u16) 0x5b87
#define AML_DATA_REGION_OP (u16) 0x5b88 /* ACPI 2.0 */
-/*
- * Combination opcodes (actually two one-byte opcodes)
- * Used by the disassembler and iASL compiler
- */
-#define AML_LGREATEREQUAL_OP (u16) 0x9295
-#define AML_LLESSEQUAL_OP (u16) 0x9294
-#define AML_LNOTEQUAL_OP (u16) 0x9293
-
/*
* Opcodes for "Field" operators
*/
#define ARGP_SIMPLENAME 0x12 /* name_string | local_term | arg_term */
#define ARGP_NAME_OR_REF 0x13 /* For object_type only */
#define ARGP_MAX 0x13
+#define ARGP_COMMENT 0x14
/*
* Resolved argument types for the AML Interpreter
#define ARGI_INVALID_OPCODE 0xFFFFFFFF
/*
- * hash offsets
- */
-#define AML_EXTOP_HASH_OFFSET 22
-#define AML_LNOT_HASH_OFFSET 19
-
-/*
- * opcode groups and types
+ * Some of the flags and types below are of the form:
+ *
+ * AML_FLAGS_EXEC_#A_#T,#R, or
+ * AML_TYPE_EXEC_#A_#T,#R where:
+ *
+ * #A is the number of required arguments
+ * #T is the number of target operands
+ * #R indicates whether there is a return value
*/
-#define OPGRP_NAMED 0x01
-#define OPGRP_FIELD 0x02
-#define OPGRP_BYTELIST 0x04
/*
- * Opcode information
+ * Opcode information flags
*/
-
-/* Opcode flags */
-
#define AML_LOGICAL 0x0001
#define AML_LOGICAL_NUMERIC 0x0002
#define AML_MATH 0x0004
#define AML_CONSTANT 0x2000
#define AML_NO_OPERAND_RESOLVE 0x4000
-/* Convenient flag groupings */
+/* Convenient flag groupings of the flags above */
#define AML_FLAGS_EXEC_0A_0T_1R AML_HAS_RETVAL
#define AML_FLAGS_EXEC_1A_0T_0R AML_HAS_ARGS /* Monadic1 */
/*
* The opcode Type is used in a dispatch table, do not change
- * without updating the table.
+ * or add anything new without updating the table.
*/
#define AML_TYPE_EXEC_0A_0T_1R 0x00
#define AML_TYPE_EXEC_1A_0T_0R 0x01 /* Monadic1 */
#define AML_TYPE_METHOD_CALL 0x10
-/* Misc */
+/* Miscellaneous types */
#define AML_TYPE_CREATE_FIELD 0x11
#define AML_TYPE_CREATE_OBJECT 0x12
#define AML_TYPE_NAMED_SIMPLE 0x16
#define AML_TYPE_NAMED_COMPLEX 0x17
#define AML_TYPE_RETURN 0x18
-
#define AML_TYPE_UNDEFINED 0x19
#define AML_TYPE_BOGUS 0x1A
status = acpi_get_object_info(obj_handle, &obj_info);
if (ACPI_FAILURE(status)) {
+ ACPI_FREE(pathname);
return (status);
}
#include "accommon.h"
#include "amlcode.h"
#include "acdebug.h"
+#include "acinterp.h"
#define _COMPONENT ACPI_CA_DEBUGGER
ACPI_MODULE_NAME("dbxface")
*
* RETURN: Status
*
- * DESCRIPTION: Called for AML_BREAK_POINT_OP
+ * DESCRIPTION: Called for AML_BREAKPOINT_OP
*
******************************************************************************/
walk_state->method_breakpoint = 1; /* Must be non-zero! */
}
+ acpi_ex_exit_interpreter();
status = acpi_db_start_command(walk_state, op);
+ acpi_ex_enter_interpreter();
/* User commands complete, continue execution of the interrupted method */
break;
- case AML_BREAK_POINT_OP:
+ case AML_BREAKPOINT_OP:
acpi_db_signal_break_point(walk_state);
*
* FUNCTION: acpi_ds_method_data_get_type
*
- * PARAMETERS: opcode - Either AML_LOCAL_OP or AML_ARG_OP
+ * PARAMETERS: opcode - Either AML_FIRST LOCAL_OP or
+ * AML_FIRST_ARG_OP
* index - Which Local or Arg whose type to get
* walk_state - Current walk state object
*
((op->common.parent->common.aml_opcode ==
AML_PACKAGE_OP)
|| (op->common.parent->common.aml_opcode ==
- AML_VAR_PACKAGE_OP))) {
+ AML_VARIABLE_PACKAGE_OP))) {
/*
* We didn't find the target and we are populating elements
* of a package - ignore if slack enabled. Some ASL code
if ((op->common.parent->common.aml_opcode == AML_PACKAGE_OP) ||
(op->common.parent->common.aml_opcode ==
- AML_VAR_PACKAGE_OP)) {
+ AML_VARIABLE_PACKAGE_OP)) {
/*
* Attempt to resolve the node to a value before we insert it into
* the package. If this is a reference to a common data type,
parent = op->common.parent;
while ((parent->common.aml_opcode == AML_PACKAGE_OP) ||
- (parent->common.aml_opcode == AML_VAR_PACKAGE_OP)) {
+ (parent->common.aml_opcode == AML_VARIABLE_PACKAGE_OP)) {
parent = parent->common.parent;
}
switch (op_info->type) {
case AML_TYPE_LOCAL_VARIABLE:
- /* Local ID (0-7) is (AML opcode - base AML_LOCAL_OP) */
+ /* Local ID (0-7) is (AML opcode - base AML_FIRST_LOCAL_OP) */
obj_desc->reference.value =
- ((u32)opcode) - AML_LOCAL_OP;
+ ((u32)opcode) - AML_FIRST_LOCAL_OP;
obj_desc->reference.class = ACPI_REFCLASS_LOCAL;
#ifndef ACPI_NO_METHOD_EXECUTION
case AML_TYPE_METHOD_ARGUMENT:
- /* Arg ID (0-6) is (AML opcode - base AML_ARG_OP) */
+ /* Arg ID (0-6) is (AML opcode - base AML_FIRST_ARG_OP) */
- obj_desc->reference.value = ((u32)opcode) - AML_ARG_OP;
+ obj_desc->reference.value =
+ ((u32)opcode) - AML_FIRST_ARG_OP;
obj_desc->reference.class = ACPI_REFCLASS_ARG;
#ifndef ACPI_NO_METHOD_EXECUTION
break;
case AML_PACKAGE_OP:
- case AML_VAR_PACKAGE_OP:
+ case AML_VARIABLE_PACKAGE_OP:
status =
acpi_ds_build_internal_package_obj(walk_state, op, length,
if ((!op->common.parent) ||
((op->common.parent->common.aml_opcode != AML_PACKAGE_OP) &&
(op->common.parent->common.aml_opcode !=
- AML_VAR_PACKAGE_OP)
+ AML_VARIABLE_PACKAGE_OP)
&& (op->common.parent->common.aml_opcode !=
AML_NAME_OP))) {
walk_state->result_obj = obj_desc;
if ((op->common.parent->common.aml_opcode == AML_REGION_OP) ||
(op->common.parent->common.aml_opcode == AML_DATA_REGION_OP)
|| (op->common.parent->common.aml_opcode == AML_PACKAGE_OP)
- || (op->common.parent->common.aml_opcode ==
- AML_VAR_PACKAGE_OP)
|| (op->common.parent->common.aml_opcode == AML_BUFFER_OP)
+ || (op->common.parent->common.aml_opcode ==
+ AML_VARIABLE_PACKAGE_OP)
|| (op->common.parent->common.aml_opcode ==
AML_INT_EVAL_SUBTREE_OP)
|| (op->common.parent->common.aml_opcode ==
*/
if (status == AE_NOT_FOUND) {
if (parent_op->common.aml_opcode ==
- AML_COND_REF_OF_OP) {
+ AML_CONDITIONAL_REF_OF_OP) {
/*
* For the Conditional Reference op, it's OK if
* the name is not found; We just need a way to
}
if ((op->common.parent->common.aml_opcode == AML_PACKAGE_OP) ||
- (op->common.parent->common.aml_opcode == AML_VAR_PACKAGE_OP) ||
+ (op->common.parent->common.aml_opcode == AML_VARIABLE_PACKAGE_OP) ||
(op->common.parent->common.aml_opcode == AML_REF_OF_OP)) {
/* TBD: Should we specify this feature as a bit of op_info->Flags of these opcodes? */
if ((op->asl.parent) &&
((op->asl.parent->asl.aml_opcode == AML_PACKAGE_OP)
|| (op->asl.parent->asl.aml_opcode ==
- AML_VAR_PACKAGE_OP))) {
+ AML_VARIABLE_PACKAGE_OP))) {
ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
"Method Reference in a Package, Op=%p\n",
op));
status = acpi_ex_create_processor(walk_state);
break;
- case AML_POWER_RES_OP:
+ case AML_POWER_RESOURCE_OP:
status = acpi_ex_create_power_resource(walk_state);
break;
ACPI_FUNCTION_TRACE(ex_do_logical_numeric_op);
switch (opcode) {
- case AML_LAND_OP: /* LAnd (Integer0, Integer1) */
+ case AML_LOGICAL_AND_OP: /* LAnd (Integer0, Integer1) */
if (integer0 && integer1) {
local_result = TRUE;
}
break;
- case AML_LOR_OP: /* LOr (Integer0, Integer1) */
+ case AML_LOGICAL_OR_OP: /* LOr (Integer0, Integer1) */
if (integer0 || integer1) {
local_result = TRUE;
integer1 = local_operand1->integer.value;
switch (opcode) {
- case AML_LEQUAL_OP: /* LEqual (Operand0, Operand1) */
+ case AML_LOGICAL_EQUAL_OP: /* LEqual (Operand0, Operand1) */
if (integer0 == integer1) {
local_result = TRUE;
}
break;
- case AML_LGREATER_OP: /* LGreater (Operand0, Operand1) */
+ case AML_LOGICAL_GREATER_OP: /* LGreater (Operand0, Operand1) */
if (integer0 > integer1) {
local_result = TRUE;
}
break;
- case AML_LLESS_OP: /* LLess (Operand0, Operand1) */
+ case AML_LOGICAL_LESS_OP: /* LLess (Operand0, Operand1) */
if (integer0 < integer1) {
local_result = TRUE;
(length0 > length1) ? length1 : length0);
switch (opcode) {
- case AML_LEQUAL_OP: /* LEqual (Operand0, Operand1) */
+ case AML_LOGICAL_EQUAL_OP: /* LEqual (Operand0, Operand1) */
/* Length and all bytes must be equal */
}
break;
- case AML_LGREATER_OP: /* LGreater (Operand0, Operand1) */
+ case AML_LOGICAL_GREATER_OP: /* LGreater (Operand0, Operand1) */
if (compare > 0) {
local_result = TRUE;
}
break;
- case AML_LLESS_OP: /* LLess (Operand0, Operand1) */
+ case AML_LOGICAL_LESS_OP: /* LLess (Operand0, Operand1) */
if (compare > 0) {
goto cleanup; /* FALSE */
/* Set up multi prefixes */
- *temp_ptr++ = AML_MULTI_NAME_PREFIX_OP;
+ *temp_ptr++ = AML_MULTI_NAME_PREFIX;
*temp_ptr++ = (char)num_name_segs;
} else if (2 == num_name_segs) {
}
break;
- case AML_MULTI_NAME_PREFIX_OP:
+ case AML_MULTI_NAME_PREFIX:
ACPI_DEBUG_PRINT((ACPI_DB_LOAD,
"MultiNamePrefix at %p\n",
case AML_FIND_SET_RIGHT_BIT_OP:
case AML_FROM_BCD_OP:
case AML_TO_BCD_OP:
- case AML_COND_REF_OF_OP:
+ case AML_CONDITIONAL_REF_OF_OP:
/* Create a return object of type Integer for these opcodes */
}
break;
- case AML_COND_REF_OF_OP: /* cond_ref_of (source_object, Result) */
+ case AML_CONDITIONAL_REF_OF_OP: /* cond_ref_of (source_object, Result) */
/*
* This op is a little strange because the internal return value is
* different than the return value stored in the result descriptor
/*
* ACPI 2.0 Opcodes
*/
- case AML_COPY_OP: /* Copy (Source, Target) */
+ case AML_COPY_OBJECT_OP: /* copy_object (Source, Target) */
status =
acpi_ut_copy_iobject_to_iobject(operand[0], &return_desc,
walk_state);
break;
- case AML_TO_DECSTRING_OP: /* to_decimal_string (Data, Result) */
+ case AML_TO_DECIMAL_STRING_OP: /* to_decimal_string (Data, Result) */
status =
acpi_ex_convert_to_string(operand[0], &return_desc,
}
break;
- case AML_TO_HEXSTRING_OP: /* to_hex_string (Data, Result) */
+ case AML_TO_HEX_STRING_OP: /* to_hex_string (Data, Result) */
status =
acpi_ex_convert_to_string(operand[0], &return_desc,
/* Examine the AML opcode */
switch (walk_state->opcode) {
- case AML_LNOT_OP: /* LNot (Operand) */
+ case AML_LOGICAL_NOT_OP: /* LNot (Operand) */
return_desc = acpi_ut_create_integer_object((u64) 0);
if (!return_desc) {
* NOTE: We use LNOT_OP here in order to force resolution of the
* reference operand to an actual integer.
*/
- status =
- acpi_ex_resolve_operands(AML_LNOT_OP, &temp_desc,
- walk_state);
+ status = acpi_ex_resolve_operands(AML_LOGICAL_NOT_OP,
+ &temp_desc, walk_state);
if (ACPI_FAILURE(status)) {
ACPI_EXCEPTION((AE_INFO, status,
"While resolving operands for [%s]",
NULL, &return_desc->integer.value);
break;
- case AML_CONCAT_OP: /* Concatenate (Data1, Data2, Result) */
+ case AML_CONCATENATE_OP: /* Concatenate (Data1, Data2, Result) */
status =
acpi_ex_do_concatenate(operand[0], operand[1], &return_desc,
operand[0]->buffer.pointer, length);
break;
- case AML_CONCAT_RES_OP:
+ case AML_CONCATENATE_TEMPLATE_OP:
/* concatenate_res_template (Buffer, Buffer, Result) (ACPI 2.0) */
* Change to: (M == P[i])
*/
status =
- acpi_ex_do_logical_op(AML_LEQUAL_OP, match_obj, package_obj,
- &logical_result);
+ acpi_ex_do_logical_op(AML_LOGICAL_EQUAL_OP, match_obj,
+ package_obj, &logical_result);
if (ACPI_FAILURE(status)) {
return (FALSE);
}
* Change to: (M >= P[i]) (M not_less than P[i])
*/
status =
- acpi_ex_do_logical_op(AML_LLESS_OP, match_obj, package_obj,
- &logical_result);
+ acpi_ex_do_logical_op(AML_LOGICAL_LESS_OP, match_obj,
+ package_obj, &logical_result);
if (ACPI_FAILURE(status)) {
return (FALSE);
}
* Change to: (M > P[i])
*/
status =
- acpi_ex_do_logical_op(AML_LGREATER_OP, match_obj,
+ acpi_ex_do_logical_op(AML_LOGICAL_GREATER_OP, match_obj,
package_obj, &logical_result);
if (ACPI_FAILURE(status)) {
return (FALSE);
* Change to: (M <= P[i]) (M not_greater than P[i])
*/
status =
- acpi_ex_do_logical_op(AML_LGREATER_OP, match_obj,
+ acpi_ex_do_logical_op(AML_LOGICAL_GREATER_OP, match_obj,
package_obj, &logical_result);
if (ACPI_FAILURE(status)) {
return (FALSE);
* Change to: (M < P[i])
*/
status =
- acpi_ex_do_logical_op(AML_LLESS_OP, match_obj, package_obj,
- &logical_result);
+ acpi_ex_do_logical_op(AML_LOGICAL_LESS_OP, match_obj,
+ package_obj, &logical_result);
if (ACPI_FAILURE(status)) {
return (FALSE);
}
if ((walk_state->opcode ==
AML_INT_METHODCALL_OP)
- || (walk_state->opcode == AML_COPY_OP)) {
+ || (walk_state->opcode ==
+ AML_COPY_OBJECT_OP)) {
break;
}
/* Only limited target types possible for everything except copy_object */
- if (walk_state->opcode != AML_COPY_OP) {
+ if (walk_state->opcode != AML_COPY_OBJECT_OP) {
/*
* Only copy_object allows all object types to be overwritten. For
* target_ref(s), there are restrictions on the object types that
case ACPI_TYPE_STRING:
case ACPI_TYPE_BUFFER:
- if ((walk_state->opcode == AML_COPY_OP) || !implicit_conversion) {
+ if ((walk_state->opcode == AML_COPY_OBJECT_OP) ||
+ !implicit_conversion) {
/*
* However, copy_object and Stores to arg_x do not perform
* an implicit conversion, as per the ACPI specification.
/* For copy_object, no further validation necessary */
- if (walk_state->opcode == AML_COPY_OP) {
+ if (walk_state->opcode == AML_COPY_OBJECT_OP) {
break;
}
{"PCI", 0x0CF8, 0x0CFF, ACPI_OSI_WIN_XP}
};
-#define ACPI_PORT_INFO_ENTRIES ACPI_ARRAY_LENGTH (acpi_protected_ports)
+#define ACPI_PORT_INFO_ENTRIES ACPI_ARRAY_LENGTH (acpi_protected_ports)
/******************************************************************************
*
acpi_io_address last_address;
const struct acpi_port_info *port_info;
- ACPI_FUNCTION_TRACE(hw_validate_io_request);
+ ACPI_FUNCTION_NAME(hw_validate_io_request);
/* Supported widths are 8/16/32 */
ACPI_ERROR((AE_INFO,
"Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X",
ACPI_FORMAT_UINT64(address), byte_width));
- return_ACPI_STATUS(AE_LIMIT);
+ return (AE_LIMIT);
}
/* Exit if requested address is not within the protected port table */
if (address > acpi_protected_ports[ACPI_PORT_INFO_ENTRIES - 1].end) {
- return_ACPI_STATUS(AE_OK);
+ return (AE_OK);
}
/* Check request against the list of protected I/O ports */
for (i = 0; i < ACPI_PORT_INFO_ENTRIES; i++, port_info++) {
/*
* Check if the requested address range will write to a reserved
- * port. Four cases to consider:
+ * port. There are four cases to consider:
*
* 1) Address range is contained completely in the port address range
* 2) Address range overlaps port range at the port range start
}
}
- return_ACPI_STATUS(AE_OK);
+ return (AE_OK);
}
/******************************************************************************
* FUNCTION: acpi_hw_read_port
*
* PARAMETERS: Address Address of I/O port/register to read
- * Value Where value is placed
+ * Value Where value (data) is returned
* Width Number of bits
*
* RETURN: Status and value read from port
/*
* There has been a protection violation within the request. Fall
* back to byte granularity port I/O and ignore the failing bytes.
- * This provides Windows compatibility.
+ * This provides compatibility with other ACPI implementations.
*/
for (i = 0, *value = 0; i < width; i += 8) {
/*
* There has been a protection violation within the request. Fall
* back to byte granularity port I/O and ignore the failing bytes.
- * This provides Windows compatibility.
+ * This provides compatibility with other ACPI implementations.
*/
for (i = 0; i < width; i += 8) {
flags));
break;
- case AML_MULTI_NAME_PREFIX_OP:
+ case AML_MULTI_NAME_PREFIX:
/* More than one name_seg, search rules do not apply */
/* Object was successfully repaired */
if (package_index != ACPI_NOT_PACKAGE_ELEMENT) {
- /*
- * The original object is a package element. We need to
- * decrement the reference count of the original object,
- * for removing it from the package.
- *
- * However, if the original object was just wrapped with a
- * package object as part of the repair, we don't need to
- * change the reference count.
- */
+
+ /* Update reference count of new object */
+
if (!(info->return_flags & ACPI_OBJECT_WRAPPED)) {
new_object->common.reference_count =
return_object->common.reference_count;
-
- if (return_object->common.reference_count > 1) {
- return_object->common.reference_count--;
- }
}
ACPI_DEBUG_PRINT((ACPI_DB_REPAIR,
return (status);
}
- /* Take care with reference counts */
-
if (original_element != *element_ptr) {
- /* Element was replaced */
+ /* Update reference count of new object */
(*element_ptr)->common.reference_count =
original_ref_count;
-
- acpi_ut_remove_reference(original_element);
}
element_ptr++;
internal_name[1] = AML_DUAL_NAME_PREFIX;
result = &internal_name[2];
} else {
- internal_name[1] = AML_MULTI_NAME_PREFIX_OP;
+ internal_name[1] = AML_MULTI_NAME_PREFIX;
internal_name[2] = (char)num_segments;
result = &internal_name[3];
}
internal_name[i] = AML_DUAL_NAME_PREFIX;
result = &internal_name[(acpi_size)i + 1];
} else {
- internal_name[i] = AML_MULTI_NAME_PREFIX_OP;
+ internal_name[i] = AML_MULTI_NAME_PREFIX;
internal_name[(acpi_size)i + 1] = (char)num_segments;
result = &internal_name[(acpi_size)i + 2];
}
*/
if (prefix_length < internal_name_length) {
switch (internal_name[prefix_length]) {
- case AML_MULTI_NAME_PREFIX_OP:
+ case AML_MULTI_NAME_PREFIX:
/* <count> 4-byte names */
void acpi_ns_terminate(void)
{
acpi_status status;
+ union acpi_operand_object *prev;
+ union acpi_operand_object *next;
ACPI_FUNCTION_TRACE(ns_terminate);
-#ifdef ACPI_EXEC_APP
- {
- union acpi_operand_object *prev;
- union acpi_operand_object *next;
+ /* Delete any module-level code blocks */
- /* Delete any module-level code blocks */
-
- next = acpi_gbl_module_code_list;
- while (next) {
- prev = next;
- next = next->method.mutex;
- prev->method.mutex = NULL; /* Clear the Mutex (cheated) field */
- acpi_ut_remove_reference(prev);
- }
+ next = acpi_gbl_module_code_list;
+ while (next) {
+ prev = next;
+ next = next->method.mutex;
+ prev->method.mutex = NULL; /* Clear the Mutex (cheated) field */
+ acpi_ut_remove_reference(prev);
}
-#endif
/*
* Free the entire namespace -- all nodes and all objects
#include "amlcode.h"
#include "acnamesp.h"
#include "acdispat.h"
+#include "acconvert.h"
#define _COMPONENT ACPI_PARSER
ACPI_MODULE_NAME("psargs")
end += 1 + (2 * ACPI_NAME_SIZE);
break;
- case AML_MULTI_NAME_PREFIX_OP:
+ case AML_MULTI_NAME_PREFIX:
/* Multiple name segments, 4 chars each, count in next byte */
/* 2) not_found during a cond_ref_of(x) is ok by definition */
else if (walk_state->op->common.aml_opcode ==
- AML_COND_REF_OF_OP) {
+ AML_CONDITIONAL_REF_OF_OP) {
status = AE_OK;
}
((arg->common.parent->common.aml_opcode ==
AML_PACKAGE_OP)
|| (arg->common.parent->common.aml_opcode ==
- AML_VAR_PACKAGE_OP))) {
+ AML_VARIABLE_PACKAGE_OP))) {
status = AE_OK;
}
}
ACPI_FUNCTION_TRACE(ps_get_next_field);
+ ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
aml = parser_state->aml;
/* Determine field type */
/* Decode the field type */
+ ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
switch (opcode) {
case AML_INT_NAMEDFIELD_OP:
acpi_ps_set_name(field, name);
parser_state->aml += ACPI_NAME_SIZE;
+ ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
+
+#ifdef ACPI_ASL_COMPILER
+ /*
+ * Because the package length isn't represented as a parse tree object,
+ * take comments surrounding this and add to the previously created
+ * parse node.
+ */
+ if (field->common.inline_comment) {
+ field->common.name_comment =
+ field->common.inline_comment;
+ }
+ field->common.inline_comment = acpi_gbl_current_inline_comment;
+ acpi_gbl_current_inline_comment = NULL;
+#endif
+
/* Get the length which is encoded as a package length */
field->common.value.size =
if (ACPI_GET8(parser_state->aml) == AML_BUFFER_OP) {
parser_state->aml++;
+ ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
pkg_end = parser_state->aml;
pkg_length =
acpi_ps_get_next_package_length(parser_state);
pkg_end += pkg_length;
+ ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
if (parser_state->aml < pkg_end) {
/* Non-empty list */
opcode = ACPI_GET8(parser_state->aml);
parser_state->aml++;
+ ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
switch (opcode) {
case AML_BYTE_OP: /* AML_BYTEDATA_ARG */
/* Fill in bytelist data */
+ ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
arg->named.value.size = buffer_length;
arg->named.data = parser_state->aml;
}
#include "acparser.h"
#include "acdispat.h"
#include "amlcode.h"
+#include "acconvert.h"
#define _COMPONENT ACPI_PARSER
ACPI_MODULE_NAME("psloop")
!walk_state->arg_count) {
walk_state->aml = walk_state->parser_state.aml;
+ switch (op->common.aml_opcode) {
+ case AML_METHOD_OP:
+ case AML_BUFFER_OP:
+ case AML_PACKAGE_OP:
+ case AML_VARIABLE_PACKAGE_OP:
+ case AML_WHILE_OP:
+
+ break;
+
+ default:
+
+ ASL_CV_CAPTURE_COMMENTS(walk_state);
+ break;
+ }
+
status =
acpi_ps_get_next_arg(walk_state,
&(walk_state->parser_state),
case AML_BUFFER_OP:
case AML_PACKAGE_OP:
- case AML_VAR_PACKAGE_OP:
+ case AML_VARIABLE_PACKAGE_OP:
if ((op->common.parent) &&
(op->common.parent->common.aml_opcode ==
/* Iterative parsing loop, while there is more AML to process: */
while ((parser_state->aml < parser_state->aml_end) || (op)) {
+ ASL_CV_CAPTURE_COMMENTS(walk_state);
+
aml_op_start = parser_state->aml;
if (!op) {
status =
*/
walk_state->arg_count = 0;
+ switch (op->common.aml_opcode) {
+ case AML_BYTE_OP:
+ case AML_WORD_OP:
+ case AML_DWORD_OP:
+ case AML_QWORD_OP:
+
+ break;
+
+ default:
+
+ ASL_CV_CAPTURE_COMMENTS(walk_state);
+ break;
+ }
+
/* Are there any arguments that must be processed? */
if (walk_state->arg_types) {
#include "accommon.h"
#include "acparser.h"
#include "amlcode.h"
+#include "acconvert.h"
#define _COMPONENT ACPI_PARSER
ACPI_MODULE_NAME("psobject")
*/
while (GET_CURRENT_ARG_TYPE(walk_state->arg_types) &&
(GET_CURRENT_ARG_TYPE(walk_state->arg_types) != ARGP_NAME)) {
+ ASL_CV_CAPTURE_COMMENTS(walk_state);
status =
acpi_ps_get_next_arg(walk_state,
&(walk_state->parser_state),
INCREMENT_ARG_LIST(walk_state->arg_types);
}
+ /* are there any inline comments associated with the name_seg?? If so, save this. */
+
+ ASL_CV_CAPTURE_COMMENTS(walk_state);
+
+#ifdef ACPI_ASL_COMPILER
+ if (acpi_gbl_current_inline_comment != NULL) {
+ unnamed_op->common.name_comment =
+ acpi_gbl_current_inline_comment;
+ acpi_gbl_current_inline_comment = NULL;
+ }
+#endif
+
/*
* Make sure that we found a NAME and didn't run out of arguments
*/
acpi_ps_append_arg(*op, unnamed_op->common.value.arg);
+#ifdef ACPI_ASL_COMPILER
+
+ /* save any comments that might be associated with unnamed_op. */
+
+ (*op)->common.inline_comment = unnamed_op->common.inline_comment;
+ (*op)->common.end_node_comment = unnamed_op->common.end_node_comment;
+ (*op)->common.close_brace_comment =
+ unnamed_op->common.close_brace_comment;
+ (*op)->common.name_comment = unnamed_op->common.name_comment;
+ (*op)->common.comment_list = unnamed_op->common.comment_list;
+ (*op)->common.end_blk_comment = unnamed_op->common.end_blk_comment;
+ (*op)->common.cv_filename = unnamed_op->common.cv_filename;
+ (*op)->common.cv_parent_filename =
+ unnamed_op->common.cv_parent_filename;
+ (*op)->named.aml = unnamed_op->common.aml;
+
+ unnamed_op->common.inline_comment = NULL;
+ unnamed_op->common.end_node_comment = NULL;
+ unnamed_op->common.close_brace_comment = NULL;
+ unnamed_op->common.name_comment = NULL;
+ unnamed_op->common.comment_list = NULL;
+ unnamed_op->common.end_blk_comment = NULL;
+#endif
+
if ((*op)->common.aml_opcode == AML_REGION_OP ||
(*op)->common.aml_opcode == AML_DATA_REGION_OP) {
/*
AML_DEVICE_OP
AML_THERMAL_ZONE_OP
AML_METHOD_OP
- AML_POWER_RES_OP
+ AML_POWER_RESOURCE_OP
AML_PROCESSOR_OP
AML_FIELD_OP
AML_INDEX_FIELD_OP
AML_DEVICE_OP
AML_THERMAL_ZONE_OP
AML_METHOD_OP
- AML_POWER_RES_OP
+ AML_POWER_RESOURCE_OP
AML_PROCESSOR_OP
AML_FIELD_OP
AML_INDEX_FIELD_OP
AML_DEVICE_OP
AML_THERMAL_ZONE_OP
AML_METHOD_OP
- AML_POWER_RES_OP
+ AML_POWER_RESOURCE_OP
AML_PROCESSOR_OP
AML_NAME_OP
AML_ALIAS_OP
AML_DEVICE_OP
AML_THERMAL_ZONE_OP
AML_METHOD_OP
- AML_POWER_RES_OP
+ AML_POWER_RESOURCE_OP
AML_PROCESSOR_OP
AML_NAME_OP
AML_ALIAS_OP
must be deferred until needed
AML_METHOD_OP
- AML_VAR_PACKAGE_OP
+ AML_VARIABLE_PACKAGE_OP
AML_CREATE_FIELD_OP
AML_CREATE_BIT_FIELD_OP
AML_CREATE_BYTE_FIELD_OP
/* 81 */ ACPI_OP("External", ARGP_EXTERNAL_OP, ARGI_EXTERNAL_OP,
ACPI_TYPE_ANY, AML_CLASS_EXECUTE, /* ? */
- AML_TYPE_EXEC_3A_0T_0R, AML_FLAGS_EXEC_3A_0T_0R)
+ AML_TYPE_EXEC_3A_0T_0R, AML_FLAGS_EXEC_3A_0T_0R),
+/* 82 */ ACPI_OP("Comment", ARGP_COMMENT_OP, ARGI_COMMENT_OP,
+ ACPI_TYPE_STRING, AML_CLASS_ARGUMENT,
+ AML_TYPE_LITERAL, AML_CONSTANT)
/*! [End] no source code translation !*/
};
/* 0x90 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x73, 0x74,
/* 0x98 */ 0x75, 0x76, _UNK, _UNK, 0x77, 0x78, 0x79, 0x7A,
/* 0xA0 */ 0x3e, 0x3f, 0x40, 0x41, 0x42, 0x43, 0x60, 0x61,
-/* 0xA8 */ 0x62, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK,
+/* 0xA8 */ 0x62, 0x82, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK,
/* 0xB0 */ _UNK, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK,
/* 0xB8 */ _UNK, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK,
/* 0xC0 */ _UNK, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK, _UNK,
aml = parser_state->aml;
opcode = (u16) ACPI_GET8(aml);
- if (opcode == AML_EXTENDED_OP_PREFIX) {
+ if (opcode == AML_EXTENDED_PREFIX) {
/* Extended opcode, get the second opcode byte */
|| (op->common.parent->common.aml_opcode ==
AML_BANK_FIELD_OP)
|| (op->common.parent->common.aml_opcode ==
- AML_VAR_PACKAGE_OP)) {
+ AML_VARIABLE_PACKAGE_OP)) {
replacement_op =
acpi_ps_alloc_op(AML_INT_RETURN_VALUE_OP,
op->common.aml);
if ((op->common.aml_opcode == AML_BUFFER_OP)
|| (op->common.aml_opcode == AML_PACKAGE_OP)
|| (op->common.aml_opcode ==
- AML_VAR_PACKAGE_OP)) {
+ AML_VARIABLE_PACKAGE_OP)) {
replacement_op =
acpi_ps_alloc_op(op->common.
aml_opcode,
#include "accommon.h"
#include "acparser.h"
#include "amlcode.h"
+#include "acconvert.h"
#define _COMPONENT ACPI_PARSER
ACPI_MODULE_NAME("pstree")
next = acpi_ps_get_arg(op, 0);
if (next) {
+ ASL_CV_LABEL_FILENODE(next);
return (next);
}
next = op->common.next;
if (next) {
+ ASL_CV_LABEL_FILENODE(next);
return (next);
}
while (parent) {
arg = acpi_ps_get_arg(parent, 0);
while (arg && (arg != origin) && (arg != op)) {
+
+ ASL_CV_LABEL_FILENODE(arg);
arg = arg->common.next;
}
/* Found sibling of parent */
+ ASL_CV_LABEL_FILENODE(parent->common.next);
return (parent->common.next);
}
parent = parent->common.parent;
}
+ ASL_CV_LABEL_FILENODE(next);
return (next);
}
child = acpi_ps_get_arg(op, 1);
break;
- case AML_POWER_RES_OP:
+ case AML_POWER_RESOURCE_OP:
case AML_INDEX_FIELD_OP:
child = acpi_ps_get_arg(op, 2);
#include "accommon.h"
#include "acparser.h"
#include "amlcode.h"
+#include "acconvert.h"
#define _COMPONENT ACPI_PARSER
ACPI_MODULE_NAME("psutils")
acpi_ps_init_op(op, opcode);
op->common.aml = aml;
op->common.flags = flags;
+ ASL_CV_CLEAR_OP_COMMENTS(op);
+
+ if (opcode == AML_SCOPE_OP) {
+ acpi_gbl_current_scope = op;
+ }
+ }
+
+ if (gbl_capture_comments) {
+ ASL_CV_TRANSFER_COMMENTS(op);
}
return (op);
{
ACPI_FUNCTION_NAME(ps_free_op);
+ ASL_CV_CLEAR_OP_COMMENTS(op);
if (op->common.aml_opcode == AML_INT_RETURN_VALUE_OP) {
ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS,
"Free retval op: %p\n", op));
if (ACPI_FAILURE(status)) {
return (status);
}
+#ifdef ACPI_ASL_COMPILER
+ /*
+ * For use with the ASL-/ASL+ option. This cache keeps track of regular
+ * 0xA9 0x01 comments.
+ */
+ status =
+ acpi_os_create_cache("Acpi-Comment",
+ sizeof(struct acpi_comment_node),
+ ACPI_MAX_COMMENT_CACHE_DEPTH,
+ &acpi_gbl_reg_comment_cache);
+ if (ACPI_FAILURE(status)) {
+ return (status);
+ }
+
+ /*
+ * This cache keeps track of the starting addresses of where the comments
+ * lie. This helps prevent duplication of comments.
+ */
+ status =
+ acpi_os_create_cache("Acpi-Comment-Addr",
+ sizeof(struct acpi_comment_addr_node),
+ ACPI_MAX_COMMENT_CACHE_DEPTH,
+ &acpi_gbl_comment_addr_cache);
+ if (ACPI_FAILURE(status)) {
+ return (status);
+ }
+
+ /*
+ * This cache will be used for nodes that represent files.
+ */
+ status =
+ acpi_os_create_cache("Acpi-File", sizeof(struct acpi_file_node),
+ ACPI_MAX_COMMENT_CACHE_DEPTH,
+ &acpi_gbl_file_cache);
+ if (ACPI_FAILURE(status)) {
+ return (status);
+ }
+#endif
+
#ifdef ACPI_DBG_TRACK_ALLOCATIONS
/* Memory allocation lists */
(void)acpi_os_delete_cache(acpi_gbl_ps_node_ext_cache);
acpi_gbl_ps_node_ext_cache = NULL;
+#ifdef ACPI_ASL_COMPILER
+ (void)acpi_os_delete_cache(acpi_gbl_reg_comment_cache);
+ acpi_gbl_reg_comment_cache = NULL;
+
+ (void)acpi_os_delete_cache(acpi_gbl_comment_addr_cache);
+ acpi_gbl_comment_addr_cache = NULL;
+
+ (void)acpi_os_delete_cache(acpi_gbl_file_cache);
+ acpi_gbl_file_cache = NULL;
+#endif
+
#ifdef ACPI_DBG_TRACK_ALLOCATIONS
/* Debug only - display leftover memory allocation, if any */
ACPI_FUNCTION_ENTRY();
- if (!cache_name || !return_cache || (object_size < 16)) {
+ if (!cache_name || !return_cache || !object_size) {
return (AE_BAD_PARAMETER);
}
}
ACPI_EXPORT_SYMBOL(acpi_trace_point)
+
#endif
return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
}
+ /*
+ * The end_tag opcode must be followed by a zero byte.
+ * Although this byte is technically defined to be a checksum,
+ * in practice, all ASL compilers set this byte to zero.
+ */
+ if (*(aml + 1) != 0) {
+ return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
+ }
+
/* Return the pointer to the end_tag if requested */
if (!user_function) {
*
* PARAMETERS: module_name - Caller's module name (for error output)
* line_number - Caller's line number (for error output)
- * status - Status to be formatted
+ * status - Status value to be decoded/formatted
* format - Printf format string + additional args
*
* RETURN: None
*
* FUNCTION: acpi_warning
*
- * PARAMETERS: module_name - Caller's module name (for error output)
- * line_number - Caller's line number (for error output)
+ * PARAMETERS: module_name - Caller's module name (for warning output)
+ * line_number - Caller's line number (for warning output)
* format - Printf format string + additional args
*
* RETURN: None
*
* FUNCTION: acpi_info
*
- * PARAMETERS: module_name - Caller's module name (for error output)
- * line_number - Caller's line number (for error output)
- * format - Printf format string + additional args
+ * PARAMETERS: format - Printf format string + additional args
*
* RETURN: None
*
* DESCRIPTION: Print generic "ACPI:" information message. There is no
* module/line/version info in order to keep the message simple.
*
- * TBD: module_name and line_number args are not needed, should be removed.
- *
******************************************************************************/
void ACPI_INTERNAL_VAR_XFACE acpi_info(const char *format, ...)
{
*
* FUNCTION: acpi_bios_warning
*
- * PARAMETERS: module_name - Caller's module name (for error output)
- * line_number - Caller's line number (for error output)
+ * PARAMETERS: module_name - Caller's module name (for warning output)
+ * line_number - Caller's line number (for warning output)
* format - Printf format string + additional args
*
* RETURN: None
return ret;
}
+static inline bool iort_iommu_driver_enabled(u8 type)
+{
+ switch (type) {
+ case ACPI_IORT_NODE_SMMU_V3:
+ return IS_BUILTIN(CONFIG_ARM_SMMU_V3);
+ case ACPI_IORT_NODE_SMMU:
+ return IS_BUILTIN(CONFIG_ARM_SMMU);
+ default:
+ pr_warn("IORT node type %u does not describe an SMMU\n", type);
+ return false;
+ }
+}
+
+#ifdef CONFIG_IOMMU_API
+static inline
+const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+{
+ return (fwspec && fwspec->ops) ? fwspec->ops : NULL;
+}
+
+static inline
+int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+{
+ int err = 0;
+
+ if (!IS_ERR_OR_NULL(ops) && ops->add_device && dev->bus &&
+ !dev->iommu_group)
+ err = ops->add_device(dev);
+
+ return err;
+}
+#else
+static inline
+const struct iommu_ops *iort_fwspec_iommu_ops(struct iommu_fwspec *fwspec)
+{ return NULL; }
+static inline
+int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev)
+{ return 0; }
+#endif
+
static const struct iommu_ops *iort_iommu_xlate(struct device *dev,
struct acpi_iort_node *node,
u32 streamid)
int ret = -ENODEV;
struct fwnode_handle *iort_fwnode;
+ /*
+ * If we already translated the fwspec there
+ * is nothing left to do, return the iommu_ops.
+ */
+ ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
+ if (ops)
+ return ops;
+
if (node) {
iort_fwnode = iort_get_fwnode(node);
if (!iort_fwnode)
return NULL;
ops = iommu_ops_from_fwnode(iort_fwnode);
+ /*
+ * If the ops look-up fails, this means that either
+ * the SMMU drivers have not been probed yet or that
+ * the SMMU drivers are not built in the kernel;
+ * Depending on whether the SMMU drivers are built-in
+ * in the kernel or not, defer the IOMMU configuration
+ * or just abort it.
+ */
if (!ops)
- return NULL;
+ return iort_iommu_driver_enabled(node->type) ?
+ ERR_PTR(-EPROBE_DEFER) : NULL;
ret = arm_smmu_iort_xlate(dev, streamid, iort_fwnode, ops);
}
struct acpi_iort_node *node, *parent;
const struct iommu_ops *ops = NULL;
u32 streamid = 0;
+ int err;
if (dev_is_pci(dev)) {
struct pci_bus *bus = to_pci_dev(dev)->bus;
while (parent) {
ops = iort_iommu_xlate(dev, parent, streamid);
+ if (IS_ERR_OR_NULL(ops))
+ return ops;
parent = iort_node_map_platform_id(node, &streamid,
IORT_IOMMU_TYPE,
}
}
+ /*
+ * If we have reason to believe the IOMMU driver missed the initial
+ * add_device callback for dev, replay it to get things in order.
+ */
+ err = iort_add_device_replay(ops, dev);
+ if (err)
+ ops = ERR_PTR(err);
+
return ops;
}
}
iort_init_platform_devices();
-
- acpi_probe_device_table(iort);
}
if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) ||
(test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) &&
(battery->capacity_now <= battery->alarm)))
- pm_wakeup_event(&battery->device->dev, 0);
+ pm_wakeup_hard_event(&battery->device->dev);
return result;
}
acpi_status status;
unsigned long long sta;
+ if (acpi_device_always_present(device)) {
+ acpi_set_device_status(device, ACPI_STA_DEFAULT);
+ return 0;
+ }
+
status = acpi_bus_get_status_handle(device->handle, &sta);
if (ACPI_FAILURE(status))
return -ENODEV;
}
if (state)
- pm_wakeup_event(&device->dev, 0);
+ pm_wakeup_hard_event(&device->dev);
ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
if (ret == NOTIFY_DONE)
} else {
int keycode;
- pm_wakeup_event(&device->dev, 0);
+ pm_wakeup_hard_event(&device->dev);
if (button->suspended)
break;
lid_device = device;
}
+ device_init_wakeup(&device->dev, true);
printk(KERN_INFO PREFIX "%s [%s]\n", name, acpi_device_bid(device));
return 0;
#include <linux/pm_qos.h>
#include <linux/pm_domain.h>
#include <linux/pm_runtime.h>
+#include <linux/suspend.h>
#include "internal.h"
mutex_lock(&acpi_pm_notifier_lock);
if (adev->wakeup.flags.notifier_present) {
- __pm_wakeup_event(adev->wakeup.ws, 0);
+ pm_wakeup_ws_event(adev->wakeup.ws, 0, true);
if (adev->wakeup.context.work.func)
queue_pm_work(&adev->wakeup.context.work);
}
struct list_head *physnode_list;
unsigned int node_id;
int retval = -EINVAL;
- enum dev_dma_attr attr;
if (has_acpi_companion(dev)) {
if (acpi_dev) {
if (!has_acpi_companion(dev))
ACPI_COMPANION_SET(dev, acpi_dev);
- attr = acpi_get_dma_attr(acpi_dev);
- if (attr != DEV_DMA_NOT_SUPPORTED)
- acpi_dma_configure(dev, attr);
-
acpi_physnode_link_name(physical_node_name, node_id);
retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj,
physical_node_name);
.address = 0x00,
.reg = 0x13,
.bit = 0x05,
- },
+ }, /* ALD1 */
{
.address = 0x04,
.reg = 0x13,
.bit = 0x06,
- },
+ }, /* ALD2 */
{
.address = 0x08,
.reg = 0x13,
.bit = 0x07,
- },
+ }, /* ALD3 */
{
.address = 0x0c,
.reg = 0x12,
.bit = 0x03,
- },
+ }, /* DLD1 */
{
.address = 0x10,
.reg = 0x12,
.bit = 0x04,
- },
+ }, /* DLD2 */
{
.address = 0x14,
.reg = 0x12,
.bit = 0x05,
- },
+ }, /* DLD3 */
{
.address = 0x18,
.reg = 0x12,
.bit = 0x06,
- },
+ }, /* DLD4 */
{
.address = 0x1c,
.reg = 0x12,
.bit = 0x00,
- },
+ }, /* ELD1 */
{
.address = 0x20,
.reg = 0x12,
.bit = 0x01,
- },
+ }, /* ELD2 */
{
.address = 0x24,
.reg = 0x12,
.bit = 0x02,
- },
+ }, /* ELD3 */
{
.address = 0x28,
.reg = 0x13,
.bit = 0x02,
- },
+ }, /* FLD1 */
{
.address = 0x2c,
.reg = 0x13,
.bit = 0x03,
- },
+ }, /* FLD2 */
{
.address = 0x30,
.reg = 0x13,
.bit = 0x04,
- },
+ }, /* FLD3 */
{
- .address = 0x38,
+ .address = 0x34,
.reg = 0x10,
.bit = 0x03,
- },
+ }, /* BUC1 */
{
- .address = 0x3c,
+ .address = 0x38,
.reg = 0x10,
.bit = 0x06,
- },
+ }, /* BUC2 */
{
- .address = 0x40,
+ .address = 0x3c,
.reg = 0x10,
.bit = 0x05,
- },
+ }, /* BUC3 */
{
- .address = 0x44,
+ .address = 0x40,
.reg = 0x10,
.bit = 0x04,
- },
+ }, /* BUC4 */
{
- .address = 0x48,
+ .address = 0x44,
.reg = 0x10,
.bit = 0x01,
- },
+ }, /* BUC5 */
{
- .address = 0x4c,
+ .address = 0x48,
.reg = 0x10,
.bit = 0x00
- },
+ }, /* BUC6 */
};
/* TMP0 - TMP5 are the same, all from GPADC */
mutex_unlock(&resource->resource_lock);
}
+
+ mutex_unlock(&power_resource_list_lock);
+}
+
+void acpi_turn_off_unused_power_resources(void)
+{
+ struct acpi_power_resource *resource;
+
+ mutex_lock(&power_resource_list_lock);
+
list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) {
int result, state;
* @dev: The pointer to the device
* @attr: device dma attributes
*/
-void acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
+int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr)
{
const struct iommu_ops *iommu;
+ u64 size;
iort_set_dma_mask(dev);
iommu = iort_iommu_configure(dev);
+ if (IS_ERR(iommu))
+ return PTR_ERR(iommu);
+ size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
/*
* Assume dma valid range starts at 0 and covers the whole
* coherent_dma_mask.
*/
- arch_setup_dma_ops(dev, 0, dev->coherent_dma_mask + 1, iommu,
- attr == DEV_DMA_COHERENT);
+ arch_setup_dma_ops(dev, 0, size, iommu, attr == DEV_DMA_COHERENT);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(acpi_dma_configure);
*/
static void acpi_pm_end(void)
{
+ acpi_turn_off_unused_power_resources();
acpi_scan_lock_release();
/*
* This is necessary in case acpi_pm_finish() is not called during a
acpi_os_wait_events_complete();
if (acpi_sci_irq_valid())
enable_irq_wake(acpi_sci_irq);
+
return 0;
}
+static void acpi_freeze_wake(void)
+{
+ /*
+ * If IRQD_WAKEUP_ARMED is not set for the SCI at this point, it means
+ * that the SCI has triggered while suspended, so cancel the wakeup in
+ * case it has not been a wakeup event (the GPEs will be checked later).
+ */
+ if (acpi_sci_irq_valid() &&
+ !irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq)))
+ pm_system_cancel_wakeup();
+}
+
+static void acpi_freeze_sync(void)
+{
+ /*
+ * Process all pending events in case there are any wakeup ones.
+ *
+ * The EC driver uses the system workqueue, so that one needs to be
+ * flushed too.
+ */
+ acpi_os_wait_events_complete();
+ flush_scheduled_work();
+}
+
static void acpi_freeze_restore(void)
{
acpi_disable_wakeup_devices(ACPI_STATE_S0);
if (acpi_sci_irq_valid())
disable_irq_wake(acpi_sci_irq);
+
acpi_enable_all_runtime_gpes();
}
static const struct platform_freeze_ops acpi_freeze_ops = {
.begin = acpi_freeze_begin,
.prepare = acpi_freeze_prepare,
+ .wake = acpi_freeze_wake,
+ .sync = acpi_freeze_sync,
.restore = acpi_freeze_restore,
.end = acpi_freeze_end,
};
extern struct mutex acpi_device_lock;
extern void acpi_resume_power_resources(void);
+extern void acpi_turn_off_unused_power_resources(void);
static inline acpi_status acpi_set_waking_vector(u32 wakeup_address)
{
--- /dev/null
+/*
+ * X86 ACPI Utility Functions
+ *
+ * Copyright (C) 2017 Hans de Goede <hdegoede@redhat.com>
+ *
+ * Based on various non upstream patches to support the CHT Whiskey Cove PMIC:
+ * Copyright (C) 2013-2015 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/acpi.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include "../internal.h"
+
+/*
+ * Some ACPI devices are hidden (status == 0x0) in recent BIOS-es because
+ * some recent Windows drivers bind to one device but poke at multiple
+ * devices at the same time, so the others get hidden.
+ * We work around this by always reporting ACPI_STA_DEFAULT for these
+ * devices. Note this MUST only be done for devices where this is safe.
+ *
+ * This forcing of devices to be present is limited to specific CPU (SoC)
+ * models both to avoid potentially causing trouble on other models and
+ * because some HIDs are re-used on different SoCs for completely
+ * different devices.
+ */
+struct always_present_id {
+ struct acpi_device_id hid[2];
+ struct x86_cpu_id cpu_ids[2];
+ const char *uid;
+};
+
+#define ICPU(model) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, }
+
+#define ENTRY(hid, uid, cpu_models) { \
+ { { hid, }, {} }, \
+ { cpu_models, {} }, \
+ uid, \
+}
+
+static const struct always_present_id always_present_ids[] = {
+ /*
+ * Bay / Cherry Trail PWM directly poked by GPU driver in win10,
+ * but Linux uses a separate PWM driver, harmless if not used.
+ */
+ ENTRY("80860F09", "1", ICPU(INTEL_FAM6_ATOM_SILVERMONT1)),
+ ENTRY("80862288", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT)),
+ /*
+ * The INT0002 device is necessary to clear wakeup interrupt sources
+ * on Cherry Trail devices, without it we get nobody cared IRQ msgs.
+ */
+ ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT)),
+};
+
+bool acpi_device_always_present(struct acpi_device *adev)
+{
+ u32 *status = (u32 *)&adev->status;
+ u32 old_status = *status;
+ bool ret = false;
+ unsigned int i;
+
+ /* acpi_match_device_ids checks status, so set it to default */
+ *status = ACPI_STA_DEFAULT;
+ for (i = 0; i < ARRAY_SIZE(always_present_ids); i++) {
+ if (acpi_match_device_ids(adev, always_present_ids[i].hid))
+ continue;
+
+ if (!adev->pnp.unique_id ||
+ strcmp(adev->pnp.unique_id, always_present_ids[i].uid))
+ continue;
+
+ if (!x86_match_cpu(always_present_ids[i].cpu_ids))
+ continue;
+
+ if (old_status != ACPI_STA_DEFAULT) /* Log only once */
+ dev_info(&adev->dev,
+ "Device [%s] is in always present list\n",
+ adev->pnp.bus_id);
+
+ ret = true;
+ break;
+ }
+ *status = old_status;
+
+ return ret;
+}
#include <linux/device.h>
#include <linux/delay.h>
+#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/wait.h>
if (ret)
goto pinctrl_bind_failed;
+ ret = dma_configure(dev);
+ if (ret)
+ goto dma_failed;
+
if (driver_sysfs_add(dev)) {
printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n",
__func__, dev_name(dev));
goto done;
probe_failed:
+ dma_deconfigure(dev);
+dma_failed:
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_DRIVER_NOT_BOUND, dev);
drv->remove(dev);
device_links_driver_cleanup(dev);
+ dma_deconfigure(dev);
+
devres_release_all(dev);
dev->driver = NULL;
dev_set_drvdata(dev, NULL);
* This file is released under the GPLv2.
*/
+#include <linux/acpi.h>
#include <linux/dma-mapping.h>
#include <linux/export.h>
#include <linux/gfp.h>
+#include <linux/of_device.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
vunmap(cpu_addr);
}
#endif
+
+/*
+ * Common configuration to enable DMA API use for a device
+ */
+#include <linux/pci.h>
+
+int dma_configure(struct device *dev)
+{
+ struct device *bridge = NULL, *dma_dev = dev;
+ enum dev_dma_attr attr;
+ int ret = 0;
+
+ if (dev_is_pci(dev)) {
+ bridge = pci_get_host_bridge_device(to_pci_dev(dev));
+ dma_dev = bridge;
+ if (IS_ENABLED(CONFIG_OF) && dma_dev->parent &&
+ dma_dev->parent->of_node)
+ dma_dev = dma_dev->parent;
+ }
+
+ if (dma_dev->of_node) {
+ ret = of_dma_configure(dev, dma_dev->of_node);
+ } else if (has_acpi_companion(dma_dev)) {
+ attr = acpi_get_dma_attr(to_acpi_device_node(dma_dev->fwnode));
+ if (attr != DEV_DMA_NOT_SUPPORTED)
+ ret = acpi_dma_configure(dev, attr);
+ }
+
+ if (bridge)
+ pci_put_host_bridge_device(bridge);
+
+ return ret;
+}
+
+void dma_deconfigure(struct device *dev)
+{
+ of_dma_deconfigure(dev);
+ acpi_dma_deconfigure(dev);
+}
if (async_error)
goto Complete;
- if (pm_wakeup_pending()) {
- async_error = -EBUSY;
- goto Complete;
- }
-
if (dev->power.syscore || dev->power.direct_complete)
goto Complete;
/* First wakeup IRQ seen by the kernel in the last cycle. */
unsigned int pm_wakeup_irq __read_mostly;
-/* If set and the system is suspending, terminate the suspend. */
-static bool pm_abort_suspend __read_mostly;
+/* If greater than 0 and the system is suspending, terminate the suspend. */
+static atomic_t pm_abort_suspend __read_mostly;
/*
* Combined counters of registered wakeup events and wakeup events in progress.
/**
* wakup_source_activate - Mark given wakeup source as active.
* @ws: Wakeup source to handle.
+ * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
*
* Update the @ws' statistics and, if @ws has just been activated, notify the PM
* core of the event by incrementing the counter of of wakeup events being
* processed.
*/
-static void wakeup_source_activate(struct wakeup_source *ws)
+static void wakeup_source_activate(struct wakeup_source *ws, bool hard)
{
unsigned int cec;
"unregistered wakeup source\n"))
return;
- /*
- * active wakeup source should bring the system
- * out of PM_SUSPEND_FREEZE state
- */
- freeze_wake();
+ if (hard)
+ pm_system_wakeup();
ws->active = true;
ws->active_count++;
/**
* wakeup_source_report_event - Report wakeup event using the given source.
* @ws: Wakeup source to report the event for.
+ * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
*/
-static void wakeup_source_report_event(struct wakeup_source *ws)
+static void wakeup_source_report_event(struct wakeup_source *ws, bool hard)
{
ws->event_count++;
/* This is racy, but the counter is approximate anyway. */
ws->wakeup_count++;
if (!ws->active)
- wakeup_source_activate(ws);
+ wakeup_source_activate(ws, hard);
}
/**
spin_lock_irqsave(&ws->lock, flags);
- wakeup_source_report_event(ws);
+ wakeup_source_report_event(ws, false);
del_timer(&ws->timer);
ws->timer_expires = 0;
}
/**
- * __pm_wakeup_event - Notify the PM core of a wakeup event.
+ * pm_wakeup_ws_event - Notify the PM core of a wakeup event.
* @ws: Wakeup source object associated with the event source.
* @msec: Anticipated event processing time (in milliseconds).
+ * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
*
* Notify the PM core of a wakeup event whose source is @ws that will take
* approximately @msec milliseconds to be processed by the kernel. If @ws is
*
* It is safe to call this function from interrupt context.
*/
-void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
+void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard)
{
unsigned long flags;
unsigned long expires;
spin_lock_irqsave(&ws->lock, flags);
- wakeup_source_report_event(ws);
+ wakeup_source_report_event(ws, hard);
if (!msec) {
wakeup_source_deactivate(ws);
unlock:
spin_unlock_irqrestore(&ws->lock, flags);
}
-EXPORT_SYMBOL_GPL(__pm_wakeup_event);
-
+EXPORT_SYMBOL_GPL(pm_wakeup_ws_event);
/**
* pm_wakeup_event - Notify the PM core of a wakeup event.
* @dev: Device the wakeup event is related to.
* @msec: Anticipated event processing time (in milliseconds).
+ * @hard: If set, abort suspends in progress and wake up from suspend-to-idle.
*
- * Call __pm_wakeup_event() for the @dev's wakeup source object.
+ * Call pm_wakeup_ws_event() for the @dev's wakeup source object.
*/
-void pm_wakeup_event(struct device *dev, unsigned int msec)
+void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard)
{
unsigned long flags;
return;
spin_lock_irqsave(&dev->power.lock, flags);
- __pm_wakeup_event(dev->power.wakeup, msec);
+ pm_wakeup_ws_event(dev->power.wakeup, msec, hard);
spin_unlock_irqrestore(&dev->power.lock, flags);
}
-EXPORT_SYMBOL_GPL(pm_wakeup_event);
+EXPORT_SYMBOL_GPL(pm_wakeup_dev_event);
void pm_print_active_wakeup_sources(void)
{
pm_print_active_wakeup_sources();
}
- return ret || pm_abort_suspend;
+ return ret || atomic_read(&pm_abort_suspend) > 0;
}
void pm_system_wakeup(void)
{
- pm_abort_suspend = true;
+ atomic_inc(&pm_abort_suspend);
freeze_wake();
}
EXPORT_SYMBOL_GPL(pm_system_wakeup);
-void pm_wakeup_clear(void)
+void pm_system_cancel_wakeup(void)
+{
+ atomic_dec(&pm_abort_suspend);
+}
+
+void pm_wakeup_clear(bool reset)
{
- pm_abort_suspend = false;
pm_wakeup_irq = 0;
+ if (reset)
+ atomic_set(&pm_abort_suspend, 0);
}
void pm_system_irq_wakeup(unsigned int irq_number)
struct rw_semaphore lock_rwsem;
enum rbd_lock_state lock_state;
+ char lock_cookie[32];
struct rbd_client_id owner_cid;
struct work_struct acquired_lock_work;
struct work_struct released_lock_work;
return minor >> RBD_SINGLE_MAJOR_PART_SHIFT;
}
-static bool rbd_is_lock_supported(struct rbd_device *rbd_dev)
-{
- return (rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK) &&
- rbd_dev->spec->snap_id == CEPH_NOSNAP &&
- !rbd_dev->mapping.read_only;
-}
-
static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev)
{
return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED ||
kref_init(&rbdc->kref);
INIT_LIST_HEAD(&rbdc->node);
- rbdc->client = ceph_create_client(ceph_opts, rbdc, 0, 0);
+ rbdc->client = ceph_create_client(ceph_opts, rbdc);
if (IS_ERR(rbdc->client))
goto out_rbdc;
ceph_opts = NULL; /* Now rbdc->client is responsible for ceph_opts */
Opt_read_only,
Opt_read_write,
Opt_lock_on_read,
+ Opt_exclusive,
Opt_err
};
{Opt_read_write, "read_write"},
{Opt_read_write, "rw"}, /* Alternate spelling */
{Opt_lock_on_read, "lock_on_read"},
+ {Opt_exclusive, "exclusive"},
{Opt_err, NULL}
};
int queue_depth;
bool read_only;
bool lock_on_read;
+ bool exclusive;
};
#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_MAX_RQ
#define RBD_READ_ONLY_DEFAULT false
#define RBD_LOCK_ON_READ_DEFAULT false
+#define RBD_EXCLUSIVE_DEFAULT false
static int parse_rbd_opts_token(char *c, void *private)
{
case Opt_lock_on_read:
rbd_opts->lock_on_read = true;
break;
+ case Opt_exclusive:
+ rbd_opts->exclusive = true;
+ break;
default:
/* libceph prints "bad option" msg */
return -EINVAL;
char cookie[32];
int ret;
- WARN_ON(__rbd_is_lock_owner(rbd_dev));
+ WARN_ON(__rbd_is_lock_owner(rbd_dev) ||
+ rbd_dev->lock_cookie[0] != '\0');
format_lock_cookie(rbd_dev, cookie);
ret = ceph_cls_lock(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc,
return ret;
rbd_dev->lock_state = RBD_LOCK_STATE_LOCKED;
+ strcpy(rbd_dev->lock_cookie, cookie);
rbd_set_owner_cid(rbd_dev, &cid);
queue_work(rbd_dev->task_wq, &rbd_dev->acquired_lock_work);
return 0;
/*
* lock_rwsem must be held for write
*/
-static int rbd_unlock(struct rbd_device *rbd_dev)
+static void rbd_unlock(struct rbd_device *rbd_dev)
{
struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
- char cookie[32];
int ret;
- WARN_ON(!__rbd_is_lock_owner(rbd_dev));
-
- rbd_dev->lock_state = RBD_LOCK_STATE_UNLOCKED;
+ WARN_ON(!__rbd_is_lock_owner(rbd_dev) ||
+ rbd_dev->lock_cookie[0] == '\0');
- format_lock_cookie(rbd_dev, cookie);
ret = ceph_cls_unlock(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc,
- RBD_LOCK_NAME, cookie);
- if (ret && ret != -ENOENT) {
- rbd_warn(rbd_dev, "cls_unlock failed: %d", ret);
- return ret;
- }
+ RBD_LOCK_NAME, rbd_dev->lock_cookie);
+ if (ret && ret != -ENOENT)
+ rbd_warn(rbd_dev, "failed to unlock: %d", ret);
+ /* treat errors as the image is unlocked */
+ rbd_dev->lock_state = RBD_LOCK_STATE_UNLOCKED;
+ rbd_dev->lock_cookie[0] = '\0';
rbd_set_owner_cid(rbd_dev, &rbd_empty_cid);
queue_work(rbd_dev->task_wq, &rbd_dev->released_lock_work);
- return 0;
}
static int __rbd_notify_op_lock(struct rbd_device *rbd_dev,
ret = rbd_request_lock(rbd_dev);
if (ret == -ETIMEDOUT) {
goto again; /* treat this as a dead client */
+ } else if (ret == -EROFS) {
+ rbd_warn(rbd_dev, "peer will not release lock");
+ /*
+ * If this is rbd_add_acquire_lock(), we want to fail
+ * immediately -- reuse BLACKLISTED flag. Otherwise we
+ * want to block.
+ */
+ if (!(rbd_dev->disk->flags & GENHD_FL_UP)) {
+ set_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags);
+ /* wake "rbd map --exclusive" process */
+ wake_requests(rbd_dev, false);
+ }
} else if (ret < 0) {
rbd_warn(rbd_dev, "error requesting lock: %d", ret);
mod_delayed_work(rbd_dev->task_wq, &rbd_dev->lock_dwork,
if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING)
return false;
- if (!rbd_unlock(rbd_dev))
- /*
- * Give others a chance to grab the lock - we would re-acquire
- * almost immediately if we got new IO during ceph_osdc_sync()
- * otherwise. We need to ack our own notifications, so this
- * lock_dwork will be requeued from rbd_wait_state_locked()
- * after wake_requests() in rbd_handle_released_lock().
- */
- cancel_delayed_work(&rbd_dev->lock_dwork);
-
+ rbd_unlock(rbd_dev);
+ /*
+ * Give others a chance to grab the lock - we would re-acquire
+ * almost immediately if we got new IO during ceph_osdc_sync()
+ * otherwise. We need to ack our own notifications, so this
+ * lock_dwork will be requeued from rbd_wait_state_locked()
+ * after wake_requests() in rbd_handle_released_lock().
+ */
+ cancel_delayed_work(&rbd_dev->lock_dwork);
return true;
}
up_read(&rbd_dev->lock_rwsem);
}
-static bool rbd_handle_request_lock(struct rbd_device *rbd_dev, u8 struct_v,
- void **p)
+/*
+ * Returns result for ResponseMessage to be encoded (<= 0), or 1 if no
+ * ResponseMessage is needed.
+ */
+static int rbd_handle_request_lock(struct rbd_device *rbd_dev, u8 struct_v,
+ void **p)
{
struct rbd_client_id my_cid = rbd_get_cid(rbd_dev);
struct rbd_client_id cid = { 0 };
- bool need_to_send;
+ int result = 1;
if (struct_v >= 2) {
cid.gid = ceph_decode_64(p);
dout("%s rbd_dev %p cid %llu-%llu\n", __func__, rbd_dev, cid.gid,
cid.handle);
if (rbd_cid_equal(&cid, &my_cid))
- return false;
+ return result;
down_read(&rbd_dev->lock_rwsem);
- need_to_send = __rbd_is_lock_owner(rbd_dev);
- if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) {
- if (!rbd_cid_equal(&rbd_dev->owner_cid, &rbd_empty_cid)) {
- dout("%s rbd_dev %p queueing unlock_work\n", __func__,
- rbd_dev);
- queue_work(rbd_dev->task_wq, &rbd_dev->unlock_work);
+ if (__rbd_is_lock_owner(rbd_dev)) {
+ if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED &&
+ rbd_cid_equal(&rbd_dev->owner_cid, &rbd_empty_cid))
+ goto out_unlock;
+
+ /*
+ * encode ResponseMessage(0) so the peer can detect
+ * a missing owner
+ */
+ result = 0;
+
+ if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) {
+ if (!rbd_dev->opts->exclusive) {
+ dout("%s rbd_dev %p queueing unlock_work\n",
+ __func__, rbd_dev);
+ queue_work(rbd_dev->task_wq,
+ &rbd_dev->unlock_work);
+ } else {
+ /* refuse to release the lock */
+ result = -EROFS;
+ }
}
}
+
+out_unlock:
up_read(&rbd_dev->lock_rwsem);
- return need_to_send;
+ return result;
}
static void __rbd_acknowledge_notify(struct rbd_device *rbd_dev,
rbd_acknowledge_notify(rbd_dev, notify_id, cookie);
break;
case RBD_NOTIFY_OP_REQUEST_LOCK:
- if (rbd_handle_request_lock(rbd_dev, struct_v, &p))
- /*
- * send ResponseMessage(0) back so the client
- * can detect a missing owner
- */
+ ret = rbd_handle_request_lock(rbd_dev, struct_v, &p);
+ if (ret <= 0)
rbd_acknowledge_notify_result(rbd_dev, notify_id,
- cookie, 0);
+ cookie, ret);
else
rbd_acknowledge_notify(rbd_dev, notify_id, cookie);
break;
ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc);
}
+/*
+ * lock_rwsem must be held for write
+ */
+static void rbd_reacquire_lock(struct rbd_device *rbd_dev)
+{
+ struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc;
+ char cookie[32];
+ int ret;
+
+ WARN_ON(rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED);
+
+ format_lock_cookie(rbd_dev, cookie);
+ ret = ceph_cls_set_cookie(osdc, &rbd_dev->header_oid,
+ &rbd_dev->header_oloc, RBD_LOCK_NAME,
+ CEPH_CLS_LOCK_EXCLUSIVE, rbd_dev->lock_cookie,
+ RBD_LOCK_TAG, cookie);
+ if (ret) {
+ if (ret != -EOPNOTSUPP)
+ rbd_warn(rbd_dev, "failed to update lock cookie: %d",
+ ret);
+
+ /*
+ * Lock cookie cannot be updated on older OSDs, so do
+ * a manual release and queue an acquire.
+ */
+ if (rbd_release_lock(rbd_dev))
+ queue_delayed_work(rbd_dev->task_wq,
+ &rbd_dev->lock_dwork, 0);
+ } else {
+ strcpy(rbd_dev->lock_cookie, cookie);
+ }
+}
+
static void rbd_reregister_watch(struct work_struct *work)
{
struct rbd_device *rbd_dev = container_of(to_delayed_work(work),
struct rbd_device, watch_dwork);
- bool was_lock_owner = false;
- bool need_to_wake = false;
int ret;
dout("%s rbd_dev %p\n", __func__, rbd_dev);
- down_write(&rbd_dev->lock_rwsem);
- if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED)
- was_lock_owner = rbd_release_lock(rbd_dev);
-
mutex_lock(&rbd_dev->watch_mutex);
if (rbd_dev->watch_state != RBD_WATCH_STATE_ERROR) {
mutex_unlock(&rbd_dev->watch_mutex);
- goto out;
+ return;
}
ret = __rbd_register_watch(rbd_dev);
rbd_warn(rbd_dev, "failed to reregister watch: %d", ret);
if (ret == -EBLACKLISTED || ret == -ENOENT) {
set_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags);
- need_to_wake = true;
+ wake_requests(rbd_dev, true);
} else {
queue_delayed_work(rbd_dev->task_wq,
&rbd_dev->watch_dwork,
RBD_RETRY_DELAY);
}
mutex_unlock(&rbd_dev->watch_mutex);
- goto out;
+ return;
}
- need_to_wake = true;
rbd_dev->watch_state = RBD_WATCH_STATE_REGISTERED;
rbd_dev->watch_cookie = rbd_dev->watch_handle->linger_id;
mutex_unlock(&rbd_dev->watch_mutex);
+ down_write(&rbd_dev->lock_rwsem);
+ if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED)
+ rbd_reacquire_lock(rbd_dev);
+ up_write(&rbd_dev->lock_rwsem);
+
ret = rbd_dev_refresh(rbd_dev);
if (ret)
rbd_warn(rbd_dev, "reregisteration refresh failed: %d", ret);
-
- if (was_lock_owner) {
- ret = rbd_try_lock(rbd_dev);
- if (ret)
- rbd_warn(rbd_dev, "reregisteration lock failed: %d",
- ret);
- }
-
-out:
- up_write(&rbd_dev->lock_rwsem);
- if (need_to_wake)
- wake_requests(rbd_dev, true);
}
/*
if (op_type != OBJ_OP_READ) {
snapc = rbd_dev->header.snapc;
ceph_get_snap_context(snapc);
- must_be_locked = rbd_is_lock_supported(rbd_dev);
- } else {
- must_be_locked = rbd_dev->opts->lock_on_read &&
- rbd_is_lock_supported(rbd_dev);
}
up_read(&rbd_dev->header_rwsem);
goto err_rq;
}
+ must_be_locked =
+ (rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK) &&
+ (op_type != OBJ_OP_READ || rbd_dev->opts->lock_on_read);
if (must_be_locked) {
down_read(&rbd_dev->lock_rwsem);
if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED &&
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags))
+ !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ if (rbd_dev->opts->exclusive) {
+ rbd_warn(rbd_dev, "exclusive lock required");
+ result = -EROFS;
+ goto err_unlock;
+ }
rbd_wait_state_locked(rbd_dev);
-
- WARN_ON((rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) ^
- !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags));
+ }
if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
result = -EBLACKLISTED;
goto err_unlock;
static void rbd_free_disk(struct rbd_device *rbd_dev)
{
- struct gendisk *disk = rbd_dev->disk;
-
- if (!disk)
- return;
-
+ blk_cleanup_queue(rbd_dev->disk->queue);
+ blk_mq_free_tag_set(&rbd_dev->tag_set);
+ put_disk(rbd_dev->disk);
rbd_dev->disk = NULL;
- if (disk->flags & GENHD_FL_UP) {
- del_gendisk(disk);
- if (disk->queue)
- blk_cleanup_queue(disk->queue);
- blk_mq_free_tag_set(&rbd_dev->tag_set);
- }
- put_disk(disk);
}
static int rbd_obj_read_sync(struct rbd_device *rbd_dev,
if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+ /*
+ * disk_release() expects a queue ref from add_disk() and will
+ * put it. Hold an extra ref until add_disk() is called.
+ */
+ WARN_ON(!blk_get_queue(q));
disk->queue = q;
-
q->queuedata = rbd_dev;
rbd_dev->disk = disk;
rbd_opts->read_only = RBD_READ_ONLY_DEFAULT;
rbd_opts->queue_depth = RBD_QUEUE_DEPTH_DEFAULT;
rbd_opts->lock_on_read = RBD_LOCK_ON_READ_DEFAULT;
+ rbd_opts->exclusive = RBD_EXCLUSIVE_DEFAULT;
copts = ceph_parse_options(options, mon_addrs,
mon_addrs + mon_addrs_size - 1,
return ret;
}
+static void rbd_dev_image_unlock(struct rbd_device *rbd_dev)
+{
+ down_write(&rbd_dev->lock_rwsem);
+ if (__rbd_is_lock_owner(rbd_dev))
+ rbd_unlock(rbd_dev);
+ up_write(&rbd_dev->lock_rwsem);
+}
+
+static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
+{
+ if (!(rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK)) {
+ rbd_warn(rbd_dev, "exclusive-lock feature is not enabled");
+ return -EINVAL;
+ }
+
+ /* FIXME: "rbd map --exclusive" should be in interruptible */
+ down_read(&rbd_dev->lock_rwsem);
+ rbd_wait_state_locked(rbd_dev);
+ up_read(&rbd_dev->lock_rwsem);
+ if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) {
+ rbd_warn(rbd_dev, "failed to acquire exclusive lock");
+ return -EROFS;
+ }
+
+ return 0;
+}
+
/*
* An rbd format 2 image has a unique identifier, distinct from the
* name given to it by the user. Internally, that identifier is
return ret;
}
+static void rbd_dev_device_release(struct rbd_device *rbd_dev)
+{
+ clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
+ rbd_dev_mapping_clear(rbd_dev);
+ rbd_free_disk(rbd_dev);
+ if (!single_major)
+ unregister_blkdev(rbd_dev->major, rbd_dev->name);
+}
+
/*
* rbd_dev->header_rwsem must be locked for write and will be unlocked
* upon return.
set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);
- dev_set_name(&rbd_dev->dev, "%d", rbd_dev->dev_id);
- ret = device_add(&rbd_dev->dev);
+ ret = dev_set_name(&rbd_dev->dev, "%d", rbd_dev->dev_id);
if (ret)
goto err_out_mapping;
- /* Everything's ready. Announce the disk to the world. */
-
set_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
up_write(&rbd_dev->header_rwsem);
-
- spin_lock(&rbd_dev_list_lock);
- list_add_tail(&rbd_dev->node, &rbd_dev_list);
- spin_unlock(&rbd_dev_list_lock);
-
- add_disk(rbd_dev->disk);
- pr_info("%s: capacity %llu features 0x%llx\n", rbd_dev->disk->disk_name,
- (unsigned long long)get_capacity(rbd_dev->disk) << SECTOR_SHIFT,
- rbd_dev->header.features);
-
- return ret;
+ return 0;
err_out_mapping:
rbd_dev_mapping_clear(rbd_dev);
static void rbd_dev_image_release(struct rbd_device *rbd_dev)
{
rbd_dev_unprobe(rbd_dev);
+ if (rbd_dev->opts)
+ rbd_unregister_watch(rbd_dev);
rbd_dev->image_format = 0;
kfree(rbd_dev->spec->image_id);
rbd_dev->spec->image_id = NULL;
-
- rbd_dev_destroy(rbd_dev);
}
/*
rbd_dev->mapping.read_only = read_only;
rc = rbd_dev_device_setup(rbd_dev);
- if (rc) {
- /*
- * rbd_unregister_watch() can't be moved into
- * rbd_dev_image_release() without refactoring, see
- * commit 1f3ef78861ac.
- */
- rbd_unregister_watch(rbd_dev);
- rbd_dev_image_release(rbd_dev);
- goto out;
+ if (rc)
+ goto err_out_image_probe;
+
+ if (rbd_dev->opts->exclusive) {
+ rc = rbd_add_acquire_lock(rbd_dev);
+ if (rc)
+ goto err_out_device_setup;
}
+ /* Everything's ready. Announce the disk to the world. */
+
+ rc = device_add(&rbd_dev->dev);
+ if (rc)
+ goto err_out_image_lock;
+
+ add_disk(rbd_dev->disk);
+ /* see rbd_init_disk() */
+ blk_put_queue(rbd_dev->disk->queue);
+
+ spin_lock(&rbd_dev_list_lock);
+ list_add_tail(&rbd_dev->node, &rbd_dev_list);
+ spin_unlock(&rbd_dev_list_lock);
+
+ pr_info("%s: capacity %llu features 0x%llx\n", rbd_dev->disk->disk_name,
+ (unsigned long long)get_capacity(rbd_dev->disk) << SECTOR_SHIFT,
+ rbd_dev->header.features);
rc = count;
out:
module_put(THIS_MODULE);
return rc;
+err_out_image_lock:
+ rbd_dev_image_unlock(rbd_dev);
+err_out_device_setup:
+ rbd_dev_device_release(rbd_dev);
+err_out_image_probe:
+ rbd_dev_image_release(rbd_dev);
err_out_rbd_dev:
rbd_dev_destroy(rbd_dev);
err_out_client:
return do_rbd_add(bus, buf, count);
}
-static void rbd_dev_device_release(struct rbd_device *rbd_dev)
-{
- rbd_free_disk(rbd_dev);
-
- spin_lock(&rbd_dev_list_lock);
- list_del_init(&rbd_dev->node);
- spin_unlock(&rbd_dev_list_lock);
-
- clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
- device_del(&rbd_dev->dev);
- rbd_dev_mapping_clear(rbd_dev);
- if (!single_major)
- unregister_blkdev(rbd_dev->major, rbd_dev->name);
-}
-
static void rbd_dev_remove_parent(struct rbd_device *rbd_dev)
{
while (rbd_dev->parent) {
}
rbd_assert(second);
rbd_dev_image_release(second);
+ rbd_dev_destroy(second);
first->parent = NULL;
first->parent_overlap = 0;
blk_set_queue_dying(rbd_dev->disk->queue);
}
- down_write(&rbd_dev->lock_rwsem);
- if (__rbd_is_lock_owner(rbd_dev))
- rbd_unlock(rbd_dev);
- up_write(&rbd_dev->lock_rwsem);
- rbd_unregister_watch(rbd_dev);
+ del_gendisk(rbd_dev->disk);
+ spin_lock(&rbd_dev_list_lock);
+ list_del_init(&rbd_dev->node);
+ spin_unlock(&rbd_dev_list_lock);
+ device_del(&rbd_dev->dev);
- /*
- * Don't free anything from rbd_dev->disk until after all
- * notifies are completely processed. Otherwise
- * rbd_bus_del_dev() will race with rbd_watch_cb(), resulting
- * in a potential use after free of rbd_dev->disk or rbd_dev.
- */
+ rbd_dev_image_unlock(rbd_dev);
rbd_dev_device_release(rbd_dev);
rbd_dev_image_release(rbd_dev);
-
+ rbd_dev_destroy(rbd_dev);
return count;
}
}
/* Discover virtqueues and write information to configuration. */
- err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
- &desc);
+ err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
if (err)
goto out;
static unsigned int irq = 0; /* interrupt number IRQ */
static unsigned long mem = 0; /* physical segment of board */
-module_param(irq, uint, 0);
+module_param_hw(irq, uint, irq, 0);
MODULE_PARM_DESC(irq, "IRQ of the Applicom board");
-module_param(mem, ulong, 0);
+module_param_hw(mem, ulong, iomem, 0);
MODULE_PARM_DESC(mem, "Shared Memory Address of Applicom board");
static unsigned int numboards; /* number of installed boards */
" interface separated by commas. The types are 'kcs',"
" 'smic', and 'bt'. For example si_type=kcs,bt will set"
" the first interface to kcs and the second to bt");
-module_param_array(addrs, ulong, &num_addrs, 0);
+module_param_hw_array(addrs, ulong, iomem, &num_addrs, 0);
MODULE_PARM_DESC(addrs, "Sets the memory address of each interface, the"
" addresses separated by commas. Only use if an interface"
" is in memory. Otherwise, set it to zero or leave"
" it blank.");
-module_param_array(ports, uint, &num_ports, 0);
+module_param_hw_array(ports, uint, ioport, &num_ports, 0);
MODULE_PARM_DESC(ports, "Sets the port address of each interface, the"
" addresses separated by commas. Only use if an interface"
" is a port. Otherwise, set it to zero or leave"
" it blank.");
-module_param_array(irqs, int, &num_irqs, 0);
+module_param_hw_array(irqs, int, irq, &num_irqs, 0);
MODULE_PARM_DESC(irqs, "Sets the interrupt of each interface, the"
" addresses separated by commas. Only use if an interface"
" has an interrupt. Otherwise, set it to zero or leave"
" it blank.");
-module_param_array(regspacings, int, &num_regspacings, 0);
+module_param_hw_array(regspacings, int, other, &num_regspacings, 0);
MODULE_PARM_DESC(regspacings, "The number of bytes between the start address"
" and each successive register used by the interface. For"
" instance, if the start address is 0xca2 and the spacing"
" is 2, then the second address is at 0xca4. Defaults"
" to 1.");
-module_param_array(regsizes, int, &num_regsizes, 0);
+module_param_hw_array(regsizes, int, other, &num_regsizes, 0);
MODULE_PARM_DESC(regsizes, "The size of the specific IPMI register in bytes."
" This should generally be 1, 2, 4, or 8 for an 8-bit,"
" 16-bit, 32-bit, or 64-bit register. Use this if you"
" the 8-bit IPMI register has to be read from a larger"
" register.");
-module_param_array(regshifts, int, &num_regshifts, 0);
+module_param_hw_array(regshifts, int, other, &num_regshifts, 0);
MODULE_PARM_DESC(regshifts, "The amount to shift the data read from the."
" IPMI register, in bits. For instance, if the data"
" is read from a 32-bit word and the IPMI data is in"
" bit 8-15, then the shift would be 8");
-module_param_array(slave_addrs, int, &num_slave_addrs, 0);
+module_param_hw_array(slave_addrs, int, other, &num_slave_addrs, 0);
MODULE_PARM_DESC(slave_addrs, "Set the default IPMB slave address for"
" the controller. Normally this is 0x20, but can be"
" overridden by this parm. This is an array indexed"
int mwave_uart_irq = 0;
int mwave_uart_io = 0;
module_param(mwave_debug, int, 0);
-module_param(mwave_3780i_irq, int, 0);
-module_param(mwave_3780i_io, int, 0);
-module_param(mwave_uart_irq, int, 0);
-module_param(mwave_uart_io, int, 0);
+module_param_hw(mwave_3780i_irq, int, irq, 0);
+module_param_hw(mwave_3780i_io, int, ioport, 0);
+module_param_hw(mwave_uart_irq, int, irq, 0);
+module_param_hw(mwave_uart_io, int, ioport, 0);
static int mwave_open(struct inode *inode, struct file *file);
static int mwave_close(struct inode *inode, struct file *file);
}
}
/* Find the queues. */
- err = portdev->vdev->config->find_vqs(portdev->vdev, nr_queues, vqs,
- io_callbacks,
- (const char **)io_names, NULL);
+ err = virtio_find_vqs(portdev->vdev, nr_queues, vqs,
+ io_callbacks,
+ (const char **)io_names, NULL);
if (err)
goto free;
clocked at 32KHz each. Clkout1 is always on, Clkout2 can off
by control register.
+config COMMON_CLK_HI655X
+ tristate "Clock driver for Hi655x"
+ depends on MFD_HI655X_PMIC || COMPILE_TEST
+ ---help---
+ This driver supports the hi655x PMIC clock. This
+ multi-function device has one fixed-rate oscillator, clocked
+ at 32KHz.
+
config COMMON_CLK_SCPI
tristate "Clock driver controlled via SCPI interface"
depends on ARM_SCPI_PROTOCOL || COMPILE_TEST
obj-$(CONFIG_COMMON_CLK_PWM) += clk-pwm.o
obj-$(CONFIG_CLK_QORIQ) += clk-qoriq.o
obj-$(CONFIG_COMMON_CLK_RK808) += clk-rk808.o
+obj-$(CONFIG_COMMON_CLK_HI655X) += clk-hi655x.o
obj-$(CONFIG_COMMON_CLK_S2MPS11) += clk-s2mps11.o
obj-$(CONFIG_COMMON_CLK_SCPI) += clk-scpi.o
obj-$(CONFIG_COMMON_CLK_SI5351) += clk-si5351.o
if (!characteristics)
return NULL;
- output = kzalloc(sizeof(*output) * num_output, GFP_KERNEL);
+ output = kcalloc(num_output, sizeof(*output), GFP_KERNEL);
if (!output)
goto out_free_characteristics;
if (num_cells > 2) {
- out = kzalloc(sizeof(*out) * num_output, GFP_KERNEL);
+ out = kcalloc(num_output, sizeof(*out), GFP_KERNEL);
if (!out)
goto out_free_output;
}
if (num_cells > 3) {
- icpll = kzalloc(sizeof(*icpll) * num_output, GFP_KERNEL);
+ icpll = kcalloc(num_output, sizeof(*icpll), GFP_KERNEL);
if (!icpll)
goto out_free_output;
}
if (rate >= VCO_LOW && rate < VCO_HIGH) {
ki = 4;
kp_index = KP_BAND_MID;
- } else if (rate >= VCO_HIGH && rate && rate < VCO_HIGH_HIGH) {
+ } else if (rate >= VCO_HIGH && rate < VCO_HIGH_HIGH) {
ki = 3;
kp_index = KP_BAND_HIGH;
} else if (rate >= VCO_HIGH_HIGH && rate < VCO_MAX) {
static const struct iproc_pll_ctrl genpll_sw = {
.flags = IPROC_CLK_AON | IPROC_CLK_PLL_SPLIT_STAT_CTRL,
- .aon = AON_VAL(0x0, 2, 9, 8),
+ .aon = AON_VAL(0x0, 1, 11, 10),
.reset = RESET_VAL(0x4, 2, 1),
.dig_filter = DF_VAL(0x0, 9, 3, 5, 4, 2, 3),
.ndiv_int = REG_VAL(0x8, 4, 10),
/* DEVICE_CTRL */
#define PLL_UNLOCK (1 << 7)
+#define AUXOUTDIS (1 << 1)
+#define CLKOUTDIS (1 << 0)
/* DEVICE_CFG1 */
#define RSEL(x) (((x) & 0x3) << 3)
#define RSEL_MASK RSEL(0x3)
#define ENDEV1 (0x1)
+/* DEVICE_CFG2 */
+#define AUTORMOD (1 << 3)
+#define LOCKCLK(x) (((x) & 0x3) << 1)
+#define LOCKCLK_MASK LOCKCLK(0x3)
+#define FRACNSRC_MASK (1 << 0)
+#define FRACNSRC_STATIC (0 << 0)
+#define FRACNSRC_DYNAMIC (1 << 1)
+
/* GLOBAL_CFG */
#define ENDEV2 (0x1)
+/* FUNC_CFG1 */
+#define CLKSKIPEN (1 << 7)
+#define REFCLKDIV(x) (((x) & 0x3) << 3)
+#define REFCLKDIV_MASK REFCLKDIV(0x3)
+
+/* FUNC_CFG2 */
+#define LFRATIO_MASK (1 << 3)
+#define LFRATIO_20_12 (0 << 3)
+#define LFRATIO_12_20 (1 << 3)
+
#define CH_SIZE_ERR(ch) ((ch < 0) || (ch >= CH_MAX))
#define hw_to_priv(_hw) container_of(_hw, struct cs2000_priv, hw)
#define priv_to_client(priv) (priv->client)
if (ret < 0)
return ret;
+ ret = cs2000_bset(priv, FUNC_CFG1, CLKSKIPEN,
+ enable ? CLKSKIPEN : 0);
+ if (ret < 0)
+ return ret;
+
+ /* FIXME: for Static ratio mode */
+ ret = cs2000_bset(priv, FUNC_CFG2, LFRATIO_MASK,
+ LFRATIO_12_20);
+ if (ret < 0)
+ return ret;
+
return 0;
}
else
return -EINVAL;
- return cs2000_bset(priv, FUNC_CFG1, 0x3 << 3, val << 3);
+ return cs2000_bset(priv, FUNC_CFG1,
+ REFCLKDIV_MASK,
+ REFCLKDIV(val));
}
static int cs2000_wait_pll_lock(struct cs2000_priv *priv)
static int cs2000_clk_out_enable(struct cs2000_priv *priv, bool enable)
{
/* enable both AUX_OUT, CLK_OUT */
- return cs2000_write(priv, DEVICE_CTRL, enable ? 0 : 0x3);
+ return cs2000_bset(priv, DEVICE_CTRL,
+ (AUXOUTDIS | CLKOUTDIS),
+ enable ? 0 :
+ (AUXOUTDIS | CLKOUTDIS));
}
static u32 cs2000_rate_to_ratio(u32 rate_in, u32 rate_out)
if (ret < 0)
return ret;
- ret = cs2000_write(priv, DEVICE_CFG2, 0x0);
+ ret = cs2000_bset(priv, DEVICE_CFG2,
+ (AUTORMOD | LOCKCLK_MASK | FRACNSRC_MASK),
+ (LOCKCLK(ch) | FRACNSRC_STATIC));
if (ret < 0)
return ret;
static int cs2000_clk_get(struct cs2000_priv *priv)
{
- struct i2c_client *client = priv_to_client(priv);
- struct device *dev = &client->dev;
+ struct device *dev = priv_to_dev(priv);
struct clk *clk_in, *ref_clk;
clk_in = devm_clk_get(dev, "clk_in");
static int cs2000_version_print(struct cs2000_priv *priv)
{
- struct i2c_client *client = priv_to_client(priv);
- struct device *dev = &client->dev;
+ struct device *dev = priv_to_dev(priv);
s32 val;
const char *revision;
static int cs2000_remove(struct i2c_client *client)
{
struct cs2000_priv *priv = i2c_get_clientdata(client);
- struct device *dev = &client->dev;
+ struct device *dev = priv_to_dev(priv);
struct device_node *np = dev->of_node;
of_clk_del_provider(np);
--- /dev/null
+/*
+ * Clock driver for Hi655x
+ *
+ * Copyright (c) 2017, Linaro Ltd.
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/hi655x-pmic.h>
+
+#define HI655X_CLK_BASE HI655X_BUS_ADDR(0x1c)
+#define HI655X_CLK_SET BIT(6)
+
+struct hi655x_clk {
+ struct hi655x_pmic *hi655x;
+ struct clk_hw clk_hw;
+};
+
+static unsigned long hi655x_clk_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ return 32768;
+}
+
+static int hi655x_clk_enable(struct clk_hw *hw, bool enable)
+{
+ struct hi655x_clk *hi655x_clk =
+ container_of(hw, struct hi655x_clk, clk_hw);
+
+ struct hi655x_pmic *hi655x = hi655x_clk->hi655x;
+
+ return regmap_update_bits(hi655x->regmap, HI655X_CLK_BASE,
+ HI655X_CLK_SET, enable ? HI655X_CLK_SET : 0);
+}
+
+static int hi655x_clk_prepare(struct clk_hw *hw)
+{
+ return hi655x_clk_enable(hw, true);
+}
+
+static void hi655x_clk_unprepare(struct clk_hw *hw)
+{
+ hi655x_clk_enable(hw, false);
+}
+
+static int hi655x_clk_is_prepared(struct clk_hw *hw)
+{
+ struct hi655x_clk *hi655x_clk =
+ container_of(hw, struct hi655x_clk, clk_hw);
+ struct hi655x_pmic *hi655x = hi655x_clk->hi655x;
+ int ret;
+ uint32_t val;
+
+ ret = regmap_read(hi655x->regmap, HI655X_CLK_BASE, &val);
+ if (ret < 0)
+ return ret;
+
+ return val & HI655X_CLK_BASE;
+}
+
+static const struct clk_ops hi655x_clk_ops = {
+ .prepare = hi655x_clk_prepare,
+ .unprepare = hi655x_clk_unprepare,
+ .is_prepared = hi655x_clk_is_prepared,
+ .recalc_rate = hi655x_clk_recalc_rate,
+};
+
+static int hi655x_clk_probe(struct platform_device *pdev)
+{
+ struct device *parent = pdev->dev.parent;
+ struct hi655x_pmic *hi655x = dev_get_drvdata(parent);
+ struct hi655x_clk *hi655x_clk;
+ const char *clk_name = "hi655x-clk";
+ struct clk_init_data init = {
+ .name = clk_name,
+ .ops = &hi655x_clk_ops
+ };
+ int ret;
+
+ hi655x_clk = devm_kzalloc(&pdev->dev, sizeof(*hi655x_clk), GFP_KERNEL);
+ if (!hi655x_clk)
+ return -ENOMEM;
+
+ of_property_read_string_index(parent->of_node, "clock-output-names",
+ 0, &clk_name);
+
+ hi655x_clk->clk_hw.init = &init;
+ hi655x_clk->hi655x = hi655x;
+
+ platform_set_drvdata(pdev, hi655x_clk);
+
+ ret = devm_clk_hw_register(&pdev->dev, &hi655x_clk->clk_hw);
+ if (ret)
+ return ret;
+
+ return of_clk_add_hw_provider(parent->of_node, of_clk_hw_simple_get,
+ &hi655x_clk->clk_hw);
+}
+
+static struct platform_driver hi655x_clk_driver = {
+ .probe = hi655x_clk_probe,
+ .driver = {
+ .name = "hi655x-clk",
+ },
+};
+
+module_platform_driver(hi655x_clk_driver);
+
+MODULE_DESCRIPTION("Clk driver for the hi655x series PMICs");
+MODULE_AUTHOR("Daniel Lezcano <daniel.lezcano@linaro.org>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:hi655x-clk");
}
pll = kzalloc(sizeof(*pll), GFP_KERNEL);
- if (!pll) {
- pr_err("%s: could not allocate PLL clk\n", __func__);
+ if (!pll)
return ERR_PTR(-ENOMEM);
- }
init.name = name;
init.ops = &pll_clk_ops;
struct clk_init_data init;
sclk = kzalloc(sizeof(*sclk), GFP_KERNEL);
- if (!sclk) {
- pr_err("could not allocate SRC clock %s\n",
- name);
+ if (!sclk)
return ERR_PTR(-ENOMEM);
- }
+
init.name = name;
init.ops = &src_clk_ops;
/* Do not force-disable the static SDRAM controller */
u32 src_pckensr0 = readl(src_base + SRC_PCKENSR0);
u32 src_pckensr1 = readl(src_base + SRC_PCKENSR1);
- seq_printf(s, "Clock: Boot: Now: Request: ASKED:\n");
+ seq_puts(s, "Clock: Boot: Now: Request: ASKED:\n");
for (i = 0; i < ARRAY_SIZE(src_clk_names); i++) {
u32 pcksrb = (i < 0x20) ? src_pcksr0_boot : src_pcksr1_boot;
u32 pcksr = (i < 0x20) ? src_pcksr0 : src_pcksr1;
return -EINVAL;
drvdata = devm_kzalloc(&client->dev, sizeof(*drvdata), GFP_KERNEL);
- if (drvdata == NULL) {
- dev_err(&client->dev, "unable to allocate driver data\n");
+ if (!drvdata)
return -ENOMEM;
- }
i2c_set_clientdata(client, drvdata);
drvdata->client = client;
else
parent_names[1] = si5351_pll_names[1];
- drvdata->msynth = devm_kzalloc(&client->dev, num_clocks *
+ drvdata->msynth = devm_kcalloc(&client->dev, num_clocks,
sizeof(*drvdata->msynth), GFP_KERNEL);
- drvdata->clkout = devm_kzalloc(&client->dev, num_clocks *
+ drvdata->clkout = devm_kcalloc(&client->dev, num_clocks,
sizeof(*drvdata->clkout), GFP_KERNEL);
drvdata->num_clkout = num_clocks;
return clk_gate_ops.is_enabled(hw);
}
+#define PLL_TIMEOUT 10000
+
static int stm32f4_pll_enable(struct clk_hw *hw)
{
struct clk_gate *gate = to_clk_gate(hw);
struct stm32f4_pll *pll = to_stm32f4_pll(gate);
- int ret = 0;
- unsigned long reg;
+ int bit_status;
+ unsigned int timeout = PLL_TIMEOUT;
- ret = clk_gate_ops.enable(hw);
+ if (clk_gate_ops.is_enabled(hw))
+ return 0;
+
+ clk_gate_ops.enable(hw);
- ret = readl_relaxed_poll_timeout_atomic(base + STM32F4_RCC_CR, reg,
- reg & (1 << pll->bit_rdy_idx), 0, 10000);
+ do {
+ bit_status = !(readl(gate->reg) & BIT(pll->bit_rdy_idx));
- return ret;
+ } while (bit_status && --timeout);
+
+ return bit_status;
}
static void stm32f4_pll_disable(struct clk_hw *hw)
u8 bit_rdy_idx;
};
-#define RTC_TIMEOUT 1000000
+#define RGATE_TIMEOUT 50000
static int rgclk_enable(struct clk_hw *hw)
{
struct clk_gate *gate = to_clk_gate(hw);
struct stm32_rgate *rgate = to_rgclk(gate);
- u32 reg;
- int ret;
+ int bit_status;
+ unsigned int timeout = RGATE_TIMEOUT;
+
+ if (clk_gate_ops.is_enabled(hw))
+ return 0;
disable_power_domain_write_protection();
clk_gate_ops.enable(hw);
- ret = readl_relaxed_poll_timeout_atomic(gate->reg, reg,
- reg & rgate->bit_rdy_idx, 1000, RTC_TIMEOUT);
+ do {
+ bit_status = !(readl(gate->reg) & BIT(rgate->bit_rdy_idx));
+ if (bit_status)
+ udelay(100);
+
+ } while (bit_status && --timeout);
enable_power_domain_write_protection();
- return ret;
+
+ return bit_status;
}
static void rgclk_disable(struct clk_hw *hw)
}
clks[CLK_LSI] = clk_register_rgate(NULL, "lsi", "clk-lsi", 0,
- base + STM32F4_RCC_CSR, 0, 2, 0, &stm32f4_clk_lock);
+ base + STM32F4_RCC_CSR, 0, 1, 0, &stm32f4_clk_lock);
if (IS_ERR(clks[CLK_LSI])) {
pr_err("Unable to register lsi clock\n");
}
clks[CLK_LSE] = clk_register_rgate(NULL, "lse", "clk-lse", 0,
- base + STM32F4_RCC_BDCR, 0, 2, 0, &stm32f4_clk_lock);
+ base + STM32F4_RCC_BDCR, 0, 1, 0, &stm32f4_clk_lock);
if (IS_ERR(clks[CLK_LSE])) {
pr_err("Unable to register lse clock\n");
#define VC5_MUX_IN_XIN BIT(0)
#define VC5_MUX_IN_CLKIN BIT(1)
+/* Maximum number of clk_out supported by this driver */
+#define VC5_MAX_CLK_OUT_NUM 5
+
+/* Maximum number of FODs supported by this driver */
+#define VC5_MAX_FOD_NUM 4
+
+/* flags to describe chip features */
+/* chip has built-in oscilator */
+#define VC5_HAS_INTERNAL_XTAL BIT(0)
+
/* Supported IDT VC5 models. */
enum vc5_model {
IDT_VC5_5P49V5923,
IDT_VC5_5P49V5933,
+ IDT_VC5_5P49V5935,
+};
+
+/* Structure to describe features of a particular VC5 model */
+struct vc5_chip_info {
+ const enum vc5_model model;
+ const unsigned int clk_fod_cnt;
+ const unsigned int clk_out_cnt;
+ const u32 flags;
};
struct vc5_driver_data;
struct vc5_driver_data {
struct i2c_client *client;
struct regmap *regmap;
- enum vc5_model model;
+ const struct vc5_chip_info *chip_info;
struct clk *pin_xin;
struct clk *pin_clkin;
unsigned char clk_mux_ins;
struct clk_hw clk_mux;
struct vc5_hw_data clk_pll;
- struct vc5_hw_data clk_fod[2];
- struct vc5_hw_data clk_out[3];
+ struct vc5_hw_data clk_fod[VC5_MAX_FOD_NUM];
+ struct vc5_hw_data clk_out[VC5_MAX_CLK_OUT_NUM];
};
static const char * const vc5_mux_names[] = {
struct vc5_driver_data *vc5 = data;
unsigned int idx = clkspec->args[0];
- if (idx > 2)
+ if (idx >= vc5->chip_info->clk_out_cnt)
return ERR_PTR(-EINVAL);
return &vc5->clk_out[idx].hw;
case IDT_VC5_5P49V5933:
return (n == 0) ? 0 : 3;
case IDT_VC5_5P49V5923:
+ case IDT_VC5_5P49V5935:
default:
return n;
}
static int vc5_probe(struct i2c_client *client,
const struct i2c_device_id *id)
{
- const struct of_device_id *of_id =
- of_match_device(clk_vc5_of_match, &client->dev);
struct vc5_driver_data *vc5;
struct clk_init_data init;
const char *parent_names[2];
- unsigned int n, idx;
+ unsigned int n, idx = 0;
int ret;
vc5 = devm_kzalloc(&client->dev, sizeof(*vc5), GFP_KERNEL);
i2c_set_clientdata(client, vc5);
vc5->client = client;
- vc5->model = (enum vc5_model)of_id->data;
+ vc5->chip_info = of_device_get_match_data(&client->dev);
vc5->pin_xin = devm_clk_get(&client->dev, "xin");
if (PTR_ERR(vc5->pin_xin) == -EPROBE_DEFER)
if (!IS_ERR(vc5->pin_xin)) {
vc5->clk_mux_ins |= VC5_MUX_IN_XIN;
parent_names[init.num_parents++] = __clk_get_name(vc5->pin_xin);
- } else if (vc5->model == IDT_VC5_5P49V5933) {
- /* IDT VC5 5P49V5933 has built-in oscilator. */
+ } else if (vc5->chip_info->flags & VC5_HAS_INTERNAL_XTAL) {
vc5->pin_xin = clk_register_fixed_rate(&client->dev,
"internal-xtal", NULL,
0, 25000000);
}
/* Register FODs */
- for (n = 0; n < 2; n++) {
- idx = vc5_map_index_to_output(vc5->model, n);
+ for (n = 0; n < vc5->chip_info->clk_fod_cnt; n++) {
+ idx = vc5_map_index_to_output(vc5->chip_info->model, n);
memset(&init, 0, sizeof(init));
init.name = vc5_fod_names[idx];
init.ops = &vc5_fod_ops;
}
/* Register FOD-connected OUTx outputs */
- for (n = 1; n < 3; n++) {
- idx = vc5_map_index_to_output(vc5->model, n - 1);
+ for (n = 1; n < vc5->chip_info->clk_out_cnt; n++) {
+ idx = vc5_map_index_to_output(vc5->chip_info->model, n - 1);
parent_names[0] = vc5_fod_names[idx];
if (n == 1)
parent_names[1] = vc5_mux_names[0];
return 0;
err_clk:
- if (vc5->model == IDT_VC5_5P49V5933)
+ if (vc5->chip_info->flags & VC5_HAS_INTERNAL_XTAL)
clk_unregister_fixed_rate(vc5->pin_xin);
return ret;
}
of_clk_del_provider(client->dev.of_node);
- if (vc5->model == IDT_VC5_5P49V5933)
+ if (vc5->chip_info->flags & VC5_HAS_INTERNAL_XTAL)
clk_unregister_fixed_rate(vc5->pin_xin);
return 0;
}
+static const struct vc5_chip_info idt_5p49v5923_info = {
+ .model = IDT_VC5_5P49V5923,
+ .clk_fod_cnt = 2,
+ .clk_out_cnt = 3,
+ .flags = 0,
+};
+
+static const struct vc5_chip_info idt_5p49v5933_info = {
+ .model = IDT_VC5_5P49V5933,
+ .clk_fod_cnt = 2,
+ .clk_out_cnt = 3,
+ .flags = VC5_HAS_INTERNAL_XTAL,
+};
+
+static const struct vc5_chip_info idt_5p49v5935_info = {
+ .model = IDT_VC5_5P49V5935,
+ .clk_fod_cnt = 4,
+ .clk_out_cnt = 5,
+ .flags = VC5_HAS_INTERNAL_XTAL,
+};
+
static const struct i2c_device_id vc5_id[] = {
{ "5p49v5923", .driver_data = IDT_VC5_5P49V5923 },
{ "5p49v5933", .driver_data = IDT_VC5_5P49V5933 },
+ { "5p49v5935", .driver_data = IDT_VC5_5P49V5935 },
{ }
};
MODULE_DEVICE_TABLE(i2c, vc5_id);
static const struct of_device_id clk_vc5_of_match[] = {
- { .compatible = "idt,5p49v5923", .data = (void *)IDT_VC5_5P49V5923 },
- { .compatible = "idt,5p49v5933", .data = (void *)IDT_VC5_5P49V5933 },
+ { .compatible = "idt,5p49v5923", .data = &idt_5p49v5923_info },
+ { .compatible = "idt,5p49v5933", .data = &idt_5p49v5933_info },
+ { .compatible = "idt,5p49v5935", .data = &idt_5p49v5935_info },
{ },
};
MODULE_DEVICE_TABLE(of, clk_vc5_of_match);
cnd.clk = cn->clk;
ret = srcu_notifier_call_chain(&cn->notifier_head, msg,
&cnd);
+ if (ret & NOTIFY_STOP_MASK)
+ return ret;
}
}
clk_dump_one(s, c, level);
hlist_for_each_entry(child, &c->children, child_node) {
- seq_printf(s, ",");
+ seq_putc(s, ',');
clk_dump_subtree(s, child, level + 1);
}
- seq_printf(s, "}");
+ seq_putc(s, '}');
}
static int clk_dump(struct seq_file *s, void *data)
bool first_node = true;
struct hlist_head **lists = (struct hlist_head **)s->private;
- seq_printf(s, "{");
-
+ seq_putc(s, '{');
clk_prepare_lock();
for (; *lists; lists++) {
hlist_for_each_entry(c, *lists, child_node) {
if (!first_node)
- seq_puts(s, ",");
+ seq_putc(s, ',');
first_node = false;
clk_dump_subtree(s, c, 0);
}
.release = single_release,
};
+static int possible_parents_dump(struct seq_file *s, void *data)
+{
+ struct clk_core *core = s->private;
+ int i;
+
+ for (i = 0; i < core->num_parents - 1; i++)
+ seq_printf(s, "%s ", core->parent_names[i]);
+
+ seq_printf(s, "%s\n", core->parent_names[i]);
+
+ return 0;
+}
+
+static int possible_parents_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, possible_parents_dump, inode->i_private);
+}
+
+static const struct file_operations possible_parents_fops = {
+ .open = possible_parents_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static int clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
{
struct dentry *d;
if (!d)
goto err_out;
+ if (core->num_parents > 1) {
+ d = debugfs_create_file("clk_possible_parents", S_IRUGO,
+ core->dentry, core, &possible_parents_fops);
+ if (!d)
+ goto err_out;
+ }
+
if (core->ops->debug_init) {
ret = core->ops->debug_init(core->hw, core->dentry);
if (ret)
/* if clk wasn't in the notifier list, allocate new clk_notifier */
if (cn->clk != clk) {
- cn = kzalloc(sizeof(struct clk_notifier), GFP_KERNEL);
+ cn = kzalloc(sizeof(*cn), GFP_KERNEL);
if (!cn)
goto out;
struct of_clk_provider *cp;
int ret;
- cp = kzalloc(sizeof(struct of_clk_provider), GFP_KERNEL);
+ cp = kzalloc(sizeof(*cp), GFP_KERNEL);
if (!cp)
return -ENOMEM;
{ HI3620_MMC3_DIV, "mmc3_div", "mmc3_mux", 0, 0x140, 5, 4, CLK_DIVIDER_HIWORD_MASK, NULL, },
};
-static struct hisi_gate_clock hi3620_seperated_gate_clks[] __initdata = {
+static struct hisi_gate_clock hi3620_separated_gate_clks[] __initdata = {
{ HI3620_TIMERCLK01, "timerclk01", "timer_rclk01", CLK_SET_RATE_PARENT, 0x20, 0, 0, },
{ HI3620_TIMER_RCLK01, "timer_rclk01", "rclk_tcxo", CLK_SET_RATE_PARENT, 0x20, 1, 0, },
{ HI3620_TIMERCLK23, "timerclk23", "timer_rclk23", CLK_SET_RATE_PARENT, 0x20, 2, 0, },
clk_data);
hisi_clk_register_divider(hi3620_div_clks, ARRAY_SIZE(hi3620_div_clks),
clk_data);
- hisi_clk_register_gate_sep(hi3620_seperated_gate_clks,
- ARRAY_SIZE(hi3620_seperated_gate_clks),
+ hisi_clk_register_gate_sep(hi3620_separated_gate_clks,
+ ARRAY_SIZE(hi3620_separated_gate_clks),
clk_data);
}
CLK_OF_DECLARE(hi3620_clk, "hisilicon,hi3620-clock", hi3620_clk_init);
struct clk_init_data init;
mclk = kzalloc(sizeof(*mclk), GFP_KERNEL);
- if (!mclk) {
- pr_err("%s: fail to allocate mmc clk\n", __func__);
+ if (!mclk)
return ERR_PTR(-ENOMEM);
- }
init.name = mmc_clk->name;
init.ops = &clk_mmc_ops;
if (WARN_ON(!clk_data))
return;
- clk_data->clks = kzalloc(sizeof(struct clk *) * num, GFP_KERNEL);
- if (!clk_data->clks) {
- pr_err("%s: fail to allocate mmc clk\n", __func__);
+ clk_data->clks = kcalloc(num, sizeof(*clk_data->clks), GFP_KERNEL);
+ if (!clk_data->clks)
return;
- }
for (i = 0; i < num; i++) {
struct hisi_mmc_clock *mmc_clk = &hi3620_mmc_clks[i];
{ HI6220_UART4_PCLK, "uart4_pclk", "uart4_src", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 8, 0, },
{ HI6220_SPI_CLK, "spi_clk", "clk_150m", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 9, 0, },
{ HI6220_TSENSOR_CLK, "tsensor_clk", "clk_bus", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x230, 12, 0, },
+ { HI6220_DAPB_CLK, "dapb_clk", "cs_dapb", CLK_SET_RATE_PARENT|CLK_IS_CRITICAL, 0x230, 18, 0, },
{ HI6220_MMU_CLK, "mmu_clk", "ddrc_axi1", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x240, 11, 0, },
{ HI6220_HIFI_SEL, "hifi_sel", "hifi_src", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 0, 0, },
{ HI6220_MMC0_SYSPLL, "mmc0_syspll", "syspll", CLK_SET_RATE_PARENT|CLK_IGNORE_UNUSED, 0x270, 1, 0, },
if (!clk_data->base)
return NULL;
- clk_table = devm_kmalloc(&pdev->dev, sizeof(struct clk *) * nr_clks,
- GFP_KERNEL);
+ clk_table = devm_kmalloc_array(&pdev->dev, nr_clks,
+ sizeof(*clk_table),
+ GFP_KERNEL);
if (!clk_table)
return NULL;
}
clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
- if (!clk_data) {
- pr_err("%s: could not allocate clock data\n", __func__);
+ if (!clk_data)
goto err;
- }
- clk_data->base = base;
- clk_table = kzalloc(sizeof(struct clk *) * nr_clks, GFP_KERNEL);
- if (!clk_table) {
- pr_err("%s: could not allocate clock lookup table\n", __func__);
+ clk_data->base = base;
+ clk_table = kcalloc(nr_clks, sizeof(*clk_table), GFP_KERNEL);
+ if (!clk_table)
goto err_data;
- }
+
clk_data->clk_data.clks = clk_table;
clk_data->clk_data.clk_num = nr_clks;
of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data->clk_data);
static struct clk_onecell_data clk_data;
static int const clks_init_on[] __initconst = {
- IMX6UL_CLK_AIPSTZ1, IMX6UL_CLK_AIPSTZ2, IMX6UL_CLK_AIPSTZ3,
+ IMX6UL_CLK_AIPSTZ1, IMX6UL_CLK_AIPSTZ2,
IMX6UL_CLK_AXI, IMX6UL_CLK_ARM, IMX6UL_CLK_ROM,
IMX6UL_CLK_MMDC_P0_FAST, IMX6UL_CLK_MMDC_P0_IPG,
};
clks[IMX6UL_CLK_GPT2_SERIAL] = imx_clk_gate2("gpt2_serial", "perclk", base + 0x68, 26);
clks[IMX6UL_CLK_UART2_IPG] = imx_clk_gate2("uart2_ipg", "ipg", base + 0x68, 28);
clks[IMX6UL_CLK_UART2_SERIAL] = imx_clk_gate2("uart2_serial", "uart_podf", base + 0x68, 28);
- if (clk_on_imx6ul())
- clks[IMX6UL_CLK_AIPSTZ3] = imx_clk_gate2("aips_tz3", "ahb", base + 0x68, 30);
- else if (clk_on_imx6ull())
+ if (clk_on_imx6ull())
clks[IMX6UL_CLK_AIPSTZ3] = imx_clk_gate2("aips_tz3", "ahb", base + 0x80, 18);
/* CCGR1 */
clks[IMX6UL_CLK_GPT1_BUS] = imx_clk_gate2("gpt1_bus", "perclk", base + 0x6c, 20);
clks[IMX6UL_CLK_GPT1_SERIAL] = imx_clk_gate2("gpt1_serial", "perclk", base + 0x6c, 22);
clks[IMX6UL_CLK_UART4_IPG] = imx_clk_gate2("uart4_ipg", "ipg", base + 0x6c, 24);
- clks[IMX6UL_CLK_UART4_SERIAL] = imx_clk_gate2("uart4_serail", "uart_podf", base + 0x6c, 24);
+ clks[IMX6UL_CLK_UART4_SERIAL] = imx_clk_gate2("uart4_serial", "uart_podf", base + 0x6c, 24);
/* CCGR2 */
if (clk_on_imx6ull()) {
for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
clk_prepare_enable(clks[clks_init_on[i]]);
+ if (clk_on_imx6ull())
+ clk_prepare_enable(clks[IMX6UL_CLK_AIPSTZ3]);
+
if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
clk_prepare_enable(clks[IMX6UL_CLK_USBPHY1_GATE]);
clk_prepare_enable(clks[IMX6UL_CLK_USBPHY2_GATE]);
IMX7D_PLL_SYS_MAIN_480M_CLK, IMX7D_NAND_USDHC_BUS_ROOT_CLK,
IMX7D_DRAM_PHYM_ROOT_CLK, IMX7D_DRAM_ROOT_CLK,
IMX7D_DRAM_PHYM_ALT_ROOT_CLK, IMX7D_DRAM_ALT_ROOT_CLK,
- IMX7D_AHB_CHANNEL_ROOT_CLK,
+ IMX7D_AHB_CHANNEL_ROOT_CLK, IMX7D_IPG_ROOT_CLK,
};
static struct clk_onecell_data clk_data;
clks[IMX7D_MAIN_AXI_ROOT_DIV] = imx_clk_divider2("axi_post_div", "axi_pre_div", base + 0x8800, 0, 6);
clks[IMX7D_DISP_AXI_ROOT_DIV] = imx_clk_divider2("disp_axi_post_div", "disp_axi_pre_div", base + 0x8880, 0, 6);
clks[IMX7D_ENET_AXI_ROOT_DIV] = imx_clk_divider2("enet_axi_post_div", "enet_axi_pre_div", base + 0x8900, 0, 6);
- clks[IMX7D_NAND_USDHC_BUS_ROOT_DIV] = imx_clk_divider2("nand_usdhc_post_div", "nand_usdhc_pre_div", base + 0x8980, 0, 6);
- clks[IMX7D_AHB_CHANNEL_ROOT_DIV] = imx_clk_divider2("ahb_post_div", "ahb_pre_div", base + 0x9000, 0, 6);
+ clks[IMX7D_NAND_USDHC_BUS_ROOT_CLK] = imx_clk_divider2("nand_usdhc_root_clk", "nand_usdhc_pre_div", base + 0x8980, 0, 6);
+ clks[IMX7D_AHB_CHANNEL_ROOT_DIV] = imx_clk_divider2("ahb_root_clk", "ahb_pre_div", base + 0x9000, 0, 6);
+ clks[IMX7D_IPG_ROOT_CLK] = imx_clk_divider2("ipg_root_clk", "ahb_root_clk", base + 0x9080, 0, 2);
clks[IMX7D_DRAM_ROOT_DIV] = imx_clk_divider2("dram_post_div", "dram_cg", base + 0x9880, 0, 3);
clks[IMX7D_DRAM_PHYM_ALT_ROOT_DIV] = imx_clk_divider2("dram_phym_alt_post_div", "dram_phym_alt_pre_div", base + 0xa000, 0, 3);
clks[IMX7D_DRAM_ALT_ROOT_DIV] = imx_clk_divider2("dram_alt_post_div", "dram_alt_pre_div", base + 0xa080, 0, 3);
clks[IMX7D_DISP_AXI_ROOT_CLK] = imx_clk_gate4("disp_axi_root_clk", "disp_axi_post_div", base + 0x4050, 0);
clks[IMX7D_ENET_AXI_ROOT_CLK] = imx_clk_gate4("enet_axi_root_clk", "enet_axi_post_div", base + 0x4060, 0);
clks[IMX7D_OCRAM_CLK] = imx_clk_gate4("ocram_clk", "axi_post_div", base + 0x4110, 0);
- clks[IMX7D_OCRAM_S_CLK] = imx_clk_gate4("ocram_s_clk", "ahb_post_div", base + 0x4120, 0);
- clks[IMX7D_NAND_USDHC_BUS_ROOT_CLK] = imx_clk_gate4("nand_usdhc_root_clk", "nand_usdhc_post_div", base + 0x4130, 0);
- clks[IMX7D_AHB_CHANNEL_ROOT_CLK] = imx_clk_gate4("ahb_root_clk", "ahb_post_div", base + 0x4200, 0);
+ clks[IMX7D_OCRAM_S_CLK] = imx_clk_gate4("ocram_s_clk", "ahb_root_clk", base + 0x4120, 0);
clks[IMX7D_DRAM_ROOT_CLK] = imx_clk_gate4("dram_root_clk", "dram_post_div", base + 0x4130, 0);
clks[IMX7D_DRAM_PHYM_ROOT_CLK] = imx_clk_gate4("dram_phym_root_clk", "dram_phym_cg", base + 0x4130, 0);
clks[IMX7D_DRAM_PHYM_ALT_ROOT_CLK] = imx_clk_gate4("dram_phym_alt_root_clk", "dram_phym_alt_post_div", base + 0x4130, 0);
---help---
This driver supports Mediatek MT2701 bdpsys clocks.
+config COMMON_CLK_MT6797
+ bool "Clock driver for Mediatek MT6797"
+ depends on (ARCH_MEDIATEK && ARM64) || COMPILE_TEST
+ select COMMON_CLK_MEDIATEK
+ default ARCH_MEDIATEK && ARM64
+ ---help---
+ This driver supports Mediatek MT6797 basic clocks.
+
+config COMMON_CLK_MT6797_MMSYS
+ bool "Clock driver for Mediatek MT6797 mmsys"
+ depends on COMMON_CLK_MT6797
+ ---help---
+ This driver supports Mediatek MT6797 mmsys clocks.
+
+config COMMON_CLK_MT6797_IMGSYS
+ bool "Clock driver for Mediatek MT6797 imgsys"
+ depends on COMMON_CLK_MT6797
+ ---help---
+ This driver supports Mediatek MT6797 imgsys clocks.
+
+config COMMON_CLK_MT6797_VDECSYS
+ bool "Clock driver for Mediatek MT6797 vdecsys"
+ depends on COMMON_CLK_MT6797
+ ---help---
+ This driver supports Mediatek MT6797 vdecsys clocks.
+
+config COMMON_CLK_MT6797_VENCSYS
+ bool "Clock driver for Mediatek MT6797 vencsys"
+ depends on COMMON_CLK_MT6797
+ ---help---
+ This driver supports Mediatek MT6797 vencsys clocks.
+
config COMMON_CLK_MT8135
bool "Clock driver for Mediatek MT8135"
depends on (ARCH_MEDIATEK && ARM) || COMPILE_TEST
obj-$(CONFIG_COMMON_CLK_MEDIATEK) += clk-mtk.o clk-pll.o clk-gate.o clk-apmixed.o
obj-$(CONFIG_RESET_CONTROLLER) += reset.o
+obj-$(CONFIG_COMMON_CLK_MT6797) += clk-mt6797.o
+obj-$(CONFIG_COMMON_CLK_MT6797_IMGSYS) += clk-mt6797-img.o
+obj-$(CONFIG_COMMON_CLK_MT6797_MMSYS) += clk-mt6797-mm.o
+obj-$(CONFIG_COMMON_CLK_MT6797_VDECSYS) += clk-mt6797-vdec.o
+obj-$(CONFIG_COMMON_CLK_MT6797_VENCSYS) += clk-mt6797-venc.o
obj-$(CONFIG_COMMON_CLK_MT2701) += clk-mt2701.o
obj-$(CONFIG_COMMON_CLK_MT2701_BDPSYS) += clk-mt2701-bdp.o
obj-$(CONFIG_COMMON_CLK_MT2701_ETHSYS) += clk-mt2701-eth.o
"could not register clock provider: %s: %d\n",
pdev->name, r);
+ mtk_register_reset_controller(node, 1, 0x34);
+
return r;
}
--- /dev/null
+/* Copyright (c) 2017 MediaTek Inc.
+ * Author: Kevin Chen <kevin-cw.chen@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+#include <dt-bindings/clock/mt6797-clk.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+static const struct mtk_gate_regs img_cg_regs = {
+ .set_ofs = 0x0004,
+ .clr_ofs = 0x0008,
+ .sta_ofs = 0x0000,
+};
+
+#define GATE_IMG(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &img_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr, \
+ }
+
+static const struct mtk_gate img_clks[] = {
+ GATE_IMG(CLK_IMG_FDVT, "img_fdvt", "mm_sel", 11),
+ GATE_IMG(CLK_IMG_DPE, "img_dpe", "mm_sel", 10),
+ GATE_IMG(CLK_IMG_DIP, "img_dip", "mm_sel", 6),
+ GATE_IMG(CLK_IMG_LARB6, "img_larb6", "mm_sel", 0),
+};
+
+static const struct of_device_id of_match_clk_mt6797_img[] = {
+ { .compatible = "mediatek,mt6797-imgsys", },
+ {}
+};
+
+static int clk_mt6797_img_probe(struct platform_device *pdev)
+{
+ struct clk_onecell_data *clk_data;
+ int r;
+ struct device_node *node = pdev->dev.of_node;
+
+ clk_data = mtk_alloc_clk_data(CLK_IMG_NR);
+
+ mtk_clk_register_gates(node, img_clks, ARRAY_SIZE(img_clks),
+ clk_data);
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ if (r)
+ dev_err(&pdev->dev,
+ "could not register clock provider: %s: %d\n",
+ pdev->name, r);
+
+ return r;
+}
+
+static struct platform_driver clk_mt6797_img_drv = {
+ .probe = clk_mt6797_img_probe,
+ .driver = {
+ .name = "clk-mt6797-img",
+ .of_match_table = of_match_clk_mt6797_img,
+ },
+};
+
+builtin_platform_driver(clk_mt6797_img_drv);
--- /dev/null
+/*
+ * Copyright (c) 2017 MediaTek Inc.
+ * Author: Kevin Chen <kevin-cw.chen@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+#include <dt-bindings/clock/mt6797-clk.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+static const struct mtk_gate_regs mm0_cg_regs = {
+ .set_ofs = 0x0104,
+ .clr_ofs = 0x0108,
+ .sta_ofs = 0x0100,
+};
+
+static const struct mtk_gate_regs mm1_cg_regs = {
+ .set_ofs = 0x0114,
+ .clr_ofs = 0x0118,
+ .sta_ofs = 0x0110,
+};
+
+#define GATE_MM0(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &mm0_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr, \
+}
+
+#define GATE_MM1(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &mm1_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr, \
+}
+
+static const struct mtk_gate mm_clks[] = {
+ GATE_MM0(CLK_MM_SMI_COMMON, "mm_smi_common", "mm_sel", 0),
+ GATE_MM0(CLK_MM_SMI_LARB0, "mm_smi_larb0", "mm_sel", 1),
+ GATE_MM0(CLK_MM_SMI_LARB5, "mm_smi_larb5", "mm_sel", 2),
+ GATE_MM0(CLK_MM_CAM_MDP, "mm_cam_mdp", "mm_sel", 3),
+ GATE_MM0(CLK_MM_MDP_RDMA0, "mm_mdp_rdma0", "mm_sel", 4),
+ GATE_MM0(CLK_MM_MDP_RDMA1, "mm_mdp_rdma1", "mm_sel", 5),
+ GATE_MM0(CLK_MM_MDP_RSZ0, "mm_mdp_rsz0", "mm_sel", 6),
+ GATE_MM0(CLK_MM_MDP_RSZ1, "mm_mdp_rsz1", "mm_sel", 7),
+ GATE_MM0(CLK_MM_MDP_RSZ2, "mm_mdp_rsz2", "mm_sel", 8),
+ GATE_MM0(CLK_MM_MDP_TDSHP, "mm_mdp_tdshp", "mm_sel", 9),
+ GATE_MM0(CLK_MM_MDP_COLOR, "mm_mdp_color", "mm_sel", 10),
+ GATE_MM0(CLK_MM_MDP_WDMA, "mm_mdp_wdma", "mm_sel", 11),
+ GATE_MM0(CLK_MM_MDP_WROT0, "mm_mdp_wrot0", "mm_sel", 12),
+ GATE_MM0(CLK_MM_MDP_WROT1, "mm_mdp_wrot1", "mm_sel", 13),
+ GATE_MM0(CLK_MM_FAKE_ENG, "mm_fake_eng", "mm_sel", 14),
+ GATE_MM0(CLK_MM_DISP_OVL0, "mm_disp_ovl0", "mm_sel", 15),
+ GATE_MM0(CLK_MM_DISP_OVL1, "mm_disp_ovl1", "mm_sel", 16),
+ GATE_MM0(CLK_MM_DISP_OVL0_2L, "mm_disp_ovl0_2l", "mm_sel", 17),
+ GATE_MM0(CLK_MM_DISP_OVL1_2L, "mm_disp_ovl1_2l", "mm_sel", 18),
+ GATE_MM0(CLK_MM_DISP_RDMA0, "mm_disp_rdma0", "mm_sel", 19),
+ GATE_MM0(CLK_MM_DISP_RDMA1, "mm_disp_rdma1", "mm_sel", 20),
+ GATE_MM0(CLK_MM_DISP_WDMA0, "mm_disp_wdma0", "mm_sel", 21),
+ GATE_MM0(CLK_MM_DISP_WDMA1, "mm_disp_wdma1", "mm_sel", 22),
+ GATE_MM0(CLK_MM_DISP_COLOR, "mm_disp_color", "mm_sel", 23),
+ GATE_MM0(CLK_MM_DISP_CCORR, "mm_disp_ccorr", "mm_sel", 24),
+ GATE_MM0(CLK_MM_DISP_AAL, "mm_disp_aal", "mm_sel", 25),
+ GATE_MM0(CLK_MM_DISP_GAMMA, "mm_disp_gamma", "mm_sel", 26),
+ GATE_MM0(CLK_MM_DISP_OD, "mm_disp_od", "mm_sel", 27),
+ GATE_MM0(CLK_MM_DISP_DITHER, "mm_disp_dither", "mm_sel", 28),
+ GATE_MM0(CLK_MM_DISP_UFOE, "mm_disp_ufoe", "mm_sel", 29),
+ GATE_MM0(CLK_MM_DISP_DSC, "mm_disp_dsc", "mm_sel", 30),
+ GATE_MM0(CLK_MM_DISP_SPLIT, "mm_disp_split", "mm_sel", 31),
+ GATE_MM1(CLK_MM_DSI0_MM_CLOCK, "mm_dsi0_mm_clock", "mm_sel", 0),
+ GATE_MM1(CLK_MM_DSI1_MM_CLOCK, "mm_dsi1_mm_clock", "mm_sel", 2),
+ GATE_MM1(CLK_MM_DPI_MM_CLOCK, "mm_dpi_mm_clock", "mm_sel", 4),
+ GATE_MM1(CLK_MM_DPI_INTERFACE_CLOCK, "mm_dpi_interface_clock",
+ "dpi0_sel", 5),
+ GATE_MM1(CLK_MM_LARB4_AXI_ASIF_MM_CLOCK, "mm_larb4_axi_asif_mm_clock",
+ "mm_sel", 6),
+ GATE_MM1(CLK_MM_LARB4_AXI_ASIF_MJC_CLOCK, "mm_larb4_axi_asif_mjc_clock",
+ "mjc_sel", 7),
+ GATE_MM1(CLK_MM_DISP_OVL0_MOUT_CLOCK, "mm_disp_ovl0_mout_clock",
+ "mm_sel", 8),
+ GATE_MM1(CLK_MM_FAKE_ENG2, "mm_fake_eng2", "mm_sel", 9),
+ GATE_MM1(CLK_MM_DSI0_INTERFACE_CLOCK, "mm_dsi0_interface_clock",
+ "clk26m", 1),
+ GATE_MM1(CLK_MM_DSI1_INTERFACE_CLOCK, "mm_dsi1_interface_clock",
+ "clk26m", 3),
+};
+
+static const struct of_device_id of_match_clk_mt6797_mm[] = {
+ { .compatible = "mediatek,mt6797-mmsys", },
+ {}
+};
+
+static int clk_mt6797_mm_probe(struct platform_device *pdev)
+{
+ struct clk_onecell_data *clk_data;
+ int r;
+ struct device_node *node = pdev->dev.of_node;
+
+ clk_data = mtk_alloc_clk_data(CLK_MM_NR);
+
+ mtk_clk_register_gates(node, mm_clks, ARRAY_SIZE(mm_clks),
+ clk_data);
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ if (r)
+ dev_err(&pdev->dev,
+ "could not register clock provider: %s: %d\n",
+ pdev->name, r);
+
+ return r;
+}
+
+static struct platform_driver clk_mt6797_mm_drv = {
+ .probe = clk_mt6797_mm_probe,
+ .driver = {
+ .name = "clk-mt6797-mm",
+ .of_match_table = of_match_clk_mt6797_mm,
+ },
+};
+
+builtin_platform_driver(clk_mt6797_mm_drv);
--- /dev/null
+/*
+ * Copyright (c) 2017 MediaTek Inc.
+ * Author: Kevin-CW Chen <kevin-cw.chen@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+#include <dt-bindings/clock/mt6797-clk.h>
+
+static const struct mtk_gate_regs vdec0_cg_regs = {
+ .set_ofs = 0x0000,
+ .clr_ofs = 0x0004,
+ .sta_ofs = 0x0000,
+};
+
+static const struct mtk_gate_regs vdec1_cg_regs = {
+ .set_ofs = 0x0008,
+ .clr_ofs = 0x000c,
+ .sta_ofs = 0x0008,
+};
+
+#define GATE_VDEC0(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &vdec0_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr_inv, \
+}
+
+#define GATE_VDEC1(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &vdec1_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr_inv, \
+}
+
+static const struct mtk_gate vdec_clks[] = {
+ GATE_VDEC0(CLK_VDEC_CKEN_ENG, "vdec_cken_eng", "vdec_sel", 8),
+ GATE_VDEC0(CLK_VDEC_ACTIVE, "vdec_active", "vdec_sel", 4),
+ GATE_VDEC0(CLK_VDEC_CKEN, "vdec_cken", "vdec_sel", 0),
+ GATE_VDEC1(CLK_VDEC_LARB1_CKEN, "vdec_larb1_cken", "mm_sel", 0),
+};
+
+static const struct of_device_id of_match_clk_mt6797_vdec[] = {
+ { .compatible = "mediatek,mt6797-vdecsys", },
+ {}
+};
+
+static int clk_mt6797_vdec_probe(struct platform_device *pdev)
+{
+ struct clk_onecell_data *clk_data;
+ int r;
+ struct device_node *node = pdev->dev.of_node;
+
+ clk_data = mtk_alloc_clk_data(CLK_VDEC_NR);
+
+ mtk_clk_register_gates(node, vdec_clks, ARRAY_SIZE(vdec_clks),
+ clk_data);
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ if (r)
+ dev_err(&pdev->dev,
+ "could not register clock provider: %s: %d\n",
+ pdev->name, r);
+
+ return r;
+}
+
+static struct platform_driver clk_mt6797_vdec_drv = {
+ .probe = clk_mt6797_vdec_probe,
+ .driver = {
+ .name = "clk-mt6797-vdec",
+ .of_match_table = of_match_clk_mt6797_vdec,
+ },
+};
+
+builtin_platform_driver(clk_mt6797_vdec_drv);
--- /dev/null
+/*
+ * Copyright (c) 2017 MediaTek Inc.
+ * Author: Kevin Chen <kevin-cw.chen@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+#include <dt-bindings/clock/mt6797-clk.h>
+
+static const struct mtk_gate_regs venc_cg_regs = {
+ .set_ofs = 0x0004,
+ .clr_ofs = 0x0008,
+ .sta_ofs = 0x0000,
+};
+
+#define GATE_VENC(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &venc_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr_inv, \
+ }
+
+static const struct mtk_gate venc_clks[] = {
+ GATE_VENC(CLK_VENC_0, "venc_0", "mm_sel", 0),
+ GATE_VENC(CLK_VENC_1, "venc_1", "venc_sel", 4),
+ GATE_VENC(CLK_VENC_2, "venc_2", "venc_sel", 8),
+ GATE_VENC(CLK_VENC_3, "venc_3", "venc_sel", 12),
+};
+
+static const struct of_device_id of_match_clk_mt6797_venc[] = {
+ { .compatible = "mediatek,mt6797-vencsys", },
+ {}
+};
+
+static int clk_mt6797_venc_probe(struct platform_device *pdev)
+{
+ struct clk_onecell_data *clk_data;
+ int r;
+ struct device_node *node = pdev->dev.of_node;
+
+ clk_data = mtk_alloc_clk_data(CLK_VENC_NR);
+
+ mtk_clk_register_gates(node, venc_clks, ARRAY_SIZE(venc_clks),
+ clk_data);
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+ if (r)
+ dev_err(&pdev->dev,
+ "could not register clock provider: %s: %d\n",
+ pdev->name, r);
+
+ return r;
+}
+
+static struct platform_driver clk_mt6797_venc_drv = {
+ .probe = clk_mt6797_venc_probe,
+ .driver = {
+ .name = "clk-mt6797-venc",
+ .of_match_table = of_match_clk_mt6797_venc,
+ },
+};
+
+builtin_platform_driver(clk_mt6797_venc_drv);
--- /dev/null
+/*
+ * Copyright (c) 2016 MediaTek Inc.
+ * Author: Kevin Chen <kevin-cw.chen@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+
+#include "clk-mtk.h"
+#include "clk-gate.h"
+
+#include <dt-bindings/clock/mt6797-clk.h>
+
+/*
+ * For some clocks, we don't care what their actual rates are. And these
+ * clocks may change their rate on different products or different scenarios.
+ * So we model these clocks' rate as 0, to denote it's not an actual rate.
+ */
+
+static DEFINE_SPINLOCK(mt6797_clk_lock);
+
+static const struct mtk_fixed_factor top_fixed_divs[] = {
+ FACTOR(CLK_TOP_SYSPLL_CK, "syspll_ck", "mainpll", 1, 1),
+ FACTOR(CLK_TOP_SYSPLL_D2, "syspll_d2", "mainpll", 1, 2),
+ FACTOR(CLK_TOP_SYSPLL1_D2, "syspll1_d2", "syspll_d2", 1, 2),
+ FACTOR(CLK_TOP_SYSPLL1_D4, "syspll1_d4", "syspll_d2", 1, 4),
+ FACTOR(CLK_TOP_SYSPLL1_D8, "syspll1_d8", "syspll_d2", 1, 8),
+ FACTOR(CLK_TOP_SYSPLL1_D16, "syspll1_d16", "syspll_d2", 1, 16),
+ FACTOR(CLK_TOP_SYSPLL_D3, "syspll_d3", "mainpll", 1, 3),
+ FACTOR(CLK_TOP_SYSPLL_D3_D3, "syspll_d3_d3", "syspll_d3", 1, 3),
+ FACTOR(CLK_TOP_SYSPLL2_D2, "syspll2_d2", "syspll_d3", 1, 2),
+ FACTOR(CLK_TOP_SYSPLL2_D4, "syspll2_d4", "syspll_d3", 1, 4),
+ FACTOR(CLK_TOP_SYSPLL2_D8, "syspll2_d8", "syspll_d3", 1, 8),
+ FACTOR(CLK_TOP_SYSPLL_D5, "syspll_d5", "mainpll", 1, 5),
+ FACTOR(CLK_TOP_SYSPLL3_D2, "syspll3_d2", "syspll_d5", 1, 2),
+ FACTOR(CLK_TOP_SYSPLL3_D4, "syspll3_d4", "syspll_d5", 1, 4),
+ FACTOR(CLK_TOP_SYSPLL_D7, "syspll_d7", "mainpll", 1, 7),
+ FACTOR(CLK_TOP_SYSPLL4_D2, "syspll4_d2", "syspll_d7", 1, 2),
+ FACTOR(CLK_TOP_SYSPLL4_D4, "syspll4_d4", "syspll_d7", 1, 4),
+ FACTOR(CLK_TOP_UNIVPLL_CK, "univpll_ck", "univpll", 1, 1),
+ FACTOR(CLK_TOP_UNIVPLL_D7, "univpll_d7", "univpll", 1, 7),
+ FACTOR(CLK_TOP_UNIVPLL_D26, "univpll_d26", "univpll", 1, 26),
+ FACTOR(CLK_TOP_SSUSB_PHY_48M_CK, "ssusb_phy_48m_ck", "univpll", 1, 1),
+ FACTOR(CLK_TOP_USB_PHY48M_CK, "usb_phy48m_ck", "univpll", 1, 1),
+ FACTOR(CLK_TOP_UNIVPLL_D2, "univpll_d2", "univpll", 1, 2),
+ FACTOR(CLK_TOP_UNIVPLL1_D2, "univpll1_d2", "univpll_d2", 1, 2),
+ FACTOR(CLK_TOP_UNIVPLL1_D4, "univpll1_d4", "univpll_d2", 1, 4),
+ FACTOR(CLK_TOP_UNIVPLL1_D8, "univpll1_d8", "univpll_d2", 1, 8),
+ FACTOR(CLK_TOP_UNIVPLL_D3, "univpll_d3", "univpll", 1, 3),
+ FACTOR(CLK_TOP_UNIVPLL2_D2, "univpll2_d2", "univpll", 1, 2),
+ FACTOR(CLK_TOP_UNIVPLL2_D4, "univpll2_d4", "univpll", 1, 4),
+ FACTOR(CLK_TOP_UNIVPLL2_D8, "univpll2_d8", "univpll", 1, 8),
+ FACTOR(CLK_TOP_UNIVPLL_D5, "univpll_d5", "univpll", 1, 5),
+ FACTOR(CLK_TOP_UNIVPLL3_D2, "univpll3_d2", "univpll_d5", 1, 2),
+ FACTOR(CLK_TOP_UNIVPLL3_D4, "univpll3_d4", "univpll_d5", 1, 4),
+ FACTOR(CLK_TOP_UNIVPLL3_D8, "univpll3_d8", "univpll_d5", 1, 8),
+ FACTOR(CLK_TOP_ULPOSC_CK_ORG, "ulposc_ck_org", "ulposc", 1, 1),
+ FACTOR(CLK_TOP_ULPOSC_CK, "ulposc_ck", "ulposc_ck_org", 1, 3),
+ FACTOR(CLK_TOP_ULPOSC_D2, "ulposc_d2", "ulposc_ck", 1, 2),
+ FACTOR(CLK_TOP_ULPOSC_D3, "ulposc_d3", "ulposc_ck", 1, 4),
+ FACTOR(CLK_TOP_ULPOSC_D4, "ulposc_d4", "ulposc_ck", 1, 8),
+ FACTOR(CLK_TOP_ULPOSC_D8, "ulposc_d8", "ulposc_ck", 1, 10),
+ FACTOR(CLK_TOP_ULPOSC_D10, "ulposc_d10", "ulposc_ck_org", 1, 1),
+ FACTOR(CLK_TOP_APLL1_CK, "apll1_ck", "apll1", 1, 1),
+ FACTOR(CLK_TOP_APLL2_CK, "apll2_ck", "apll2", 1, 1),
+ FACTOR(CLK_TOP_MFGPLL_CK, "mfgpll_ck", "mfgpll", 1, 1),
+ FACTOR(CLK_TOP_MFGPLL_D2, "mfgpll_d2", "mfgpll_ck", 1, 2),
+ FACTOR(CLK_TOP_IMGPLL_CK, "imgpll_ck", "imgpll", 1, 1),
+ FACTOR(CLK_TOP_IMGPLL_D2, "imgpll_d2", "imgpll_ck", 1, 2),
+ FACTOR(CLK_TOP_IMGPLL_D4, "imgpll_d4", "imgpll_ck", 1, 4),
+ FACTOR(CLK_TOP_CODECPLL_CK, "codecpll_ck", "codecpll", 1, 1),
+ FACTOR(CLK_TOP_CODECPLL_D2, "codecpll_d2", "codecpll_ck", 1, 2),
+ FACTOR(CLK_TOP_VDECPLL_CK, "vdecpll_ck", "vdecpll", 1, 1),
+ FACTOR(CLK_TOP_TVDPLL_CK, "tvdpll_ck", "tvdpll", 1, 1),
+ FACTOR(CLK_TOP_TVDPLL_D2, "tvdpll_d2", "tvdpll_ck", 1, 2),
+ FACTOR(CLK_TOP_TVDPLL_D4, "tvdpll_d4", "tvdpll_ck", 1, 4),
+ FACTOR(CLK_TOP_TVDPLL_D8, "tvdpll_d8", "tvdpll_ck", 1, 8),
+ FACTOR(CLK_TOP_TVDPLL_D16, "tvdpll_d16", "tvdpll_ck", 1, 16),
+ FACTOR(CLK_TOP_MSDCPLL_CK, "msdcpll_ck", "msdcpll", 1, 1),
+ FACTOR(CLK_TOP_MSDCPLL_D2, "msdcpll_d2", "msdcpll_ck", 1, 2),
+ FACTOR(CLK_TOP_MSDCPLL_D4, "msdcpll_d4", "msdcpll_ck", 1, 4),
+ FACTOR(CLK_TOP_MSDCPLL_D8, "msdcpll_d8", "msdcpll_ck", 1, 8),
+};
+
+static const char * const axi_parents[] = {
+ "clk26m",
+ "syspll_d7",
+ "ulposc_axi_ck_mux",
+};
+
+static const char * const ulposc_axi_ck_mux_parents[] = {
+ "syspll1_d4",
+ "ulposc_axi_ck_mux_pre",
+};
+
+static const char * const ulposc_axi_ck_mux_pre_parents[] = {
+ "ulposc_d2",
+ "ulposc_d3",
+};
+
+static const char * const ddrphycfg_parents[] = {
+ "clk26m",
+ "syspll3_d2",
+ "syspll2_d4",
+ "syspll1_d8",
+};
+
+static const char * const mm_parents[] = {
+ "clk26m",
+ "imgpll_ck",
+ "univpll1_d2",
+ "syspll1_d2",
+};
+
+static const char * const pwm_parents[] = {
+ "clk26m",
+ "univpll2_d4",
+ "ulposc_d2",
+ "ulposc_d3",
+ "ulposc_d8",
+ "ulposc_d10",
+ "ulposc_d4",
+};
+
+static const char * const vdec_parents[] = {
+ "clk26m",
+ "vdecpll_ck",
+ "imgpll_ck",
+ "syspll_d3",
+ "univpll_d5",
+ "clk26m",
+ "clk26m",
+};
+
+static const char * const venc_parents[] = {
+ "clk26m",
+ "codecpll_ck",
+ "syspll_d3",
+};
+
+static const char * const mfg_parents[] = {
+ "clk26m",
+ "mfgpll_ck",
+ "syspll_d3",
+ "univpll_d3",
+};
+
+static const char * const camtg[] = {
+ "clk26m",
+ "univpll_d26",
+ "univpll2_d2",
+};
+
+static const char * const uart_parents[] = {
+ "clk26m",
+ "univpll2_d8",
+};
+
+static const char * const spi_parents[] = {
+ "clk26m",
+ "syspll3_d2",
+ "syspll2_d4",
+ "ulposc_spi_ck_mux",
+};
+
+static const char * const ulposc_spi_ck_mux_parents[] = {
+ "ulposc_d2",
+ "ulposc_d3",
+};
+
+static const char * const usb20_parents[] = {
+ "clk26m",
+ "univpll1_d8",
+ "syspll4_d2",
+};
+
+static const char * const msdc50_0_hclk_parents[] = {
+ "clk26m",
+ "syspll1_d2",
+ "syspll2_d2",
+ "syspll4_d2",
+};
+
+static const char * const msdc50_0_parents[] = {
+ "clk26m",
+ "msdcpll",
+ "syspll_d3",
+ "univpll1_d4",
+ "syspll2_d2",
+ "syspll_d7",
+ "msdcpll_d2",
+ "univpll1_d2",
+ "univpll_d3",
+};
+
+static const char * const msdc30_1_parents[] = {
+ "clk26m",
+ "univpll2_d2",
+ "msdcpll_d2",
+ "univpll1_d4",
+ "syspll2_d2",
+ "syspll_d7",
+ "univpll_d7",
+};
+
+static const char * const msdc30_2_parents[] = {
+ "clk26m",
+ "univpll2_d8",
+ "syspll2_d8",
+ "syspll1_d8",
+ "msdcpll_d8",
+ "syspll3_d4",
+ "univpll_d26",
+};
+
+static const char * const audio_parents[] = {
+ "clk26m",
+ "syspll3_d4",
+ "syspll4_d4",
+ "syspll1_d16",
+};
+
+static const char * const aud_intbus_parents[] = {
+ "clk26m",
+ "syspll1_d4",
+ "syspll4_d2",
+};
+
+static const char * const pmicspi_parents[] = {
+ "clk26m",
+ "univpll_d26",
+ "syspll3_d4",
+ "syspll1_d8",
+ "ulposc_d4",
+ "ulposc_d8",
+ "syspll2_d8",
+};
+
+static const char * const scp_parents[] = {
+ "clk26m",
+ "syspll_d3",
+ "ulposc_ck",
+ "univpll_d5",
+};
+
+static const char * const atb_parents[] = {
+ "clk26m",
+ "syspll1_d2",
+ "syspll_d5",
+};
+
+static const char * const mjc_parents[] = {
+ "clk26m",
+ "imgpll_ck",
+ "univpll_d5",
+ "syspll1_d2",
+};
+
+static const char * const dpi0_parents[] = {
+ "clk26m",
+ "tvdpll_d2",
+ "tvdpll_d4",
+ "tvdpll_d8",
+ "tvdpll_d16",
+ "clk26m",
+ "clk26m",
+};
+
+static const char * const aud_1_parents[] = {
+ "clk26m",
+ "apll1_ck",
+};
+
+static const char * const aud_2_parents[] = {
+ "clk26m",
+ "apll2_ck",
+};
+
+static const char * const ssusb_top_sys_parents[] = {
+ "clk26m",
+ "univpll3_d2",
+};
+
+static const char * const spm_parents[] = {
+ "clk26m",
+ "syspll1_d8",
+};
+
+static const char * const bsi_spi_parents[] = {
+ "clk26m",
+ "syspll_d3_d3",
+ "syspll1_d4",
+ "syspll_d7",
+};
+
+static const char * const audio_h_parents[] = {
+ "clk26m",
+ "apll2_ck",
+ "apll1_ck",
+ "univpll_d7",
+};
+
+static const char * const mfg_52m_parents[] = {
+ "clk26m",
+ "univpll2_d8",
+ "univpll2_d4",
+ "univpll2_d4",
+};
+
+static const char * const anc_md32_parents[] = {
+ "clk26m",
+ "syspll1_d2",
+ "univpll_d5",
+};
+
+static const struct mtk_composite top_muxes[] = {
+ MUX(CLK_TOP_MUX_ULPOSC_AXI_CK_MUX_PRE, "ulposc_axi_ck_mux_pre",
+ ulposc_axi_ck_mux_pre_parents, 0x0040, 3, 1),
+ MUX(CLK_TOP_MUX_ULPOSC_AXI_CK_MUX, "ulposc_axi_ck_mux",
+ ulposc_axi_ck_mux_parents, 0x0040, 2, 1),
+ MUX(CLK_TOP_MUX_AXI, "axi_sel", axi_parents,
+ 0x0040, 0, 2),
+ MUX(CLK_TOP_MUX_DDRPHYCFG, "ddrphycfg_sel", ddrphycfg_parents,
+ 0x0040, 16, 2),
+ MUX(CLK_TOP_MUX_MM, "mm_sel", mm_parents,
+ 0x0040, 24, 2),
+ MUX_GATE(CLK_TOP_MUX_PWM, "pwm_sel", pwm_parents, 0x0050, 0, 3, 7),
+ MUX_GATE(CLK_TOP_MUX_VDEC, "vdec_sel", vdec_parents, 0x0050, 8, 3, 15),
+ MUX_GATE(CLK_TOP_MUX_VENC, "venc_sel", venc_parents, 0x0050, 16, 2, 23),
+ MUX_GATE(CLK_TOP_MUX_MFG, "mfg_sel", mfg_parents, 0x0050, 24, 2, 31),
+ MUX_GATE(CLK_TOP_MUX_CAMTG, "camtg_sel", camtg, 0x0060, 0, 2, 7),
+ MUX_GATE(CLK_TOP_MUX_UART, "uart_sel", uart_parents, 0x0060, 8, 1, 15),
+ MUX_GATE(CLK_TOP_MUX_SPI, "spi_sel", spi_parents, 0x0060, 16, 2, 23),
+ MUX(CLK_TOP_MUX_ULPOSC_SPI_CK_MUX, "ulposc_spi_ck_mux",
+ ulposc_spi_ck_mux_parents, 0x0060, 18, 1),
+ MUX_GATE(CLK_TOP_MUX_USB20, "usb20_sel", usb20_parents,
+ 0x0060, 24, 2, 31),
+ MUX(CLK_TOP_MUX_MSDC50_0_HCLK, "msdc50_0_hclk_sel",
+ msdc50_0_hclk_parents, 0x0070, 8, 2),
+ MUX_GATE(CLK_TOP_MUX_MSDC50_0, "msdc50_0_sel", msdc50_0_parents,
+ 0x0070, 16, 4, 23),
+ MUX_GATE(CLK_TOP_MUX_MSDC30_1, "msdc30_1_sel", msdc30_1_parents,
+ 0x0070, 24, 3, 31),
+ MUX_GATE(CLK_TOP_MUX_MSDC30_2, "msdc30_2_sel", msdc30_2_parents,
+ 0x0080, 0, 3, 7),
+ MUX_GATE(CLK_TOP_MUX_AUDIO, "audio_sel", audio_parents,
+ 0x0080, 16, 2, 23),
+ MUX(CLK_TOP_MUX_AUD_INTBUS, "aud_intbus_sel", aud_intbus_parents,
+ 0x0080, 24, 2),
+ MUX(CLK_TOP_MUX_PMICSPI, "pmicspi_sel", pmicspi_parents,
+ 0x0090, 0, 3),
+ MUX(CLK_TOP_MUX_SCP, "scp_sel", scp_parents,
+ 0x0090, 8, 2),
+ MUX(CLK_TOP_MUX_ATB, "atb_sel", atb_parents,
+ 0x0090, 16, 2),
+ MUX_GATE(CLK_TOP_MUX_MJC, "mjc_sel", mjc_parents, 0x0090, 24, 2, 31),
+ MUX_GATE(CLK_TOP_MUX_DPI0, "dpi0_sel", dpi0_parents, 0x00A0, 0, 3, 7),
+ MUX_GATE(CLK_TOP_MUX_AUD_1, "aud_1_sel", aud_1_parents,
+ 0x00A0, 16, 1, 23),
+ MUX_GATE(CLK_TOP_MUX_AUD_2, "aud_2_sel", aud_2_parents,
+ 0x00A0, 24, 1, 31),
+ MUX(CLK_TOP_MUX_SSUSB_TOP_SYS, "ssusb_top_sys_sel",
+ ssusb_top_sys_parents, 0x00B0, 8, 1),
+ MUX(CLK_TOP_MUX_SPM, "spm_sel", spm_parents,
+ 0x00C0, 0, 1),
+ MUX(CLK_TOP_MUX_BSI_SPI, "bsi_spi_sel", bsi_spi_parents,
+ 0x00C0, 8, 2),
+ MUX_GATE(CLK_TOP_MUX_AUDIO_H, "audio_h_sel", audio_h_parents,
+ 0x00C0, 16, 2, 23),
+ MUX_GATE(CLK_TOP_MUX_ANC_MD32, "anc_md32_sel", anc_md32_parents,
+ 0x00C0, 24, 2, 31),
+ MUX(CLK_TOP_MUX_MFG_52M, "mfg_52m_sel", mfg_52m_parents,
+ 0x0104, 1, 2),
+};
+
+static int mtk_topckgen_init(struct platform_device *pdev)
+{
+ struct clk_onecell_data *clk_data;
+ void __iomem *base;
+ struct device_node *node = pdev->dev.of_node;
+ struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+ base = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ clk_data = mtk_alloc_clk_data(CLK_TOP_NR);
+
+ mtk_clk_register_factors(top_fixed_divs, ARRAY_SIZE(top_fixed_divs),
+ clk_data);
+
+ mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base,
+ &mt6797_clk_lock, clk_data);
+
+ return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+}
+
+static const struct mtk_gate_regs infra0_cg_regs = {
+ .set_ofs = 0x0080,
+ .clr_ofs = 0x0084,
+ .sta_ofs = 0x0090,
+};
+
+static const struct mtk_gate_regs infra1_cg_regs = {
+ .set_ofs = 0x0088,
+ .clr_ofs = 0x008c,
+ .sta_ofs = 0x0094,
+};
+
+static const struct mtk_gate_regs infra2_cg_regs = {
+ .set_ofs = 0x00a8,
+ .clr_ofs = 0x00ac,
+ .sta_ofs = 0x00b0,
+};
+
+#define GATE_ICG0(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &infra0_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr, \
+}
+
+#define GATE_ICG1(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &infra1_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr, \
+}
+
+#define GATE_ICG2(_id, _name, _parent, _shift) { \
+ .id = _id, \
+ .name = _name, \
+ .parent_name = _parent, \
+ .regs = &infra2_cg_regs, \
+ .shift = _shift, \
+ .ops = &mtk_clk_gate_ops_setclr, \
+}
+
+static const struct mtk_gate infra_clks[] = {
+ GATE_ICG0(CLK_INFRA_PMIC_TMR, "infra_pmic_tmr", "ulposc", 0),
+ GATE_ICG0(CLK_INFRA_PMIC_AP, "infra_pmic_ap", "pmicspi_sel", 1),
+ GATE_ICG0(CLK_INFRA_PMIC_MD, "infra_pmic_md", "pmicspi_sel", 2),
+ GATE_ICG0(CLK_INFRA_PMIC_CONN, "infra_pmic_conn", "pmicspi_sel", 3),
+ GATE_ICG0(CLK_INFRA_SCP, "infra_scp", "scp_sel", 4),
+ GATE_ICG0(CLK_INFRA_SEJ, "infra_sej", "axi_sel", 5),
+ GATE_ICG0(CLK_INFRA_APXGPT, "infra_apxgpt", "axi_sel", 6),
+ GATE_ICG0(CLK_INFRA_SEJ_13M, "infra_sej_13m", "clk26m", 7),
+ GATE_ICG0(CLK_INFRA_ICUSB, "infra_icusb", "usb20_sel", 8),
+ GATE_ICG0(CLK_INFRA_GCE, "infra_gce", "axi_sel", 9),
+ GATE_ICG0(CLK_INFRA_THERM, "infra_therm", "axi_sel", 10),
+ GATE_ICG0(CLK_INFRA_I2C0, "infra_i2c0", "axi_sel", 11),
+ GATE_ICG0(CLK_INFRA_I2C1, "infra_i2c1", "axi_sel", 12),
+ GATE_ICG0(CLK_INFRA_I2C2, "infra_i2c2", "axi_sel", 13),
+ GATE_ICG0(CLK_INFRA_I2C3, "infra_i2c3", "axi_sel", 14),
+ GATE_ICG0(CLK_INFRA_PWM_HCLK, "infra_pwm_hclk", "axi_sel", 15),
+ GATE_ICG0(CLK_INFRA_PWM1, "infra_pwm1", "axi_sel", 16),
+ GATE_ICG0(CLK_INFRA_PWM2, "infra_pwm2", "axi_sel", 17),
+ GATE_ICG0(CLK_INFRA_PWM3, "infra_pwm3", "axi_sel", 18),
+ GATE_ICG0(CLK_INFRA_PWM4, "infra_pwm4", "axi_sel", 19),
+ GATE_ICG0(CLK_INFRA_PWM, "infra_pwm", "axi_sel", 21),
+ GATE_ICG0(CLK_INFRA_UART0, "infra_uart0", "uart_sel", 22),
+ GATE_ICG0(CLK_INFRA_UART1, "infra_uart1", "uart_sel", 23),
+ GATE_ICG0(CLK_INFRA_UART2, "infra_uart2", "uart_sel", 24),
+ GATE_ICG0(CLK_INFRA_UART3, "infra_uart3", "uart_sel", 25),
+ GATE_ICG0(CLK_INFRA_MD2MD_CCIF_0, "infra_md2md_ccif_0", "axi_sel", 27),
+ GATE_ICG0(CLK_INFRA_MD2MD_CCIF_1, "infra_md2md_ccif_1", "axi_sel", 28),
+ GATE_ICG0(CLK_INFRA_MD2MD_CCIF_2, "infra_md2md_ccif_2", "axi_sel", 29),
+ GATE_ICG0(CLK_INFRA_FHCTL, "infra_fhctl", "clk26m", 30),
+ GATE_ICG0(CLK_INFRA_BTIF, "infra_btif", "axi_sel", 31),
+ GATE_ICG1(CLK_INFRA_MD2MD_CCIF_3, "infra_md2md_ccif_3", "axi_sel", 0),
+ GATE_ICG1(CLK_INFRA_SPI, "infra_spi", "spi_sel", 1),
+ GATE_ICG1(CLK_INFRA_MSDC0, "infra_msdc0", "msdc50_0_sel", 2),
+ GATE_ICG1(CLK_INFRA_MD2MD_CCIF_4, "infra_md2md_ccif_4", "axi_sel", 3),
+ GATE_ICG1(CLK_INFRA_MSDC1, "infra_msdc1", "msdc30_1_sel", 4),
+ GATE_ICG1(CLK_INFRA_MSDC2, "infra_msdc2", "msdc30_2_sel", 5),
+ GATE_ICG1(CLK_INFRA_MD2MD_CCIF_5, "infra_md2md_ccif_5", "axi_sel", 7),
+ GATE_ICG1(CLK_INFRA_GCPU, "infra_gcpu", "axi_sel", 8),
+ GATE_ICG1(CLK_INFRA_TRNG, "infra_trng", "axi_sel", 9),
+ GATE_ICG1(CLK_INFRA_AUXADC, "infra_auxadc", "clk26m", 10),
+ GATE_ICG1(CLK_INFRA_CPUM, "infra_cpum", "axi_sel", 11),
+ GATE_ICG1(CLK_INFRA_AP_C2K_CCIF_0, "infra_ap_c2k_ccif_0",
+ "axi_sel", 12),
+ GATE_ICG1(CLK_INFRA_AP_C2K_CCIF_1, "infra_ap_c2k_ccif_1",
+ "axi_sel", 13),
+ GATE_ICG1(CLK_INFRA_CLDMA, "infra_cldma", "axi_sel", 16),
+ GATE_ICG1(CLK_INFRA_DISP_PWM, "infra_disp_pwm", "pwm_sel", 17),
+ GATE_ICG1(CLK_INFRA_AP_DMA, "infra_ap_dma", "axi_sel", 18),
+ GATE_ICG1(CLK_INFRA_DEVICE_APC, "infra_device_apc", "axi_sel", 20),
+ GATE_ICG1(CLK_INFRA_L2C_SRAM, "infra_l2c_sram", "mm_sel", 22),
+ GATE_ICG1(CLK_INFRA_CCIF_AP, "infra_ccif_ap", "axi_sel", 23),
+ GATE_ICG1(CLK_INFRA_AUDIO, "infra_audio", "axi_sel", 25),
+ GATE_ICG1(CLK_INFRA_CCIF_MD, "infra_ccif_md", "axi_sel", 26),
+ GATE_ICG1(CLK_INFRA_DRAMC_F26M, "infra_dramc_f26m", "clk26m", 31),
+ GATE_ICG2(CLK_INFRA_I2C4, "infra_i2c4", "axi_sel", 0),
+ GATE_ICG2(CLK_INFRA_I2C_APPM, "infra_i2c_appm", "axi_sel", 1),
+ GATE_ICG2(CLK_INFRA_I2C_GPUPM, "infra_i2c_gpupm", "axi_sel", 2),
+ GATE_ICG2(CLK_INFRA_I2C2_IMM, "infra_i2c2_imm", "axi_sel", 3),
+ GATE_ICG2(CLK_INFRA_I2C2_ARB, "infra_i2c2_arb", "axi_sel", 4),
+ GATE_ICG2(CLK_INFRA_I2C3_IMM, "infra_i2c3_imm", "axi_sel", 5),
+ GATE_ICG2(CLK_INFRA_I2C3_ARB, "infra_i2c3_arb", "axi_sel", 6),
+ GATE_ICG2(CLK_INFRA_I2C5, "infra_i2c5", "axi_sel", 7),
+ GATE_ICG2(CLK_INFRA_SYS_CIRQ, "infra_sys_cirq", "axi_sel", 8),
+ GATE_ICG2(CLK_INFRA_SPI1, "infra_spi1", "spi_sel", 10),
+ GATE_ICG2(CLK_INFRA_DRAMC_B_F26M, "infra_dramc_b_f26m", "clk26m", 11),
+ GATE_ICG2(CLK_INFRA_ANC_MD32, "infra_anc_md32", "anc_md32_sel", 12),
+ GATE_ICG2(CLK_INFRA_ANC_MD32_32K, "infra_anc_md32_32k", "clk26m", 13),
+ GATE_ICG2(CLK_INFRA_DVFS_SPM1, "infra_dvfs_spm1", "axi_sel", 15),
+ GATE_ICG2(CLK_INFRA_AES_TOP0, "infra_aes_top0", "axi_sel", 16),
+ GATE_ICG2(CLK_INFRA_AES_TOP1, "infra_aes_top1", "axi_sel", 17),
+ GATE_ICG2(CLK_INFRA_SSUSB_BUS, "infra_ssusb_bus", "axi_sel", 18),
+ GATE_ICG2(CLK_INFRA_SPI2, "infra_spi2", "spi_sel", 19),
+ GATE_ICG2(CLK_INFRA_SPI3, "infra_spi3", "spi_sel", 20),
+ GATE_ICG2(CLK_INFRA_SPI4, "infra_spi4", "spi_sel", 21),
+ GATE_ICG2(CLK_INFRA_SPI5, "infra_spi5", "spi_sel", 22),
+ GATE_ICG2(CLK_INFRA_IRTX, "infra_irtx", "spi_sel", 23),
+ GATE_ICG2(CLK_INFRA_SSUSB_SYS, "infra_ssusb_sys",
+ "ssusb_top_sys_sel", 24),
+ GATE_ICG2(CLK_INFRA_SSUSB_REF, "infra_ssusb_ref", "clk26m", 9),
+ GATE_ICG2(CLK_INFRA_AUDIO_26M, "infra_audio_26m", "clk26m", 26),
+ GATE_ICG2(CLK_INFRA_AUDIO_26M_PAD_TOP, "infra_audio_26m_pad_top",
+ "clk26m", 27),
+ GATE_ICG2(CLK_INFRA_MODEM_TEMP_SHARE, "infra_modem_temp_share",
+ "axi_sel", 28),
+ GATE_ICG2(CLK_INFRA_VAD_WRAP_SOC, "infra_vad_wrap_soc", "axi_sel", 29),
+ GATE_ICG2(CLK_INFRA_DRAMC_CONF, "infra_dramc_conf", "axi_sel", 30),
+ GATE_ICG2(CLK_INFRA_DRAMC_B_CONF, "infra_dramc_b_conf", "axi_sel", 31),
+ GATE_ICG1(CLK_INFRA_MFG_VCG, "infra_mfg_vcg", "mfg_52m_sel", 14),
+};
+
+static const struct mtk_fixed_factor infra_fixed_divs[] = {
+ FACTOR(CLK_INFRA_13M, "clk13m", "clk26m", 1, 2),
+};
+
+static struct clk_onecell_data *infra_clk_data;
+
+static void mtk_infrasys_init_early(struct device_node *node)
+{
+ int r, i;
+
+ if (!infra_clk_data) {
+ infra_clk_data = mtk_alloc_clk_data(CLK_INFRA_NR);
+
+ for (i = 0; i < CLK_INFRA_NR; i++)
+ infra_clk_data->clks[i] = ERR_PTR(-EPROBE_DEFER);
+ }
+
+ mtk_clk_register_factors(infra_fixed_divs, ARRAY_SIZE(infra_fixed_divs),
+ infra_clk_data);
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, infra_clk_data);
+ if (r)
+ pr_err("%s(): could not register clock provider: %d\n",
+ __func__, r);
+}
+
+CLK_OF_DECLARE_DRIVER(mtk_infra, "mediatek,mt6797-infracfg",
+ mtk_infrasys_init_early);
+
+static int mtk_infrasys_init(struct platform_device *pdev)
+{
+ int r, i;
+ struct device_node *node = pdev->dev.of_node;
+
+ if (!infra_clk_data) {
+ infra_clk_data = mtk_alloc_clk_data(CLK_INFRA_NR);
+ } else {
+ for (i = 0; i < CLK_INFRA_NR; i++) {
+ if (infra_clk_data->clks[i] == ERR_PTR(-EPROBE_DEFER))
+ infra_clk_data->clks[i] = ERR_PTR(-ENOENT);
+ }
+ }
+
+ mtk_clk_register_gates(node, infra_clks, ARRAY_SIZE(infra_clks),
+ infra_clk_data);
+ mtk_clk_register_factors(infra_fixed_divs, ARRAY_SIZE(infra_fixed_divs),
+ infra_clk_data);
+
+ r = of_clk_add_provider(node, of_clk_src_onecell_get, infra_clk_data);
+ if (r)
+ return r;
+
+ return 0;
+}
+
+#define MT6797_PLL_FMAX (3000UL * MHZ)
+
+#define CON0_MT6797_RST_BAR BIT(24)
+
+#define PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \
+ _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \
+ _pcw_shift, _div_table) { \
+ .id = _id, \
+ .name = _name, \
+ .reg = _reg, \
+ .pwr_reg = _pwr_reg, \
+ .en_mask = _en_mask, \
+ .flags = _flags, \
+ .rst_bar_mask = CON0_MT6797_RST_BAR, \
+ .fmax = MT6797_PLL_FMAX, \
+ .pcwbits = _pcwbits, \
+ .pd_reg = _pd_reg, \
+ .pd_shift = _pd_shift, \
+ .tuner_reg = _tuner_reg, \
+ .pcw_reg = _pcw_reg, \
+ .pcw_shift = _pcw_shift, \
+ .div_table = _div_table, \
+}
+
+#define PLL(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \
+ _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, \
+ _pcw_shift) \
+ PLL_B(_id, _name, _reg, _pwr_reg, _en_mask, _flags, _pcwbits, \
+ _pd_reg, _pd_shift, _tuner_reg, _pcw_reg, _pcw_shift, \
+ NULL)
+
+static const struct mtk_pll_data plls[] = {
+ PLL(CLK_APMIXED_MAINPLL, "mainpll", 0x0220, 0x022C, 0xF0000101, PLL_AO,
+ 21, 0x220, 4, 0x0, 0x224, 0),
+ PLL(CLK_APMIXED_UNIVPLL, "univpll", 0x0230, 0x023C, 0xFE000011, 0, 7,
+ 0x230, 4, 0x0, 0x234, 14),
+ PLL(CLK_APMIXED_MFGPLL, "mfgpll", 0x0240, 0x024C, 0x00000101, 0, 21,
+ 0x244, 24, 0x0, 0x244, 0),
+ PLL(CLK_APMIXED_MSDCPLL, "msdcpll", 0x0250, 0x025C, 0x00000121, 0, 21,
+ 0x250, 4, 0x0, 0x254, 0),
+ PLL(CLK_APMIXED_IMGPLL, "imgpll", 0x0260, 0x026C, 0x00000121, 0, 21,
+ 0x260, 4, 0x0, 0x264, 0),
+ PLL(CLK_APMIXED_TVDPLL, "tvdpll", 0x0270, 0x027C, 0xC0000121, 0, 21,
+ 0x270, 4, 0x0, 0x274, 0),
+ PLL(CLK_APMIXED_CODECPLL, "codecpll", 0x0290, 0x029C, 0x00000121, 0, 21,
+ 0x290, 4, 0x0, 0x294, 0),
+ PLL(CLK_APMIXED_VDECPLL, "vdecpll", 0x02E4, 0x02F0, 0x00000121, 0, 21,
+ 0x2E4, 4, 0x0, 0x2E8, 0),
+ PLL(CLK_APMIXED_APLL1, "apll1", 0x02A0, 0x02B0, 0x00000131, 0, 31,
+ 0x2A0, 4, 0x2A8, 0x2A4, 0),
+ PLL(CLK_APMIXED_APLL2, "apll2", 0x02B4, 0x02C4, 0x00000131, 0, 31,
+ 0x2B4, 4, 0x2BC, 0x2B8, 0),
+};
+
+static int mtk_apmixedsys_init(struct platform_device *pdev)
+{
+ struct clk_onecell_data *clk_data;
+ struct device_node *node = pdev->dev.of_node;
+
+ clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR);
+ if (!clk_data)
+ return -ENOMEM;
+
+ mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data);
+
+ return of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
+}
+
+static const struct of_device_id of_match_clk_mt6797[] = {
+ {
+ .compatible = "mediatek,mt6797-topckgen",
+ .data = mtk_topckgen_init,
+ }, {
+ .compatible = "mediatek,mt6797-infracfg",
+ .data = mtk_infrasys_init,
+ }, {
+ .compatible = "mediatek,mt6797-apmixedsys",
+ .data = mtk_apmixedsys_init,
+ }, {
+ /* sentinel */
+ }
+};
+
+static int clk_mt6797_probe(struct platform_device *pdev)
+{
+ int (*clk_init)(struct platform_device *);
+ int r;
+
+ clk_init = of_device_get_match_data(&pdev->dev);
+ if (!clk_init)
+ return -EINVAL;
+
+ r = clk_init(pdev);
+ if (r)
+ dev_err(&pdev->dev,
+ "could not register clock provider: %s: %d\n",
+ pdev->name, r);
+
+ return r;
+}
+
+static struct platform_driver clk_mt6797_drv = {
+ .probe = clk_mt6797_probe,
+ .driver = {
+ .name = "clk-mt6797",
+ .of_match_table = of_match_clk_mt6797,
+ },
+};
+
+static int __init clk_mt6797_init(void)
+{
+ return platform_driver_register(&clk_mt6797_drv);
+}
+
+arch_initcall(clk_mt6797_init);
# Makefile for Meson specific clk
#
-obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-cpu.o clk-mpll.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-cpu.o clk-mpll.o clk-audio-divider.o
obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
obj-$(CONFIG_COMMON_CLK_GXBB) += gxbb.o gxbb-aoclk.o
--- /dev/null
+/*
+ * Copyright (c) 2017 AmLogic, Inc.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * i2s master clock divider: The algorithm of the generic clk-divider used with
+ * a very precise clock parent such as the mpll tends to select a low divider
+ * factor. This gives poor results with this particular divider, especially with
+ * high frequencies (> 100 MHz)
+ *
+ * This driver try to select the maximum possible divider with the rate the
+ * upstream clock can provide.
+ */
+
+#include <linux/clk-provider.h>
+#include "clkc.h"
+
+#define to_meson_clk_audio_divider(_hw) container_of(_hw, \
+ struct meson_clk_audio_divider, hw)
+
+static int _div_round(unsigned long parent_rate, unsigned long rate,
+ unsigned long flags)
+{
+ if (flags & CLK_DIVIDER_ROUND_CLOSEST)
+ return DIV_ROUND_CLOSEST_ULL((u64)parent_rate, rate);
+
+ return DIV_ROUND_UP_ULL((u64)parent_rate, rate);
+}
+
+static int _get_val(unsigned long parent_rate, unsigned long rate)
+{
+ return DIV_ROUND_UP_ULL((u64)parent_rate, rate) - 1;
+}
+
+static int _valid_divider(struct clk_hw *hw, int divider)
+{
+ struct meson_clk_audio_divider *adiv =
+ to_meson_clk_audio_divider(hw);
+ int max_divider;
+ u8 width;
+
+ width = adiv->div.width;
+ max_divider = 1 << width;
+
+ return clamp(divider, 1, max_divider);
+}
+
+static unsigned long audio_divider_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ struct meson_clk_audio_divider *adiv =
+ to_meson_clk_audio_divider(hw);
+ struct parm *p;
+ unsigned long reg, divider;
+
+ p = &adiv->div;
+ reg = readl(adiv->base + p->reg_off);
+ divider = PARM_GET(p->width, p->shift, reg) + 1;
+
+ return DIV_ROUND_UP_ULL((u64)parent_rate, divider);
+}
+
+static long audio_divider_round_rate(struct clk_hw *hw,
+ unsigned long rate,
+ unsigned long *parent_rate)
+{
+ struct meson_clk_audio_divider *adiv =
+ to_meson_clk_audio_divider(hw);
+ unsigned long max_prate;
+ int divider;
+
+ if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
+ divider = _div_round(*parent_rate, rate, adiv->flags);
+ divider = _valid_divider(hw, divider);
+ return DIV_ROUND_UP_ULL((u64)*parent_rate, divider);
+ }
+
+ /* Get the maximum parent rate */
+ max_prate = clk_hw_round_rate(clk_hw_get_parent(hw), ULONG_MAX);
+
+ /* Get the corresponding rounded down divider */
+ divider = max_prate / rate;
+ divider = _valid_divider(hw, divider);
+
+ /* Get actual rate of the parent */
+ *parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw),
+ divider * rate);
+
+ return DIV_ROUND_UP_ULL((u64)*parent_rate, divider);
+}
+
+static int audio_divider_set_rate(struct clk_hw *hw,
+ unsigned long rate,
+ unsigned long parent_rate)
+{
+ struct meson_clk_audio_divider *adiv =
+ to_meson_clk_audio_divider(hw);
+ struct parm *p;
+ unsigned long reg, flags = 0;
+ int val;
+
+ val = _get_val(parent_rate, rate);
+
+ if (adiv->lock)
+ spin_lock_irqsave(adiv->lock, flags);
+ else
+ __acquire(adiv->lock);
+
+ p = &adiv->div;
+ reg = readl(adiv->base + p->reg_off);
+ reg = PARM_SET(p->width, p->shift, reg, val);
+ writel(reg, adiv->base + p->reg_off);
+
+ if (adiv->lock)
+ spin_unlock_irqrestore(adiv->lock, flags);
+ else
+ __release(adiv->lock);
+
+ return 0;
+}
+
+const struct clk_ops meson_clk_audio_divider_ro_ops = {
+ .recalc_rate = audio_divider_recalc_rate,
+ .round_rate = audio_divider_round_rate,
+};
+
+const struct clk_ops meson_clk_audio_divider_ops = {
+ .recalc_rate = audio_divider_recalc_rate,
+ .round_rate = audio_divider_round_rate,
+ .set_rate = audio_divider_set_rate,
+};
#include <linux/clk-provider.h>
#include "clkc.h"
-#define SDM_MAX 16384
+#define SDM_DEN 16384
+#define N2_MIN 4
+#define N2_MAX 511
#define to_meson_clk_mpll(_hw) container_of(_hw, struct meson_clk_mpll, hw)
+static long rate_from_params(unsigned long parent_rate,
+ unsigned long sdm,
+ unsigned long n2)
+{
+ unsigned long divisor = (SDM_DEN * n2) + sdm;
+
+ if (n2 < N2_MIN)
+ return -EINVAL;
+
+ return DIV_ROUND_UP_ULL((u64)parent_rate * SDM_DEN, divisor);
+}
+
+static void params_from_rate(unsigned long requested_rate,
+ unsigned long parent_rate,
+ unsigned long *sdm,
+ unsigned long *n2)
+{
+ uint64_t div = parent_rate;
+ unsigned long rem = do_div(div, requested_rate);
+
+ if (div < N2_MIN) {
+ *n2 = N2_MIN;
+ *sdm = 0;
+ } else if (div > N2_MAX) {
+ *n2 = N2_MAX;
+ *sdm = SDM_DEN - 1;
+ } else {
+ *n2 = div;
+ *sdm = DIV_ROUND_UP(rem * SDM_DEN, requested_rate);
+ }
+}
+
static unsigned long mpll_recalc_rate(struct clk_hw *hw,
unsigned long parent_rate)
{
struct meson_clk_mpll *mpll = to_meson_clk_mpll(hw);
struct parm *p;
- unsigned long rate = 0;
unsigned long reg, sdm, n2;
+ long rate;
p = &mpll->sdm;
reg = readl(mpll->base + p->reg_off);
reg = readl(mpll->base + p->reg_off);
n2 = PARM_GET(p->width, p->shift, reg);
- rate = (parent_rate * SDM_MAX) / ((SDM_MAX * n2) + sdm);
+ rate = rate_from_params(parent_rate, sdm, n2);
+ if (rate < 0)
+ return 0;
return rate;
}
+static long mpll_round_rate(struct clk_hw *hw,
+ unsigned long rate,
+ unsigned long *parent_rate)
+{
+ unsigned long sdm, n2;
+
+ params_from_rate(rate, *parent_rate, &sdm, &n2);
+ return rate_from_params(*parent_rate, sdm, n2);
+}
+
+static int mpll_set_rate(struct clk_hw *hw,
+ unsigned long rate,
+ unsigned long parent_rate)
+{
+ struct meson_clk_mpll *mpll = to_meson_clk_mpll(hw);
+ struct parm *p;
+ unsigned long reg, sdm, n2;
+ unsigned long flags = 0;
+
+ params_from_rate(rate, parent_rate, &sdm, &n2);
+
+ if (mpll->lock)
+ spin_lock_irqsave(mpll->lock, flags);
+ else
+ __acquire(mpll->lock);
+
+ p = &mpll->sdm;
+ reg = readl(mpll->base + p->reg_off);
+ reg = PARM_SET(p->width, p->shift, reg, sdm);
+ writel(reg, mpll->base + p->reg_off);
+
+ p = &mpll->sdm_en;
+ reg = readl(mpll->base + p->reg_off);
+ reg = PARM_SET(p->width, p->shift, reg, 1);
+ writel(reg, mpll->base + p->reg_off);
+
+ p = &mpll->n2;
+ reg = readl(mpll->base + p->reg_off);
+ reg = PARM_SET(p->width, p->shift, reg, n2);
+ writel(reg, mpll->base + p->reg_off);
+
+ if (mpll->lock)
+ spin_unlock_irqrestore(mpll->lock, flags);
+ else
+ __release(mpll->lock);
+
+ return 0;
+}
+
+static void mpll_enable_core(struct clk_hw *hw, int enable)
+{
+ struct meson_clk_mpll *mpll = to_meson_clk_mpll(hw);
+ struct parm *p;
+ unsigned long reg;
+ unsigned long flags = 0;
+
+ if (mpll->lock)
+ spin_lock_irqsave(mpll->lock, flags);
+ else
+ __acquire(mpll->lock);
+
+ p = &mpll->en;
+ reg = readl(mpll->base + p->reg_off);
+ reg = PARM_SET(p->width, p->shift, reg, enable ? 1 : 0);
+ writel(reg, mpll->base + p->reg_off);
+
+ if (mpll->lock)
+ spin_unlock_irqrestore(mpll->lock, flags);
+ else
+ __release(mpll->lock);
+}
+
+
+static int mpll_enable(struct clk_hw *hw)
+{
+ mpll_enable_core(hw, 1);
+
+ return 0;
+}
+
+static void mpll_disable(struct clk_hw *hw)
+{
+ mpll_enable_core(hw, 0);
+}
+
+static int mpll_is_enabled(struct clk_hw *hw)
+{
+ struct meson_clk_mpll *mpll = to_meson_clk_mpll(hw);
+ struct parm *p;
+ unsigned long reg;
+ int en;
+
+ p = &mpll->en;
+ reg = readl(mpll->base + p->reg_off);
+ en = PARM_GET(p->width, p->shift, reg);
+
+ return en;
+}
+
const struct clk_ops meson_clk_mpll_ro_ops = {
- .recalc_rate = mpll_recalc_rate,
+ .recalc_rate = mpll_recalc_rate,
+ .round_rate = mpll_round_rate,
+ .is_enabled = mpll_is_enabled,
+};
+
+const struct clk_ops meson_clk_mpll_ops = {
+ .recalc_rate = mpll_recalc_rate,
+ .round_rate = mpll_round_rate,
+ .set_rate = mpll_set_rate,
+ .enable = mpll_enable,
+ .disable = mpll_disable,
+ .is_enabled = mpll_is_enabled,
};
return NULL;
}
+/* Specific wait loop for GXL/GXM GP0 PLL */
+static int meson_clk_pll_wait_lock_reset(struct meson_clk_pll *pll,
+ struct parm *p_n)
+{
+ int delay = 100;
+ u32 reg;
+
+ while (delay > 0) {
+ reg = readl(pll->base + p_n->reg_off);
+ writel(reg | MESON_PLL_RESET, pll->base + p_n->reg_off);
+ udelay(10);
+ writel(reg & ~MESON_PLL_RESET, pll->base + p_n->reg_off);
+
+ /* This delay comes from AMLogic tree clk-gp0-gxl driver */
+ mdelay(1);
+
+ reg = readl(pll->base + p_n->reg_off);
+ if (reg & MESON_PLL_LOCK)
+ return 0;
+ delay--;
+ }
+ return -ETIMEDOUT;
+}
+
static int meson_clk_pll_wait_lock(struct meson_clk_pll *pll,
struct parm *p_n)
{
return -ETIMEDOUT;
}
+static void meson_clk_pll_init_params(struct meson_clk_pll *pll)
+{
+ int i;
+
+ for (i = 0 ; i < pll->params.params_count ; ++i)
+ writel(pll->params.params_table[i].value,
+ pll->base + pll->params.params_table[i].reg_off);
+}
+
static int meson_clk_pll_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
if (!rate_set)
return -EINVAL;
+ /* Initialize the PLL in a clean state if specified */
+ if (pll->params.params_count)
+ meson_clk_pll_init_params(pll);
+
/* PLL reset */
p = &pll->n;
reg = readl(pll->base + p->reg_off);
- writel(reg | MESON_PLL_RESET, pll->base + p->reg_off);
+ /* If no_init_reset is provided, avoid resetting at this point */
+ if (!pll->params.no_init_reset)
+ writel(reg | MESON_PLL_RESET, pll->base + p->reg_off);
reg = PARM_SET(p->width, p->shift, reg, rate_set->n);
writel(reg, pll->base + p->reg_off);
}
p = &pll->n;
- ret = meson_clk_pll_wait_lock(pll, p);
+ /* If clear_reset_for_lock is provided, remove the reset bit here */
+ if (pll->params.clear_reset_for_lock) {
+ reg = readl(pll->base + p->reg_off);
+ writel(reg & ~MESON_PLL_RESET, pll->base + p->reg_off);
+ }
+
+ /* If reset_lock_loop, use a special loop including resetting */
+ if (pll->params.reset_lock_loop)
+ ret = meson_clk_pll_wait_lock_reset(pll, p);
+ else
+ ret = meson_clk_pll_wait_lock(pll, p);
if (ret) {
pr_warn("%s: pll did not lock, trying to restore old rate %lu\n",
__func__, old_rate);
#define PARM_GET(width, shift, reg) \
(((reg) & SETPMASK(width, shift)) >> (shift))
#define PARM_SET(width, shift, reg, val) \
- (((reg) & CLRPMASK(width, shift)) | (val << (shift)))
+ (((reg) & CLRPMASK(width, shift)) | ((val) << (shift)))
#define MESON_PARM_APPLICABLE(p) (!!((p)->width))
.frac = (_frac), \
} \
+struct pll_params_table {
+ unsigned int reg_off;
+ unsigned int value;
+};
+
+#define PLL_PARAM(_reg, _val) \
+ { \
+ .reg_off = (_reg), \
+ .value = (_val), \
+ }
+
+struct pll_setup_params {
+ struct pll_params_table *params_table;
+ unsigned int params_count;
+ /* Workaround for GP0, do not reset before configuring */
+ bool no_init_reset;
+ /* Workaround for GP0, unreset right before checking for lock */
+ bool clear_reset_for_lock;
+ /* Workaround for GXL GP0, reset in the lock checking loop */
+ bool reset_lock_loop;
+};
+
struct meson_clk_pll {
struct clk_hw hw;
void __iomem *base;
struct parm frac;
struct parm od;
struct parm od2;
+ const struct pll_setup_params params;
const struct pll_rate_table *rate_table;
unsigned int rate_count;
spinlock_t *lock;
struct clk_hw hw;
void __iomem *base;
struct parm sdm;
+ struct parm sdm_en;
struct parm n2;
- /* FIXME ssen gate control? */
+ struct parm en;
+ spinlock_t *lock;
+};
+
+struct meson_clk_audio_divider {
+ struct clk_hw hw;
+ void __iomem *base;
+ struct parm div;
+ u8 flags;
spinlock_t *lock;
};
extern const struct clk_ops meson_clk_pll_ops;
extern const struct clk_ops meson_clk_cpu_ops;
extern const struct clk_ops meson_clk_mpll_ro_ops;
+extern const struct clk_ops meson_clk_mpll_ops;
+extern const struct clk_ops meson_clk_audio_divider_ro_ops;
+extern const struct clk_ops meson_clk_audio_divider_ops;
#endif /* __CLKC_H */
#include <linux/clk.h>
#include <linux/clk-provider.h>
#include <linux/of_address.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/init.h>
{ /* sentinel */ },
};
-static const struct pll_rate_table gp0_pll_rate_table[] = {
+static const struct pll_rate_table gxbb_gp0_pll_rate_table[] = {
PLL_RATE(96000000, 32, 1, 3),
PLL_RATE(99000000, 33, 1, 3),
PLL_RATE(102000000, 34, 1, 3),
{ /* sentinel */ },
};
+static const struct pll_rate_table gxl_gp0_pll_rate_table[] = {
+ PLL_RATE(504000000, 42, 1, 1),
+ PLL_RATE(516000000, 43, 1, 1),
+ PLL_RATE(528000000, 44, 1, 1),
+ PLL_RATE(540000000, 45, 1, 1),
+ PLL_RATE(552000000, 46, 1, 1),
+ PLL_RATE(564000000, 47, 1, 1),
+ PLL_RATE(576000000, 48, 1, 1),
+ PLL_RATE(588000000, 49, 1, 1),
+ PLL_RATE(600000000, 50, 1, 1),
+ PLL_RATE(612000000, 51, 1, 1),
+ PLL_RATE(624000000, 52, 1, 1),
+ PLL_RATE(636000000, 53, 1, 1),
+ PLL_RATE(648000000, 54, 1, 1),
+ PLL_RATE(660000000, 55, 1, 1),
+ PLL_RATE(672000000, 56, 1, 1),
+ PLL_RATE(684000000, 57, 1, 1),
+ PLL_RATE(696000000, 58, 1, 1),
+ PLL_RATE(708000000, 59, 1, 1),
+ PLL_RATE(720000000, 60, 1, 1),
+ PLL_RATE(732000000, 61, 1, 1),
+ PLL_RATE(744000000, 62, 1, 1),
+ PLL_RATE(756000000, 63, 1, 1),
+ PLL_RATE(768000000, 64, 1, 1),
+ PLL_RATE(780000000, 65, 1, 1),
+ PLL_RATE(792000000, 66, 1, 1),
+ { /* sentinel */ },
+};
+
static const struct clk_div_table cpu_div_table[] = {
{ .val = 1, .div = 1 },
{ .val = 2, .div = 2 },
},
};
+struct pll_params_table gxbb_gp0_params_table[] = {
+ PLL_PARAM(HHI_GP0_PLL_CNTL, 0x6a000228),
+ PLL_PARAM(HHI_GP0_PLL_CNTL2, 0x69c80000),
+ PLL_PARAM(HHI_GP0_PLL_CNTL3, 0x0a5590c4),
+ PLL_PARAM(HHI_GP0_PLL_CNTL4, 0x0000500d),
+};
+
static struct meson_clk_pll gxbb_gp0_pll = {
.m = {
.reg_off = HHI_GP0_PLL_CNTL,
.shift = 16,
.width = 2,
},
- .rate_table = gp0_pll_rate_table,
- .rate_count = ARRAY_SIZE(gp0_pll_rate_table),
+ .params = {
+ .params_table = gxbb_gp0_params_table,
+ .params_count = ARRAY_SIZE(gxbb_gp0_params_table),
+ .no_init_reset = true,
+ .clear_reset_for_lock = true,
+ },
+ .rate_table = gxbb_gp0_pll_rate_table,
+ .rate_count = ARRAY_SIZE(gxbb_gp0_pll_rate_table),
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "gp0_pll",
+ .ops = &meson_clk_pll_ops,
+ .parent_names = (const char *[]){ "xtal" },
+ .num_parents = 1,
+ .flags = CLK_GET_RATE_NOCACHE,
+ },
+};
+
+struct pll_params_table gxl_gp0_params_table[] = {
+ PLL_PARAM(HHI_GP0_PLL_CNTL, 0x40010250),
+ PLL_PARAM(HHI_GP0_PLL_CNTL1, 0xc084a000),
+ PLL_PARAM(HHI_GP0_PLL_CNTL2, 0xb75020be),
+ PLL_PARAM(HHI_GP0_PLL_CNTL3, 0x0a59a288),
+ PLL_PARAM(HHI_GP0_PLL_CNTL4, 0xc000004d),
+ PLL_PARAM(HHI_GP0_PLL_CNTL5, 0x00078000),
+};
+
+static struct meson_clk_pll gxl_gp0_pll = {
+ .m = {
+ .reg_off = HHI_GP0_PLL_CNTL,
+ .shift = 0,
+ .width = 9,
+ },
+ .n = {
+ .reg_off = HHI_GP0_PLL_CNTL,
+ .shift = 9,
+ .width = 5,
+ },
+ .od = {
+ .reg_off = HHI_GP0_PLL_CNTL,
+ .shift = 16,
+ .width = 2,
+ },
+ .params = {
+ .params_table = gxl_gp0_params_table,
+ .params_count = ARRAY_SIZE(gxl_gp0_params_table),
+ .no_init_reset = true,
+ .reset_lock_loop = true,
+ },
+ .rate_table = gxl_gp0_pll_rate_table,
+ .rate_count = ARRAY_SIZE(gxl_gp0_pll_rate_table),
.lock = &clk_lock,
.hw.init = &(struct clk_init_data){
.name = "gp0_pll",
.shift = 0,
.width = 14,
},
+ .sdm_en = {
+ .reg_off = HHI_MPLL_CNTL7,
+ .shift = 15,
+ .width = 1,
+ },
.n2 = {
.reg_off = HHI_MPLL_CNTL7,
.shift = 16,
.width = 9,
},
+ .en = {
+ .reg_off = HHI_MPLL_CNTL7,
+ .shift = 14,
+ .width = 1,
+ },
.lock = &clk_lock,
.hw.init = &(struct clk_init_data){
.name = "mpll0",
- .ops = &meson_clk_mpll_ro_ops,
+ .ops = &meson_clk_mpll_ops,
.parent_names = (const char *[]){ "fixed_pll" },
.num_parents = 1,
},
.shift = 0,
.width = 14,
},
+ .sdm_en = {
+ .reg_off = HHI_MPLL_CNTL8,
+ .shift = 15,
+ .width = 1,
+ },
.n2 = {
.reg_off = HHI_MPLL_CNTL8,
.shift = 16,
.width = 9,
},
+ .en = {
+ .reg_off = HHI_MPLL_CNTL8,
+ .shift = 14,
+ .width = 1,
+ },
.lock = &clk_lock,
.hw.init = &(struct clk_init_data){
.name = "mpll1",
- .ops = &meson_clk_mpll_ro_ops,
+ .ops = &meson_clk_mpll_ops,
.parent_names = (const char *[]){ "fixed_pll" },
.num_parents = 1,
},
.shift = 0,
.width = 14,
},
+ .sdm_en = {
+ .reg_off = HHI_MPLL_CNTL9,
+ .shift = 15,
+ .width = 1,
+ },
.n2 = {
.reg_off = HHI_MPLL_CNTL9,
.shift = 16,
.width = 9,
},
+ .en = {
+ .reg_off = HHI_MPLL_CNTL9,
+ .shift = 14,
+ .width = 1,
+ },
.lock = &clk_lock,
.hw.init = &(struct clk_init_data){
.name = "mpll2",
- .ops = &meson_clk_mpll_ro_ops,
+ .ops = &meson_clk_mpll_ops,
.parent_names = (const char *[]){ "fixed_pll" },
.num_parents = 1,
},
},
};
+/*
+ * The MALI IP is clocked by two identical clocks (mali_0 and mali_1)
+ * muxed by a glitch-free switch.
+ */
+
+static u32 mux_table_mali_0_1[] = {0, 1, 2, 3, 4, 5, 6, 7};
+static const char *gxbb_mali_0_1_parent_names[] = {
+ "xtal", "gp0_pll", "mpll2", "mpll1", "fclk_div7",
+ "fclk_div4", "fclk_div3", "fclk_div5"
+};
+
+static struct clk_mux gxbb_mali_0_sel = {
+ .reg = (void *)HHI_MALI_CLK_CNTL,
+ .mask = 0x7,
+ .shift = 9,
+ .table = mux_table_mali_0_1,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mali_0_sel",
+ .ops = &clk_mux_ops,
+ /*
+ * bits 10:9 selects from 8 possible parents:
+ * xtal, gp0_pll, mpll2, mpll1, fclk_div7,
+ * fclk_div4, fclk_div3, fclk_div5
+ */
+ .parent_names = gxbb_mali_0_1_parent_names,
+ .num_parents = 8,
+ .flags = CLK_SET_RATE_NO_REPARENT,
+ },
+};
+
+static struct clk_divider gxbb_mali_0_div = {
+ .reg = (void *)HHI_MALI_CLK_CNTL,
+ .shift = 0,
+ .width = 7,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mali_0_div",
+ .ops = &clk_divider_ops,
+ .parent_names = (const char *[]){ "mali_0_sel" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_NO_REPARENT,
+ },
+};
+
+static struct clk_gate gxbb_mali_0 = {
+ .reg = (void *)HHI_MALI_CLK_CNTL,
+ .bit_idx = 8,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mali_0",
+ .ops = &clk_gate_ops,
+ .parent_names = (const char *[]){ "mali_0_div" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_PARENT,
+ },
+};
+
+static struct clk_mux gxbb_mali_1_sel = {
+ .reg = (void *)HHI_MALI_CLK_CNTL,
+ .mask = 0x7,
+ .shift = 25,
+ .table = mux_table_mali_0_1,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mali_1_sel",
+ .ops = &clk_mux_ops,
+ /*
+ * bits 10:9 selects from 8 possible parents:
+ * xtal, gp0_pll, mpll2, mpll1, fclk_div7,
+ * fclk_div4, fclk_div3, fclk_div5
+ */
+ .parent_names = gxbb_mali_0_1_parent_names,
+ .num_parents = 8,
+ .flags = CLK_SET_RATE_NO_REPARENT,
+ },
+};
+
+static struct clk_divider gxbb_mali_1_div = {
+ .reg = (void *)HHI_MALI_CLK_CNTL,
+ .shift = 16,
+ .width = 7,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mali_1_div",
+ .ops = &clk_divider_ops,
+ .parent_names = (const char *[]){ "mali_1_sel" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_NO_REPARENT,
+ },
+};
+
+static struct clk_gate gxbb_mali_1 = {
+ .reg = (void *)HHI_MALI_CLK_CNTL,
+ .bit_idx = 24,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mali_1",
+ .ops = &clk_gate_ops,
+ .parent_names = (const char *[]){ "mali_1_div" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_PARENT,
+ },
+};
+
+static u32 mux_table_mali[] = {0, 1};
+static const char *gxbb_mali_parent_names[] = {
+ "mali_0", "mali_1"
+};
+
+static struct clk_mux gxbb_mali = {
+ .reg = (void *)HHI_MALI_CLK_CNTL,
+ .mask = 1,
+ .shift = 31,
+ .table = mux_table_mali,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mali",
+ .ops = &clk_mux_ops,
+ .parent_names = gxbb_mali_parent_names,
+ .num_parents = 2,
+ .flags = CLK_SET_RATE_NO_REPARENT,
+ },
+};
+
+static struct clk_mux gxbb_cts_amclk_sel = {
+ .reg = (void *) HHI_AUD_CLK_CNTL,
+ .mask = 0x3,
+ .shift = 9,
+ /* Default parent unknown (register reset value: 0) */
+ .table = (u32[]){ 1, 2, 3 },
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "cts_amclk_sel",
+ .ops = &clk_mux_ops,
+ .parent_names = (const char *[]){ "mpll0", "mpll1", "mpll2" },
+ .num_parents = 3,
+ .flags = CLK_SET_RATE_PARENT,
+ },
+};
+
+static struct meson_clk_audio_divider gxbb_cts_amclk_div = {
+ .div = {
+ .reg_off = HHI_AUD_CLK_CNTL,
+ .shift = 0,
+ .width = 8,
+ },
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "cts_amclk_div",
+ .ops = &meson_clk_audio_divider_ops,
+ .parent_names = (const char *[]){ "cts_amclk_sel" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_PARENT | CLK_DIVIDER_ROUND_CLOSEST,
+ },
+};
+
+static struct clk_gate gxbb_cts_amclk = {
+ .reg = (void *) HHI_AUD_CLK_CNTL,
+ .bit_idx = 8,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "cts_amclk",
+ .ops = &clk_gate_ops,
+ .parent_names = (const char *[]){ "cts_amclk_div" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_PARENT,
+ },
+};
+
+static struct clk_mux gxbb_cts_mclk_i958_sel = {
+ .reg = (void *)HHI_AUD_CLK_CNTL2,
+ .mask = 0x3,
+ .shift = 25,
+ /* Default parent unknown (register reset value: 0) */
+ .table = (u32[]){ 1, 2, 3 },
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "cts_mclk_i958_sel",
+ .ops = &clk_mux_ops,
+ .parent_names = (const char *[]){ "mpll0", "mpll1", "mpll2" },
+ .num_parents = 3,
+ .flags = CLK_SET_RATE_PARENT,
+ },
+};
+
+static struct clk_divider gxbb_cts_mclk_i958_div = {
+ .reg = (void *)HHI_AUD_CLK_CNTL2,
+ .shift = 16,
+ .width = 8,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "cts_mclk_i958_div",
+ .ops = &clk_divider_ops,
+ .parent_names = (const char *[]){ "cts_mclk_i958_sel" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_PARENT | CLK_DIVIDER_ROUND_CLOSEST,
+ },
+};
+
+static struct clk_gate gxbb_cts_mclk_i958 = {
+ .reg = (void *)HHI_AUD_CLK_CNTL2,
+ .bit_idx = 24,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "cts_mclk_i958",
+ .ops = &clk_gate_ops,
+ .parent_names = (const char *[]){ "cts_mclk_i958_div" },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_PARENT,
+ },
+};
+
+static struct clk_mux gxbb_cts_i958 = {
+ .reg = (void *)HHI_AUD_CLK_CNTL2,
+ .mask = 0x1,
+ .shift = 27,
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "cts_i958",
+ .ops = &clk_mux_ops,
+ .parent_names = (const char *[]){ "cts_amclk", "cts_mclk_i958" },
+ .num_parents = 2,
+ /*
+ *The parent is specific to origin of the audio data. Let the
+ * consumer choose the appropriate parent
+ */
+ .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+ },
+};
+
/* Everything Else (EE) domain gates */
static MESON_GATE(gxbb_ddr, HHI_GCLK_MPEG0, 0);
static MESON_GATE(gxbb_dos, HHI_GCLK_MPEG0, 1);
[CLKID_SAR_ADC_CLK] = &gxbb_sar_adc_clk.hw,
[CLKID_SAR_ADC_SEL] = &gxbb_sar_adc_clk_sel.hw,
[CLKID_SAR_ADC_DIV] = &gxbb_sar_adc_clk_div.hw,
+ [CLKID_MALI_0_SEL] = &gxbb_mali_0_sel.hw,
+ [CLKID_MALI_0_DIV] = &gxbb_mali_0_div.hw,
+ [CLKID_MALI_0] = &gxbb_mali_0.hw,
+ [CLKID_MALI_1_SEL] = &gxbb_mali_1_sel.hw,
+ [CLKID_MALI_1_DIV] = &gxbb_mali_1_div.hw,
+ [CLKID_MALI_1] = &gxbb_mali_1.hw,
+ [CLKID_MALI] = &gxbb_mali.hw,
+ [CLKID_CTS_AMCLK] = &gxbb_cts_amclk.hw,
+ [CLKID_CTS_AMCLK_SEL] = &gxbb_cts_amclk_sel.hw,
+ [CLKID_CTS_AMCLK_DIV] = &gxbb_cts_amclk_div.hw,
+ [CLKID_CTS_MCLK_I958] = &gxbb_cts_mclk_i958.hw,
+ [CLKID_CTS_MCLK_I958_SEL] = &gxbb_cts_mclk_i958_sel.hw,
+ [CLKID_CTS_MCLK_I958_DIV] = &gxbb_cts_mclk_i958_div.hw,
+ [CLKID_CTS_I958] = &gxbb_cts_i958.hw,
+ },
+ .num = NR_CLKS,
+};
+
+static struct clk_hw_onecell_data gxl_hw_onecell_data = {
+ .hws = {
+ [CLKID_SYS_PLL] = &gxbb_sys_pll.hw,
+ [CLKID_CPUCLK] = &gxbb_cpu_clk.hw,
+ [CLKID_HDMI_PLL] = &gxbb_hdmi_pll.hw,
+ [CLKID_FIXED_PLL] = &gxbb_fixed_pll.hw,
+ [CLKID_FCLK_DIV2] = &gxbb_fclk_div2.hw,
+ [CLKID_FCLK_DIV3] = &gxbb_fclk_div3.hw,
+ [CLKID_FCLK_DIV4] = &gxbb_fclk_div4.hw,
+ [CLKID_FCLK_DIV5] = &gxbb_fclk_div5.hw,
+ [CLKID_FCLK_DIV7] = &gxbb_fclk_div7.hw,
+ [CLKID_GP0_PLL] = &gxl_gp0_pll.hw,
+ [CLKID_MPEG_SEL] = &gxbb_mpeg_clk_sel.hw,
+ [CLKID_MPEG_DIV] = &gxbb_mpeg_clk_div.hw,
+ [CLKID_CLK81] = &gxbb_clk81.hw,
+ [CLKID_MPLL0] = &gxbb_mpll0.hw,
+ [CLKID_MPLL1] = &gxbb_mpll1.hw,
+ [CLKID_MPLL2] = &gxbb_mpll2.hw,
+ [CLKID_DDR] = &gxbb_ddr.hw,
+ [CLKID_DOS] = &gxbb_dos.hw,
+ [CLKID_ISA] = &gxbb_isa.hw,
+ [CLKID_PL301] = &gxbb_pl301.hw,
+ [CLKID_PERIPHS] = &gxbb_periphs.hw,
+ [CLKID_SPICC] = &gxbb_spicc.hw,
+ [CLKID_I2C] = &gxbb_i2c.hw,
+ [CLKID_SAR_ADC] = &gxbb_sar_adc.hw,
+ [CLKID_SMART_CARD] = &gxbb_smart_card.hw,
+ [CLKID_RNG0] = &gxbb_rng0.hw,
+ [CLKID_UART0] = &gxbb_uart0.hw,
+ [CLKID_SDHC] = &gxbb_sdhc.hw,
+ [CLKID_STREAM] = &gxbb_stream.hw,
+ [CLKID_ASYNC_FIFO] = &gxbb_async_fifo.hw,
+ [CLKID_SDIO] = &gxbb_sdio.hw,
+ [CLKID_ABUF] = &gxbb_abuf.hw,
+ [CLKID_HIU_IFACE] = &gxbb_hiu_iface.hw,
+ [CLKID_ASSIST_MISC] = &gxbb_assist_misc.hw,
+ [CLKID_SPI] = &gxbb_spi.hw,
+ [CLKID_I2S_SPDIF] = &gxbb_i2s_spdif.hw,
+ [CLKID_ETH] = &gxbb_eth.hw,
+ [CLKID_DEMUX] = &gxbb_demux.hw,
+ [CLKID_AIU_GLUE] = &gxbb_aiu_glue.hw,
+ [CLKID_IEC958] = &gxbb_iec958.hw,
+ [CLKID_I2S_OUT] = &gxbb_i2s_out.hw,
+ [CLKID_AMCLK] = &gxbb_amclk.hw,
+ [CLKID_AIFIFO2] = &gxbb_aififo2.hw,
+ [CLKID_MIXER] = &gxbb_mixer.hw,
+ [CLKID_MIXER_IFACE] = &gxbb_mixer_iface.hw,
+ [CLKID_ADC] = &gxbb_adc.hw,
+ [CLKID_BLKMV] = &gxbb_blkmv.hw,
+ [CLKID_AIU] = &gxbb_aiu.hw,
+ [CLKID_UART1] = &gxbb_uart1.hw,
+ [CLKID_G2D] = &gxbb_g2d.hw,
+ [CLKID_USB0] = &gxbb_usb0.hw,
+ [CLKID_USB1] = &gxbb_usb1.hw,
+ [CLKID_RESET] = &gxbb_reset.hw,
+ [CLKID_NAND] = &gxbb_nand.hw,
+ [CLKID_DOS_PARSER] = &gxbb_dos_parser.hw,
+ [CLKID_USB] = &gxbb_usb.hw,
+ [CLKID_VDIN1] = &gxbb_vdin1.hw,
+ [CLKID_AHB_ARB0] = &gxbb_ahb_arb0.hw,
+ [CLKID_EFUSE] = &gxbb_efuse.hw,
+ [CLKID_BOOT_ROM] = &gxbb_boot_rom.hw,
+ [CLKID_AHB_DATA_BUS] = &gxbb_ahb_data_bus.hw,
+ [CLKID_AHB_CTRL_BUS] = &gxbb_ahb_ctrl_bus.hw,
+ [CLKID_HDMI_INTR_SYNC] = &gxbb_hdmi_intr_sync.hw,
+ [CLKID_HDMI_PCLK] = &gxbb_hdmi_pclk.hw,
+ [CLKID_USB1_DDR_BRIDGE] = &gxbb_usb1_ddr_bridge.hw,
+ [CLKID_USB0_DDR_BRIDGE] = &gxbb_usb0_ddr_bridge.hw,
+ [CLKID_MMC_PCLK] = &gxbb_mmc_pclk.hw,
+ [CLKID_DVIN] = &gxbb_dvin.hw,
+ [CLKID_UART2] = &gxbb_uart2.hw,
+ [CLKID_SANA] = &gxbb_sana.hw,
+ [CLKID_VPU_INTR] = &gxbb_vpu_intr.hw,
+ [CLKID_SEC_AHB_AHB3_BRIDGE] = &gxbb_sec_ahb_ahb3_bridge.hw,
+ [CLKID_CLK81_A53] = &gxbb_clk81_a53.hw,
+ [CLKID_VCLK2_VENCI0] = &gxbb_vclk2_venci0.hw,
+ [CLKID_VCLK2_VENCI1] = &gxbb_vclk2_venci1.hw,
+ [CLKID_VCLK2_VENCP0] = &gxbb_vclk2_vencp0.hw,
+ [CLKID_VCLK2_VENCP1] = &gxbb_vclk2_vencp1.hw,
+ [CLKID_GCLK_VENCI_INT0] = &gxbb_gclk_venci_int0.hw,
+ [CLKID_GCLK_VENCI_INT] = &gxbb_gclk_vencp_int.hw,
+ [CLKID_DAC_CLK] = &gxbb_dac_clk.hw,
+ [CLKID_AOCLK_GATE] = &gxbb_aoclk_gate.hw,
+ [CLKID_IEC958_GATE] = &gxbb_iec958_gate.hw,
+ [CLKID_ENC480P] = &gxbb_enc480p.hw,
+ [CLKID_RNG1] = &gxbb_rng1.hw,
+ [CLKID_GCLK_VENCI_INT1] = &gxbb_gclk_venci_int1.hw,
+ [CLKID_VCLK2_VENCLMCC] = &gxbb_vclk2_venclmcc.hw,
+ [CLKID_VCLK2_VENCL] = &gxbb_vclk2_vencl.hw,
+ [CLKID_VCLK_OTHER] = &gxbb_vclk_other.hw,
+ [CLKID_EDP] = &gxbb_edp.hw,
+ [CLKID_AO_MEDIA_CPU] = &gxbb_ao_media_cpu.hw,
+ [CLKID_AO_AHB_SRAM] = &gxbb_ao_ahb_sram.hw,
+ [CLKID_AO_AHB_BUS] = &gxbb_ao_ahb_bus.hw,
+ [CLKID_AO_IFACE] = &gxbb_ao_iface.hw,
+ [CLKID_AO_I2C] = &gxbb_ao_i2c.hw,
+ [CLKID_SD_EMMC_A] = &gxbb_emmc_a.hw,
+ [CLKID_SD_EMMC_B] = &gxbb_emmc_b.hw,
+ [CLKID_SD_EMMC_C] = &gxbb_emmc_c.hw,
+ [CLKID_SAR_ADC_CLK] = &gxbb_sar_adc_clk.hw,
+ [CLKID_SAR_ADC_SEL] = &gxbb_sar_adc_clk_sel.hw,
+ [CLKID_SAR_ADC_DIV] = &gxbb_sar_adc_clk_div.hw,
+ [CLKID_MALI_0_SEL] = &gxbb_mali_0_sel.hw,
+ [CLKID_MALI_0_DIV] = &gxbb_mali_0_div.hw,
+ [CLKID_MALI_0] = &gxbb_mali_0.hw,
+ [CLKID_MALI_1_SEL] = &gxbb_mali_1_sel.hw,
+ [CLKID_MALI_1_DIV] = &gxbb_mali_1_div.hw,
+ [CLKID_MALI_1] = &gxbb_mali_1.hw,
+ [CLKID_MALI] = &gxbb_mali.hw,
+ [CLKID_CTS_AMCLK] = &gxbb_cts_amclk.hw,
+ [CLKID_CTS_AMCLK_SEL] = &gxbb_cts_amclk_sel.hw,
+ [CLKID_CTS_AMCLK_DIV] = &gxbb_cts_amclk_div.hw,
+ [CLKID_CTS_MCLK_I958] = &gxbb_cts_mclk_i958.hw,
+ [CLKID_CTS_MCLK_I958_SEL] = &gxbb_cts_mclk_i958_sel.hw,
+ [CLKID_CTS_MCLK_I958_DIV] = &gxbb_cts_mclk_i958_div.hw,
+ [CLKID_CTS_I958] = &gxbb_cts_i958.hw,
},
.num = NR_CLKS,
};
&gxbb_gp0_pll,
};
+static struct meson_clk_pll *const gxl_clk_plls[] = {
+ &gxbb_fixed_pll,
+ &gxbb_hdmi_pll,
+ &gxbb_sys_pll,
+ &gxl_gp0_pll,
+};
+
static struct meson_clk_mpll *const gxbb_clk_mplls[] = {
&gxbb_mpll0,
&gxbb_mpll1,
&gxbb_mpll2,
};
-static struct clk_gate *gxbb_clk_gates[] = {
+static struct clk_gate *const gxbb_clk_gates[] = {
&gxbb_clk81,
&gxbb_ddr,
&gxbb_dos,
&gxbb_emmc_b,
&gxbb_emmc_c,
&gxbb_sar_adc_clk,
+ &gxbb_mali_0,
+ &gxbb_mali_1,
+ &gxbb_cts_amclk,
+ &gxbb_cts_mclk_i958,
+};
+
+static struct clk_mux *const gxbb_clk_muxes[] = {
+ &gxbb_mpeg_clk_sel,
+ &gxbb_sar_adc_clk_sel,
+ &gxbb_mali_0_sel,
+ &gxbb_mali_1_sel,
+ &gxbb_mali,
+ &gxbb_cts_amclk_sel,
+ &gxbb_cts_mclk_i958_sel,
+ &gxbb_cts_i958,
+};
+
+static struct clk_divider *const gxbb_clk_dividers[] = {
+ &gxbb_mpeg_clk_div,
+ &gxbb_sar_adc_clk_div,
+ &gxbb_mali_0_div,
+ &gxbb_mali_1_div,
+ &gxbb_cts_mclk_i958_div,
+};
+
+static struct meson_clk_audio_divider *const gxbb_audio_dividers[] = {
+ &gxbb_cts_amclk_div,
+};
+
+struct clkc_data {
+ struct clk_gate *const *clk_gates;
+ unsigned int clk_gates_count;
+ struct meson_clk_mpll *const *clk_mplls;
+ unsigned int clk_mplls_count;
+ struct meson_clk_pll *const *clk_plls;
+ unsigned int clk_plls_count;
+ struct clk_mux *const *clk_muxes;
+ unsigned int clk_muxes_count;
+ struct clk_divider *const *clk_dividers;
+ unsigned int clk_dividers_count;
+ struct meson_clk_audio_divider *const *clk_audio_dividers;
+ unsigned int clk_audio_dividers_count;
+ struct meson_clk_cpu *cpu_clk;
+ struct clk_hw_onecell_data *hw_onecell_data;
+};
+
+static const struct clkc_data gxbb_clkc_data = {
+ .clk_gates = gxbb_clk_gates,
+ .clk_gates_count = ARRAY_SIZE(gxbb_clk_gates),
+ .clk_mplls = gxbb_clk_mplls,
+ .clk_mplls_count = ARRAY_SIZE(gxbb_clk_mplls),
+ .clk_plls = gxbb_clk_plls,
+ .clk_plls_count = ARRAY_SIZE(gxbb_clk_plls),
+ .clk_muxes = gxbb_clk_muxes,
+ .clk_muxes_count = ARRAY_SIZE(gxbb_clk_muxes),
+ .clk_dividers = gxbb_clk_dividers,
+ .clk_dividers_count = ARRAY_SIZE(gxbb_clk_dividers),
+ .clk_audio_dividers = gxbb_audio_dividers,
+ .clk_audio_dividers_count = ARRAY_SIZE(gxbb_audio_dividers),
+ .cpu_clk = &gxbb_cpu_clk,
+ .hw_onecell_data = &gxbb_hw_onecell_data,
+};
+
+static const struct clkc_data gxl_clkc_data = {
+ .clk_gates = gxbb_clk_gates,
+ .clk_gates_count = ARRAY_SIZE(gxbb_clk_gates),
+ .clk_mplls = gxbb_clk_mplls,
+ .clk_mplls_count = ARRAY_SIZE(gxbb_clk_mplls),
+ .clk_plls = gxl_clk_plls,
+ .clk_plls_count = ARRAY_SIZE(gxl_clk_plls),
+ .clk_muxes = gxbb_clk_muxes,
+ .clk_muxes_count = ARRAY_SIZE(gxbb_clk_muxes),
+ .clk_dividers = gxbb_clk_dividers,
+ .clk_dividers_count = ARRAY_SIZE(gxbb_clk_dividers),
+ .clk_audio_dividers = gxbb_audio_dividers,
+ .clk_audio_dividers_count = ARRAY_SIZE(gxbb_audio_dividers),
+ .cpu_clk = &gxbb_cpu_clk,
+ .hw_onecell_data = &gxl_hw_onecell_data,
+};
+
+static const struct of_device_id clkc_match_table[] = {
+ { .compatible = "amlogic,gxbb-clkc", .data = &gxbb_clkc_data },
+ { .compatible = "amlogic,gxl-clkc", .data = &gxl_clkc_data },
+ {},
};
static int gxbb_clkc_probe(struct platform_device *pdev)
{
+ const struct clkc_data *clkc_data;
void __iomem *clk_base;
int ret, clkid, i;
struct clk_hw *parent_hw;
struct clk *parent_clk;
struct device *dev = &pdev->dev;
+ clkc_data = of_device_get_match_data(&pdev->dev);
+ if (!clkc_data)
+ return -EINVAL;
+
/* Generic clocks and PLLs */
clk_base = of_iomap(dev->of_node, 0);
if (!clk_base) {
}
/* Populate base address for PLLs */
- for (i = 0; i < ARRAY_SIZE(gxbb_clk_plls); i++)
- gxbb_clk_plls[i]->base = clk_base;
+ for (i = 0; i < clkc_data->clk_plls_count; i++)
+ clkc_data->clk_plls[i]->base = clk_base;
/* Populate base address for MPLLs */
- for (i = 0; i < ARRAY_SIZE(gxbb_clk_mplls); i++)
- gxbb_clk_mplls[i]->base = clk_base;
+ for (i = 0; i < clkc_data->clk_mplls_count; i++)
+ clkc_data->clk_mplls[i]->base = clk_base;
/* Populate the base address for CPU clk */
- gxbb_cpu_clk.base = clk_base;
+ clkc_data->cpu_clk->base = clk_base;
+
+ /* Populate base address for gates */
+ for (i = 0; i < clkc_data->clk_gates_count; i++)
+ clkc_data->clk_gates[i]->reg = clk_base +
+ (u64)clkc_data->clk_gates[i]->reg;
- /* Populate the base address for the MPEG clks */
- gxbb_mpeg_clk_sel.reg = clk_base + (u64)gxbb_mpeg_clk_sel.reg;
- gxbb_mpeg_clk_div.reg = clk_base + (u64)gxbb_mpeg_clk_div.reg;
+ /* Populate base address for muxes */
+ for (i = 0; i < clkc_data->clk_muxes_count; i++)
+ clkc_data->clk_muxes[i]->reg = clk_base +
+ (u64)clkc_data->clk_muxes[i]->reg;
- /* Populate the base address for the SAR ADC clks */
- gxbb_sar_adc_clk_sel.reg = clk_base + (u64)gxbb_sar_adc_clk_sel.reg;
- gxbb_sar_adc_clk_div.reg = clk_base + (u64)gxbb_sar_adc_clk_div.reg;
+ /* Populate base address for dividers */
+ for (i = 0; i < clkc_data->clk_dividers_count; i++)
+ clkc_data->clk_dividers[i]->reg = clk_base +
+ (u64)clkc_data->clk_dividers[i]->reg;
- /* Populate base address for gates */
- for (i = 0; i < ARRAY_SIZE(gxbb_clk_gates); i++)
- gxbb_clk_gates[i]->reg = clk_base +
- (u64)gxbb_clk_gates[i]->reg;
+ /* Populate base address for the audio dividers */
+ for (i = 0; i < clkc_data->clk_audio_dividers_count; i++)
+ clkc_data->clk_audio_dividers[i]->base = clk_base;
/*
* register all clks
*/
- for (clkid = 0; clkid < NR_CLKS; clkid++) {
- ret = devm_clk_hw_register(dev, gxbb_hw_onecell_data.hws[clkid]);
+ for (clkid = 0; clkid < clkc_data->hw_onecell_data->num; clkid++) {
+ /* array might be sparse */
+ if (!clkc_data->hw_onecell_data->hws[clkid])
+ continue;
+
+ ret = devm_clk_hw_register(dev,
+ clkc_data->hw_onecell_data->hws[clkid]);
if (ret)
goto iounmap;
}
* a new clk_hw, and this hack will no longer work. Releasing the ccr
* feature before that time solves the problem :-)
*/
- parent_hw = clk_hw_get_parent(&gxbb_cpu_clk.hw);
+ parent_hw = clk_hw_get_parent(&clkc_data->cpu_clk->hw);
parent_clk = parent_hw->clk;
- ret = clk_notifier_register(parent_clk, &gxbb_cpu_clk.clk_nb);
+ ret = clk_notifier_register(parent_clk, &clkc_data->cpu_clk->clk_nb);
if (ret) {
pr_err("%s: failed to register clock notifier for cpu_clk\n",
__func__);
}
return of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
- &gxbb_hw_onecell_data);
+ clkc_data->hw_onecell_data);
iounmap:
iounmap(clk_base);
return ret;
}
-static const struct of_device_id gxbb_clkc_match_table[] = {
- { .compatible = "amlogic,gxbb-clkc" },
- { }
-};
-
static struct platform_driver gxbb_driver = {
.probe = gxbb_clkc_probe,
.driver = {
.name = "gxbb-clkc",
- .of_match_table = gxbb_clkc_match_table,
+ .of_match_table = clkc_match_table,
},
};
#define HHI_GP0_PLL_CNTL2 0x44 /* 0x11 offset in data sheet */
#define HHI_GP0_PLL_CNTL3 0x48 /* 0x12 offset in data sheet */
#define HHI_GP0_PLL_CNTL4 0x4c /* 0x13 offset in data sheet */
+#define HHI_GP0_PLL_CNTL5 0x50 /* 0x14 offset in data sheet */
+#define HHI_GP0_PLL_CNTL1 0x58 /* 0x16 offset in data sheet */
#define HHI_XTAL_DIVN_CNTL 0xbc /* 0x2f offset in data sheet */
#define HHI_TIMER90K 0xec /* 0x3b offset in data sheet */
#define CLKID_MALI_1_DIV 104
/* CLKID_MALI_1 */
/* CLKID_MALI */
+#define CLKID_CTS_AMCLK 107
+#define CLKID_CTS_AMCLK_SEL 108
+#define CLKID_CTS_AMCLK_DIV 109
+#define CLKID_CTS_MCLK_I958 110
+#define CLKID_CTS_MCLK_I958_SEL 111
+#define CLKID_CTS_MCLK_I958_DIV 112
+#define CLKID_CTS_I958 113
-#define NR_CLKS 107
+#define NR_CLKS 114
/* include the CLKIDs that have been made part of the stable DT binding */
#include <dt-bindings/clock/gxbb-clkc.h>
},
};
+static struct meson_clk_mpll meson8b_mpll0 = {
+ .sdm = {
+ .reg_off = HHI_MPLL_CNTL7,
+ .shift = 0,
+ .width = 14,
+ },
+ .sdm_en = {
+ .reg_off = HHI_MPLL_CNTL7,
+ .shift = 15,
+ .width = 1,
+ },
+ .n2 = {
+ .reg_off = HHI_MPLL_CNTL7,
+ .shift = 16,
+ .width = 9,
+ },
+ .en = {
+ .reg_off = HHI_MPLL_CNTL7,
+ .shift = 14,
+ .width = 1,
+ },
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mpll0",
+ .ops = &meson_clk_mpll_ops,
+ .parent_names = (const char *[]){ "fixed_pll" },
+ .num_parents = 1,
+ },
+};
+
+static struct meson_clk_mpll meson8b_mpll1 = {
+ .sdm = {
+ .reg_off = HHI_MPLL_CNTL8,
+ .shift = 0,
+ .width = 14,
+ },
+ .sdm_en = {
+ .reg_off = HHI_MPLL_CNTL8,
+ .shift = 15,
+ .width = 1,
+ },
+ .n2 = {
+ .reg_off = HHI_MPLL_CNTL8,
+ .shift = 16,
+ .width = 9,
+ },
+ .en = {
+ .reg_off = HHI_MPLL_CNTL8,
+ .shift = 14,
+ .width = 1,
+ },
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mpll1",
+ .ops = &meson_clk_mpll_ops,
+ .parent_names = (const char *[]){ "fixed_pll" },
+ .num_parents = 1,
+ },
+};
+
+static struct meson_clk_mpll meson8b_mpll2 = {
+ .sdm = {
+ .reg_off = HHI_MPLL_CNTL9,
+ .shift = 0,
+ .width = 14,
+ },
+ .sdm_en = {
+ .reg_off = HHI_MPLL_CNTL9,
+ .shift = 15,
+ .width = 1,
+ },
+ .n2 = {
+ .reg_off = HHI_MPLL_CNTL9,
+ .shift = 16,
+ .width = 9,
+ },
+ .en = {
+ .reg_off = HHI_MPLL_CNTL9,
+ .shift = 14,
+ .width = 1,
+ },
+ .lock = &clk_lock,
+ .hw.init = &(struct clk_init_data){
+ .name = "mpll2",
+ .ops = &meson_clk_mpll_ops,
+ .parent_names = (const char *[]){ "fixed_pll" },
+ .num_parents = 1,
+ },
+};
+
/*
* FIXME cpu clocks and the legacy composite clocks (e.g. clk81) are both PLL
* post-dividers and should be modeled with their respective PLLs via the
[CLKID_AO_AHB_SRAM] = &meson8b_ao_ahb_sram.hw,
[CLKID_AO_AHB_BUS] = &meson8b_ao_ahb_bus.hw,
[CLKID_AO_IFACE] = &meson8b_ao_iface.hw,
+ [CLKID_MPLL0] = &meson8b_mpll0.hw,
+ [CLKID_MPLL1] = &meson8b_mpll1.hw,
+ [CLKID_MPLL2] = &meson8b_mpll2.hw,
},
.num = CLK_NR_CLKS,
};
&meson8b_sys_pll,
};
-static struct clk_gate *meson8b_clk_gates[] = {
+static struct meson_clk_mpll *const meson8b_clk_mplls[] = {
+ &meson8b_mpll0,
+ &meson8b_mpll1,
+ &meson8b_mpll2,
+};
+
+static struct clk_gate *const meson8b_clk_gates[] = {
&meson8b_clk81,
&meson8b_ddr,
&meson8b_dos,
&meson8b_ao_iface,
};
+static struct clk_mux *const meson8b_clk_muxes[] = {
+ &meson8b_mpeg_clk_sel,
+};
+
+static struct clk_divider *const meson8b_clk_dividers[] = {
+ &meson8b_mpeg_clk_div,
+};
+
static int meson8b_clkc_probe(struct platform_device *pdev)
{
void __iomem *clk_base;
for (i = 0; i < ARRAY_SIZE(meson8b_clk_plls); i++)
meson8b_clk_plls[i]->base = clk_base;
+ /* Populate base address for MPLLs */
+ for (i = 0; i < ARRAY_SIZE(meson8b_clk_mplls); i++)
+ meson8b_clk_mplls[i]->base = clk_base;
+
/* Populate the base address for CPU clk */
meson8b_cpu_clk.base = clk_base;
- /* Populate the base address for the MPEG clks */
- meson8b_mpeg_clk_sel.reg = clk_base + (u32)meson8b_mpeg_clk_sel.reg;
- meson8b_mpeg_clk_div.reg = clk_base + (u32)meson8b_mpeg_clk_div.reg;
-
/* Populate base address for gates */
for (i = 0; i < ARRAY_SIZE(meson8b_clk_gates); i++)
meson8b_clk_gates[i]->reg = clk_base +
(u32)meson8b_clk_gates[i]->reg;
+ /* Populate base address for muxes */
+ for (i = 0; i < ARRAY_SIZE(meson8b_clk_muxes); i++)
+ meson8b_clk_muxes[i]->reg = clk_base +
+ (u32)meson8b_clk_muxes[i]->reg;
+
+ /* Populate base address for dividers */
+ for (i = 0; i < ARRAY_SIZE(meson8b_clk_dividers); i++)
+ meson8b_clk_dividers[i]->reg = clk_base +
+ (u32)meson8b_clk_dividers[i]->reg;
+
/*
* register all clks
* CLKID_UNUSED = 0, so skip it and start with CLKID_XTAL = 1
#define HHI_SYS_PLL_CNTL 0x300 /* 0xc0 offset in data sheet */
#define HHI_VID_PLL_CNTL 0x320 /* 0xc8 offset in data sheet */
+/*
+ * MPLL register offeset taken from the S905 datasheet. Vendor kernel source
+ * confirm these are the same for the S805.
+ */
+#define HHI_MPLL_CNTL 0x280 /* 0xa0 offset in data sheet */
+#define HHI_MPLL_CNTL2 0x284 /* 0xa1 offset in data sheet */
+#define HHI_MPLL_CNTL3 0x288 /* 0xa2 offset in data sheet */
+#define HHI_MPLL_CNTL4 0x28C /* 0xa3 offset in data sheet */
+#define HHI_MPLL_CNTL5 0x290 /* 0xa4 offset in data sheet */
+#define HHI_MPLL_CNTL6 0x294 /* 0xa5 offset in data sheet */
+#define HHI_MPLL_CNTL7 0x298 /* 0xa6 offset in data sheet */
+#define HHI_MPLL_CNTL8 0x29C /* 0xa7 offset in data sheet */
+#define HHI_MPLL_CNTL9 0x2A0 /* 0xa8 offset in data sheet */
+#define HHI_MPLL_CNTL10 0x2A4 /* 0xa9 offset in data sheet */
+
/*
* CLKID index values
*
#define CLKID_AO_AHB_SRAM 90
#define CLKID_AO_AHB_BUS 91
#define CLKID_AO_IFACE 92
+#define CLKID_MPLL0 93
+#define CLKID_MPLL1 94
+#define CLKID_MPLL2 95
-#define CLK_NR_CLKS 93
+#define CLK_NR_CLKS 96
/* include the CLKIDs that have been made part of the stable DT binding */
#include <dt-bindings/clock/meson8b-clkc.h>
for_each_node_by_type(dn, "cpu")
ncpus++;
- cpuclk = kzalloc(ncpus * sizeof(*cpuclk), GFP_KERNEL);
+ cpuclk = kcalloc(ncpus, sizeof(*cpuclk), GFP_KERNEL);
if (WARN_ON(!cpuclk))
goto cpuclk_out;
- clks = kzalloc(ncpus * sizeof(*clks), GFP_KERNEL);
+ clks = kcalloc(ncpus, sizeof(*clks), GFP_KERNEL);
if (WARN_ON(!clks))
goto clks_out;
if (desc->get_refclk_freq)
clk_data.clk_num += 1;
- clk_data.clks = kzalloc(clk_data.clk_num * sizeof(struct clk *),
+ clk_data.clks = kcalloc(clk_data.clk_num, sizeof(*clk_data.clks),
GFP_KERNEL);
if (WARN_ON(!clk_data.clks)) {
iounmap(base);
n++;
ctrl->num_gates = n;
- ctrl->gates = kzalloc(ctrl->num_gates * sizeof(struct clk *),
+ ctrl->gates = kcalloc(ctrl->num_gates, sizeof(*ctrl->gates),
GFP_KERNEL);
if (WARN_ON(!ctrl->gates))
goto gates_out;
struct clk_smd_rpm_req req = {
.key = cpu_to_le32(r->rpm_key),
.nbytes = cpu_to_le32(sizeof(u32)),
- .value = cpu_to_le32(INT_MAX),
+ .value = cpu_to_le32(r->branch ? 1 : INT_MAX),
};
ret = qcom_rpm_smd_write(r->rpm, QCOM_SMD_RPM_ACTIVE_STATE,
.pd = {
.name = "venus_core0",
},
+ .parent = &venus_gdsc.pd,
.pwrsts = PWRSTS_OFF_ON,
.flags = HW_CTRL,
};
.pd = {
.name = "venus_core1",
},
+ .parent = &venus_gdsc.pd,
.pwrsts = PWRSTS_OFF_ON,
.flags = HW_CTRL,
};
.cxcs = (unsigned int []){ 0x36ac },
.cxc_count = 1,
.pd = {
- .name = "vfe0",
+ .name = "vfe1",
},
.parent = &camss_gdsc.pd,
.pwrsts = PWRSTS_OFF_ON,
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/soc/renesas/rcar-rst.h>
+#include <linux/sys_soc.h>
#include <dt-bindings/clock/r8a7795-cpg-mssr.h>
enum clk_ids {
/* Core Clock Outputs exported to DT */
- LAST_DT_CORE_CLK = R8A7795_CLK_OSC,
+ LAST_DT_CORE_CLK = R8A7795_CLK_S0D12,
/* External Input Clocks */
CLK_EXTAL,
MOD_CLK_BASE
};
-static const struct cpg_core_clk r8a7795_core_clks[] __initconst = {
+static struct cpg_core_clk r8a7795_core_clks[] __initdata = {
/* External Clock Inputs */
- DEF_INPUT("extal", CLK_EXTAL),
- DEF_INPUT("extalr", CLK_EXTALR),
+ DEF_INPUT("extal", CLK_EXTAL),
+ DEF_INPUT("extalr", CLK_EXTALR),
/* Internal Core Clocks */
DEF_BASE(".main", CLK_MAIN, CLK_TYPE_GEN3_MAIN, CLK_EXTAL),
DEF_FIXED("zt", R8A7795_CLK_ZT, CLK_PLL1_DIV2, 4, 1),
DEF_FIXED("zx", R8A7795_CLK_ZX, CLK_PLL1_DIV2, 2, 1),
DEF_FIXED("s0d1", R8A7795_CLK_S0D1, CLK_S0, 1, 1),
+ DEF_FIXED("s0d2", R8A7795_CLK_S0D2, CLK_S0, 2, 1),
+ DEF_FIXED("s0d3", R8A7795_CLK_S0D3, CLK_S0, 3, 1),
DEF_FIXED("s0d4", R8A7795_CLK_S0D4, CLK_S0, 4, 1),
+ DEF_FIXED("s0d6", R8A7795_CLK_S0D6, CLK_S0, 6, 1),
+ DEF_FIXED("s0d8", R8A7795_CLK_S0D8, CLK_S0, 8, 1),
+ DEF_FIXED("s0d12", R8A7795_CLK_S0D12, CLK_S0, 12, 1),
DEF_FIXED("s1d1", R8A7795_CLK_S1D1, CLK_S1, 1, 1),
DEF_FIXED("s1d2", R8A7795_CLK_S1D2, CLK_S1, 2, 1),
DEF_FIXED("s1d4", R8A7795_CLK_S1D4, CLK_S1, 4, 1),
DEF_FIXED("s3d2", R8A7795_CLK_S3D2, CLK_S3, 2, 1),
DEF_FIXED("s3d4", R8A7795_CLK_S3D4, CLK_S3, 4, 1),
- DEF_GEN3_SD("sd0", R8A7795_CLK_SD0, CLK_SDSRC, 0x0074),
- DEF_GEN3_SD("sd1", R8A7795_CLK_SD1, CLK_SDSRC, 0x0078),
- DEF_GEN3_SD("sd2", R8A7795_CLK_SD2, CLK_SDSRC, 0x0268),
- DEF_GEN3_SD("sd3", R8A7795_CLK_SD3, CLK_SDSRC, 0x026c),
+ DEF_GEN3_SD("sd0", R8A7795_CLK_SD0, CLK_SDSRC, 0x074),
+ DEF_GEN3_SD("sd1", R8A7795_CLK_SD1, CLK_SDSRC, 0x078),
+ DEF_GEN3_SD("sd2", R8A7795_CLK_SD2, CLK_SDSRC, 0x268),
+ DEF_GEN3_SD("sd3", R8A7795_CLK_SD3, CLK_SDSRC, 0x26c),
DEF_FIXED("cl", R8A7795_CLK_CL, CLK_PLL1_DIV2, 48, 1),
DEF_FIXED("cp", R8A7795_CLK_CP, CLK_EXTAL, 2, 1),
- DEF_DIV6P1("mso", R8A7795_CLK_MSO, CLK_PLL1_DIV4, 0x014),
- DEF_DIV6P1("hdmi", R8A7795_CLK_HDMI, CLK_PLL1_DIV4, 0x250),
DEF_DIV6P1("canfd", R8A7795_CLK_CANFD, CLK_PLL1_DIV4, 0x244),
DEF_DIV6P1("csi0", R8A7795_CLK_CSI0, CLK_PLL1_DIV4, 0x00c),
+ DEF_DIV6P1("mso", R8A7795_CLK_MSO, CLK_PLL1_DIV4, 0x014),
+ DEF_DIV6P1("hdmi", R8A7795_CLK_HDMI, CLK_PLL1_DIV4, 0x250),
- DEF_DIV6_RO("osc", R8A7795_CLK_OSC, CLK_EXTAL, CPG_RCKCR, 8),
+ DEF_DIV6_RO("osc", R8A7795_CLK_OSC, CLK_EXTAL, CPG_RCKCR, 8),
DEF_DIV6_RO("r_int", CLK_RINT, CLK_EXTAL, CPG_RCKCR, 32),
- DEF_BASE("r", R8A7795_CLK_R, CLK_TYPE_GEN3_R, CLK_RINT),
+ DEF_BASE("r", R8A7795_CLK_R, CLK_TYPE_GEN3_R, CLK_RINT),
};
-static const struct mssr_mod_clk r8a7795_mod_clks[] __initconst = {
- DEF_MOD("fdp1-2", 117, R8A7795_CLK_S2D1),
- DEF_MOD("fdp1-1", 118, R8A7795_CLK_S2D1),
- DEF_MOD("fdp1-0", 119, R8A7795_CLK_S2D1),
+static struct mssr_mod_clk r8a7795_mod_clks[] __initdata = {
+ DEF_MOD("fdp1-2", 117, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("fdp1-1", 118, R8A7795_CLK_S0D1),
+ DEF_MOD("fdp1-0", 119, R8A7795_CLK_S0D1),
DEF_MOD("scif5", 202, R8A7795_CLK_S3D4),
DEF_MOD("scif4", 203, R8A7795_CLK_S3D4),
DEF_MOD("scif3", 204, R8A7795_CLK_S3D4),
DEF_MOD("msiof2", 209, R8A7795_CLK_MSO),
DEF_MOD("msiof1", 210, R8A7795_CLK_MSO),
DEF_MOD("msiof0", 211, R8A7795_CLK_MSO),
- DEF_MOD("sys-dmac2", 217, R8A7795_CLK_S3D1),
- DEF_MOD("sys-dmac1", 218, R8A7795_CLK_S3D1),
- DEF_MOD("sys-dmac0", 219, R8A7795_CLK_S3D1),
+ DEF_MOD("sys-dmac2", 217, R8A7795_CLK_S0D3),
+ DEF_MOD("sys-dmac1", 218, R8A7795_CLK_S0D3),
+ DEF_MOD("sys-dmac0", 219, R8A7795_CLK_S0D3),
DEF_MOD("cmt3", 300, R8A7795_CLK_R),
DEF_MOD("cmt2", 301, R8A7795_CLK_R),
DEF_MOD("cmt1", 302, R8A7795_CLK_R),
DEF_MOD("sdif0", 314, R8A7795_CLK_SD0),
DEF_MOD("pcie1", 318, R8A7795_CLK_S3D1),
DEF_MOD("pcie0", 319, R8A7795_CLK_S3D1),
- DEF_MOD("usb3-if1", 327, R8A7795_CLK_S3D1),
+ DEF_MOD("usb3-if1", 327, R8A7795_CLK_S3D1), /* ES1.x */
DEF_MOD("usb3-if0", 328, R8A7795_CLK_S3D1),
DEF_MOD("usb-dmac0", 330, R8A7795_CLK_S3D1),
DEF_MOD("usb-dmac1", 331, R8A7795_CLK_S3D1),
- DEF_MOD("rwdt0", 402, R8A7795_CLK_R),
+ DEF_MOD("rwdt", 402, R8A7795_CLK_R),
DEF_MOD("intc-ex", 407, R8A7795_CLK_CP),
DEF_MOD("intc-ap", 408, R8A7795_CLK_S3D1),
- DEF_MOD("audmac0", 502, R8A7795_CLK_S3D4),
- DEF_MOD("audmac1", 501, R8A7795_CLK_S3D4),
+ DEF_MOD("audmac1", 501, R8A7795_CLK_S0D3),
+ DEF_MOD("audmac0", 502, R8A7795_CLK_S0D3),
DEF_MOD("drif7", 508, R8A7795_CLK_S3D2),
DEF_MOD("drif6", 509, R8A7795_CLK_S3D2),
DEF_MOD("drif5", 510, R8A7795_CLK_S3D2),
DEF_MOD("hscif0", 520, R8A7795_CLK_S3D1),
DEF_MOD("thermal", 522, R8A7795_CLK_CP),
DEF_MOD("pwm", 523, R8A7795_CLK_S3D4),
- DEF_MOD("fcpvd3", 600, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvd2", 601, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvd1", 602, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvd0", 603, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvb1", 606, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvb0", 607, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvi2", 609, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvi1", 610, R8A7795_CLK_S2D1),
- DEF_MOD("fcpvi0", 611, R8A7795_CLK_S2D1),
- DEF_MOD("fcpf2", 613, R8A7795_CLK_S2D1),
- DEF_MOD("fcpf1", 614, R8A7795_CLK_S2D1),
- DEF_MOD("fcpf0", 615, R8A7795_CLK_S2D1),
- DEF_MOD("fcpci1", 616, R8A7795_CLK_S2D1),
- DEF_MOD("fcpci0", 617, R8A7795_CLK_S2D1),
- DEF_MOD("fcpcs", 619, R8A7795_CLK_S2D1),
- DEF_MOD("vspd3", 620, R8A7795_CLK_S2D1),
- DEF_MOD("vspd2", 621, R8A7795_CLK_S2D1),
- DEF_MOD("vspd1", 622, R8A7795_CLK_S2D1),
- DEF_MOD("vspd0", 623, R8A7795_CLK_S2D1),
- DEF_MOD("vspbc", 624, R8A7795_CLK_S2D1),
- DEF_MOD("vspbd", 626, R8A7795_CLK_S2D1),
- DEF_MOD("vspi2", 629, R8A7795_CLK_S2D1),
- DEF_MOD("vspi1", 630, R8A7795_CLK_S2D1),
- DEF_MOD("vspi0", 631, R8A7795_CLK_S2D1),
+ DEF_MOD("fcpvd3", 600, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("fcpvd2", 601, R8A7795_CLK_S0D2),
+ DEF_MOD("fcpvd1", 602, R8A7795_CLK_S0D2),
+ DEF_MOD("fcpvd0", 603, R8A7795_CLK_S0D2),
+ DEF_MOD("fcpvb1", 606, R8A7795_CLK_S0D1),
+ DEF_MOD("fcpvb0", 607, R8A7795_CLK_S0D1),
+ DEF_MOD("fcpvi2", 609, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("fcpvi1", 610, R8A7795_CLK_S0D1),
+ DEF_MOD("fcpvi0", 611, R8A7795_CLK_S0D1),
+ DEF_MOD("fcpf2", 613, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("fcpf1", 614, R8A7795_CLK_S0D1),
+ DEF_MOD("fcpf0", 615, R8A7795_CLK_S0D1),
+ DEF_MOD("fcpci1", 616, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("fcpci0", 617, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("fcpcs", 619, R8A7795_CLK_S0D1),
+ DEF_MOD("vspd3", 620, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("vspd2", 621, R8A7795_CLK_S0D2),
+ DEF_MOD("vspd1", 622, R8A7795_CLK_S0D2),
+ DEF_MOD("vspd0", 623, R8A7795_CLK_S0D2),
+ DEF_MOD("vspbc", 624, R8A7795_CLK_S0D1),
+ DEF_MOD("vspbd", 626, R8A7795_CLK_S0D1),
+ DEF_MOD("vspi2", 629, R8A7795_CLK_S2D1), /* ES1.x */
+ DEF_MOD("vspi1", 630, R8A7795_CLK_S0D1),
+ DEF_MOD("vspi0", 631, R8A7795_CLK_S0D1),
DEF_MOD("ehci2", 701, R8A7795_CLK_S3D4),
DEF_MOD("ehci1", 702, R8A7795_CLK_S3D4),
DEF_MOD("ehci0", 703, R8A7795_CLK_S3D4),
DEF_MOD("hsusb", 704, R8A7795_CLK_S3D4),
- DEF_MOD("csi21", 713, R8A7795_CLK_CSI0),
+ DEF_MOD("csi21", 713, R8A7795_CLK_CSI0), /* ES1.x */
DEF_MOD("csi20", 714, R8A7795_CLK_CSI0),
DEF_MOD("csi41", 715, R8A7795_CLK_CSI0),
DEF_MOD("csi40", 716, R8A7795_CLK_CSI0),
DEF_MOD("lvds", 727, R8A7795_CLK_S0D4),
DEF_MOD("hdmi1", 728, R8A7795_CLK_HDMI),
DEF_MOD("hdmi0", 729, R8A7795_CLK_HDMI),
- DEF_MOD("vin7", 804, R8A7795_CLK_S2D1),
- DEF_MOD("vin6", 805, R8A7795_CLK_S2D1),
- DEF_MOD("vin5", 806, R8A7795_CLK_S2D1),
- DEF_MOD("vin4", 807, R8A7795_CLK_S2D1),
- DEF_MOD("vin3", 808, R8A7795_CLK_S2D1),
- DEF_MOD("vin2", 809, R8A7795_CLK_S2D1),
- DEF_MOD("vin1", 810, R8A7795_CLK_S2D1),
- DEF_MOD("vin0", 811, R8A7795_CLK_S2D1),
- DEF_MOD("etheravb", 812, R8A7795_CLK_S3D2),
+ DEF_MOD("vin7", 804, R8A7795_CLK_S0D2),
+ DEF_MOD("vin6", 805, R8A7795_CLK_S0D2),
+ DEF_MOD("vin5", 806, R8A7795_CLK_S0D2),
+ DEF_MOD("vin4", 807, R8A7795_CLK_S0D2),
+ DEF_MOD("vin3", 808, R8A7795_CLK_S0D2),
+ DEF_MOD("vin2", 809, R8A7795_CLK_S0D2),
+ DEF_MOD("vin1", 810, R8A7795_CLK_S0D2),
+ DEF_MOD("vin0", 811, R8A7795_CLK_S0D2),
+ DEF_MOD("etheravb", 812, R8A7795_CLK_S0D6),
DEF_MOD("sata0", 815, R8A7795_CLK_S3D2),
+ DEF_MOD("imr3", 820, R8A7795_CLK_S0D2),
+ DEF_MOD("imr2", 821, R8A7795_CLK_S0D2),
+ DEF_MOD("imr1", 822, R8A7795_CLK_S0D2),
+ DEF_MOD("imr0", 823, R8A7795_CLK_S0D2),
DEF_MOD("gpio7", 905, R8A7795_CLK_CP),
DEF_MOD("gpio6", 906, R8A7795_CLK_CP),
DEF_MOD("gpio5", 907, R8A7795_CLK_CP),
{ 2, 192, 192, },
};
+static const struct soc_device_attribute r8a7795es1[] __initconst = {
+ { .soc_id = "r8a7795", .revision = "ES1.*" },
+ { /* sentinel */ }
+};
+
+
+ /*
+ * Fixups for R-Car H3 ES1.x
+ */
+
+static const unsigned int r8a7795es1_mod_nullify[] __initconst = {
+ MOD_CLK_ID(326), /* USB-DMAC3-0 */
+ MOD_CLK_ID(329), /* USB-DMAC3-1 */
+ MOD_CLK_ID(700), /* EHCI/OHCI3 */
+ MOD_CLK_ID(705), /* HS-USB-IF3 */
+
+};
+
+static const struct mssr_mod_reparent r8a7795es1_mod_reparent[] __initconst = {
+ { MOD_CLK_ID(118), R8A7795_CLK_S2D1 }, /* FDP1-1 */
+ { MOD_CLK_ID(119), R8A7795_CLK_S2D1 }, /* FDP1-0 */
+ { MOD_CLK_ID(217), R8A7795_CLK_S3D1 }, /* SYS-DMAC2 */
+ { MOD_CLK_ID(218), R8A7795_CLK_S3D1 }, /* SYS-DMAC1 */
+ { MOD_CLK_ID(219), R8A7795_CLK_S3D1 }, /* SYS-DMAC0 */
+ { MOD_CLK_ID(501), R8A7795_CLK_S3D1 }, /* AUDMAC1 */
+ { MOD_CLK_ID(502), R8A7795_CLK_S3D1 }, /* AUDMAC0 */
+ { MOD_CLK_ID(601), R8A7795_CLK_S2D1 }, /* FCPVD2 */
+ { MOD_CLK_ID(602), R8A7795_CLK_S2D1 }, /* FCPVD1 */
+ { MOD_CLK_ID(603), R8A7795_CLK_S2D1 }, /* FCPVD0 */
+ { MOD_CLK_ID(606), R8A7795_CLK_S2D1 }, /* FCPVB1 */
+ { MOD_CLK_ID(607), R8A7795_CLK_S2D1 }, /* FCPVB0 */
+ { MOD_CLK_ID(610), R8A7795_CLK_S2D1 }, /* FCPVI1 */
+ { MOD_CLK_ID(611), R8A7795_CLK_S2D1 }, /* FCPVI0 */
+ { MOD_CLK_ID(614), R8A7795_CLK_S2D1 }, /* FCPF1 */
+ { MOD_CLK_ID(615), R8A7795_CLK_S2D1 }, /* FCPF0 */
+ { MOD_CLK_ID(619), R8A7795_CLK_S2D1 }, /* FCPCS */
+ { MOD_CLK_ID(621), R8A7795_CLK_S2D1 }, /* VSPD2 */
+ { MOD_CLK_ID(622), R8A7795_CLK_S2D1 }, /* VSPD1 */
+ { MOD_CLK_ID(623), R8A7795_CLK_S2D1 }, /* VSPD0 */
+ { MOD_CLK_ID(624), R8A7795_CLK_S2D1 }, /* VSPBC */
+ { MOD_CLK_ID(626), R8A7795_CLK_S2D1 }, /* VSPBD */
+ { MOD_CLK_ID(630), R8A7795_CLK_S2D1 }, /* VSPI1 */
+ { MOD_CLK_ID(631), R8A7795_CLK_S2D1 }, /* VSPI0 */
+ { MOD_CLK_ID(804), R8A7795_CLK_S2D1 }, /* VIN7 */
+ { MOD_CLK_ID(805), R8A7795_CLK_S2D1 }, /* VIN6 */
+ { MOD_CLK_ID(806), R8A7795_CLK_S2D1 }, /* VIN5 */
+ { MOD_CLK_ID(807), R8A7795_CLK_S2D1 }, /* VIN4 */
+ { MOD_CLK_ID(808), R8A7795_CLK_S2D1 }, /* VIN3 */
+ { MOD_CLK_ID(809), R8A7795_CLK_S2D1 }, /* VIN2 */
+ { MOD_CLK_ID(810), R8A7795_CLK_S2D1 }, /* VIN1 */
+ { MOD_CLK_ID(811), R8A7795_CLK_S2D1 }, /* VIN0 */
+ { MOD_CLK_ID(812), R8A7795_CLK_S3D2 }, /* EAVB-IF */
+ { MOD_CLK_ID(820), R8A7795_CLK_S2D1 }, /* IMR3 */
+ { MOD_CLK_ID(821), R8A7795_CLK_S2D1 }, /* IMR2 */
+ { MOD_CLK_ID(822), R8A7795_CLK_S2D1 }, /* IMR1 */
+ { MOD_CLK_ID(823), R8A7795_CLK_S2D1 }, /* IMR0 */
+};
+
+
+ /*
+ * Fixups for R-Car H3 ES2.x
+ */
+
+static const unsigned int r8a7795es2_mod_nullify[] __initconst = {
+ MOD_CLK_ID(117), /* FDP1-2 */
+ MOD_CLK_ID(327), /* USB3-IF1 */
+ MOD_CLK_ID(600), /* FCPVD3 */
+ MOD_CLK_ID(609), /* FCPVI2 */
+ MOD_CLK_ID(613), /* FCPF2 */
+ MOD_CLK_ID(616), /* FCPCI1 */
+ MOD_CLK_ID(617), /* FCPCI0 */
+ MOD_CLK_ID(620), /* VSPD3 */
+ MOD_CLK_ID(629), /* VSPI2 */
+ MOD_CLK_ID(713), /* CSI21 */
+};
+
static int __init r8a7795_cpg_mssr_init(struct device *dev)
{
const struct rcar_gen3_cpg_pll_config *cpg_pll_config;
return -EINVAL;
}
- return rcar_gen3_cpg_init(cpg_pll_config, CLK_EXTALR);
+ if (soc_device_match(r8a7795es1)) {
+ cpg_core_nullify_range(r8a7795_core_clks,
+ ARRAY_SIZE(r8a7795_core_clks),
+ R8A7795_CLK_S0D2, R8A7795_CLK_S0D12);
+ mssr_mod_nullify(r8a7795_mod_clks,
+ ARRAY_SIZE(r8a7795_mod_clks),
+ r8a7795es1_mod_nullify,
+ ARRAY_SIZE(r8a7795es1_mod_nullify));
+ mssr_mod_reparent(r8a7795_mod_clks,
+ ARRAY_SIZE(r8a7795_mod_clks),
+ r8a7795es1_mod_reparent,
+ ARRAY_SIZE(r8a7795es1_mod_reparent));
+ } else {
+ mssr_mod_nullify(r8a7795_mod_clks,
+ ARRAY_SIZE(r8a7795_mod_clks),
+ r8a7795es2_mod_nullify,
+ ARRAY_SIZE(r8a7795es2_mod_nullify));
+ }
+
+ return rcar_gen3_cpg_init(cpg_pll_config, CLK_EXTALR, cpg_mode);
}
const struct cpg_mssr_info r8a7795_cpg_mssr_info __initconst = {
static const struct cpg_core_clk r8a7796_core_clks[] __initconst = {
/* External Clock Inputs */
- DEF_INPUT("extal", CLK_EXTAL),
- DEF_INPUT("extalr", CLK_EXTALR),
+ DEF_INPUT("extal", CLK_EXTAL),
+ DEF_INPUT("extalr", CLK_EXTALR),
/* Internal Core Clocks */
DEF_BASE(".main", CLK_MAIN, CLK_TYPE_GEN3_MAIN, CLK_EXTAL),
DEF_FIXED("s3d2", R8A7796_CLK_S3D2, CLK_S3, 2, 1),
DEF_FIXED("s3d4", R8A7796_CLK_S3D4, CLK_S3, 4, 1),
- DEF_GEN3_SD("sd0", R8A7796_CLK_SD0, CLK_SDSRC, 0x0074),
- DEF_GEN3_SD("sd1", R8A7796_CLK_SD1, CLK_SDSRC, 0x0078),
- DEF_GEN3_SD("sd2", R8A7796_CLK_SD2, CLK_SDSRC, 0x0268),
- DEF_GEN3_SD("sd3", R8A7796_CLK_SD3, CLK_SDSRC, 0x026c),
+ DEF_GEN3_SD("sd0", R8A7796_CLK_SD0, CLK_SDSRC, 0x074),
+ DEF_GEN3_SD("sd1", R8A7796_CLK_SD1, CLK_SDSRC, 0x078),
+ DEF_GEN3_SD("sd2", R8A7796_CLK_SD2, CLK_SDSRC, 0x268),
+ DEF_GEN3_SD("sd3", R8A7796_CLK_SD3, CLK_SDSRC, 0x26c),
DEF_FIXED("cl", R8A7796_CLK_CL, CLK_PLL1_DIV2, 48, 1),
DEF_FIXED("cp", R8A7796_CLK_CP, CLK_EXTAL, 2, 1),
DEF_MOD("sdif2", 312, R8A7796_CLK_SD2),
DEF_MOD("sdif1", 313, R8A7796_CLK_SD1),
DEF_MOD("sdif0", 314, R8A7796_CLK_SD0),
- DEF_MOD("rwdt0", 402, R8A7796_CLK_R),
+ DEF_MOD("rwdt", 402, R8A7796_CLK_R),
DEF_MOD("intc-ap", 408, R8A7796_CLK_S3D1),
DEF_MOD("drif7", 508, R8A7796_CLK_S3D2),
DEF_MOD("drif6", 509, R8A7796_CLK_S3D2),
DEF_MOD("vin1", 810, R8A7796_CLK_S0D2),
DEF_MOD("vin0", 811, R8A7796_CLK_S0D2),
DEF_MOD("etheravb", 812, R8A7796_CLK_S0D6),
+ DEF_MOD("imr1", 822, R8A7796_CLK_S0D2),
+ DEF_MOD("imr0", 823, R8A7796_CLK_S0D2),
DEF_MOD("gpio7", 905, R8A7796_CLK_S3D4),
DEF_MOD("gpio6", 906, R8A7796_CLK_S3D4),
DEF_MOD("gpio5", 907, R8A7796_CLK_S3D4),
return -EINVAL;
}
- return rcar_gen3_cpg_init(cpg_pll_config, CLK_EXTALR);
+ return rcar_gen3_cpg_init(cpg_pll_config, CLK_EXTALR, cpg_mode);
}
const struct cpg_mssr_info r8a7796_cpg_mssr_info __initconst = {
#include <linux/init.h>
#include <linux/io.h>
#include <linux/slab.h>
+#include <linux/sys_soc.h>
#include "renesas-cpg-mssr.h"
#include "rcar-gen3-cpg.h"
static const struct rcar_gen3_cpg_pll_config *cpg_pll_config __initdata;
static unsigned int cpg_clk_extalr __initdata;
+static u32 cpg_mode __initdata;
+static u32 cpg_quirks __initdata;
+
+#define PLL_ERRATA BIT(0) /* Missing PLL0/2/4 post-divider */
+#define RCKCR_CKSEL BIT(1) /* Manual RCLK parent selection */
+
+static const struct soc_device_attribute cpg_quirks_match[] __initconst = {
+ {
+ .soc_id = "r8a7795", .revision = "ES1.0",
+ .data = (void *)(PLL_ERRATA | RCKCR_CKSEL),
+ },
+ {
+ .soc_id = "r8a7795", .revision = "ES1.*",
+ .data = (void *)RCKCR_CKSEL,
+ },
+ {
+ .soc_id = "r8a7796", .revision = "ES1.0",
+ .data = (void *)RCKCR_CKSEL,
+ },
+ { /* sentinel */ }
+};
struct clk * __init rcar_gen3_cpg_clk_register(struct device *dev,
const struct cpg_core_clk *core, const struct cpg_mssr_info *info,
*/
value = readl(base + CPG_PLL0CR);
mult = (((value >> 24) & 0x7f) + 1) * 2;
+ if (cpg_quirks & PLL_ERRATA)
+ mult *= 2;
break;
case CLK_TYPE_GEN3_PLL1:
*/
value = readl(base + CPG_PLL2CR);
mult = (((value >> 24) & 0x7f) + 1) * 2;
+ if (cpg_quirks & PLL_ERRATA)
+ mult *= 2;
break;
case CLK_TYPE_GEN3_PLL3:
*/
value = readl(base + CPG_PLL4CR);
mult = (((value >> 24) & 0x7f) + 1) * 2;
+ if (cpg_quirks & PLL_ERRATA)
+ mult *= 2;
break;
case CLK_TYPE_GEN3_SD:
return cpg_sd_clk_register(core, base, __clk_get_name(parent));
case CLK_TYPE_GEN3_R:
- /*
- * RINT is default.
- * Only if EXTALR is populated, we switch to it.
- */
- value = readl(base + CPG_RCKCR) & 0x3f;
-
- if (clk_get_rate(clks[cpg_clk_extalr])) {
- parent = clks[cpg_clk_extalr];
- value |= BIT(15);
+ if (cpg_quirks & RCKCR_CKSEL) {
+ /*
+ * RINT is default.
+ * Only if EXTALR is populated, we switch to it.
+ */
+ value = readl(base + CPG_RCKCR) & 0x3f;
+
+ if (clk_get_rate(clks[cpg_clk_extalr])) {
+ parent = clks[cpg_clk_extalr];
+ value |= BIT(15);
+ }
+
+ writel(value, base + CPG_RCKCR);
+ break;
}
- writel(value, base + CPG_RCKCR);
+ /* Select parent clock of RCLK by MD28 */
+ if (cpg_mode & BIT(28))
+ parent = clks[cpg_clk_extalr];
break;
default:
}
int __init rcar_gen3_cpg_init(const struct rcar_gen3_cpg_pll_config *config,
- unsigned int clk_extalr)
+ unsigned int clk_extalr, u32 mode)
{
+ const struct soc_device_attribute *attr;
+
cpg_pll_config = config;
cpg_clk_extalr = clk_extalr;
+ cpg_mode = mode;
+ attr = soc_device_match(cpg_quirks_match);
+ if (attr)
+ cpg_quirks = (uintptr_t)attr->data;
+ pr_debug("%s: mode = 0x%x quirks = 0x%x\n", __func__, mode, cpg_quirks);
return 0;
}
const struct cpg_core_clk *core, const struct cpg_mssr_info *info,
struct clk **clks, void __iomem *base);
int rcar_gen3_cpg_init(const struct rcar_gen3_cpg_pll_config *config,
- unsigned int clk_extalr);
+ unsigned int clk_extalr, u32 mode);
#endif
WARN_DEBUG(id >= priv->num_core_clks);
WARN_DEBUG(PTR_ERR(priv->clks[id]) != -ENOENT);
+ if (!core->name) {
+ /* Skip NULLified clock */
+ return;
+ }
+
switch (core->type) {
case CLK_TYPE_IN:
clk = of_clk_get_by_name(priv->dev->of_node, core->name);
WARN_DEBUG(mod->parent >= priv->num_core_clks + priv->num_mod_clks);
WARN_DEBUG(PTR_ERR(priv->clks[id]) != -ENOENT);
+ if (!mod->name) {
+ /* Skip NULLified clock */
+ return;
+ }
+
parent = priv->clks[mod->parent];
if (IS_ERR(parent)) {
clk = parent;
subsys_initcall(cpg_mssr_init);
+void __init cpg_core_nullify_range(struct cpg_core_clk *core_clks,
+ unsigned int num_core_clks,
+ unsigned int first_clk,
+ unsigned int last_clk)
+{
+ unsigned int i;
+
+ for (i = 0; i < num_core_clks; i++)
+ if (core_clks[i].id >= first_clk &&
+ core_clks[i].id <= last_clk)
+ core_clks[i].name = NULL;
+}
+
+void __init mssr_mod_nullify(struct mssr_mod_clk *mod_clks,
+ unsigned int num_mod_clks,
+ const unsigned int *clks, unsigned int n)
+{
+ unsigned int i, j;
+
+ for (i = 0, j = 0; i < num_mod_clks && j < n; i++)
+ if (mod_clks[i].id == clks[j]) {
+ mod_clks[i].name = NULL;
+ j++;
+ }
+}
+
+void __init mssr_mod_reparent(struct mssr_mod_clk *mod_clks,
+ unsigned int num_mod_clks,
+ const struct mssr_mod_reparent *clks,
+ unsigned int n)
+{
+ unsigned int i, j;
+
+ for (i = 0, j = 0; i < num_mod_clks && j < n; i++)
+ if (mod_clks[i].id == clks[j].clk) {
+ mod_clks[i].parent = clks[j].parent;
+ j++;
+ }
+}
+
MODULE_DESCRIPTION("Renesas CPG/MSSR Driver");
MODULE_LICENSE("GPL v2");
extern const struct cpg_mssr_info r8a7745_cpg_mssr_info;
extern const struct cpg_mssr_info r8a7795_cpg_mssr_info;
extern const struct cpg_mssr_info r8a7796_cpg_mssr_info;
+
+
+ /*
+ * Helpers for fixing up clock tables depending on SoC revision
+ */
+
+struct mssr_mod_reparent {
+ unsigned int clk, parent;
+};
+
+
+extern void cpg_core_nullify_range(struct cpg_core_clk *core_clks,
+ unsigned int num_core_clks,
+ unsigned int first_clk,
+ unsigned int last_clk);
+extern void mssr_mod_nullify(struct mssr_mod_clk *mod_clks,
+ unsigned int num_mod_clks,
+ const unsigned int *clks, unsigned int n);
+extern void mssr_mod_reparent(struct mssr_mod_clk *mod_clks,
+ unsigned int num_mod_clks,
+ const struct mssr_mod_reparent *clks,
+ unsigned int n);
#endif
obj-y += clk-ddr.o
obj-$(CONFIG_RESET_CONTROLLER) += softrst.o
-obj-y += clk-rk1108.o
+obj-y += clk-rv1108.o
obj-y += clk-rk3036.o
obj-y += clk-rk3188.o
obj-y += clk-rk3228.o
writel(HIWORD_UPDATE(0, RK3036_PLLCON1_PWRDOWN, 0),
pll->reg_base + RK3036_PLLCON(1));
+ rockchip_pll_wait_lock(pll);
return 0;
}
writel(HIWORD_UPDATE(0, RK3066_PLLCON3_PWRDOWN, 0),
pll->reg_base + RK3066_PLLCON(3));
+ rockchip_pll_wait_lock(pll);
return 0;
}
writel(HIWORD_UPDATE(0, RK3399_PLLCON3_PWRDOWN, 0),
pll->reg_base + RK3399_PLLCON(3));
+ rockchip_rk3399_pll_wait_lock(pll);
return 0;
}
#include <dt-bindings/clock/rk3328-cru.h>
#include "clk.h"
+#define RK3328_GRF_SOC_CON4 0x410
#define RK3328_GRF_SOC_STATUS0 0x480
#define RK3328_GRF_MAC_CON1 0x904
#define RK3328_GRF_MAC_CON2 0x908
"gmac_clkin" };
PNAME(mux_mac2phy_src_p) = { "clk_mac2phy_src",
"phy_50m_out" };
+PNAME(mux_mac2io_ext_p) = { "clk_mac2io",
+ "gmac_clkin" };
static struct rockchip_pll_clock rk3328_pll_clks[] __initdata = {
[apll] = PLL(pll_rk3328, PLL_APLL, "apll", mux_pll_p,
COMPOSITE(SCLK_MAC2IO_OUT, "clk_mac2io_out", mux_2plls_p, 0,
RK3328_CLKSEL_CON(27), 15, 1, MFLAGS, 8, 5, DFLAGS,
RK3328_CLKGATE_CON(3), 5, GFLAGS),
+ MUXGRF(SCLK_MAC2IO, "clk_mac2io", mux_mac2io_src_p, CLK_SET_RATE_NO_REPARENT,
+ RK3328_GRF_MAC_CON1, 10, 1, MFLAGS),
+ MUXGRF(SCLK_MAC2IO_EXT, "clk_mac2io_ext", mux_mac2io_ext_p, CLK_SET_RATE_NO_REPARENT,
+ RK3328_GRF_SOC_CON4, 14, 1, MFLAGS),
COMPOSITE(SCLK_MAC2PHY_SRC, "clk_mac2phy_src", mux_2plls_p, 0,
RK3328_CLKSEL_CON(26), 7, 1, MFLAGS, 0, 5, DFLAGS,
COMPOSITE_NOMUX(SCLK_MAC2PHY_OUT, "clk_mac2phy_out", "clk_mac2phy", 0,
RK3328_CLKSEL_CON(26), 8, 2, DFLAGS,
RK3328_CLKGATE_CON(9), 2, GFLAGS),
+ MUXGRF(SCLK_MAC2PHY, "clk_mac2phy", mux_mac2phy_src_p, CLK_SET_RATE_NO_REPARENT,
+ RK3328_GRF_MAC_CON2, 10, 1, MFLAGS),
FACTOR(0, "xin12m", "xin24m", 0, 1, 2),
GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 0, GFLAGS),
/* timer gates */
- GATE(0, "sclk_timer15", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 11, GFLAGS),
- GATE(0, "sclk_timer14", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 10, GFLAGS),
- GATE(0, "sclk_timer13", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 9, GFLAGS),
- GATE(0, "sclk_timer12", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 8, GFLAGS),
- GATE(0, "sclk_timer11", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 7, GFLAGS),
- GATE(0, "sclk_timer10", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 6, GFLAGS),
- GATE(0, "sclk_timer05", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 5, GFLAGS),
- GATE(0, "sclk_timer04", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 4, GFLAGS),
- GATE(0, "sclk_timer03", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 3, GFLAGS),
- GATE(0, "sclk_timer02", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 2, GFLAGS),
- GATE(0, "sclk_timer01", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 1, GFLAGS),
- GATE(0, "sclk_timer00", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 0, GFLAGS),
+ GATE(SCLK_TIMER15, "sclk_timer15", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 11, GFLAGS),
+ GATE(SCLK_TIMER14, "sclk_timer14", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 10, GFLAGS),
+ GATE(SCLK_TIMER13, "sclk_timer13", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 9, GFLAGS),
+ GATE(SCLK_TIMER12, "sclk_timer12", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 8, GFLAGS),
+ GATE(SCLK_TIMER11, "sclk_timer11", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 7, GFLAGS),
+ GATE(SCLK_TIMER10, "sclk_timer10", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 6, GFLAGS),
+ GATE(SCLK_TIMER05, "sclk_timer05", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 5, GFLAGS),
+ GATE(SCLK_TIMER04, "sclk_timer04", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 4, GFLAGS),
+ GATE(SCLK_TIMER03, "sclk_timer03", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 3, GFLAGS),
+ GATE(SCLK_TIMER02, "sclk_timer02", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 2, GFLAGS),
+ GATE(SCLK_TIMER01, "sclk_timer01", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 1, GFLAGS),
+ GATE(SCLK_TIMER00, "sclk_timer00", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 0, GFLAGS),
};
static const char *const rk3368_critical_clocks[] __initconst = {
*/
"pclk_pwm1",
"pclk_pd_pmu",
+ "pclk_pd_alive",
+ "pclk_peri",
+ "hclk_peri",
};
static void __init rk3368_clk_init(struct device_node *np)
GATE(PCLK_UART4_PMU, "pclk_uart4_pmu", "pclk_pmu_src", 0, RK3399_PMU_CLKGATE_CON(1), 14, GFLAGS),
GATE(PCLK_WDT_M0_PMU, "pclk_wdt_m0_pmu", "pclk_pmu_src", 0, RK3399_PMU_CLKGATE_CON(1), 15, GFLAGS),
- GATE(FCLK_CM0S_PMU, "fclk_cm0s_pmu", "fclk_cm0s_src_pmu", 0, RK3399_PMU_CLKGATE_CON(2), 0, GFLAGS),
- GATE(SCLK_CM0S_PMU, "sclk_cm0s_pmu", "fclk_cm0s_src_pmu", 0, RK3399_PMU_CLKGATE_CON(2), 1, GFLAGS),
- GATE(HCLK_CM0S_PMU, "hclk_cm0s_pmu", "fclk_cm0s_src_pmu", 0, RK3399_PMU_CLKGATE_CON(2), 2, GFLAGS),
- GATE(DCLK_CM0S_PMU, "dclk_cm0s_pmu", "fclk_cm0s_src_pmu", 0, RK3399_PMU_CLKGATE_CON(2), 3, GFLAGS),
+ GATE(FCLK_CM0S_PMU, "fclk_cm0s_pmu", "fclk_cm0s_src_pmu", CLK_IGNORE_UNUSED, RK3399_PMU_CLKGATE_CON(2), 0, GFLAGS),
+ GATE(SCLK_CM0S_PMU, "sclk_cm0s_pmu", "fclk_cm0s_src_pmu", CLK_IGNORE_UNUSED, RK3399_PMU_CLKGATE_CON(2), 1, GFLAGS),
+ GATE(HCLK_CM0S_PMU, "hclk_cm0s_pmu", "fclk_cm0s_src_pmu", CLK_IGNORE_UNUSED, RK3399_PMU_CLKGATE_CON(2), 2, GFLAGS),
+ GATE(DCLK_CM0S_PMU, "dclk_cm0s_pmu", "fclk_cm0s_src_pmu", CLK_IGNORE_UNUSED, RK3399_PMU_CLKGATE_CON(2), 3, GFLAGS),
GATE(HCLK_NOC_PMU, "hclk_noc_pmu", "fclk_cm0s_src_pmu", CLK_IGNORE_UNUSED, RK3399_PMU_CLKGATE_CON(2), 5, GFLAGS),
};
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/syscore_ops.h>
-#include <dt-bindings/clock/rk1108-cru.h>
+#include <dt-bindings/clock/rv1108-cru.h>
#include "clk.h"
-#define RK1108_GRF_SOC_STATUS0 0x480
+#define RV1108_GRF_SOC_STATUS0 0x480
-enum rk1108_plls {
+enum rv1108_plls {
apll, dpll, gpll,
};
-static struct rockchip_pll_rate_table rk1108_pll_rates[] = {
+static struct rockchip_pll_rate_table rv1108_pll_rates[] = {
/* _mhz, _refdiv, _fbdiv, _postdiv1, _postdiv2, _dsmpd, _frac */
RK3036_PLL_RATE(1608000000, 1, 67, 1, 1, 1, 0),
RK3036_PLL_RATE(1584000000, 1, 66, 1, 1, 1, 0),
{ /* sentinel */ },
};
-#define RK1108_DIV_CORE_MASK 0xf
-#define RK1108_DIV_CORE_SHIFT 4
+#define RV1108_DIV_CORE_MASK 0xf
+#define RV1108_DIV_CORE_SHIFT 4
-#define RK1108_CLKSEL0(_core_peri_div) \
+#define RV1108_CLKSEL0(_core_peri_div) \
{ \
- .reg = RK1108_CLKSEL_CON(1), \
- .val = HIWORD_UPDATE(_core_peri_div, RK1108_DIV_CORE_MASK,\
- RK1108_DIV_CORE_SHIFT) \
+ .reg = RV1108_CLKSEL_CON(1), \
+ .val = HIWORD_UPDATE(_core_peri_div, RV1108_DIV_CORE_MASK,\
+ RV1108_DIV_CORE_SHIFT) \
}
-#define RK1108_CPUCLK_RATE(_prate, _core_peri_div) \
+#define RV1108_CPUCLK_RATE(_prate, _core_peri_div) \
{ \
.prate = _prate, \
.divs = { \
- RK1108_CLKSEL0(_core_peri_div), \
+ RV1108_CLKSEL0(_core_peri_div), \
}, \
}
-static struct rockchip_cpuclk_rate_table rk1108_cpuclk_rates[] __initdata = {
- RK1108_CPUCLK_RATE(816000000, 4),
- RK1108_CPUCLK_RATE(600000000, 4),
- RK1108_CPUCLK_RATE(312000000, 4),
+static struct rockchip_cpuclk_rate_table rv1108_cpuclk_rates[] __initdata = {
+ RV1108_CPUCLK_RATE(816000000, 4),
+ RV1108_CPUCLK_RATE(600000000, 4),
+ RV1108_CPUCLK_RATE(312000000, 4),
};
-static const struct rockchip_cpuclk_reg_data rk1108_cpuclk_data = {
- .core_reg = RK1108_CLKSEL_CON(0),
+static const struct rockchip_cpuclk_reg_data rv1108_cpuclk_data = {
+ .core_reg = RV1108_CLKSEL_CON(0),
.div_core_shift = 0,
.div_core_mask = 0x1f,
.mux_core_alt = 1,
PNAME(mux_i2s1_p) = { "i2s1_src", "i2s1_frac", "xin12m" };
PNAME(mux_i2s2_p) = { "i2s2_src", "i2s2_frac", "xin12m" };
-static struct rockchip_pll_clock rk1108_pll_clks[] __initdata = {
- [apll] = PLL(pll_rk3399, PLL_APLL, "apll", mux_pll_p, 0, RK1108_PLL_CON(0),
- RK1108_PLL_CON(3), 8, 31, 0, rk1108_pll_rates),
- [dpll] = PLL(pll_rk3399, PLL_DPLL, "dpll", mux_pll_p, 0, RK1108_PLL_CON(8),
- RK1108_PLL_CON(11), 8, 31, 0, NULL),
- [gpll] = PLL(pll_rk3399, PLL_GPLL, "gpll", mux_pll_p, 0, RK1108_PLL_CON(16),
- RK1108_PLL_CON(19), 8, 31, ROCKCHIP_PLL_SYNC_RATE, rk1108_pll_rates),
+static struct rockchip_pll_clock rv1108_pll_clks[] __initdata = {
+ [apll] = PLL(pll_rk3399, PLL_APLL, "apll", mux_pll_p, 0, RV1108_PLL_CON(0),
+ RV1108_PLL_CON(3), 8, 31, 0, rv1108_pll_rates),
+ [dpll] = PLL(pll_rk3399, PLL_DPLL, "dpll", mux_pll_p, 0, RV1108_PLL_CON(8),
+ RV1108_PLL_CON(11), 8, 31, 0, NULL),
+ [gpll] = PLL(pll_rk3399, PLL_GPLL, "gpll", mux_pll_p, 0, RV1108_PLL_CON(16),
+ RV1108_PLL_CON(19), 8, 31, ROCKCHIP_PLL_SYNC_RATE, rv1108_pll_rates),
};
#define MFLAGS CLK_MUX_HIWORD_MASK
#define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
#define IFLAGS ROCKCHIP_INVERTER_HIWORD_MASK
-static struct rockchip_clk_branch rk1108_uart0_fracmux __initdata =
+static struct rockchip_clk_branch rv1108_uart0_fracmux __initdata =
MUX(SCLK_UART0, "sclk_uart0", mux_uart0_p, CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(13), 8, 2, MFLAGS);
+ RV1108_CLKSEL_CON(13), 8, 2, MFLAGS);
-static struct rockchip_clk_branch rk1108_uart1_fracmux __initdata =
+static struct rockchip_clk_branch rv1108_uart1_fracmux __initdata =
MUX(SCLK_UART1, "sclk_uart1", mux_uart1_p, CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(14), 8, 2, MFLAGS);
+ RV1108_CLKSEL_CON(14), 8, 2, MFLAGS);
-static struct rockchip_clk_branch rk1108_uart2_fracmux __initdata =
+static struct rockchip_clk_branch rv1108_uart2_fracmux __initdata =
MUX(SCLK_UART2, "sclk_uart2", mux_uart2_p, CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(15), 8, 2, MFLAGS);
+ RV1108_CLKSEL_CON(15), 8, 2, MFLAGS);
-static struct rockchip_clk_branch rk1108_i2s0_fracmux __initdata =
+static struct rockchip_clk_branch rv1108_i2s0_fracmux __initdata =
MUX(0, "i2s0_pre", mux_i2s0_pre_p, CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(5), 12, 2, MFLAGS);
+ RV1108_CLKSEL_CON(5), 12, 2, MFLAGS);
-static struct rockchip_clk_branch rk1108_i2s1_fracmux __initdata =
+static struct rockchip_clk_branch rv1108_i2s1_fracmux __initdata =
MUX(0, "i2s1_pre", mux_i2s1_p, CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(6), 12, 2, MFLAGS);
+ RV1108_CLKSEL_CON(6), 12, 2, MFLAGS);
-static struct rockchip_clk_branch rk1108_i2s2_fracmux __initdata =
+static struct rockchip_clk_branch rv1108_i2s2_fracmux __initdata =
MUX(0, "i2s2_pre", mux_i2s2_p, CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(7), 12, 2, MFLAGS);
+ RV1108_CLKSEL_CON(7), 12, 2, MFLAGS);
-static struct rockchip_clk_branch rk1108_clk_branches[] __initdata = {
+static struct rockchip_clk_branch rv1108_clk_branches[] __initdata = {
MUX(0, "hdmi_phy", mux_hdmiphy_phy_p, CLK_SET_RATE_PARENT,
- RK1108_MISC_CON, 13, 2, MFLAGS),
+ RV1108_MISC_CON, 13, 2, MFLAGS),
MUX(0, "usb480m", mux_usb480m_pre_p, CLK_SET_RATE_PARENT,
- RK1108_MISC_CON, 15, 2, MFLAGS),
+ RV1108_MISC_CON, 15, 2, MFLAGS),
/*
* Clock-Architecture Diagram 2
*/
/* PD_CORE */
GATE(0, "dpll_core", "dpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(0), 1, GFLAGS),
+ RV1108_CLKGATE_CON(0), 1, GFLAGS),
GATE(0, "apll_core", "apll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(0), 0, GFLAGS),
+ RV1108_CLKGATE_CON(0), 0, GFLAGS),
GATE(0, "gpll_core", "gpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(0), 2, GFLAGS),
+ RV1108_CLKGATE_CON(0), 2, GFLAGS),
COMPOSITE_NOMUX(0, "pclken_dbg", "armclk", CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(1), 4, 4, DFLAGS | CLK_DIVIDER_READ_ONLY,
- RK1108_CLKGATE_CON(0), 5, GFLAGS),
+ RV1108_CLKSEL_CON(1), 4, 4, DFLAGS | CLK_DIVIDER_READ_ONLY,
+ RV1108_CLKGATE_CON(0), 5, GFLAGS),
COMPOSITE_NOMUX(ACLK_ENMCORE, "aclkenm_core", "armclk", CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(1), 0, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
- RK1108_CLKGATE_CON(0), 4, GFLAGS),
+ RV1108_CLKSEL_CON(1), 0, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
+ RV1108_CLKGATE_CON(0), 4, GFLAGS),
GATE(ACLK_CORE, "aclk_core", "aclkenm_core", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(11), 0, GFLAGS),
+ RV1108_CLKGATE_CON(11), 0, GFLAGS),
GATE(0, "pclk_dbg", "pclken_dbg", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(11), 1, GFLAGS),
+ RV1108_CLKGATE_CON(11), 1, GFLAGS),
/* PD_RKVENC */
/* PD_PMU_wrapper */
COMPOSITE_NOMUX(0, "pmu_24m_ena", "gpll", CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(38), 0, 5, DFLAGS,
- RK1108_CLKGATE_CON(8), 12, GFLAGS),
+ RV1108_CLKSEL_CON(38), 0, 5, DFLAGS,
+ RV1108_CLKGATE_CON(8), 12, GFLAGS),
GATE(0, "pmu", "pmu_24m_ena", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(10), 0, GFLAGS),
+ RV1108_CLKGATE_CON(10), 0, GFLAGS),
GATE(0, "intmem1", "pmu_24m_ena", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(10), 1, GFLAGS),
+ RV1108_CLKGATE_CON(10), 1, GFLAGS),
GATE(0, "gpio0_pmu", "pmu_24m_ena", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(10), 2, GFLAGS),
+ RV1108_CLKGATE_CON(10), 2, GFLAGS),
GATE(0, "pmugrf", "pmu_24m_ena", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(10), 3, GFLAGS),
+ RV1108_CLKGATE_CON(10), 3, GFLAGS),
GATE(0, "pmu_noc", "pmu_24m_ena", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(10), 4, GFLAGS),
+ RV1108_CLKGATE_CON(10), 4, GFLAGS),
GATE(0, "i2c0_pmu_pclk", "pmu_24m_ena", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(10), 5, GFLAGS),
+ RV1108_CLKGATE_CON(10), 5, GFLAGS),
GATE(0, "pwm0_pmu_pclk", "pmu_24m_ena", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(10), 6, GFLAGS),
+ RV1108_CLKGATE_CON(10), 6, GFLAGS),
COMPOSITE(0, "pwm0_pmu_clk", mux_pll_src_2plls_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(12), 7, 1, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(8), 15, GFLAGS),
+ RV1108_CLKSEL_CON(12), 7, 1, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(8), 15, GFLAGS),
COMPOSITE(0, "i2c0_pmu_clk", mux_pll_src_2plls_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(19), 7, 1, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(8), 14, GFLAGS),
+ RV1108_CLKSEL_CON(19), 7, 1, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(8), 14, GFLAGS),
GATE(0, "pvtm_pmu", "xin24m", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(8), 13, GFLAGS),
+ RV1108_CLKGATE_CON(8), 13, GFLAGS),
/*
* Clock-Architecture Diagram 4
*/
COMPOSITE(0, "aclk_vio0_2wrap_occ", mux_pll_src_4plls_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(28), 6, 2, MFLAGS, 0, 5, DFLAGS,
- RK1108_CLKGATE_CON(6), 0, GFLAGS),
+ RV1108_CLKSEL_CON(28), 6, 2, MFLAGS, 0, 5, DFLAGS,
+ RV1108_CLKGATE_CON(6), 0, GFLAGS),
GATE(0, "aclk_vio0_pre", "aclk_vio0_2wrap_occ", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(17), 0, GFLAGS),
+ RV1108_CLKGATE_CON(17), 0, GFLAGS),
COMPOSITE_NOMUX(0, "hclk_vio_pre", "aclk_vio0_pre", 0,
- RK1108_CLKSEL_CON(29), 0, 5, DFLAGS,
- RK1108_CLKGATE_CON(7), 2, GFLAGS),
+ RV1108_CLKSEL_CON(29), 0, 5, DFLAGS,
+ RV1108_CLKGATE_CON(7), 2, GFLAGS),
COMPOSITE_NOMUX(0, "pclk_vio_pre", "aclk_vio0_pre", 0,
- RK1108_CLKSEL_CON(29), 8, 5, DFLAGS,
- RK1108_CLKGATE_CON(7), 3, GFLAGS),
+ RV1108_CLKSEL_CON(29), 8, 5, DFLAGS,
+ RV1108_CLKGATE_CON(7), 3, GFLAGS),
INVERTER(0, "pclk_vip", "ext_vip",
- RK1108_CLKSEL_CON(31), 8, IFLAGS),
+ RV1108_CLKSEL_CON(31), 8, IFLAGS),
GATE(0, "pclk_isp_pre", "pclk_vip", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(7), 6, GFLAGS),
+ RV1108_CLKGATE_CON(7), 6, GFLAGS),
GATE(0, "pclk_isp", "pclk_isp_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(18), 10, GFLAGS),
+ RV1108_CLKGATE_CON(18), 10, GFLAGS),
GATE(0, "dclk_hdmiphy_src_gpll", "gpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(6), 5, GFLAGS),
+ RV1108_CLKGATE_CON(6), 5, GFLAGS),
GATE(0, "dclk_hdmiphy_src_dpll", "dpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(6), 4, GFLAGS),
+ RV1108_CLKGATE_CON(6), 4, GFLAGS),
COMPOSITE_NOGATE(0, "dclk_hdmiphy", mux_dclk_hdmiphy_pre_p, 0,
- RK1108_CLKSEL_CON(32), 6, 2, MFLAGS, 8, 6, DFLAGS),
+ RV1108_CLKSEL_CON(32), 6, 2, MFLAGS, 8, 6, DFLAGS),
/*
* Clock-Architecture Diagram 5
FACTOR(0, "xin12m", "xin24m", 0, 1, 2),
COMPOSITE(0, "i2s0_src", mux_pll_src_2plls_p, 0,
- RK1108_CLKSEL_CON(5), 8, 1, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(2), 0, GFLAGS),
+ RV1108_CLKSEL_CON(5), 8, 1, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(2), 0, GFLAGS),
COMPOSITE_FRACMUX(0, "i2s1_frac", "i2s1_src", CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(8), 0,
- RK1108_CLKGATE_CON(2), 1, GFLAGS,
- &rk1108_i2s0_fracmux),
+ RV1108_CLKSEL_CON(8), 0,
+ RV1108_CLKGATE_CON(2), 1, GFLAGS,
+ &rv1108_i2s0_fracmux),
GATE(SCLK_I2S0, "sclk_i2s0", "i2s0_pre", CLK_SET_RATE_PARENT,
- RK1108_CLKGATE_CON(2), 2, GFLAGS),
+ RV1108_CLKGATE_CON(2), 2, GFLAGS),
COMPOSITE_NODIV(0, "i2s_out", mux_i2s_out_p, 0,
- RK1108_CLKSEL_CON(5), 15, 1, MFLAGS,
- RK1108_CLKGATE_CON(2), 3, GFLAGS),
+ RV1108_CLKSEL_CON(5), 15, 1, MFLAGS,
+ RV1108_CLKGATE_CON(2), 3, GFLAGS),
COMPOSITE(0, "i2s1_src", mux_pll_src_2plls_p, 0,
- RK1108_CLKSEL_CON(6), 8, 1, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(2), 4, GFLAGS),
+ RV1108_CLKSEL_CON(6), 8, 1, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(2), 4, GFLAGS),
COMPOSITE_FRACMUX(0, "i2s1_frac", "i2s1_src", CLK_SET_RATE_PARENT,
RK2928_CLKSEL_CON(9), 0,
RK2928_CLKGATE_CON(2), 5, GFLAGS,
- &rk1108_i2s1_fracmux),
+ &rv1108_i2s1_fracmux),
GATE(SCLK_I2S1, "sclk_i2s1", "i2s1_pre", CLK_SET_RATE_PARENT,
- RK1108_CLKGATE_CON(2), 6, GFLAGS),
+ RV1108_CLKGATE_CON(2), 6, GFLAGS),
COMPOSITE(0, "i2s2_src", mux_pll_src_2plls_p, 0,
- RK1108_CLKSEL_CON(7), 8, 1, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 8, GFLAGS),
+ RV1108_CLKSEL_CON(7), 8, 1, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 8, GFLAGS),
COMPOSITE_FRACMUX(0, "i2s2_frac", "i2s2_src", CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(10), 0,
- RK1108_CLKGATE_CON(2), 9, GFLAGS,
- &rk1108_i2s2_fracmux),
+ RV1108_CLKSEL_CON(10), 0,
+ RV1108_CLKGATE_CON(2), 9, GFLAGS,
+ &rv1108_i2s2_fracmux),
GATE(SCLK_I2S2, "sclk_i2s2", "i2s2_pre", CLK_SET_RATE_PARENT,
- RK1108_CLKGATE_CON(2), 10, GFLAGS),
+ RV1108_CLKGATE_CON(2), 10, GFLAGS),
/* PD_BUS */
GATE(0, "aclk_bus_src_gpll", "gpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 0, GFLAGS),
+ RV1108_CLKGATE_CON(1), 0, GFLAGS),
GATE(0, "aclk_bus_src_apll", "apll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 1, GFLAGS),
+ RV1108_CLKGATE_CON(1), 1, GFLAGS),
GATE(0, "aclk_bus_src_dpll", "dpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 2, GFLAGS),
+ RV1108_CLKGATE_CON(1), 2, GFLAGS),
COMPOSITE_NOGATE(ACLK_PRE, "aclk_bus_pre", mux_aclk_bus_src_p, 0,
- RK1108_CLKSEL_CON(2), 8, 2, MFLAGS, 0, 5, DFLAGS),
+ RV1108_CLKSEL_CON(2), 8, 2, MFLAGS, 0, 5, DFLAGS),
COMPOSITE_NOMUX(0, "hclk_bus_pre", "aclk_bus_2wrap_occ", 0,
- RK1108_CLKSEL_CON(3), 0, 5, DFLAGS,
- RK1108_CLKGATE_CON(1), 4, GFLAGS),
+ RV1108_CLKSEL_CON(3), 0, 5, DFLAGS,
+ RV1108_CLKGATE_CON(1), 4, GFLAGS),
COMPOSITE_NOMUX(0, "pclken_bus", "aclk_bus_2wrap_occ", 0,
- RK1108_CLKSEL_CON(3), 8, 5, DFLAGS,
- RK1108_CLKGATE_CON(1), 5, GFLAGS),
+ RV1108_CLKSEL_CON(3), 8, 5, DFLAGS,
+ RV1108_CLKGATE_CON(1), 5, GFLAGS),
GATE(0, "pclk_bus_pre", "pclken_bus", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 6, GFLAGS),
+ RV1108_CLKGATE_CON(1), 6, GFLAGS),
GATE(0, "pclk_top_pre", "pclken_bus", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 7, GFLAGS),
+ RV1108_CLKGATE_CON(1), 7, GFLAGS),
GATE(0, "pclk_ddr_pre", "pclken_bus", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 8, GFLAGS),
+ RV1108_CLKGATE_CON(1), 8, GFLAGS),
GATE(0, "clk_timer0", "mux_pll_p", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 9, GFLAGS),
+ RV1108_CLKGATE_CON(1), 9, GFLAGS),
GATE(0, "clk_timer1", "mux_pll_p", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(1), 10, GFLAGS),
+ RV1108_CLKGATE_CON(1), 10, GFLAGS),
GATE(0, "pclk_timer", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 4, GFLAGS),
+ RV1108_CLKGATE_CON(13), 4, GFLAGS),
COMPOSITE(0, "uart0_src", mux_pll_src_dpll_gpll_usb480m_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(13), 12, 2, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 1, GFLAGS),
+ RV1108_CLKSEL_CON(13), 12, 2, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 1, GFLAGS),
COMPOSITE(0, "uart1_src", mux_pll_src_dpll_gpll_usb480m_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(14), 12, 2, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 3, GFLAGS),
+ RV1108_CLKSEL_CON(14), 12, 2, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 3, GFLAGS),
COMPOSITE(0, "uart21_src", mux_pll_src_dpll_gpll_usb480m_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(15), 12, 2, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 5, GFLAGS),
+ RV1108_CLKSEL_CON(15), 12, 2, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 5, GFLAGS),
COMPOSITE_FRACMUX(0, "uart0_frac", "uart0_src", CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(16), 0,
- RK1108_CLKGATE_CON(3), 2, GFLAGS,
- &rk1108_uart0_fracmux),
+ RV1108_CLKSEL_CON(16), 0,
+ RV1108_CLKGATE_CON(3), 2, GFLAGS,
+ &rv1108_uart0_fracmux),
COMPOSITE_FRACMUX(0, "uart1_frac", "uart1_src", CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(17), 0,
- RK1108_CLKGATE_CON(3), 4, GFLAGS,
- &rk1108_uart1_fracmux),
+ RV1108_CLKSEL_CON(17), 0,
+ RV1108_CLKGATE_CON(3), 4, GFLAGS,
+ &rv1108_uart1_fracmux),
COMPOSITE_FRACMUX(0, "uart2_frac", "uart2_src", CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(18), 0,
- RK1108_CLKGATE_CON(3), 6, GFLAGS,
- &rk1108_uart2_fracmux),
+ RV1108_CLKSEL_CON(18), 0,
+ RV1108_CLKGATE_CON(3), 6, GFLAGS,
+ &rv1108_uart2_fracmux),
GATE(PCLK_UART0, "pclk_uart0", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 10, GFLAGS),
+ RV1108_CLKGATE_CON(13), 10, GFLAGS),
GATE(PCLK_UART1, "pclk_uart1", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 11, GFLAGS),
+ RV1108_CLKGATE_CON(13), 11, GFLAGS),
GATE(PCLK_UART2, "pclk_uart2", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 12, GFLAGS),
+ RV1108_CLKGATE_CON(13), 12, GFLAGS),
COMPOSITE(0, "clk_i2c1", mux_pll_src_2plls_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(19), 15, 2, MFLAGS, 8, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 7, GFLAGS),
+ RV1108_CLKSEL_CON(19), 15, 2, MFLAGS, 8, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 7, GFLAGS),
COMPOSITE(0, "clk_i2c2", mux_pll_src_2plls_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(20), 7, 2, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 8, GFLAGS),
+ RV1108_CLKSEL_CON(20), 7, 2, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 8, GFLAGS),
COMPOSITE(0, "clk_i2c3", mux_pll_src_2plls_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(20), 15, 2, MFLAGS, 8, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 9, GFLAGS),
+ RV1108_CLKSEL_CON(20), 15, 2, MFLAGS, 8, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 9, GFLAGS),
GATE(0, "pclk_i2c1", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 0, GFLAGS),
+ RV1108_CLKGATE_CON(13), 0, GFLAGS),
GATE(0, "pclk_i2c2", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 1, GFLAGS),
+ RV1108_CLKGATE_CON(13), 1, GFLAGS),
GATE(0, "pclk_i2c3", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 2, GFLAGS),
+ RV1108_CLKGATE_CON(13), 2, GFLAGS),
COMPOSITE(0, "clk_pwm1", mux_pll_src_2plls_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(12), 15, 2, MFLAGS, 8, 7, DFLAGS,
- RK1108_CLKGATE_CON(3), 10, GFLAGS),
+ RV1108_CLKSEL_CON(12), 15, 2, MFLAGS, 8, 7, DFLAGS,
+ RV1108_CLKGATE_CON(3), 10, GFLAGS),
GATE(0, "pclk_pwm1", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 6, GFLAGS),
+ RV1108_CLKGATE_CON(13), 6, GFLAGS),
GATE(0, "pclk_wdt", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 3, GFLAGS),
+ RV1108_CLKGATE_CON(13), 3, GFLAGS),
GATE(0, "pclk_gpio1", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 7, GFLAGS),
+ RV1108_CLKGATE_CON(13), 7, GFLAGS),
GATE(0, "pclk_gpio2", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 8, GFLAGS),
+ RV1108_CLKGATE_CON(13), 8, GFLAGS),
GATE(0, "pclk_gpio3", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(13), 9, GFLAGS),
+ RV1108_CLKGATE_CON(13), 9, GFLAGS),
GATE(0, "pclk_grf", "pclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(14), 0, GFLAGS),
+ RV1108_CLKGATE_CON(14), 0, GFLAGS),
GATE(ACLK_DMAC, "aclk_dmac", "aclk_bus_pre", 0,
- RK1108_CLKGATE_CON(12), 2, GFLAGS),
+ RV1108_CLKGATE_CON(12), 2, GFLAGS),
GATE(0, "hclk_rom", "hclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(12), 3, GFLAGS),
+ RV1108_CLKGATE_CON(12), 3, GFLAGS),
GATE(0, "aclk_intmem", "aclk_bus_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(12), 1, GFLAGS),
+ RV1108_CLKGATE_CON(12), 1, GFLAGS),
/* PD_DDR */
GATE(0, "apll_ddr", "apll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(0), 8, GFLAGS),
+ RV1108_CLKGATE_CON(0), 8, GFLAGS),
GATE(0, "dpll_ddr", "dpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(0), 9, GFLAGS),
+ RV1108_CLKGATE_CON(0), 9, GFLAGS),
GATE(0, "gpll_ddr", "gpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(0), 10, GFLAGS),
+ RV1108_CLKGATE_CON(0), 10, GFLAGS),
COMPOSITE(0, "ddrphy4x", mux_ddrphy_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(4), 8, 2, MFLAGS, 0, 3,
+ RV1108_CLKSEL_CON(4), 8, 2, MFLAGS, 0, 3,
DFLAGS | CLK_DIVIDER_POWER_OF_TWO,
- RK1108_CLKGATE_CON(10), 9, GFLAGS),
+ RV1108_CLKGATE_CON(10), 9, GFLAGS),
GATE(0, "ddrupctl", "ddrphy_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(12), 4, GFLAGS),
+ RV1108_CLKGATE_CON(12), 4, GFLAGS),
GATE(0, "ddrc", "ddrphy", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(12), 5, GFLAGS),
+ RV1108_CLKGATE_CON(12), 5, GFLAGS),
GATE(0, "ddrmon", "ddrphy_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(12), 6, GFLAGS),
+ RV1108_CLKGATE_CON(12), 6, GFLAGS),
GATE(0, "timer_clk", "xin24m", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(0), 11, GFLAGS),
+ RV1108_CLKGATE_CON(0), 11, GFLAGS),
/*
* Clock-Architecture Diagram 6
/* PD_PERI */
COMPOSITE_NOMUX(0, "pclk_periph_pre", "gpll", 0,
- RK1108_CLKSEL_CON(23), 10, 5, DFLAGS,
- RK1108_CLKGATE_CON(4), 5, GFLAGS),
+ RV1108_CLKSEL_CON(23), 10, 5, DFLAGS,
+ RV1108_CLKGATE_CON(4), 5, GFLAGS),
GATE(0, "pclk_periph", "pclk_periph_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(15), 13, GFLAGS),
+ RV1108_CLKGATE_CON(15), 13, GFLAGS),
COMPOSITE_NOMUX(0, "hclk_periph_pre", "gpll", 0,
- RK1108_CLKSEL_CON(23), 5, 5, DFLAGS,
- RK1108_CLKGATE_CON(4), 4, GFLAGS),
+ RV1108_CLKSEL_CON(23), 5, 5, DFLAGS,
+ RV1108_CLKGATE_CON(4), 4, GFLAGS),
GATE(0, "hclk_periph", "hclk_periph_pre", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(15), 12, GFLAGS),
+ RV1108_CLKGATE_CON(15), 12, GFLAGS),
GATE(0, "aclk_peri_src_dpll", "dpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(4), 1, GFLAGS),
+ RV1108_CLKGATE_CON(4), 1, GFLAGS),
GATE(0, "aclk_peri_src_gpll", "gpll", CLK_IGNORE_UNUSED,
- RK1108_CLKGATE_CON(4), 2, GFLAGS),
+ RV1108_CLKGATE_CON(4), 2, GFLAGS),
COMPOSITE(0, "aclk_periph", mux_aclk_peri_src_p, CLK_IGNORE_UNUSED,
- RK1108_CLKSEL_CON(23), 15, 2, MFLAGS, 0, 5, DFLAGS,
- RK1108_CLKGATE_CON(15), 11, GFLAGS),
+ RV1108_CLKSEL_CON(23), 15, 2, MFLAGS, 0, 5, DFLAGS,
+ RV1108_CLKGATE_CON(15), 11, GFLAGS),
COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0,
- RK1108_CLKSEL_CON(25), 8, 2, MFLAGS, 0, 8, DFLAGS,
- RK1108_CLKGATE_CON(5), 0, GFLAGS),
+ RV1108_CLKSEL_CON(25), 8, 2, MFLAGS, 0, 8, DFLAGS,
+ RV1108_CLKGATE_CON(5), 0, GFLAGS),
COMPOSITE_NODIV(0, "sclk_sdio_src", mux_mmc_src_p, 0,
- RK1108_CLKSEL_CON(25), 10, 2, MFLAGS,
- RK1108_CLKGATE_CON(5), 2, GFLAGS),
+ RV1108_CLKSEL_CON(25), 10, 2, MFLAGS,
+ RV1108_CLKGATE_CON(5), 2, GFLAGS),
DIV(SCLK_SDIO, "sclk_sdio", "sclk_sdio_src", 0,
- RK1108_CLKSEL_CON(26), 0, 8, DFLAGS),
+ RV1108_CLKSEL_CON(26), 0, 8, DFLAGS),
COMPOSITE_NODIV(0, "sclk_emmc_src", mux_mmc_src_p, 0,
- RK1108_CLKSEL_CON(25), 12, 2, MFLAGS,
- RK1108_CLKGATE_CON(5), 1, GFLAGS),
+ RV1108_CLKSEL_CON(25), 12, 2, MFLAGS,
+ RV1108_CLKGATE_CON(5), 1, GFLAGS),
DIV(SCLK_EMMC, "sclk_emmc", "sclk_emmc_src", 0,
RK2928_CLKSEL_CON(26), 8, 8, DFLAGS),
- GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_periph", 0, RK1108_CLKGATE_CON(15), 0, GFLAGS),
- GATE(HCLK_SDIO, "hclk_sdio", "hclk_periph", 0, RK1108_CLKGATE_CON(15), 1, GFLAGS),
- GATE(HCLK_EMMC, "hclk_emmc", "hclk_periph", 0, RK1108_CLKGATE_CON(15), 2, GFLAGS),
+ GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_periph", 0, RV1108_CLKGATE_CON(15), 0, GFLAGS),
+ GATE(HCLK_SDIO, "hclk_sdio", "hclk_periph", 0, RV1108_CLKGATE_CON(15), 1, GFLAGS),
+ GATE(HCLK_EMMC, "hclk_emmc", "hclk_periph", 0, RV1108_CLKGATE_CON(15), 2, GFLAGS),
COMPOSITE(SCLK_NANDC, "sclk_nandc", mux_pll_src_2plls_p, 0,
- RK1108_CLKSEL_CON(27), 14, 2, MFLAGS, 8, 5, DFLAGS,
- RK1108_CLKGATE_CON(5), 3, GFLAGS),
- GATE(HCLK_NANDC, "hclk_nandc", "hclk_periph", 0, RK1108_CLKGATE_CON(15), 3, GFLAGS),
+ RV1108_CLKSEL_CON(27), 14, 2, MFLAGS, 8, 5, DFLAGS,
+ RV1108_CLKGATE_CON(5), 3, GFLAGS),
+ GATE(HCLK_NANDC, "hclk_nandc", "hclk_periph", 0, RV1108_CLKGATE_CON(15), 3, GFLAGS),
COMPOSITE(SCLK_SFC, "sclk_sfc", mux_pll_src_2plls_p, 0,
- RK1108_CLKSEL_CON(27), 7, 2, MFLAGS, 0, 7, DFLAGS,
- RK1108_CLKGATE_CON(5), 4, GFLAGS),
- GATE(HCLK_SFC, "hclk_sfc", "hclk_periph", 0, RK1108_CLKGATE_CON(15), 10, GFLAGS),
+ RV1108_CLKSEL_CON(27), 7, 2, MFLAGS, 0, 7, DFLAGS,
+ RV1108_CLKGATE_CON(5), 4, GFLAGS),
+ GATE(HCLK_SFC, "hclk_sfc", "hclk_periph", 0, RV1108_CLKGATE_CON(15), 10, GFLAGS),
COMPOSITE(0, "sclk_macphy_pre", mux_pll_src_apll_gpll_p, 0,
- RK1108_CLKSEL_CON(24), 12, 2, MFLAGS, 0, 5, DFLAGS,
- RK1108_CLKGATE_CON(4), 10, GFLAGS),
+ RV1108_CLKSEL_CON(24), 12, 2, MFLAGS, 0, 5, DFLAGS,
+ RV1108_CLKGATE_CON(4), 10, GFLAGS),
MUX(0, "sclk_macphy", mux_sclk_macphy_p, CLK_SET_RATE_PARENT,
- RK1108_CLKSEL_CON(24), 8, 2, MFLAGS),
- GATE(0, "sclk_macphy_rx", "sclk_macphy", 0, RK1108_CLKGATE_CON(4), 8, GFLAGS),
- GATE(0, "sclk_mac_ref", "sclk_macphy", 0, RK1108_CLKGATE_CON(4), 6, GFLAGS),
- GATE(0, "sclk_mac_refout", "sclk_macphy", 0, RK1108_CLKGATE_CON(4), 7, GFLAGS),
+ RV1108_CLKSEL_CON(24), 8, 2, MFLAGS),
+ GATE(0, "sclk_macphy_rx", "sclk_macphy", 0, RV1108_CLKGATE_CON(4), 8, GFLAGS),
+ GATE(0, "sclk_mac_ref", "sclk_macphy", 0, RV1108_CLKGATE_CON(4), 6, GFLAGS),
+ GATE(0, "sclk_mac_refout", "sclk_macphy", 0, RV1108_CLKGATE_CON(4), 7, GFLAGS),
- MMC(SCLK_SDMMC_DRV, "sdmmc_drv", "sclk_sdmmc", RK1108_SDMMC_CON0, 1),
- MMC(SCLK_SDMMC_SAMPLE, "sdmmc_sample", "sclk_sdmmc", RK1108_SDMMC_CON1, 1),
+ MMC(SCLK_SDMMC_DRV, "sdmmc_drv", "sclk_sdmmc", RV1108_SDMMC_CON0, 1),
+ MMC(SCLK_SDMMC_SAMPLE, "sdmmc_sample", "sclk_sdmmc", RV1108_SDMMC_CON1, 1),
- MMC(SCLK_SDIO_DRV, "sdio_drv", "sclk_sdio", RK1108_SDIO_CON0, 1),
- MMC(SCLK_SDIO_SAMPLE, "sdio_sample", "sclk_sdio", RK1108_SDIO_CON1, 1),
+ MMC(SCLK_SDIO_DRV, "sdio_drv", "sclk_sdio", RV1108_SDIO_CON0, 1),
+ MMC(SCLK_SDIO_SAMPLE, "sdio_sample", "sclk_sdio", RV1108_SDIO_CON1, 1),
- MMC(SCLK_EMMC_DRV, "emmc_drv", "sclk_emmc", RK1108_EMMC_CON0, 1),
- MMC(SCLK_EMMC_SAMPLE, "emmc_sample", "sclk_emmc", RK1108_EMMC_CON1, 1),
+ MMC(SCLK_EMMC_DRV, "emmc_drv", "sclk_emmc", RV1108_EMMC_CON0, 1),
+ MMC(SCLK_EMMC_SAMPLE, "emmc_sample", "sclk_emmc", RV1108_EMMC_CON1, 1),
};
-static const char *const rk1108_critical_clocks[] __initconst = {
+static const char *const rv1108_critical_clocks[] __initconst = {
"aclk_core",
"aclk_bus_src_gpll",
"aclk_periph",
"pclk_periph",
};
-static void __init rk1108_clk_init(struct device_node *np)
+static void __init rv1108_clk_init(struct device_node *np)
{
struct rockchip_clk_provider *ctx;
void __iomem *reg_base;
return;
}
- rockchip_clk_register_plls(ctx, rk1108_pll_clks,
- ARRAY_SIZE(rk1108_pll_clks),
- RK1108_GRF_SOC_STATUS0);
- rockchip_clk_register_branches(ctx, rk1108_clk_branches,
- ARRAY_SIZE(rk1108_clk_branches));
- rockchip_clk_protect_critical(rk1108_critical_clocks,
- ARRAY_SIZE(rk1108_critical_clocks));
+ rockchip_clk_register_plls(ctx, rv1108_pll_clks,
+ ARRAY_SIZE(rv1108_pll_clks),
+ RV1108_GRF_SOC_STATUS0);
+ rockchip_clk_register_branches(ctx, rv1108_clk_branches,
+ ARRAY_SIZE(rv1108_clk_branches));
+ rockchip_clk_protect_critical(rv1108_critical_clocks,
+ ARRAY_SIZE(rv1108_critical_clocks));
rockchip_clk_register_armclk(ctx, ARMCLK, "armclk",
mux_armclk_p, ARRAY_SIZE(mux_armclk_p),
- &rk1108_cpuclk_data, rk1108_cpuclk_rates,
- ARRAY_SIZE(rk1108_cpuclk_rates));
+ &rv1108_cpuclk_data, rv1108_cpuclk_rates,
+ ARRAY_SIZE(rv1108_cpuclk_rates));
- rockchip_register_softrst(np, 13, reg_base + RK1108_SOFTRST_CON(0),
+ rockchip_register_softrst(np, 13, reg_base + RV1108_SOFTRST_CON(0),
ROCKCHIP_SOFTRST_HIWORD_MASK);
- rockchip_register_restart_notifier(ctx, RK1108_GLB_SRST_FST, NULL);
+ rockchip_register_restart_notifier(ctx, RV1108_GLB_SRST_FST, NULL);
rockchip_clk_of_add_provider(np, ctx);
}
-CLK_OF_DECLARE(rk1108_cru, "rockchip,rk1108-cru", rk1108_clk_init);
+CLK_OF_DECLARE(rv1108_cru, "rockchip,rv1108-cru", rv1108_clk_init);
#define HIWORD_UPDATE(val, mask, shift) \
((val) << (shift) | (mask) << ((shift) + 16))
-/* register positions shared by RK1108, RK2928, RK3036, RK3066, RK3188 and RK3228 */
-#define RK1108_PLL_CON(x) ((x) * 0x4)
-#define RK1108_CLKSEL_CON(x) ((x) * 0x4 + 0x60)
-#define RK1108_CLKGATE_CON(x) ((x) * 0x4 + 0x120)
-#define RK1108_SOFTRST_CON(x) ((x) * 0x4 + 0x180)
-#define RK1108_GLB_SRST_FST 0x1c0
-#define RK1108_GLB_SRST_SND 0x1c4
-#define RK1108_MISC_CON 0x1cc
-#define RK1108_SDMMC_CON0 0x1d8
-#define RK1108_SDMMC_CON1 0x1dc
-#define RK1108_SDIO_CON0 0x1e0
-#define RK1108_SDIO_CON1 0x1e4
-#define RK1108_EMMC_CON0 0x1e8
-#define RK1108_EMMC_CON1 0x1ec
+/* register positions shared by RV1108, RK2928, RK3036, RK3066, RK3188 and RK3228 */
+#define RV1108_PLL_CON(x) ((x) * 0x4)
+#define RV1108_CLKSEL_CON(x) ((x) * 0x4 + 0x60)
+#define RV1108_CLKGATE_CON(x) ((x) * 0x4 + 0x120)
+#define RV1108_SOFTRST_CON(x) ((x) * 0x4 + 0x180)
+#define RV1108_GLB_SRST_FST 0x1c0
+#define RV1108_GLB_SRST_SND 0x1c4
+#define RV1108_MISC_CON 0x1cc
+#define RV1108_SDMMC_CON0 0x1d8
+#define RV1108_SDMMC_CON1 0x1dc
+#define RV1108_SDIO_CON0 0x1e0
+#define RV1108_SDIO_CON1 0x1e4
+#define RV1108_EMMC_CON0 0x1e8
+#define RV1108_EMMC_CON1 0x1ec
#define RK2928_PLL_CON(x) ((x) * 0x4)
#define RK2928_MODE_CON 0x40
/* clock derived from apb clk */
clk = clk_register_gate(NULL, "adc_clk", "apb_clk", 0, PERIP1_CLK_ENB,
ADC_CLK_ENB, 0, &_lock);
- clk_register_clkdev(clk, NULL, "adc");
+ clk_register_clkdev(clk, NULL, "d820b000.adc");
clk = clk_register_fixed_factor(NULL, "gpio0_clk", "apb_clk", 0, 1, 1);
clk_register_clkdev(clk, NULL, "f0100000.gpio");
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
default ARM64 && ARCH_SUNXI
+ depends on (ARM64 && ARCH_SUNXI) || COMPILE_TEST
config SUN5I_CCU
bool "Support for the Allwinner sun5i family CCM"
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
default MACH_SUN5I
+ depends on MACH_SUN5I || COMPILE_TEST
config SUN6I_A31_CCU
bool "Support for the Allwinner A31/A31s CCU"
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
default MACH_SUN6I
+ depends on MACH_SUN6I || COMPILE_TEST
config SUN8I_A23_CCU
bool "Support for the Allwinner A23 CCU"
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
default MACH_SUN8I
+ depends on MACH_SUN8I || COMPILE_TEST
config SUN8I_A33_CCU
bool "Support for the Allwinner A33 CCU"
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
default MACH_SUN8I
+ depends on MACH_SUN8I || COMPILE_TEST
config SUN8I_H3_CCU
bool "Support for the Allwinner H3 CCU"
select SUNXI_CCU_NM
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
- default MACH_SUN8I
+ default MACH_SUN8I || (ARM64 && ARCH_SUNXI)
+ depends on MACH_SUN8I || (ARM64 && ARCH_SUNXI) || COMPILE_TEST
config SUN8I_V3S_CCU
bool "Support for the Allwinner V3s CCU"
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
default MACH_SUN8I
+ depends on MACH_SUN8I || COMPILE_TEST
config SUN9I_A80_CCU
bool "Support for the Allwinner A80 CCU"
select SUNXI_CCU_MP
select SUNXI_CCU_PHASE
default MACH_SUN9I
+ depends on MACH_SUN9I || COMPILE_TEST
+
+config SUN8I_R_CCU
+ bool "Support for Allwinner SoCs' PRCM CCUs"
+ select SUNXI_CCU_DIV
+ select SUNXI_CCU_GATE
+ default MACH_SUN8I || (ARCH_SUNXI && ARM64)
endif
obj-$(CONFIG_SUN8I_A33_CCU) += ccu-sun8i-a33.o
obj-$(CONFIG_SUN8I_H3_CCU) += ccu-sun8i-h3.o
obj-$(CONFIG_SUN8I_V3S_CCU) += ccu-sun8i-v3s.o
+obj-$(CONFIG_SUN8I_R_CCU) += ccu-sun8i-r.o
obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80.o
obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80-de.o
obj-$(CONFIG_SUN9I_A80_CCU) += ccu-sun9i-a80-usb.o
static const u8 csi_table[] = { 0, 1, 2, 5, 6 };
static SUNXI_CCU_M_WITH_MUX_TABLE_GATE(csi_clk, "csi",
csi_parents, csi_table,
- 0x134, 0, 5, 24, 2, BIT(31), 0);
+ 0x134, 0, 5, 24, 3, BIT(31), 0);
static SUNXI_CCU_GATE(ve_clk, "ve", "pll-ve",
0x13c, BIT(31), CLK_SET_RATE_PARENT);
BIT(28), /* lock */
CLK_SET_RATE_UNGATE);
-/* TODO: Fix N */
-static SUNXI_CCU_N_WITH_GATE_LOCK(pll_ddr1_clk, "pll-ddr1",
- "osc24M", 0x04c,
- 8, 6, /* N */
- BIT(31), /* gate */
- BIT(28), /* lock */
- CLK_SET_RATE_UNGATE);
+static struct ccu_mult pll_ddr1_clk = {
+ .enable = BIT(31),
+ .lock = BIT(28),
+ .mult = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 6, 0, 12, 0),
+ .common = {
+ .reg = 0x04c,
+ .hw.init = CLK_HW_INIT("pll-ddr1", "osc24M",
+ &ccu_mult_ops,
+ CLK_SET_RATE_UNGATE),
+ },
+};
static const char * const cpux_parents[] = { "osc32k", "osc24M",
"pll-cpux" , "pll-cpux" };
0x06c, BIT(18), 0);
static SUNXI_CCU_GATE(bus_uart3_clk, "bus-uart3", "apb2",
0x06c, BIT(19), 0);
-static SUNXI_CCU_GATE(bus_scr_clk, "bus-scr", "apb2",
+static SUNXI_CCU_GATE(bus_scr0_clk, "bus-scr0", "apb2",
0x06c, BIT(20), 0);
+static SUNXI_CCU_GATE(bus_scr1_clk, "bus-scr1", "apb2",
+ 0x06c, BIT(21), 0);
static SUNXI_CCU_GATE(bus_ephy_clk, "bus-ephy", "ahb1",
0x070, BIT(0), 0);
&bus_uart1_clk.common,
&bus_uart2_clk.common,
&bus_uart3_clk.common,
- &bus_scr_clk.common,
+ &bus_scr0_clk.common,
&bus_ephy_clk.common,
&bus_dbg_clk.common,
&ths_clk.common,
&gpu_clk.common,
};
+static struct ccu_common *sun50i_h5_ccu_clks[] = {
+ &pll_cpux_clk.common,
+ &pll_audio_base_clk.common,
+ &pll_video_clk.common,
+ &pll_ve_clk.common,
+ &pll_ddr_clk.common,
+ &pll_periph0_clk.common,
+ &pll_gpu_clk.common,
+ &pll_periph1_clk.common,
+ &pll_de_clk.common,
+ &cpux_clk.common,
+ &axi_clk.common,
+ &ahb1_clk.common,
+ &apb1_clk.common,
+ &apb2_clk.common,
+ &ahb2_clk.common,
+ &bus_ce_clk.common,
+ &bus_dma_clk.common,
+ &bus_mmc0_clk.common,
+ &bus_mmc1_clk.common,
+ &bus_mmc2_clk.common,
+ &bus_nand_clk.common,
+ &bus_dram_clk.common,
+ &bus_emac_clk.common,
+ &bus_ts_clk.common,
+ &bus_hstimer_clk.common,
+ &bus_spi0_clk.common,
+ &bus_spi1_clk.common,
+ &bus_otg_clk.common,
+ &bus_ehci0_clk.common,
+ &bus_ehci1_clk.common,
+ &bus_ehci2_clk.common,
+ &bus_ehci3_clk.common,
+ &bus_ohci0_clk.common,
+ &bus_ohci1_clk.common,
+ &bus_ohci2_clk.common,
+ &bus_ohci3_clk.common,
+ &bus_ve_clk.common,
+ &bus_tcon0_clk.common,
+ &bus_tcon1_clk.common,
+ &bus_deinterlace_clk.common,
+ &bus_csi_clk.common,
+ &bus_tve_clk.common,
+ &bus_hdmi_clk.common,
+ &bus_de_clk.common,
+ &bus_gpu_clk.common,
+ &bus_msgbox_clk.common,
+ &bus_spinlock_clk.common,
+ &bus_codec_clk.common,
+ &bus_spdif_clk.common,
+ &bus_pio_clk.common,
+ &bus_ths_clk.common,
+ &bus_i2s0_clk.common,
+ &bus_i2s1_clk.common,
+ &bus_i2s2_clk.common,
+ &bus_i2c0_clk.common,
+ &bus_i2c1_clk.common,
+ &bus_i2c2_clk.common,
+ &bus_uart0_clk.common,
+ &bus_uart1_clk.common,
+ &bus_uart2_clk.common,
+ &bus_uart3_clk.common,
+ &bus_scr0_clk.common,
+ &bus_scr1_clk.common,
+ &bus_ephy_clk.common,
+ &bus_dbg_clk.common,
+ &ths_clk.common,
+ &nand_clk.common,
+ &mmc0_clk.common,
+ &mmc1_clk.common,
+ &mmc2_clk.common,
+ &ts_clk.common,
+ &ce_clk.common,
+ &spi0_clk.common,
+ &spi1_clk.common,
+ &i2s0_clk.common,
+ &i2s1_clk.common,
+ &i2s2_clk.common,
+ &spdif_clk.common,
+ &usb_phy0_clk.common,
+ &usb_phy1_clk.common,
+ &usb_phy2_clk.common,
+ &usb_phy3_clk.common,
+ &usb_ohci0_clk.common,
+ &usb_ohci1_clk.common,
+ &usb_ohci2_clk.common,
+ &usb_ohci3_clk.common,
+ &dram_clk.common,
+ &dram_ve_clk.common,
+ &dram_csi_clk.common,
+ &dram_deinterlace_clk.common,
+ &dram_ts_clk.common,
+ &de_clk.common,
+ &tcon_clk.common,
+ &tve_clk.common,
+ &deinterlace_clk.common,
+ &csi_misc_clk.common,
+ &csi_sclk_clk.common,
+ &csi_mclk_clk.common,
+ &ve_clk.common,
+ &ac_dig_clk.common,
+ &avs_clk.common,
+ &hdmi_clk.common,
+ &hdmi_ddc_clk.common,
+ &mbus_clk.common,
+ &gpu_clk.common,
+};
+
/* We hardcode the divider to 4 for now */
static CLK_FIXED_FACTOR(pll_audio_clk, "pll-audio",
"pll-audio-base", 4, 1, CLK_SET_RATE_PARENT);
[CLK_BUS_UART1] = &bus_uart1_clk.common.hw,
[CLK_BUS_UART2] = &bus_uart2_clk.common.hw,
[CLK_BUS_UART3] = &bus_uart3_clk.common.hw,
- [CLK_BUS_SCR] = &bus_scr_clk.common.hw,
+ [CLK_BUS_SCR0] = &bus_scr0_clk.common.hw,
[CLK_BUS_EPHY] = &bus_ephy_clk.common.hw,
[CLK_BUS_DBG] = &bus_dbg_clk.common.hw,
[CLK_THS] = &ths_clk.common.hw,
[CLK_MBUS] = &mbus_clk.common.hw,
[CLK_GPU] = &gpu_clk.common.hw,
},
- .num = CLK_NUMBER,
+ .num = CLK_NUMBER_H3,
+};
+
+static struct clk_hw_onecell_data sun50i_h5_hw_clks = {
+ .hws = {
+ [CLK_PLL_CPUX] = &pll_cpux_clk.common.hw,
+ [CLK_PLL_AUDIO_BASE] = &pll_audio_base_clk.common.hw,
+ [CLK_PLL_AUDIO] = &pll_audio_clk.hw,
+ [CLK_PLL_AUDIO_2X] = &pll_audio_2x_clk.hw,
+ [CLK_PLL_AUDIO_4X] = &pll_audio_4x_clk.hw,
+ [CLK_PLL_AUDIO_8X] = &pll_audio_8x_clk.hw,
+ [CLK_PLL_VIDEO] = &pll_video_clk.common.hw,
+ [CLK_PLL_VE] = &pll_ve_clk.common.hw,
+ [CLK_PLL_DDR] = &pll_ddr_clk.common.hw,
+ [CLK_PLL_PERIPH0] = &pll_periph0_clk.common.hw,
+ [CLK_PLL_PERIPH0_2X] = &pll_periph0_2x_clk.hw,
+ [CLK_PLL_GPU] = &pll_gpu_clk.common.hw,
+ [CLK_PLL_PERIPH1] = &pll_periph1_clk.common.hw,
+ [CLK_PLL_DE] = &pll_de_clk.common.hw,
+ [CLK_CPUX] = &cpux_clk.common.hw,
+ [CLK_AXI] = &axi_clk.common.hw,
+ [CLK_AHB1] = &ahb1_clk.common.hw,
+ [CLK_APB1] = &apb1_clk.common.hw,
+ [CLK_APB2] = &apb2_clk.common.hw,
+ [CLK_AHB2] = &ahb2_clk.common.hw,
+ [CLK_BUS_CE] = &bus_ce_clk.common.hw,
+ [CLK_BUS_DMA] = &bus_dma_clk.common.hw,
+ [CLK_BUS_MMC0] = &bus_mmc0_clk.common.hw,
+ [CLK_BUS_MMC1] = &bus_mmc1_clk.common.hw,
+ [CLK_BUS_MMC2] = &bus_mmc2_clk.common.hw,
+ [CLK_BUS_NAND] = &bus_nand_clk.common.hw,
+ [CLK_BUS_DRAM] = &bus_dram_clk.common.hw,
+ [CLK_BUS_EMAC] = &bus_emac_clk.common.hw,
+ [CLK_BUS_TS] = &bus_ts_clk.common.hw,
+ [CLK_BUS_HSTIMER] = &bus_hstimer_clk.common.hw,
+ [CLK_BUS_SPI0] = &bus_spi0_clk.common.hw,
+ [CLK_BUS_SPI1] = &bus_spi1_clk.common.hw,
+ [CLK_BUS_OTG] = &bus_otg_clk.common.hw,
+ [CLK_BUS_EHCI0] = &bus_ehci0_clk.common.hw,
+ [CLK_BUS_EHCI1] = &bus_ehci1_clk.common.hw,
+ [CLK_BUS_EHCI2] = &bus_ehci2_clk.common.hw,
+ [CLK_BUS_EHCI3] = &bus_ehci3_clk.common.hw,
+ [CLK_BUS_OHCI0] = &bus_ohci0_clk.common.hw,
+ [CLK_BUS_OHCI1] = &bus_ohci1_clk.common.hw,
+ [CLK_BUS_OHCI2] = &bus_ohci2_clk.common.hw,
+ [CLK_BUS_OHCI3] = &bus_ohci3_clk.common.hw,
+ [CLK_BUS_VE] = &bus_ve_clk.common.hw,
+ [CLK_BUS_TCON0] = &bus_tcon0_clk.common.hw,
+ [CLK_BUS_TCON1] = &bus_tcon1_clk.common.hw,
+ [CLK_BUS_DEINTERLACE] = &bus_deinterlace_clk.common.hw,
+ [CLK_BUS_CSI] = &bus_csi_clk.common.hw,
+ [CLK_BUS_TVE] = &bus_tve_clk.common.hw,
+ [CLK_BUS_HDMI] = &bus_hdmi_clk.common.hw,
+ [CLK_BUS_DE] = &bus_de_clk.common.hw,
+ [CLK_BUS_GPU] = &bus_gpu_clk.common.hw,
+ [CLK_BUS_MSGBOX] = &bus_msgbox_clk.common.hw,
+ [CLK_BUS_SPINLOCK] = &bus_spinlock_clk.common.hw,
+ [CLK_BUS_CODEC] = &bus_codec_clk.common.hw,
+ [CLK_BUS_SPDIF] = &bus_spdif_clk.common.hw,
+ [CLK_BUS_PIO] = &bus_pio_clk.common.hw,
+ [CLK_BUS_THS] = &bus_ths_clk.common.hw,
+ [CLK_BUS_I2S0] = &bus_i2s0_clk.common.hw,
+ [CLK_BUS_I2S1] = &bus_i2s1_clk.common.hw,
+ [CLK_BUS_I2S2] = &bus_i2s2_clk.common.hw,
+ [CLK_BUS_I2C0] = &bus_i2c0_clk.common.hw,
+ [CLK_BUS_I2C1] = &bus_i2c1_clk.common.hw,
+ [CLK_BUS_I2C2] = &bus_i2c2_clk.common.hw,
+ [CLK_BUS_UART0] = &bus_uart0_clk.common.hw,
+ [CLK_BUS_UART1] = &bus_uart1_clk.common.hw,
+ [CLK_BUS_UART2] = &bus_uart2_clk.common.hw,
+ [CLK_BUS_UART3] = &bus_uart3_clk.common.hw,
+ [CLK_BUS_SCR0] = &bus_scr0_clk.common.hw,
+ [CLK_BUS_SCR1] = &bus_scr1_clk.common.hw,
+ [CLK_BUS_EPHY] = &bus_ephy_clk.common.hw,
+ [CLK_BUS_DBG] = &bus_dbg_clk.common.hw,
+ [CLK_THS] = &ths_clk.common.hw,
+ [CLK_NAND] = &nand_clk.common.hw,
+ [CLK_MMC0] = &mmc0_clk.common.hw,
+ [CLK_MMC1] = &mmc1_clk.common.hw,
+ [CLK_MMC2] = &mmc2_clk.common.hw,
+ [CLK_TS] = &ts_clk.common.hw,
+ [CLK_CE] = &ce_clk.common.hw,
+ [CLK_SPI0] = &spi0_clk.common.hw,
+ [CLK_SPI1] = &spi1_clk.common.hw,
+ [CLK_I2S0] = &i2s0_clk.common.hw,
+ [CLK_I2S1] = &i2s1_clk.common.hw,
+ [CLK_I2S2] = &i2s2_clk.common.hw,
+ [CLK_SPDIF] = &spdif_clk.common.hw,
+ [CLK_USB_PHY0] = &usb_phy0_clk.common.hw,
+ [CLK_USB_PHY1] = &usb_phy1_clk.common.hw,
+ [CLK_USB_PHY2] = &usb_phy2_clk.common.hw,
+ [CLK_USB_PHY3] = &usb_phy3_clk.common.hw,
+ [CLK_USB_OHCI0] = &usb_ohci0_clk.common.hw,
+ [CLK_USB_OHCI1] = &usb_ohci1_clk.common.hw,
+ [CLK_USB_OHCI2] = &usb_ohci2_clk.common.hw,
+ [CLK_USB_OHCI3] = &usb_ohci3_clk.common.hw,
+ [CLK_DRAM] = &dram_clk.common.hw,
+ [CLK_DRAM_VE] = &dram_ve_clk.common.hw,
+ [CLK_DRAM_CSI] = &dram_csi_clk.common.hw,
+ [CLK_DRAM_DEINTERLACE] = &dram_deinterlace_clk.common.hw,
+ [CLK_DRAM_TS] = &dram_ts_clk.common.hw,
+ [CLK_DE] = &de_clk.common.hw,
+ [CLK_TCON0] = &tcon_clk.common.hw,
+ [CLK_TVE] = &tve_clk.common.hw,
+ [CLK_DEINTERLACE] = &deinterlace_clk.common.hw,
+ [CLK_CSI_MISC] = &csi_misc_clk.common.hw,
+ [CLK_CSI_SCLK] = &csi_sclk_clk.common.hw,
+ [CLK_CSI_MCLK] = &csi_mclk_clk.common.hw,
+ [CLK_VE] = &ve_clk.common.hw,
+ [CLK_AC_DIG] = &ac_dig_clk.common.hw,
+ [CLK_AVS] = &avs_clk.common.hw,
+ [CLK_HDMI] = &hdmi_clk.common.hw,
+ [CLK_HDMI_DDC] = &hdmi_ddc_clk.common.hw,
+ [CLK_MBUS] = &mbus_clk.common.hw,
+ [CLK_GPU] = &gpu_clk.common.hw,
+ },
+ .num = CLK_NUMBER_H5,
};
static struct ccu_reset_map sun8i_h3_ccu_resets[] = {
[RST_BUS_UART1] = { 0x2d8, BIT(17) },
[RST_BUS_UART2] = { 0x2d8, BIT(18) },
[RST_BUS_UART3] = { 0x2d8, BIT(19) },
- [RST_BUS_SCR] = { 0x2d8, BIT(20) },
+ [RST_BUS_SCR0] = { 0x2d8, BIT(20) },
+};
+
+static struct ccu_reset_map sun50i_h5_ccu_resets[] = {
+ [RST_USB_PHY0] = { 0x0cc, BIT(0) },
+ [RST_USB_PHY1] = { 0x0cc, BIT(1) },
+ [RST_USB_PHY2] = { 0x0cc, BIT(2) },
+ [RST_USB_PHY3] = { 0x0cc, BIT(3) },
+
+ [RST_MBUS] = { 0x0fc, BIT(31) },
+
+ [RST_BUS_CE] = { 0x2c0, BIT(5) },
+ [RST_BUS_DMA] = { 0x2c0, BIT(6) },
+ [RST_BUS_MMC0] = { 0x2c0, BIT(8) },
+ [RST_BUS_MMC1] = { 0x2c0, BIT(9) },
+ [RST_BUS_MMC2] = { 0x2c0, BIT(10) },
+ [RST_BUS_NAND] = { 0x2c0, BIT(13) },
+ [RST_BUS_DRAM] = { 0x2c0, BIT(14) },
+ [RST_BUS_EMAC] = { 0x2c0, BIT(17) },
+ [RST_BUS_TS] = { 0x2c0, BIT(18) },
+ [RST_BUS_HSTIMER] = { 0x2c0, BIT(19) },
+ [RST_BUS_SPI0] = { 0x2c0, BIT(20) },
+ [RST_BUS_SPI1] = { 0x2c0, BIT(21) },
+ [RST_BUS_OTG] = { 0x2c0, BIT(23) },
+ [RST_BUS_EHCI0] = { 0x2c0, BIT(24) },
+ [RST_BUS_EHCI1] = { 0x2c0, BIT(25) },
+ [RST_BUS_EHCI2] = { 0x2c0, BIT(26) },
+ [RST_BUS_EHCI3] = { 0x2c0, BIT(27) },
+ [RST_BUS_OHCI0] = { 0x2c0, BIT(28) },
+ [RST_BUS_OHCI1] = { 0x2c0, BIT(29) },
+ [RST_BUS_OHCI2] = { 0x2c0, BIT(30) },
+ [RST_BUS_OHCI3] = { 0x2c0, BIT(31) },
+
+ [RST_BUS_VE] = { 0x2c4, BIT(0) },
+ [RST_BUS_TCON0] = { 0x2c4, BIT(3) },
+ [RST_BUS_TCON1] = { 0x2c4, BIT(4) },
+ [RST_BUS_DEINTERLACE] = { 0x2c4, BIT(5) },
+ [RST_BUS_CSI] = { 0x2c4, BIT(8) },
+ [RST_BUS_TVE] = { 0x2c4, BIT(9) },
+ [RST_BUS_HDMI0] = { 0x2c4, BIT(10) },
+ [RST_BUS_HDMI1] = { 0x2c4, BIT(11) },
+ [RST_BUS_DE] = { 0x2c4, BIT(12) },
+ [RST_BUS_GPU] = { 0x2c4, BIT(20) },
+ [RST_BUS_MSGBOX] = { 0x2c4, BIT(21) },
+ [RST_BUS_SPINLOCK] = { 0x2c4, BIT(22) },
+ [RST_BUS_DBG] = { 0x2c4, BIT(31) },
+
+ [RST_BUS_EPHY] = { 0x2c8, BIT(2) },
+
+ [RST_BUS_CODEC] = { 0x2d0, BIT(0) },
+ [RST_BUS_SPDIF] = { 0x2d0, BIT(1) },
+ [RST_BUS_THS] = { 0x2d0, BIT(8) },
+ [RST_BUS_I2S0] = { 0x2d0, BIT(12) },
+ [RST_BUS_I2S1] = { 0x2d0, BIT(13) },
+ [RST_BUS_I2S2] = { 0x2d0, BIT(14) },
+
+ [RST_BUS_I2C0] = { 0x2d8, BIT(0) },
+ [RST_BUS_I2C1] = { 0x2d8, BIT(1) },
+ [RST_BUS_I2C2] = { 0x2d8, BIT(2) },
+ [RST_BUS_UART0] = { 0x2d8, BIT(16) },
+ [RST_BUS_UART1] = { 0x2d8, BIT(17) },
+ [RST_BUS_UART2] = { 0x2d8, BIT(18) },
+ [RST_BUS_UART3] = { 0x2d8, BIT(19) },
+ [RST_BUS_SCR0] = { 0x2d8, BIT(20) },
+ [RST_BUS_SCR1] = { 0x2d8, BIT(20) },
};
static const struct sunxi_ccu_desc sun8i_h3_ccu_desc = {
.num_resets = ARRAY_SIZE(sun8i_h3_ccu_resets),
};
+static const struct sunxi_ccu_desc sun50i_h5_ccu_desc = {
+ .ccu_clks = sun50i_h5_ccu_clks,
+ .num_ccu_clks = ARRAY_SIZE(sun50i_h5_ccu_clks),
+
+ .hw_clks = &sun50i_h5_hw_clks,
+
+ .resets = sun50i_h5_ccu_resets,
+ .num_resets = ARRAY_SIZE(sun50i_h5_ccu_resets),
+};
+
static struct ccu_mux_nb sun8i_h3_cpu_nb = {
.common = &cpux_clk.common,
.cm = &cpux_clk.mux,
.bypass_index = 1, /* index of 24 MHz oscillator */
};
-static void __init sun8i_h3_ccu_setup(struct device_node *node)
+static void __init sunxi_h3_h5_ccu_init(struct device_node *node,
+ const struct sunxi_ccu_desc *desc)
{
void __iomem *reg;
u32 val;
val &= ~GENMASK(19, 16);
writel(val | (3 << 16), reg + SUN8I_H3_PLL_AUDIO_REG);
- sunxi_ccu_probe(node, reg, &sun8i_h3_ccu_desc);
+ sunxi_ccu_probe(node, reg, desc);
ccu_mux_notifier_register(pll_cpux_clk.common.hw.clk,
&sun8i_h3_cpu_nb);
}
+
+static void __init sun8i_h3_ccu_setup(struct device_node *node)
+{
+ sunxi_h3_h5_ccu_init(node, &sun8i_h3_ccu_desc);
+}
CLK_OF_DECLARE(sun8i_h3_ccu, "allwinner,sun8i-h3-ccu",
sun8i_h3_ccu_setup);
+
+static void __init sun50i_h5_ccu_setup(struct device_node *node)
+{
+ sunxi_h3_h5_ccu_init(node, &sun50i_h5_ccu_desc);
+}
+CLK_OF_DECLARE(sun50i_h5_ccu, "allwinner,sun50i-h5-ccu",
+ sun50i_h5_ccu_setup);
/* And the GPU module clock is exported */
-#define CLK_NUMBER (CLK_GPU + 1)
+#define CLK_NUMBER_H3 (CLK_GPU + 1)
+#define CLK_NUMBER_H5 (CLK_BUS_SCR1 + 1)
#endif /* _CCU_SUN8I_H3_H_ */
--- /dev/null
+/*
+ * Copyright (c) 2016 Icenowy Zheng <icenowy@aosc.xyz>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+
+#include "ccu_common.h"
+#include "ccu_reset.h"
+
+#include "ccu_div.h"
+#include "ccu_gate.h"
+#include "ccu_mp.h"
+#include "ccu_nm.h"
+
+#include "ccu-sun8i-r.h"
+
+static const char * const ar100_parents[] = { "osc32k", "osc24M",
+ "pll-periph0", "iosc" };
+
+static struct ccu_div ar100_clk = {
+ .div = _SUNXI_CCU_DIV_FLAGS(4, 2, CLK_DIVIDER_POWER_OF_TWO),
+
+ .mux = {
+ .shift = 16,
+ .width = 2,
+
+ .variable_prediv = {
+ .index = 2,
+ .shift = 8,
+ .width = 5,
+ },
+ },
+
+ .common = {
+ .reg = 0x00,
+ .features = CCU_FEATURE_VARIABLE_PREDIV,
+ .hw.init = CLK_HW_INIT_PARENTS("ar100",
+ ar100_parents,
+ &ccu_div_ops,
+ 0),
+ },
+};
+
+static CLK_FIXED_FACTOR(ahb0_clk, "ahb0", "ar100", 1, 1, 0);
+
+static struct ccu_div apb0_clk = {
+ .div = _SUNXI_CCU_DIV_FLAGS(0, 2, CLK_DIVIDER_POWER_OF_TWO),
+
+ .common = {
+ .reg = 0x0c,
+ .hw.init = CLK_HW_INIT("apb0",
+ "ahb0",
+ &ccu_div_ops,
+ 0),
+ },
+};
+
+static SUNXI_CCU_GATE(apb0_pio_clk, "apb0-pio", "apb0",
+ 0x28, BIT(0), 0);
+static SUNXI_CCU_GATE(apb0_ir_clk, "apb0-ir", "apb0",
+ 0x28, BIT(1), 0);
+static SUNXI_CCU_GATE(apb0_timer_clk, "apb0-timer", "apb0",
+ 0x28, BIT(2), 0);
+static SUNXI_CCU_GATE(apb0_rsb_clk, "apb0-rsb", "apb0",
+ 0x28, BIT(3), 0);
+static SUNXI_CCU_GATE(apb0_uart_clk, "apb0-uart", "apb0",
+ 0x28, BIT(4), 0);
+static SUNXI_CCU_GATE(apb0_i2c_clk, "apb0-i2c", "apb0",
+ 0x28, BIT(6), 0);
+static SUNXI_CCU_GATE(apb0_twd_clk, "apb0-twd", "apb0",
+ 0x28, BIT(7), 0);
+
+static const char * const r_mod0_default_parents[] = { "osc32k", "osc24M" };
+static SUNXI_CCU_MP_WITH_MUX_GATE(ir_clk, "ir",
+ r_mod0_default_parents, 0x54,
+ 0, 4, /* M */
+ 16, 2, /* P */
+ 24, 2, /* mux */
+ BIT(31), /* gate */
+ 0);
+
+static struct ccu_common *sun8i_h3_r_ccu_clks[] = {
+ &ar100_clk.common,
+ &apb0_clk.common,
+ &apb0_pio_clk.common,
+ &apb0_ir_clk.common,
+ &apb0_timer_clk.common,
+ &apb0_uart_clk.common,
+ &apb0_i2c_clk.common,
+ &apb0_twd_clk.common,
+ &ir_clk.common,
+};
+
+static struct ccu_common *sun50i_a64_r_ccu_clks[] = {
+ &ar100_clk.common,
+ &apb0_clk.common,
+ &apb0_pio_clk.common,
+ &apb0_ir_clk.common,
+ &apb0_timer_clk.common,
+ &apb0_rsb_clk.common,
+ &apb0_uart_clk.common,
+ &apb0_i2c_clk.common,
+ &apb0_twd_clk.common,
+ &ir_clk.common,
+};
+
+static struct clk_hw_onecell_data sun8i_h3_r_hw_clks = {
+ .hws = {
+ [CLK_AR100] = &ar100_clk.common.hw,
+ [CLK_AHB0] = &ahb0_clk.hw,
+ [CLK_APB0] = &apb0_clk.common.hw,
+ [CLK_APB0_PIO] = &apb0_pio_clk.common.hw,
+ [CLK_APB0_IR] = &apb0_ir_clk.common.hw,
+ [CLK_APB0_TIMER] = &apb0_timer_clk.common.hw,
+ [CLK_APB0_UART] = &apb0_uart_clk.common.hw,
+ [CLK_APB0_I2C] = &apb0_i2c_clk.common.hw,
+ [CLK_APB0_TWD] = &apb0_twd_clk.common.hw,
+ [CLK_IR] = &ir_clk.common.hw,
+ },
+ .num = CLK_NUMBER,
+};
+
+static struct clk_hw_onecell_data sun50i_a64_r_hw_clks = {
+ .hws = {
+ [CLK_AR100] = &ar100_clk.common.hw,
+ [CLK_AHB0] = &ahb0_clk.hw,
+ [CLK_APB0] = &apb0_clk.common.hw,
+ [CLK_APB0_PIO] = &apb0_pio_clk.common.hw,
+ [CLK_APB0_IR] = &apb0_ir_clk.common.hw,
+ [CLK_APB0_TIMER] = &apb0_timer_clk.common.hw,
+ [CLK_APB0_RSB] = &apb0_rsb_clk.common.hw,
+ [CLK_APB0_UART] = &apb0_uart_clk.common.hw,
+ [CLK_APB0_I2C] = &apb0_i2c_clk.common.hw,
+ [CLK_APB0_TWD] = &apb0_twd_clk.common.hw,
+ [CLK_IR] = &ir_clk.common.hw,
+ },
+ .num = CLK_NUMBER,
+};
+
+static struct ccu_reset_map sun8i_h3_r_ccu_resets[] = {
+ [RST_APB0_IR] = { 0xb0, BIT(1) },
+ [RST_APB0_TIMER] = { 0xb0, BIT(2) },
+ [RST_APB0_UART] = { 0xb0, BIT(4) },
+ [RST_APB0_I2C] = { 0xb0, BIT(6) },
+};
+
+static struct ccu_reset_map sun50i_a64_r_ccu_resets[] = {
+ [RST_APB0_IR] = { 0xb0, BIT(1) },
+ [RST_APB0_TIMER] = { 0xb0, BIT(2) },
+ [RST_APB0_RSB] = { 0xb0, BIT(3) },
+ [RST_APB0_UART] = { 0xb0, BIT(4) },
+ [RST_APB0_I2C] = { 0xb0, BIT(6) },
+};
+
+static const struct sunxi_ccu_desc sun8i_h3_r_ccu_desc = {
+ .ccu_clks = sun8i_h3_r_ccu_clks,
+ .num_ccu_clks = ARRAY_SIZE(sun8i_h3_r_ccu_clks),
+
+ .hw_clks = &sun8i_h3_r_hw_clks,
+
+ .resets = sun8i_h3_r_ccu_resets,
+ .num_resets = ARRAY_SIZE(sun8i_h3_r_ccu_resets),
+};
+
+static const struct sunxi_ccu_desc sun50i_a64_r_ccu_desc = {
+ .ccu_clks = sun50i_a64_r_ccu_clks,
+ .num_ccu_clks = ARRAY_SIZE(sun50i_a64_r_ccu_clks),
+
+ .hw_clks = &sun50i_a64_r_hw_clks,
+
+ .resets = sun50i_a64_r_ccu_resets,
+ .num_resets = ARRAY_SIZE(sun50i_a64_r_ccu_resets),
+};
+
+static void __init sunxi_r_ccu_init(struct device_node *node,
+ const struct sunxi_ccu_desc *desc)
+{
+ void __iomem *reg;
+
+ reg = of_io_request_and_map(node, 0, of_node_full_name(node));
+ if (IS_ERR(reg)) {
+ pr_err("%s: Could not map the clock registers\n",
+ of_node_full_name(node));
+ return;
+ }
+
+ sunxi_ccu_probe(node, reg, desc);
+}
+
+static void __init sun8i_h3_r_ccu_setup(struct device_node *node)
+{
+ sunxi_r_ccu_init(node, &sun8i_h3_r_ccu_desc);
+}
+CLK_OF_DECLARE(sun8i_h3_r_ccu, "allwinner,sun8i-h3-r-ccu",
+ sun8i_h3_r_ccu_setup);
+
+static void __init sun50i_a64_r_ccu_setup(struct device_node *node)
+{
+ sunxi_r_ccu_init(node, &sun50i_a64_r_ccu_desc);
+}
+CLK_OF_DECLARE(sun50i_a64_r_ccu, "allwinner,sun50i-a64-r-ccu",
+ sun50i_a64_r_ccu_setup);
--- /dev/null
+/*
+ * Copyright 2016 Icenowy <icenowy@aosc.xyz>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _CCU_SUN8I_R_H
+#define _CCU_SUN8I_R_H_
+
+#include <dt-bindings/clock/sun8i-r-ccu.h>
+#include <dt-bindings/reset/sun8i-r-ccu.h>
+
+/* AHB/APB bus clocks are not exported */
+#define CLK_AHB0 1
+#define CLK_APB0 2
+
+#define CLK_NUMBER (CLK_IR + 1)
+
+#endif /* _CCU_SUN8I_R_H */
#define CCU_SUN9I_LOCK_REG 0x09c
-static struct clk_div_table pll_cpux_p_div_table[] = {
- { .val = 0, .div = 1 },
- { .val = 1, .div = 4 },
- { /* Sentinel */ },
-};
-
/*
- * The CPU PLLs are actually NP clocks, but P is /1 or /4, so here we
- * use the NM clocks with a divider table for M.
+ * The CPU PLLs are actually NP clocks, with P being /1 or /4. However
+ * P should only be used for output frequencies lower than 228 MHz.
+ * Neither mainline Linux, U-boot, nor the vendor BSPs use these.
+ *
+ * For now we can just model it as a multiplier clock, and force P to /1.
*/
-static struct ccu_nm pll_c0cpux_clk = {
+#define SUN9I_A80_PLL_C0CPUX_REG 0x000
+#define SUN9I_A80_PLL_C1CPUX_REG 0x004
+
+static struct ccu_mult pll_c0cpux_clk = {
.enable = BIT(31),
.lock = BIT(0),
- .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0),
- .m = _SUNXI_CCU_DIV_TABLE(16, 1, pll_cpux_p_div_table),
+ .mult = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0),
.common = {
- .reg = 0x000,
+ .reg = SUN9I_A80_PLL_C0CPUX_REG,
.lock_reg = CCU_SUN9I_LOCK_REG,
.features = CCU_FEATURE_LOCK_REG,
.hw.init = CLK_HW_INIT("pll-c0cpux", "osc24M",
- &ccu_nm_ops, CLK_SET_RATE_UNGATE),
+ &ccu_mult_ops,
+ CLK_SET_RATE_UNGATE),
},
};
-static struct ccu_nm pll_c1cpux_clk = {
+static struct ccu_mult pll_c1cpux_clk = {
.enable = BIT(31),
.lock = BIT(1),
- .n = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0),
- .m = _SUNXI_CCU_DIV_TABLE(16, 1, pll_cpux_p_div_table),
+ .mult = _SUNXI_CCU_MULT_OFFSET_MIN_MAX(8, 8, 0, 12, 0),
.common = {
- .reg = 0x004,
+ .reg = SUN9I_A80_PLL_C1CPUX_REG,
.lock_reg = CCU_SUN9I_LOCK_REG,
.features = CCU_FEATURE_LOCK_REG,
.hw.init = CLK_HW_INIT("pll-c1cpux", "osc24M",
- &ccu_nm_ops, CLK_SET_RATE_UNGATE),
+ &ccu_mult_ops,
+ CLK_SET_RATE_UNGATE),
},
};
/*
* The Audio PLL has d1, d2 dividers in addition to the usual N, M
* factors. Since we only need 2 frequencies from this PLL: 22.5792 MHz
- * and 24.576 MHz, ignore them for now. Enforce the default for them,
- * which is d1 = 0, d2 = 1.
+ * and 24.576 MHz, ignore them for now. Enforce d1 = 0 and d2 = 0.
*/
#define SUN9I_A80_PLL_AUDIO_REG 0x008
.num_resets = ARRAY_SIZE(sun9i_a80_ccu_resets),
};
+#define SUN9I_A80_PLL_P_SHIFT 16
+#define SUN9I_A80_PLL_N_SHIFT 8
+#define SUN9I_A80_PLL_N_WIDTH 8
+
+static void sun9i_a80_cpu_pll_fixup(void __iomem *reg)
+{
+ u32 val = readl(reg);
+
+ /* bail out if P divider is not used */
+ if (!(val & BIT(SUN9I_A80_PLL_P_SHIFT)))
+ return;
+
+ /*
+ * If P is used, output should be less than 288 MHz. When we
+ * set P to 1, we should also decrease the multiplier so the
+ * output doesn't go out of range, but not too much such that
+ * the multiplier stays above 12, the minimal operation value.
+ *
+ * To keep it simple, set the multiplier to 17, the reset value.
+ */
+ val &= ~GENMASK(SUN9I_A80_PLL_N_SHIFT + SUN9I_A80_PLL_N_WIDTH - 1,
+ SUN9I_A80_PLL_N_SHIFT);
+ val |= 17 << SUN9I_A80_PLL_N_SHIFT;
+
+ /* And clear P */
+ val &= ~BIT(SUN9I_A80_PLL_P_SHIFT);
+
+ writel(val, reg);
+}
+
static int sun9i_a80_ccu_probe(struct platform_device *pdev)
{
struct resource *res;
val &= (BIT(16) & BIT(18));
writel(val, reg + SUN9I_A80_PLL_AUDIO_REG);
+ /* Enforce P = 1 for both CPU cluster PLLs */
+ sun9i_a80_cpu_pll_fixup(reg + SUN9I_A80_PLL_C0CPUX_REG);
+ sun9i_a80_cpu_pll_fixup(reg + SUN9I_A80_PLL_C1CPUX_REG);
+
return sunxi_ccu_probe(pdev->dev.of_node, reg, &sun9i_a80_ccu_desc);
}
ret = clk_hw_register(NULL, hw);
if (ret) {
- pr_err("Couldn't register clock %s\n",
- clk_hw_get_name(hw));
+ pr_err("Couldn't register clock %d - %s\n",
+ i, clk_hw_get_name(hw));
goto err_clk_unreg;
}
}
return ccu_gate_helper_is_enabled(&cg->common, cg->enable);
}
+static unsigned long ccu_gate_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ struct ccu_gate *cg = hw_to_ccu_gate(hw);
+ unsigned long rate = parent_rate;
+
+ if (cg->common.features & CCU_FEATURE_ALL_PREDIV)
+ rate /= cg->common.prediv;
+
+ return rate;
+}
+
+static long ccu_gate_round_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long *prate)
+{
+ struct ccu_gate *cg = hw_to_ccu_gate(hw);
+ int div = 1;
+
+ if (cg->common.features & CCU_FEATURE_ALL_PREDIV)
+ div = cg->common.prediv;
+
+ if (clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT) {
+ unsigned long best_parent = rate;
+
+ if (cg->common.features & CCU_FEATURE_ALL_PREDIV)
+ best_parent *= div;
+ *prate = clk_hw_round_rate(clk_hw_get_parent(hw), best_parent);
+ }
+
+ return *prate / div;
+}
+
+static int ccu_gate_set_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long parent_rate)
+{
+ /*
+ * We must report success but we can do so unconditionally because
+ * clk_factor_round_rate returns values that ensure this call is a
+ * nop.
+ */
+
+ return 0;
+}
+
const struct clk_ops ccu_gate_ops = {
.disable = ccu_gate_disable,
.enable = ccu_gate_enable,
.is_enabled = ccu_gate_is_enabled,
+ .round_rate = ccu_gate_round_rate,
+ .set_rate = ccu_gate_set_rate,
+ .recalc_rate = ccu_gate_recalc_rate,
};
spin_unlock_irqrestore(cm->common.lock, flags);
+ ccu_helper_wait_for_lock(&cm->common, cm->lock);
+
return 0;
}
struct ccu_mult {
u32 enable;
+ u32 lock;
struct ccu_frac_internal frac;
struct ccu_mult_internal mult;
_flags) \
struct ccu_mult _struct = { \
.enable = _gate, \
+ .lock = _lock, \
.mult = _SUNXI_CCU_MULT(_mshift, _mwidth), \
.common = { \
.reg = _reg, \
if (nk->common.features & CCU_FEATURE_FIXED_POSTDIV)
rate *= nk->fixed_post_div;
- _nk.min_n = nk->n.min;
+ _nk.min_n = nk->n.min ?: 1;
_nk.max_n = nk->n.max ?: 1 << nk->n.width;
- _nk.min_k = nk->k.min;
+ _nk.min_k = nk->k.min ?: 1;
_nk.max_k = nk->k.max ?: 1 << nk->k.width;
ccu_nk_find_best(*parent_rate, rate, &_nk);
if (nk->common.features & CCU_FEATURE_FIXED_POSTDIV)
rate = rate * nk->fixed_post_div;
- _nk.min_n = nk->n.min;
+ _nk.min_n = nk->n.min ?: 1;
_nk.max_n = nk->n.max ?: 1 << nk->n.width;
- _nk.min_k = nk->k.min;
+ _nk.min_k = nk->k.min ?: 1;
_nk.max_k = nk->k.max ?: 1 << nk->k.width;
ccu_nk_find_best(parent_rate, rate, &_nk);
struct ccu_nkm *nkm = data;
struct _ccu_nkm _nkm;
- _nkm.min_n = nkm->n.min;
+ _nkm.min_n = nkm->n.min ?: 1;
_nkm.max_n = nkm->n.max ?: 1 << nkm->n.width;
- _nkm.min_k = nkm->k.min;
+ _nkm.min_k = nkm->k.min ?: 1;
_nkm.max_k = nkm->k.max ?: 1 << nkm->k.width;
_nkm.min_m = 1;
_nkm.max_m = nkm->m.max ?: 1 << nkm->m.width;
unsigned long flags;
u32 reg;
- _nkm.min_n = nkm->n.min;
+ _nkm.min_n = nkm->n.min ?: 1;
_nkm.max_n = nkm->n.max ?: 1 << nkm->n.width;
- _nkm.min_k = nkm->k.min;
+ _nkm.min_k = nkm->k.min ?: 1;
_nkm.max_k = nkm->k.max ?: 1 << nkm->k.width;
_nkm.min_m = 1;
_nkm.max_m = nkm->m.max ?: 1 << nkm->m.width;
struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
struct _ccu_nkmp _nkmp;
- _nkmp.min_n = nkmp->n.min;
+ _nkmp.min_n = nkmp->n.min ?: 1;
_nkmp.max_n = nkmp->n.max ?: 1 << nkmp->n.width;
- _nkmp.min_k = nkmp->k.min;
+ _nkmp.min_k = nkmp->k.min ?: 1;
_nkmp.max_k = nkmp->k.max ?: 1 << nkmp->k.width;
_nkmp.min_m = 1;
_nkmp.max_m = nkmp->m.max ?: 1 << nkmp->m.width;
unsigned long flags;
u32 reg;
- _nkmp.min_n = 1;
+ _nkmp.min_n = nkmp->n.min ?: 1;
_nkmp.max_n = nkmp->n.max ?: 1 << nkmp->n.width;
- _nkmp.min_k = 1;
+ _nkmp.min_k = nkmp->k.min ?: 1;
_nkmp.max_k = nkmp->k.max ?: 1 << nkmp->k.width;
_nkmp.min_m = 1;
_nkmp.max_m = nkmp->m.max ?: 1 << nkmp->m.width;
struct ccu_nm *nm = hw_to_ccu_nm(hw);
struct _ccu_nm _nm;
- _nm.min_n = nm->n.min;
+ _nm.min_n = nm->n.min ?: 1;
_nm.max_n = nm->n.max ?: 1 << nm->n.width;
_nm.min_m = 1;
_nm.max_m = nm->m.max ?: 1 << nm->m.width;
else
ccu_frac_helper_disable(&nm->common, &nm->frac);
- _nm.min_n = 1;
+ _nm.min_n = nm->n.min ?: 1;
_nm.max_n = nm->n.max ?: 1 << nm->n.width;
_nm.min_m = 1;
_nm.max_m = nm->m.max ?: 1 << nm->m.width;
tegra_clk_xusb_ssp_src,
tegra_clk_sclk_mux,
tegra_clk_sor_safe,
+ tegra_clk_cec,
+ tegra_clk_ispa,
+ tegra_clk_dmic1,
+ tegra_clk_dmic2,
+ tegra_clk_dmic3,
+ tegra_clk_dmic1_sync_clk,
+ tegra_clk_dmic2_sync_clk,
+ tegra_clk_dmic3_sync_clk,
+ tegra_clk_dmic1_sync_clk_mux,
+ tegra_clk_dmic2_sync_clk_mux,
+ tegra_clk_dmic3_sync_clk_mux,
+ tegra_clk_iqc1,
+ tegra_clk_iqc2,
+ tegra_clk_pll_a_out_adsp,
+ tegra_clk_pll_a_out0_out_adsp,
+ tegra_clk_adsp,
+ tegra_clk_adsp_neon,
tegra_clk_max,
};
gate->enable_refcnt = enable_refcnt;
gate->regs = pregs;
+ if (read_enb(gate) & periph_clk_to_bit(gate))
+ enable_refcnt[clk_num]++;
+
/* Data in .init is copied by clk_register(), so stack variable OK */
gate->hw.init = &init;
};
static struct clk *_tegra_clk_register_periph(const char *name,
- const char **parent_names, int num_parents,
+ const char * const *parent_names, int num_parents,
struct tegra_clk_periph *periph,
void __iomem *clk_base, u32 offset,
unsigned long flags)
}
struct clk *tegra_clk_register_periph(const char *name,
- const char **parent_names, int num_parents,
+ const char * const *parent_names, int num_parents,
struct tegra_clk_periph *periph, void __iomem *clk_base,
u32 offset, unsigned long flags)
{
}
struct clk *tegra_clk_register_periph_nodiv(const char *name,
- const char **parent_names, int num_parents,
+ const char * const *parent_names, int num_parents,
struct tegra_clk_periph *periph, void __iomem *clk_base,
u32 offset)
{
return val & PLLE_BASE_ENABLE ? 1 : 0;
}
-static int clk_pllu_tegra210_enable(struct clk_hw *hw)
-{
- struct tegra_clk_pll *pll = to_clk_pll(hw);
- struct clk_hw *pll_ref = clk_hw_get_parent(hw);
- struct clk_hw *osc = clk_hw_get_parent(pll_ref);
- const struct utmi_clk_param *params = NULL;
- unsigned long flags = 0, input_rate;
- unsigned int i;
- int ret = 0;
- u32 value;
-
- if (!osc) {
- pr_err("%s: failed to get OSC clock\n", __func__);
- return -EINVAL;
- }
-
- input_rate = clk_hw_get_rate(osc);
-
- if (pll->lock)
- spin_lock_irqsave(pll->lock, flags);
-
- _clk_pll_enable(hw);
-
- ret = clk_pll_wait_for_lock(pll);
- if (ret < 0)
- goto out;
-
- for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
- if (input_rate == utmi_parameters[i].osc_frequency) {
- params = &utmi_parameters[i];
- break;
- }
- }
-
- if (!params) {
- pr_err("%s: unexpected input rate %lu Hz\n", __func__,
- input_rate);
- ret = -EINVAL;
- goto out;
- }
-
- value = pll_readl_base(pll);
- value &= ~PLLU_BASE_OVERRIDE;
- pll_writel_base(value, pll);
-
- /* Put PLLU under HW control */
- value = readl_relaxed(pll->clk_base + PLLU_HW_PWRDN_CFG0);
- value |= PLLU_HW_PWRDN_CFG0_IDDQ_PD_INCLUDE |
- PLLU_HW_PWRDN_CFG0_USE_SWITCH_DETECT |
- PLLU_HW_PWRDN_CFG0_USE_LOCKDET;
- value &= ~(PLLU_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL |
- PLLU_HW_PWRDN_CFG0_CLK_SWITCH_SWCTL);
- writel_relaxed(value, pll->clk_base + PLLU_HW_PWRDN_CFG0);
-
- value = readl_relaxed(pll->clk_base + XUSB_PLL_CFG0);
- value &= ~XUSB_PLL_CFG0_PLLU_LOCK_DLY;
- writel_relaxed(value, pll->clk_base + XUSB_PLL_CFG0);
-
- udelay(1);
-
- value = readl_relaxed(pll->clk_base + PLLU_HW_PWRDN_CFG0);
- value |= PLLU_HW_PWRDN_CFG0_SEQ_ENABLE;
- writel_relaxed(value, pll->clk_base + PLLU_HW_PWRDN_CFG0);
-
- udelay(1);
-
- /* Disable PLLU clock branch to UTMIPLL since it uses OSC */
- value = pll_readl_base(pll);
- value &= ~PLLU_BASE_CLKENABLE_USB;
- pll_writel_base(value, pll);
-
- value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
- if (value & UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE) {
- pr_debug("UTMIPLL already enabled\n");
- goto out;
- }
-
- value &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
- writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
- /* Program UTMIP PLL stable and active counts */
- value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG2);
- value &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
- value |= UTMIP_PLL_CFG2_STABLE_COUNT(params->stable_count);
- value &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
- value |= UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(params->active_delay_count);
- value |= UTMIP_PLL_CFG2_PHY_XTAL_CLOCKEN;
- writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG2);
-
- /* Program UTMIP PLL delay and oscillator frequency counts */
- value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
- value &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
- value |= UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(params->enable_delay_count);
- value &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
- value |= UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(params->xtal_freq_count);
- writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG1);
-
- /* Remove power downs from UTMIP PLL control bits */
- value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
- value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
- value |= UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
- writel(value, pll->clk_base + UTMIP_PLL_CFG1);
-
- udelay(1);
-
- /* Enable samplers for SNPS, XUSB_HOST, XUSB_DEV */
- value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG2);
- value |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERUP;
- value |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERUP;
- value |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERUP;
- value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
- value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
- value &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERDOWN;
- writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG2);
-
- /* Setup HW control of UTMIPLL */
- value = readl_relaxed(pll->clk_base + UTMIP_PLL_CFG1);
- value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
- value &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
- writel_relaxed(value, pll->clk_base + UTMIP_PLL_CFG1);
-
- value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
- value |= UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET;
- value &= ~UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL;
- writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
- udelay(1);
-
- value = readl_relaxed(pll->clk_base + XUSB_PLL_CFG0);
- value &= ~XUSB_PLL_CFG0_UTMIPLL_LOCK_DLY;
- writel_relaxed(value, pll->clk_base + XUSB_PLL_CFG0);
-
- udelay(1);
-
- /* Enable HW control of UTMIPLL */
- value = readl_relaxed(pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
- value |= UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE;
- writel_relaxed(value, pll->clk_base + UTMIPLL_HW_PWRDN_CFG0);
-
-out:
- if (pll->lock)
- spin_unlock_irqrestore(pll->lock, flags);
-
- return ret;
-}
-
static const struct clk_ops tegra_clk_plle_tegra210_ops = {
.is_enabled = clk_plle_tegra210_is_enabled,
.enable = clk_plle_tegra210_enable,
.recalc_rate = clk_pll_recalc_rate,
};
-static const struct clk_ops tegra_clk_pllu_tegra210_ops = {
- .is_enabled = clk_pll_is_enabled,
- .enable = clk_pllu_tegra210_enable,
- .disable = clk_pll_disable,
- .recalc_rate = clk_pllre_recalc_rate,
-};
-
struct clk *tegra_clk_register_plle_tegra210(const char *name,
const char *parent_name,
void __iomem *clk_base, unsigned long flags,
return clk;
}
-struct clk *tegra_clk_register_pllu_tegra210(const char *name,
- const char *parent_name, void __iomem *clk_base,
- unsigned long flags, struct tegra_clk_pll_params *pll_params,
- spinlock_t *lock)
-{
- struct tegra_clk_pll *pll;
- struct clk *clk;
-
- pll_params->flags |= TEGRA_PLLU;
-
- pll = _tegra_init_pll(clk_base, NULL, pll_params, lock);
- if (IS_ERR(pll))
- return ERR_CAST(pll);
-
- clk = _tegra_clk_register_pll(pll, name, parent_name, flags,
- &tegra_clk_pllu_tegra210_ops);
- if (IS_ERR(clk))
- kfree(pll);
-
- return clk;
-}
#endif
return err;
}
+const struct clk_ops tegra_clk_super_mux_ops = {
+ .get_parent = clk_super_get_parent,
+ .set_parent = clk_super_set_parent,
+};
+
+static long clk_super_round_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long *parent_rate)
+{
+ struct tegra_clk_super_mux *super = to_clk_super_mux(hw);
+ struct clk_hw *div_hw = &super->frac_div.hw;
+
+ __clk_hw_set_clk(div_hw, hw);
+
+ return super->div_ops->round_rate(div_hw, rate, parent_rate);
+}
+
+static unsigned long clk_super_recalc_rate(struct clk_hw *hw,
+ unsigned long parent_rate)
+{
+ struct tegra_clk_super_mux *super = to_clk_super_mux(hw);
+ struct clk_hw *div_hw = &super->frac_div.hw;
+
+ __clk_hw_set_clk(div_hw, hw);
+
+ return super->div_ops->recalc_rate(div_hw, parent_rate);
+}
+
+static int clk_super_set_rate(struct clk_hw *hw, unsigned long rate,
+ unsigned long parent_rate)
+{
+ struct tegra_clk_super_mux *super = to_clk_super_mux(hw);
+ struct clk_hw *div_hw = &super->frac_div.hw;
+
+ __clk_hw_set_clk(div_hw, hw);
+
+ return super->div_ops->set_rate(div_hw, rate, parent_rate);
+}
+
const struct clk_ops tegra_clk_super_ops = {
.get_parent = clk_super_get_parent,
.set_parent = clk_super_set_parent,
+ .set_rate = clk_super_set_rate,
+ .round_rate = clk_super_round_rate,
+ .recalc_rate = clk_super_recalc_rate,
};
struct clk *tegra_clk_register_super_mux(const char *name,
struct clk_init_data init;
super = kzalloc(sizeof(*super), GFP_KERNEL);
- if (!super) {
- pr_err("%s: could not allocate super clk\n", __func__);
+ if (!super)
return ERR_PTR(-ENOMEM);
- }
init.name = name;
- init.ops = &tegra_clk_super_ops;
+ init.ops = &tegra_clk_super_mux_ops;
init.flags = flags;
init.parent_names = parent_names;
init.num_parents = num_parents;
return clk;
}
+
+struct clk *tegra_clk_register_super_clk(const char *name,
+ const char * const *parent_names, u8 num_parents,
+ unsigned long flags, void __iomem *reg, u8 clk_super_flags,
+ spinlock_t *lock)
+{
+ struct tegra_clk_super_mux *super;
+ struct clk *clk;
+ struct clk_init_data init;
+
+ super = kzalloc(sizeof(*super), GFP_KERNEL);
+ if (!super)
+ return ERR_PTR(-ENOMEM);
+
+ init.name = name;
+ init.ops = &tegra_clk_super_ops;
+ init.flags = flags;
+ init.parent_names = parent_names;
+ init.num_parents = num_parents;
+
+ super->reg = reg;
+ super->lock = lock;
+ super->width = 4;
+ super->flags = clk_super_flags;
+ super->frac_div.reg = reg + 4;
+ super->frac_div.shift = 16;
+ super->frac_div.width = 8;
+ super->frac_div.frac_width = 1;
+ super->frac_div.lock = lock;
+ super->div_ops = &tegra_clk_frac_div_ops;
+
+ /* Data in .init is copied by clk_register(), so stack variable OK */
+ super->hw.init = &init;
+
+ clk = clk_register(NULL, &super->hw);
+ if (IS_ERR(clk))
+ kfree(super);
+
+ return clk;
+}
#define AUDIO_SYNC_CLK_I2S3 0x4ac
#define AUDIO_SYNC_CLK_I2S4 0x4b0
#define AUDIO_SYNC_CLK_SPDIF 0x4b4
+#define AUDIO_SYNC_CLK_DMIC1 0x560
+#define AUDIO_SYNC_CLK_DMIC2 0x564
+#define AUDIO_SYNC_CLK_DMIC3 0x6b8
#define AUDIO_SYNC_DOUBLER 0x49c
static DEFINE_SPINLOCK(clk_doubler_lock);
-static const char *mux_audio_sync_clk[] = { "spdif_in_sync", "i2s0_sync",
- "i2s1_sync", "i2s2_sync", "i2s3_sync", "i2s4_sync", "vimclk_sync",
+static const char * const mux_audio_sync_clk[] = { "spdif_in_sync",
+ "i2s0_sync", "i2s1_sync", "i2s2_sync", "i2s3_sync", "i2s4_sync",
+ "pll_a_out0", "vimclk_sync",
+};
+
+static const char * const mux_dmic_sync_clk[] = { "unused", "i2s0_sync",
+ "i2s1_sync", "i2s2_sync", "i2s3_sync", "i2s4_sync", "pll_a_out0",
+ "vimclk_sync",
};
static struct tegra_sync_source_initdata sync_source_clks[] __initdata = {
AUDIO(spdif, AUDIO_SYNC_CLK_SPDIF),
};
+static struct tegra_audio_clk_initdata dmic_clks[] = {
+ AUDIO(dmic1_sync_clk, AUDIO_SYNC_CLK_DMIC1),
+ AUDIO(dmic2_sync_clk, AUDIO_SYNC_CLK_DMIC2),
+ AUDIO(dmic3_sync_clk, AUDIO_SYNC_CLK_DMIC3),
+};
+
static struct tegra_audio2x_clk_initdata audio2x_clks[] = {
AUDIO2X(audio0, 113, 24),
AUDIO2X(audio1, 114, 25),
AUDIO2X(spdif, 118, 29),
};
+static void __init tegra_audio_sync_clk_init(void __iomem *clk_base,
+ struct tegra_clk *tegra_clks,
+ struct tegra_audio_clk_initdata *sync,
+ int num_sync_clks,
+ const char * const *mux_names,
+ int num_mux_inputs)
+{
+ struct clk *clk;
+ struct clk **dt_clk;
+ struct tegra_audio_clk_initdata *data;
+ int i;
+
+ for (i = 0, data = sync; i < num_sync_clks; i++, data++) {
+ dt_clk = tegra_lookup_dt_id(data->mux_clk_id, tegra_clks);
+ if (!dt_clk)
+ continue;
+
+ clk = clk_register_mux(NULL, data->mux_name, mux_names,
+ num_mux_inputs,
+ CLK_SET_RATE_NO_REPARENT,
+ clk_base + data->offset, 0, 3, 0,
+ NULL);
+ *dt_clk = clk;
+
+ dt_clk = tegra_lookup_dt_id(data->gate_clk_id, tegra_clks);
+ if (!dt_clk)
+ continue;
+
+ clk = clk_register_gate(NULL, data->gate_name, data->mux_name,
+ 0, clk_base + data->offset, 4,
+ CLK_GATE_SET_TO_DISABLE, NULL);
+ *dt_clk = clk;
+ }
+}
+
void __init tegra_audio_clk_init(void __iomem *clk_base,
void __iomem *pmc_base, struct tegra_clk *tegra_clks,
struct tegra_audio_clk_info *audio_info,
*dt_clk = clk;
}
- for (i = 0; i < ARRAY_SIZE(audio_clks); i++) {
- struct tegra_audio_clk_initdata *data;
+ tegra_audio_sync_clk_init(clk_base, tegra_clks, audio_clks,
+ ARRAY_SIZE(audio_clks), mux_audio_sync_clk,
+ ARRAY_SIZE(mux_audio_sync_clk));
- data = &audio_clks[i];
- dt_clk = tegra_lookup_dt_id(data->mux_clk_id, tegra_clks);
+ /* make sure the DMIC sync clocks have a valid parent */
+ for (i = 0; i < ARRAY_SIZE(dmic_clks); i++)
+ writel_relaxed(1, clk_base + dmic_clks[i].offset);
- if (!dt_clk)
- continue;
- clk = clk_register_mux(NULL, data->mux_name, mux_audio_sync_clk,
- ARRAY_SIZE(mux_audio_sync_clk),
- CLK_SET_RATE_NO_REPARENT,
- clk_base + data->offset, 0, 3, 0,
- NULL);
- *dt_clk = clk;
-
- dt_clk = tegra_lookup_dt_id(data->gate_clk_id, tegra_clks);
- if (!dt_clk)
- continue;
-
- clk = clk_register_gate(NULL, data->gate_name, data->mux_name,
- 0, clk_base + data->offset, 4,
- CLK_GATE_SET_TO_DISABLE, NULL);
- *dt_clk = clk;
- }
+ tegra_audio_sync_clk_init(clk_base, tegra_clks, dmic_clks,
+ ARRAY_SIZE(dmic_clks), mux_dmic_sync_clk,
+ ARRAY_SIZE(mux_dmic_sync_clk));
for (i = 0; i < ARRAY_SIZE(audio2x_clks); i++) {
struct tegra_audio2x_clk_initdata *data;
#define CLK_SOURCE_TSECB 0x6d8
#define CLK_SOURCE_MAUD 0x6d4
#define CLK_SOURCE_USB2_HSIC_TRK 0x6cc
+#define CLK_SOURCE_DMIC1 0x64c
+#define CLK_SOURCE_DMIC2 0x650
+#define CLK_SOURCE_DMIC3 0x6bc
#define MASK(x) (BIT(x) - 1)
0, TEGRA_PERIPH_NO_GATE, _clk_id,\
_parents##_idx, 0, _lock)
+#define MUX8_NOGATE(_name, _parents, _offset, _clk_id) \
+ TEGRA_INIT_DATA_TABLE(_name, NULL, NULL, _parents, _offset, \
+ 29, MASK(3), 0, 0, 8, 1, TEGRA_DIVIDER_ROUND_UP,\
+ 0, TEGRA_PERIPH_NO_GATE, _clk_id,\
+ _parents##_idx, 0, NULL)
+
#define INT(_name, _parents, _offset, \
_clk_num, _gate_flags, _clk_id) \
TEGRA_INIT_DATA_TABLE(_name, NULL, NULL, _parents, _offset,\
};
#define mux_clkm_plldp_sor0lvds_idx NULL
+static const char * const mux_dmic1[] = {
+ "pll_a_out0", "dmic1_sync_clk", "pll_p", "clk_m"
+};
+#define mux_dmic1_idx NULL
+
+static const char * const mux_dmic2[] = {
+ "pll_a_out0", "dmic2_sync_clk", "pll_p", "clk_m"
+};
+#define mux_dmic2_idx NULL
+
+static const char * const mux_dmic3[] = {
+ "pll_a_out0", "dmic3_sync_clk", "pll_p", "clk_m"
+};
+#define mux_dmic3_idx NULL
+
static struct tegra_periph_init_data periph_clks[] = {
AUDIO("d_audio", CLK_SOURCE_D_AUDIO, 106, TEGRA_PERIPH_ON_APB, tegra_clk_d_audio),
AUDIO("dam0", CLK_SOURCE_DAM0, 108, TEGRA_PERIPH_ON_APB, tegra_clk_dam0),
MUX8("soc_therm", mux_clkm_pllc_pllp_plla, CLK_SOURCE_SOC_THERM, 78, TEGRA_PERIPH_ON_APB, tegra_clk_soc_therm_8),
MUX8("vi_sensor", mux_pllm_pllc2_c_c3_pllp_plla, CLK_SOURCE_VI_SENSOR, 164, TEGRA_PERIPH_NO_RESET, tegra_clk_vi_sensor_8),
MUX8("isp", mux_pllm_pllc_pllp_plla_clkm_pllc4, CLK_SOURCE_ISP, 23, TEGRA_PERIPH_ON_APB, tegra_clk_isp_8),
- MUX8("isp", mux_pllc_pllp_plla1_pllc2_c3_clkm_pllc4, CLK_SOURCE_ISP, 23, TEGRA_PERIPH_ON_APB, tegra_clk_isp_9),
+ MUX8_NOGATE("isp", mux_pllc_pllp_plla1_pllc2_c3_clkm_pllc4, CLK_SOURCE_ISP, tegra_clk_isp_9),
MUX8("entropy", mux_pllp_clkm1, CLK_SOURCE_ENTROPY, 149, 0, tegra_clk_entropy),
MUX8("entropy", mux_pllp_clkm_clk32_plle, CLK_SOURCE_ENTROPY, 149, 0, tegra_clk_entropy_8),
MUX8("hdmi_audio", mux_pllp3_pllc_clkm, CLK_SOURCE_HDMI_AUDIO, 176, TEGRA_PERIPH_NO_RESET, tegra_clk_hdmi_audio),
MUX("uartape", mux_pllp_pllc_clkm, CLK_SOURCE_UARTAPE, 212, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_uartape),
MUX8("tsecb", mux_pllp_pllc2_c_c3_clkm, CLK_SOURCE_TSECB, 206, 0, tegra_clk_tsecb),
MUX8("maud", mux_pllp_pllp_out3_clkm_clk32k_plla, CLK_SOURCE_MAUD, 202, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_maud),
+ MUX8("dmic1", mux_dmic1, CLK_SOURCE_DMIC1, 161, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_dmic1),
+ MUX8("dmic2", mux_dmic2, CLK_SOURCE_DMIC2, 162, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_dmic2),
+ MUX8("dmic3", mux_dmic3, CLK_SOURCE_DMIC3, 197, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_dmic3),
};
static struct tegra_periph_init_data gate_clks[] = {
GATE("usb2", "clk_m", 58, 0, tegra_clk_usb2, 0),
GATE("usb3", "clk_m", 59, 0, tegra_clk_usb3, 0),
GATE("csi", "pll_p_out3", 52, 0, tegra_clk_csi, 0),
- GATE("afi", "clk_m", 72, 0, tegra_clk_afi, 0),
+ GATE("afi", "mselect", 72, 0, tegra_clk_afi, 0),
GATE("csus", "clk_m", 92, TEGRA_PERIPH_NO_RESET, tegra_clk_csus, 0),
GATE("dds", "clk_m", 150, TEGRA_PERIPH_ON_APB, tegra_clk_dds, 0),
GATE("dp2", "clk_m", 152, TEGRA_PERIPH_ON_APB, tegra_clk_dp2, 0),
GATE("xusb_dev", "xusb_dev_src", 95, 0, tegra_clk_xusb_dev, 0),
GATE("emc", "emc_mux", 57, 0, tegra_clk_emc, CLK_IGNORE_UNUSED),
GATE("sata_cold", "clk_m", 129, TEGRA_PERIPH_ON_APB, tegra_clk_sata_cold, 0),
- GATE("ispb", "clk_m", 3, 0, tegra_clk_ispb, 0),
+ GATE("ispa", "isp", 23, 0, tegra_clk_ispa, 0),
+ GATE("ispb", "isp", 3, 0, tegra_clk_ispb, 0),
GATE("vim2_clk", "clk_m", 11, 0, tegra_clk_vim2_clk, 0),
GATE("pcie", "clk_m", 70, 0, tegra_clk_pcie, 0),
GATE("gpu", "pll_ref", 184, 0, tegra_clk_gpu, 0),
GATE("pll_p_out_cpu", "pll_p", 223, 0, tegra_clk_pll_p_out_cpu, 0),
GATE("pll_p_out_adsp", "pll_p", 187, 0, tegra_clk_pll_p_out_adsp, 0),
GATE("apb2ape", "clk_m", 107, 0, tegra_clk_apb2ape, 0),
+ GATE("cec", "pclk", 136, 0, tegra_clk_cec, 0),
+ GATE("iqc1", "clk_m", 221, 0, tegra_clk_iqc1, 0),
+ GATE("iqc2", "clk_m", 220, 0, tegra_clk_iqc1, 0),
+ GATE("pll_a_out_adsp", "pll_a", 188, 0, tegra_clk_pll_a_out_adsp, 0),
+ GATE("pll_a_out0_out_adsp", "pll_a", 188, 0, tegra_clk_pll_a_out0_out_adsp, 0),
+ GATE("adsp", "aclk", 199, 0, tegra_clk_adsp, 0),
+ GATE("adsp_neon", "aclk", 218, 0, tegra_clk_adsp_neon, 0),
};
static struct tegra_periph_init_data div_clks[] = {
continue;
clk = clk_register_mux(NULL, data->mux_name, data->parents,
- data->num_parents, CLK_SET_RATE_NO_REPARENT,
+ data->num_parents,
+ CLK_SET_RATE_NO_REPARENT | CLK_SET_RATE_PARENT,
pmc_base + PMC_CLK_OUT_CNTRL, data->mux_shift,
3, 0, &clk_out_lock);
*dt_clk = clk;
continue;
clk = clk_register_gate(NULL, data->gate_name, data->mux_name,
- 0, pmc_base + PMC_CLK_OUT_CNTRL,
+ CLK_SET_RATE_PARENT,
+ pmc_base + PMC_CLK_OUT_CNTRL,
data->gate_shift, 0, &clk_out_lock);
*dt_clk = clk;
clk_register_clkdev(clk, data->dev_name, data->gate_name);
[tegra_clk_clk_out_3_mux] = { .dt_id = TEGRA114_CLK_CLK_OUT_3_MUX, .present = true },
[tegra_clk_dsia_mux] = { .dt_id = TEGRA114_CLK_DSIA_MUX, .present = true },
[tegra_clk_dsib_mux] = { .dt_id = TEGRA114_CLK_DSIB_MUX, .present = true },
+ [tegra_clk_cec] = { .dt_id = TEGRA114_CLK_CEC, .present = true },
};
static struct tegra_devclk devclks[] __initdata = {
[tegra_clk_clk_out_1_mux] = { .dt_id = TEGRA124_CLK_CLK_OUT_1_MUX, .present = true },
[tegra_clk_clk_out_2_mux] = { .dt_id = TEGRA124_CLK_CLK_OUT_2_MUX, .present = true },
[tegra_clk_clk_out_3_mux] = { .dt_id = TEGRA124_CLK_CLK_OUT_3_MUX, .present = true },
+ [tegra_clk_cec] = { .dt_id = TEGRA124_CLK_CEC, .present = true },
};
static struct tegra_devclk devclks[] __initdata = {
#include <linux/export.h>
#include <linux/clk/tegra.h>
#include <dt-bindings/clock/tegra210-car.h>
+#include <dt-bindings/reset/tegra210-car.h>
+#include <linux/iopoll.h>
#include "clk.h"
#include "clk-id.h"
#define PMC_PLLM_WB0_OVERRIDE 0x1dc
#define PMC_PLLM_WB0_OVERRIDE_2 0x2b0
+#define UTMIP_PLL_CFG2 0x488
+#define UTMIP_PLL_CFG2_STABLE_COUNT(x) (((x) & 0xfff) << 6)
+#define UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(x) (((x) & 0x3f) << 18)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN BIT(0)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERUP BIT(1)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN BIT(2)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERUP BIT(3)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERDOWN BIT(4)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_C_POWERUP BIT(5)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERDOWN BIT(24)
+#define UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERUP BIT(25)
+
+#define UTMIP_PLL_CFG1 0x484
+#define UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(x) (((x) & 0x1f) << 27)
+#define UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(x) (((x) & 0xfff) << 0)
+#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERUP BIT(17)
+#define UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN BIT(16)
+#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP BIT(15)
+#define UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN BIT(14)
+#define UTMIP_PLL_CFG1_FORCE_PLL_ACTIVE_POWERDOWN BIT(12)
+
#define SATA_PLL_CFG0 0x490
#define SATA_PLL_CFG0_PADPLL_RESET_SWCTL BIT(0)
#define SATA_PLL_CFG0_PADPLL_USE_LOCKDET BIT(2)
+#define SATA_PLL_CFG0_SATA_SEQ_IN_SWCTL BIT(4)
+#define SATA_PLL_CFG0_SATA_SEQ_RESET_INPUT_VALUE BIT(5)
+#define SATA_PLL_CFG0_SATA_SEQ_LANE_PD_INPUT_VALUE BIT(6)
+#define SATA_PLL_CFG0_SATA_SEQ_PADPLL_PD_INPUT_VALUE BIT(7)
+
#define SATA_PLL_CFG0_PADPLL_SLEEP_IDDQ BIT(13)
#define SATA_PLL_CFG0_SEQ_ENABLE BIT(24)
#define CLK_M_DIVISOR_SHIFT 2
#define CLK_M_DIVISOR_MASK 0x3
+#define RST_DFLL_DVCO 0x2f4
+#define DVFS_DFLL_RESET_SHIFT 0
+
+#define CLK_RST_CONTROLLER_RST_DEV_Y_SET 0x2a8
+#define CLK_RST_CONTROLLER_RST_DEV_Y_CLR 0x2ac
+
/*
* SDM fractional divisor is 16-bit 2's complement signed number within
* (-2^12 ... 2^12-1) range. Represented in PLL data structure as unsigned
}
EXPORT_SYMBOL_GPL(tegra210_sata_pll_hw_sequence_start);
+void tegra210_set_sata_pll_seq_sw(bool state)
+{
+ u32 val;
+
+ val = readl_relaxed(clk_base + SATA_PLL_CFG0);
+ if (state) {
+ val |= SATA_PLL_CFG0_SATA_SEQ_IN_SWCTL;
+ val |= SATA_PLL_CFG0_SATA_SEQ_RESET_INPUT_VALUE;
+ val |= SATA_PLL_CFG0_SATA_SEQ_LANE_PD_INPUT_VALUE;
+ val |= SATA_PLL_CFG0_SATA_SEQ_PADPLL_PD_INPUT_VALUE;
+ } else {
+ val &= ~SATA_PLL_CFG0_SATA_SEQ_IN_SWCTL;
+ val &= ~SATA_PLL_CFG0_SATA_SEQ_RESET_INPUT_VALUE;
+ val &= ~SATA_PLL_CFG0_SATA_SEQ_LANE_PD_INPUT_VALUE;
+ val &= ~SATA_PLL_CFG0_SATA_SEQ_PADPLL_PD_INPUT_VALUE;
+ }
+ writel_relaxed(val, clk_base + SATA_PLL_CFG0);
+}
+EXPORT_SYMBOL_GPL(tegra210_set_sata_pll_seq_sw);
+
static inline void _pll_misc_chk_default(void __iomem *base,
struct tegra_clk_pll_params *params,
u8 misc_num, u32 default_val, u32 mask)
{
pllcx->params->defaults_set = true;
- if (readl_relaxed(clk_base + pllcx->params->base_reg) &
- PLL_ENABLE) {
+ if (readl_relaxed(clk_base + pllcx->params->base_reg) & PLL_ENABLE) {
/* PLL is ON: only check if defaults already set */
pllcx_check_defaults(pllcx->params);
- pr_warn("%s already enabled. Postponing set full defaults\n",
- name);
+ if (!pllcx->params->defaults_set)
+ pr_warn("%s already enabled. Postponing set full defaults\n",
+ name);
return;
}
if (readl_relaxed(clk_base + plld->params->base_reg) &
PLL_ENABLE) {
- pr_warn("PLL_D already enabled. Postponing set full defaults\n");
/*
* PLL is ON: check if defaults already set, then set those
_pll_misc_chk_default(clk_base, plld->params, 0, val,
~mask & PLLD_MISC0_WRITE_MASK);
+ if (!plld->params->defaults_set)
+ pr_warn("PLL_D already enabled. Postponing set full defaults\n");
+
/* Enable lock detect */
mask = PLLD_MISC0_LOCK_ENABLE | PLLD_MISC0_LOCK_OVERRIDE;
val = readl_relaxed(clk_base + plld->params->ext_misc_reg[0]);
val |= step_b << PLLX_MISC2_DYNRAMP_STEPB_SHIFT;
if (readl_relaxed(clk_base + pllx->params->base_reg) & PLL_ENABLE) {
- pr_warn("PLL_X already enabled. Postponing set full defaults\n");
/*
* PLL is ON: check if defaults already set, then set those
*/
pllx_check_defaults(pllx);
+ if (!pllx->params->defaults_set)
+ pr_warn("PLL_X already enabled. Postponing set full defaults\n");
/* Configure dyn ramp, disable lock override */
writel_relaxed(val, clk_base + pllx->params->ext_misc_reg[2]);
pllmb->params->defaults_set = true;
if (val & PLL_ENABLE) {
- pr_warn("PLL_MB already enabled. Postponing set full defaults\n");
/*
* PLL is ON: check if defaults already set, then set those
_pll_misc_chk_default(clk_base, pllmb->params, 0, val,
~mask & PLLMB_MISC1_WRITE_MASK);
+ if (!pllmb->params->defaults_set)
+ pr_warn("PLL_MB already enabled. Postponing set full defaults\n");
/* Enable lock detect */
val = readl_relaxed(clk_base + pllmb->params->ext_misc_reg[0]);
val &= ~mask;
pllp->params->defaults_set = true;
if (val & PLL_ENABLE) {
- pr_warn("PLL_P already enabled. Postponing set full defaults\n");
/*
* PLL is ON: check if defaults already set, then set those
* that can be updated in flight.
*/
pllp_check_defaults(pllp, true);
+ if (!pllp->params->defaults_set)
+ pr_warn("PLL_P already enabled. Postponing set full defaults\n");
/* Enable lock detect */
val = readl_relaxed(clk_base + pllp->params->ext_misc_reg[0]);
* Both VCO and post-divider output rates are fixed at 480MHz and 240MHz,
* respectively.
*/
-static void pllu_check_defaults(struct tegra_clk_pll *pll, bool hw_control)
+static void pllu_check_defaults(struct tegra_clk_pll_params *params,
+ bool hw_control)
{
u32 val, mask;
/* Ignore lock enable (will be set) and IDDQ if under h/w control */
val = PLLU_MISC0_DEFAULT_VALUE & (~PLLU_MISC0_IDDQ);
mask = PLLU_MISC0_LOCK_ENABLE | (hw_control ? PLLU_MISC0_IDDQ : 0);
- _pll_misc_chk_default(clk_base, pll->params, 0, val,
+ _pll_misc_chk_default(clk_base, params, 0, val,
~mask & PLLU_MISC0_WRITE_MASK);
val = PLLU_MISC1_DEFAULT_VALUE;
mask = PLLU_MISC1_LOCK_OVERRIDE;
- _pll_misc_chk_default(clk_base, pll->params, 1, val,
+ _pll_misc_chk_default(clk_base, params, 1, val,
~mask & PLLU_MISC1_WRITE_MASK);
}
-static void tegra210_pllu_set_defaults(struct tegra_clk_pll *pllu)
+static void tegra210_pllu_set_defaults(struct tegra_clk_pll_params *pllu)
{
- u32 val = readl_relaxed(clk_base + pllu->params->base_reg);
+ u32 val = readl_relaxed(clk_base + pllu->base_reg);
- pllu->params->defaults_set = true;
+ pllu->defaults_set = true;
if (val & PLL_ENABLE) {
- pr_warn("PLL_U already enabled. Postponing set full defaults\n");
/*
* PLL is ON: check if defaults already set, then set those
* that can be updated in flight.
*/
pllu_check_defaults(pllu, false);
+ if (!pllu->defaults_set)
+ pr_warn("PLL_U already enabled. Postponing set full defaults\n");
/* Enable lock detect */
- val = readl_relaxed(clk_base + pllu->params->ext_misc_reg[0]);
+ val = readl_relaxed(clk_base + pllu->ext_misc_reg[0]);
val &= ~PLLU_MISC0_LOCK_ENABLE;
val |= PLLU_MISC0_DEFAULT_VALUE & PLLU_MISC0_LOCK_ENABLE;
- writel_relaxed(val, clk_base + pllu->params->ext_misc_reg[0]);
+ writel_relaxed(val, clk_base + pllu->ext_misc_reg[0]);
- val = readl_relaxed(clk_base + pllu->params->ext_misc_reg[1]);
+ val = readl_relaxed(clk_base + pllu->ext_misc_reg[1]);
val &= ~PLLU_MISC1_LOCK_OVERRIDE;
val |= PLLU_MISC1_DEFAULT_VALUE & PLLU_MISC1_LOCK_OVERRIDE;
- writel_relaxed(val, clk_base + pllu->params->ext_misc_reg[1]);
+ writel_relaxed(val, clk_base + pllu->ext_misc_reg[1]);
udelay(1);
return;
/* set IDDQ, enable lock detect */
writel_relaxed(PLLU_MISC0_DEFAULT_VALUE,
- clk_base + pllu->params->ext_misc_reg[0]);
+ clk_base + pllu->ext_misc_reg[0]);
writel_relaxed(PLLU_MISC1_DEFAULT_VALUE,
- clk_base + pllu->params->ext_misc_reg[1]);
+ clk_base + pllu->ext_misc_reg[1]);
udelay(1);
}
cfg->n = p_rate / cf;
cfg->sdm_data = 0;
+ cfg->output_rate = input_rate;
if (params->sdm_ctrl_reg) {
unsigned long rem = p_rate - cf * cfg->n;
/* If ssc is enabled SDM enabled as well, even for integer n */
s -= PLL_SDM_COEFF / 2;
cfg->sdm_data = sdin_din_to_data(s);
}
+ cfg->output_rate *= cfg->n * PLL_SDM_COEFF + PLL_SDM_COEFF/2 +
+ sdin_data_to_din(cfg->sdm_data);
+ cfg->output_rate /= p * cfg->m * PLL_SDM_COEFF;
+ } else {
+ cfg->output_rate *= cfg->n;
+ cfg->output_rate /= p * cfg->m;
}
cfg->input_rate = input_rate;
- cfg->output_rate = rate;
return 0;
}
.misc_reg = PLLA1_MISC0,
.lock_mask = PLLCX_BASE_LOCK,
.lock_delay = 300,
- .iddq_reg = PLLA1_MISC0,
+ .iddq_reg = PLLA1_MISC1,
.iddq_bit_idx = PLLCX_IDDQ_BIT,
.reset_reg = PLLA1_MISC0,
.reset_bit_idx = PLLCX_RESET_BIT,
};
static struct tegra_clk_pll_freq_table pll_u_freq_table[] = {
- { 12000000, 480000000, 40, 1, 1, 0 },
- { 13000000, 480000000, 36, 1, 1, 0 }, /* actual: 468.0 MHz */
- { 38400000, 480000000, 25, 2, 1, 0 },
+ { 12000000, 480000000, 40, 1, 0, 0 },
+ { 13000000, 480000000, 36, 1, 0, 0 }, /* actual: 468.0 MHz */
+ { 38400000, 480000000, 25, 2, 0, 0 },
{ 0, 0, 0, 0, 0, 0 },
};
.div_nmp = &pllu_nmp,
.freq_table = pll_u_freq_table,
.flags = TEGRA_PLLU | TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT,
- .set_defaults = tegra210_pllu_set_defaults,
- .calc_rate = tegra210_pll_fixed_mdiv_cfg,
+};
+
+struct utmi_clk_param {
+ /* Oscillator Frequency in KHz */
+ u32 osc_frequency;
+ /* UTMIP PLL Enable Delay Count */
+ u8 enable_delay_count;
+ /* UTMIP PLL Stable count */
+ u16 stable_count;
+ /* UTMIP PLL Active delay count */
+ u8 active_delay_count;
+ /* UTMIP PLL Xtal frequency count */
+ u16 xtal_freq_count;
+};
+
+static const struct utmi_clk_param utmi_parameters[] = {
+ {
+ .osc_frequency = 38400000, .enable_delay_count = 0x0,
+ .stable_count = 0x0, .active_delay_count = 0x6,
+ .xtal_freq_count = 0x80
+ }, {
+ .osc_frequency = 13000000, .enable_delay_count = 0x02,
+ .stable_count = 0x33, .active_delay_count = 0x05,
+ .xtal_freq_count = 0x7f
+ }, {
+ .osc_frequency = 19200000, .enable_delay_count = 0x03,
+ .stable_count = 0x4b, .active_delay_count = 0x06,
+ .xtal_freq_count = 0xbb
+ }, {
+ .osc_frequency = 12000000, .enable_delay_count = 0x02,
+ .stable_count = 0x2f, .active_delay_count = 0x08,
+ .xtal_freq_count = 0x76
+ }, {
+ .osc_frequency = 26000000, .enable_delay_count = 0x04,
+ .stable_count = 0x66, .active_delay_count = 0x09,
+ .xtal_freq_count = 0xfe
+ }, {
+ .osc_frequency = 16800000, .enable_delay_count = 0x03,
+ .stable_count = 0x41, .active_delay_count = 0x0a,
+ .xtal_freq_count = 0xa4
+ },
};
static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = {
[tegra_clk_pll_c2] = { .dt_id = TEGRA210_CLK_PLL_C2, .present = true },
[tegra_clk_pll_c3] = { .dt_id = TEGRA210_CLK_PLL_C3, .present = true },
[tegra_clk_pll_m] = { .dt_id = TEGRA210_CLK_PLL_M, .present = true },
- [tegra_clk_pll_m_out1] = { .dt_id = TEGRA210_CLK_PLL_M_OUT1, .present = true },
[tegra_clk_pll_p] = { .dt_id = TEGRA210_CLK_PLL_P, .present = true },
[tegra_clk_pll_p_out1] = { .dt_id = TEGRA210_CLK_PLL_P_OUT1, .present = true },
[tegra_clk_pll_p_out3] = { .dt_id = TEGRA210_CLK_PLL_P_OUT3, .present = true },
[tegra_clk_pll_c4_out2] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT2, .present = true },
[tegra_clk_pll_c4_out3] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT3, .present = true },
[tegra_clk_apb2ape] = { .dt_id = TEGRA210_CLK_APB2APE, .present = true },
+ [tegra_clk_pll_a1] = { .dt_id = TEGRA210_CLK_PLL_A1, .present = true },
+ [tegra_clk_ispa] = { .dt_id = TEGRA210_CLK_ISPA, .present = true },
+ [tegra_clk_cec] = { .dt_id = TEGRA210_CLK_CEC, .present = true },
+ [tegra_clk_dmic1] = { .dt_id = TEGRA210_CLK_DMIC1, .present = true },
+ [tegra_clk_dmic2] = { .dt_id = TEGRA210_CLK_DMIC2, .present = true },
+ [tegra_clk_dmic3] = { .dt_id = TEGRA210_CLK_DMIC3, .present = true },
+ [tegra_clk_dmic1_sync_clk] = { .dt_id = TEGRA210_CLK_DMIC1_SYNC_CLK, .present = true },
+ [tegra_clk_dmic2_sync_clk] = { .dt_id = TEGRA210_CLK_DMIC2_SYNC_CLK, .present = true },
+ [tegra_clk_dmic3_sync_clk] = { .dt_id = TEGRA210_CLK_DMIC3_SYNC_CLK, .present = true },
+ [tegra_clk_dmic1_sync_clk_mux] = { .dt_id = TEGRA210_CLK_DMIC1_SYNC_CLK_MUX, .present = true },
+ [tegra_clk_dmic2_sync_clk_mux] = { .dt_id = TEGRA210_CLK_DMIC2_SYNC_CLK_MUX, .present = true },
+ [tegra_clk_dmic3_sync_clk_mux] = { .dt_id = TEGRA210_CLK_DMIC3_SYNC_CLK_MUX, .present = true },
+ [tegra_clk_dp2] = { .dt_id = TEGRA210_CLK_DP2, .present = true },
+ [tegra_clk_iqc1] = { .dt_id = TEGRA210_CLK_IQC1, .present = true },
+ [tegra_clk_iqc2] = { .dt_id = TEGRA210_CLK_IQC2, .present = true },
+ [tegra_clk_pll_a_out_adsp] = { .dt_id = TEGRA210_CLK_PLL_A_OUT_ADSP, .present = true },
+ [tegra_clk_pll_a_out0_out_adsp] = { .dt_id = TEGRA210_CLK_PLL_A_OUT0_OUT_ADSP, .present = true },
+ [tegra_clk_adsp] = { .dt_id = TEGRA210_CLK_ADSP, .present = true },
+ [tegra_clk_adsp_neon] = { .dt_id = TEGRA210_CLK_ADSP_NEON, .present = true },
};
static struct tegra_devclk devclks[] __initdata = {
{ .con_id = "pll_p_out3", .dt_id = TEGRA210_CLK_PLL_P_OUT3 },
{ .con_id = "pll_p_out4", .dt_id = TEGRA210_CLK_PLL_P_OUT4 },
{ .con_id = "pll_m", .dt_id = TEGRA210_CLK_PLL_M },
- { .con_id = "pll_m_out1", .dt_id = TEGRA210_CLK_PLL_M_OUT1 },
{ .con_id = "pll_x", .dt_id = TEGRA210_CLK_PLL_X },
{ .con_id = "pll_x_out0", .dt_id = TEGRA210_CLK_PLL_X_OUT0 },
{ .con_id = "pll_u", .dt_id = TEGRA210_CLK_PLL_U },
static struct clk **clks;
+static const char * const aclk_parents[] = {
+ "pll_a1", "pll_c", "pll_p", "pll_a_out0", "pll_c2", "pll_c3",
+ "clk_m"
+};
+
+void tegra210_put_utmipll_in_iddq(void)
+{
+ u32 reg;
+
+ reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+ if (reg & UTMIPLL_HW_PWRDN_CFG0_UTMIPLL_LOCK) {
+ pr_err("trying to assert IDDQ while UTMIPLL is locked\n");
+ return;
+ }
+
+ reg |= UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
+ writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
+}
+EXPORT_SYMBOL_GPL(tegra210_put_utmipll_in_iddq);
+
+void tegra210_put_utmipll_out_iddq(void)
+{
+ u32 reg;
+
+ reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
+ reg &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
+ writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
+}
+EXPORT_SYMBOL_GPL(tegra210_put_utmipll_out_iddq);
+
+static void tegra210_utmi_param_configure(void)
+{
+ u32 reg;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(utmi_parameters); i++) {
+ if (osc_freq == utmi_parameters[i].osc_frequency)
+ break;
+ }
+
+ if (i >= ARRAY_SIZE(utmi_parameters)) {
+ pr_err("%s: Unexpected oscillator freq %lu\n", __func__,
+ osc_freq);
+ return;
+ }
+
+ reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
+ reg &= ~UTMIPLL_HW_PWRDN_CFG0_IDDQ_OVERRIDE;
+ writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+ udelay(10);
+
+ reg = readl_relaxed(clk_base + UTMIP_PLL_CFG2);
+
+ /* Program UTMIP PLL stable and active counts */
+ /* [FIXME] arclk_rst.h says WRONG! This should be 1ms -> 0x50 Check! */
+ reg &= ~UTMIP_PLL_CFG2_STABLE_COUNT(~0);
+ reg |= UTMIP_PLL_CFG2_STABLE_COUNT(utmi_parameters[i].stable_count);
+
+ reg &= ~UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(~0);
+
+ reg |=
+ UTMIP_PLL_CFG2_ACTIVE_DLY_COUNT(utmi_parameters[i].active_delay_count);
+ writel_relaxed(reg, clk_base + UTMIP_PLL_CFG2);
+
+ /* Program UTMIP PLL delay and oscillator frequency counts */
+ reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
+ reg &= ~UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(~0);
+
+ reg |=
+ UTMIP_PLL_CFG1_ENABLE_DLY_COUNT(utmi_parameters[i].enable_delay_count);
+
+ reg &= ~UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(~0);
+ reg |=
+ UTMIP_PLL_CFG1_XTAL_FREQ_COUNT(utmi_parameters[i].xtal_freq_count);
+
+ reg |= UTMIP_PLL_CFG1_FORCE_PLLU_POWERDOWN;
+ writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
+
+ /* Remove power downs from UTMIP PLL control bits */
+ reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
+ reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
+ reg |= UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
+ writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
+ udelay(1);
+
+ /* Enable samplers for SNPS, XUSB_HOST, XUSB_DEV */
+ reg = readl_relaxed(clk_base + UTMIP_PLL_CFG2);
+ reg |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERUP;
+ reg |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERUP;
+ reg |= UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERUP;
+ reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_A_POWERDOWN;
+ reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_B_POWERDOWN;
+ reg &= ~UTMIP_PLL_CFG2_FORCE_PD_SAMP_D_POWERDOWN;
+ writel_relaxed(reg, clk_base + UTMIP_PLL_CFG2);
+
+ /* Setup HW control of UTMIPLL */
+ reg = readl_relaxed(clk_base + UTMIP_PLL_CFG1);
+ reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERDOWN;
+ reg &= ~UTMIP_PLL_CFG1_FORCE_PLL_ENABLE_POWERUP;
+ writel_relaxed(reg, clk_base + UTMIP_PLL_CFG1);
+
+ reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
+ reg |= UTMIPLL_HW_PWRDN_CFG0_USE_LOCKDET;
+ reg &= ~UTMIPLL_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL;
+ writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
+
+ udelay(1);
+
+ reg = readl_relaxed(clk_base + XUSB_PLL_CFG0);
+ reg &= ~XUSB_PLL_CFG0_UTMIPLL_LOCK_DLY;
+ writel_relaxed(reg, clk_base + XUSB_PLL_CFG0);
+
+ udelay(1);
+
+ /* Enable HW control UTMIPLL */
+ reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
+ reg |= UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE;
+ writel_relaxed(reg, clk_base + UTMIPLL_HW_PWRDN_CFG0);
+}
+
+static int tegra210_enable_pllu(void)
+{
+ struct tegra_clk_pll_freq_table *fentry;
+ struct tegra_clk_pll pllu;
+ u32 reg;
+
+ for (fentry = pll_u_freq_table; fentry->input_rate; fentry++) {
+ if (fentry->input_rate == pll_ref_freq)
+ break;
+ }
+
+ if (!fentry->input_rate) {
+ pr_err("Unknown PLL_U reference frequency %lu\n", pll_ref_freq);
+ return -EINVAL;
+ }
+
+ /* clear IDDQ bit */
+ pllu.params = &pll_u_vco_params;
+ reg = readl_relaxed(clk_base + pllu.params->ext_misc_reg[0]);
+ reg &= ~BIT(pllu.params->iddq_bit_idx);
+ writel_relaxed(reg, clk_base + pllu.params->ext_misc_reg[0]);
+
+ reg = readl_relaxed(clk_base + PLLU_BASE);
+ reg &= ~GENMASK(20, 0);
+ reg |= fentry->m;
+ reg |= fentry->n << 8;
+ reg |= fentry->p << 16;
+ writel(reg, clk_base + PLLU_BASE);
+ reg |= PLL_ENABLE;
+ writel(reg, clk_base + PLLU_BASE);
+
+ readl_relaxed_poll_timeout(clk_base + PLLU_BASE, reg,
+ reg & PLL_BASE_LOCK, 2, 1000);
+ if (!(reg & PLL_BASE_LOCK)) {
+ pr_err("Timed out waiting for PLL_U to lock\n");
+ return -ETIMEDOUT;
+ }
+
+ return 0;
+}
+
+static int tegra210_init_pllu(void)
+{
+ u32 reg;
+ int err;
+
+ tegra210_pllu_set_defaults(&pll_u_vco_params);
+ /* skip initialization when pllu is in hw controlled mode */
+ reg = readl_relaxed(clk_base + PLLU_BASE);
+ if (reg & PLLU_BASE_OVERRIDE) {
+ if (!(reg & PLL_ENABLE)) {
+ err = tegra210_enable_pllu();
+ if (err < 0) {
+ WARN_ON(1);
+ return err;
+ }
+ }
+ /* enable hw controlled mode */
+ reg = readl_relaxed(clk_base + PLLU_BASE);
+ reg &= ~PLLU_BASE_OVERRIDE;
+ writel(reg, clk_base + PLLU_BASE);
+
+ reg = readl_relaxed(clk_base + PLLU_HW_PWRDN_CFG0);
+ reg |= PLLU_HW_PWRDN_CFG0_IDDQ_PD_INCLUDE |
+ PLLU_HW_PWRDN_CFG0_USE_SWITCH_DETECT |
+ PLLU_HW_PWRDN_CFG0_USE_LOCKDET;
+ reg &= ~(PLLU_HW_PWRDN_CFG0_CLK_ENABLE_SWCTL |
+ PLLU_HW_PWRDN_CFG0_CLK_SWITCH_SWCTL);
+ writel_relaxed(reg, clk_base + PLLU_HW_PWRDN_CFG0);
+
+ reg = readl_relaxed(clk_base + XUSB_PLL_CFG0);
+ reg &= ~XUSB_PLL_CFG0_PLLU_LOCK_DLY_MASK;
+ writel_relaxed(reg, clk_base + XUSB_PLL_CFG0);
+ udelay(1);
+
+ reg = readl_relaxed(clk_base + PLLU_HW_PWRDN_CFG0);
+ reg |= PLLU_HW_PWRDN_CFG0_SEQ_ENABLE;
+ writel_relaxed(reg, clk_base + PLLU_HW_PWRDN_CFG0);
+ udelay(1);
+
+ reg = readl_relaxed(clk_base + PLLU_BASE);
+ reg &= ~PLLU_BASE_CLKENABLE_USB;
+ writel_relaxed(reg, clk_base + PLLU_BASE);
+ }
+
+ /* enable UTMIPLL hw control if not yet done by the bootloader */
+ reg = readl_relaxed(clk_base + UTMIPLL_HW_PWRDN_CFG0);
+ if (!(reg & UTMIPLL_HW_PWRDN_CFG0_SEQ_ENABLE))
+ tegra210_utmi_param_configure();
+
+ return 0;
+}
+
static __init void tegra210_periph_clk_init(void __iomem *clk_base,
void __iomem *pmc_base)
{
clk_register_clkdev(clk, "cml1", NULL);
clks[TEGRA210_CLK_CML1] = clk;
+ clk = tegra_clk_register_super_clk("aclk", aclk_parents,
+ ARRAY_SIZE(aclk_parents), 0, clk_base + 0x6e0,
+ 0, NULL);
+ clks[TEGRA210_CLK_ACLK] = clk;
+
tegra_periph_clk_init(clk_base, pmc_base, tegra210_clks, &pll_p_params);
}
clk_register_clkdev(clk, "pll_mb", NULL);
clks[TEGRA210_CLK_PLL_MB] = clk;
- clk_register_clkdev(clk, "pll_m_out1", NULL);
- clks[TEGRA210_CLK_PLL_M_OUT1] = clk;
-
/* PLLM_UD */
clk = clk_register_fixed_factor(NULL, "pll_m_ud", "pll_m",
CLK_SET_RATE_PARENT, 1, 1);
clks[TEGRA210_CLK_PLL_M_UD] = clk;
/* PLLU_VCO */
- clk = tegra_clk_register_pllu_tegra210("pll_u_vco", "pll_ref",
- clk_base, 0, &pll_u_vco_params,
- &pll_u_lock);
- clk_register_clkdev(clk, "pll_u_vco", NULL);
- clks[TEGRA210_CLK_PLL_U] = clk;
+ if (!tegra210_init_pllu()) {
+ clk = clk_register_fixed_rate(NULL, "pll_u_vco", "pll_ref", 0,
+ 480*1000*1000);
+ clk_register_clkdev(clk, "pll_u_vco", NULL);
+ clks[TEGRA210_CLK_PLL_U] = clk;
+ }
/* PLLU_OUT */
clk = clk_register_divider_table(NULL, "pll_u_out", "pll_u_vco", 0,
{ TEGRA210_CLK_EMC, TEGRA210_CLK_CLK_MAX, 0, 1 },
{ TEGRA210_CLK_MSELECT, TEGRA210_CLK_CLK_MAX, 0, 1 },
{ TEGRA210_CLK_CSITE, TEGRA210_CLK_CLK_MAX, 0, 1 },
+ /* TODO find a way to enable this on-demand */
+ { TEGRA210_CLK_DBGAPB, TEGRA210_CLK_CLK_MAX, 0, 1 },
{ TEGRA210_CLK_TSENSOR, TEGRA210_CLK_CLK_M, 400000, 0 },
{ TEGRA210_CLK_I2C1, TEGRA210_CLK_PLL_P, 0, 0 },
{ TEGRA210_CLK_I2C2, TEGRA210_CLK_PLL_P, 0, 0 },
{ TEGRA210_CLK_PLL_DP, TEGRA210_CLK_CLK_MAX, 270000000, 0 },
{ TEGRA210_CLK_SOC_THERM, TEGRA210_CLK_PLL_P, 51000000, 0 },
{ TEGRA210_CLK_CCLK_G, TEGRA210_CLK_CLK_MAX, 0, 1 },
+ { TEGRA210_CLK_PLL_U_OUT1, TEGRA210_CLK_CLK_MAX, 48000000, 1 },
+ { TEGRA210_CLK_PLL_U_OUT2, TEGRA210_CLK_CLK_MAX, 60000000, 1 },
/* This MUST be the last entry. */
{ TEGRA210_CLK_CLK_MAX, TEGRA210_CLK_CLK_MAX, 0, 0 },
};
tegra_init_from_table(init_table, clks, TEGRA210_CLK_CLK_MAX);
}
+/**
+ * tegra210_car_barrier - wait for pending writes to the CAR to complete
+ *
+ * Wait for any outstanding writes to the CAR MMIO space from this CPU
+ * to complete before continuing execution. No return value.
+ */
+static void tegra210_car_barrier(void)
+{
+ readl_relaxed(clk_base + RST_DFLL_DVCO);
+}
+
+/**
+ * tegra210_clock_assert_dfll_dvco_reset - assert the DFLL's DVCO reset
+ *
+ * Assert the reset line of the DFLL's DVCO. No return value.
+ */
+static void tegra210_clock_assert_dfll_dvco_reset(void)
+{
+ u32 v;
+
+ v = readl_relaxed(clk_base + RST_DFLL_DVCO);
+ v |= (1 << DVFS_DFLL_RESET_SHIFT);
+ writel_relaxed(v, clk_base + RST_DFLL_DVCO);
+ tegra210_car_barrier();
+}
+
+/**
+ * tegra210_clock_deassert_dfll_dvco_reset - deassert the DFLL's DVCO reset
+ *
+ * Deassert the reset line of the DFLL's DVCO, allowing the DVCO to
+ * operate. No return value.
+ */
+static void tegra210_clock_deassert_dfll_dvco_reset(void)
+{
+ u32 v;
+
+ v = readl_relaxed(clk_base + RST_DFLL_DVCO);
+ v &= ~(1 << DVFS_DFLL_RESET_SHIFT);
+ writel_relaxed(v, clk_base + RST_DFLL_DVCO);
+ tegra210_car_barrier();
+}
+
+static int tegra210_reset_assert(unsigned long id)
+{
+ if (id == TEGRA210_RST_DFLL_DVCO)
+ tegra210_clock_assert_dfll_dvco_reset();
+ else if (id == TEGRA210_RST_ADSP)
+ writel(GENMASK(26, 21) | BIT(7),
+ clk_base + CLK_RST_CONTROLLER_RST_DEV_Y_SET);
+ else
+ return -EINVAL;
+
+ return 0;
+}
+
+static int tegra210_reset_deassert(unsigned long id)
+{
+ if (id == TEGRA210_RST_DFLL_DVCO)
+ tegra210_clock_deassert_dfll_dvco_reset();
+ else if (id == TEGRA210_RST_ADSP) {
+ writel(BIT(21), clk_base + CLK_RST_CONTROLLER_RST_DEV_Y_CLR);
+ /*
+ * Considering adsp cpu clock (min: 12.5MHZ, max: 1GHz)
+ * a delay of 5us ensures that it's at least
+ * 6 * adsp_cpu_cycle_period long.
+ */
+ udelay(5);
+ writel(GENMASK(26, 22) | BIT(7),
+ clk_base + CLK_RST_CONTROLLER_RST_DEV_Y_CLR);
+ } else
+ return -EINVAL;
+
+ return 0;
+}
+
/**
* tegra210_clock_init - Tegra210-specific clock initialization
* @np: struct device_node * of the DT node for the SoC CAR IP block
tegra_super_clk_gen5_init(clk_base, pmc_base, tegra210_clks,
&pll_x_params);
+ tegra_init_special_resets(2, tegra210_reset_assert,
+ tegra210_reset_deassert);
+
tegra_add_of_provider(np);
tegra_register_devclks(devclks, ARRAY_SIZE(devclks));
[tegra_clk_pll_p_out4] = { .dt_id = TEGRA30_CLK_PLL_P_OUT4, .present = true },
[tegra_clk_pll_a] = { .dt_id = TEGRA30_CLK_PLL_A, .present = true },
[tegra_clk_pll_a_out0] = { .dt_id = TEGRA30_CLK_PLL_A_OUT0, .present = true },
+ [tegra_clk_cec] = { .dt_id = TEGRA30_CLK_CEC, .present = true },
};
static const char *pll_e_parents[] = { "pll_ref", "pll_p" };
#include <linux/clkdev.h>
#include <linux/clk.h>
#include <linux/clk-provider.h>
+#include <linux/delay.h>
#include <linux/of.h>
#include <linux/clk/tegra.h>
#include <linux/reset-controller.h>
return -EINVAL;
}
+static int tegra_clk_rst_reset(struct reset_controller_dev *rcdev,
+ unsigned long id)
+{
+ int err;
+
+ err = tegra_clk_rst_assert(rcdev, id);
+ if (err)
+ return err;
+
+ udelay(1);
+
+ return tegra_clk_rst_deassert(rcdev, id);
+}
+
const struct tegra_clk_periph_regs *get_reg_bank(int clkid)
{
int reg_bank = clkid / 32;
static const struct reset_control_ops rst_ops = {
.assert = tegra_clk_rst_assert,
.deassert = tegra_clk_rst_deassert,
+ .reset = tegra_clk_rst_reset,
};
static struct reset_controller_dev rst_ctlr = {
unsigned long input_rate;
unsigned long output_rate;
u32 n;
- u16 m;
+ u32 m;
u8 p;
u8 cpcon;
u16 sdm_data;
extern const struct clk_ops tegra_clk_periph_ops;
struct clk *tegra_clk_register_periph(const char *name,
- const char **parent_names, int num_parents,
+ const char * const *parent_names, int num_parents,
struct tegra_clk_periph *periph, void __iomem *clk_base,
u32 offset, unsigned long flags);
struct clk *tegra_clk_register_periph_nodiv(const char *name,
- const char **parent_names, int num_parents,
+ const char * const *parent_names, int num_parents,
struct tegra_clk_periph *periph, void __iomem *clk_base,
u32 offset);
const char *name;
int clk_id;
union {
- const char **parent_names;
+ const char *const *parent_names;
const char *parent_name;
} p;
int num_parents;
struct tegra_clk_super_mux {
struct clk_hw hw;
void __iomem *reg;
+ struct tegra_clk_frac_div frac_div;
+ const struct clk_ops *div_ops;
u8 width;
u8 flags;
u8 div2_index;
const char **parent_names, u8 num_parents,
unsigned long flags, void __iomem *reg, u8 clk_super_flags,
u8 width, u8 pllx_index, u8 div2_index, spinlock_t *lock);
-
+struct clk *tegra_clk_register_super_clk(const char *name,
+ const char * const *parent_names, u8 num_parents,
+ unsigned long flags, void __iomem *reg, u8 clk_super_flags,
+ spinlock_t *lock);
/**
* struct clk_init_table - clock initialization table
* @clk_id: clock id as mentioned in device tree bindings
state <<= __ffs(ad->idlest_mask);
/* Check is already locked */
- v = ti_clk_ll_ops->clk_readl(ad->idlest_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->idlest_reg);
if ((v & ad->idlest_mask) == state)
return r;
- v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->control_reg);
v &= ~ad->enable_mask;
v |= APLL_FORCE_LOCK << __ffs(ad->enable_mask);
- ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &ad->control_reg);
state <<= __ffs(ad->idlest_mask);
while (1) {
- v = ti_clk_ll_ops->clk_readl(ad->idlest_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->idlest_reg);
if ((v & ad->idlest_mask) == state)
break;
if (i > MAX_APLL_WAIT_TRIES)
state <<= __ffs(ad->idlest_mask);
- v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->control_reg);
v &= ~ad->enable_mask;
v |= APLL_AUTO_IDLE << __ffs(ad->enable_mask);
- ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &ad->control_reg);
}
static int dra7_apll_is_enabled(struct clk_hw *hw)
ad = clk->dpll_data;
- v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->control_reg);
v &= ad->enable_mask;
v >>= __ffs(ad->enable_mask);
ad->clk_bypass = __clk_get_hw(clk);
- clk = clk_register(NULL, &clk_hw->hw);
+ clk = ti_clk_register(NULL, &clk_hw->hw, node->name);
if (!IS_ERR(clk)) {
of_clk_add_provider(node, of_clk_src_simple_get, clk);
kfree(clk_hw->hw.init->parent_names);
struct clk_hw_omap *clk_hw = NULL;
struct clk_init_data *init = NULL;
const char **parent_names = NULL;
+ int ret;
ad = kzalloc(sizeof(*ad), GFP_KERNEL);
clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
clk_hw->dpll_data = ad;
clk_hw->hw.init = init;
- clk_hw->flags = MEMMAP_ADDRESSING;
init->name = node->name;
init->ops = &apll_ck_ops;
init->parent_names = parent_names;
- ad->control_reg = ti_clk_get_reg_addr(node, 0);
- ad->idlest_reg = ti_clk_get_reg_addr(node, 1);
+ ret = ti_clk_get_reg_addr(node, 0, &ad->control_reg);
+ ret |= ti_clk_get_reg_addr(node, 1, &ad->idlest_reg);
- if (IS_ERR(ad->control_reg) || IS_ERR(ad->idlest_reg))
+ if (ret)
goto cleanup;
ad->idlest_mask = 0x1;
struct dpll_data *ad = clk->dpll_data;
u32 v;
- v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->control_reg);
v &= ad->enable_mask;
v >>= __ffs(ad->enable_mask);
u32 v;
int i = 0;
- v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->control_reg);
v &= ~ad->enable_mask;
v |= OMAP2_EN_APLL_LOCKED << __ffs(ad->enable_mask);
- ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &ad->control_reg);
while (1) {
- v = ti_clk_ll_ops->clk_readl(ad->idlest_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->idlest_reg);
if (v & ad->idlest_mask)
break;
if (i > MAX_APLL_WAIT_TRIES)
struct dpll_data *ad = clk->dpll_data;
u32 v;
- v = ti_clk_ll_ops->clk_readl(ad->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->control_reg);
v &= ~ad->enable_mask;
v |= OMAP2_EN_APLL_STOPPED << __ffs(ad->enable_mask);
- ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &ad->control_reg);
}
static struct clk_ops omap2_apll_ops = {
struct dpll_data *ad = clk->dpll_data;
u32 v;
- v = ti_clk_ll_ops->clk_readl(ad->autoidle_reg);
+ v = ti_clk_ll_ops->clk_readl(&ad->autoidle_reg);
v &= ~ad->autoidle_mask;
v |= val << __ffs(ad->autoidle_mask);
- ti_clk_ll_ops->clk_writel(v, ad->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &ad->control_reg);
}
#define OMAP2_APLL_AUTOIDLE_LOW_POWER_STOP 0x3
struct clk *clk;
const char *parent_name;
u32 val;
+ int ret;
ad = kzalloc(sizeof(*ad), GFP_KERNEL);
clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
ad->idlest_mask = 1 << val;
- ad->control_reg = ti_clk_get_reg_addr(node, 0);
- ad->autoidle_reg = ti_clk_get_reg_addr(node, 1);
- ad->idlest_reg = ti_clk_get_reg_addr(node, 2);
+ ret = ti_clk_get_reg_addr(node, 0, &ad->control_reg);
+ ret |= ti_clk_get_reg_addr(node, 1, &ad->autoidle_reg);
+ ret |= ti_clk_get_reg_addr(node, 2, &ad->idlest_reg);
- if (IS_ERR(ad->control_reg) || IS_ERR(ad->autoidle_reg) ||
- IS_ERR(ad->idlest_reg))
+ if (ret)
goto cleanup;
clk = clk_register(NULL, &clk_hw->hw);
#include "clock.h"
struct clk_ti_autoidle {
- void __iomem *reg;
+ struct clk_omap_reg reg;
u8 shift;
u8 flags;
const char *name;
{
u32 val;
- val = ti_clk_ll_ops->clk_readl(clk->reg);
+ val = ti_clk_ll_ops->clk_readl(&clk->reg);
if (clk->flags & AUTOIDLE_LOW)
val &= ~(1 << clk->shift);
else
val |= (1 << clk->shift);
- ti_clk_ll_ops->clk_writel(val, clk->reg);
+ ti_clk_ll_ops->clk_writel(val, &clk->reg);
}
static void _deny_autoidle(struct clk_ti_autoidle *clk)
{
u32 val;
- val = ti_clk_ll_ops->clk_readl(clk->reg);
+ val = ti_clk_ll_ops->clk_readl(&clk->reg);
if (clk->flags & AUTOIDLE_LOW)
val |= (1 << clk->shift);
else
val &= ~(1 << clk->shift);
- ti_clk_ll_ops->clk_writel(val, clk->reg);
+ ti_clk_ll_ops->clk_writel(val, &clk->reg);
}
/**
{
u32 shift;
struct clk_ti_autoidle *clk;
+ int ret;
/* Check if this clock has autoidle support or not */
if (of_property_read_u32(node, "ti,autoidle-shift", &shift))
clk->shift = shift;
clk->name = node->name;
- clk->reg = ti_clk_get_reg_addr(node, 0);
-
- if (IS_ERR(clk->reg)) {
+ ret = ti_clk_get_reg_addr(node, 0, &clk->reg);
+ if (ret) {
kfree(clk);
- return -EINVAL;
+ return ret;
}
if (of_property_read_bool(node, "ti,invert-autoidle-bit"))
* @idlest_reg and @idlest_bit. No return value.
*/
static void omap3430es2_clk_ssi_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg,
+ struct clk_omap_reg *idlest_reg,
u8 *idlest_bit,
u8 *idlest_val)
{
- u32 r;
-
- r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
- *idlest_reg = (__force void __iomem *)r;
+ memcpy(idlest_reg, &clk->enable_reg, sizeof(*idlest_reg));
+ idlest_reg->offset &= ~0xf0;
+ idlest_reg->offset |= 0x20;
*idlest_bit = OMAP3430ES2_ST_SSI_IDLE_SHIFT;
*idlest_val = OMAP34XX_CM_IDLEST_VAL;
}
* default find_idlest code assumes that they are at the same
* position.) No return value.
*/
-static void omap3430es2_clk_dss_usbhost_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg,
- u8 *idlest_bit,
- u8 *idlest_val)
+static void
+omap3430es2_clk_dss_usbhost_find_idlest(struct clk_hw_omap *clk,
+ struct clk_omap_reg *idlest_reg,
+ u8 *idlest_bit, u8 *idlest_val)
{
- u32 r;
+ memcpy(idlest_reg, &clk->enable_reg, sizeof(*idlest_reg));
- r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
- *idlest_reg = (__force void __iomem *)r;
+ idlest_reg->offset &= ~0xf0;
+ idlest_reg->offset |= 0x20;
/* USBHOST_IDLE has same shift */
*idlest_bit = OMAP3430ES2_ST_DSS_IDLE_SHIFT;
*idlest_val = OMAP34XX_CM_IDLEST_VAL;
* shift from the CM_{I,F}CLKEN bit. Pass back the correct info via
* @idlest_reg and @idlest_bit. No return value.
*/
-static void omap3430es2_clk_hsotgusb_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg,
- u8 *idlest_bit,
- u8 *idlest_val)
+static void
+omap3430es2_clk_hsotgusb_find_idlest(struct clk_hw_omap *clk,
+ struct clk_omap_reg *idlest_reg,
+ u8 *idlest_bit,
+ u8 *idlest_val)
{
- u32 r;
-
- r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
- *idlest_reg = (__force void __iomem *)r;
+ memcpy(idlest_reg, &clk->enable_reg, sizeof(*idlest_reg));
+ idlest_reg->offset &= ~0xf0;
+ idlest_reg->offset |= 0x20;
*idlest_bit = OMAP3430ES2_ST_HSOTGUSB_IDLE_SHIFT;
*idlest_val = OMAP34XX_CM_IDLEST_VAL;
}
* bit. A value of 1 indicates that clock is enabled.
*/
static void am35xx_clk_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg,
+ struct clk_omap_reg *idlest_reg,
u8 *idlest_bit,
u8 *idlest_val)
{
- *idlest_reg = (__force void __iomem *)(clk->enable_reg);
+ memcpy(idlest_reg, &clk->enable_reg, sizeof(*idlest_reg));
*idlest_bit = clk->enable_bit + AM35XX_IPSS_ICK_EN_ACK_OFFSET;
*idlest_val = AM35XX_IPSS_CLK_IDLEST_VAL;
}
* avoid this issue, and remove the casts. No return value.
*/
static void am35xx_clk_find_companion(struct clk_hw_omap *clk,
- void __iomem **other_reg,
+ struct clk_omap_reg *other_reg,
u8 *other_bit)
{
- *other_reg = (__force void __iomem *)(clk->enable_reg);
+ memcpy(other_reg, &clk->enable_reg, sizeof(*other_reg));
if (clk->enable_bit & AM35XX_IPSS_ICK_MASK)
*other_bit = clk->enable_bit + AM35XX_IPSS_ICK_FCK_OFFSET;
else
* and @idlest_bit. No return value.
*/
static void am35xx_clk_ipss_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg,
+ struct clk_omap_reg *idlest_reg,
u8 *idlest_bit,
u8 *idlest_val)
{
- u32 r;
+ memcpy(idlest_reg, &clk->enable_reg, sizeof(*idlest_reg));
- r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
- *idlest_reg = (__force void __iomem *)r;
+ idlest_reg->offset &= ~0xf0;
+ idlest_reg->offset |= 0x20;
*idlest_bit = AM35XX_ST_IPSS_SHIFT;
*idlest_val = OMAP34XX_CM_IDLEST_VAL;
}
#define OMAP4_DPLL_USB_DEFFREQ 960000000
static struct ti_dt_clk omap44xx_clks[] = {
- DT_CLK(NULL, "extalt_clkin_ck", "extalt_clkin_ck"),
- DT_CLK(NULL, "pad_clks_src_ck", "pad_clks_src_ck"),
- DT_CLK(NULL, "pad_clks_ck", "pad_clks_ck"),
- DT_CLK(NULL, "pad_slimbus_core_clks_ck", "pad_slimbus_core_clks_ck"),
- DT_CLK(NULL, "secure_32k_clk_src_ck", "secure_32k_clk_src_ck"),
- DT_CLK(NULL, "slimbus_src_clk", "slimbus_src_clk"),
- DT_CLK(NULL, "slimbus_clk", "slimbus_clk"),
- DT_CLK(NULL, "sys_32k_ck", "sys_32k_ck"),
- DT_CLK(NULL, "virt_12000000_ck", "virt_12000000_ck"),
- DT_CLK(NULL, "virt_13000000_ck", "virt_13000000_ck"),
- DT_CLK(NULL, "virt_16800000_ck", "virt_16800000_ck"),
- DT_CLK(NULL, "virt_19200000_ck", "virt_19200000_ck"),
- DT_CLK(NULL, "virt_26000000_ck", "virt_26000000_ck"),
- DT_CLK(NULL, "virt_27000000_ck", "virt_27000000_ck"),
- DT_CLK(NULL, "virt_38400000_ck", "virt_38400000_ck"),
- DT_CLK(NULL, "sys_clkin_ck", "sys_clkin_ck"),
- DT_CLK(NULL, "tie_low_clock_ck", "tie_low_clock_ck"),
- DT_CLK(NULL, "utmi_phy_clkout_ck", "utmi_phy_clkout_ck"),
- DT_CLK(NULL, "xclk60mhsp1_ck", "xclk60mhsp1_ck"),
- DT_CLK(NULL, "xclk60mhsp2_ck", "xclk60mhsp2_ck"),
- DT_CLK(NULL, "xclk60motg_ck", "xclk60motg_ck"),
- DT_CLK(NULL, "abe_dpll_bypass_clk_mux_ck", "abe_dpll_bypass_clk_mux_ck"),
- DT_CLK(NULL, "abe_dpll_refclk_mux_ck", "abe_dpll_refclk_mux_ck"),
- DT_CLK(NULL, "dpll_abe_ck", "dpll_abe_ck"),
- DT_CLK(NULL, "dpll_abe_x2_ck", "dpll_abe_x2_ck"),
- DT_CLK(NULL, "dpll_abe_m2x2_ck", "dpll_abe_m2x2_ck"),
- DT_CLK(NULL, "abe_24m_fclk", "abe_24m_fclk"),
- DT_CLK(NULL, "abe_clk", "abe_clk"),
- DT_CLK(NULL, "aess_fclk", "aess_fclk"),
- DT_CLK(NULL, "dpll_abe_m3x2_ck", "dpll_abe_m3x2_ck"),
- DT_CLK(NULL, "core_hsd_byp_clk_mux_ck", "core_hsd_byp_clk_mux_ck"),
- DT_CLK(NULL, "dpll_core_ck", "dpll_core_ck"),
- DT_CLK(NULL, "dpll_core_x2_ck", "dpll_core_x2_ck"),
- DT_CLK(NULL, "dpll_core_m6x2_ck", "dpll_core_m6x2_ck"),
- DT_CLK(NULL, "dbgclk_mux_ck", "dbgclk_mux_ck"),
- DT_CLK(NULL, "dpll_core_m2_ck", "dpll_core_m2_ck"),
- DT_CLK(NULL, "ddrphy_ck", "ddrphy_ck"),
- DT_CLK(NULL, "dpll_core_m5x2_ck", "dpll_core_m5x2_ck"),
- DT_CLK(NULL, "div_core_ck", "div_core_ck"),
- DT_CLK(NULL, "div_iva_hs_clk", "div_iva_hs_clk"),
- DT_CLK(NULL, "div_mpu_hs_clk", "div_mpu_hs_clk"),
- DT_CLK(NULL, "dpll_core_m4x2_ck", "dpll_core_m4x2_ck"),
- DT_CLK(NULL, "dll_clk_div_ck", "dll_clk_div_ck"),
- DT_CLK(NULL, "dpll_abe_m2_ck", "dpll_abe_m2_ck"),
- DT_CLK(NULL, "dpll_core_m3x2_ck", "dpll_core_m3x2_ck"),
- DT_CLK(NULL, "dpll_core_m7x2_ck", "dpll_core_m7x2_ck"),
- DT_CLK(NULL, "iva_hsd_byp_clk_mux_ck", "iva_hsd_byp_clk_mux_ck"),
- DT_CLK(NULL, "dpll_iva_ck", "dpll_iva_ck"),
- DT_CLK(NULL, "dpll_iva_x2_ck", "dpll_iva_x2_ck"),
- DT_CLK(NULL, "dpll_iva_m4x2_ck", "dpll_iva_m4x2_ck"),
- DT_CLK(NULL, "dpll_iva_m5x2_ck", "dpll_iva_m5x2_ck"),
- DT_CLK(NULL, "dpll_mpu_ck", "dpll_mpu_ck"),
- DT_CLK(NULL, "dpll_mpu_m2_ck", "dpll_mpu_m2_ck"),
- DT_CLK(NULL, "per_hs_clk_div_ck", "per_hs_clk_div_ck"),
- DT_CLK(NULL, "per_hsd_byp_clk_mux_ck", "per_hsd_byp_clk_mux_ck"),
- DT_CLK(NULL, "dpll_per_ck", "dpll_per_ck"),
- DT_CLK(NULL, "dpll_per_m2_ck", "dpll_per_m2_ck"),
- DT_CLK(NULL, "dpll_per_x2_ck", "dpll_per_x2_ck"),
- DT_CLK(NULL, "dpll_per_m2x2_ck", "dpll_per_m2x2_ck"),
- DT_CLK(NULL, "dpll_per_m3x2_ck", "dpll_per_m3x2_ck"),
- DT_CLK(NULL, "dpll_per_m4x2_ck", "dpll_per_m4x2_ck"),
- DT_CLK(NULL, "dpll_per_m5x2_ck", "dpll_per_m5x2_ck"),
- DT_CLK(NULL, "dpll_per_m6x2_ck", "dpll_per_m6x2_ck"),
- DT_CLK(NULL, "dpll_per_m7x2_ck", "dpll_per_m7x2_ck"),
- DT_CLK(NULL, "usb_hs_clk_div_ck", "usb_hs_clk_div_ck"),
- DT_CLK(NULL, "dpll_usb_ck", "dpll_usb_ck"),
- DT_CLK(NULL, "dpll_usb_clkdcoldo_ck", "dpll_usb_clkdcoldo_ck"),
- DT_CLK(NULL, "dpll_usb_m2_ck", "dpll_usb_m2_ck"),
- DT_CLK(NULL, "ducati_clk_mux_ck", "ducati_clk_mux_ck"),
- DT_CLK(NULL, "func_12m_fclk", "func_12m_fclk"),
- DT_CLK(NULL, "func_24m_clk", "func_24m_clk"),
- DT_CLK(NULL, "func_24mc_fclk", "func_24mc_fclk"),
- DT_CLK(NULL, "func_48m_fclk", "func_48m_fclk"),
- DT_CLK(NULL, "func_48mc_fclk", "func_48mc_fclk"),
- DT_CLK(NULL, "func_64m_fclk", "func_64m_fclk"),
- DT_CLK(NULL, "func_96m_fclk", "func_96m_fclk"),
- DT_CLK(NULL, "init_60m_fclk", "init_60m_fclk"),
- DT_CLK(NULL, "l3_div_ck", "l3_div_ck"),
- DT_CLK(NULL, "l4_div_ck", "l4_div_ck"),
- DT_CLK(NULL, "lp_clk_div_ck", "lp_clk_div_ck"),
- DT_CLK(NULL, "l4_wkup_clk_mux_ck", "l4_wkup_clk_mux_ck"),
DT_CLK("smp_twd", NULL, "mpu_periphclk"),
- DT_CLK(NULL, "ocp_abe_iclk", "ocp_abe_iclk"),
- DT_CLK(NULL, "per_abe_24m_fclk", "per_abe_24m_fclk"),
- DT_CLK(NULL, "per_abe_nc_fclk", "per_abe_nc_fclk"),
- DT_CLK(NULL, "syc_clk_div_ck", "syc_clk_div_ck"),
- DT_CLK(NULL, "aes1_fck", "aes1_fck"),
- DT_CLK(NULL, "aes2_fck", "aes2_fck"),
- DT_CLK(NULL, "dmic_sync_mux_ck", "dmic_sync_mux_ck"),
- DT_CLK(NULL, "func_dmic_abe_gfclk", "func_dmic_abe_gfclk"),
- DT_CLK(NULL, "dss_sys_clk", "dss_sys_clk"),
- DT_CLK(NULL, "dss_tv_clk", "dss_tv_clk"),
- DT_CLK(NULL, "dss_dss_clk", "dss_dss_clk"),
- DT_CLK(NULL, "dss_48mhz_clk", "dss_48mhz_clk"),
- DT_CLK(NULL, "dss_fck", "dss_fck"),
DT_CLK("omapdss_dss", "ick", "dss_fck"),
- DT_CLK(NULL, "fdif_fck", "fdif_fck"),
- DT_CLK(NULL, "gpio1_dbclk", "gpio1_dbclk"),
- DT_CLK(NULL, "gpio2_dbclk", "gpio2_dbclk"),
- DT_CLK(NULL, "gpio3_dbclk", "gpio3_dbclk"),
- DT_CLK(NULL, "gpio4_dbclk", "gpio4_dbclk"),
- DT_CLK(NULL, "gpio5_dbclk", "gpio5_dbclk"),
- DT_CLK(NULL, "gpio6_dbclk", "gpio6_dbclk"),
- DT_CLK(NULL, "sgx_clk_mux", "sgx_clk_mux"),
- DT_CLK(NULL, "hsi_fck", "hsi_fck"),
- DT_CLK(NULL, "iss_ctrlclk", "iss_ctrlclk"),
- DT_CLK(NULL, "mcasp_sync_mux_ck", "mcasp_sync_mux_ck"),
- DT_CLK(NULL, "func_mcasp_abe_gfclk", "func_mcasp_abe_gfclk"),
- DT_CLK(NULL, "mcbsp1_sync_mux_ck", "mcbsp1_sync_mux_ck"),
- DT_CLK(NULL, "func_mcbsp1_gfclk", "func_mcbsp1_gfclk"),
- DT_CLK(NULL, "mcbsp2_sync_mux_ck", "mcbsp2_sync_mux_ck"),
- DT_CLK(NULL, "func_mcbsp2_gfclk", "func_mcbsp2_gfclk"),
- DT_CLK(NULL, "mcbsp3_sync_mux_ck", "mcbsp3_sync_mux_ck"),
- DT_CLK(NULL, "func_mcbsp3_gfclk", "func_mcbsp3_gfclk"),
- DT_CLK(NULL, "mcbsp4_sync_mux_ck", "mcbsp4_sync_mux_ck"),
- DT_CLK(NULL, "per_mcbsp4_gfclk", "per_mcbsp4_gfclk"),
- DT_CLK(NULL, "hsmmc1_fclk", "hsmmc1_fclk"),
- DT_CLK(NULL, "hsmmc2_fclk", "hsmmc2_fclk"),
- DT_CLK(NULL, "ocp2scp_usb_phy_phy_48m", "ocp2scp_usb_phy_phy_48m"),
- DT_CLK(NULL, "sha2md5_fck", "sha2md5_fck"),
- DT_CLK(NULL, "slimbus1_fclk_1", "slimbus1_fclk_1"),
- DT_CLK(NULL, "slimbus1_fclk_0", "slimbus1_fclk_0"),
- DT_CLK(NULL, "slimbus1_fclk_2", "slimbus1_fclk_2"),
- DT_CLK(NULL, "slimbus1_slimbus_clk", "slimbus1_slimbus_clk"),
- DT_CLK(NULL, "slimbus2_fclk_1", "slimbus2_fclk_1"),
- DT_CLK(NULL, "slimbus2_fclk_0", "slimbus2_fclk_0"),
- DT_CLK(NULL, "slimbus2_slimbus_clk", "slimbus2_slimbus_clk"),
- DT_CLK(NULL, "smartreflex_core_fck", "smartreflex_core_fck"),
- DT_CLK(NULL, "smartreflex_iva_fck", "smartreflex_iva_fck"),
- DT_CLK(NULL, "smartreflex_mpu_fck", "smartreflex_mpu_fck"),
- DT_CLK(NULL, "dmt1_clk_mux", "dmt1_clk_mux"),
- DT_CLK(NULL, "cm2_dm10_mux", "cm2_dm10_mux"),
- DT_CLK(NULL, "cm2_dm11_mux", "cm2_dm11_mux"),
- DT_CLK(NULL, "cm2_dm2_mux", "cm2_dm2_mux"),
- DT_CLK(NULL, "cm2_dm3_mux", "cm2_dm3_mux"),
- DT_CLK(NULL, "cm2_dm4_mux", "cm2_dm4_mux"),
- DT_CLK(NULL, "timer5_sync_mux", "timer5_sync_mux"),
- DT_CLK(NULL, "timer6_sync_mux", "timer6_sync_mux"),
- DT_CLK(NULL, "timer7_sync_mux", "timer7_sync_mux"),
- DT_CLK(NULL, "timer8_sync_mux", "timer8_sync_mux"),
- DT_CLK(NULL, "cm2_dm9_mux", "cm2_dm9_mux"),
- DT_CLK(NULL, "usb_host_fs_fck", "usb_host_fs_fck"),
DT_CLK("usbhs_omap", "fs_fck", "usb_host_fs_fck"),
- DT_CLK(NULL, "utmi_p1_gfclk", "utmi_p1_gfclk"),
- DT_CLK(NULL, "usb_host_hs_utmi_p1_clk", "usb_host_hs_utmi_p1_clk"),
- DT_CLK(NULL, "utmi_p2_gfclk", "utmi_p2_gfclk"),
- DT_CLK(NULL, "usb_host_hs_utmi_p2_clk", "usb_host_hs_utmi_p2_clk"),
- DT_CLK(NULL, "usb_host_hs_utmi_p3_clk", "usb_host_hs_utmi_p3_clk"),
- DT_CLK(NULL, "usb_host_hs_hsic480m_p1_clk", "usb_host_hs_hsic480m_p1_clk"),
- DT_CLK(NULL, "usb_host_hs_hsic60m_p1_clk", "usb_host_hs_hsic60m_p1_clk"),
- DT_CLK(NULL, "usb_host_hs_hsic60m_p2_clk", "usb_host_hs_hsic60m_p2_clk"),
- DT_CLK(NULL, "usb_host_hs_hsic480m_p2_clk", "usb_host_hs_hsic480m_p2_clk"),
- DT_CLK(NULL, "usb_host_hs_func48mclk", "usb_host_hs_func48mclk"),
- DT_CLK(NULL, "usb_host_hs_fck", "usb_host_hs_fck"),
DT_CLK("usbhs_omap", "hs_fck", "usb_host_hs_fck"),
- DT_CLK(NULL, "otg_60m_gfclk", "otg_60m_gfclk"),
- DT_CLK(NULL, "usb_otg_hs_xclk", "usb_otg_hs_xclk"),
- DT_CLK(NULL, "usb_otg_hs_ick", "usb_otg_hs_ick"),
DT_CLK("musb-omap2430", "ick", "usb_otg_hs_ick"),
- DT_CLK(NULL, "usb_phy_cm_clk32k", "usb_phy_cm_clk32k"),
- DT_CLK(NULL, "usb_tll_hs_usb_ch2_clk", "usb_tll_hs_usb_ch2_clk"),
- DT_CLK(NULL, "usb_tll_hs_usb_ch0_clk", "usb_tll_hs_usb_ch0_clk"),
- DT_CLK(NULL, "usb_tll_hs_usb_ch1_clk", "usb_tll_hs_usb_ch1_clk"),
- DT_CLK(NULL, "usb_tll_hs_ick", "usb_tll_hs_ick"),
DT_CLK("usbhs_omap", "usbtll_ick", "usb_tll_hs_ick"),
DT_CLK("usbhs_tll", "usbtll_ick", "usb_tll_hs_ick"),
- DT_CLK(NULL, "usim_ck", "usim_ck"),
- DT_CLK(NULL, "usim_fclk", "usim_fclk"),
- DT_CLK(NULL, "pmd_stm_clock_mux_ck", "pmd_stm_clock_mux_ck"),
- DT_CLK(NULL, "pmd_trace_clk_mux_ck", "pmd_trace_clk_mux_ck"),
- DT_CLK(NULL, "stm_clk_div_ck", "stm_clk_div_ck"),
- DT_CLK(NULL, "trace_clk_div_ck", "trace_clk_div_ck"),
- DT_CLK(NULL, "auxclk0_src_ck", "auxclk0_src_ck"),
- DT_CLK(NULL, "auxclk0_ck", "auxclk0_ck"),
- DT_CLK(NULL, "auxclkreq0_ck", "auxclkreq0_ck"),
- DT_CLK(NULL, "auxclk1_src_ck", "auxclk1_src_ck"),
- DT_CLK(NULL, "auxclk1_ck", "auxclk1_ck"),
- DT_CLK(NULL, "auxclkreq1_ck", "auxclkreq1_ck"),
- DT_CLK(NULL, "auxclk2_src_ck", "auxclk2_src_ck"),
- DT_CLK(NULL, "auxclk2_ck", "auxclk2_ck"),
- DT_CLK(NULL, "auxclkreq2_ck", "auxclkreq2_ck"),
- DT_CLK(NULL, "auxclk3_src_ck", "auxclk3_src_ck"),
- DT_CLK(NULL, "auxclk3_ck", "auxclk3_ck"),
- DT_CLK(NULL, "auxclkreq3_ck", "auxclkreq3_ck"),
- DT_CLK(NULL, "auxclk4_src_ck", "auxclk4_src_ck"),
- DT_CLK(NULL, "auxclk4_ck", "auxclk4_ck"),
- DT_CLK(NULL, "auxclkreq4_ck", "auxclkreq4_ck"),
- DT_CLK(NULL, "auxclk5_src_ck", "auxclk5_src_ck"),
- DT_CLK(NULL, "auxclk5_ck", "auxclk5_ck"),
- DT_CLK(NULL, "auxclkreq5_ck", "auxclkreq5_ck"),
DT_CLK("omap_i2c.1", "ick", "dummy_ck"),
DT_CLK("omap_i2c.2", "ick", "dummy_ck"),
DT_CLK("omap_i2c.3", "ick", "dummy_ck"),
DT_CLK("4013c000.timer", "timer_sys_ck", "syc_clk_div_ck"),
DT_CLK("4013e000.timer", "timer_sys_ck", "syc_clk_div_ck"),
DT_CLK(NULL, "cpufreq_ck", "dpll_mpu_ck"),
- DT_CLK(NULL, "bandgap_fclk", "bandgap_fclk"),
- DT_CLK(NULL, "div_ts_ck", "div_ts_ck"),
- DT_CLK(NULL, "bandgap_ts_fclk", "bandgap_ts_fclk"),
{ .node_name = NULL },
};
omap2_clk_disable_autoidle_all();
+ ti_clk_add_aliases();
+
/*
* Lock USB DPLL on OMAP4 devices so that the L3INIT power
* domain can transition to retention state when not in use.
#include <linux/of_address.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
+#include <linux/clk/ti.h>
+
+#include "clock.h"
#define DRA7_ATL_INSTANCES 4
struct clk_init_data init = { NULL };
const char **parent_names = NULL;
struct clk *clk;
+ int ret;
clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
if (!clk_hw) {
init.parent_names = parent_names;
- clk = clk_register(NULL, &clk_hw->hw);
+ clk = ti_clk_register(NULL, &clk_hw->hw, node->name);
if (!IS_ERR(clk)) {
+ ret = ti_clk_add_alias(NULL, clk, node->name);
+ if (ret) {
+ clk_unregister(clk);
+ goto cleanup;
+ }
of_clk_add_provider(node, of_clk_src_simple_get, clk);
kfree(parent_names);
return;
#include <linux/list.h>
#include <linux/regmap.h>
#include <linux/bootmem.h>
+#include <linux/device.h>
#include "clock.h"
static struct clk_iomap *clk_memmaps[CLK_MAX_MEMMAPS];
-static void clk_memmap_writel(u32 val, void __iomem *reg)
+static void clk_memmap_writel(u32 val, const struct clk_omap_reg *reg)
{
- struct clk_omap_reg *r = (struct clk_omap_reg *)®
- struct clk_iomap *io = clk_memmaps[r->index];
+ struct clk_iomap *io = clk_memmaps[reg->index];
- if (io->regmap)
- regmap_write(io->regmap, r->offset, val);
+ if (reg->ptr)
+ writel_relaxed(val, reg->ptr);
+ else if (io->regmap)
+ regmap_write(io->regmap, reg->offset, val);
else
- writel_relaxed(val, io->mem + r->offset);
+ writel_relaxed(val, io->mem + reg->offset);
}
-static u32 clk_memmap_readl(void __iomem *reg)
+static u32 clk_memmap_readl(const struct clk_omap_reg *reg)
{
u32 val;
- struct clk_omap_reg *r = (struct clk_omap_reg *)®
- struct clk_iomap *io = clk_memmaps[r->index];
+ struct clk_iomap *io = clk_memmaps[reg->index];
- if (io->regmap)
- regmap_read(io->regmap, r->offset, &val);
+ if (reg->ptr)
+ val = readl_relaxed(reg->ptr);
+ else if (io->regmap)
+ regmap_read(io->regmap, reg->offset, &val);
else
- val = readl_relaxed(io->mem + r->offset);
+ val = readl_relaxed(io->mem + reg->offset);
return val;
}
* ti_clk_get_reg_addr - get register address for a clock register
* @node: device node for the clock
* @index: register index from the clock node
+ * @reg: pointer to target register struct
*
- * Builds clock register address from device tree information. This
- * is a struct of type clk_omap_reg. Returns a pointer to the register
- * address, or a pointer error value in failure.
+ * Builds clock register address from device tree information, and returns
+ * the data via the provided output pointer @reg. Returns 0 on success,
+ * negative error value on failure.
*/
-void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index)
+int ti_clk_get_reg_addr(struct device_node *node, int index,
+ struct clk_omap_reg *reg)
{
- struct clk_omap_reg *reg;
u32 val;
- u32 tmp;
int i;
- reg = (struct clk_omap_reg *)&tmp;
-
for (i = 0; i < CLK_MAX_MEMMAPS; i++) {
if (clocks_node_ptr[i] == node->parent)
break;
if (i == CLK_MAX_MEMMAPS) {
pr_err("clk-provider not found for %s!\n", node->name);
- return IOMEM_ERR_PTR(-ENOENT);
+ return -ENOENT;
}
reg->index = i;
if (of_property_read_u32_index(node, "reg", index, &val)) {
pr_err("%s must have reg[%d]!\n", node->name, index);
- return IOMEM_ERR_PTR(-EINVAL);
+ return -EINVAL;
}
reg->offset = val;
+ reg->ptr = NULL;
- return (__force void __iomem *)tmp;
+ return 0;
}
/**
struct ti_clk_fixed *fixed;
struct ti_clk_fixed_factor *fixed_factor;
struct clk_hw *clk_hw;
+ int ret;
if (setup->clk)
return setup->clk;
clk = clk_register_fixed_rate(NULL, setup->name, NULL, 0,
fixed->frequency);
+ if (!IS_ERR(clk)) {
+ ret = ti_clk_add_alias(NULL, clk, setup->name);
+ if (ret) {
+ clk_unregister(clk);
+ clk = ERR_PTR(ret);
+ }
+ }
break;
case TI_CLK_MUX:
clk = ti_clk_register_mux(setup);
fixed_factor->parent,
0, fixed_factor->mult,
fixed_factor->div);
+ if (!IS_ERR(clk)) {
+ ret = ti_clk_add_alias(NULL, clk, setup->name);
+ if (ret) {
+ clk_unregister(clk);
+ clk = ERR_PTR(ret);
+ }
+ }
break;
case TI_CLK_GATE:
clk = ti_clk_register_gate(setup);
clks->clk->name, PTR_ERR(clk));
return PTR_ERR(clk);
}
- } else {
- clks->lk.clk = clk;
- clkdev_add(&clks->lk);
}
clks++;
}
}
} else {
retry = true;
- retry_clk->lk.clk = clk;
- clkdev_add(&retry_clk->lk);
list_del(&retry_clk->link);
}
}
}
#endif
+static const struct of_device_id simple_clk_match_table[] __initconst = {
+ { .compatible = "fixed-clock" },
+ { .compatible = "fixed-factor-clock" },
+ { }
+};
+
+/**
+ * ti_clk_add_aliases - setup clock aliases
+ *
+ * Sets up any missing clock aliases. No return value.
+ */
+void __init ti_clk_add_aliases(void)
+{
+ struct device_node *np;
+ struct clk *clk;
+
+ for_each_matching_node(np, simple_clk_match_table) {
+ struct of_phandle_args clkspec;
+
+ clkspec.np = np;
+ clk = of_clk_get_from_provider(&clkspec);
+
+ ti_clk_add_alias(NULL, clk, np->name);
+ }
+}
+
/**
* ti_clk_setup_features - setup clock features flags
* @features: features definition to use
clk_prepare_enable(init_clk);
}
}
+
+/**
+ * ti_clk_add_alias - add a clock alias for a TI clock
+ * @dev: device alias for this clock
+ * @clk: clock handle to create alias for
+ * @con: connection ID for this clock
+ *
+ * Creates a clock alias for a TI clock. Allocates the clock lookup entry
+ * and assigns the data to it. Returns 0 if successful, negative error
+ * value otherwise.
+ */
+int ti_clk_add_alias(struct device *dev, struct clk *clk, const char *con)
+{
+ struct clk_lookup *cl;
+
+ if (!clk)
+ return 0;
+
+ if (IS_ERR(clk))
+ return PTR_ERR(clk);
+
+ cl = kzalloc(sizeof(*cl), GFP_KERNEL);
+ if (!cl)
+ return -ENOMEM;
+
+ if (dev)
+ cl->dev_id = dev_name(dev);
+ cl->con_id = con;
+ cl->clk = clk;
+
+ clkdev_add(cl);
+
+ return 0;
+}
+
+/**
+ * ti_clk_register - register a TI clock to the common clock framework
+ * @dev: device for this clock
+ * @hw: hardware clock handle
+ * @con: connection ID for this clock
+ *
+ * Registers a TI clock to the common clock framework, and adds a clock
+ * alias for it. Returns a handle to the registered clock if successful,
+ * ERR_PTR value in failure.
+ */
+struct clk *ti_clk_register(struct device *dev, struct clk_hw *hw,
+ const char *con)
+{
+ struct clk *clk;
+ int ret;
+
+ clk = clk_register(dev, hw);
+ if (IS_ERR(clk))
+ return clk;
+
+ ret = ti_clk_add_alias(dev, clk, con);
+ if (ret) {
+ clk_unregister(clk);
+ return ERR_PTR(ret);
+ }
+
+ return clk;
+}
* elapsed. XXX Deprecated - should be moved into drivers for the
* individual IP block that the IDLEST register exists in.
*/
-static int _wait_idlest_generic(struct clk_hw_omap *clk, void __iomem *reg,
+static int _wait_idlest_generic(struct clk_hw_omap *clk,
+ struct clk_omap_reg *reg,
u32 mask, u8 idlest, const char *name)
{
int i = 0, ena = 0;
*/
static void _omap2_module_wait_ready(struct clk_hw_omap *clk)
{
- void __iomem *companion_reg, *idlest_reg;
+ struct clk_omap_reg companion_reg, idlest_reg;
u8 other_bit, idlest_bit, idlest_val, idlest_reg_id;
s16 prcm_mod;
int r;
/* Not all modules have multiple clocks that their IDLEST depends on */
if (clk->ops->find_companion) {
clk->ops->find_companion(clk, &companion_reg, &other_bit);
- if (!(ti_clk_ll_ops->clk_readl(companion_reg) &
+ if (!(ti_clk_ll_ops->clk_readl(&companion_reg) &
(1 << other_bit)))
return;
}
clk->ops->find_idlest(clk, &idlest_reg, &idlest_bit, &idlest_val);
- r = ti_clk_ll_ops->cm_split_idlest_reg(idlest_reg, &prcm_mod,
+ r = ti_clk_ll_ops->cm_split_idlest_reg(&idlest_reg, &prcm_mod,
&idlest_reg_id);
if (r) {
/* IDLEST register not in the CM module */
- _wait_idlest_generic(clk, idlest_reg, (1 << idlest_bit),
+ _wait_idlest_generic(clk, &idlest_reg, (1 << idlest_bit),
idlest_val, clk_hw_get_name(&clk->hw));
} else {
ti_clk_ll_ops->cm_wait_module_ready(0, prcm_mod, idlest_reg_id,
* avoid this issue, and remove the casts. No return value.
*/
void omap2_clk_dflt_find_companion(struct clk_hw_omap *clk,
- void __iomem **other_reg, u8 *other_bit)
+ struct clk_omap_reg *other_reg,
+ u8 *other_bit)
{
- u32 r;
+ memcpy(other_reg, &clk->enable_reg, sizeof(*other_reg));
/*
* Convert CM_ICLKEN* <-> CM_FCLKEN*. This conversion assumes
* it's just a matter of XORing the bits.
*/
- r = ((__force u32)clk->enable_reg ^ (CM_FCLKEN ^ CM_ICLKEN));
+ other_reg->offset ^= (CM_FCLKEN ^ CM_ICLKEN);
- *other_reg = (__force void __iomem *)r;
*other_bit = clk->enable_bit;
}
* CM_IDLEST2). This is not true for all modules. No return value.
*/
void omap2_clk_dflt_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg, u8 *idlest_bit,
+ struct clk_omap_reg *idlest_reg, u8 *idlest_bit,
u8 *idlest_val)
{
- u32 r;
+ memcpy(idlest_reg, &clk->enable_reg, sizeof(*idlest_reg));
+
+ idlest_reg->offset &= ~0xf0;
+ idlest_reg->offset |= 0x20;
- r = (((__force u32)clk->enable_reg & ~0xf0) | 0x20);
- *idlest_reg = (__force void __iomem *)r;
*idlest_bit = clk->enable_bit;
/*
}
}
- if (IS_ERR(clk->enable_reg)) {
- pr_err("%s: %s missing enable_reg\n", __func__,
- clk_hw_get_name(hw));
- ret = -EINVAL;
- goto err;
- }
-
/* FIXME should not have INVERT_ENABLE bit here */
- v = ti_clk_ll_ops->clk_readl(clk->enable_reg);
+ v = ti_clk_ll_ops->clk_readl(&clk->enable_reg);
if (clk->flags & INVERT_ENABLE)
v &= ~(1 << clk->enable_bit);
else
v |= (1 << clk->enable_bit);
- ti_clk_ll_ops->clk_writel(v, clk->enable_reg);
- v = ti_clk_ll_ops->clk_readl(clk->enable_reg); /* OCP barrier */
+ ti_clk_ll_ops->clk_writel(v, &clk->enable_reg);
+ v = ti_clk_ll_ops->clk_readl(&clk->enable_reg); /* OCP barrier */
if (clk->ops && clk->ops->find_idlest)
_omap2_module_wait_ready(clk);
return 0;
-
-err:
- if (clkdm_control && clk->clkdm)
- ti_clk_ll_ops->clkdm_clk_disable(clk->clkdm, hw->clk);
- return ret;
}
/**
u32 v;
clk = to_clk_hw_omap(hw);
- if (IS_ERR(clk->enable_reg)) {
- /*
- * 'independent' here refers to a clock which is not
- * controlled by its parent.
- */
- pr_err("%s: independent clock %s has no enable_reg\n",
- __func__, clk_hw_get_name(hw));
- return;
- }
- v = ti_clk_ll_ops->clk_readl(clk->enable_reg);
+ v = ti_clk_ll_ops->clk_readl(&clk->enable_reg);
if (clk->flags & INVERT_ENABLE)
v |= (1 << clk->enable_bit);
else
v &= ~(1 << clk->enable_bit);
- ti_clk_ll_ops->clk_writel(v, clk->enable_reg);
+ ti_clk_ll_ops->clk_writel(v, &clk->enable_reg);
/* No OCP barrier needed here since it is a disable operation */
if (!(ti_clk_get_features()->flags & TI_CLK_DISABLE_CLKDM_CONTROL) &&
struct clk_hw_omap *clk = to_clk_hw_omap(hw);
u32 v;
- v = ti_clk_ll_ops->clk_readl(clk->enable_reg);
+ v = ti_clk_ll_ops->clk_readl(&clk->enable_reg);
if (clk->flags & INVERT_ENABLE)
v ^= BIT(clk->enable_bit);
if (!dd)
return -EINVAL;
- v = ti_clk_ll_ops->clk_readl(dd->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->control_reg);
v &= dd->enable_mask;
v >>= __ffs(dd->enable_mask);
return 0;
/* Return bypass rate if DPLL is bypassed */
- v = ti_clk_ll_ops->clk_readl(dd->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->control_reg);
v &= dd->enable_mask;
v >>= __ffs(dd->enable_mask);
if (_omap2_dpll_is_in_bypass(v))
return clk_hw_get_rate(dd->clk_bypass);
- v = ti_clk_ll_ops->clk_readl(dd->mult_div1_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->mult_div1_reg);
dpll_mult = v & dd->mult_mask;
dpll_mult >>= __ffs(dd->mult_mask);
dpll_div = v & dd->div1_mask;
void omap2_clkt_iclk_allow_idle(struct clk_hw_omap *clk)
{
u32 v;
- void __iomem *r;
+ struct clk_omap_reg r;
- r = (__force void __iomem *)
- ((__force u32)clk->enable_reg ^ (CM_AUTOIDLE ^ CM_ICLKEN));
+ memcpy(&r, &clk->enable_reg, sizeof(r));
+ r.offset ^= (CM_AUTOIDLE ^ CM_ICLKEN);
- v = ti_clk_ll_ops->clk_readl(r);
+ v = ti_clk_ll_ops->clk_readl(&r);
v |= (1 << clk->enable_bit);
- ti_clk_ll_ops->clk_writel(v, r);
+ ti_clk_ll_ops->clk_writel(v, &r);
}
/* XXX */
void omap2_clkt_iclk_deny_idle(struct clk_hw_omap *clk)
{
u32 v;
- void __iomem *r;
+ struct clk_omap_reg r;
- r = (__force void __iomem *)
- ((__force u32)clk->enable_reg ^ (CM_AUTOIDLE ^ CM_ICLKEN));
+ memcpy(&r, &clk->enable_reg, sizeof(r));
- v = ti_clk_ll_ops->clk_readl(r);
+ r.offset ^= (CM_AUTOIDLE ^ CM_ICLKEN);
+
+ v = ti_clk_ll_ops->clk_readl(&r);
v &= ~(1 << clk->enable_bit);
- ti_clk_ll_ops->clk_writel(v, r);
+ ti_clk_ll_ops->clk_writel(v, &r);
}
/**
* modules. No return value.
*/
static void omap2430_clk_i2chs_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg,
+ struct clk_omap_reg *idlest_reg,
u8 *idlest_bit,
u8 *idlest_val)
{
- u32 r;
-
- r = ((__force u32)clk->enable_reg ^ (OMAP24XX_CM_FCLKEN2 ^ CM_IDLEST));
- *idlest_reg = (__force void __iomem *)r;
+ memcpy(idlest_reg, &clk->enable_reg, sizeof(*idlest_reg));
+ idlest_reg->offset ^= (OMAP24XX_CM_FCLKEN2 ^ CM_IDLEST);
*idlest_bit = clk->enable_bit;
*idlest_val = OMAP24XX_CM_IDLEST_VAL;
}
#ifndef __DRIVERS_CLK_TI_CLOCK__
#define __DRIVERS_CLK_TI_CLOCK__
+struct clk_omap_divider {
+ struct clk_hw hw;
+ struct clk_omap_reg reg;
+ u8 shift;
+ u8 width;
+ u8 flags;
+ const struct clk_div_table *table;
+};
+
+#define to_clk_omap_divider(_hw) container_of(_hw, struct clk_omap_divider, hw)
+
+struct clk_omap_mux {
+ struct clk_hw hw;
+ struct clk_omap_reg reg;
+ u32 *table;
+ u32 mask;
+ u8 shift;
+ u8 flags;
+};
+
+#define to_clk_omap_mux(_hw) container_of(_hw, struct clk_omap_mux, hw)
+
enum {
TI_CLK_FIXED,
TI_CLK_MUX,
int num_parents;
u16 reg;
u8 module;
- const char **parents;
+ const char * const *parents;
u16 flags;
};
struct clk *ti_clk_register_divider(struct ti_clk *setup);
struct clk *ti_clk_register_composite(struct ti_clk *setup);
struct clk *ti_clk_register_dpll(struct ti_clk *setup);
+struct clk *ti_clk_register(struct device *dev, struct clk_hw *hw,
+ const char *con);
+int ti_clk_add_alias(struct device *dev, struct clk *clk, const char *con);
+void ti_clk_add_aliases(void);
struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup);
struct clk_hw *ti_clk_build_component_gate(struct ti_clk_gate *setup);
struct clk_hw *ti_clk_build_component_mux(struct ti_clk_mux *setup);
+int ti_clk_parse_divider_data(int *div_table, int num_dividers, int max_div,
+ u8 flags, u8 *width,
+ const struct clk_div_table **table);
+
void ti_clk_patch_legacy_clks(struct ti_clk **patch);
struct clk *ti_clk_register_clk(struct ti_clk *setup);
int ti_clk_register_legacy_clks(struct ti_clk_alias *clks);
-void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index);
+int ti_clk_get_reg_addr(struct device_node *node, int index,
+ struct clk_omap_reg *reg);
void ti_dt_clocks_register(struct ti_dt_clk *oclks);
int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw,
ti_of_clk_init_cb_t func);
extern const struct clk_ops ti_clk_divider_ops;
extern const struct clk_ops ti_clk_mux_ops;
+extern const struct clk_ops omap_gate_clk_ops;
+void omap2_init_clk_clkdm(struct clk_hw *hw);
int omap2_clkops_enable_clkdm(struct clk_hw *hw);
void omap2_clkops_disable_clkdm(struct clk_hw *hw);
void omap2_dflt_clk_disable(struct clk_hw *hw);
int omap2_dflt_clk_is_enabled(struct clk_hw *hw);
void omap2_clk_dflt_find_companion(struct clk_hw_omap *clk,
- void __iomem **other_reg,
+ struct clk_omap_reg *other_reg,
u8 *other_bit);
void omap2_clk_dflt_find_idlest(struct clk_hw_omap *clk,
- void __iomem **idlest_reg,
+ struct clk_omap_reg *idlest_reg,
u8 *idlest_bit, u8 *idlest_val);
void omap2_clkt_iclk_allow_idle(struct clk_hw_omap *clk);
return -EINVAL;
}
- if (unlikely(clk->enable_reg))
- pr_err("%s: %s: should use dflt_clk_enable ?!\n", __func__,
- clk_hw_get_name(hw));
-
if (ti_clk_get_features()->flags & TI_CLK_DISABLE_CLKDM_CONTROL) {
pr_err("%s: %s: clkfw-based clockdomain control disabled ?!\n",
__func__, clk_hw_get_name(hw));
return;
}
- if (unlikely(clk->enable_reg))
- pr_err("%s: %s: should use dflt_clk_disable ?!\n", __func__,
- clk_hw_get_name(hw));
-
if (ti_clk_get_features()->flags & TI_CLK_DISABLE_CLKDM_CONTROL) {
pr_err("%s: %s: clkfw-based clockdomain control disabled ?!\n",
__func__, clk_hw_get_name(hw));
ti_clk_ll_ops->clkdm_clk_disable(clk->clkdm, hw->clk);
}
+/**
+ * omap2_init_clk_clkdm - look up a clockdomain name, store pointer in clk
+ * @clk: OMAP clock struct ptr to use
+ *
+ * Convert a clockdomain name stored in a struct clk 'clk' into a
+ * clockdomain pointer, and save it into the struct clk. Intended to be
+ * called during clk_register(). No return value.
+ */
+void omap2_init_clk_clkdm(struct clk_hw *hw)
+{
+ struct clk_hw_omap *clk = to_clk_hw_omap(hw);
+ struct clockdomain *clkdm;
+ const char *clk_name;
+
+ if (!clk->clkdm_name)
+ return;
+
+ clk_name = __clk_get_name(hw->clk);
+
+ clkdm = ti_clk_ll_ops->clkdm_lookup(clk->clkdm_name);
+ if (clkdm) {
+ pr_debug("clock: associated clk %s to clkdm %s\n",
+ clk_name, clk->clkdm_name);
+ clk->clkdm = clkdm;
+ } else {
+ pr_debug("clock: could not associate clk %s to clkdm %s\n",
+ clk_name, clk->clkdm_name);
+ }
+}
+
static void __init of_ti_clockdomain_setup(struct device_node *node)
{
struct clk *clk;
struct clk_hw *mux;
struct clk_hw *div;
int num_parents = 1;
- const char **parent_names = NULL;
+ const char * const *parent_names = NULL;
struct clk *clk;
+ int ret;
comp = setup->data;
&ti_composite_divider_ops, gate,
&ti_composite_gate_ops, 0);
+ ret = ti_clk_add_alias(NULL, clk, setup->name);
+ if (ret) {
+ clk_unregister(clk);
+ return ERR_PTR(ret);
+ }
+
return clk;
}
#endif
int num_parents = 0;
const char **parent_names = NULL;
int i;
+ int ret;
/* Check for presence of each component clock */
for (i = 0; i < CLK_COMPONENT_TYPE_MAX; i++) {
_get_hw(cclk, CLK_COMPONENT_TYPE_GATE),
&ti_composite_gate_ops, 0);
- if (!IS_ERR(clk))
+ if (!IS_ERR(clk)) {
+ ret = ti_clk_add_alias(NULL, clk, node->name);
+ if (ret) {
+ clk_unregister(clk);
+ goto cleanup;
+ }
of_clk_add_provider(node, of_clk_src_simple_get, clk);
+ }
cleanup:
/* Free component clock list entries */
return maxdiv;
}
-static unsigned int _get_maxdiv(struct clk_divider *divider)
+static unsigned int _get_maxdiv(struct clk_omap_divider *divider)
{
if (divider->flags & CLK_DIVIDER_ONE_BASED)
return div_mask(divider);
return 0;
}
-static unsigned int _get_div(struct clk_divider *divider, unsigned int val)
+static unsigned int _get_div(struct clk_omap_divider *divider, unsigned int val)
{
if (divider->flags & CLK_DIVIDER_ONE_BASED)
return val;
return 0;
}
-static unsigned int _get_val(struct clk_divider *divider, u8 div)
+static unsigned int _get_val(struct clk_omap_divider *divider, u8 div)
{
if (divider->flags & CLK_DIVIDER_ONE_BASED)
return div;
static unsigned long ti_clk_divider_recalc_rate(struct clk_hw *hw,
unsigned long parent_rate)
{
- struct clk_divider *divider = to_clk_divider(hw);
+ struct clk_omap_divider *divider = to_clk_omap_divider(hw);
unsigned int div, val;
- val = ti_clk_ll_ops->clk_readl(divider->reg) >> divider->shift;
+ val = ti_clk_ll_ops->clk_readl(÷r->reg) >> divider->shift;
val &= div_mask(divider);
div = _get_div(divider, val);
return false;
}
-static bool _is_valid_div(struct clk_divider *divider, unsigned int div)
+static bool _is_valid_div(struct clk_omap_divider *divider, unsigned int div)
{
if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
return is_power_of_2(div);
static int ti_clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
unsigned long *best_parent_rate)
{
- struct clk_divider *divider = to_clk_divider(hw);
+ struct clk_omap_divider *divider = to_clk_omap_divider(hw);
int i, bestdiv = 0;
unsigned long parent_rate, best = 0, now, maxdiv;
unsigned long parent_rate_saved = *best_parent_rate;
static int ti_clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
unsigned long parent_rate)
{
- struct clk_divider *divider;
+ struct clk_omap_divider *divider;
unsigned int div, value;
u32 val;
if (!hw || !rate)
return -EINVAL;
- divider = to_clk_divider(hw);
+ divider = to_clk_omap_divider(hw);
div = DIV_ROUND_UP(parent_rate, rate);
value = _get_val(divider, div);
if (divider->flags & CLK_DIVIDER_HIWORD_MASK) {
val = div_mask(divider) << (divider->shift + 16);
} else {
- val = ti_clk_ll_ops->clk_readl(divider->reg);
+ val = ti_clk_ll_ops->clk_readl(÷r->reg);
val &= ~(div_mask(divider) << divider->shift);
}
val |= value << divider->shift;
- ti_clk_ll_ops->clk_writel(val, divider->reg);
+ ti_clk_ll_ops->clk_writel(val, ÷r->reg);
return 0;
}
static struct clk *_register_divider(struct device *dev, const char *name,
const char *parent_name,
- unsigned long flags, void __iomem *reg,
+ unsigned long flags,
+ struct clk_omap_reg *reg,
u8 shift, u8 width, u8 clk_divider_flags,
const struct clk_div_table *table)
{
- struct clk_divider *div;
+ struct clk_omap_divider *div;
struct clk *clk;
struct clk_init_data init;
init.num_parents = (parent_name ? 1 : 0);
/* struct clk_divider assignments */
- div->reg = reg;
+ memcpy(&div->reg, reg, sizeof(*reg));
div->shift = shift;
div->width = width;
div->flags = clk_divider_flags;
div->table = table;
/* register the clock */
- clk = clk_register(dev, &div->hw);
+ clk = ti_clk_register(dev, &div->hw, name);
if (IS_ERR(clk))
kfree(div);
return clk;
}
-static struct clk_div_table *
-_get_div_table_from_setup(struct ti_clk_divider *setup, u8 *width)
+int ti_clk_parse_divider_data(int *div_table, int num_dividers, int max_div,
+ u8 flags, u8 *width,
+ const struct clk_div_table **table)
{
int valid_div = 0;
- struct clk_div_table *table;
- int i;
- int div;
u32 val;
- u8 flags;
-
- if (!setup->num_dividers) {
- /* Clk divider table not provided, determine min/max divs */
- flags = setup->flags;
+ int div;
+ int i;
+ struct clk_div_table *tmp;
+ if (!div_table) {
if (flags & CLKF_INDEX_STARTS_AT_ONE)
val = 1;
else
div = 1;
- while (div < setup->max_div) {
+ while (div < max_div) {
if (flags & CLKF_INDEX_POWER_OF_TWO)
div <<= 1;
else
}
*width = fls(val);
+ *table = NULL;
- return NULL;
+ return 0;
}
- for (i = 0; i < setup->num_dividers; i++)
- if (setup->dividers[i])
+ i = 0;
+
+ while (!num_dividers || i < num_dividers) {
+ if (div_table[i] == -1)
+ break;
+ if (div_table[i])
valid_div++;
+ i++;
+ }
- table = kzalloc(sizeof(*table) * (valid_div + 1), GFP_KERNEL);
- if (!table)
- return ERR_PTR(-ENOMEM);
+ num_dividers = i;
+
+ tmp = kzalloc(sizeof(*tmp) * (valid_div + 1), GFP_KERNEL);
+ if (!tmp)
+ return -ENOMEM;
valid_div = 0;
*width = 0;
- for (i = 0; i < setup->num_dividers; i++)
- if (setup->dividers[i]) {
- table[valid_div].div = setup->dividers[i];
- table[valid_div].val = i;
+ for (i = 0; i < num_dividers; i++)
+ if (div_table[i] > 0) {
+ tmp[valid_div].div = div_table[i];
+ tmp[valid_div].val = i;
valid_div++;
*width = i;
}
*width = fls(*width);
+ *table = tmp;
+
+ return 0;
+}
+
+static const struct clk_div_table *
+_get_div_table_from_setup(struct ti_clk_divider *setup, u8 *width)
+{
+ const struct clk_div_table *table = NULL;
+
+ ti_clk_parse_divider_data(setup->dividers, setup->num_dividers,
+ setup->max_div, setup->flags, width,
+ &table);
return table;
}
struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup)
{
- struct clk_divider *div;
+ struct clk_omap_divider *div;
struct clk_omap_reg *reg;
if (!setup)
struct clk *ti_clk_register_divider(struct ti_clk *setup)
{
- struct ti_clk_divider *div;
- struct clk_omap_reg *reg_setup;
- u32 reg;
+ struct ti_clk_divider *div = setup->data;
+ struct clk_omap_reg reg = {
+ .index = div->module,
+ .offset = div->reg,
+ };
u8 width;
u32 flags = 0;
u8 div_flags = 0;
- struct clk_div_table *table;
+ const struct clk_div_table *table;
struct clk *clk;
- div = setup->data;
-
- reg_setup = (struct clk_omap_reg *)®
-
- reg_setup->index = div->module;
- reg_setup->offset = div->reg;
-
if (div->flags & CLKF_INDEX_STARTS_AT_ONE)
div_flags |= CLK_DIVIDER_ONE_BASED;
return (struct clk *)table;
clk = _register_divider(NULL, setup->name, div->parent,
- flags, (void __iomem *)reg, div->bit_shift,
+ flags, ®, div->bit_shift,
width, div_flags, table);
if (IS_ERR(clk))
}
static int __init ti_clk_divider_populate(struct device_node *node,
- void __iomem **reg, const struct clk_div_table **table,
+ struct clk_omap_reg *reg, const struct clk_div_table **table,
u32 *flags, u8 *div_flags, u8 *width, u8 *shift)
{
u32 val;
+ int ret;
- *reg = ti_clk_get_reg_addr(node, 0);
- if (IS_ERR(*reg))
- return PTR_ERR(*reg);
+ ret = ti_clk_get_reg_addr(node, 0, reg);
+ if (ret)
+ return ret;
if (!of_property_read_u32(node, "ti,bit-shift", &val))
*shift = val;
{
struct clk *clk;
const char *parent_name;
- void __iomem *reg;
+ struct clk_omap_reg reg;
u8 clk_divider_flags = 0;
u8 width = 0;
u8 shift = 0;
&clk_divider_flags, &width, &shift))
goto cleanup;
- clk = _register_divider(NULL, node->name, parent_name, flags, reg,
+ clk = _register_divider(NULL, node->name, parent_name, flags, ®,
shift, width, clk_divider_flags, table);
if (!IS_ERR(clk)) {
static void __init of_ti_composite_divider_clk_setup(struct device_node *node)
{
- struct clk_divider *div;
+ struct clk_omap_divider *div;
u32 val;
div = kzalloc(sizeof(*div), GFP_KERNEL);
dd->clk_bypass = __clk_get_hw(clk);
/* register the clock */
- clk = clk_register(NULL, &clk_hw->hw);
+ clk = ti_clk_register(NULL, &clk_hw->hw, node->name);
if (!IS_ERR(clk)) {
omap2_init_clk_hw_omap_clocks(&clk_hw->hw);
}
#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_ATAGS)
-static void __iomem *_get_reg(u8 module, u16 offset)
+void _get_reg(u8 module, u16 offset, struct clk_omap_reg *reg)
{
- u32 reg;
- struct clk_omap_reg *reg_setup;
-
- reg_setup = (struct clk_omap_reg *)®
-
- reg_setup->index = module;
- reg_setup->offset = offset;
-
- return (void __iomem *)reg;
+ reg->index = module;
+ reg->offset = offset;
}
struct clk *ti_clk_register_dpll(struct ti_clk *setup)
clk_hw->dpll_data = dd;
clk_hw->ops = &clkhwops_omap3_dpll;
clk_hw->hw.init = &init;
- clk_hw->flags = MEMMAP_ADDRESSING;
init.name = setup->name;
init.ops = ops;
init.num_parents = dpll->num_parents;
init.parent_names = dpll->parents;
- dd->control_reg = _get_reg(dpll->module, dpll->control_reg);
- dd->idlest_reg = _get_reg(dpll->module, dpll->idlest_reg);
- dd->mult_div1_reg = _get_reg(dpll->module, dpll->mult_div1_reg);
- dd->autoidle_reg = _get_reg(dpll->module, dpll->autoidle_reg);
+ _get_reg(dpll->module, dpll->control_reg, &dd->control_reg);
+ _get_reg(dpll->module, dpll->idlest_reg, &dd->idlest_reg);
+ _get_reg(dpll->module, dpll->mult_div1_reg, &dd->mult_div1_reg);
+ _get_reg(dpll->module, dpll->autoidle_reg, &dd->autoidle_reg);
dd->modes = dpll->modes;
dd->div1_mask = dpll->div1_mask;
if (dpll->flags & CLKF_J_TYPE)
dd->flags |= DPLL_J_TYPE;
- clk = clk_register(NULL, &clk_hw->hw);
+ clk = ti_clk_register(NULL, &clk_hw->hw, setup->name);
if (!IS_ERR(clk))
return clk;
init.parent_names = &parent_name;
init.num_parents = 1;
+#if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5) || \
+ defined(CONFIG_SOC_DRA7XX)
+ if (hw_ops == &clkhwops_omap4_dpllmx) {
+ int ret;
+
+ /* Check if register defined, if not, drop hw-ops */
+ ret = of_property_count_elems_of_size(node, "reg", 1);
+ if (ret <= 0) {
+ clk_hw->ops = NULL;
+ } else if (ti_clk_get_reg_addr(node, 0, &clk_hw->clksel_reg)) {
+ kfree(clk_hw);
+ return;
+ }
+ }
+#endif
+
/* register the clock */
- clk = clk_register(NULL, &clk_hw->hw);
+ clk = ti_clk_register(NULL, &clk_hw->hw, name);
if (IS_ERR(clk)) {
kfree(clk_hw);
clk_hw->dpll_data = dd;
clk_hw->ops = &clkhwops_omap3_dpll;
clk_hw->hw.init = init;
- clk_hw->flags = MEMMAP_ADDRESSING;
init->name = node->name;
init->ops = ops;
init->parent_names = parent_names;
- dd->control_reg = ti_clk_get_reg_addr(node, 0);
+ if (ti_clk_get_reg_addr(node, 0, &dd->control_reg))
+ goto cleanup;
/*
* Special case for OMAP2 DPLL, register order is different due to
* missing idlest_mask.
*/
if (!dd->idlest_mask) {
- dd->mult_div1_reg = ti_clk_get_reg_addr(node, 1);
+ if (ti_clk_get_reg_addr(node, 1, &dd->mult_div1_reg))
+ goto cleanup;
#ifdef CONFIG_ARCH_OMAP2
clk_hw->ops = &clkhwops_omap2xxx_dpll;
omap2xxx_clkt_dpllcore_init(&clk_hw->hw);
#endif
} else {
- dd->idlest_reg = ti_clk_get_reg_addr(node, 1);
- if (IS_ERR(dd->idlest_reg))
+ if (ti_clk_get_reg_addr(node, 1, &dd->idlest_reg))
goto cleanup;
- dd->mult_div1_reg = ti_clk_get_reg_addr(node, 2);
+ if (ti_clk_get_reg_addr(node, 2, &dd->mult_div1_reg))
+ goto cleanup;
}
- if (IS_ERR(dd->control_reg) || IS_ERR(dd->mult_div1_reg))
- goto cleanup;
-
if (dd->autoidle_mask) {
- dd->autoidle_reg = ti_clk_get_reg_addr(node, 3);
- if (IS_ERR(dd->autoidle_reg))
+ if (ti_clk_get_reg_addr(node, 3, &dd->autoidle_reg))
goto cleanup;
}
dd = clk->dpll_data;
- v = ti_clk_ll_ops->clk_readl(dd->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->control_reg);
v &= ~dd->enable_mask;
v |= clken_bits << __ffs(dd->enable_mask);
- ti_clk_ll_ops->clk_writel(v, dd->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &dd->control_reg);
}
/* _omap3_wait_dpll_status: wait for a DPLL to enter a specific state */
state <<= __ffs(dd->idlest_mask);
- while (((ti_clk_ll_ops->clk_readl(dd->idlest_reg) & dd->idlest_mask)
+ while (((ti_clk_ll_ops->clk_readl(&dd->idlest_reg) & dd->idlest_mask)
!= state) && i < MAX_DPLL_WAIT_TRIES) {
i++;
udelay(1);
state <<= __ffs(dd->idlest_mask);
/* Check if already locked */
- if ((ti_clk_ll_ops->clk_readl(dd->idlest_reg) & dd->idlest_mask) ==
+ if ((ti_clk_ll_ops->clk_readl(&dd->idlest_reg) & dd->idlest_mask) ==
state)
goto done;
* only since freqsel field is no longer present on other devices.
*/
if (ti_clk_get_features()->flags & TI_CLK_DPLL_HAS_FREQSEL) {
- v = ti_clk_ll_ops->clk_readl(dd->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->control_reg);
v &= ~dd->freqsel_mask;
v |= freqsel << __ffs(dd->freqsel_mask);
- ti_clk_ll_ops->clk_writel(v, dd->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &dd->control_reg);
}
/* Set DPLL multiplier, divider */
- v = ti_clk_ll_ops->clk_readl(dd->mult_div1_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->mult_div1_reg);
/* Handle Duty Cycle Correction */
if (dd->dcc_mask) {
}
}
- ti_clk_ll_ops->clk_writel(v, dd->mult_div1_reg);
+ ti_clk_ll_ops->clk_writel(v, &dd->mult_div1_reg);
/* Set 4X multiplier and low-power mode */
if (dd->m4xen_mask || dd->lpmode_mask) {
- v = ti_clk_ll_ops->clk_readl(dd->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->control_reg);
if (dd->m4xen_mask) {
if (dd->last_rounded_m4xen)
v &= ~dd->lpmode_mask;
}
- ti_clk_ll_ops->clk_writel(v, dd->control_reg);
+ ti_clk_ll_ops->clk_writel(v, &dd->control_reg);
}
/* We let the clock framework set the other output dividers later */
dd = clk->dpll_data;
- if (!dd->autoidle_reg)
+ if (!dd->autoidle_mask)
return -EINVAL;
- v = ti_clk_ll_ops->clk_readl(dd->autoidle_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->autoidle_reg);
v &= dd->autoidle_mask;
v >>= __ffs(dd->autoidle_mask);
dd = clk->dpll_data;
- if (!dd->autoidle_reg)
+ if (!dd->autoidle_mask)
return;
/*
* by writing 0x5 instead of 0x1. Add some mechanism to
* optionally enter this mode.
*/
- v = ti_clk_ll_ops->clk_readl(dd->autoidle_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->autoidle_reg);
v &= ~dd->autoidle_mask;
v |= DPLL_AUTOIDLE_LOW_POWER_STOP << __ffs(dd->autoidle_mask);
- ti_clk_ll_ops->clk_writel(v, dd->autoidle_reg);
+ ti_clk_ll_ops->clk_writel(v, &dd->autoidle_reg);
}
/**
dd = clk->dpll_data;
- if (!dd->autoidle_reg)
+ if (!dd->autoidle_mask)
return;
- v = ti_clk_ll_ops->clk_readl(dd->autoidle_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->autoidle_reg);
v &= ~dd->autoidle_mask;
v |= DPLL_AUTOIDLE_DISABLE << __ffs(dd->autoidle_mask);
- ti_clk_ll_ops->clk_writel(v, dd->autoidle_reg);
+ ti_clk_ll_ops->clk_writel(v, &dd->autoidle_reg);
}
/* Clock control for DPLL outputs */
WARN_ON(!dd->enable_mask);
- v = ti_clk_ll_ops->clk_readl(dd->control_reg) & dd->enable_mask;
+ v = ti_clk_ll_ops->clk_readl(&dd->control_reg) & dd->enable_mask;
v >>= __ffs(dd->enable_mask);
if ((v != OMAP3XXX_EN_DPLL_LOCKED) || (dd->flags & DPLL_J_TYPE))
rate = parent_rate;
u32 v;
u32 mask;
- if (!clk || !clk->clksel_reg)
+ if (!clk)
return;
mask = clk->flags & CLOCK_CLKOUTX2 ?
OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_MASK :
OMAP4430_DPLL_CLKOUT_GATE_CTRL_MASK;
- v = ti_clk_ll_ops->clk_readl(clk->clksel_reg);
+ v = ti_clk_ll_ops->clk_readl(&clk->clksel_reg);
/* Clear the bit to allow gatectrl */
v &= ~mask;
- ti_clk_ll_ops->clk_writel(v, clk->clksel_reg);
+ ti_clk_ll_ops->clk_writel(v, &clk->clksel_reg);
}
static void omap4_dpllmx_deny_gatectrl(struct clk_hw_omap *clk)
u32 v;
u32 mask;
- if (!clk || !clk->clksel_reg)
+ if (!clk)
return;
mask = clk->flags & CLOCK_CLKOUTX2 ?
OMAP4430_DPLL_CLKOUTX2_GATE_CTRL_MASK :
OMAP4430_DPLL_CLKOUT_GATE_CTRL_MASK;
- v = ti_clk_ll_ops->clk_readl(clk->clksel_reg);
+ v = ti_clk_ll_ops->clk_readl(&clk->clksel_reg);
/* Set the bit to deny gatectrl */
v |= mask;
- ti_clk_ll_ops->clk_writel(v, clk->clksel_reg);
+ ti_clk_ll_ops->clk_writel(v, &clk->clksel_reg);
}
const struct clk_hw_omap_ops clkhwops_omap4_dpllmx = {
rate = omap2_get_dpll_rate(clk);
/* regm4xen adds a multiplier of 4 to DPLL calculations */
- v = ti_clk_ll_ops->clk_readl(dd->control_reg);
+ v = ti_clk_ll_ops->clk_readl(&dd->control_reg);
if (v & OMAP4430_DPLL_REGM4XEN_MASK)
rate *= OMAP4430_REGM4XEN_MULT;
if (!IS_ERR(clk)) {
of_clk_add_provider(node, of_clk_src_simple_get, clk);
of_ti_clk_autoidle_setup(node);
+ ti_clk_add_alias(NULL, clk, clk_name);
}
}
CLK_OF_DECLARE(ti_fixed_factor_clk, "ti,fixed-factor-clock",
.disable = &omap2_clkops_disable_clkdm,
};
-static const struct clk_ops omap_gate_clk_ops = {
+const struct clk_ops omap_gate_clk_ops = {
.init = &omap2_init_clk_clkdm,
.enable = &omap2_dflt_clk_enable,
.disable = &omap2_dflt_clk_disable,
*/
static int omap36xx_gate_clk_enable_with_hsdiv_restore(struct clk_hw *hw)
{
- struct clk_divider *parent;
+ struct clk_omap_divider *parent;
struct clk_hw *parent_hw;
u32 dummy_v, orig_v;
int ret;
/* Parent is the x2 node, get parent of parent for the m2 div */
parent_hw = clk_hw_get_parent(clk_hw_get_parent(hw));
- parent = to_clk_divider(parent_hw);
+ parent = to_clk_omap_divider(parent_hw);
/* Restore the dividers */
if (!ret) {
- orig_v = ti_clk_ll_ops->clk_readl(parent->reg);
+ orig_v = ti_clk_ll_ops->clk_readl(&parent->reg);
dummy_v = orig_v;
/* Write any other value different from the Read value */
dummy_v ^= (1 << parent->shift);
- ti_clk_ll_ops->clk_writel(dummy_v, parent->reg);
+ ti_clk_ll_ops->clk_writel(dummy_v, &parent->reg);
/* Write the original divider */
- ti_clk_ll_ops->clk_writel(orig_v, parent->reg);
+ ti_clk_ll_ops->clk_writel(orig_v, &parent->reg);
}
return ret;
static struct clk *_register_gate(struct device *dev, const char *name,
const char *parent_name, unsigned long flags,
- void __iomem *reg, u8 bit_idx,
+ struct clk_omap_reg *reg, u8 bit_idx,
u8 clk_gate_flags, const struct clk_ops *ops,
const struct clk_hw_omap_ops *hw_ops)
{
init.name = name;
init.ops = ops;
- clk_hw->enable_reg = reg;
+ memcpy(&clk_hw->enable_reg, reg, sizeof(*reg));
clk_hw->enable_bit = bit_idx;
clk_hw->ops = hw_ops;
- clk_hw->flags = MEMMAP_ADDRESSING | clk_gate_flags;
+ clk_hw->flags = clk_gate_flags;
init.parent_names = &parent_name;
init.num_parents = 1;
init.flags = flags;
- clk = clk_register(NULL, &clk_hw->hw);
+ clk = ti_clk_register(NULL, &clk_hw->hw, name);
if (IS_ERR(clk))
kfree(clk_hw);
{
const struct clk_ops *ops = &omap_gate_clk_ops;
const struct clk_hw_omap_ops *hw_ops = NULL;
- u32 reg;
- struct clk_omap_reg *reg_setup;
+ struct clk_omap_reg reg;
u32 flags = 0;
u8 clk_gate_flags = 0;
struct ti_clk_gate *gate;
if (gate->flags & CLKF_INTERFACE)
return ti_clk_register_interface(setup);
- reg_setup = (struct clk_omap_reg *)®
-
if (gate->flags & CLKF_SET_RATE_PARENT)
flags |= CLK_SET_RATE_PARENT;
if (gate->flags & CLKF_AM35XX)
hw_ops = &clkhwops_am35xx_ipss_module_wait;
- reg_setup->index = gate->module;
- reg_setup->offset = gate->reg;
+ reg.index = gate->module;
+ reg.offset = gate->reg;
+ reg.ptr = NULL;
return _register_gate(NULL, setup->name, gate->parent, flags,
- (void __iomem *)reg, gate->bit_shift,
+ ®, gate->bit_shift,
clk_gate_flags, ops, hw_ops);
}
ops = &clkhwops_iclk_wait;
gate->ops = ops;
- gate->flags = MEMMAP_ADDRESSING;
return &gate->hw;
}
{
struct clk *clk;
const char *parent_name;
- void __iomem *reg = NULL;
+ struct clk_omap_reg reg;
u8 enable_bit = 0;
u32 val;
u32 flags = 0;
u8 clk_gate_flags = 0;
if (ops != &omap_gate_clkdm_clk_ops) {
- reg = ti_clk_get_reg_addr(node, 0);
- if (IS_ERR(reg))
+ if (ti_clk_get_reg_addr(node, 0, ®))
return;
if (!of_property_read_u32(node, "ti,bit-shift", &val))
if (of_property_read_bool(node, "ti,set-bit-to-disable"))
clk_gate_flags |= INVERT_ENABLE;
- clk = _register_gate(NULL, node->name, parent_name, flags, reg,
+ clk = _register_gate(NULL, node->name, parent_name, flags, ®,
enable_bit, clk_gate_flags, ops, hw_ops);
if (!IS_ERR(clk))
if (!gate)
return;
- gate->enable_reg = ti_clk_get_reg_addr(node, 0);
- if (IS_ERR(gate->enable_reg))
+ if (ti_clk_get_reg_addr(node, 0, &gate->enable_reg))
goto cleanup;
of_property_read_u32(node, "ti,bit-shift", &val);
gate->enable_bit = val;
gate->ops = hw_ops;
- gate->flags = MEMMAP_ADDRESSING;
if (!ti_clk_add_component(node, &gate->hw, CLK_COMPONENT_TYPE_GATE))
return;
static struct clk *_register_interface(struct device *dev, const char *name,
const char *parent_name,
- void __iomem *reg, u8 bit_idx,
+ struct clk_omap_reg *reg, u8 bit_idx,
const struct clk_hw_omap_ops *ops)
{
struct clk_init_data init = { NULL };
clk_hw->hw.init = &init;
clk_hw->ops = ops;
- clk_hw->flags = MEMMAP_ADDRESSING;
- clk_hw->enable_reg = reg;
+ memcpy(&clk_hw->enable_reg, reg, sizeof(*reg));
clk_hw->enable_bit = bit_idx;
init.name = name;
init.num_parents = 1;
init.parent_names = &parent_name;
- clk = clk_register(NULL, &clk_hw->hw);
+ clk = ti_clk_register(NULL, &clk_hw->hw, name);
if (IS_ERR(clk))
kfree(clk_hw);
struct clk *ti_clk_register_interface(struct ti_clk *setup)
{
const struct clk_hw_omap_ops *ops = &clkhwops_iclk_wait;
- u32 reg;
- struct clk_omap_reg *reg_setup;
+ struct clk_omap_reg reg;
struct ti_clk_gate *gate;
gate = setup->data;
- reg_setup = (struct clk_omap_reg *)®
- reg_setup->index = gate->module;
- reg_setup->offset = gate->reg;
+ reg.index = gate->module;
+ reg.offset = gate->reg;
+ reg.ptr = NULL;
if (gate->flags & CLKF_NO_WAIT)
ops = &clkhwops_iclk;
ops = &clkhwops_am35xx_ipss_wait;
return _register_interface(NULL, setup->name, gate->parent,
- (void __iomem *)reg, gate->bit_shift, ops);
+ ®, gate->bit_shift, ops);
}
#endif
{
struct clk *clk;
const char *parent_name;
- void __iomem *reg;
+ struct clk_omap_reg reg;
u8 enable_bit = 0;
u32 val;
- reg = ti_clk_get_reg_addr(node, 0);
- if (IS_ERR(reg))
+ if (ti_clk_get_reg_addr(node, 0, ®))
return;
if (!of_property_read_u32(node, "ti,bit-shift", &val))
return;
}
- clk = _register_interface(NULL, node->name, parent_name, reg,
+ clk = _register_interface(NULL, node->name, parent_name, ®,
enable_bit, ops);
if (!IS_ERR(clk))
static u8 ti_clk_mux_get_parent(struct clk_hw *hw)
{
- struct clk_mux *mux = to_clk_mux(hw);
+ struct clk_omap_mux *mux = to_clk_omap_mux(hw);
int num_parents = clk_hw_get_num_parents(hw);
u32 val;
* OTOH, pmd_trace_clk_mux_ck uses a separate bit for each clock, so
* val = 0x4 really means "bit 2, index starts at bit 0"
*/
- val = ti_clk_ll_ops->clk_readl(mux->reg) >> mux->shift;
+ val = ti_clk_ll_ops->clk_readl(&mux->reg) >> mux->shift;
val &= mux->mask;
if (mux->table) {
static int ti_clk_mux_set_parent(struct clk_hw *hw, u8 index)
{
- struct clk_mux *mux = to_clk_mux(hw);
+ struct clk_omap_mux *mux = to_clk_omap_mux(hw);
u32 val;
if (mux->table) {
if (mux->flags & CLK_MUX_HIWORD_MASK) {
val = mux->mask << (mux->shift + 16);
} else {
- val = ti_clk_ll_ops->clk_readl(mux->reg);
+ val = ti_clk_ll_ops->clk_readl(&mux->reg);
val &= ~(mux->mask << mux->shift);
}
val |= index << mux->shift;
- ti_clk_ll_ops->clk_writel(val, mux->reg);
+ ti_clk_ll_ops->clk_writel(val, &mux->reg);
return 0;
}
};
static struct clk *_register_mux(struct device *dev, const char *name,
- const char **parent_names, u8 num_parents,
- unsigned long flags, void __iomem *reg,
- u8 shift, u32 mask, u8 clk_mux_flags,
- u32 *table)
+ const char * const *parent_names,
+ u8 num_parents, unsigned long flags,
+ struct clk_omap_reg *reg, u8 shift, u32 mask,
+ u8 clk_mux_flags, u32 *table)
{
- struct clk_mux *mux;
+ struct clk_omap_mux *mux;
struct clk *clk;
struct clk_init_data init;
init.num_parents = num_parents;
/* struct clk_mux assignments */
- mux->reg = reg;
+ memcpy(&mux->reg, reg, sizeof(*reg));
mux->shift = shift;
mux->mask = mask;
mux->flags = clk_mux_flags;
mux->table = table;
mux->hw.init = &init;
- clk = clk_register(dev, &mux->hw);
+ clk = ti_clk_register(dev, &mux->hw, name);
if (IS_ERR(clk))
kfree(mux);
struct ti_clk_mux *mux;
u32 flags;
u8 mux_flags = 0;
- struct clk_omap_reg *reg_setup;
- u32 reg;
+ struct clk_omap_reg reg;
u32 mask;
- reg_setup = (struct clk_omap_reg *)®
-
mux = setup->data;
flags = CLK_SET_RATE_NO_REPARENT;
mask--;
mask = (1 << fls(mask)) - 1;
- reg_setup->index = mux->module;
- reg_setup->offset = mux->reg;
+ reg.index = mux->module;
+ reg.offset = mux->reg;
+ reg.ptr = NULL;
if (mux->flags & CLKF_INDEX_STARTS_AT_ONE)
mux_flags |= CLK_MUX_INDEX_ONE;
flags |= CLK_SET_RATE_PARENT;
return _register_mux(NULL, setup->name, mux->parents, mux->num_parents,
- flags, (void __iomem *)reg, mux->bit_shift, mask,
+ flags, ®, mux->bit_shift, mask,
mux_flags, NULL);
}
static void of_mux_clk_setup(struct device_node *node)
{
struct clk *clk;
- void __iomem *reg;
+ struct clk_omap_reg reg;
unsigned int num_parents;
const char **parent_names;
u8 clk_mux_flags = 0;
of_clk_parent_fill(node, parent_names, num_parents);
- reg = ti_clk_get_reg_addr(node, 0);
-
- if (IS_ERR(reg))
+ if (ti_clk_get_reg_addr(node, 0, ®))
goto cleanup;
of_property_read_u32(node, "ti,bit-shift", &shift);
mask = (1 << fls(mask)) - 1;
clk = _register_mux(NULL, node->name, parent_names, num_parents,
- flags, reg, shift, mask, clk_mux_flags, NULL);
+ flags, ®, shift, mask, clk_mux_flags, NULL);
if (!IS_ERR(clk))
of_clk_add_provider(node, of_clk_src_simple_get, clk);
struct clk_hw *ti_clk_build_component_mux(struct ti_clk_mux *setup)
{
- struct clk_mux *mux;
- struct clk_omap_reg *reg;
+ struct clk_omap_mux *mux;
int num_parents;
if (!setup)
if (!mux)
return ERR_PTR(-ENOMEM);
- reg = (struct clk_omap_reg *)&mux->reg;
-
mux->shift = setup->bit_shift;
- reg->index = setup->module;
- reg->offset = setup->reg;
+ mux->reg.index = setup->module;
+ mux->reg.offset = setup->reg;
if (setup->flags & CLKF_INDEX_STARTS_AT_ONE)
mux->flags |= CLK_MUX_INDEX_ONE;
static void __init of_ti_composite_mux_clk_setup(struct device_node *node)
{
- struct clk_mux *mux;
+ struct clk_omap_mux *mux;
unsigned int num_parents;
u32 val;
if (!mux)
return;
- mux->reg = ti_clk_get_reg_addr(node, 0);
-
- if (IS_ERR(mux->reg))
+ if (ti_clk_get_reg_addr(node, 0, &mux->reg))
goto cleanup;
if (!of_property_read_u32(node, "ti,bit-shift", &val))
struct clk_plt_fixed **parents;
u8 nparents;
struct clk_plt *clks[PMC_CLK_NUM];
+ struct clk_lookup *mclk_lookup;
};
/* Return an index in parent table */
goto err_unreg_clk_plt;
}
}
+ data->mclk_lookup = clkdev_hw_create(&data->clks[3]->hw, "mclk", NULL);
+ if (!data->mclk_lookup) {
+ err = -ENOMEM;
+ goto err_unreg_clk_plt;
+ }
plt_clk_free_parent_names_loop(parent_names, data->nparents);
data = platform_get_drvdata(pdev);
+ clkdev_drop(data->mclk_lookup);
plt_clk_unregister_loop(data, PMC_CLK_NUM);
plt_clk_unregister_parents(data);
return 0;
static DEFINE_SPINLOCK(clk_lock);
-static struct zx_pll_config pll_cpu_table[] = {
+static const struct zx_pll_config pll_cpu_table[] = {
PLL_RATE(1312000000, 0x00103621, 0x04aaaaaa),
PLL_RATE(1407000000, 0x00103a21, 0x04aaaaaa),
PLL_RATE(1503000000, 0x00103e21, 0x04aaaaaa),
PLL_RATE(1600000000, 0x00104221, 0x04aaaaaa),
};
+static const struct zx_pll_config pll_vga_table[] = {
+ PLL_RATE(36000000, 0x00102464, 0x04000000), /* 800x600@56 */
+ PLL_RATE(40000000, 0x00102864, 0x04000000), /* 800x600@60 */
+ PLL_RATE(49500000, 0x00103164, 0x04800000), /* 800x600@75 */
+ PLL_RATE(50000000, 0x00103264, 0x04000000), /* 800x600@72 */
+ PLL_RATE(56250000, 0x00103864, 0x04400000), /* 800x600@85 */
+ PLL_RATE(65000000, 0x00104164, 0x04000000), /* 1024x768@60 */
+ PLL_RATE(74375000, 0x00104a64, 0x04600000), /* 1280x720@60 */
+ PLL_RATE(75000000, 0x00104b64, 0x04800000), /* 1024x768@70 */
+ PLL_RATE(78750000, 0x00104e64, 0x04c00000), /* 1024x768@75 */
+ PLL_RATE(85500000, 0x00105564, 0x04800000), /* 1360x768@60 */
+ PLL_RATE(106500000, 0x00106a64, 0x04800000), /* 1440x900@60 */
+ PLL_RATE(108000000, 0x00106c64, 0x04000000), /* 1280x1024@60 */
+ PLL_RATE(110000000, 0x00106e64, 0x04000000), /* 1024x768@85 */
+ PLL_RATE(135000000, 0x00105a44, 0x04000000), /* 1280x1024@75 */
+ PLL_RATE(136750000, 0x00104462, 0x04600000), /* 1440x900@75 */
+ PLL_RATE(148500000, 0x00104a62, 0x04400000), /* 1920x1080@60 */
+ PLL_RATE(157000000, 0x00104e62, 0x04800000), /* 1440x900@85 */
+ PLL_RATE(157500000, 0x00104e62, 0x04c00000), /* 1280x1024@85 */
+ PLL_RATE(162000000, 0x00105162, 0x04000000), /* 1600x1200@60 */
+ PLL_RATE(193250000, 0x00106062, 0x04a00000), /* 1920x1200@60 */
+};
+
PNAME(osc) = {
"osc24m",
"osc32k",
static struct clk_zx_pll zx296718_pll_clk[] = {
ZX296718_PLL("pll_cpu", "osc24m", PLL_CPU_REG, pll_cpu_table),
+ ZX296718_PLL("pll_vga", "osc24m", PLL_VGA_REG, pll_vga_table),
};
static struct zx_clk_fixed_factor top_ffactor_clk[] = {
FFACTOR(0, "clk54m", "pll_mm1", 1, 24, 0),
/* vga */
FFACTOR(0, "pll_vga_1800m", "pll_vga", 1, 1, 0),
- FFACTOR(0, "clk_vga", "pll_vga", 1, 2, 0),
+ FFACTOR(0, "clk_vga", "pll_vga", 1, 1, CLK_SET_RATE_PARENT),
/* pll ddr */
FFACTOR(0, "clk466m", "pll_ddr", 1, 2, 0),
MUX(0, "sappu_a_mux", sappu_aclk_p, TOP_CLK_MUX5, 4, 2),
MUX(0, "sappu_w_mux", sappu_wclk_p, TOP_CLK_MUX5, 8, 3),
MUX(0, "vou_a_mux", vou_aclk_p, TOP_CLK_MUX7, 0, 3),
- MUX(0, "vou_main_w_mux", vou_main_wclk_p, TOP_CLK_MUX7, 4, 3),
- MUX(0, "vou_aux_w_mux", vou_aux_wclk_p, TOP_CLK_MUX7, 8, 3),
+ MUX_F(0, "vou_main_w_mux", vou_main_wclk_p, TOP_CLK_MUX7, 4, 3, CLK_SET_RATE_PARENT, 0),
+ MUX_F(0, "vou_aux_w_mux", vou_aux_wclk_p, TOP_CLK_MUX7, 8, 3, CLK_SET_RATE_PARENT, 0),
MUX(0, "vou_ppu_w_mux", vou_ppu_wclk_p, TOP_CLK_MUX7, 12, 3),
MUX(0, "vga_i2c_mux", vga_i2c_wclk_p, TOP_CLK_MUX7, 16, 1),
MUX(0, "viu_m0_a_mux", viu_m0_aclk_p, TOP_CLK_MUX6, 0, 3),
/* For matching the value in lookup table */
hw_cfg0 &= ~BIT(zx_pll->lock_bit);
- hw_cfg0 |= BIT(zx_pll->pd_bit);
+
+ /* Check availability of pd_bit */
+ if (zx_pll->pd_bit < 32)
+ hw_cfg0 |= BIT(zx_pll->pd_bit);
for (i = 0; i < zx_pll->count; i++) {
if (hw_cfg0 == config[i].cfg0 && hw_cfg1 == config[i].cfg1)
struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw);
u32 reg;
+ /* If pd_bit is not available, simply return success. */
+ if (zx_pll->pd_bit > 31)
+ return 0;
+
reg = readl_relaxed(zx_pll->reg_base);
writel_relaxed(reg & ~BIT(zx_pll->pd_bit), zx_pll->reg_base);
struct clk_zx_pll *zx_pll = to_clk_zx_pll(hw);
u32 reg;
+ if (zx_pll->pd_bit > 31)
+ return;
+
reg = readl_relaxed(zx_pll->reg_base);
writel_relaxed(reg | BIT(zx_pll->pd_bit), zx_pll->reg_base);
}
CLK_GET_RATE_NOCACHE), \
}
+/*
+ * The pd_bit is not available on ZX296718, so let's pass something
+ * bigger than 31, e.g. 0xff, to indicate that.
+ */
#define ZX296718_PLL(_name, _parent, _reg, _table) \
-ZX_PLL(_name, _parent, _reg, _table, 0, 30)
+ZX_PLL(_name, _parent, _reg, _table, 0xff, 30)
struct zx_clk_gate {
struct clk_gate gate;
#define DRV_NAME "cs5535-clockevt"
static int timer_irq;
-module_param_named(irq, timer_irq, int, 0644);
+module_param_hw_named(irq, timer_irq, int, irq, 0644);
MODULE_PARM_DESC(irq, "Which IRQ to use for the clock source MFGPT ticks.");
/*
cpufreq_unregister_driver(&speedstep_driver);
}
-module_param(smi_port, int, 0444);
+module_param_hw(smi_port, int, ioport, 0444);
module_param(smi_cmd, int, 0444);
module_param(smi_sig, uint, 0444);
preempt_disable();
dev = cpuidle_get_device();
- dev->use_deepest_state = enable;
+ if (dev)
+ dev->use_deepest_state = enable;
preempt_enable();
}
names[i] = vi->data_vq[i].name;
}
- ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
- names, NULL);
+ ret = virtio_find_vqs(vi->vdev, total_vqs, vqs, callbacks, names, NULL);
if (ret)
goto err_find;
Enable support for the Timberdale FPGA DMA engine.
config TI_CPPI41
- tristate "AM33xx CPPI41 DMA support"
- depends on ARCH_OMAP
+ tristate "CPPI 4.1 DMA support"
+ depends on (ARCH_OMAP || ARCH_DAVINCI_DA8XX)
select DMA_ENGINE
help
The Communications Port Programming Interface (CPPI) 4.1 DMA engine
- is currently used by the USB driver on AM335x platforms.
+ is currently used by the USB driver on AM335x and DA8xx platforms.
config TI_DMA_CROSSBAR
bool
config DMATEST
tristate "DMA Test client"
depends on DMA_ENGINE
+ select DMA_ENGINE_RAID
help
Simple DMA test client. Say N unless you're debugging a
DMA Device driver.
/**
* struct vendor_data - vendor-specific config parameters for PL08x derivatives
+ * @config_offset: offset to the configuration register
* @channels: the number of channels available in this variant
* @signals: the number of request signals available from the hardware
* @dualmaster: whether this version supports dual AHB masters or not.
/**
* struct pl08x_phy_chan - holder for the physical channels
* @id: physical index to this channel
+ * @base: memory base address for this physical channel
+ * @reg_config: configuration address for this physical channel
* @lock: a lock to use when altering an instance of this struct
* @serving: the virtual channel currently being served by this physical
* channel
};
/**
- * struct pl08x_dma_chan_state - holds the PL08x specific virtual channel
+ * enum pl08x_dma_chan_state - holds the PL08x specific virtual channel
* states
* @PL08X_CHAN_IDLE: the channel is idle
* @PL08X_CHAN_RUNNING: the channel has allocated a physical transport
* @phychan: the physical channel utilized by this channel, if there is one
* @name: name of channel
* @cd: channel platform data
- * @runtime_addr: address for RX/TX according to the runtime config
+ * @cfg: slave configuration
* @at: active transaction on this channel
- * @lock: a lock for this channel data
* @host: a pointer to the host (internal use)
* @state: whether the channel is idle, paused, running etc
* @slave: whether this channel is a device (slave) or for memcpy
* @lli_buses: bitmask to or in to LLI pointer selecting AHB port for LLI
* fetches
* @mem_buses: set to indicate memory transfers on AHB2.
- * @lock: a spinlock for this struct
+ * @lli_words: how many words are used in each LLI item for this variant
*/
struct pl08x_driver_data {
struct dma_device slave;
/* Enable the DMA channel */
/* Do not access config register until channel shows as disabled */
- while (readl(pl08x->base + PL080_EN_CHAN) & (1 << phychan->id))
+ while (readl(pl08x->base + PL080_EN_CHAN) & BIT(phychan->id))
cpu_relax();
/* Do not access config register until channel shows as inactive */
writel(val, ch->reg_config);
- writel(1 << ch->id, pl08x->base + PL080_ERR_CLEAR);
- writel(1 << ch->id, pl08x->base + PL080_TC_CLEAR);
+ writel(BIT(ch->id), pl08x->base + PL080_ERR_CLEAR);
+ writel(BIT(ch->id), pl08x->base + PL080_TC_CLEAR);
}
static inline u32 get_bytes_in_cctl(u32 cctl)
return IRQ_NONE;
for (i = 0; i < pl08x->vd->channels; i++) {
- if (((1 << i) & err) || ((1 << i) & tc)) {
+ if ((BIT(i) & err) || (BIT(i) & tc)) {
/* Locate physical channel */
struct pl08x_phy_chan *phychan = &pl08x->phy_chans[i];
struct pl08x_dma_chan *plchan = phychan->serving;
}
spin_unlock(&plchan->vc.lock);
- mask |= (1 << i);
+ mask |= BIT(i);
}
}
#define QMGR_MEMCTRL_IDX_SH 16
#define QMGR_MEMCTRL_DESC_SH 8
-#define QMGR_NUM_PEND 5
#define QMGR_PEND(x) (0x90 + (x) * 4)
#define QMGR_PENDING_SLOT_Q(x) (x / 32)
u32 first_td_desc;
struct cppi41_channel *chan_busy[ALLOC_DECS_NUM];
- void __iomem *usbss_mem;
void __iomem *ctrl_mem;
void __iomem *sched_mem;
void __iomem *qmgr_mem;
const struct chan_queues *queues_rx;
const struct chan_queues *queues_tx;
struct chan_queues td_queue;
+ u16 first_completion_queue;
+ u16 qmgr_num_pend;
+ u32 n_chans;
+ u8 platform;
struct list_head pending; /* Pending queued transfers */
spinlock_t lock; /* Lock for pending list */
bool is_suspended;
};
-#define FIST_COMPLETION_QUEUE 93
-static struct chan_queues usb_queues_tx[] = {
+static struct chan_queues am335x_usb_queues_tx[] = {
/* USB0 ENDP 1 */
[ 0] = { .submit = 32, .complete = 93},
[ 1] = { .submit = 34, .complete = 94},
[29] = { .submit = 90, .complete = 139},
};
-static const struct chan_queues usb_queues_rx[] = {
+static const struct chan_queues am335x_usb_queues_rx[] = {
/* USB0 ENDP 1 */
[ 0] = { .submit = 1, .complete = 109},
[ 1] = { .submit = 2, .complete = 110},
[29] = { .submit = 30, .complete = 155},
};
+static const struct chan_queues da8xx_usb_queues_tx[] = {
+ [0] = { .submit = 16, .complete = 24},
+ [1] = { .submit = 18, .complete = 24},
+ [2] = { .submit = 20, .complete = 24},
+ [3] = { .submit = 22, .complete = 24},
+};
+
+static const struct chan_queues da8xx_usb_queues_rx[] = {
+ [0] = { .submit = 1, .complete = 26},
+ [1] = { .submit = 3, .complete = 26},
+ [2] = { .submit = 5, .complete = 26},
+ [3] = { .submit = 7, .complete = 26},
+};
+
struct cppi_glue_infos {
- irqreturn_t (*isr)(int irq, void *data);
const struct chan_queues *queues_rx;
const struct chan_queues *queues_tx;
struct chan_queues td_queue;
+ u16 first_completion_queue;
+ u16 qmgr_num_pend;
};
static struct cppi41_channel *to_cpp41_chan(struct dma_chan *c)
static irqreturn_t cppi41_irq(int irq, void *data)
{
struct cppi41_dd *cdd = data;
+ u16 first_completion_queue = cdd->first_completion_queue;
+ u16 qmgr_num_pend = cdd->qmgr_num_pend;
struct cppi41_channel *c;
int i;
- for (i = QMGR_PENDING_SLOT_Q(FIST_COMPLETION_QUEUE); i < QMGR_NUM_PEND;
+ for (i = QMGR_PENDING_SLOT_Q(first_completion_queue); i < qmgr_num_pend;
i++) {
u32 val;
u32 q_num;
val = cppi_readl(cdd->qmgr_mem + QMGR_PEND(i));
- if (i == QMGR_PENDING_SLOT_Q(FIST_COMPLETION_QUEUE) && val) {
+ if (i == QMGR_PENDING_SLOT_Q(first_completion_queue) && val) {
u32 mask;
/* set corresponding bit for completetion Q 93 */
- mask = 1 << QMGR_PENDING_BIT_Q(FIST_COMPLETION_QUEUE);
+ mask = 1 << QMGR_PENDING_BIT_Q(first_completion_queue);
/* not set all bits for queues less than Q 93 */
mask--;
/* now invert and keep only Q 93+ set */
struct cppi41_channel *c = to_cpp41_chan(chan);
enum dma_status ret;
- /* lock */
ret = dma_cookie_status(chan, cookie, txstate);
- if (txstate && ret == DMA_COMPLETE)
- txstate->residue = c->residue;
- /* unlock */
+
+ dma_set_residue(txstate, c->residue);
return ret;
}
if (!c->is_tx) {
reg |= GCR_STARV_RETRY;
reg |= GCR_DESC_TYPE_HOST;
- reg |= c->q_comp_num;
+ reg |= cdd->td_queue.complete;
}
reg |= GCR_TEARDOWN;
cppi_writel(reg, c->gcr_reg);
if (!c->td_seen || !c->td_desc_seen) {
desc_phys = cppi41_pop_desc(cdd, cdd->td_queue.complete);
- if (!desc_phys)
+ if (!desc_phys && c->is_tx)
desc_phys = cppi41_pop_desc(cdd, c->q_comp_num);
if (desc_phys == c->desc_phys) {
return 0;
}
-static void cleanup_chans(struct cppi41_dd *cdd)
-{
- while (!list_empty(&cdd->ddev.channels)) {
- struct cppi41_channel *cchan;
-
- cchan = list_first_entry(&cdd->ddev.channels,
- struct cppi41_channel, chan.device_node);
- list_del(&cchan->chan.device_node);
- kfree(cchan);
- }
-}
-
static int cppi41_add_chans(struct device *dev, struct cppi41_dd *cdd)
{
- struct cppi41_channel *cchan;
+ struct cppi41_channel *cchan, *chans;
int i;
- int ret;
- u32 n_chans;
+ u32 n_chans = cdd->n_chans;
- ret = of_property_read_u32(dev->of_node, "#dma-channels",
- &n_chans);
- if (ret)
- return ret;
/*
* The channels can only be used as TX or as RX. So we add twice
* that much dma channels because USB can only do RX or TX.
*/
n_chans *= 2;
+ chans = devm_kcalloc(dev, n_chans, sizeof(*chans), GFP_KERNEL);
+ if (!chans)
+ return -ENOMEM;
+
for (i = 0; i < n_chans; i++) {
- cchan = kzalloc(sizeof(*cchan), GFP_KERNEL);
- if (!cchan)
- goto err;
+ cchan = &chans[i];
cchan->cdd = cdd;
if (i & 1) {
cdd->first_td_desc = n_chans;
return 0;
-err:
- cleanup_chans(cdd);
- return -ENOMEM;
}
static void purge_descs(struct device *dev, struct cppi41_dd *cdd)
word = 0;
cppi_writel(0, cdd->sched_mem + DMA_SCHED_CTRL);
- for (ch = 0; ch < 15 * 2; ch += 2) {
+ for (ch = 0; ch < cdd->n_chans; ch += 2) {
reg = SCHED_ENTRY0_CHAN(ch);
reg |= SCHED_ENTRY1_CHAN(ch) | SCHED_ENTRY1_IS_RX;
cppi_writel(reg, cdd->sched_mem + DMA_SCHED_WORD(word));
word++;
}
- reg = 15 * 2 * 2 - 1;
+ reg = cdd->n_chans * 2 - 1;
reg |= DMA_SCHED_CTRL_EN;
cppi_writel(reg, cdd->sched_mem + DMA_SCHED_CTRL);
}
return -ENOMEM;
cppi_writel(cdd->scratch_phys, cdd->qmgr_mem + QMGR_LRAM0_BASE);
- cppi_writel(QMGR_SCRATCH_SIZE, cdd->qmgr_mem + QMGR_LRAM_SIZE);
+ cppi_writel(TOTAL_DESCS_NUM, cdd->qmgr_mem + QMGR_LRAM_SIZE);
cppi_writel(0, cdd->qmgr_mem + QMGR_LRAM1_BASE);
ret = init_descs(dev, cdd);
cppi_writel(cdd->td_queue.submit, cdd->ctrl_mem + DMA_TDFDQ);
init_sched(cdd);
+
return 0;
err_td:
deinit_cppi41(dev, cdd);
else
queues = cdd->queues_rx;
- BUILD_BUG_ON(ARRAY_SIZE(usb_queues_rx) != ARRAY_SIZE(usb_queues_tx));
- if (WARN_ON(cchan->port_num > ARRAY_SIZE(usb_queues_rx)))
+ BUILD_BUG_ON(ARRAY_SIZE(am335x_usb_queues_rx) !=
+ ARRAY_SIZE(am335x_usb_queues_tx));
+ if (WARN_ON(cchan->port_num > ARRAY_SIZE(am335x_usb_queues_rx)))
return false;
cchan->q_num = queues[cchan->port_num].submit;
&dma_spec->args[0]);
}
-static const struct cppi_glue_infos usb_infos = {
- .isr = cppi41_irq,
- .queues_rx = usb_queues_rx,
- .queues_tx = usb_queues_tx,
+static const struct cppi_glue_infos am335x_usb_infos = {
+ .queues_rx = am335x_usb_queues_rx,
+ .queues_tx = am335x_usb_queues_tx,
.td_queue = { .submit = 31, .complete = 0 },
+ .first_completion_queue = 93,
+ .qmgr_num_pend = 5,
+};
+
+static const struct cppi_glue_infos da8xx_usb_infos = {
+ .queues_rx = da8xx_usb_queues_rx,
+ .queues_tx = da8xx_usb_queues_tx,
+ .td_queue = { .submit = 31, .complete = 0 },
+ .first_completion_queue = 24,
+ .qmgr_num_pend = 2,
};
static const struct of_device_id cppi41_dma_ids[] = {
- { .compatible = "ti,am3359-cppi41", .data = &usb_infos},
+ { .compatible = "ti,am3359-cppi41", .data = &am335x_usb_infos},
+ { .compatible = "ti,da830-cppi41", .data = &da8xx_usb_infos},
{},
};
MODULE_DEVICE_TABLE(of, cppi41_dma_ids);
struct cppi41_dd *cdd;
struct device *dev = &pdev->dev;
const struct cppi_glue_infos *glue_info;
+ struct resource *mem;
+ int index;
int irq;
int ret;
INIT_LIST_HEAD(&cdd->ddev.channels);
cpp41_dma_info.dma_cap = cdd->ddev.cap_mask;
- cdd->usbss_mem = of_iomap(dev->of_node, 0);
- cdd->ctrl_mem = of_iomap(dev->of_node, 1);
- cdd->sched_mem = of_iomap(dev->of_node, 2);
- cdd->qmgr_mem = of_iomap(dev->of_node, 3);
+ index = of_property_match_string(dev->of_node,
+ "reg-names", "controller");
+ if (index < 0)
+ return index;
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, index);
+ cdd->ctrl_mem = devm_ioremap_resource(dev, mem);
+ if (IS_ERR(cdd->ctrl_mem))
+ return PTR_ERR(cdd->ctrl_mem);
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, index + 1);
+ cdd->sched_mem = devm_ioremap_resource(dev, mem);
+ if (IS_ERR(cdd->sched_mem))
+ return PTR_ERR(cdd->sched_mem);
+
+ mem = platform_get_resource(pdev, IORESOURCE_MEM, index + 2);
+ cdd->qmgr_mem = devm_ioremap_resource(dev, mem);
+ if (IS_ERR(cdd->qmgr_mem))
+ return PTR_ERR(cdd->qmgr_mem);
+
spin_lock_init(&cdd->lock);
INIT_LIST_HEAD(&cdd->pending);
platform_set_drvdata(pdev, cdd);
- if (!cdd->usbss_mem || !cdd->ctrl_mem || !cdd->sched_mem ||
- !cdd->qmgr_mem)
- return -ENXIO;
-
pm_runtime_enable(dev);
pm_runtime_set_autosuspend_delay(dev, 100);
pm_runtime_use_autosuspend(dev);
cdd->queues_rx = glue_info->queues_rx;
cdd->queues_tx = glue_info->queues_tx;
cdd->td_queue = glue_info->td_queue;
+ cdd->qmgr_num_pend = glue_info->qmgr_num_pend;
+ cdd->first_completion_queue = glue_info->first_completion_queue;
+
+ ret = of_property_read_u32(dev->of_node,
+ "#dma-channels", &cdd->n_chans);
+ if (ret)
+ goto err_get_n_chans;
ret = init_cppi41(dev, cdd);
if (ret)
irq = irq_of_parse_and_map(dev->of_node, 0);
if (!irq) {
ret = -EINVAL;
- goto err_irq;
+ goto err_chans;
}
- ret = devm_request_irq(&pdev->dev, irq, glue_info->isr, IRQF_SHARED,
+ ret = devm_request_irq(&pdev->dev, irq, cppi41_irq, IRQF_SHARED,
dev_name(dev), cdd);
if (ret)
- goto err_irq;
+ goto err_chans;
cdd->irq = irq;
ret = dma_async_device_register(&cdd->ddev);
if (ret)
- goto err_dma_reg;
+ goto err_chans;
ret = of_dma_controller_register(dev->of_node,
cppi41_dma_xlate, &cpp41_dma_info);
return 0;
err_of:
dma_async_device_unregister(&cdd->ddev);
-err_dma_reg:
-err_irq:
- cleanup_chans(cdd);
err_chans:
deinit_cppi41(dev, cdd);
err_init_cppi:
pm_runtime_dont_use_autosuspend(dev);
+err_get_n_chans:
err_get_sync:
pm_runtime_put_sync(dev);
pm_runtime_disable(dev);
- iounmap(cdd->usbss_mem);
- iounmap(cdd->ctrl_mem);
- iounmap(cdd->sched_mem);
- iounmap(cdd->qmgr_mem);
return ret;
}
dma_async_device_unregister(&cdd->ddev);
devm_free_irq(&pdev->dev, cdd->irq, cdd);
- cleanup_chans(cdd);
deinit_cppi41(&pdev->dev, cdd);
- iounmap(cdd->usbss_mem);
- iounmap(cdd->ctrl_mem);
- iounmap(cdd->sched_mem);
- iounmap(cdd->qmgr_mem);
pm_runtime_dont_use_autosuspend(&pdev->dev);
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
total_tests++;
+ /* Check if buffer count fits into map count variable (u8) */
+ if ((src_cnt + dst_cnt) >= 255) {
+ pr_err("too many buffers (%d of 255 supported)\n",
+ src_cnt + dst_cnt);
+ break;
+ }
+
if (1 << align > params->buf_size) {
pr_err("%u-byte buffer too small for %d-byte alignment\n",
params->buf_size, 1 << align);
for (i = 0; i < src_cnt; i++) {
void *buf = thread->srcs[i];
struct page *pg = virt_to_page(buf);
- unsigned pg_off = (unsigned long) buf & ~PAGE_MASK;
+ unsigned long pg_off = offset_in_page(buf);
um->addr[i] = dma_map_page(dev->dev, pg, pg_off,
um->len, DMA_TO_DEVICE);
for (i = 0; i < dst_cnt; i++) {
void *buf = thread->dsts[i];
struct page *pg = virt_to_page(buf);
- unsigned pg_off = (unsigned long) buf & ~PAGE_MASK;
+ unsigned long pg_off = offset_in_page(buf);
dsts[i] = dma_map_page(dev->dev, pg, pg_off, um->len,
DMA_BIDIRECTIONAL);
return 0;
}
+static int sdma_disable_channel_with_delay(struct dma_chan *chan)
+{
+ sdma_disable_channel(chan);
+
+ /*
+ * According to NXP R&D team a delay of one BD SDMA cost time
+ * (maximum is 1ms) should be added after disable of the channel
+ * bit, to ensure SDMA core has really been stopped after SDMA
+ * clients call .device_terminate_all.
+ */
+ mdelay(1);
+
+ return 0;
+}
+
static void sdma_set_watermarklevel_for_p2p(struct sdma_channel *sdmac)
{
struct sdma_engine *sdma = sdmac->sdma;
sdma->dma_device.device_prep_slave_sg = sdma_prep_slave_sg;
sdma->dma_device.device_prep_dma_cyclic = sdma_prep_dma_cyclic;
sdma->dma_device.device_config = sdma_config;
- sdma->dma_device.device_terminate_all = sdma_disable_channel;
+ sdma->dma_device.device_terminate_all = sdma_disable_channel_with_delay;
sdma->dma_device.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
sdma->dma_device.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
sdma->dma_device.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
- sdma->dma_device.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+ sdma->dma_device.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
sdma->dma_device.device_issue_pending = sdma_issue_pending;
sdma->dma_device.dev->dma_parms = &sdma->dma_parms;
dma_set_max_seg_size(sdma->dma_device.dev, 65535);
dma_cookie_init(&ioat_chan->dma_chan);
list_add_tail(&ioat_chan->dma_chan.device_node, &dma->channels);
ioat_dma->idx[idx] = ioat_chan;
- init_timer(&ioat_chan->timer);
- ioat_chan->timer.function = ioat_timer_event;
- ioat_chan->timer.data = data;
+ setup_timer(&ioat_chan->timer, ioat_timer_event, data);
tasklet_init(&ioat_chan->cleanup_task, ioat_cleanup_event, data);
}
}
src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src),
- (size_t)src & ~PAGE_MASK, PAGE_SIZE,
+ offset_in_page(src), PAGE_SIZE,
DMA_TO_DEVICE);
unmap->addr[0] = src_dma;
unmap->to_cnt = 1;
dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest),
- (size_t)dest & ~PAGE_MASK, PAGE_SIZE,
+ offset_in_page(dest), PAGE_SIZE,
DMA_FROM_DEVICE);
unmap->addr[1] = dest_dma;
int irq;
cd = &pdata->channels[i];
- if (!cd) {
- ret = -ENODEV;
- goto err_channel_add;
- }
-
irq = platform_get_irq(pdev, i);
if (irq < 0) {
ret = irq;
#include <linux/dma-mapping.h>
#include <linux/dmaengine.h>
#include <linux/amba/bus.h>
-#include <linux/amba/pl330.h>
#include <linux/scatterlist.h>
#include <linux/of.h>
#include <linux/of_dma.h>
}
}
-bool pl330_filter(struct dma_chan *chan, void *param)
-{
- u8 *peri_id;
-
- if (chan->device->dev->driver != &pl330_driver.drv)
- return false;
-
- peri_id = chan->private;
- return *peri_id == (unsigned long)param;
-}
-EXPORT_SYMBOL(pl330_filter);
-
static struct dma_chan *of_dma_pl330_xlate(struct of_phandle_args *dma_spec,
struct of_dma *ofdma)
{
static int
pl330_probe(struct amba_device *adev, const struct amba_id *id)
{
- struct dma_pl330_platdata *pdat;
struct pl330_config *pcfg;
struct pl330_dmac *pl330;
struct dma_pl330_chan *pch, *_p;
int num_chan;
struct device_node *np = adev->dev.of_node;
- pdat = dev_get_platdata(&adev->dev);
-
ret = dma_set_mask_and_coherent(&adev->dev, DMA_BIT_MASK(32));
if (ret)
return ret;
pd = &pl330->ddma;
pd->dev = &adev->dev;
- pl330->mcbufsz = pdat ? pdat->mcbuf_sz : 0;
+ pl330->mcbufsz = 0;
/* get quirk */
for (i = 0; i < ARRAY_SIZE(of_quirks); i++)
INIT_LIST_HEAD(&pd->channels);
/* Initialize channel parameters */
- if (pdat)
- num_chan = max_t(int, pdat->nr_valid_peri, pcfg->num_chan);
- else
- num_chan = max_t(int, pcfg->num_peri, pcfg->num_chan);
+ num_chan = max_t(int, pcfg->num_peri, pcfg->num_chan);
pl330->num_peripherals = num_chan;
for (i = 0; i < num_chan; i++) {
pch = &pl330->peripherals[i];
- if (!adev->dev.of_node)
- pch->chan.private = pdat ? &pdat->peri_id[i] : NULL;
- else
- pch->chan.private = adev->dev.of_node;
+ pch->chan.private = adev->dev.of_node;
INIT_LIST_HEAD(&pch->submitted_list);
INIT_LIST_HEAD(&pch->work_list);
INIT_LIST_HEAD(&pch->completed_list);
list_add_tail(&pch->chan.device_node, &pd->channels);
}
- if (pdat) {
- pd->cap_mask = pdat->cap_mask;
- } else {
- dma_cap_set(DMA_MEMCPY, pd->cap_mask);
- if (pcfg->num_peri) {
- dma_cap_set(DMA_SLAVE, pd->cap_mask);
- dma_cap_set(DMA_CYCLIC, pd->cap_mask);
- dma_cap_set(DMA_PRIVATE, pd->cap_mask);
- }
+ dma_cap_set(DMA_MEMCPY, pd->cap_mask);
+ if (pcfg->num_peri) {
+ dma_cap_set(DMA_SLAVE, pd->cap_mask);
+ dma_cap_set(DMA_CYCLIC, pd->cap_mask);
+ dma_cap_set(DMA_PRIVATE, pd->cap_mask);
}
pd->device_alloc_chan_resources = pl330_alloc_chan_resources;
return rc;
}
+static void hidma_shutdown(struct platform_device *pdev)
+{
+ struct hidma_dev *dmadev = platform_get_drvdata(pdev);
+
+ dev_info(dmadev->ddev.dev, "HI-DMA engine shutdown\n");
+
+ pm_runtime_get_sync(dmadev->ddev.dev);
+ if (hidma_ll_disable(dmadev->lldev))
+ dev_warn(dmadev->ddev.dev, "channel did not stop\n");
+ pm_runtime_mark_last_busy(dmadev->ddev.dev);
+ pm_runtime_put_autosuspend(dmadev->ddev.dev);
+
+}
+
static int hidma_remove(struct platform_device *pdev)
{
struct hidma_dev *dmadev = platform_get_drvdata(pdev);
static struct platform_driver hidma_driver = {
.probe = hidma_probe,
.remove = hidma_remove,
+ .shutdown = hidma_shutdown,
.driver = {
.name = "hidma",
.of_match_table = hidma_match,
lldev->trch_state = HIDMA_CH_ENABLED;
lldev->evch_state = HIDMA_CH_ENABLED;
+ /* enable irqs */
+ writel(ENABLE_IRQS, lldev->evca + HIDMA_EVCA_IRQ_EN_REG);
+
return 0;
}
lldev->trch_state = HIDMA_CH_SUSPENDED;
lldev->evch_state = HIDMA_CH_SUSPENDED;
+
+ /* disable interrupts */
+ writel(0, lldev->evca + HIDMA_EVCA_IRQ_EN_REG);
return 0;
}
rcar_dmac_chan_write(chan, RCAR_DMARS, chan->mid_rid);
if (desc->hwdescs.use) {
- struct rcar_dmac_xfer_chunk *chunk;
+ struct rcar_dmac_xfer_chunk *chunk =
+ list_first_entry(&desc->chunks,
+ struct rcar_dmac_xfer_chunk, node);
dev_dbg(chan->chan.device->dev,
"chan%u: queue desc %p: %u@%pad\n",
chan->index, desc, desc->nchunks, &desc->hwdescs.dma);
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ rcar_dmac_chan_write(chan, RCAR_DMAFIXSAR,
+ chunk->src_addr >> 32);
+ rcar_dmac_chan_write(chan, RCAR_DMAFIXDAR,
+ chunk->dst_addr >> 32);
rcar_dmac_chan_write(chan, RCAR_DMAFIXDPBASE,
desc->hwdescs.dma >> 32);
#endif
* should. Initialize it manually with the destination address
* of the first chunk.
*/
- chunk = list_first_entry(&desc->chunks,
- struct rcar_dmac_xfer_chunk, node);
rcar_dmac_chan_write(chan, RCAR_DMADAR,
chunk->dst_addr & 0xffffffff);
unsigned int nchunks = 0;
unsigned int max_chunk_size;
unsigned int full_size = 0;
- bool highmem = false;
+ bool cross_boundary = false;
unsigned int i;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ u32 high_dev_addr;
+ u32 high_mem_addr;
+#endif
desc = rcar_dmac_desc_get(chan);
if (!desc)
full_size += len;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+ if (i == 0) {
+ high_dev_addr = dev_addr >> 32;
+ high_mem_addr = mem_addr >> 32;
+ }
+
+ if ((dev_addr >> 32 != high_dev_addr) ||
+ (mem_addr >> 32 != high_mem_addr))
+ cross_boundary = true;
+#endif
while (len) {
unsigned int size = min(len, max_chunk_size);
* Prevent individual transfers from crossing 4GB
* boundaries.
*/
- if (dev_addr >> 32 != (dev_addr + size - 1) >> 32)
+ if (dev_addr >> 32 != (dev_addr + size - 1) >> 32) {
size = ALIGN(dev_addr, 1ULL << 32) - dev_addr;
- if (mem_addr >> 32 != (mem_addr + size - 1) >> 32)
+ cross_boundary = true;
+ }
+ if (mem_addr >> 32 != (mem_addr + size - 1) >> 32) {
size = ALIGN(mem_addr, 1ULL << 32) - mem_addr;
-
- /*
- * Check if either of the source or destination address
- * can't be expressed in 32 bits. If so we can't use
- * hardware descriptor lists.
- */
- if (dev_addr >> 32 || mem_addr >> 32)
- highmem = true;
+ cross_boundary = true;
+ }
#endif
chunk = rcar_dmac_xfer_chunk_get(chan);
* Use hardware descriptor lists if possible when more than one chunk
* needs to be transferred (otherwise they don't make much sense).
*
- * The highmem check currently covers the whole transfer. As an
- * optimization we could use descriptor lists for consecutive lowmem
- * chunks and direct manual mode for highmem chunks. Whether the
- * performance improvement would be significant enough compared to the
- * additional complexity remains to be investigated.
+ * Source/Destination address should be located in same 4GiB region
+ * in the 40bit address space when it uses Hardware descriptor,
+ * and cross_boundary is checking it.
*/
- desc->hwdescs.use = !highmem && nchunks > 1;
+ desc->hwdescs.use = !cross_boundary && nchunks > 1;
if (desc->hwdescs.use) {
if (rcar_dmac_fill_hwdesc(chan, desc) < 0)
desc->hwdescs.use = false;
c = dma_get_slave_channel(&chan->vchan.chan);
if (!c) {
- dev_err(dev, "No more channel avalaible\n");
+ dev_err(dev, "No more channels available\n");
return NULL;
}
}
spin_lock_irqsave(&priv->lock, flags);
- for_each_clear_bit_from(i, &priv->pchans_used, max) {
+ for_each_clear_bit_from(i, priv->pchans_used, max) {
pchan = &pchans[i];
pchan->vchan = vchan;
set_bit(i, priv->pchans_used);
static void vchan_complete(unsigned long arg)
{
struct virt_dma_chan *vc = (struct virt_dma_chan *)arg;
- struct virt_dma_desc *vd;
+ struct virt_dma_desc *vd, *_vd;
struct dmaengine_desc_callback cb;
LIST_HEAD(head);
dmaengine_desc_callback_invoke(&cb, NULL);
- while (!list_empty(&head)) {
- vd = list_first_entry(&head, struct virt_dma_desc, node);
+ list_for_each_entry_safe(vd, _vd, &head, node) {
dmaengine_desc_get_callback(&vd->tx, &cb);
list_del(&vd->node);
void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head)
{
- while (!list_empty(head)) {
- struct virt_dma_desc *vd = list_first_entry(head,
- struct virt_dma_desc, node);
+ struct virt_dma_desc *vd, *_vd;
+
+ list_for_each_entry_safe(vd, _vd, head, node) {
if (dmaengine_desc_test_reuse(&vd->tx)) {
list_move_tail(&vd->node, &vc->desc_allocated);
} else {
* @seg_v: Statically allocated segments base
* @cyclic_seg_v: Statically allocated segment base for cyclic transfers
* @start_transfer: Differentiate b/w DMA IP's transfer
+ * @stop_transfer: Differentiate b/w DMA IP's quiesce
*/
struct xilinx_dma_chan {
struct xilinx_dma_device *xdev;
struct xilinx_axidma_tx_segment *seg_v;
struct xilinx_axidma_tx_segment *cyclic_seg_v;
void (*start_transfer)(struct xilinx_dma_chan *chan);
+ int (*stop_transfer)(struct xilinx_dma_chan *chan);
u16 tdest;
};
}
/**
- * xilinx_dma_halt - Halt DMA channel
+ * xilinx_dma_stop_transfer - Halt DMA channel
* @chan: Driver specific DMA channel
*/
-static void xilinx_dma_halt(struct xilinx_dma_chan *chan)
+static int xilinx_dma_stop_transfer(struct xilinx_dma_chan *chan)
{
- int err;
u32 val;
dma_ctrl_clr(chan, XILINX_DMA_REG_DMACR, XILINX_DMA_DMACR_RUNSTOP);
/* Wait for the hardware to halt */
- err = xilinx_dma_poll_timeout(chan, XILINX_DMA_REG_DMASR, val,
- (val & XILINX_DMA_DMASR_HALTED), 0,
- XILINX_DMA_LOOP_COUNT);
+ return xilinx_dma_poll_timeout(chan, XILINX_DMA_REG_DMASR, val,
+ val & XILINX_DMA_DMASR_HALTED, 0,
+ XILINX_DMA_LOOP_COUNT);
+}
- if (err) {
- dev_err(chan->dev, "Cannot stop channel %p: %x\n",
- chan, dma_ctrl_read(chan, XILINX_DMA_REG_DMASR));
- chan->err = true;
- }
+/**
+ * xilinx_cdma_stop_transfer - Wait for the current transfer to complete
+ * @chan: Driver specific DMA channel
+ */
+static int xilinx_cdma_stop_transfer(struct xilinx_dma_chan *chan)
+{
+ u32 val;
+
+ return xilinx_dma_poll_timeout(chan, XILINX_DMA_REG_DMASR, val,
+ val & XILINX_DMA_DMASR_IDLE, 0,
+ XILINX_DMA_LOOP_COUNT);
}
/**
{
struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
struct xilinx_dma_tx_descriptor *desc;
- struct xilinx_cdma_tx_segment *segment, *prev;
+ struct xilinx_cdma_tx_segment *segment;
struct xilinx_cdma_desc_hw *hw;
if (!len || len > XILINX_DMA_MAX_TRANS_LEN)
hw->dest_addr_msb = upper_32_bits(dma_dst);
}
- /* Fill the previous next descriptor with current */
- prev = list_last_entry(&desc->segments,
- struct xilinx_cdma_tx_segment, node);
- prev->hw.next_desc = segment->phys;
-
/* Insert the segment into the descriptor segments list. */
list_add_tail(&segment->node, &desc->segments);
- prev = segment;
-
- /* Link the last hardware descriptor with the first. */
- segment = list_first_entry(&desc->segments,
- struct xilinx_cdma_tx_segment, node);
desc->async_tx.phys = segment->phys;
- prev->hw.next_desc = segment->phys;
+ hw->next_desc = segment->phys;
return &desc->async_tx;
{
struct xilinx_dma_chan *chan = to_xilinx_chan(dchan);
u32 reg;
+ int err;
if (chan->cyclic)
xilinx_dma_chan_reset(chan);
- /* Halt the DMA engine */
- xilinx_dma_halt(chan);
+ err = chan->stop_transfer(chan);
+ if (err) {
+ dev_err(chan->dev, "Cannot stop channel %p: %x\n",
+ chan, dma_ctrl_read(chan, XILINX_DMA_REG_DMASR));
+ chan->err = true;
+ }
/* Remove and free all of the descriptors in the lists */
xilinx_dma_free_descriptors(chan);
return err;
}
- if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA)
+ if (xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
chan->start_transfer = xilinx_dma_start_transfer;
- else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA)
+ chan->stop_transfer = xilinx_dma_stop_transfer;
+ } else if (xdev->dma_config->dmatype == XDMA_TYPE_CDMA) {
chan->start_transfer = xilinx_cdma_start_transfer;
- else
+ chan->stop_transfer = xilinx_cdma_stop_transfer;
+ } else {
chan->start_transfer = xilinx_vdma_start_transfer;
+ chan->stop_transfer = xilinx_dma_stop_transfer;
+ }
/* Initialize the tasklet */
tasklet_init(&chan->tasklet, xilinx_dma_do_tasklet,
static unsigned int base[MAX_NUM_DIO48E];
static unsigned int num_dio48e;
-module_param_array(base, uint, &num_dio48e, 0);
+module_param_hw_array(base, uint, ioport, &num_dio48e, 0);
MODULE_PARM_DESC(base, "ACCES 104-DIO-48E base addresses");
static unsigned int irq[MAX_NUM_DIO48E];
-module_param_array(irq, uint, NULL, 0);
+module_param_hw_array(irq, uint, irq, NULL, 0);
MODULE_PARM_DESC(irq, "ACCES 104-DIO-48E interrupt line numbers");
/**
static unsigned int base[MAX_NUM_IDI_48];
static unsigned int num_idi_48;
-module_param_array(base, uint, &num_idi_48, 0);
+module_param_hw_array(base, uint, ioport, &num_idi_48, 0);
MODULE_PARM_DESC(base, "ACCES 104-IDI-48 base addresses");
static unsigned int irq[MAX_NUM_IDI_48];
-module_param_array(irq, uint, NULL, 0);
+module_param_hw_array(irq, uint, irq, NULL, 0);
MODULE_PARM_DESC(irq, "ACCES 104-IDI-48 interrupt line numbers");
/**
static unsigned int base[MAX_NUM_IDIO_16];
static unsigned int num_idio_16;
-module_param_array(base, uint, &num_idio_16, 0);
+module_param_hw_array(base, uint, ioport, &num_idio_16, 0);
MODULE_PARM_DESC(base, "ACCES 104-IDIO-16 base addresses");
static unsigned int irq[MAX_NUM_IDIO_16];
-module_param_array(irq, uint, NULL, 0);
+module_param_hw_array(irq, uint, irq, NULL, 0);
MODULE_PARM_DESC(irq, "ACCES 104-IDIO-16 interrupt line numbers");
/**
static unsigned int base[MAX_NUM_GPIOMM];
static unsigned int num_gpiomm;
-module_param_array(base, uint, &num_gpiomm, 0);
+module_param_hw_array(base, uint, ioport, &num_gpiomm, 0);
MODULE_PARM_DESC(base, "Diamond Systems GPIO-MM base addresses");
/**
static unsigned int base[MAX_NUM_WS16C48];
static unsigned int num_ws16c48;
-module_param_array(base, uint, &num_ws16c48, 0);
+module_param_hw_array(base, uint, ioport, &num_ws16c48, 0);
MODULE_PARM_DESC(base, "WinSystems WS16C48 base addresses");
static unsigned int irq[MAX_NUM_WS16C48];
-module_param_array(irq, uint, NULL, 0);
+module_param_hw_array(irq, uint, irq, NULL, 0);
MODULE_PARM_DESC(irq, "WinSystems WS16C48 interrupt line numbers");
/**
dev_priv->requests = KMEM_CACHE(drm_i915_gem_request,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
- SLAB_DESTROY_BY_RCU);
+ SLAB_TYPESAFE_BY_RCU);
if (!dev_priv->requests)
goto err_vmas;
__i915_gem_active_get_rcu(const struct i915_gem_active *active)
{
/* Performing a lockless retrieval of the active request is super
- * tricky. SLAB_DESTROY_BY_RCU merely guarantees that the backing
+ * tricky. SLAB_TYPESAFE_BY_RCU merely guarantees that the backing
* slab of request objects will not be freed whilst we hold the
* RCU read lock. It does not guarantee that the request itself
* will not be freed and then *reused*. Viz,
i915->requests = KMEM_CACHE(mock_request,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
- SLAB_DESTROY_BY_RCU);
+ SLAB_TYPESAFE_BY_RCU);
if (!i915->requests)
goto err_vmas;
DRM_INFO("virgl 3d acceleration not supported by guest\n");
#endif
- ret = vgdev->vdev->config->find_vqs(vgdev->vdev, 2, vqs,
- callbacks, names, NULL);
+ ret = virtio_find_vqs(vgdev->vdev, 2, vqs, callbacks, names, NULL);
if (ret) {
DRM_ERROR("failed to find virt queues\n");
goto err_vqs;
/* If force_addr is set to anything different from 0, we forcibly enable
the device at the given address. */
static u16 force_addr;
-module_param(force_addr, ushort, 0);
+module_param_hw(force_addr, ushort, ioport, 0);
MODULE_PARM_DESC(force_addr,
"Initialize the base address of the i2c controller");
{ "AMDI0010", ACCESS_INTR_MASK },
{ "AMDI0510", 0 },
{ "APMC0D0F", 0 },
+ { "HISI02A1", 0 },
+ { "HISI02A2", 0 },
{ }
};
MODULE_DEVICE_TABLE(acpi, dw_i2c_acpi_match);
MODULE_DESCRIPTION("I2C-Bus adapter routines for PCF8584 ISA bus adapter");
MODULE_LICENSE("GPL");
-module_param(base, int, 0);
-module_param(irq, int, 0);
+module_param_hw(base, int, ioport_or_iomem, 0);
+module_param_hw(irq, int, irq, 0);
module_param(clock, int, 0);
module_param(own, int, 0);
-module_param(mmapped, int, 0);
+module_param_hw(mmapped, int, other, 0);
module_isa_driver(i2c_elektor_driver, 1);
static struct platform_device *pdev;
static u16 base;
-module_param(base, ushort, 0);
+module_param_hw(base, ushort, ioport, 0);
MODULE_PARM_DESC(base, "Base I/O address");
static int irq;
-module_param(irq, int, 0);
+module_param_hw(irq, int, irq, 0);
MODULE_PARM_DESC(irq, "IRQ (optional)");
/* ----- Low-level parallel port access ----------------------------------- */
MODULE_DESCRIPTION("ISA base PCA9564/PCA9665 driver");
MODULE_LICENSE("GPL");
-module_param(base, ulong, 0);
+module_param_hw(base, ulong, ioport, 0);
MODULE_PARM_DESC(base, "I/O base address");
-module_param(irq, int, 0);
+module_param_hw(irq, int, irq, 0);
MODULE_PARM_DESC(irq, "IRQ");
module_param(clock, int, 0);
MODULE_PARM_DESC(clock, "Clock rate in hertz.\n\t\t"
/* If force_addr is set to anything different from 0, we forcibly enable
the PIIX4 at the given address. VERY DANGEROUS! */
static int force_addr;
-module_param (force_addr, int, 0);
+module_param_hw(force_addr, int, ioport, 0);
MODULE_PARM_DESC(force_addr,
"Forcibly enable the PIIX4 at the given address. "
"EXTREMELY DANGEROUS!");
/* If force_addr is set to anything different from 0, we forcibly enable
the device at the given address. */
static u16 force_addr;
-module_param(force_addr, ushort, 0);
+module_param_hw(force_addr, ushort, ioport, 0);
MODULE_PARM_DESC(force_addr, "Initialize the base address of the i2c controller");
static struct pci_driver sis5595_driver;
/* If force_addr is set to anything different from 0, we forcibly enable
the VT596 at the given address. VERY DANGEROUS! */
static u16 force_addr;
-module_param(force_addr, ushort, 0);
+module_param_hw(force_addr, ushort, ioport, 0);
MODULE_PARM_DESC(force_addr,
"Forcibly enable the SMBus at the given address. "
"EXTREMELY DANGEROUS!");
#define MAX_DEVICES 4
static int base[MAX_DEVICES] = { 0x820, 0x840 };
-module_param_array(base, int, NULL, 0);
+module_param_hw_array(base, int, ioport, NULL, 0);
MODULE_PARM_DESC(base, "Base addresses for the ACCESS.bus controllers");
#define POLL_TIMEOUT (HZ/5)
if (cmd->tf_flags & IDE_TFLAG_DYN)
kfree(orig_cmd);
- else
+ else if (cmd != orig_cmd)
memcpy(orig_cmd, cmd, sizeof(*cmd));
}
}
spin_lock_init(&hwif->lock);
- init_timer(&hwif->timer);
- hwif->timer.function = &ide_timer_expiry;
- hwif->timer.data = (unsigned long)hwif;
+ setup_timer(&hwif->timer, &ide_timer_expiry, (unsigned long)hwif);
init_completion(&hwif->gendev_rel_comp);
ICPU(INTEL_FAM6_XEON_PHI_KNL, idle_cpu_knl),
ICPU(INTEL_FAM6_XEON_PHI_KNM, idle_cpu_knl),
ICPU(INTEL_FAM6_ATOM_GOLDMONT, idle_cpu_bxt),
+ ICPU(INTEL_FAM6_ATOM_GEMINI_LAKE, idle_cpu_bxt),
ICPU(INTEL_FAM6_ATOM_DENVERTON, idle_cpu_dnv),
{}
};
ivt_idle_state_table_update();
break;
case INTEL_FAM6_ATOM_GOLDMONT:
+ case INTEL_FAM6_ATOM_GEMINI_LAKE:
bxt_idle_state_table_update();
break;
case INTEL_FAM6_SKYLAKE_DESKTOP:
static unsigned int base[max_num_isa_dev(STX104_EXTENT)];
static unsigned int num_stx104;
-module_param_array(base, uint, &num_stx104, 0);
+module_param_hw_array(base, uint, ioport, &num_stx104, 0);
MODULE_PARM_DESC(base, "Apex Embedded Systems STX104 base addresses");
/**
static unsigned int base[max_num_isa_dev(CIO_DAC_EXTENT)];
static unsigned int num_cio_dac;
-module_param_array(base, uint, &num_cio_dac, 0);
+module_param_hw_array(base, uint, ioport, &num_cio_dac, 0);
MODULE_PARM_DESC(base, "Measurement Computing CIO-DAC base addresses");
/**
#include <rdma/ib_user_verbs.h>
#include <linux/netdevice.h>
#include <linux/iommu.h>
+#include <linux/pci.h>
#include <net/addrconf.h>
#include <linux/qed/qede_roce.h>
#include <linux/qed/qed_chain.h>
#define INPORT_IRQ 5
static int inport_irq = INPORT_IRQ;
-module_param_named(irq, inport_irq, uint, 0);
+module_param_hw_named(irq, inport_irq, uint, irq, 0);
MODULE_PARM_DESC(irq, "IRQ number (5=default)");
static struct input_dev *inport_dev;
#define LOGIBM_IRQ 5
static int logibm_irq = LOGIBM_IRQ;
-module_param_named(irq, logibm_irq, uint, 0);
+module_param_hw_named(irq, logibm_irq, uint, irq, 0);
MODULE_PARM_DESC(irq, "IRQ number (5=default)");
static struct input_dev *logibm_dev;
MODULE_LICENSE("GPL");
static unsigned int mk712_io = 0x260; /* Also 0x200, 0x208, 0x300 */
-module_param_named(io, mk712_io, uint, 0);
+module_param_hw_named(io, mk712_io, uint, ioport, 0);
MODULE_PARM_DESC(io, "I/O base address of MK712 touchscreen controller");
static unsigned int mk712_irq = 10; /* Also 12, 14, 15 */
-module_param_named(irq, mk712_irq, uint, 0);
+module_param_hw_named(irq, mk712_irq, uint, irq, 0);
MODULE_PARM_DESC(irq, "IRQ of MK712 touchscreen controller");
/* eight 8-bit registers */
out_unregister:
mmu_notifier_unregister(&pasid_state->mn, mm);
+ mmput(mm);
out_free:
- mmput(mm);
free_pasid_state(pasid_state);
out:
};
struct arm_smmu_strtab_ent {
- bool valid;
-
- bool bypass; /* Overrides s1/s2 config */
+ /*
+ * An STE is "assigned" if the master emitting the corresponding SID
+ * is attached to a domain. The behaviour of an unassigned STE is
+ * determined by the disable_bypass parameter, whereas an assigned
+ * STE behaves according to s1_cfg/s2_cfg, which themselves are
+ * configured according to the domain type.
+ */
+ bool assigned;
struct arm_smmu_s1_cfg *s1_cfg;
struct arm_smmu_s2_cfg *s2_cfg;
};
ARM_SMMU_DOMAIN_S1 = 0,
ARM_SMMU_DOMAIN_S2,
ARM_SMMU_DOMAIN_NESTED,
+ ARM_SMMU_DOMAIN_BYPASS,
};
struct arm_smmu_domain {
* This is hideously complicated, but we only really care about
* three cases at the moment:
*
- * 1. Invalid (all zero) -> bypass (init)
- * 2. Bypass -> translation (attach)
- * 3. Translation -> bypass (detach)
+ * 1. Invalid (all zero) -> bypass/fault (init)
+ * 2. Bypass/fault -> translation/bypass (attach)
+ * 3. Translation/bypass -> bypass/fault (detach)
*
* Given that we can't update the STE atomically and the SMMU
* doesn't read the thing in a defined order, that leaves us
}
/* Nuke the existing STE_0 value, as we're going to rewrite it */
- val = ste->valid ? STRTAB_STE_0_V : 0;
+ val = STRTAB_STE_0_V;
+
+ /* Bypass/fault */
+ if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) {
+ if (!ste->assigned && disable_bypass)
+ val |= STRTAB_STE_0_CFG_ABORT;
+ else
+ val |= STRTAB_STE_0_CFG_BYPASS;
- if (ste->bypass) {
- val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
- : STRTAB_STE_0_CFG_BYPASS;
dst[0] = cpu_to_le64(val);
dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING
<< STRTAB_STE_1_SHCFG_SHIFT);
static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
{
unsigned int i;
- struct arm_smmu_strtab_ent ste = {
- .valid = true,
- .bypass = true,
- };
+ struct arm_smmu_strtab_ent ste = { .assigned = false };
for (i = 0; i < nent; ++i) {
arm_smmu_write_strtab_ent(NULL, -1, strtab, &ste);
{
struct arm_smmu_domain *smmu_domain;
- if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
+ if (type != IOMMU_DOMAIN_UNMANAGED &&
+ type != IOMMU_DOMAIN_DMA &&
+ type != IOMMU_DOMAIN_IDENTITY)
return NULL;
/*
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct arm_smmu_device *smmu = smmu_domain->smmu;
+ if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+ smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
+ return 0;
+ }
+
/* Restrict the stage to what we can actually support */
if (!(smmu->features & ARM_SMMU_FEAT_TRANS_S1))
smmu_domain->stage = ARM_SMMU_DOMAIN_S2;
return step;
}
-static int arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
+static void arm_smmu_install_ste_for_dev(struct iommu_fwspec *fwspec)
{
int i;
struct arm_smmu_master_data *master = fwspec->iommu_priv;
arm_smmu_write_strtab_ent(smmu, sid, step, &master->ste);
}
-
- return 0;
}
static void arm_smmu_detach_dev(struct device *dev)
{
struct arm_smmu_master_data *master = dev->iommu_fwspec->iommu_priv;
- master->ste.bypass = true;
- if (arm_smmu_install_ste_for_dev(dev->iommu_fwspec) < 0)
- dev_warn(dev, "failed to install bypass STE\n");
+ master->ste.assigned = false;
+ arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
}
static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
ste = &master->ste;
/* Already attached to a different domain? */
- if (!ste->bypass)
+ if (ste->assigned)
arm_smmu_detach_dev(dev);
mutex_lock(&smmu_domain->init_mutex);
goto out_unlock;
}
- ste->bypass = false;
- ste->valid = true;
+ ste->assigned = true;
- if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS) {
+ ste->s1_cfg = NULL;
+ ste->s2_cfg = NULL;
+ } else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
ste->s1_cfg = &smmu_domain->s1_cfg;
ste->s2_cfg = NULL;
arm_smmu_write_ctx_desc(smmu, ste->s1_cfg);
ste->s2_cfg = &smmu_domain->s2_cfg;
}
- ret = arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
- if (ret < 0)
- ste->valid = false;
-
+ arm_smmu_install_ste_for_dev(dev->iommu_fwspec);
out_unlock:
mutex_unlock(&smmu_domain->init_mutex);
return ret;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct io_pgtable_ops *ops = smmu_domain->pgtbl_ops;
+ if (domain->type == IOMMU_DOMAIN_IDENTITY)
+ return iova;
+
if (!ops)
return 0;
master = fwspec->iommu_priv;
smmu = master->smmu;
- if (master && master->ste.valid)
+ if (master && master->ste.assigned)
arm_smmu_detach_dev(dev);
iommu_group_remove_device(dev);
iommu_device_unlink(&smmu->iommu, dev);
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+
switch (attr) {
case DOMAIN_ATTR_NESTING:
*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
int ret = 0;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+
mutex_lock(&smmu_domain->init_mutex);
switch (attr) {
return;
list_add_tail(®ion->list, head);
+
+ iommu_dma_get_resv_regions(dev, head);
}
static void arm_smmu_put_resv_regions(struct device *dev,
.probe = arm_smmu_device_probe,
.remove = arm_smmu_device_remove,
};
+module_platform_driver(arm_smmu_driver);
-static int __init arm_smmu_init(void)
-{
- static bool registered;
- int ret = 0;
-
- if (!registered) {
- ret = platform_driver_register(&arm_smmu_driver);
- registered = !ret;
- }
- return ret;
-}
-
-static void __exit arm_smmu_exit(void)
-{
- return platform_driver_unregister(&arm_smmu_driver);
-}
-
-subsys_initcall(arm_smmu_init);
-module_exit(arm_smmu_exit);
-
-static int __init arm_smmu_of_init(struct device_node *np)
-{
- int ret = arm_smmu_init();
-
- if (ret)
- return ret;
-
- if (!of_platform_device_create(np, NULL, platform_bus_type.dev_root))
- return -ENODEV;
-
- return 0;
-}
-IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", arm_smmu_of_init);
-
-#ifdef CONFIG_ACPI
-static int __init acpi_smmu_v3_init(struct acpi_table_header *table)
-{
- if (iort_node_match(ACPI_IORT_NODE_SMMU_V3))
- return arm_smmu_init();
-
- return 0;
-}
-IORT_ACPI_DECLARE(arm_smmu_v3, ACPI_SIG_IORT, acpi_smmu_v3_init);
-#endif
+IOMMU_OF_DECLARE(arm_smmuv3, "arm,smmu-v3", NULL);
MODULE_DESCRIPTION("IOMMU API for ARM architected SMMUv3 implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
#define ARM_SMMU_GR0_sTLBGSTATUS 0x74
#define sTLBGSTATUS_GSACTIVE (1 << 0)
#define TLB_LOOP_TIMEOUT 1000000 /* 1s! */
+#define TLB_SPIN_COUNT 10
/* Stream mapping registers */
#define ARM_SMMU_GR0_SMR(n) (0x800 + ((n) << 2))
#define CBA2R_VMID_MASK 0xffff
/* Translation context bank */
-#define ARM_SMMU_CB_BASE(smmu) ((smmu)->base + ((smmu)->size >> 1))
-#define ARM_SMMU_CB(smmu, n) ((n) * (1 << (smmu)->pgshift))
+#define ARM_SMMU_CB(smmu, n) ((smmu)->cb_base + ((n) << (smmu)->pgshift))
#define ARM_SMMU_CB_SCTLR 0x0
#define ARM_SMMU_CB_ACTLR 0x4
#define ARM_SMMU_CB_S1_TLBIVAL 0x620
#define ARM_SMMU_CB_S2_TLBIIPAS2 0x630
#define ARM_SMMU_CB_S2_TLBIIPAS2L 0x638
+#define ARM_SMMU_CB_TLBSYNC 0x7f0
+#define ARM_SMMU_CB_TLBSTATUS 0x7f4
#define ARM_SMMU_CB_ATS1PR 0x800
#define ARM_SMMU_CB_ATSR 0x8f0
struct device *dev;
void __iomem *base;
- unsigned long size;
+ void __iomem *cb_base;
unsigned long pgshift;
#define ARM_SMMU_FEAT_COHERENT_WALK (1 << 0)
struct arm_smmu_cfg {
u8 cbndx;
u8 irptndx;
+ union {
+ u16 asid;
+ u16 vmid;
+ };
u32 cbar;
enum arm_smmu_context_fmt fmt;
};
#define INVALID_IRPTNDX 0xff
-#define ARM_SMMU_CB_ASID(smmu, cfg) ((u16)(smmu)->cavium_id_base + (cfg)->cbndx)
-#define ARM_SMMU_CB_VMID(smmu, cfg) ((u16)(smmu)->cavium_id_base + (cfg)->cbndx + 1)
-
enum arm_smmu_domain_stage {
ARM_SMMU_DOMAIN_S1 = 0,
ARM_SMMU_DOMAIN_S2,
ARM_SMMU_DOMAIN_NESTED,
+ ARM_SMMU_DOMAIN_BYPASS,
};
struct arm_smmu_domain {
}
/* Wait for any pending TLB invalidations to complete */
-static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu)
+static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu,
+ void __iomem *sync, void __iomem *status)
{
- int count = 0;
- void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
-
- writel_relaxed(0, gr0_base + ARM_SMMU_GR0_sTLBGSYNC);
- while (readl_relaxed(gr0_base + ARM_SMMU_GR0_sTLBGSTATUS)
- & sTLBGSTATUS_GSACTIVE) {
- cpu_relax();
- if (++count == TLB_LOOP_TIMEOUT) {
- dev_err_ratelimited(smmu->dev,
- "TLB sync timed out -- SMMU may be deadlocked\n");
- return;
+ unsigned int spin_cnt, delay;
+
+ writel_relaxed(0, sync);
+ for (delay = 1; delay < TLB_LOOP_TIMEOUT; delay *= 2) {
+ for (spin_cnt = TLB_SPIN_COUNT; spin_cnt > 0; spin_cnt--) {
+ if (!(readl_relaxed(status) & sTLBGSTATUS_GSACTIVE))
+ return;
+ cpu_relax();
}
- udelay(1);
+ udelay(delay);
}
+ dev_err_ratelimited(smmu->dev,
+ "TLB sync timed out -- SMMU may be deadlocked\n");
}
-static void arm_smmu_tlb_sync(void *cookie)
+static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu)
+{
+ void __iomem *base = ARM_SMMU_GR0(smmu);
+
+ __arm_smmu_tlb_sync(smmu, base + ARM_SMMU_GR0_sTLBGSYNC,
+ base + ARM_SMMU_GR0_sTLBGSTATUS);
+}
+
+static void arm_smmu_tlb_sync_context(void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
- __arm_smmu_tlb_sync(smmu_domain->smmu);
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ void __iomem *base = ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx);
+
+ __arm_smmu_tlb_sync(smmu, base + ARM_SMMU_CB_TLBSYNC,
+ base + ARM_SMMU_CB_TLBSTATUS);
}
-static void arm_smmu_tlb_inv_context(void *cookie)
+static void arm_smmu_tlb_sync_vmid(void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+
+ arm_smmu_tlb_sync_global(smmu_domain->smmu);
+}
+
+static void arm_smmu_tlb_inv_context_s1(void *cookie)
{
struct arm_smmu_domain *smmu_domain = cookie;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
- struct arm_smmu_device *smmu = smmu_domain->smmu;
- bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
- void __iomem *base;
+ void __iomem *base = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx);
- if (stage1) {
- base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
- writel_relaxed(ARM_SMMU_CB_ASID(smmu, cfg),
- base + ARM_SMMU_CB_S1_TLBIASID);
- } else {
- base = ARM_SMMU_GR0(smmu);
- writel_relaxed(ARM_SMMU_CB_VMID(smmu, cfg),
- base + ARM_SMMU_GR0_TLBIVMID);
- }
+ writel_relaxed(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID);
+ arm_smmu_tlb_sync_context(cookie);
+}
+
+static void arm_smmu_tlb_inv_context_s2(void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ struct arm_smmu_device *smmu = smmu_domain->smmu;
+ void __iomem *base = ARM_SMMU_GR0(smmu);
- __arm_smmu_tlb_sync(smmu);
+ writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
+ arm_smmu_tlb_sync_global(smmu);
}
static void arm_smmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
{
struct arm_smmu_domain *smmu_domain = cookie;
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
- struct arm_smmu_device *smmu = smmu_domain->smmu;
bool stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
- void __iomem *reg;
+ void __iomem *reg = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx);
if (stage1) {
- reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
reg += leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;
if (cfg->fmt != ARM_SMMU_CTX_FMT_AARCH64) {
iova &= ~12UL;
- iova |= ARM_SMMU_CB_ASID(smmu, cfg);
+ iova |= cfg->asid;
do {
writel_relaxed(iova, reg);
iova += granule;
} while (size -= granule);
} else {
iova >>= 12;
- iova |= (u64)ARM_SMMU_CB_ASID(smmu, cfg) << 48;
+ iova |= (u64)cfg->asid << 48;
do {
writeq_relaxed(iova, reg);
iova += granule >> 12;
} while (size -= granule);
}
- } else if (smmu->version == ARM_SMMU_V2) {
- reg = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+ } else {
reg += leaf ? ARM_SMMU_CB_S2_TLBIIPAS2L :
ARM_SMMU_CB_S2_TLBIIPAS2;
iova >>= 12;
smmu_write_atomic_lq(iova, reg);
iova += granule >> 12;
} while (size -= granule);
- } else {
- reg = ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_TLBIVMID;
- writel_relaxed(ARM_SMMU_CB_VMID(smmu, cfg), reg);
}
}
-static const struct iommu_gather_ops arm_smmu_gather_ops = {
- .tlb_flush_all = arm_smmu_tlb_inv_context,
+/*
+ * On MMU-401 at least, the cost of firing off multiple TLBIVMIDs appears
+ * almost negligible, but the benefit of getting the first one in as far ahead
+ * of the sync as possible is significant, hence we don't just make this a
+ * no-op and set .tlb_sync to arm_smmu_inv_context_s2() as you might think.
+ */
+static void arm_smmu_tlb_inv_vmid_nosync(unsigned long iova, size_t size,
+ size_t granule, bool leaf, void *cookie)
+{
+ struct arm_smmu_domain *smmu_domain = cookie;
+ void __iomem *base = ARM_SMMU_GR0(smmu_domain->smmu);
+
+ writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
+}
+
+static const struct iommu_gather_ops arm_smmu_s1_tlb_ops = {
+ .tlb_flush_all = arm_smmu_tlb_inv_context_s1,
.tlb_add_flush = arm_smmu_tlb_inv_range_nosync,
- .tlb_sync = arm_smmu_tlb_sync,
+ .tlb_sync = arm_smmu_tlb_sync_context,
+};
+
+static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v2 = {
+ .tlb_flush_all = arm_smmu_tlb_inv_context_s2,
+ .tlb_add_flush = arm_smmu_tlb_inv_range_nosync,
+ .tlb_sync = arm_smmu_tlb_sync_context,
+};
+
+static const struct iommu_gather_ops arm_smmu_s2_tlb_ops_v1 = {
+ .tlb_flush_all = arm_smmu_tlb_inv_context_s2,
+ .tlb_add_flush = arm_smmu_tlb_inv_vmid_nosync,
+ .tlb_sync = arm_smmu_tlb_sync_vmid,
};
static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
struct arm_smmu_device *smmu = smmu_domain->smmu;
void __iomem *cb_base;
- cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+ cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
fsr = readl_relaxed(cb_base + ARM_SMMU_CB_FSR);
if (!(fsr & FSR_FAULT))
gr1_base = ARM_SMMU_GR1(smmu);
stage1 = cfg->cbar != CBAR_TYPE_S2_TRANS;
- cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+ cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
if (smmu->version > ARM_SMMU_V1) {
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
reg = CBA2R_RW64_32BIT;
/* 16-bit VMIDs live in CBA2R */
if (smmu->features & ARM_SMMU_FEAT_VMID16)
- reg |= ARM_SMMU_CB_VMID(smmu, cfg) << CBA2R_VMID_SHIFT;
+ reg |= cfg->vmid << CBA2R_VMID_SHIFT;
writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBA2R(cfg->cbndx));
}
(CBAR_S1_MEMATTR_WB << CBAR_S1_MEMATTR_SHIFT);
} else if (!(smmu->features & ARM_SMMU_FEAT_VMID16)) {
/* 8-bit VMIDs live in CBAR */
- reg |= ARM_SMMU_CB_VMID(smmu, cfg) << CBAR_VMID_SHIFT;
+ reg |= cfg->vmid << CBAR_VMID_SHIFT;
}
writel_relaxed(reg, gr1_base + ARM_SMMU_GR1_CBAR(cfg->cbndx));
- /* TTBRs */
- if (stage1) {
- u16 asid = ARM_SMMU_CB_ASID(smmu, cfg);
-
- if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
- reg = pgtbl_cfg->arm_v7s_cfg.ttbr[0];
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0);
- reg = pgtbl_cfg->arm_v7s_cfg.ttbr[1];
- writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1);
- writel_relaxed(asid, cb_base + ARM_SMMU_CB_CONTEXTIDR);
- } else {
- reg64 = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
- reg64 |= (u64)asid << TTBRn_ASID_SHIFT;
- writeq_relaxed(reg64, cb_base + ARM_SMMU_CB_TTBR0);
- reg64 = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
- reg64 |= (u64)asid << TTBRn_ASID_SHIFT;
- writeq_relaxed(reg64, cb_base + ARM_SMMU_CB_TTBR1);
- }
- } else {
- reg64 = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
- writeq_relaxed(reg64, cb_base + ARM_SMMU_CB_TTBR0);
- }
-
- /* TTBCR */
+ /*
+ * TTBCR
+ * We must write this before the TTBRs, since it determines the
+ * access behaviour of some fields (in particular, ASID[15:8]).
+ */
if (stage1) {
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
reg = pgtbl_cfg->arm_v7s_cfg.tcr;
}
writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBCR);
+ /* TTBRs */
+ if (stage1) {
+ if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
+ reg = pgtbl_cfg->arm_v7s_cfg.ttbr[0];
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR0);
+ reg = pgtbl_cfg->arm_v7s_cfg.ttbr[1];
+ writel_relaxed(reg, cb_base + ARM_SMMU_CB_TTBR1);
+ writel_relaxed(cfg->asid, cb_base + ARM_SMMU_CB_CONTEXTIDR);
+ } else {
+ reg64 = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[0];
+ reg64 |= (u64)cfg->asid << TTBRn_ASID_SHIFT;
+ writeq_relaxed(reg64, cb_base + ARM_SMMU_CB_TTBR0);
+ reg64 = pgtbl_cfg->arm_lpae_s1_cfg.ttbr[1];
+ reg64 |= (u64)cfg->asid << TTBRn_ASID_SHIFT;
+ writeq_relaxed(reg64, cb_base + ARM_SMMU_CB_TTBR1);
+ }
+ } else {
+ reg64 = pgtbl_cfg->arm_lpae_s2_cfg.vttbr;
+ writeq_relaxed(reg64, cb_base + ARM_SMMU_CB_TTBR0);
+ }
+
/* MAIRs (stage-1 only) */
if (stage1) {
if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH32_S) {
enum io_pgtable_fmt fmt;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
+ const struct iommu_gather_ops *tlb_ops;
mutex_lock(&smmu_domain->init_mutex);
if (smmu_domain->smmu)
goto out_unlock;
+ if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+ smmu_domain->stage = ARM_SMMU_DOMAIN_BYPASS;
+ smmu_domain->smmu = smmu;
+ goto out_unlock;
+ }
+
/*
* Mapping the requested stage onto what we support is surprisingly
* complicated, mainly because the spec allows S1+S2 SMMUs without
ias = min(ias, 32UL);
oas = min(oas, 32UL);
}
+ tlb_ops = &arm_smmu_s1_tlb_ops;
break;
case ARM_SMMU_DOMAIN_NESTED:
/*
ias = min(ias, 40UL);
oas = min(oas, 40UL);
}
+ if (smmu->version == ARM_SMMU_V2)
+ tlb_ops = &arm_smmu_s2_tlb_ops_v2;
+ else
+ tlb_ops = &arm_smmu_s2_tlb_ops_v1;
break;
default:
ret = -EINVAL;
goto out_unlock;
}
-
ret = __arm_smmu_alloc_bitmap(smmu->context_map, start,
smmu->num_context_banks);
if (ret < 0)
cfg->irptndx = cfg->cbndx;
}
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_S2)
+ cfg->vmid = cfg->cbndx + 1 + smmu->cavium_id_base;
+ else
+ cfg->asid = cfg->cbndx + smmu->cavium_id_base;
+
pgtbl_cfg = (struct io_pgtable_cfg) {
.pgsize_bitmap = smmu->pgsize_bitmap,
.ias = ias,
.oas = oas,
- .tlb = &arm_smmu_gather_ops,
+ .tlb = tlb_ops,
.iommu_dev = smmu->dev,
};
void __iomem *cb_base;
int irq;
- if (!smmu)
+ if (!smmu || domain->type == IOMMU_DOMAIN_IDENTITY)
return;
/*
* Disable the context bank and free the page tables before freeing
* it.
*/
- cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+ cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
if (cfg->irptndx != INVALID_IRPTNDX) {
{
struct arm_smmu_domain *smmu_domain;
- if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
+ if (type != IOMMU_DOMAIN_UNMANAGED &&
+ type != IOMMU_DOMAIN_DMA &&
+ type != IOMMU_DOMAIN_IDENTITY)
return NULL;
/*
* Allocate the domain and initialise some of its data structures.
{
struct arm_smmu_device *smmu = smmu_domain->smmu;
struct arm_smmu_s2cr *s2cr = smmu->s2crs;
- enum arm_smmu_s2cr_type type = S2CR_TYPE_TRANS;
u8 cbndx = smmu_domain->cfg.cbndx;
+ enum arm_smmu_s2cr_type type;
int i, idx;
+ if (smmu_domain->stage == ARM_SMMU_DOMAIN_BYPASS)
+ type = S2CR_TYPE_BYPASS;
+ else
+ type = S2CR_TYPE_TRANS;
+
for_each_cfg_sme(fwspec, i, idx) {
if (type == s2cr[idx].type && cbndx == s2cr[idx].cbndx)
continue;
u64 phys;
unsigned long va;
- cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, cfg->cbndx);
+ cb_base = ARM_SMMU_CB(smmu, cfg->cbndx);
/* ATS1 registers can only be written atomically */
va = iova & ~0xfffUL;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
struct io_pgtable_ops *ops= smmu_domain->pgtbl_ops;
+ if (domain->type == IOMMU_DOMAIN_IDENTITY)
+ return iova;
+
if (!ops)
return 0;
}
if (mask & ~smmu->smr_mask_mask) {
dev_err(dev, "SMR mask 0x%x out of range for SMMU (0x%x)\n",
- sid, smmu->smr_mask_mask);
+ mask, smmu->smr_mask_mask);
goto out_free;
}
}
{
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+
switch (attr) {
case DOMAIN_ATTR_NESTING:
*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
int ret = 0;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+ if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+ return -EINVAL;
+
mutex_lock(&smmu_domain->init_mutex);
switch (attr) {
static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
{
- u32 fwid = 0;
+ u32 mask, fwid = 0;
if (args->args_count > 0)
fwid |= (u16)args->args[0];
if (args->args_count > 1)
fwid |= (u16)args->args[1] << SMR_MASK_SHIFT;
+ else if (!of_property_read_u32(args->np, "stream-match-mask", &mask))
+ fwid |= (u16)mask << SMR_MASK_SHIFT;
return iommu_fwspec_add_ids(dev, &fwid, 1);
}
return;
list_add_tail(®ion->list, head);
+
+ iommu_dma_get_resv_regions(dev, head);
}
static void arm_smmu_put_resv_regions(struct device *dev,
/* Make sure all context banks are disabled and clear CB_FSR */
for (i = 0; i < smmu->num_context_banks; ++i) {
- cb_base = ARM_SMMU_CB_BASE(smmu) + ARM_SMMU_CB(smmu, i);
+ cb_base = ARM_SMMU_CB(smmu, i);
writel_relaxed(0, cb_base + ARM_SMMU_CB_SCTLR);
writel_relaxed(FSR_FAULT, cb_base + ARM_SMMU_CB_FSR);
/*
reg |= sCR0_EXIDENABLE;
/* Push the button */
- __arm_smmu_tlb_sync(smmu);
+ arm_smmu_tlb_sync_global(smmu);
writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
}
/* Check for size mismatch of SMMU address space from mapped region */
size = 1 << (((id >> ID1_NUMPAGENDXB_SHIFT) & ID1_NUMPAGENDXB_MASK) + 1);
- size *= 2 << smmu->pgshift;
- if (smmu->size != size)
+ size <<= smmu->pgshift;
+ if (smmu->cb_base != gr0_base + size)
dev_warn(smmu->dev,
- "SMMU address space size (0x%lx) differs from mapped region size (0x%lx)!\n",
- size, smmu->size);
+ "SMMU address space size (0x%lx) differs from mapped region size (0x%tx)!\n",
+ size * 2, (smmu->cb_base - gr0_base) * 2);
smmu->num_s2_context_banks = (id >> ID1_NUMS2CB_SHIFT) & ID1_NUMS2CB_MASK;
smmu->num_context_banks = (id >> ID1_NUMCB_SHIFT) & ID1_NUMCB_MASK;
atomic_add_return(smmu->num_context_banks,
&cavium_smmu_context_count);
smmu->cavium_id_base -= smmu->num_context_banks;
+ dev_notice(smmu->dev, "\tenabling workaround for Cavium erratum 27704\n");
}
/* ID2 */
return 0;
}
+static void arm_smmu_bus_init(void)
+{
+ /* Oh, for a proper bus abstraction */
+ if (!iommu_present(&platform_bus_type))
+ bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
+#ifdef CONFIG_ARM_AMBA
+ if (!iommu_present(&amba_bustype))
+ bus_set_iommu(&amba_bustype, &arm_smmu_ops);
+#endif
+#ifdef CONFIG_PCI
+ if (!iommu_present(&pci_bus_type)) {
+ pci_request_acs();
+ bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
+ }
+#endif
+}
+
static int arm_smmu_device_probe(struct platform_device *pdev)
{
struct resource *res;
smmu->base = devm_ioremap_resource(dev, res);
if (IS_ERR(smmu->base))
return PTR_ERR(smmu->base);
- smmu->size = resource_size(res);
+ smmu->cb_base = smmu->base + resource_size(res) / 2;
num_irqs = 0;
while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, num_irqs))) {
arm_smmu_device_reset(smmu);
arm_smmu_test_smr_masks(smmu);
- /* Oh, for a proper bus abstraction */
- if (!iommu_present(&platform_bus_type))
- bus_set_iommu(&platform_bus_type, &arm_smmu_ops);
-#ifdef CONFIG_ARM_AMBA
- if (!iommu_present(&amba_bustype))
- bus_set_iommu(&amba_bustype, &arm_smmu_ops);
-#endif
-#ifdef CONFIG_PCI
- if (!iommu_present(&pci_bus_type)) {
- pci_request_acs();
- bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
- }
-#endif
+ /*
+ * For ACPI and generic DT bindings, an SMMU will be probed before
+ * any device which might need it, so we want the bus ops in place
+ * ready to handle default domain setup as soon as any SMMU exists.
+ */
+ if (!using_legacy_binding)
+ arm_smmu_bus_init();
+
+ return 0;
+}
+
+/*
+ * With the legacy DT binding in play, though, we have no guarantees about
+ * probe order, but then we're also not doing default domains, so we can
+ * delay setting bus ops until we're sure every possible SMMU is ready,
+ * and that way ensure that no add_device() calls get missed.
+ */
+static int arm_smmu_legacy_bus_init(void)
+{
+ if (using_legacy_binding)
+ arm_smmu_bus_init();
return 0;
}
+device_initcall_sync(arm_smmu_legacy_bus_init);
static int arm_smmu_device_remove(struct platform_device *pdev)
{
.probe = arm_smmu_device_probe,
.remove = arm_smmu_device_remove,
};
-
-static int __init arm_smmu_init(void)
-{
- static bool registered;
- int ret = 0;
-
- if (!registered) {
- ret = platform_driver_register(&arm_smmu_driver);
- registered = !ret;
- }
- return ret;
-}
-
-static void __exit arm_smmu_exit(void)
-{
- return platform_driver_unregister(&arm_smmu_driver);
-}
-
-subsys_initcall(arm_smmu_init);
-module_exit(arm_smmu_exit);
-
-static int __init arm_smmu_of_init(struct device_node *np)
-{
- int ret = arm_smmu_init();
-
- if (ret)
- return ret;
-
- if (!of_platform_device_create(np, NULL, platform_bus_type.dev_root))
- return -ENODEV;
-
- return 0;
-}
-IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1", arm_smmu_of_init);
-IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2", arm_smmu_of_init);
-IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400", arm_smmu_of_init);
-IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401", arm_smmu_of_init);
-IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", arm_smmu_of_init);
-IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", arm_smmu_of_init);
-
-#ifdef CONFIG_ACPI
-static int __init arm_smmu_acpi_init(struct acpi_table_header *table)
-{
- if (iort_node_match(ACPI_IORT_NODE_SMMU))
- return arm_smmu_init();
-
- return 0;
-}
-IORT_ACPI_DECLARE(arm_smmu, ACPI_SIG_IORT, arm_smmu_acpi_init);
-#endif
+module_platform_driver(arm_smmu_driver);
+
+IOMMU_OF_DECLARE(arm_smmuv1, "arm,smmu-v1", NULL);
+IOMMU_OF_DECLARE(arm_smmuv2, "arm,smmu-v2", NULL);
+IOMMU_OF_DECLARE(arm_mmu400, "arm,mmu-400", NULL);
+IOMMU_OF_DECLARE(arm_mmu401, "arm,mmu-401", NULL);
+IOMMU_OF_DECLARE(arm_mmu500, "arm,mmu-500", NULL);
+IOMMU_OF_DECLARE(cavium_smmuv2, "cavium,smmu-v2", NULL);
MODULE_DESCRIPTION("IOMMU API for ARM architected SMMU implementations");
MODULE_AUTHOR("Will Deacon <will.deacon@arm.com>");
return PAGE_SIZE;
}
-static inline struct iova_domain *cookie_iovad(struct iommu_domain *domain)
-{
- struct iommu_dma_cookie *cookie = domain->iova_cookie;
-
- if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
- return &cookie->iovad;
- return NULL;
-}
-
static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
{
struct iommu_dma_cookie *cookie;
}
EXPORT_SYMBOL(iommu_put_dma_cookie);
-static void iova_reserve_pci_windows(struct pci_dev *dev,
- struct iova_domain *iovad)
+/**
+ * iommu_dma_get_resv_regions - Reserved region driver helper
+ * @dev: Device from iommu_get_resv_regions()
+ * @list: Reserved region list from iommu_get_resv_regions()
+ *
+ * IOMMU drivers can use this to implement their .get_resv_regions callback
+ * for general non-IOMMU-specific reservations. Currently, this covers host
+ * bridge windows for PCI devices.
+ */
+void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
{
- struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus);
+ struct pci_host_bridge *bridge;
struct resource_entry *window;
- unsigned long lo, hi;
+ if (!dev_is_pci(dev))
+ return;
+
+ bridge = pci_find_host_bridge(to_pci_dev(dev)->bus);
resource_list_for_each_entry(window, &bridge->windows) {
- if (resource_type(window->res) != IORESOURCE_MEM &&
- resource_type(window->res) != IORESOURCE_IO)
+ struct iommu_resv_region *region;
+ phys_addr_t start;
+ size_t length;
+
+ if (resource_type(window->res) != IORESOURCE_MEM)
+ continue;
+
+ start = window->res->start - window->offset;
+ length = window->res->end - window->res->start + 1;
+ region = iommu_alloc_resv_region(start, length, 0,
+ IOMMU_RESV_RESERVED);
+ if (!region)
+ return;
+
+ list_add_tail(®ion->list, list);
+ }
+}
+EXPORT_SYMBOL(iommu_dma_get_resv_regions);
+
+static int cookie_init_hw_msi_region(struct iommu_dma_cookie *cookie,
+ phys_addr_t start, phys_addr_t end)
+{
+ struct iova_domain *iovad = &cookie->iovad;
+ struct iommu_dma_msi_page *msi_page;
+ int i, num_pages;
+
+ start -= iova_offset(iovad, start);
+ num_pages = iova_align(iovad, end - start) >> iova_shift(iovad);
+
+ msi_page = kcalloc(num_pages, sizeof(*msi_page), GFP_KERNEL);
+ if (!msi_page)
+ return -ENOMEM;
+
+ for (i = 0; i < num_pages; i++) {
+ msi_page[i].phys = start;
+ msi_page[i].iova = start;
+ INIT_LIST_HEAD(&msi_page[i].list);
+ list_add(&msi_page[i].list, &cookie->msi_page_list);
+ start += iovad->granule;
+ }
+
+ return 0;
+}
+
+static int iova_reserve_iommu_regions(struct device *dev,
+ struct iommu_domain *domain)
+{
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+ struct iova_domain *iovad = &cookie->iovad;
+ struct iommu_resv_region *region;
+ LIST_HEAD(resv_regions);
+ int ret = 0;
+
+ iommu_get_resv_regions(dev, &resv_regions);
+ list_for_each_entry(region, &resv_regions, list) {
+ unsigned long lo, hi;
+
+ /* We ARE the software that manages these! */
+ if (region->type == IOMMU_RESV_SW_MSI)
continue;
- lo = iova_pfn(iovad, window->res->start - window->offset);
- hi = iova_pfn(iovad, window->res->end - window->offset);
+ lo = iova_pfn(iovad, region->start);
+ hi = iova_pfn(iovad, region->start + region->length - 1);
reserve_iova(iovad, lo, hi);
+
+ if (region->type == IOMMU_RESV_MSI)
+ ret = cookie_init_hw_msi_region(cookie, region->start,
+ region->start + region->length);
+ if (ret)
+ break;
}
+ iommu_put_resv_regions(dev, &resv_regions);
+
+ return ret;
}
/**
struct iommu_dma_cookie *cookie = domain->iova_cookie;
struct iova_domain *iovad = &cookie->iovad;
unsigned long order, base_pfn, end_pfn;
- bool pci = dev && dev_is_pci(dev);
if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
return -EINVAL;
* leave the cache limit at the top of their range to save an rb_last()
* traversal on every allocation.
*/
- if (pci)
+ if (dev && dev_is_pci(dev))
end_pfn &= DMA_BIT_MASK(32) >> order;
/* start_pfn is always nonzero for an already-initialised domain */
* area cache limit down for the benefit of the smaller one.
*/
iovad->dma_32bit_pfn = min(end_pfn, iovad->dma_32bit_pfn);
- } else {
- init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
- if (pci)
- iova_reserve_pci_windows(to_pci_dev(dev), iovad);
+
+ return 0;
}
- return 0;
+
+ init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
+ if (!dev)
+ return 0;
+
+ return iova_reserve_iommu_regions(dev, domain);
}
EXPORT_SYMBOL(iommu_dma_init_domain);
}
}
-static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size,
- dma_addr_t dma_limit, struct device *dev)
+static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
+ size_t size, dma_addr_t dma_limit, struct device *dev)
{
- struct iova_domain *iovad = cookie_iovad(domain);
- unsigned long shift = iova_shift(iovad);
- unsigned long length = iova_align(iovad, size) >> shift;
- struct iova *iova = NULL;
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+ struct iova_domain *iovad = &cookie->iovad;
+ unsigned long shift, iova_len, iova = 0;
+
+ if (cookie->type == IOMMU_DMA_MSI_COOKIE) {
+ cookie->msi_iova += size;
+ return cookie->msi_iova - size;
+ }
+
+ shift = iova_shift(iovad);
+ iova_len = size >> shift;
+ /*
+ * Freeing non-power-of-two-sized allocations back into the IOVA caches
+ * will come back to bite us badly, so we have to waste a bit of space
+ * rounding up anything cacheable to make sure that can't happen. The
+ * order of the unadjusted size will still match upon freeing.
+ */
+ if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
+ iova_len = roundup_pow_of_two(iova_len);
if (domain->geometry.force_aperture)
dma_limit = min(dma_limit, domain->geometry.aperture_end);
/* Try to get PCI devices a SAC address */
if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
- iova = alloc_iova(iovad, length, DMA_BIT_MASK(32) >> shift,
- true);
- /*
- * Enforce size-alignment to be safe - there could perhaps be an
- * attribute to control this per-device, or at least per-domain...
- */
+ iova = alloc_iova_fast(iovad, iova_len, DMA_BIT_MASK(32) >> shift);
+
if (!iova)
- iova = alloc_iova(iovad, length, dma_limit >> shift, true);
+ iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift);
- return iova;
+ return (dma_addr_t)iova << shift;
}
-/* The IOVA allocator knows what we mapped, so just unmap whatever that was */
-static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr)
+static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
+ dma_addr_t iova, size_t size)
{
- struct iova_domain *iovad = cookie_iovad(domain);
+ struct iova_domain *iovad = &cookie->iovad;
unsigned long shift = iova_shift(iovad);
- unsigned long pfn = dma_addr >> shift;
- struct iova *iova = find_iova(iovad, pfn);
- size_t size;
- if (WARN_ON(!iova))
- return;
+ /* The MSI case is only ever cleaning up its most recent allocation */
+ if (cookie->type == IOMMU_DMA_MSI_COOKIE)
+ cookie->msi_iova -= size;
+ else
+ free_iova_fast(iovad, iova >> shift, size >> shift);
+}
+
+static void __iommu_dma_unmap(struct iommu_domain *domain, dma_addr_t dma_addr,
+ size_t size)
+{
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+ struct iova_domain *iovad = &cookie->iovad;
+ size_t iova_off = iova_offset(iovad, dma_addr);
+
+ dma_addr -= iova_off;
+ size = iova_align(iovad, size + iova_off);
- size = iova_size(iova) << shift;
- size -= iommu_unmap(domain, pfn << shift, size);
- /* ...and if we can't, then something is horribly, horribly wrong */
- WARN_ON(size > 0);
- __free_iova(iovad, iova);
+ WARN_ON(iommu_unmap(domain, dma_addr, size) != size);
+ iommu_dma_free_iova(cookie, dma_addr, size);
}
static void __iommu_dma_free_pages(struct page **pages, int count)
void iommu_dma_free(struct device *dev, struct page **pages, size_t size,
dma_addr_t *handle)
{
- __iommu_dma_unmap(iommu_get_domain_for_dev(dev), *handle);
+ __iommu_dma_unmap(iommu_get_domain_for_dev(dev), *handle, size);
__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
*handle = DMA_ERROR_CODE;
}
void (*flush_page)(struct device *, const void *, phys_addr_t))
{
struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
- struct iova_domain *iovad = cookie_iovad(domain);
- struct iova *iova;
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+ struct iova_domain *iovad = &cookie->iovad;
struct page **pages;
struct sg_table sgt;
- dma_addr_t dma_addr;
+ dma_addr_t iova;
unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
*handle = DMA_ERROR_CODE;
if (!pages)
return NULL;
- iova = __alloc_iova(domain, size, dev->coherent_dma_mask, dev);
+ size = iova_align(iovad, size);
+ iova = iommu_dma_alloc_iova(domain, size, dev->coherent_dma_mask, dev);
if (!iova)
goto out_free_pages;
- size = iova_align(iovad, size);
if (sg_alloc_table_from_pages(&sgt, pages, count, 0, size, GFP_KERNEL))
goto out_free_iova;
sg_miter_stop(&miter);
}
- dma_addr = iova_dma_addr(iovad, iova);
- if (iommu_map_sg(domain, dma_addr, sgt.sgl, sgt.orig_nents, prot)
+ if (iommu_map_sg(domain, iova, sgt.sgl, sgt.orig_nents, prot)
< size)
goto out_free_sg;
- *handle = dma_addr;
+ *handle = iova;
sg_free_table(&sgt);
return pages;
out_free_sg:
sg_free_table(&sgt);
out_free_iova:
- __free_iova(iovad, iova);
+ iommu_dma_free_iova(cookie, iova, size);
out_free_pages:
__iommu_dma_free_pages(pages, count);
return NULL;
static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
size_t size, int prot)
{
- dma_addr_t dma_addr;
struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
- struct iova_domain *iovad = cookie_iovad(domain);
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+ struct iova_domain *iovad = &cookie->iovad;
size_t iova_off = iova_offset(iovad, phys);
- size_t len = iova_align(iovad, size + iova_off);
- struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev), dev);
+ dma_addr_t iova;
+ size = iova_align(iovad, size + iova_off);
+ iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
if (!iova)
return DMA_ERROR_CODE;
- dma_addr = iova_dma_addr(iovad, iova);
- if (iommu_map(domain, dma_addr, phys - iova_off, len, prot)) {
- __free_iova(iovad, iova);
+ if (iommu_map(domain, iova, phys - iova_off, size, prot)) {
+ iommu_dma_free_iova(cookie, iova, size);
return DMA_ERROR_CODE;
}
- return dma_addr + iova_off;
+ return iova + iova_off;
}
dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
void iommu_dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
enum dma_data_direction dir, unsigned long attrs)
{
- __iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle);
+ __iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle, size);
}
/*
int nents, int prot)
{
struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
- struct iova_domain *iovad = cookie_iovad(domain);
- struct iova *iova;
+ struct iommu_dma_cookie *cookie = domain->iova_cookie;
+ struct iova_domain *iovad = &cookie->iovad;
struct scatterlist *s, *prev = NULL;
- dma_addr_t dma_addr;
+ dma_addr_t iova;
size_t iova_len = 0;
unsigned long mask = dma_get_seg_boundary(dev);
int i;
prev = s;
}
- iova = __alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
+ iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
if (!iova)
goto out_restore_sg;
* We'll leave any physical concatenation to the IOMMU driver's
* implementation - it knows better than we do.
*/
- dma_addr = iova_dma_addr(iovad, iova);
- if (iommu_map_sg(domain, dma_addr, sg, nents, prot) < iova_len)
+ if (iommu_map_sg(domain, iova, sg, nents, prot) < iova_len)
goto out_free_iova;
- return __finalise_sg(dev, sg, nents, dma_addr);
+ return __finalise_sg(dev, sg, nents, iova);
out_free_iova:
- __free_iova(iovad, iova);
+ iommu_dma_free_iova(cookie, iova, iova_len);
out_restore_sg:
__invalidate_sg(sg, nents);
return 0;
void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
enum dma_data_direction dir, unsigned long attrs)
{
+ dma_addr_t start, end;
+ struct scatterlist *tmp;
+ int i;
/*
* The scatterlist segments are mapped into a single
* contiguous IOVA allocation, so this is incredibly easy.
*/
- __iommu_dma_unmap(iommu_get_domain_for_dev(dev), sg_dma_address(sg));
+ start = sg_dma_address(sg);
+ for_each_sg(sg_next(sg), tmp, nents - 1, i) {
+ if (sg_dma_len(tmp) == 0)
+ break;
+ sg = tmp;
+ }
+ end = sg_dma_address(sg) + sg_dma_len(sg);
+ __iommu_dma_unmap(iommu_get_domain_for_dev(dev), start, end - start);
}
dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
size_t size, enum dma_data_direction dir, unsigned long attrs)
{
- __iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle);
+ __iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle, size);
}
int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
struct iommu_dma_cookie *cookie = domain->iova_cookie;
struct iommu_dma_msi_page *msi_page;
- struct iova_domain *iovad = cookie_iovad(domain);
- struct iova *iova;
+ dma_addr_t iova;
int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
size_t size = cookie_msi_granule(cookie);
if (!msi_page)
return NULL;
- msi_page->phys = msi_addr;
- if (iovad) {
- iova = __alloc_iova(domain, size, dma_get_mask(dev), dev);
- if (!iova)
- goto out_free_page;
- msi_page->iova = iova_dma_addr(iovad, iova);
- } else {
- msi_page->iova = cookie->msi_iova;
- cookie->msi_iova += size;
- }
-
- if (iommu_map(domain, msi_page->iova, msi_addr, size, prot))
- goto out_free_iova;
+ iova = __iommu_dma_map(dev, msi_addr, size, prot);
+ if (iommu_dma_mapping_error(dev, iova))
+ goto out_free_page;
INIT_LIST_HEAD(&msi_page->list);
+ msi_page->phys = msi_addr;
+ msi_page->iova = iova;
list_add(&msi_page->list, &cookie->msi_page_list);
return msi_page;
-out_free_iova:
- if (iovad)
- __free_iova(iovad, iova);
- else
- cookie->msi_iova -= size;
out_free_page:
kfree(msi_page);
return NULL;
((void *)drhd) + drhd->header.length,
dmaru->segment,
dmaru->devices, dmaru->devices_cnt);
- if (ret != 0)
+ if (ret)
break;
}
if (ret >= 0)
{
struct acpi_dmar_hardware_unit *drhd;
struct dmar_drhd_unit *dmaru;
- int ret = 0;
+ int ret;
drhd = (struct acpi_dmar_hardware_unit *)header;
dmaru = dmar_find_dmaru(drhd);
status = AE_NOT_FOUND;
}
- return (ACPI_SUCCESS(status) ? 1 : 0);
+ return ACPI_SUCCESS(status) ? 0 : -ENOENT;
}
static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
size_t len, struct dmar_res_callback *cb)
{
- int ret = 0;
struct acpi_dmar_header *iter, *next;
struct acpi_dmar_header *end = ((void *)start) + len;
- for (iter = start; iter < end && ret == 0; iter = next) {
+ for (iter = start; iter < end; iter = next) {
next = (void *)iter + iter->length;
if (iter->length == 0) {
/* Avoid looping forever on bad ACPI tables */
} else if (next > end) {
/* Avoid passing table end */
pr_warn(FW_BUG "Record passes table end\n");
- ret = -EINVAL;
- break;
+ return -EINVAL;
}
if (cb->print_entry)
pr_debug("Unknown DMAR structure type %d\n",
iter->type);
} else if (cb->cb[iter->type]) {
+ int ret;
+
ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
+ if (ret)
+ return ret;
} else if (!cb->ignore_unhandled) {
pr_warn("No handler for DMAR structure type %d\n",
iter->type);
- ret = -EINVAL;
+ return -EINVAL;
}
}
- return ret;
+ return 0;
}
static inline int dmar_walk_dmar_table(struct acpi_table_dmar *dmar,
parse_dmar_table(void)
{
struct acpi_table_dmar *dmar;
- int ret = 0;
int drhd_count = 0;
+ int ret;
struct dmar_res_callback cb = {
.print_entry = true,
.ignore_unhandled = true,
down_write(&dmar_global_lock);
ret = dmar_table_detect();
- if (ret)
- ret = !dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
- &validate_drhd_cb);
- if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
+ if (!ret)
+ ret = dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
+ &validate_drhd_cb);
+ if (!ret && !no_iommu && !iommu_detected && !dmar_disabled) {
iommu_detected = 1;
/* Make sure ACS will be enabled */
pci_request_acs();
}
#ifdef CONFIG_X86
- if (ret)
+ if (!ret)
x86_init.iommu.iommu_init = intel_iommu_init;
#endif
}
up_write(&dmar_global_lock);
- return ret ? 1 : -ENODEV;
+ return ret ? ret : 1;
}
-
static void unmap_iommu(struct intel_iommu *iommu)
{
iounmap(iommu->reg);
#define REG_V5_PT_BASE_PFN 0x00C
#define REG_V5_MMU_FLUSH_ALL 0x010
#define REG_V5_MMU_FLUSH_ENTRY 0x014
+#define REG_V5_MMU_FLUSH_RANGE 0x018
+#define REG_V5_MMU_FLUSH_START 0x020
+#define REG_V5_MMU_FLUSH_END 0x024
#define REG_V5_INT_STATUS 0x060
#define REG_V5_INT_CLEAR 0x064
#define REG_V5_FAULT_AR_VA 0x070
{
unsigned int i;
- for (i = 0; i < num_inv; i++) {
- if (MMU_MAJ_VER(data->version) < 5)
+ if (MMU_MAJ_VER(data->version) < 5) {
+ for (i = 0; i < num_inv; i++) {
writel((iova & SPAGE_MASK) | 1,
data->sfrbase + REG_MMU_FLUSH_ENTRY);
- else
+ iova += SPAGE_SIZE;
+ }
+ } else {
+ if (num_inv == 1) {
writel((iova & SPAGE_MASK) | 1,
data->sfrbase + REG_V5_MMU_FLUSH_ENTRY);
- iova += SPAGE_SIZE;
+ } else {
+ writel((iova & SPAGE_MASK),
+ data->sfrbase + REG_V5_MMU_FLUSH_START);
+ writel((iova & SPAGE_MASK) + (num_inv - 1) * SPAGE_SIZE,
+ data->sfrbase + REG_V5_MMU_FLUSH_END);
+ writel(1, data->sfrbase + REG_V5_MMU_FLUSH_RANGE);
+ }
}
}
goto err_counter;
/* Workaround for System MMU v3.3 to prevent caching 1MiB mapping */
- for (i = 0; i < NUM_LV1ENTRIES; i += 8) {
- domain->pgtable[i + 0] = ZERO_LV2LINK;
- domain->pgtable[i + 1] = ZERO_LV2LINK;
- domain->pgtable[i + 2] = ZERO_LV2LINK;
- domain->pgtable[i + 3] = ZERO_LV2LINK;
- domain->pgtable[i + 4] = ZERO_LV2LINK;
- domain->pgtable[i + 5] = ZERO_LV2LINK;
- domain->pgtable[i + 6] = ZERO_LV2LINK;
- domain->pgtable[i + 7] = ZERO_LV2LINK;
- }
+ for (i = 0; i < NUM_LV1ENTRIES; i++)
+ domain->pgtable[i] = ZERO_LV2LINK;
handle = dma_map_single(dma_dev, domain->pgtable, LV1TABLE_SIZE,
DMA_TO_DEVICE);
#define __FSL_PAMU_H
#include <linux/iommu.h>
+#include <linux/pci.h>
#include <asm/fsl_pamu_stash.h>
* (used when kernel is launched w/ TXT)
*/
static int force_on = 0;
+int intel_iommu_tboot_noforce;
/*
* 0: Present
"Intel-IOMMU: enable pre-production PASID support\n");
intel_iommu_pasid28 = 1;
iommu_identity_mapping |= IDENTMAP_GFX;
+ } else if (!strncmp(str, "tboot_noforce", 13)) {
+ printk(KERN_INFO
+ "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
+ intel_iommu_tboot_noforce = 1;
}
str += strcspn(str, ",");
return 0;
}
+static void intel_disable_iommus(void)
+{
+ struct intel_iommu *iommu = NULL;
+ struct dmar_drhd_unit *drhd;
+
+ for_each_iommu(iommu, drhd)
+ iommu_disable_translation(iommu);
+}
+
static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev)
{
return container_of(dev, struct intel_iommu, iommu.dev);
goto out_free_dmar;
}
- if (no_iommu || dmar_disabled)
+ if (no_iommu || dmar_disabled) {
+ /*
+ * We exit the function here to ensure IOMMU's remapping and
+ * mempool aren't setup, which means that the IOMMU's PMRs
+ * won't be disabled via the call to init_dmars(). So disable
+ * it explicitly here. The PMRs were setup by tboot prior to
+ * calling SENTER, but the kernel is expected to reset/tear
+ * down the PMRs.
+ */
+ if (intel_iommu_tboot_noforce) {
+ for_each_iommu(iommu, drhd)
+ iommu_disable_protect_mem_regions(iommu);
+ }
+
+ /*
+ * Make sure the IOMMUs are switched off, even when we
+ * boot into a kexec kernel and the previous kernel left
+ * them enabled
+ */
+ intel_disable_iommus();
goto out_free_dmar;
+ }
if (list_empty(&dmar_rmrr_units))
pr_info("No RMRR found\n");
size_t size;
u64 irta;
- if (!is_kdump_kernel()) {
- pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
- iommu->name);
- clear_ir_pre_enabled(iommu);
- iommu_disable_irq_remapping(iommu);
- return -EINVAL;
- }
-
/* Check whether the old ir-table has the same size as ours */
irta = dmar_readq(iommu->reg + DMAR_IRTA_REG);
if ((irta & INTR_REMAP_TABLE_REG_SIZE_MASK)
init_ir_status(iommu);
if (ir_pre_enabled(iommu)) {
- if (iommu_load_old_irte(iommu))
+ if (!is_kdump_kernel()) {
+ pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
+ iommu->name);
+ clear_ir_pre_enabled(iommu);
+ iommu_disable_irq_remapping(iommu);
+ } else if (iommu_load_old_irte(iommu))
pr_err("Failed to copy IR table for %s from previous kernel\n",
iommu->name);
else
/* Calculate the block/page mapping size at level l for pagetable in d. */
#define ARM_LPAE_BLOCK_SIZE(l,d) \
- (1 << (ilog2(sizeof(arm_lpae_iopte)) + \
+ (1ULL << (ilog2(sizeof(arm_lpae_iopte)) + \
((ARM_LPAE_MAX_LEVELS - (l)) * (d)->bits_per_level)))
/* Page table bits */
static struct kset *iommu_group_kset;
static DEFINE_IDA(iommu_group_ida);
+static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA;
struct iommu_callback_data {
const struct iommu_ops *ops;
static void __iommu_detach_group(struct iommu_domain *domain,
struct iommu_group *group);
+static int __init iommu_set_def_domain_type(char *str)
+{
+ bool pt;
+
+ if (!str || strtobool(str, &pt))
+ return -EINVAL;
+
+ iommu_def_domain_type = pt ? IOMMU_DOMAIN_IDENTITY : IOMMU_DOMAIN_DMA;
+ return 0;
+}
+early_param("iommu.passthrough", iommu_set_def_domain_type);
+
static ssize_t iommu_group_attr_show(struct kobject *kobj,
struct attribute *__attr, char *buf)
{
* IOMMU driver.
*/
if (!group->default_domain) {
- group->default_domain = __iommu_domain_alloc(dev->bus,
- IOMMU_DOMAIN_DMA);
+ struct iommu_domain *dom;
+
+ dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
+ if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
+ dev_warn(dev,
+ "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
+ iommu_def_domain_type);
+ dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
+ }
+
+ group->default_domain = dom;
if (!group->domain)
- group->domain = group->default_domain;
+ group->domain = dom;
}
ret = iommu_group_add_device(group, dev);
* result in ADD/DEL notifiers to group->notifier
*/
if (action == BUS_NOTIFY_ADD_DEVICE) {
- if (ops->add_device)
- return ops->add_device(dev);
+ if (ops->add_device) {
+ int ret;
+
+ ret = ops->add_device(dev);
+ return (ret) ? NOTIFY_DONE : NOTIFY_OK;
+ }
} else if (action == BUS_NOTIFY_REMOVED_DEVICE) {
if (ops->remove_device && dev->iommu_group) {
ops->remove_device(dev);
}
EXPORT_SYMBOL_GPL(iommu_domain_window_disable);
+/**
+ * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
+ * @domain: the iommu domain where the fault has happened
+ * @dev: the device where the fault has happened
+ * @iova: the faulting address
+ * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...)
+ *
+ * This function should be called by the low-level IOMMU implementations
+ * whenever IOMMU faults happen, to allow high-level users, that are
+ * interested in such events, to know about them.
+ *
+ * This event may be useful for several possible use cases:
+ * - mere logging of the event
+ * - dynamic TLB/PTE loading
+ * - if restarting of the faulting device is required
+ *
+ * Returns 0 on success and an appropriate error code otherwise (if dynamic
+ * PTE/TLB loading will one day be supported, implementations will be able
+ * to tell whether it succeeded or not according to this return value).
+ *
+ * Specifically, -ENOSYS is returned if a fault handler isn't installed
+ * (though fault handlers can also return -ENOSYS, in case they want to
+ * elicit the default behavior of the IOMMU drivers).
+ */
+int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
+ unsigned long iova, int flags)
+{
+ int ret = -ENOSYS;
+
+ /*
+ * if upper layers showed interest and installed a fault handler,
+ * invoke it.
+ */
+ if (domain->handler)
+ ret = domain->handler(domain, dev, iova, flags,
+ domain->handler_token);
+
+ trace_io_page_fault(dev, iova, flags);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(report_iommu_fault);
+
static int __init iommu_init(void)
{
iommu_group_kset = kset_create_and_add("iommu_groups",
break; /* found a free slot */
}
adjust_limit_pfn:
- limit_pfn = curr_iova->pfn_lo - 1;
+ limit_pfn = curr_iova->pfn_lo ? (curr_iova->pfn_lo - 1) : 0;
move_left:
prev = curr;
curr = rb_prev(curr);
static int mtk_iommu_add_device(struct device *dev)
{
- struct iommu_group *group;
struct of_phandle_args iommu_spec;
struct of_phandle_iterator it;
+ struct mtk_iommu_data *data;
+ struct iommu_group *group;
int err;
of_for_each_phandle(&it, err, dev->of_node, "iommus",
if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
return -ENODEV; /* Not a iommu client device */
+ data = dev->iommu_fwspec->iommu_priv;
+ iommu_device_link(&data->iommu, dev);
+
group = iommu_group_get_for_dev(dev);
if (IS_ERR(group))
return PTR_ERR(group);
static void mtk_iommu_remove_device(struct device *dev)
{
+ struct mtk_iommu_data *data;
+
if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
return;
+ data = dev->iommu_fwspec->iommu_priv;
+ iommu_device_unlink(&data->iommu, dev);
+
iommu_group_remove_device(dev);
iommu_fwspec_free(dev);
}
if (ret)
return ret;
+ ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
+ dev_name(&pdev->dev));
+ if (ret)
+ return ret;
+
+ iommu_device_set_ops(&data->iommu, &mtk_iommu_ops);
+
+ ret = iommu_device_register(&data->iommu);
+ if (ret)
+ return ret;
+
if (!iommu_present(&platform_bus_type))
bus_set_iommu(&platform_bus_type, &mtk_iommu_ops);
{
struct mtk_iommu_data *data = platform_get_drvdata(pdev);
+ iommu_device_sysfs_remove(&data->iommu);
+ iommu_device_unregister(&data->iommu);
+
if (iommu_present(&platform_bus_type))
bus_set_iommu(&platform_bus_type, NULL);
}
EXPORT_SYMBOL_GPL(of_get_dma_window);
+static bool of_iommu_driver_present(struct device_node *np)
+{
+ /*
+ * If the IOMMU still isn't ready by the time we reach init, assume
+ * it never will be. We don't want to defer indefinitely, nor attempt
+ * to dereference __iommu_of_table after it's been freed.
+ */
+ if (system_state > SYSTEM_BOOTING)
+ return false;
+
+ return of_match_node(&__iommu_of_table, np);
+}
+
+static const struct iommu_ops
+*of_iommu_xlate(struct device *dev, struct of_phandle_args *iommu_spec)
+{
+ const struct iommu_ops *ops;
+ struct fwnode_handle *fwnode = &iommu_spec->np->fwnode;
+ int err;
+
+ ops = iommu_ops_from_fwnode(fwnode);
+ if ((ops && !ops->of_xlate) ||
+ (!ops && !of_iommu_driver_present(iommu_spec->np)))
+ return NULL;
+
+ err = iommu_fwspec_init(dev, &iommu_spec->np->fwnode, ops);
+ if (err)
+ return ERR_PTR(err);
+ /*
+ * The otherwise-empty fwspec handily serves to indicate the specific
+ * IOMMU device we're waiting for, which will be useful if we ever get
+ * a proper probe-ordering dependency mechanism in future.
+ */
+ if (!ops)
+ return ERR_PTR(-EPROBE_DEFER);
+
+ err = ops->of_xlate(dev, iommu_spec);
+ if (err)
+ return ERR_PTR(err);
+
+ return ops;
+}
+
static int __get_pci_rid(struct pci_dev *pdev, u16 alias, void *data)
{
struct of_phandle_args *iommu_spec = data;
}
static const struct iommu_ops
-*of_pci_iommu_configure(struct pci_dev *pdev, struct device_node *bridge_np)
+*of_pci_iommu_init(struct pci_dev *pdev, struct device_node *bridge_np)
{
const struct iommu_ops *ops;
struct of_phandle_args iommu_spec;
+ int err;
/*
* Start by tracing the RID alias down the PCI topology as
* bus into the system beyond, and which IOMMU it ends up at.
*/
iommu_spec.np = NULL;
- if (of_pci_map_rid(bridge_np, iommu_spec.args[0], "iommu-map",
- "iommu-map-mask", &iommu_spec.np, iommu_spec.args))
- return NULL;
+ err = of_pci_map_rid(bridge_np, iommu_spec.args[0], "iommu-map",
+ "iommu-map-mask", &iommu_spec.np,
+ iommu_spec.args);
+ if (err)
+ return err == -ENODEV ? NULL : ERR_PTR(err);
- ops = iommu_ops_from_fwnode(&iommu_spec.np->fwnode);
- if (!ops || !ops->of_xlate ||
- iommu_fwspec_init(&pdev->dev, &iommu_spec.np->fwnode, ops) ||
- ops->of_xlate(&pdev->dev, &iommu_spec))
- ops = NULL;
+ ops = of_iommu_xlate(&pdev->dev, &iommu_spec);
of_node_put(iommu_spec.np);
return ops;
}
-const struct iommu_ops *of_iommu_configure(struct device *dev,
- struct device_node *master_np)
+static const struct iommu_ops
+*of_platform_iommu_init(struct device *dev, struct device_node *np)
{
struct of_phandle_args iommu_spec;
- struct device_node *np;
const struct iommu_ops *ops = NULL;
int idx = 0;
- if (dev_is_pci(dev))
- return of_pci_iommu_configure(to_pci_dev(dev), master_np);
-
/*
* We don't currently walk up the tree looking for a parent IOMMU.
* See the `Notes:' section of
* Documentation/devicetree/bindings/iommu/iommu.txt
*/
- while (!of_parse_phandle_with_args(master_np, "iommus",
- "#iommu-cells", idx,
- &iommu_spec)) {
- np = iommu_spec.np;
- ops = iommu_ops_from_fwnode(&np->fwnode);
-
- if (!ops || !ops->of_xlate ||
- iommu_fwspec_init(dev, &np->fwnode, ops) ||
- ops->of_xlate(dev, &iommu_spec))
- goto err_put_node;
-
- of_node_put(np);
+ while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells",
+ idx, &iommu_spec)) {
+ ops = of_iommu_xlate(dev, &iommu_spec);
+ of_node_put(iommu_spec.np);
idx++;
+ if (IS_ERR_OR_NULL(ops))
+ break;
}
return ops;
+}
+
+const struct iommu_ops *of_iommu_configure(struct device *dev,
+ struct device_node *master_np)
+{
+ const struct iommu_ops *ops;
+ struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+
+ if (!master_np)
+ return NULL;
+
+ if (fwspec) {
+ if (fwspec->ops)
+ return fwspec->ops;
+
+ /* In the deferred case, start again from scratch */
+ iommu_fwspec_free(dev);
+ }
-err_put_node:
- of_node_put(np);
- return NULL;
+ if (dev_is_pci(dev))
+ ops = of_pci_iommu_init(to_pci_dev(dev), master_np);
+ else
+ ops = of_platform_iommu_init(dev, master_np);
+ /*
+ * If we have reason to believe the IOMMU driver missed the initial
+ * add_device callback for dev, replay it to get things in order.
+ */
+ if (!IS_ERR_OR_NULL(ops) && ops->add_device &&
+ dev->bus && !dev->iommu_group) {
+ int err = ops->add_device(dev);
+
+ if (err)
+ ops = ERR_PTR(err);
+ }
+
+ return ops;
}
static int __init of_iommu_init(void)
for_each_matching_node_and_match(np, matches, &match) {
const of_iommu_init_fn init_fn = match->data;
- if (init_fn(np))
+ if (init_fn && init_fn(np))
pr_err("Failed to initialise IOMMU %s\n",
of_node_full_name(np));
}
#include "omap-iopgtable.h"
#include "omap-iommu.h"
+static const struct iommu_ops omap_iommu_ops;
+
#define to_iommu(dev) \
((struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)))
/* bitmap of the page sizes currently supported */
#define OMAP_IOMMU_PGSIZES (SZ_4K | SZ_64K | SZ_1M | SZ_16M)
-/**
- * struct omap_iommu_domain - omap iommu domain
- * @pgtable: the page table
- * @iommu_dev: an omap iommu device attached to this domain. only a single
- * iommu device can be attached for now.
- * @dev: Device using this domain.
- * @lock: domain lock, should be taken when attaching/detaching
- */
-struct omap_iommu_domain {
- u32 *pgtable;
- struct omap_iommu *iommu_dev;
- struct device *dev;
- spinlock_t lock;
- struct iommu_domain domain;
-};
-
#define MMU_LOCK_BASE_SHIFT 10
#define MMU_LOCK_BASE_MASK (0x1f << MMU_LOCK_BASE_SHIFT)
#define MMU_LOCK_BASE(x) \
return IRQ_NONE;
}
-static int device_match_by_alias(struct device *dev, void *data)
-{
- struct omap_iommu *obj = to_iommu(dev);
- const char *name = data;
-
- pr_debug("%s: %s %s\n", __func__, obj->name, name);
-
- return strcmp(obj->name, name) == 0;
-}
-
/**
* omap_iommu_attach() - attach iommu device to an iommu domain
- * @name: name of target omap iommu device
+ * @obj: target omap iommu device
* @iopgd: page table
**/
-static struct omap_iommu *omap_iommu_attach(const char *name, u32 *iopgd)
+static int omap_iommu_attach(struct omap_iommu *obj, u32 *iopgd)
{
int err;
- struct device *dev;
- struct omap_iommu *obj;
-
- dev = driver_find_device(&omap_iommu_driver.driver, NULL, (void *)name,
- device_match_by_alias);
- if (!dev)
- return ERR_PTR(-ENODEV);
-
- obj = to_iommu(dev);
spin_lock(&obj->iommu_lock);
spin_unlock(&obj->iommu_lock);
dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
- return obj;
+
+ return 0;
err_enable:
spin_unlock(&obj->iommu_lock);
- return ERR_PTR(err);
+
+ return err;
}
/**
int irq;
struct omap_iommu *obj;
struct resource *res;
- struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct device_node *of = pdev->dev.of_node;
+ if (!of) {
+ pr_err("%s: only DT-based devices are supported\n", __func__);
+ return -ENODEV;
+ }
+
obj = devm_kzalloc(&pdev->dev, sizeof(*obj) + MMU_REG_SIZE, GFP_KERNEL);
if (!obj)
return -ENOMEM;
- if (of) {
- obj->name = dev_name(&pdev->dev);
- obj->nr_tlb_entries = 32;
- err = of_property_read_u32(of, "ti,#tlb-entries",
- &obj->nr_tlb_entries);
- if (err && err != -EINVAL)
- return err;
- if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8)
- return -EINVAL;
- if (of_find_property(of, "ti,iommu-bus-err-back", NULL))
- obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN;
- } else {
- obj->nr_tlb_entries = pdata->nr_tlb_entries;
- obj->name = pdata->name;
- }
+ obj->name = dev_name(&pdev->dev);
+ obj->nr_tlb_entries = 32;
+ err = of_property_read_u32(of, "ti,#tlb-entries", &obj->nr_tlb_entries);
+ if (err && err != -EINVAL)
+ return err;
+ if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8)
+ return -EINVAL;
+ if (of_find_property(of, "ti,iommu-bus-err-back", NULL))
+ obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN;
obj->dev = &pdev->dev;
obj->ctx = (void *)obj + sizeof(*obj);
return err;
platform_set_drvdata(pdev, obj);
+ obj->group = iommu_group_alloc();
+ if (IS_ERR(obj->group))
+ return PTR_ERR(obj->group);
+
+ err = iommu_device_sysfs_add(&obj->iommu, obj->dev, NULL, obj->name);
+ if (err)
+ goto out_group;
+
+ iommu_device_set_ops(&obj->iommu, &omap_iommu_ops);
+
+ err = iommu_device_register(&obj->iommu);
+ if (err)
+ goto out_sysfs;
+
pm_runtime_irq_safe(obj->dev);
pm_runtime_enable(obj->dev);
omap_iommu_debugfs_add(obj);
dev_info(&pdev->dev, "%s registered\n", obj->name);
+
return 0;
+
+out_sysfs:
+ iommu_device_sysfs_remove(&obj->iommu);
+out_group:
+ iommu_group_put(obj->group);
+ return err;
}
static int omap_iommu_remove(struct platform_device *pdev)
{
struct omap_iommu *obj = platform_get_drvdata(pdev);
+ iommu_group_put(obj->group);
+ obj->group = NULL;
+
+ iommu_device_sysfs_remove(&obj->iommu);
+ iommu_device_unregister(&obj->iommu);
+
omap_iommu_debugfs_remove(obj);
pm_runtime_disable(obj->dev);
omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
- struct omap_iommu *oiommu;
struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+ struct omap_iommu *oiommu;
int ret = 0;
- if (!arch_data || !arch_data->name) {
+ if (!arch_data || !arch_data->iommu_dev) {
dev_err(dev, "device doesn't have an associated iommu\n");
return -EINVAL;
}
goto out;
}
+ oiommu = arch_data->iommu_dev;
+
/* get a handle to and enable the omap iommu */
- oiommu = omap_iommu_attach(arch_data->name, omap_domain->pgtable);
- if (IS_ERR(oiommu)) {
- ret = PTR_ERR(oiommu);
+ ret = omap_iommu_attach(oiommu, omap_domain->pgtable);
+ if (ret) {
dev_err(dev, "can't get omap iommu: %d\n", ret);
goto out;
}
- omap_domain->iommu_dev = arch_data->iommu_dev = oiommu;
+ omap_domain->iommu_dev = oiommu;
omap_domain->dev = dev;
oiommu->domain = domain;
struct device *dev)
{
struct omap_iommu *oiommu = dev_to_omap_iommu(dev);
- struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
/* only a single device is supported per domain for now */
if (omap_domain->iommu_dev != oiommu) {
omap_iommu_detach(oiommu);
- omap_domain->iommu_dev = arch_data->iommu_dev = NULL;
+ omap_domain->iommu_dev = NULL;
omap_domain->dev = NULL;
oiommu->domain = NULL;
}
static int omap_iommu_add_device(struct device *dev)
{
struct omap_iommu_arch_data *arch_data;
+ struct omap_iommu *oiommu;
+ struct iommu_group *group;
struct device_node *np;
struct platform_device *pdev;
+ int ret;
/*
* Allocate the archdata iommu structure for DT-based devices.
return -EINVAL;
}
+ oiommu = platform_get_drvdata(pdev);
+ if (!oiommu) {
+ of_node_put(np);
+ return -EINVAL;
+ }
+
arch_data = kzalloc(sizeof(*arch_data), GFP_KERNEL);
if (!arch_data) {
of_node_put(np);
return -ENOMEM;
}
- arch_data->name = kstrdup(dev_name(&pdev->dev), GFP_KERNEL);
+ ret = iommu_device_link(&oiommu->iommu, dev);
+ if (ret) {
+ kfree(arch_data);
+ of_node_put(np);
+ return ret;
+ }
+
+ arch_data->iommu_dev = oiommu;
dev->archdata.iommu = arch_data;
+ /*
+ * IOMMU group initialization calls into omap_iommu_device_group, which
+ * needs a valid dev->archdata.iommu pointer
+ */
+ group = iommu_group_get_for_dev(dev);
+ if (IS_ERR(group)) {
+ iommu_device_unlink(&oiommu->iommu, dev);
+ dev->archdata.iommu = NULL;
+ kfree(arch_data);
+ return PTR_ERR(group);
+ }
+ iommu_group_put(group);
+
of_node_put(np);
return 0;
if (!dev->of_node || !arch_data)
return;
- kfree(arch_data->name);
+ iommu_device_unlink(&arch_data->iommu_dev->iommu, dev);
+ iommu_group_remove_device(dev);
+
+ dev->archdata.iommu = NULL;
kfree(arch_data);
+
+}
+
+static struct iommu_group *omap_iommu_device_group(struct device *dev)
+{
+ struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
+ struct iommu_group *group = NULL;
+
+ if (arch_data->iommu_dev)
+ group = arch_data->iommu_dev->group;
+
+ return group;
}
static const struct iommu_ops omap_iommu_ops = {
.iova_to_phys = omap_iommu_iova_to_phys,
.add_device = omap_iommu_add_device,
.remove_device = omap_iommu_remove_device,
+ .device_group = omap_iommu_device_group,
.pgsize_bitmap = OMAP_IOMMU_PGSIZES,
};
const unsigned long flags = SLAB_HWCACHE_ALIGN;
size_t align = 1 << 10; /* L2 pagetable alignement */
struct device_node *np;
+ int ret;
np = of_find_matching_node(NULL, omap_iommu_of_match);
if (!np)
return -ENOMEM;
iopte_cachep = p;
- bus_set_iommu(&platform_bus_type, &omap_iommu_ops);
-
omap_iommu_debugfs_init();
- return platform_driver_register(&omap_iommu_driver);
+ ret = platform_driver_register(&omap_iommu_driver);
+ if (ret) {
+ pr_err("%s: failed to register driver\n", __func__);
+ goto fail_driver;
+ }
+
+ ret = bus_set_iommu(&platform_bus_type, &omap_iommu_ops);
+ if (ret)
+ goto fail_bus;
+
+ return 0;
+
+fail_bus:
+ platform_driver_unregister(&omap_iommu_driver);
+fail_driver:
+ kmem_cache_destroy(iopte_cachep);
+ return ret;
}
subsys_initcall(omap_iommu_init);
/* must be ready before omap3isp is probed */
#define _OMAP_IOMMU_H
#include <linux/bitops.h>
+#include <linux/iommu.h>
#define for_each_iotlb_cr(obj, n, __i, cr) \
for (__i = 0; \
u32 endian, elsz, mixed;
};
+/**
+ * struct omap_iommu_domain - omap iommu domain
+ * @pgtable: the page table
+ * @iommu_dev: an omap iommu device attached to this domain. only a single
+ * iommu device can be attached for now.
+ * @dev: Device using this domain.
+ * @lock: domain lock, should be taken when attaching/detaching
+ * @domain: generic domain handle used by iommu core code
+ */
+struct omap_iommu_domain {
+ u32 *pgtable;
+ struct omap_iommu *iommu_dev;
+ struct device *dev;
+ spinlock_t lock;
+ struct iommu_domain domain;
+};
+
struct omap_iommu {
const char *name;
void __iomem *regbase;
int has_bus_err_back;
u32 id;
+
+ struct iommu_device iommu;
+ struct iommu_group *group;
+};
+
+/**
+ * struct omap_iommu_arch_data - omap iommu private data
+ * @iommu_dev: handle of the iommu device
+ *
+ * This is an omap iommu private data object, which binds an iommu user
+ * to its iommu device. This object should be placed at the iommu user's
+ * dev_archdata so generic IOMMU API can be used without having to
+ * utilize omap-specific plumbing anymore.
+ */
+struct omap_iommu_arch_data {
+ struct omap_iommu *iommu_dev;
};
struct cr_regs {
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/dma-iommu.h>
+#include <linux/dma-mapping.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/io.h>
void __iomem **bases;
int num_mmu;
int irq;
+ struct iommu_device iommu;
struct list_head node; /* entry in rk_iommu_domain.iommus */
struct iommu_domain *domain; /* domain to which iommu is attached */
};
static int rk_iommu_add_device(struct device *dev)
{
struct iommu_group *group;
+ struct rk_iommu *iommu;
int ret;
if (!rk_iommu_is_dev_iommu_master(dev))
if (ret)
goto err_remove_device;
+ iommu = rk_iommu_from_dev(dev);
+ if (iommu)
+ iommu_device_link(&iommu->iommu, dev);
+
iommu_group_put(group);
return 0;
static void rk_iommu_remove_device(struct device *dev)
{
+ struct rk_iommu *iommu;
+
if (!rk_iommu_is_dev_iommu_master(dev))
return;
+ iommu = rk_iommu_from_dev(dev);
+ if (iommu)
+ iommu_device_unlink(&iommu->iommu, dev);
+
iommu_group_remove_device(dev);
}
struct rk_iommu *iommu;
struct resource *res;
int num_res = pdev->num_resources;
- int i;
+ int err, i;
iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
if (!iommu)
return -ENXIO;
}
- return 0;
+ err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev));
+ if (err)
+ return err;
+
+ iommu_device_set_ops(&iommu->iommu, &rk_iommu_ops);
+ err = iommu_device_register(&iommu->iommu);
+
+ return err;
}
static int rk_iommu_remove(struct platform_device *pdev)
{
+ struct rk_iommu *iommu = platform_get_drvdata(pdev);
+
+ if (iommu) {
+ iommu_device_sysfs_remove(&iommu->iommu);
+ iommu_device_unregister(&iommu->iommu);
+ }
+
return 0;
}
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
+#include <linux/dma-mapping.h>
#include <soc/tegra/ahb.h>
#include <soc/tegra/mc.h>
static int io[MAX_CARDS];
static int irq[MAX_CARDS];
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(io, "I/O base address(es)");
MODULE_PARM_DESC(irq, "IRQ number(s) (assigned)");
static int irq[MAX_CARDS];
static int cardnr[MAX_CARDS];
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param_array(cardnr, int, NULL, 0);
MODULE_PARM_DESC(io, "I/O base address(es)");
MODULE_PARM_DESC(irq, "IRQ number(s) (assigned)");
MODULE_LICENSE("GPL");
module_param_array(type, int, NULL, 0);
module_param_array(protocol, int, NULL, 0);
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
-module_param_array(mem, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
+module_param_hw_array(mem, int, iomem, NULL, 0);
module_param(id, charp, 0);
#ifdef IO0_IO1
-module_param_array(io0, int, NULL, 0);
-module_param_array(io1, int, NULL, 0);
+module_param_hw_array(io0, int, ioport, NULL, 0);
+module_param_hw_array(io1, int, ioport, NULL, 0);
#endif
#endif /* MODULE */
*/
static unsigned long vidmem; /* default = 0 - Video memory base address */
-module_param(vidmem, ulong, 0444);
+module_param_hw(vidmem, ulong, iomem, 0444);
MODULE_PARM_DESC(vidmem, "Default video memory base address");
/*
#include <linux/of_reserved_mem.h>
#include <linux/sched.h>
#include <linux/sizes.h>
+#include <linux/dma-mapping.h>
#include "mtk_vpu.h"
{
arm_iommu_release_mapping(isp->mapping);
isp->mapping = NULL;
- iommu_group_remove_device(isp->dev);
}
static int isp_attach_iommu(struct isp_device *isp)
{
struct dma_iommu_mapping *mapping;
- struct iommu_group *group;
int ret;
- /* Create a device group and add the device to it. */
- group = iommu_group_alloc();
- if (IS_ERR(group)) {
- dev_err(isp->dev, "failed to allocate IOMMU group\n");
- return PTR_ERR(group);
- }
-
- ret = iommu_group_add_device(group, isp->dev);
- iommu_group_put(group);
-
- if (ret < 0) {
- dev_err(isp->dev, "failed to add device to IPMMU group\n");
- return ret;
- }
-
/*
* Create the ARM mapping, used by the ARM DMA mapping core to allocate
* VAs. This will allocate a corresponding IOMMU domain.
#include <linux/clk-provider.h>
#include <linux/device.h>
#include <linux/io.h>
-#include <linux/iommu.h>
#include <linux/platform_device.h>
#include <linux/wait.h>
module_param(type, int, 0444);
MODULE_PARM_DESC(type, "Hardware type (0 = home-brew, 1 = IRdeo, 2 = IRdeo Remote, 3 = AnimaX, 4 = IgorPlug");
-module_param(io, int, 0444);
+module_param_hw(io, int, ioport, 0444);
MODULE_PARM_DESC(io, "I/O address base (0x3f8 or 0x2f8)");
/* some architectures (e.g. intel xscale) have memory mapped registers */
-module_param(iommap, ulong, 0444);
+module_param_hw(iommap, ulong, other, 0444);
MODULE_PARM_DESC(iommap, "physical base for memory mapped I/O (0 = no memory mapped io)");
/*
* on 32bit word boundaries.
* See linux-kernel/drivers/tty/serial/8250/8250.c serial_in()/out()
*/
-module_param(ioshift, int, 0444);
+module_param_hw(ioshift, int, other, 0444);
MODULE_PARM_DESC(ioshift, "shift I/O register offset (0 = no shift)");
-module_param(irq, int, 0444);
+module_param_hw(irq, int, irq, 0444);
MODULE_PARM_DESC(irq, "Interrupt (4 or 3)");
-module_param(share_irq, bool, 0444);
+module_param_hw(share_irq, bool, other, 0444);
MODULE_PARM_DESC(share_irq, "Share interrupts (0 = off, 1 = on)");
module_param(sense, int, 0444);
config FSL_IFC
bool
- depends on FSL_SOC || ARCH_LAYERSCAPE
+ depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
config JZ4780_NEMC
bool "Ingenic JZ4780 SoC NEMC driver"
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jiri Kosina");
-module_param(irq, uint, 0444);
+module_param_hw(irq, uint, irq, 0444);
MODULE_PARM_DESC(irq, "The IRQ to register for");
MODULE_DESCRIPTION("Dummy IRQ handler driver");
static struct virtqueue *vop_find_vq(struct virtio_device *dev,
unsigned index,
void (*callback)(struct virtqueue *vq),
- const char *name)
+ const char *name, bool ctx)
{
struct _vop_vdev *vdev = to_vopvdev(dev);
struct vop_device *vpdev = vdev->vpdev;
le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN,
dev,
false,
+ ctx,
(void __force *)va, vop_notify, callback, name);
if (!vq) {
err = -ENOMEM;
static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
- const char * const names[], struct irq_affinity *desc)
+ const char * const names[], const bool *ctx,
+ struct irq_affinity *desc)
{
struct _vop_vdev *vdev = to_vopvdev(dev);
struct vop_device *vpdev = vdev->vpdev;
for (i = 0; i < nvqs; ++i) {
dev_dbg(_vop_dev(vdev), "%s: %d: %s\n",
__func__, i, names[i]);
- vqs[i] = vop_find_vq(dev, i, callbacks[i], names[i]);
+ vqs[i] = vop_find_vq(dev, i, callbacks[i], names[i],
+ ctx ? ctx[i] : false);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
goto error;
module_init(wbsd_drv_init);
module_exit(wbsd_drv_exit);
#ifdef CONFIG_PNP
-module_param_named(nopnp, param_nopnp, uint, 0444);
+module_param_hw_named(nopnp, param_nopnp, uint, other, 0444);
#endif
-module_param_named(io, param_io, uint, 0444);
-module_param_named(irq, param_irq, uint, 0444);
-module_param_named(dma, param_dma, int, 0444);
+module_param_hw_named(io, param_io, uint, ioport, 0444);
+module_param_hw_named(irq, param_irq, uint, irq, 0444);
+module_param_hw_named(dma, param_dma, int, dma, 0444);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pierre Ossman <pierre@ossman.eu>");
* it should report a size of 8KBytes (0x0020*256).
*/
cfi->cfiq->EraseRegionInfo[0] = 0x002003ff;
- pr_warning("%s: Bad 38VF640x CFI data; adjusting sector size from 64 to 8KiB\n", mtd->name);
+ pr_warn("%s: Bad 38VF640x CFI data; adjusting sector size from 64 to 8KiB\n",
+ mtd->name);
}
static void fixup_s29gl064n_sectors(struct mtd_info *mtd)
if ((cfi->cfiq->EraseRegionInfo[0] & 0xffff) == 0x003f) {
cfi->cfiq->EraseRegionInfo[0] |= 0x0040;
- pr_warning("%s: Bad S29GL064N CFI data; adjust from 64 to 128 sectors\n", mtd->name);
+ pr_warn("%s: Bad S29GL064N CFI data; adjust from 64 to 128 sectors\n",
+ mtd->name);
}
}
if ((cfi->cfiq->EraseRegionInfo[1] & 0xffff) == 0x007e) {
cfi->cfiq->EraseRegionInfo[1] &= ~0x0040;
- pr_warning("%s: Bad S29GL032N CFI data; adjust from 127 to 63 sectors\n", mtd->name);
+ pr_warn("%s: Bad S29GL032N CFI data; adjust from 127 to 63 sectors\n",
+ mtd->name);
}
}
* which is not permitted by CFI.
*/
cfi->cfiq->EraseRegionInfo[0] = 0x020001ff;
- pr_warning("%s: Bad S29NS512P CFI data; adjust to 512 sectors\n", mtd->name);
+ pr_warn("%s: Bad S29NS512P CFI data; adjust to 512 sectors\n",
+ mtd->name);
}
/* Used to fix CFI-Tables of chips without Extended Query Tables */
obj-$(CONFIG_MTD_TSUNAMI) += tsunami_flash.o
obj-$(CONFIG_MTD_PXA2XX) += pxa2xx-flash.o
obj-$(CONFIG_MTD_PHYSMAP) += physmap.o
-ifdef CONFIG_MTD_PHYSMAP_OF_VERSATILE
-physmap_of-objs += physmap_of_versatile.o
-endif
-ifdef CONFIG_MTD_PHYSMAP_OF_GEMINI
-physmap_of-objs += physmap_of_gemini.o
-endif
+physmap_of-objs-y += physmap_of_core.o
+physmap_of-objs-$(CONFIG_MTD_PHYSMAP_OF_VERSATILE) += physmap_of_versatile.o
+physmap_of-objs-$(CONFIG_MTD_PHYSMAP_OF_GEMINI) += physmap_of_gemini.o
+physmap_of-objs := $(physmap_of-objs-y)
obj-$(CONFIG_MTD_PHYSMAP_OF) += physmap_of.o
obj-$(CONFIG_MTD_PISMO) += pismo.o
obj-$(CONFIG_MTD_PMC_MSP_EVM) += pmcmsp-flash.o
static const char * const *of_get_probes(struct device_node *dp)
{
- const char *cp;
- int cplen;
- unsigned int l;
- unsigned int count;
const char **res;
+ int count;
- cp = of_get_property(dp, "linux,part-probe", &cplen);
- if (cp == NULL)
+ count = of_property_count_strings(dp, "linux,part-probe");
+ if (count < 0)
return part_probe_types_def;
- count = 0;
- for (l = 0; l != cplen; l++)
- if (cp[l] == 0)
- count++;
-
- res = kzalloc((count + 1)*sizeof(*res), GFP_KERNEL);
+ res = kzalloc((count + 1) * sizeof(*res), GFP_KERNEL);
if (!res)
return NULL;
- count = 0;
- while (cplen > 0) {
- res[count] = cp;
- l = strlen(cp) + 1;
- cp += l;
- cplen -= l;
- count++;
- }
+
+ count = of_property_read_string_array(dp, "linux,part-probe", res,
+ count);
+ if (count < 0)
+ return NULL;
+
return res;
}
if (root->rb_node) {
count[i] = d->trees[i].count;
- min[i] = rb_entry(rb_first(root), struct swap_eb,
- rb)->erase_count;
- max[i] = rb_entry(rb_last(root), struct swap_eb,
- rb)->erase_count;
+ min[i] = MTDSWAP_ECNT_MIN(root);
+ max[i] = MTDSWAP_ECNT_MAX(root);
} else
count[i] = 0;
}
menuconfig MTD_NAND
tristate "NAND Device Support"
depends on MTD
- select MTD_NAND_IDS
select MTD_NAND_ECC
help
This enables support for accessing all type of NAND flash
Enable the driver for NAND flash on platforms using a Denali NAND
controller as a DT device.
-config MTD_NAND_DENALI_SCRATCH_REG_ADDR
- hex "Denali NAND size scratch register address"
- default "0xFF108018"
- depends on MTD_NAND_DENALI_PCI
- help
- Some platforms place the NAND chip size in a scratch register
- because (some versions of) the driver aren't able to automatically
- determine the size of certain chips. Set the address of the
- scratch register here to enable this feature. On Intel Moorestown
- boards, the scratch register is at 0xFF108018.
-
config MTD_NAND_GPIO
tristate "GPIO assisted NAND Flash driver"
depends on GPIOLIB || COMPILE_TEST
config MTD_NAND_OMAP_BCH_BUILD
def_tristate MTD_NAND_OMAP2 && MTD_NAND_OMAP_BCH
-config MTD_NAND_IDS
- tristate
-
config MTD_NAND_RICOH
tristate "Ricoh xD card reader"
default n
If you say "m", the module will be called cs553x_nand.
config MTD_NAND_ATMEL
- tristate "Support for NAND Flash / SmartMedia on AT91 and AVR32"
- depends on ARCH_AT91 || AVR32
+ tristate "Support for NAND Flash / SmartMedia on AT91"
+ depends on ARCH_AT91
help
Enables support for NAND Flash / Smart Media Card interface
- on Atmel AT91 and AVR32 processors.
+ on Atmel AT91 processors.
config MTD_NAND_PXA3xx
tristate "NAND support on PXA3xx and Armada 370/XP"
config MTD_NAND_FSL_IFC
tristate "NAND support for Freescale IFC controller"
- depends on FSL_SOC || ARCH_LAYERSCAPE
+ depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
select FSL_IFC
select MEMORY
help
obj-$(CONFIG_MTD_NAND) += nand.o
obj-$(CONFIG_MTD_NAND_ECC) += nand_ecc.o
obj-$(CONFIG_MTD_NAND_BCH) += nand_bch.o
-obj-$(CONFIG_MTD_NAND_IDS) += nand_ids.o
obj-$(CONFIG_MTD_SM_COMMON) += sm_common.o
obj-$(CONFIG_MTD_NAND_CAFE) += cafe_nand.o
obj-$(CONFIG_MTD_NAND_NANDSIM) += nandsim.o
obj-$(CONFIG_MTD_NAND_CS553X) += cs553x_nand.o
obj-$(CONFIG_MTD_NAND_NDFC) += ndfc.o
-obj-$(CONFIG_MTD_NAND_ATMEL) += atmel_nand.o
+obj-$(CONFIG_MTD_NAND_ATMEL) += atmel/
obj-$(CONFIG_MTD_NAND_GPIO) += gpio.o
omap2_nand-objs := omap2.o
obj-$(CONFIG_MTD_NAND_OMAP2) += omap2_nand.o
obj-$(CONFIG_MTD_NAND_QCOM) += qcom_nandc.o
obj-$(CONFIG_MTD_NAND_MTK) += mtk_nand.o mtk_ecc.o
-nand-objs := nand_base.o nand_bbt.o nand_timings.o
+nand-objs := nand_base.o nand_bbt.o nand_timings.o nand_ids.o
+nand-objs += nand_amd.o
+nand-objs += nand_hynix.o
+nand-objs += nand_macronix.o
+nand-objs += nand_micron.o
+nand-objs += nand_samsung.o
+nand-objs += nand_toshiba.o
--- /dev/null
+obj-$(CONFIG_MTD_NAND_ATMEL) += atmel-nand-controller.o atmel-pmecc.o
+
+atmel-nand-controller-objs := nand-controller.o
+atmel-pmecc-objs := pmecc.o
--- /dev/null
+/*
+ * Copyright 2017 ATMEL
+ * Copyright 2017 Free Electrons
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * Derived from the atmel_nand.c driver which contained the following
+ * copyrights:
+ *
+ * Copyright 2003 Rick Bronson
+ *
+ * Derived from drivers/mtd/nand/autcpu12.c
+ * Copyright 2001 Thomas Gleixner (gleixner@autronix.de)
+ *
+ * Derived from drivers/mtd/spia.c
+ * Copyright 2000 Steven J. Hill (sjhill@cotw.com)
+ *
+ *
+ * Add Hardware ECC support for AT91SAM9260 / AT91SAM9263
+ * Richard Genoud (richard.genoud@gmail.com), Adeneo Copyright 2007
+ *
+ * Derived from Das U-Boot source code
+ * (u-boot-1.1.5/board/atmel/at91sam9263ek/nand.c)
+ * Copyright 2006 ATMEL Rousset, Lacressonniere Nicolas
+ *
+ * Add Programmable Multibit ECC support for various AT91 SoC
+ * Copyright 2012 ATMEL, Hong Xu
+ *
+ * Add Nand Flash Controller support for SAMA5 SoC
+ * Copyright 2013 ATMEL, Josh Wu (josh.wu@atmel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * A few words about the naming convention in this file. This convention
+ * applies to structure and function names.
+ *
+ * Prefixes:
+ *
+ * - atmel_nand_: all generic structures/functions
+ * - atmel_smc_nand_: all structures/functions specific to the SMC interface
+ * (at91sam9 and avr32 SoCs)
+ * - atmel_hsmc_nand_: all structures/functions specific to the HSMC interface
+ * (sama5 SoCs and later)
+ * - atmel_nfc_: all structures/functions used to manipulate the NFC sub-block
+ * that is available in the HSMC block
+ * - <soc>_nand_: all SoC specific structures/functions
+ */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/genalloc.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mfd/syscon/atmel-matrix.h>
+#include <linux/module.h>
+#include <linux/mtd/nand.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/iopoll.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/atmel.h>
+#include <linux/regmap.h>
+
+#include "pmecc.h"
+
+#define ATMEL_HSMC_NFC_CFG 0x0
+#define ATMEL_HSMC_NFC_CFG_SPARESIZE(x) (((x) / 4) << 24)
+#define ATMEL_HSMC_NFC_CFG_SPARESIZE_MASK GENMASK(30, 24)
+#define ATMEL_HSMC_NFC_CFG_DTO(cyc, mul) (((cyc) << 16) | ((mul) << 20))
+#define ATMEL_HSMC_NFC_CFG_DTO_MAX GENMASK(22, 16)
+#define ATMEL_HSMC_NFC_CFG_RBEDGE BIT(13)
+#define ATMEL_HSMC_NFC_CFG_FALLING_EDGE BIT(12)
+#define ATMEL_HSMC_NFC_CFG_RSPARE BIT(9)
+#define ATMEL_HSMC_NFC_CFG_WSPARE BIT(8)
+#define ATMEL_HSMC_NFC_CFG_PAGESIZE_MASK GENMASK(2, 0)
+#define ATMEL_HSMC_NFC_CFG_PAGESIZE(x) (fls((x) / 512) - 1)
+
+#define ATMEL_HSMC_NFC_CTRL 0x4
+#define ATMEL_HSMC_NFC_CTRL_EN BIT(0)
+#define ATMEL_HSMC_NFC_CTRL_DIS BIT(1)
+
+#define ATMEL_HSMC_NFC_SR 0x8
+#define ATMEL_HSMC_NFC_IER 0xc
+#define ATMEL_HSMC_NFC_IDR 0x10
+#define ATMEL_HSMC_NFC_IMR 0x14
+#define ATMEL_HSMC_NFC_SR_ENABLED BIT(1)
+#define ATMEL_HSMC_NFC_SR_RB_RISE BIT(4)
+#define ATMEL_HSMC_NFC_SR_RB_FALL BIT(5)
+#define ATMEL_HSMC_NFC_SR_BUSY BIT(8)
+#define ATMEL_HSMC_NFC_SR_WR BIT(11)
+#define ATMEL_HSMC_NFC_SR_CSID GENMASK(14, 12)
+#define ATMEL_HSMC_NFC_SR_XFRDONE BIT(16)
+#define ATMEL_HSMC_NFC_SR_CMDDONE BIT(17)
+#define ATMEL_HSMC_NFC_SR_DTOE BIT(20)
+#define ATMEL_HSMC_NFC_SR_UNDEF BIT(21)
+#define ATMEL_HSMC_NFC_SR_AWB BIT(22)
+#define ATMEL_HSMC_NFC_SR_NFCASE BIT(23)
+#define ATMEL_HSMC_NFC_SR_ERRORS (ATMEL_HSMC_NFC_SR_DTOE | \
+ ATMEL_HSMC_NFC_SR_UNDEF | \
+ ATMEL_HSMC_NFC_SR_AWB | \
+ ATMEL_HSMC_NFC_SR_NFCASE)
+#define ATMEL_HSMC_NFC_SR_RBEDGE(x) BIT((x) + 24)
+
+#define ATMEL_HSMC_NFC_ADDR 0x18
+#define ATMEL_HSMC_NFC_BANK 0x1c
+
+#define ATMEL_NFC_MAX_RB_ID 7
+
+#define ATMEL_NFC_SRAM_SIZE 0x2400
+
+#define ATMEL_NFC_CMD(pos, cmd) ((cmd) << (((pos) * 8) + 2))
+#define ATMEL_NFC_VCMD2 BIT(18)
+#define ATMEL_NFC_ACYCLE(naddrs) ((naddrs) << 19)
+#define ATMEL_NFC_CSID(cs) ((cs) << 22)
+#define ATMEL_NFC_DATAEN BIT(25)
+#define ATMEL_NFC_NFCWR BIT(26)
+
+#define ATMEL_NFC_MAX_ADDR_CYCLES 5
+
+#define ATMEL_NAND_ALE_OFFSET BIT(21)
+#define ATMEL_NAND_CLE_OFFSET BIT(22)
+
+#define DEFAULT_TIMEOUT_MS 1000
+#define MIN_DMA_LEN 128
+
+enum atmel_nand_rb_type {
+ ATMEL_NAND_NO_RB,
+ ATMEL_NAND_NATIVE_RB,
+ ATMEL_NAND_GPIO_RB,
+};
+
+struct atmel_nand_rb {
+ enum atmel_nand_rb_type type;
+ union {
+ struct gpio_desc *gpio;
+ int id;
+ };
+};
+
+struct atmel_nand_cs {
+ int id;
+ struct atmel_nand_rb rb;
+ struct gpio_desc *csgpio;
+ struct {
+ void __iomem *virt;
+ dma_addr_t dma;
+ } io;
+};
+
+struct atmel_nand {
+ struct list_head node;
+ struct device *dev;
+ struct nand_chip base;
+ struct atmel_nand_cs *activecs;
+ struct atmel_pmecc_user *pmecc;
+ struct gpio_desc *cdgpio;
+ int numcs;
+ struct atmel_nand_cs cs[];
+};
+
+static inline struct atmel_nand *to_atmel_nand(struct nand_chip *chip)
+{
+ return container_of(chip, struct atmel_nand, base);
+}
+
+enum atmel_nfc_data_xfer {
+ ATMEL_NFC_NO_DATA,
+ ATMEL_NFC_READ_DATA,
+ ATMEL_NFC_WRITE_DATA,
+};
+
+struct atmel_nfc_op {
+ u8 cs;
+ u8 ncmds;
+ u8 cmds[2];
+ u8 naddrs;
+ u8 addrs[5];
+ enum atmel_nfc_data_xfer data;
+ u32 wait;
+ u32 errors;
+};
+
+struct atmel_nand_controller;
+struct atmel_nand_controller_caps;
+
+struct atmel_nand_controller_ops {
+ int (*probe)(struct platform_device *pdev,
+ const struct atmel_nand_controller_caps *caps);
+ int (*remove)(struct atmel_nand_controller *nc);
+ void (*nand_init)(struct atmel_nand_controller *nc,
+ struct atmel_nand *nand);
+ int (*ecc_init)(struct atmel_nand *nand);
+};
+
+struct atmel_nand_controller_caps {
+ bool has_dma;
+ bool legacy_of_bindings;
+ u32 ale_offs;
+ u32 cle_offs;
+ const struct atmel_nand_controller_ops *ops;
+};
+
+struct atmel_nand_controller {
+ struct nand_hw_control base;
+ const struct atmel_nand_controller_caps *caps;
+ struct device *dev;
+ struct regmap *smc;
+ struct dma_chan *dmac;
+ struct atmel_pmecc *pmecc;
+ struct list_head chips;
+ struct clk *mck;
+};
+
+static inline struct atmel_nand_controller *
+to_nand_controller(struct nand_hw_control *ctl)
+{
+ return container_of(ctl, struct atmel_nand_controller, base);
+}
+
+struct atmel_smc_nand_controller {
+ struct atmel_nand_controller base;
+ struct regmap *matrix;
+ unsigned int ebi_csa_offs;
+};
+
+static inline struct atmel_smc_nand_controller *
+to_smc_nand_controller(struct nand_hw_control *ctl)
+{
+ return container_of(to_nand_controller(ctl),
+ struct atmel_smc_nand_controller, base);
+}
+
+struct atmel_hsmc_nand_controller {
+ struct atmel_nand_controller base;
+ struct {
+ struct gen_pool *pool;
+ void __iomem *virt;
+ dma_addr_t dma;
+ } sram;
+ struct regmap *io;
+ struct atmel_nfc_op op;
+ struct completion complete;
+ int irq;
+
+ /* Only used when instantiating from legacy DT bindings. */
+ struct clk *clk;
+};
+
+static inline struct atmel_hsmc_nand_controller *
+to_hsmc_nand_controller(struct nand_hw_control *ctl)
+{
+ return container_of(to_nand_controller(ctl),
+ struct atmel_hsmc_nand_controller, base);
+}
+
+static bool atmel_nfc_op_done(struct atmel_nfc_op *op, u32 status)
+{
+ op->errors |= status & ATMEL_HSMC_NFC_SR_ERRORS;
+ op->wait ^= status & op->wait;
+
+ return !op->wait || op->errors;
+}
+
+static irqreturn_t atmel_nfc_interrupt(int irq, void *data)
+{
+ struct atmel_hsmc_nand_controller *nc = data;
+ u32 sr, rcvd;
+ bool done;
+
+ regmap_read(nc->base.smc, ATMEL_HSMC_NFC_SR, &sr);
+
+ rcvd = sr & (nc->op.wait | ATMEL_HSMC_NFC_SR_ERRORS);
+ done = atmel_nfc_op_done(&nc->op, sr);
+
+ if (rcvd)
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_IDR, rcvd);
+
+ if (done)
+ complete(&nc->complete);
+
+ return rcvd ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static int atmel_nfc_wait(struct atmel_hsmc_nand_controller *nc, bool poll,
+ unsigned int timeout_ms)
+{
+ int ret;
+
+ if (!timeout_ms)
+ timeout_ms = DEFAULT_TIMEOUT_MS;
+
+ if (poll) {
+ u32 status;
+
+ ret = regmap_read_poll_timeout(nc->base.smc,
+ ATMEL_HSMC_NFC_SR, status,
+ atmel_nfc_op_done(&nc->op,
+ status),
+ 0, timeout_ms * 1000);
+ } else {
+ init_completion(&nc->complete);
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_IER,
+ nc->op.wait | ATMEL_HSMC_NFC_SR_ERRORS);
+ ret = wait_for_completion_timeout(&nc->complete,
+ msecs_to_jiffies(timeout_ms));
+ if (!ret)
+ ret = -ETIMEDOUT;
+ else
+ ret = 0;
+
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_IDR, 0xffffffff);
+ }
+
+ if (nc->op.errors & ATMEL_HSMC_NFC_SR_DTOE) {
+ dev_err(nc->base.dev, "Waiting NAND R/B Timeout\n");
+ ret = -ETIMEDOUT;
+ }
+
+ if (nc->op.errors & ATMEL_HSMC_NFC_SR_UNDEF) {
+ dev_err(nc->base.dev, "Access to an undefined area\n");
+ ret = -EIO;
+ }
+
+ if (nc->op.errors & ATMEL_HSMC_NFC_SR_AWB) {
+ dev_err(nc->base.dev, "Access while busy\n");
+ ret = -EIO;
+ }
+
+ if (nc->op.errors & ATMEL_HSMC_NFC_SR_NFCASE) {
+ dev_err(nc->base.dev, "Wrong access size\n");
+ ret = -EIO;
+ }
+
+ return ret;
+}
+
+static void atmel_nand_dma_transfer_finished(void *data)
+{
+ struct completion *finished = data;
+
+ complete(finished);
+}
+
+static int atmel_nand_dma_transfer(struct atmel_nand_controller *nc,
+ void *buf, dma_addr_t dev_dma, size_t len,
+ enum dma_data_direction dir)
+{
+ DECLARE_COMPLETION_ONSTACK(finished);
+ dma_addr_t src_dma, dst_dma, buf_dma;
+ struct dma_async_tx_descriptor *tx;
+ dma_cookie_t cookie;
+
+ buf_dma = dma_map_single(nc->dev, buf, len, dir);
+ if (dma_mapping_error(nc->dev, dev_dma)) {
+ dev_err(nc->dev,
+ "Failed to prepare a buffer for DMA access\n");
+ goto err;
+ }
+
+ if (dir == DMA_FROM_DEVICE) {
+ src_dma = dev_dma;
+ dst_dma = buf_dma;
+ } else {
+ src_dma = buf_dma;
+ dst_dma = dev_dma;
+ }
+
+ tx = dmaengine_prep_dma_memcpy(nc->dmac, dst_dma, src_dma, len,
+ DMA_CTRL_ACK | DMA_PREP_INTERRUPT);
+ if (!tx) {
+ dev_err(nc->dev, "Failed to prepare DMA memcpy\n");
+ goto err_unmap;
+ }
+
+ tx->callback = atmel_nand_dma_transfer_finished;
+ tx->callback_param = &finished;
+
+ cookie = dmaengine_submit(tx);
+ if (dma_submit_error(cookie)) {
+ dev_err(nc->dev, "Failed to do DMA tx_submit\n");
+ goto err_unmap;
+ }
+
+ dma_async_issue_pending(nc->dmac);
+ wait_for_completion(&finished);
+
+ return 0;
+
+err_unmap:
+ dma_unmap_single(nc->dev, buf_dma, len, dir);
+
+err:
+ dev_dbg(nc->dev, "Fall back to CPU I/O\n");
+
+ return -EIO;
+}
+
+static u8 atmel_nand_read_byte(struct mtd_info *mtd)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+
+ return ioread8(nand->activecs->io.virt);
+}
+
+static u16 atmel_nand_read_word(struct mtd_info *mtd)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+
+ return ioread16(nand->activecs->io.virt);
+}
+
+static void atmel_nand_write_byte(struct mtd_info *mtd, u8 byte)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+
+ if (chip->options & NAND_BUSWIDTH_16)
+ iowrite16(byte | (byte << 8), nand->activecs->io.virt);
+ else
+ iowrite8(byte, nand->activecs->io.virt);
+}
+
+static void atmel_nand_read_buf(struct mtd_info *mtd, u8 *buf, int len)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_nand_controller *nc;
+
+ nc = to_nand_controller(chip->controller);
+
+ /*
+ * If the controller supports DMA, the buffer address is DMA-able and
+ * len is long enough to make DMA transfers profitable, let's trigger
+ * a DMA transfer. If it fails, fallback to PIO mode.
+ */
+ if (nc->dmac && virt_addr_valid(buf) &&
+ len >= MIN_DMA_LEN &&
+ !atmel_nand_dma_transfer(nc, buf, nand->activecs->io.dma, len,
+ DMA_FROM_DEVICE))
+ return;
+
+ if (chip->options & NAND_BUSWIDTH_16)
+ ioread16_rep(nand->activecs->io.virt, buf, len / 2);
+ else
+ ioread8_rep(nand->activecs->io.virt, buf, len);
+}
+
+static void atmel_nand_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_nand_controller *nc;
+
+ nc = to_nand_controller(chip->controller);
+
+ /*
+ * If the controller supports DMA, the buffer address is DMA-able and
+ * len is long enough to make DMA transfers profitable, let's trigger
+ * a DMA transfer. If it fails, fallback to PIO mode.
+ */
+ if (nc->dmac && virt_addr_valid(buf) &&
+ len >= MIN_DMA_LEN &&
+ !atmel_nand_dma_transfer(nc, (void *)buf, nand->activecs->io.dma,
+ len, DMA_TO_DEVICE))
+ return;
+
+ if (chip->options & NAND_BUSWIDTH_16)
+ iowrite16_rep(nand->activecs->io.virt, buf, len / 2);
+ else
+ iowrite8_rep(nand->activecs->io.virt, buf, len);
+}
+
+static int atmel_nand_dev_ready(struct mtd_info *mtd)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+
+ return gpiod_get_value(nand->activecs->rb.gpio);
+}
+
+static void atmel_nand_select_chip(struct mtd_info *mtd, int cs)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+
+ if (cs < 0 || cs >= nand->numcs) {
+ nand->activecs = NULL;
+ chip->dev_ready = NULL;
+ return;
+ }
+
+ nand->activecs = &nand->cs[cs];
+
+ if (nand->activecs->rb.type == ATMEL_NAND_GPIO_RB)
+ chip->dev_ready = atmel_nand_dev_ready;
+}
+
+static int atmel_hsmc_nand_dev_ready(struct mtd_info *mtd)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_hsmc_nand_controller *nc;
+ u32 status;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ regmap_read(nc->base.smc, ATMEL_HSMC_NFC_SR, &status);
+
+ return status & ATMEL_HSMC_NFC_SR_RBEDGE(nand->activecs->rb.id);
+}
+
+static void atmel_hsmc_nand_select_chip(struct mtd_info *mtd, int cs)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_hsmc_nand_controller *nc;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ atmel_nand_select_chip(mtd, cs);
+
+ if (!nand->activecs) {
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_CTRL,
+ ATMEL_HSMC_NFC_CTRL_DIS);
+ return;
+ }
+
+ if (nand->activecs->rb.type == ATMEL_NAND_NATIVE_RB)
+ chip->dev_ready = atmel_hsmc_nand_dev_ready;
+
+ regmap_update_bits(nc->base.smc, ATMEL_HSMC_NFC_CFG,
+ ATMEL_HSMC_NFC_CFG_PAGESIZE_MASK |
+ ATMEL_HSMC_NFC_CFG_SPARESIZE_MASK |
+ ATMEL_HSMC_NFC_CFG_RSPARE |
+ ATMEL_HSMC_NFC_CFG_WSPARE,
+ ATMEL_HSMC_NFC_CFG_PAGESIZE(mtd->writesize) |
+ ATMEL_HSMC_NFC_CFG_SPARESIZE(mtd->oobsize) |
+ ATMEL_HSMC_NFC_CFG_RSPARE);
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_CTRL,
+ ATMEL_HSMC_NFC_CTRL_EN);
+}
+
+static int atmel_nfc_exec_op(struct atmel_hsmc_nand_controller *nc, bool poll)
+{
+ u8 *addrs = nc->op.addrs;
+ unsigned int op = 0;
+ u32 addr, val;
+ int i, ret;
+
+ nc->op.wait = ATMEL_HSMC_NFC_SR_CMDDONE;
+
+ for (i = 0; i < nc->op.ncmds; i++)
+ op |= ATMEL_NFC_CMD(i, nc->op.cmds[i]);
+
+ if (nc->op.naddrs == ATMEL_NFC_MAX_ADDR_CYCLES)
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_ADDR, *addrs++);
+
+ op |= ATMEL_NFC_CSID(nc->op.cs) |
+ ATMEL_NFC_ACYCLE(nc->op.naddrs);
+
+ if (nc->op.ncmds > 1)
+ op |= ATMEL_NFC_VCMD2;
+
+ addr = addrs[0] | (addrs[1] << 8) | (addrs[2] << 16) |
+ (addrs[3] << 24);
+
+ if (nc->op.data != ATMEL_NFC_NO_DATA) {
+ op |= ATMEL_NFC_DATAEN;
+ nc->op.wait |= ATMEL_HSMC_NFC_SR_XFRDONE;
+
+ if (nc->op.data == ATMEL_NFC_WRITE_DATA)
+ op |= ATMEL_NFC_NFCWR;
+ }
+
+ /* Clear all flags. */
+ regmap_read(nc->base.smc, ATMEL_HSMC_NFC_SR, &val);
+
+ /* Send the command. */
+ regmap_write(nc->io, op, addr);
+
+ ret = atmel_nfc_wait(nc, poll, 0);
+ if (ret)
+ dev_err(nc->base.dev,
+ "Failed to send NAND command (err = %d)!",
+ ret);
+
+ /* Reset the op state. */
+ memset(&nc->op, 0, sizeof(nc->op));
+
+ return ret;
+}
+
+static void atmel_hsmc_nand_cmd_ctrl(struct mtd_info *mtd, int dat,
+ unsigned int ctrl)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_hsmc_nand_controller *nc;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ if (ctrl & NAND_ALE) {
+ if (nc->op.naddrs == ATMEL_NFC_MAX_ADDR_CYCLES)
+ return;
+
+ nc->op.addrs[nc->op.naddrs++] = dat;
+ } else if (ctrl & NAND_CLE) {
+ if (nc->op.ncmds > 1)
+ return;
+
+ nc->op.cmds[nc->op.ncmds++] = dat;
+ }
+
+ if (dat == NAND_CMD_NONE) {
+ nc->op.cs = nand->activecs->id;
+ atmel_nfc_exec_op(nc, true);
+ }
+}
+
+static void atmel_nand_cmd_ctrl(struct mtd_info *mtd, int cmd,
+ unsigned int ctrl)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_nand_controller *nc;
+
+ nc = to_nand_controller(chip->controller);
+
+ if ((ctrl & NAND_CTRL_CHANGE) && nand->activecs->csgpio) {
+ if (ctrl & NAND_NCE)
+ gpiod_set_value(nand->activecs->csgpio, 0);
+ else
+ gpiod_set_value(nand->activecs->csgpio, 1);
+ }
+
+ if (ctrl & NAND_ALE)
+ writeb(cmd, nand->activecs->io.virt + nc->caps->ale_offs);
+ else if (ctrl & NAND_CLE)
+ writeb(cmd, nand->activecs->io.virt + nc->caps->cle_offs);
+}
+
+static void atmel_nfc_copy_to_sram(struct nand_chip *chip, const u8 *buf,
+ bool oob_required)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_hsmc_nand_controller *nc;
+ int ret = -EIO;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ if (nc->base.dmac)
+ ret = atmel_nand_dma_transfer(&nc->base, (void *)buf,
+ nc->sram.dma, mtd->writesize,
+ DMA_TO_DEVICE);
+
+ /* Falling back to CPU copy. */
+ if (ret)
+ memcpy_toio(nc->sram.virt, buf, mtd->writesize);
+
+ if (oob_required)
+ memcpy_toio(nc->sram.virt + mtd->writesize, chip->oob_poi,
+ mtd->oobsize);
+}
+
+static void atmel_nfc_copy_from_sram(struct nand_chip *chip, u8 *buf,
+ bool oob_required)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_hsmc_nand_controller *nc;
+ int ret = -EIO;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ if (nc->base.dmac)
+ ret = atmel_nand_dma_transfer(&nc->base, buf, nc->sram.dma,
+ mtd->writesize, DMA_FROM_DEVICE);
+
+ /* Falling back to CPU copy. */
+ if (ret)
+ memcpy_fromio(buf, nc->sram.virt, mtd->writesize);
+
+ if (oob_required)
+ memcpy_fromio(chip->oob_poi, nc->sram.virt + mtd->writesize,
+ mtd->oobsize);
+}
+
+static void atmel_nfc_set_op_addr(struct nand_chip *chip, int page, int column)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_hsmc_nand_controller *nc;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ if (column >= 0) {
+ nc->op.addrs[nc->op.naddrs++] = column;
+
+ /*
+ * 2 address cycles for the column offset on large page NANDs.
+ */
+ if (mtd->writesize > 512)
+ nc->op.addrs[nc->op.naddrs++] = column >> 8;
+ }
+
+ if (page >= 0) {
+ nc->op.addrs[nc->op.naddrs++] = page;
+ nc->op.addrs[nc->op.naddrs++] = page >> 8;
+
+ if ((mtd->writesize > 512 && chip->chipsize > SZ_128M) ||
+ (mtd->writesize <= 512 && chip->chipsize > SZ_32M))
+ nc->op.addrs[nc->op.naddrs++] = page >> 16;
+ }
+}
+
+static int atmel_nand_pmecc_enable(struct nand_chip *chip, int op, bool raw)
+{
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_nand_controller *nc;
+ int ret;
+
+ nc = to_nand_controller(chip->controller);
+
+ if (raw)
+ return 0;
+
+ ret = atmel_pmecc_enable(nand->pmecc, op);
+ if (ret)
+ dev_err(nc->dev,
+ "Failed to enable ECC engine (err = %d)\n", ret);
+
+ return ret;
+}
+
+static void atmel_nand_pmecc_disable(struct nand_chip *chip, bool raw)
+{
+ struct atmel_nand *nand = to_atmel_nand(chip);
+
+ if (!raw)
+ atmel_pmecc_disable(nand->pmecc);
+}
+
+static int atmel_nand_pmecc_generate_eccbytes(struct nand_chip *chip, bool raw)
+{
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand_controller *nc;
+ struct mtd_oob_region oobregion;
+ void *eccbuf;
+ int ret, i;
+
+ nc = to_nand_controller(chip->controller);
+
+ if (raw)
+ return 0;
+
+ ret = atmel_pmecc_wait_rdy(nand->pmecc);
+ if (ret) {
+ dev_err(nc->dev,
+ "Failed to transfer NAND page data (err = %d)\n",
+ ret);
+ return ret;
+ }
+
+ mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ eccbuf = chip->oob_poi + oobregion.offset;
+
+ for (i = 0; i < chip->ecc.steps; i++) {
+ atmel_pmecc_get_generated_eccbytes(nand->pmecc, i,
+ eccbuf);
+ eccbuf += chip->ecc.bytes;
+ }
+
+ return 0;
+}
+
+static int atmel_nand_pmecc_correct_data(struct nand_chip *chip, void *buf,
+ bool raw)
+{
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand_controller *nc;
+ struct mtd_oob_region oobregion;
+ int ret, i, max_bitflips = 0;
+ void *databuf, *eccbuf;
+
+ nc = to_nand_controller(chip->controller);
+
+ if (raw)
+ return 0;
+
+ ret = atmel_pmecc_wait_rdy(nand->pmecc);
+ if (ret) {
+ dev_err(nc->dev,
+ "Failed to read NAND page data (err = %d)\n",
+ ret);
+ return ret;
+ }
+
+ mtd_ooblayout_ecc(mtd, 0, &oobregion);
+ eccbuf = chip->oob_poi + oobregion.offset;
+ databuf = buf;
+
+ for (i = 0; i < chip->ecc.steps; i++) {
+ ret = atmel_pmecc_correct_sector(nand->pmecc, i, databuf,
+ eccbuf);
+ if (ret < 0 && !atmel_pmecc_correct_erased_chunks(nand->pmecc))
+ ret = nand_check_erased_ecc_chunk(databuf,
+ chip->ecc.size,
+ eccbuf,
+ chip->ecc.bytes,
+ NULL, 0,
+ chip->ecc.strength);
+
+ if (ret >= 0)
+ max_bitflips = max(ret, max_bitflips);
+ else
+ mtd->ecc_stats.failed++;
+
+ databuf += chip->ecc.size;
+ eccbuf += chip->ecc.bytes;
+ }
+
+ return max_bitflips;
+}
+
+static int atmel_nand_pmecc_write_pg(struct nand_chip *chip, const u8 *buf,
+ bool oob_required, int page, bool raw)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ int ret;
+
+ ret = atmel_nand_pmecc_enable(chip, NAND_ECC_WRITE, raw);
+ if (ret)
+ return ret;
+
+ atmel_nand_write_buf(mtd, buf, mtd->writesize);
+
+ ret = atmel_nand_pmecc_generate_eccbytes(chip, raw);
+ if (ret) {
+ atmel_pmecc_disable(nand->pmecc);
+ return ret;
+ }
+
+ atmel_nand_pmecc_disable(chip, raw);
+
+ atmel_nand_write_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+ return 0;
+}
+
+static int atmel_nand_pmecc_write_page(struct mtd_info *mtd,
+ struct nand_chip *chip, const u8 *buf,
+ int oob_required, int page)
+{
+ return atmel_nand_pmecc_write_pg(chip, buf, oob_required, page, false);
+}
+
+static int atmel_nand_pmecc_write_page_raw(struct mtd_info *mtd,
+ struct nand_chip *chip,
+ const u8 *buf, int oob_required,
+ int page)
+{
+ return atmel_nand_pmecc_write_pg(chip, buf, oob_required, page, true);
+}
+
+static int atmel_nand_pmecc_read_pg(struct nand_chip *chip, u8 *buf,
+ bool oob_required, int page, bool raw)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ int ret;
+
+ ret = atmel_nand_pmecc_enable(chip, NAND_ECC_READ, raw);
+ if (ret)
+ return ret;
+
+ atmel_nand_read_buf(mtd, buf, mtd->writesize);
+ atmel_nand_read_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+ ret = atmel_nand_pmecc_correct_data(chip, buf, raw);
+
+ atmel_nand_pmecc_disable(chip, raw);
+
+ return ret;
+}
+
+static int atmel_nand_pmecc_read_page(struct mtd_info *mtd,
+ struct nand_chip *chip, u8 *buf,
+ int oob_required, int page)
+{
+ return atmel_nand_pmecc_read_pg(chip, buf, oob_required, page, false);
+}
+
+static int atmel_nand_pmecc_read_page_raw(struct mtd_info *mtd,
+ struct nand_chip *chip, u8 *buf,
+ int oob_required, int page)
+{
+ return atmel_nand_pmecc_read_pg(chip, buf, oob_required, page, true);
+}
+
+static int atmel_hsmc_nand_pmecc_write_pg(struct nand_chip *chip,
+ const u8 *buf, bool oob_required,
+ int page, bool raw)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_hsmc_nand_controller *nc;
+ int ret;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ atmel_nfc_copy_to_sram(chip, buf, false);
+
+ nc->op.cmds[0] = NAND_CMD_SEQIN;
+ nc->op.ncmds = 1;
+ atmel_nfc_set_op_addr(chip, page, 0x0);
+ nc->op.cs = nand->activecs->id;
+ nc->op.data = ATMEL_NFC_WRITE_DATA;
+
+ ret = atmel_nand_pmecc_enable(chip, NAND_ECC_WRITE, raw);
+ if (ret)
+ return ret;
+
+ ret = atmel_nfc_exec_op(nc, false);
+ if (ret) {
+ atmel_nand_pmecc_disable(chip, raw);
+ dev_err(nc->base.dev,
+ "Failed to transfer NAND page data (err = %d)\n",
+ ret);
+ return ret;
+ }
+
+ ret = atmel_nand_pmecc_generate_eccbytes(chip, raw);
+
+ atmel_nand_pmecc_disable(chip, raw);
+
+ if (ret)
+ return ret;
+
+ atmel_nand_write_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+ nc->op.cmds[0] = NAND_CMD_PAGEPROG;
+ nc->op.ncmds = 1;
+ nc->op.cs = nand->activecs->id;
+ ret = atmel_nfc_exec_op(nc, false);
+ if (ret)
+ dev_err(nc->base.dev, "Failed to program NAND page (err = %d)\n",
+ ret);
+
+ return ret;
+}
+
+static int atmel_hsmc_nand_pmecc_write_page(struct mtd_info *mtd,
+ struct nand_chip *chip,
+ const u8 *buf, int oob_required,
+ int page)
+{
+ return atmel_hsmc_nand_pmecc_write_pg(chip, buf, oob_required, page,
+ false);
+}
+
+static int atmel_hsmc_nand_pmecc_write_page_raw(struct mtd_info *mtd,
+ struct nand_chip *chip,
+ const u8 *buf,
+ int oob_required, int page)
+{
+ return atmel_hsmc_nand_pmecc_write_pg(chip, buf, oob_required, page,
+ true);
+}
+
+static int atmel_hsmc_nand_pmecc_read_pg(struct nand_chip *chip, u8 *buf,
+ bool oob_required, int page,
+ bool raw)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_hsmc_nand_controller *nc;
+ int ret;
+
+ nc = to_hsmc_nand_controller(chip->controller);
+
+ /*
+ * Optimized read page accessors only work when the NAND R/B pin is
+ * connected to a native SoC R/B pin. If that's not the case, fallback
+ * to the non-optimized one.
+ */
+ if (nand->activecs->rb.type != ATMEL_NAND_NATIVE_RB) {
+ chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page);
+
+ return atmel_nand_pmecc_read_pg(chip, buf, oob_required, page,
+ raw);
+ }
+
+ nc->op.cmds[nc->op.ncmds++] = NAND_CMD_READ0;
+
+ if (mtd->writesize > 512)
+ nc->op.cmds[nc->op.ncmds++] = NAND_CMD_READSTART;
+
+ atmel_nfc_set_op_addr(chip, page, 0x0);
+ nc->op.cs = nand->activecs->id;
+ nc->op.data = ATMEL_NFC_READ_DATA;
+
+ ret = atmel_nand_pmecc_enable(chip, NAND_ECC_READ, raw);
+ if (ret)
+ return ret;
+
+ ret = atmel_nfc_exec_op(nc, false);
+ if (ret) {
+ atmel_nand_pmecc_disable(chip, raw);
+ dev_err(nc->base.dev,
+ "Failed to load NAND page data (err = %d)\n",
+ ret);
+ return ret;
+ }
+
+ atmel_nfc_copy_from_sram(chip, buf, true);
+
+ ret = atmel_nand_pmecc_correct_data(chip, buf, raw);
+
+ atmel_nand_pmecc_disable(chip, raw);
+
+ return ret;
+}
+
+static int atmel_hsmc_nand_pmecc_read_page(struct mtd_info *mtd,
+ struct nand_chip *chip, u8 *buf,
+ int oob_required, int page)
+{
+ return atmel_hsmc_nand_pmecc_read_pg(chip, buf, oob_required, page,
+ false);
+}
+
+static int atmel_hsmc_nand_pmecc_read_page_raw(struct mtd_info *mtd,
+ struct nand_chip *chip,
+ u8 *buf, int oob_required,
+ int page)
+{
+ return atmel_hsmc_nand_pmecc_read_pg(chip, buf, oob_required, page,
+ true);
+}
+
+static int atmel_nand_pmecc_init(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand *nand = to_atmel_nand(chip);
+ struct atmel_nand_controller *nc;
+ struct atmel_pmecc_user_req req;
+
+ nc = to_nand_controller(chip->controller);
+
+ if (!nc->pmecc) {
+ dev_err(nc->dev, "HW ECC not supported\n");
+ return -ENOTSUPP;
+ }
+
+ if (nc->caps->legacy_of_bindings) {
+ u32 val;
+
+ if (!of_property_read_u32(nc->dev->of_node, "atmel,pmecc-cap",
+ &val))
+ chip->ecc.strength = val;
+
+ if (!of_property_read_u32(nc->dev->of_node,
+ "atmel,pmecc-sector-size",
+ &val))
+ chip->ecc.size = val;
+ }
+
+ if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+ req.ecc.strength = ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH;
+ else if (chip->ecc.strength)
+ req.ecc.strength = chip->ecc.strength;
+ else if (chip->ecc_strength_ds)
+ req.ecc.strength = chip->ecc_strength_ds;
+ else
+ req.ecc.strength = ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH;
+
+ if (chip->ecc.size)
+ req.ecc.sectorsize = chip->ecc.size;
+ else if (chip->ecc_step_ds)
+ req.ecc.sectorsize = chip->ecc_step_ds;
+ else
+ req.ecc.sectorsize = ATMEL_PMECC_SECTOR_SIZE_AUTO;
+
+ req.pagesize = mtd->writesize;
+ req.oobsize = mtd->oobsize;
+
+ if (mtd->writesize <= 512) {
+ req.ecc.bytes = 4;
+ req.ecc.ooboffset = 0;
+ } else {
+ req.ecc.bytes = mtd->oobsize - 2;
+ req.ecc.ooboffset = ATMEL_PMECC_OOBOFFSET_AUTO;
+ }
+
+ nand->pmecc = atmel_pmecc_create_user(nc->pmecc, &req);
+ if (IS_ERR(nand->pmecc))
+ return PTR_ERR(nand->pmecc);
+
+ chip->ecc.algo = NAND_ECC_BCH;
+ chip->ecc.size = req.ecc.sectorsize;
+ chip->ecc.bytes = req.ecc.bytes / req.ecc.nsectors;
+ chip->ecc.strength = req.ecc.strength;
+
+ chip->options |= NAND_NO_SUBPAGE_WRITE;
+
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+
+ return 0;
+}
+
+static int atmel_nand_ecc_init(struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+ struct atmel_nand_controller *nc;
+ int ret;
+
+ nc = to_nand_controller(chip->controller);
+
+ switch (chip->ecc.mode) {
+ case NAND_ECC_NONE:
+ case NAND_ECC_SOFT:
+ /*
+ * Nothing to do, the core will initialize everything for us.
+ */
+ break;
+
+ case NAND_ECC_HW:
+ ret = atmel_nand_pmecc_init(chip);
+ if (ret)
+ return ret;
+
+ chip->ecc.read_page = atmel_nand_pmecc_read_page;
+ chip->ecc.write_page = atmel_nand_pmecc_write_page;
+ chip->ecc.read_page_raw = atmel_nand_pmecc_read_page_raw;
+ chip->ecc.write_page_raw = atmel_nand_pmecc_write_page_raw;
+ break;
+
+ default:
+ /* Other modes are not supported. */
+ dev_err(nc->dev, "Unsupported ECC mode: %d\n",
+ chip->ecc.mode);
+ return -ENOTSUPP;
+ }
+
+ return 0;
+}
+
+static int atmel_hsmc_nand_ecc_init(struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+ int ret;
+
+ ret = atmel_nand_ecc_init(nand);
+ if (ret)
+ return ret;
+
+ if (chip->ecc.mode != NAND_ECC_HW)
+ return 0;
+
+ /* Adjust the ECC operations for the HSMC IP. */
+ chip->ecc.read_page = atmel_hsmc_nand_pmecc_read_page;
+ chip->ecc.write_page = atmel_hsmc_nand_pmecc_write_page;
+ chip->ecc.read_page_raw = atmel_hsmc_nand_pmecc_read_page_raw;
+ chip->ecc.write_page_raw = atmel_hsmc_nand_pmecc_write_page_raw;
+ chip->ecc.options |= NAND_ECC_CUSTOM_PAGE_ACCESS;
+
+ return 0;
+}
+
+static void atmel_nand_init(struct atmel_nand_controller *nc,
+ struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+ struct mtd_info *mtd = nand_to_mtd(chip);
+
+ mtd->dev.parent = nc->dev;
+ nand->base.controller = &nc->base;
+
+ chip->cmd_ctrl = atmel_nand_cmd_ctrl;
+ chip->read_byte = atmel_nand_read_byte;
+ chip->read_word = atmel_nand_read_word;
+ chip->write_byte = atmel_nand_write_byte;
+ chip->read_buf = atmel_nand_read_buf;
+ chip->write_buf = atmel_nand_write_buf;
+ chip->select_chip = atmel_nand_select_chip;
+
+ /* Some NANDs require a longer delay than the default one (20us). */
+ chip->chip_delay = 40;
+
+ /*
+ * Use a bounce buffer when the buffer passed by the MTD user is not
+ * suitable for DMA.
+ */
+ if (nc->dmac)
+ chip->options |= NAND_USE_BOUNCE_BUFFER;
+
+ /* Default to HW ECC if pmecc is available. */
+ if (nc->pmecc)
+ chip->ecc.mode = NAND_ECC_HW;
+}
+
+static void atmel_smc_nand_init(struct atmel_nand_controller *nc,
+ struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+ struct atmel_smc_nand_controller *smc_nc;
+ int i;
+
+ atmel_nand_init(nc, nand);
+
+ smc_nc = to_smc_nand_controller(chip->controller);
+ if (!smc_nc->matrix)
+ return;
+
+ /* Attach the CS to the NAND Flash logic. */
+ for (i = 0; i < nand->numcs; i++)
+ regmap_update_bits(smc_nc->matrix, smc_nc->ebi_csa_offs,
+ BIT(nand->cs[i].id), BIT(nand->cs[i].id));
+}
+
+static void atmel_hsmc_nand_init(struct atmel_nand_controller *nc,
+ struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+
+ atmel_nand_init(nc, nand);
+
+ /* Overload some methods for the HSMC controller. */
+ chip->cmd_ctrl = atmel_hsmc_nand_cmd_ctrl;
+ chip->select_chip = atmel_hsmc_nand_select_chip;
+}
+
+static int atmel_nand_detect(struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand_controller *nc;
+ int ret;
+
+ nc = to_nand_controller(chip->controller);
+
+ ret = nand_scan_ident(mtd, nand->numcs, NULL);
+ if (ret)
+ dev_err(nc->dev, "nand_scan_ident() failed: %d\n", ret);
+
+ return ret;
+}
+
+static int atmel_nand_unregister(struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ int ret;
+
+ ret = mtd_device_unregister(mtd);
+ if (ret)
+ return ret;
+
+ nand_cleanup(chip);
+ list_del(&nand->node);
+
+ return 0;
+}
+
+static int atmel_nand_register(struct atmel_nand *nand)
+{
+ struct nand_chip *chip = &nand->base;
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ struct atmel_nand_controller *nc;
+ int ret;
+
+ nc = to_nand_controller(chip->controller);
+
+ if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
+ /*
+ * We keep the MTD name unchanged to avoid breaking platforms
+ * where the MTD cmdline parser is used and the bootloader
+ * has not been updated to use the new naming scheme.
+ */
+ mtd->name = "atmel_nand";
+ } else if (!mtd->name) {
+ /*
+ * If the new bindings are used and the bootloader has not been
+ * updated to pass a new mtdparts parameter on the cmdline, you
+ * should define the following property in your nand node:
+ *
+ * label = "atmel_nand";
+ *
+ * This way, mtd->name will be set by the core when
+ * nand_set_flash_node() is called.
+ */
+ mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
+ "%s:nand.%d", dev_name(nc->dev),
+ nand->cs[0].id);
+ if (!mtd->name) {
+ dev_err(nc->dev, "Failed to allocate mtd->name\n");
+ return -ENOMEM;
+ }
+ }
+
+ ret = nand_scan_tail(mtd);
+ if (ret) {
+ dev_err(nc->dev, "nand_scan_tail() failed: %d\n", ret);
+ return ret;
+ }
+
+ ret = mtd_device_register(mtd, NULL, 0);
+ if (ret) {
+ dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
+ nand_cleanup(chip);
+ return ret;
+ }
+
+ list_add_tail(&nand->node, &nc->chips);
+
+ return 0;
+}
+
+static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
+ struct device_node *np,
+ int reg_cells)
+{
+ struct atmel_nand *nand;
+ struct gpio_desc *gpio;
+ int numcs, ret, i;
+
+ numcs = of_property_count_elems_of_size(np, "reg",
+ reg_cells * sizeof(u32));
+ if (numcs < 1) {
+ dev_err(nc->dev, "Missing or invalid reg property\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ nand = devm_kzalloc(nc->dev,
+ sizeof(*nand) + (numcs * sizeof(*nand->cs)),
+ GFP_KERNEL);
+ if (!nand) {
+ dev_err(nc->dev, "Failed to allocate NAND object\n");
+ return ERR_PTR(-ENOMEM);
+ }
+
+ nand->numcs = numcs;
+
+ gpio = devm_fwnode_get_index_gpiod_from_child(nc->dev, "det", 0,
+ &np->fwnode, GPIOD_IN,
+ "nand-det");
+ if (IS_ERR(gpio) && PTR_ERR(gpio) != -ENOENT) {
+ dev_err(nc->dev,
+ "Failed to get detect gpio (err = %ld)\n",
+ PTR_ERR(gpio));
+ return ERR_CAST(gpio);
+ }
+
+ if (!IS_ERR(gpio))
+ nand->cdgpio = gpio;
+
+ for (i = 0; i < numcs; i++) {
+ struct resource res;
+ u32 val;
+
+ ret = of_address_to_resource(np, 0, &res);
+ if (ret) {
+ dev_err(nc->dev, "Invalid reg property (err = %d)\n",
+ ret);
+ return ERR_PTR(ret);
+ }
+
+ ret = of_property_read_u32_index(np, "reg", i * reg_cells,
+ &val);
+ if (ret) {
+ dev_err(nc->dev, "Invalid reg property (err = %d)\n",
+ ret);
+ return ERR_PTR(ret);
+ }
+
+ nand->cs[i].id = val;
+
+ nand->cs[i].io.dma = res.start;
+ nand->cs[i].io.virt = devm_ioremap_resource(nc->dev, &res);
+ if (IS_ERR(nand->cs[i].io.virt))
+ return ERR_CAST(nand->cs[i].io.virt);
+
+ if (!of_property_read_u32(np, "atmel,rb", &val)) {
+ if (val > ATMEL_NFC_MAX_RB_ID)
+ return ERR_PTR(-EINVAL);
+
+ nand->cs[i].rb.type = ATMEL_NAND_NATIVE_RB;
+ nand->cs[i].rb.id = val;
+ } else {
+ gpio = devm_fwnode_get_index_gpiod_from_child(nc->dev,
+ "rb", i, &np->fwnode,
+ GPIOD_IN, "nand-rb");
+ if (IS_ERR(gpio) && PTR_ERR(gpio) != -ENOENT) {
+ dev_err(nc->dev,
+ "Failed to get R/B gpio (err = %ld)\n",
+ PTR_ERR(gpio));
+ return ERR_CAST(gpio);
+ }
+
+ if (!IS_ERR(gpio)) {
+ nand->cs[i].rb.type = ATMEL_NAND_GPIO_RB;
+ nand->cs[i].rb.gpio = gpio;
+ }
+ }
+
+ gpio = devm_fwnode_get_index_gpiod_from_child(nc->dev, "cs",
+ i, &np->fwnode,
+ GPIOD_OUT_HIGH,
+ "nand-cs");
+ if (IS_ERR(gpio) && PTR_ERR(gpio) != -ENOENT) {
+ dev_err(nc->dev,
+ "Failed to get CS gpio (err = %ld)\n",
+ PTR_ERR(gpio));
+ return ERR_CAST(gpio);
+ }
+
+ if (!IS_ERR(gpio))
+ nand->cs[i].csgpio = gpio;
+ }
+
+ nand_set_flash_node(&nand->base, np);
+
+ return nand;
+}
+
+static int
+atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
+ struct atmel_nand *nand)
+{
+ int ret;
+
+ /* No card inserted, skip this NAND. */
+ if (nand->cdgpio && gpiod_get_value(nand->cdgpio)) {
+ dev_info(nc->dev, "No SmartMedia card inserted.\n");
+ return 0;
+ }
+
+ nc->caps->ops->nand_init(nc, nand);
+
+ ret = atmel_nand_detect(nand);
+ if (ret)
+ return ret;
+
+ ret = nc->caps->ops->ecc_init(nand);
+ if (ret)
+ return ret;
+
+ return atmel_nand_register(nand);
+}
+
+static int
+atmel_nand_controller_remove_nands(struct atmel_nand_controller *nc)
+{
+ struct atmel_nand *nand, *tmp;
+ int ret;
+
+ list_for_each_entry_safe(nand, tmp, &nc->chips, node) {
+ ret = atmel_nand_unregister(nand);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int
+atmel_nand_controller_legacy_add_nands(struct atmel_nand_controller *nc)
+{
+ struct device *dev = nc->dev;
+ struct platform_device *pdev = to_platform_device(dev);
+ struct atmel_nand *nand;
+ struct gpio_desc *gpio;
+ struct resource *res;
+
+ /*
+ * Legacy bindings only allow connecting a single NAND with a unique CS
+ * line to the controller.
+ */
+ nand = devm_kzalloc(nc->dev, sizeof(*nand) + sizeof(*nand->cs),
+ GFP_KERNEL);
+ if (!nand)
+ return -ENOMEM;
+
+ nand->numcs = 1;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ nand->cs[0].io.virt = devm_ioremap_resource(dev, res);
+ if (IS_ERR(nand->cs[0].io.virt))
+ return PTR_ERR(nand->cs[0].io.virt);
+
+ nand->cs[0].io.dma = res->start;
+
+ /*
+ * The old driver was hardcoding the CS id to 3 for all sama5
+ * controllers. Since this id is only meaningful for the sama5
+ * controller we can safely assign this id to 3 no matter the
+ * controller.
+ * If one wants to connect a NAND to a different CS line, he will
+ * have to use the new bindings.
+ */
+ nand->cs[0].id = 3;
+
+ /* R/B GPIO. */
+ gpio = devm_gpiod_get_index_optional(dev, NULL, 0, GPIOD_IN);
+ if (IS_ERR(gpio)) {
+ dev_err(dev, "Failed to get R/B gpio (err = %ld)\n",
+ PTR_ERR(gpio));
+ return PTR_ERR(gpio);
+ }
+
+ if (gpio) {
+ nand->cs[0].rb.type = ATMEL_NAND_GPIO_RB;
+ nand->cs[0].rb.gpio = gpio;
+ }
+
+ /* CS GPIO. */
+ gpio = devm_gpiod_get_index_optional(dev, NULL, 1, GPIOD_OUT_HIGH);
+ if (IS_ERR(gpio)) {
+ dev_err(dev, "Failed to get CS gpio (err = %ld)\n",
+ PTR_ERR(gpio));
+ return PTR_ERR(gpio);
+ }
+
+ nand->cs[0].csgpio = gpio;
+
+ /* Card detect GPIO. */
+ gpio = devm_gpiod_get_index_optional(nc->dev, NULL, 2, GPIOD_IN);
+ if (IS_ERR(gpio)) {
+ dev_err(dev,
+ "Failed to get detect gpio (err = %ld)\n",
+ PTR_ERR(gpio));
+ return PTR_ERR(gpio);
+ }
+
+ nand->cdgpio = gpio;
+
+ nand_set_flash_node(&nand->base, nc->dev->of_node);
+
+ return atmel_nand_controller_add_nand(nc, nand);
+}
+
+static int atmel_nand_controller_add_nands(struct atmel_nand_controller *nc)
+{
+ struct device_node *np, *nand_np;
+ struct device *dev = nc->dev;
+ int ret, reg_cells;
+ u32 val;
+
+ /* We do not retrieve the SMC syscon when parsing old DTs. */
+ if (nc->caps->legacy_of_bindings)
+ return atmel_nand_controller_legacy_add_nands(nc);
+
+ np = dev->of_node;
+
+ ret = of_property_read_u32(np, "#address-cells", &val);
+ if (ret) {
+ dev_err(dev, "missing #address-cells property\n");
+ return ret;
+ }
+
+ reg_cells = val;
+
+ ret = of_property_read_u32(np, "#size-cells", &val);
+ if (ret) {
+ dev_err(dev, "missing #address-cells property\n");
+ return ret;
+ }
+
+ reg_cells += val;
+
+ for_each_child_of_node(np, nand_np) {
+ struct atmel_nand *nand;
+
+ nand = atmel_nand_create(nc, nand_np, reg_cells);
+ if (IS_ERR(nand)) {
+ ret = PTR_ERR(nand);
+ goto err;
+ }
+
+ ret = atmel_nand_controller_add_nand(nc, nand);
+ if (ret)
+ goto err;
+ }
+
+ return 0;
+
+err:
+ atmel_nand_controller_remove_nands(nc);
+
+ return ret;
+}
+
+static void atmel_nand_controller_cleanup(struct atmel_nand_controller *nc)
+{
+ if (nc->dmac)
+ dma_release_channel(nc->dmac);
+
+ clk_put(nc->mck);
+}
+
+static const struct of_device_id atmel_matrix_of_ids[] = {
+ {
+ .compatible = "atmel,at91sam9260-matrix",
+ .data = (void *)AT91SAM9260_MATRIX_EBICSA,
+ },
+ {
+ .compatible = "atmel,at91sam9261-matrix",
+ .data = (void *)AT91SAM9261_MATRIX_EBICSA,
+ },
+ {
+ .compatible = "atmel,at91sam9263-matrix",
+ .data = (void *)AT91SAM9263_MATRIX_EBI0CSA,
+ },
+ {
+ .compatible = "atmel,at91sam9rl-matrix",
+ .data = (void *)AT91SAM9RL_MATRIX_EBICSA,
+ },
+ {
+ .compatible = "atmel,at91sam9g45-matrix",
+ .data = (void *)AT91SAM9G45_MATRIX_EBICSA,
+ },
+ {
+ .compatible = "atmel,at91sam9n12-matrix",
+ .data = (void *)AT91SAM9N12_MATRIX_EBICSA,
+ },
+ {
+ .compatible = "atmel,at91sam9x5-matrix",
+ .data = (void *)AT91SAM9X5_MATRIX_EBICSA,
+ },
+ { /* sentinel */ },
+};
+
+static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
+ struct platform_device *pdev,
+ const struct atmel_nand_controller_caps *caps)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ int ret;
+
+ nand_hw_control_init(&nc->base);
+ INIT_LIST_HEAD(&nc->chips);
+ nc->dev = dev;
+ nc->caps = caps;
+
+ platform_set_drvdata(pdev, nc);
+
+ nc->pmecc = devm_atmel_pmecc_get(dev);
+ if (IS_ERR(nc->pmecc)) {
+ ret = PTR_ERR(nc->pmecc);
+ if (ret != -EPROBE_DEFER)
+ dev_err(dev, "Could not get PMECC object (err = %d)\n",
+ ret);
+ return ret;
+ }
+
+ if (nc->caps->has_dma) {
+ dma_cap_mask_t mask;
+
+ dma_cap_zero(mask);
+ dma_cap_set(DMA_MEMCPY, mask);
+
+ nc->dmac = dma_request_channel(mask, NULL, NULL);
+ if (!nc->dmac)
+ dev_err(nc->dev, "Failed to request DMA channel\n");
+ }
+
+ /* We do not retrieve the SMC syscon when parsing old DTs. */
+ if (nc->caps->legacy_of_bindings)
+ return 0;
+
+ np = of_parse_phandle(dev->parent->of_node, "atmel,smc", 0);
+ if (!np) {
+ dev_err(dev, "Missing or invalid atmel,smc property\n");
+ return -EINVAL;
+ }
+
+ nc->smc = syscon_node_to_regmap(np);
+ of_node_put(np);
+ if (IS_ERR(nc->smc)) {
+ ret = PTR_ERR(nc->smc);
+ dev_err(dev, "Could not get SMC regmap (err = %d)\n", ret);
+ return ret;
+ }
+
+ return 0;
+}
+
+static int
+atmel_smc_nand_controller_init(struct atmel_smc_nand_controller *nc)
+{
+ struct device *dev = nc->base.dev;
+ const struct of_device_id *match;
+ struct device_node *np;
+ int ret;
+
+ /* We do not retrieve the matrix syscon when parsing old DTs. */
+ if (nc->base.caps->legacy_of_bindings)
+ return 0;
+
+ np = of_parse_phandle(dev->parent->of_node, "atmel,matrix", 0);
+ if (!np)
+ return 0;
+
+ match = of_match_node(atmel_matrix_of_ids, np);
+ if (!match) {
+ of_node_put(np);
+ return 0;
+ }
+
+ nc->matrix = syscon_node_to_regmap(np);
+ of_node_put(np);
+ if (IS_ERR(nc->matrix)) {
+ ret = PTR_ERR(nc->matrix);
+ dev_err(dev, "Could not get Matrix regmap (err = %d)\n", ret);
+ return ret;
+ }
+
+ nc->ebi_csa_offs = (unsigned int)match->data;
+
+ /*
+ * The at91sam9263 has 2 EBIs, if the NAND controller is under EBI1
+ * add 4 to ->ebi_csa_offs.
+ */
+ if (of_device_is_compatible(dev->parent->of_node,
+ "atmel,at91sam9263-ebi1"))
+ nc->ebi_csa_offs += 4;
+
+ return 0;
+}
+
+static int
+atmel_hsmc_nand_controller_legacy_init(struct atmel_hsmc_nand_controller *nc)
+{
+ struct regmap_config regmap_conf = {
+ .reg_bits = 32,
+ .val_bits = 32,
+ .reg_stride = 4,
+ };
+
+ struct device *dev = nc->base.dev;
+ struct device_node *nand_np, *nfc_np;
+ void __iomem *iomem;
+ struct resource res;
+ int ret;
+
+ nand_np = dev->of_node;
+ nfc_np = of_find_compatible_node(dev->of_node, NULL,
+ "atmel,sama5d3-nfc");
+
+ nc->clk = of_clk_get(nfc_np, 0);
+ if (IS_ERR(nc->clk)) {
+ ret = PTR_ERR(nc->clk);
+ dev_err(dev, "Failed to retrieve HSMC clock (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ ret = clk_prepare_enable(nc->clk);
+ if (ret) {
+ dev_err(dev, "Failed to enable the HSMC clock (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ nc->irq = of_irq_get(nand_np, 0);
+ if (nc->irq < 0) {
+ ret = nc->irq;
+ if (ret != -EPROBE_DEFER)
+ dev_err(dev, "Failed to get IRQ number (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ ret = of_address_to_resource(nfc_np, 0, &res);
+ if (ret) {
+ dev_err(dev, "Invalid or missing NFC IO resource (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ iomem = devm_ioremap_resource(dev, &res);
+ if (IS_ERR(iomem)) {
+ ret = PTR_ERR(iomem);
+ goto out;
+ }
+
+ regmap_conf.name = "nfc-io";
+ regmap_conf.max_register = resource_size(&res) - 4;
+ nc->io = devm_regmap_init_mmio(dev, iomem, ®map_conf);
+ if (IS_ERR(nc->io)) {
+ ret = PTR_ERR(nc->io);
+ dev_err(dev, "Could not create NFC IO regmap (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ ret = of_address_to_resource(nfc_np, 1, &res);
+ if (ret) {
+ dev_err(dev, "Invalid or missing HSMC resource (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ iomem = devm_ioremap_resource(dev, &res);
+ if (IS_ERR(iomem)) {
+ ret = PTR_ERR(iomem);
+ goto out;
+ }
+
+ regmap_conf.name = "smc";
+ regmap_conf.max_register = resource_size(&res) - 4;
+ nc->base.smc = devm_regmap_init_mmio(dev, iomem, ®map_conf);
+ if (IS_ERR(nc->base.smc)) {
+ ret = PTR_ERR(nc->base.smc);
+ dev_err(dev, "Could not create NFC IO regmap (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ ret = of_address_to_resource(nfc_np, 2, &res);
+ if (ret) {
+ dev_err(dev, "Invalid or missing SRAM resource (err = %d)\n",
+ ret);
+ goto out;
+ }
+
+ nc->sram.virt = devm_ioremap_resource(dev, &res);
+ if (IS_ERR(nc->sram.virt)) {
+ ret = PTR_ERR(nc->sram.virt);
+ goto out;
+ }
+
+ nc->sram.dma = res.start;
+
+out:
+ of_node_put(nfc_np);
+
+ return ret;
+}
+
+static int
+atmel_hsmc_nand_controller_init(struct atmel_hsmc_nand_controller *nc)
+{
+ struct device *dev = nc->base.dev;
+ struct device_node *np;
+ int ret;
+
+ np = of_parse_phandle(dev->parent->of_node, "atmel,smc", 0);
+ if (!np) {
+ dev_err(dev, "Missing or invalid atmel,smc property\n");
+ return -EINVAL;
+ }
+
+ nc->irq = of_irq_get(np, 0);
+ of_node_put(np);
+ if (nc->irq < 0) {
+ if (nc->irq != -EPROBE_DEFER)
+ dev_err(dev, "Failed to get IRQ number (err = %d)\n",
+ nc->irq);
+ return nc->irq;
+ }
+
+ np = of_parse_phandle(dev->of_node, "atmel,nfc-io", 0);
+ if (!np) {
+ dev_err(dev, "Missing or invalid atmel,nfc-io property\n");
+ return -EINVAL;
+ }
+
+ nc->io = syscon_node_to_regmap(np);
+ of_node_put(np);
+ if (IS_ERR(nc->io)) {
+ ret = PTR_ERR(nc->io);
+ dev_err(dev, "Could not get NFC IO regmap (err = %d)\n", ret);
+ return ret;
+ }
+
+ nc->sram.pool = of_gen_pool_get(nc->base.dev->of_node,
+ "atmel,nfc-sram", 0);
+ if (!nc->sram.pool) {
+ dev_err(nc->base.dev, "Missing SRAM\n");
+ return -ENOMEM;
+ }
+
+ nc->sram.virt = gen_pool_dma_alloc(nc->sram.pool,
+ ATMEL_NFC_SRAM_SIZE,
+ &nc->sram.dma);
+ if (!nc->sram.virt) {
+ dev_err(nc->base.dev,
+ "Could not allocate memory from the NFC SRAM pool\n");
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static int
+atmel_hsmc_nand_controller_remove(struct atmel_nand_controller *nc)
+{
+ struct atmel_hsmc_nand_controller *hsmc_nc;
+ int ret;
+
+ ret = atmel_nand_controller_remove_nands(nc);
+ if (ret)
+ return ret;
+
+ hsmc_nc = container_of(nc, struct atmel_hsmc_nand_controller, base);
+ if (hsmc_nc->sram.pool)
+ gen_pool_free(hsmc_nc->sram.pool,
+ (unsigned long)hsmc_nc->sram.virt,
+ ATMEL_NFC_SRAM_SIZE);
+
+ if (hsmc_nc->clk) {
+ clk_disable_unprepare(hsmc_nc->clk);
+ clk_put(hsmc_nc->clk);
+ }
+
+ atmel_nand_controller_cleanup(nc);
+
+ return 0;
+}
+
+static int atmel_hsmc_nand_controller_probe(struct platform_device *pdev,
+ const struct atmel_nand_controller_caps *caps)
+{
+ struct device *dev = &pdev->dev;
+ struct atmel_hsmc_nand_controller *nc;
+ int ret;
+
+ nc = devm_kzalloc(dev, sizeof(*nc), GFP_KERNEL);
+ if (!nc)
+ return -ENOMEM;
+
+ ret = atmel_nand_controller_init(&nc->base, pdev, caps);
+ if (ret)
+ return ret;
+
+ if (caps->legacy_of_bindings)
+ ret = atmel_hsmc_nand_controller_legacy_init(nc);
+ else
+ ret = atmel_hsmc_nand_controller_init(nc);
+
+ if (ret)
+ return ret;
+
+ /* Make sure all irqs are masked before registering our IRQ handler. */
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_IDR, 0xffffffff);
+ ret = devm_request_irq(dev, nc->irq, atmel_nfc_interrupt,
+ IRQF_SHARED, "nfc", nc);
+ if (ret) {
+ dev_err(dev,
+ "Could not get register NFC interrupt handler (err = %d)\n",
+ ret);
+ goto err;
+ }
+
+ /* Initial NFC configuration. */
+ regmap_write(nc->base.smc, ATMEL_HSMC_NFC_CFG,
+ ATMEL_HSMC_NFC_CFG_DTO_MAX);
+
+ ret = atmel_nand_controller_add_nands(&nc->base);
+ if (ret)
+ goto err;
+
+ return 0;
+
+err:
+ atmel_hsmc_nand_controller_remove(&nc->base);
+
+ return ret;
+}
+
+static const struct atmel_nand_controller_ops atmel_hsmc_nc_ops = {
+ .probe = atmel_hsmc_nand_controller_probe,
+ .remove = atmel_hsmc_nand_controller_remove,
+ .ecc_init = atmel_hsmc_nand_ecc_init,
+ .nand_init = atmel_hsmc_nand_init,
+};
+
+static const struct atmel_nand_controller_caps atmel_sama5_nc_caps = {
+ .has_dma = true,
+ .ale_offs = BIT(21),
+ .cle_offs = BIT(22),
+ .ops = &atmel_hsmc_nc_ops,
+};
+
+/* Only used to parse old bindings. */
+static const struct atmel_nand_controller_caps atmel_sama5_nand_caps = {
+ .has_dma = true,
+ .ale_offs = BIT(21),
+ .cle_offs = BIT(22),
+ .ops = &atmel_hsmc_nc_ops,
+ .legacy_of_bindings = true,
+};
+
+static int atmel_smc_nand_controller_probe(struct platform_device *pdev,
+ const struct atmel_nand_controller_caps *caps)
+{
+ struct device *dev = &pdev->dev;
+ struct atmel_smc_nand_controller *nc;
+ int ret;
+
+ nc = devm_kzalloc(dev, sizeof(*nc), GFP_KERNEL);
+ if (!nc)
+ return -ENOMEM;
+
+ ret = atmel_nand_controller_init(&nc->base, pdev, caps);
+ if (ret)
+ return ret;
+
+ ret = atmel_smc_nand_controller_init(nc);
+ if (ret)
+ return ret;
+
+ return atmel_nand_controller_add_nands(&nc->base);
+}
+
+static int
+atmel_smc_nand_controller_remove(struct atmel_nand_controller *nc)
+{
+ int ret;
+
+ ret = atmel_nand_controller_remove_nands(nc);
+ if (ret)
+ return ret;
+
+ atmel_nand_controller_cleanup(nc);
+
+ return 0;
+}
+
+static const struct atmel_nand_controller_ops atmel_smc_nc_ops = {
+ .probe = atmel_smc_nand_controller_probe,
+ .remove = atmel_smc_nand_controller_remove,
+ .ecc_init = atmel_nand_ecc_init,
+ .nand_init = atmel_smc_nand_init,
+};
+
+static const struct atmel_nand_controller_caps atmel_rm9200_nc_caps = {
+ .ale_offs = BIT(21),
+ .cle_offs = BIT(22),
+ .ops = &atmel_smc_nc_ops,
+};
+
+static const struct atmel_nand_controller_caps atmel_sam9261_nc_caps = {
+ .ale_offs = BIT(22),
+ .cle_offs = BIT(21),
+ .ops = &atmel_smc_nc_ops,
+};
+
+static const struct atmel_nand_controller_caps atmel_sam9g45_nc_caps = {
+ .has_dma = true,
+ .ale_offs = BIT(21),
+ .cle_offs = BIT(22),
+ .ops = &atmel_smc_nc_ops,
+};
+
+/* Only used to parse old bindings. */
+static const struct atmel_nand_controller_caps atmel_rm9200_nand_caps = {
+ .ale_offs = BIT(21),
+ .cle_offs = BIT(22),
+ .ops = &atmel_smc_nc_ops,
+ .legacy_of_bindings = true,
+};
+
+static const struct atmel_nand_controller_caps atmel_sam9261_nand_caps = {
+ .ale_offs = BIT(22),
+ .cle_offs = BIT(21),
+ .ops = &atmel_smc_nc_ops,
+ .legacy_of_bindings = true,
+};
+
+static const struct atmel_nand_controller_caps atmel_sam9g45_nand_caps = {
+ .has_dma = true,
+ .ale_offs = BIT(21),
+ .cle_offs = BIT(22),
+ .ops = &atmel_smc_nc_ops,
+ .legacy_of_bindings = true,
+};
+
+static const struct of_device_id atmel_nand_controller_of_ids[] = {
+ {
+ .compatible = "atmel,at91rm9200-nand-controller",
+ .data = &atmel_rm9200_nc_caps,
+ },
+ {
+ .compatible = "atmel,at91sam9260-nand-controller",
+ .data = &atmel_rm9200_nc_caps,
+ },
+ {
+ .compatible = "atmel,at91sam9261-nand-controller",
+ .data = &atmel_sam9261_nc_caps,
+ },
+ {
+ .compatible = "atmel,at91sam9g45-nand-controller",
+ .data = &atmel_sam9g45_nc_caps,
+ },
+ {
+ .compatible = "atmel,sama5d3-nand-controller",
+ .data = &atmel_sama5_nc_caps,
+ },
+ /* Support for old/deprecated bindings: */
+ {
+ .compatible = "atmel,at91rm9200-nand",
+ .data = &atmel_rm9200_nand_caps,
+ },
+ {
+ .compatible = "atmel,sama5d4-nand",
+ .data = &atmel_rm9200_nand_caps,
+ },
+ {
+ .compatible = "atmel,sama5d2-nand",
+ .data = &atmel_rm9200_nand_caps,
+ },
+ { /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, atmel_nand_controller_of_ids);
+
+static int atmel_nand_controller_probe(struct platform_device *pdev)
+{
+ const struct atmel_nand_controller_caps *caps;
+
+ if (pdev->id_entry)
+ caps = (void *)pdev->id_entry->driver_data;
+ else
+ caps = of_device_get_match_data(&pdev->dev);
+
+ if (!caps) {
+ dev_err(&pdev->dev, "Could not retrieve NFC caps\n");
+ return -EINVAL;
+ }
+
+ if (caps->legacy_of_bindings) {
+ u32 ale_offs = 21;
+
+ /*
+ * If we are parsing legacy DT props and the DT contains a
+ * valid NFC node, forward the request to the sama5 logic.
+ */
+ if (of_find_compatible_node(pdev->dev.of_node, NULL,
+ "atmel,sama5d3-nfc"))
+ caps = &atmel_sama5_nand_caps;
+
+ /*
+ * Even if the compatible says we are dealing with an
+ * at91rm9200 controller, the atmel,nand-has-dma specify that
+ * this controller supports DMA, which means we are in fact
+ * dealing with an at91sam9g45+ controller.
+ */
+ if (!caps->has_dma &&
+ of_property_read_bool(pdev->dev.of_node,
+ "atmel,nand-has-dma"))
+ caps = &atmel_sam9g45_nand_caps;
+
+ /*
+ * All SoCs except the at91sam9261 are assigning ALE to A21 and
+ * CLE to A22. If atmel,nand-addr-offset != 21 this means we're
+ * actually dealing with an at91sam9261 controller.
+ */
+ of_property_read_u32(pdev->dev.of_node,
+ "atmel,nand-addr-offset", &ale_offs);
+ if (ale_offs != 21)
+ caps = &atmel_sam9261_nand_caps;
+ }
+
+ return caps->ops->probe(pdev, caps);
+}
+
+static int atmel_nand_controller_remove(struct platform_device *pdev)
+{
+ struct atmel_nand_controller *nc = platform_get_drvdata(pdev);
+
+ return nc->caps->ops->remove(nc);
+}
+
+static struct platform_driver atmel_nand_controller_driver = {
+ .driver = {
+ .name = "atmel-nand-controller",
+ .of_match_table = of_match_ptr(atmel_nand_controller_of_ids),
+ },
+ .probe = atmel_nand_controller_probe,
+ .remove = atmel_nand_controller_remove,
+};
+module_platform_driver(atmel_nand_controller_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Boris Brezillon <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("NAND Flash Controller driver for Atmel SoCs");
+MODULE_ALIAS("platform:atmel-nand-controller");
--- /dev/null
+/*
+ * Copyright 2017 ATMEL
+ * Copyright 2017 Free Electrons
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * Derived from the atmel_nand.c driver which contained the following
+ * copyrights:
+ *
+ * Copyright 2003 Rick Bronson
+ *
+ * Derived from drivers/mtd/nand/autcpu12.c
+ * Copyright 2001 Thomas Gleixner (gleixner@autronix.de)
+ *
+ * Derived from drivers/mtd/spia.c
+ * Copyright 2000 Steven J. Hill (sjhill@cotw.com)
+ *
+ * Add Hardware ECC support for AT91SAM9260 / AT91SAM9263
+ * Richard Genoud (richard.genoud@gmail.com), Adeneo Copyright 2007
+ *
+ * Derived from Das U-Boot source code
+ * (u-boot-1.1.5/board/atmel/at91sam9263ek/nand.c)
+ * Copyright 2006 ATMEL Rousset, Lacressonniere Nicolas
+ *
+ * Add Programmable Multibit ECC support for various AT91 SoC
+ * Copyright 2012 ATMEL, Hong Xu
+ *
+ * Add Nand Flash Controller support for SAMA5 SoC
+ * Copyright 2013 ATMEL, Josh Wu (josh.wu@atmel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * The PMECC is an hardware assisted BCH engine, which means part of the
+ * ECC algorithm is left to the software. The hardware/software repartition
+ * is explained in the "PMECC Controller Functional Description" chapter in
+ * Atmel datasheets, and some of the functions in this file are directly
+ * implementing the algorithms described in the "Software Implementation"
+ * sub-section.
+ *
+ * TODO: it seems that the software BCH implementation in lib/bch.c is already
+ * providing some of the logic we are implementing here. It would be smart
+ * to expose the needed lib/bch.c helpers/functions and re-use them here.
+ */
+
+#include <linux/genalloc.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/mtd/nand.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "pmecc.h"
+
+/* Galois field dimension */
+#define PMECC_GF_DIMENSION_13 13
+#define PMECC_GF_DIMENSION_14 14
+
+/* Primitive Polynomial used by PMECC */
+#define PMECC_GF_13_PRIMITIVE_POLY 0x201b
+#define PMECC_GF_14_PRIMITIVE_POLY 0x4443
+
+#define PMECC_LOOKUP_TABLE_SIZE_512 0x2000
+#define PMECC_LOOKUP_TABLE_SIZE_1024 0x4000
+
+/* Time out value for reading PMECC status register */
+#define PMECC_MAX_TIMEOUT_MS 100
+
+/* PMECC Register Definitions */
+#define ATMEL_PMECC_CFG 0x0
+#define PMECC_CFG_BCH_STRENGTH(x) (x)
+#define PMECC_CFG_BCH_STRENGTH_MASK GENMASK(2, 0)
+#define PMECC_CFG_SECTOR512 (0 << 4)
+#define PMECC_CFG_SECTOR1024 (1 << 4)
+#define PMECC_CFG_NSECTORS(x) ((fls(x) - 1) << 8)
+#define PMECC_CFG_READ_OP (0 << 12)
+#define PMECC_CFG_WRITE_OP (1 << 12)
+#define PMECC_CFG_SPARE_ENABLE BIT(16)
+#define PMECC_CFG_AUTO_ENABLE BIT(20)
+
+#define ATMEL_PMECC_SAREA 0x4
+#define ATMEL_PMECC_SADDR 0x8
+#define ATMEL_PMECC_EADDR 0xc
+
+#define ATMEL_PMECC_CLK 0x10
+#define PMECC_CLK_133MHZ (2 << 0)
+
+#define ATMEL_PMECC_CTRL 0x14
+#define PMECC_CTRL_RST BIT(0)
+#define PMECC_CTRL_DATA BIT(1)
+#define PMECC_CTRL_USER BIT(2)
+#define PMECC_CTRL_ENABLE BIT(4)
+#define PMECC_CTRL_DISABLE BIT(5)
+
+#define ATMEL_PMECC_SR 0x18
+#define PMECC_SR_BUSY BIT(0)
+#define PMECC_SR_ENABLE BIT(4)
+
+#define ATMEL_PMECC_IER 0x1c
+#define ATMEL_PMECC_IDR 0x20
+#define ATMEL_PMECC_IMR 0x24
+#define ATMEL_PMECC_ISR 0x28
+#define PMECC_ERROR_INT BIT(0)
+
+#define ATMEL_PMECC_ECC(sector, n) \
+ ((((sector) + 1) * 0x40) + (n))
+
+#define ATMEL_PMECC_REM(sector, n) \
+ ((((sector) + 1) * 0x40) + ((n) * 4) + 0x200)
+
+/* PMERRLOC Register Definitions */
+#define ATMEL_PMERRLOC_ELCFG 0x0
+#define PMERRLOC_ELCFG_SECTOR_512 (0 << 0)
+#define PMERRLOC_ELCFG_SECTOR_1024 (1 << 0)
+#define PMERRLOC_ELCFG_NUM_ERRORS(n) ((n) << 16)
+
+#define ATMEL_PMERRLOC_ELPRIM 0x4
+#define ATMEL_PMERRLOC_ELEN 0x8
+#define ATMEL_PMERRLOC_ELDIS 0xc
+#define PMERRLOC_DISABLE BIT(0)
+
+#define ATMEL_PMERRLOC_ELSR 0x10
+#define PMERRLOC_ELSR_BUSY BIT(0)
+
+#define ATMEL_PMERRLOC_ELIER 0x14
+#define ATMEL_PMERRLOC_ELIDR 0x18
+#define ATMEL_PMERRLOC_ELIMR 0x1c
+#define ATMEL_PMERRLOC_ELISR 0x20
+#define PMERRLOC_ERR_NUM_MASK GENMASK(12, 8)
+#define PMERRLOC_CALC_DONE BIT(0)
+
+#define ATMEL_PMERRLOC_SIGMA(x) (((x) * 0x4) + 0x28)
+
+#define ATMEL_PMERRLOC_EL(offs, x) (((x) * 0x4) + (offs))
+
+struct atmel_pmecc_gf_tables {
+ u16 *alpha_to;
+ u16 *index_of;
+};
+
+struct atmel_pmecc_caps {
+ const int *strengths;
+ int nstrengths;
+ int el_offset;
+ bool correct_erased_chunks;
+};
+
+struct atmel_pmecc {
+ struct device *dev;
+ const struct atmel_pmecc_caps *caps;
+
+ struct {
+ void __iomem *base;
+ void __iomem *errloc;
+ } regs;
+
+ struct mutex lock;
+};
+
+struct atmel_pmecc_user_conf_cache {
+ u32 cfg;
+ u32 sarea;
+ u32 saddr;
+ u32 eaddr;
+};
+
+struct atmel_pmecc_user {
+ struct atmel_pmecc_user_conf_cache cache;
+ struct atmel_pmecc *pmecc;
+ const struct atmel_pmecc_gf_tables *gf_tables;
+ int eccbytes;
+ s16 *partial_syn;
+ s16 *si;
+ s16 *lmu;
+ s16 *smu;
+ s32 *mu;
+ s32 *dmu;
+ s32 *delta;
+ u32 isr;
+};
+
+static DEFINE_MUTEX(pmecc_gf_tables_lock);
+static const struct atmel_pmecc_gf_tables *pmecc_gf_tables_512;
+static const struct atmel_pmecc_gf_tables *pmecc_gf_tables_1024;
+
+static inline int deg(unsigned int poly)
+{
+ /* polynomial degree is the most-significant bit index */
+ return fls(poly) - 1;
+}
+
+static int atmel_pmecc_build_gf_tables(int mm, unsigned int poly,
+ struct atmel_pmecc_gf_tables *gf_tables)
+{
+ unsigned int i, x = 1;
+ const unsigned int k = BIT(deg(poly));
+ unsigned int nn = BIT(mm) - 1;
+
+ /* primitive polynomial must be of degree m */
+ if (k != (1u << mm))
+ return -EINVAL;
+
+ for (i = 0; i < nn; i++) {
+ gf_tables->alpha_to[i] = x;
+ gf_tables->index_of[x] = i;
+ if (i && (x == 1))
+ /* polynomial is not primitive (a^i=1 with 0<i<2^m-1) */
+ return -EINVAL;
+ x <<= 1;
+ if (x & k)
+ x ^= poly;
+ }
+ gf_tables->alpha_to[nn] = 1;
+ gf_tables->index_of[0] = 0;
+
+ return 0;
+}
+
+static const struct atmel_pmecc_gf_tables *
+atmel_pmecc_create_gf_tables(const struct atmel_pmecc_user_req *req)
+{
+ struct atmel_pmecc_gf_tables *gf_tables;
+ unsigned int poly, degree, table_size;
+ int ret;
+
+ if (req->ecc.sectorsize == 512) {
+ degree = PMECC_GF_DIMENSION_13;
+ poly = PMECC_GF_13_PRIMITIVE_POLY;
+ table_size = PMECC_LOOKUP_TABLE_SIZE_512;
+ } else {
+ degree = PMECC_GF_DIMENSION_14;
+ poly = PMECC_GF_14_PRIMITIVE_POLY;
+ table_size = PMECC_LOOKUP_TABLE_SIZE_1024;
+ }
+
+ gf_tables = kzalloc(sizeof(*gf_tables) +
+ (2 * table_size * sizeof(u16)),
+ GFP_KERNEL);
+ if (!gf_tables)
+ return ERR_PTR(-ENOMEM);
+
+ gf_tables->alpha_to = (void *)(gf_tables + 1);
+ gf_tables->index_of = gf_tables->alpha_to + table_size;
+
+ ret = atmel_pmecc_build_gf_tables(degree, poly, gf_tables);
+ if (ret) {
+ kfree(gf_tables);
+ return ERR_PTR(ret);
+ }
+
+ return gf_tables;
+}
+
+static const struct atmel_pmecc_gf_tables *
+atmel_pmecc_get_gf_tables(const struct atmel_pmecc_user_req *req)
+{
+ const struct atmel_pmecc_gf_tables **gf_tables, *ret;
+
+ mutex_lock(&pmecc_gf_tables_lock);
+ if (req->ecc.sectorsize == 512)
+ gf_tables = &pmecc_gf_tables_512;
+ else
+ gf_tables = &pmecc_gf_tables_1024;
+
+ ret = *gf_tables;
+
+ if (!ret) {
+ ret = atmel_pmecc_create_gf_tables(req);
+ if (!IS_ERR(ret))
+ *gf_tables = ret;
+ }
+ mutex_unlock(&pmecc_gf_tables_lock);
+
+ return ret;
+}
+
+static int atmel_pmecc_prepare_user_req(struct atmel_pmecc *pmecc,
+ struct atmel_pmecc_user_req *req)
+{
+ int i, max_eccbytes, eccbytes = 0, eccstrength = 0;
+
+ if (req->pagesize <= 0 || req->oobsize <= 0 || req->ecc.bytes <= 0)
+ return -EINVAL;
+
+ if (req->ecc.ooboffset >= 0 &&
+ req->ecc.ooboffset + req->ecc.bytes > req->oobsize)
+ return -EINVAL;
+
+ if (req->ecc.sectorsize == ATMEL_PMECC_SECTOR_SIZE_AUTO) {
+ if (req->ecc.strength != ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH)
+ return -EINVAL;
+
+ if (req->pagesize > 512)
+ req->ecc.sectorsize = 1024;
+ else
+ req->ecc.sectorsize = 512;
+ }
+
+ if (req->ecc.sectorsize != 512 && req->ecc.sectorsize != 1024)
+ return -EINVAL;
+
+ if (req->pagesize % req->ecc.sectorsize)
+ return -EINVAL;
+
+ req->ecc.nsectors = req->pagesize / req->ecc.sectorsize;
+
+ max_eccbytes = req->ecc.bytes;
+
+ for (i = 0; i < pmecc->caps->nstrengths; i++) {
+ int nbytes, strength = pmecc->caps->strengths[i];
+
+ if (req->ecc.strength != ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH &&
+ strength < req->ecc.strength)
+ continue;
+
+ nbytes = DIV_ROUND_UP(strength * fls(8 * req->ecc.sectorsize),
+ 8);
+ nbytes *= req->ecc.nsectors;
+
+ if (nbytes > max_eccbytes)
+ break;
+
+ eccstrength = strength;
+ eccbytes = nbytes;
+
+ if (req->ecc.strength != ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH)
+ break;
+ }
+
+ if (!eccstrength)
+ return -EINVAL;
+
+ req->ecc.bytes = eccbytes;
+ req->ecc.strength = eccstrength;
+
+ if (req->ecc.ooboffset < 0)
+ req->ecc.ooboffset = req->oobsize - eccbytes;
+
+ return 0;
+}
+
+struct atmel_pmecc_user *
+atmel_pmecc_create_user(struct atmel_pmecc *pmecc,
+ struct atmel_pmecc_user_req *req)
+{
+ struct atmel_pmecc_user *user;
+ const struct atmel_pmecc_gf_tables *gf_tables;
+ int strength, size, ret;
+
+ ret = atmel_pmecc_prepare_user_req(pmecc, req);
+ if (ret)
+ return ERR_PTR(ret);
+
+ size = sizeof(*user);
+ size = ALIGN(size, sizeof(u16));
+ /* Reserve space for partial_syn, si and smu */
+ size += ((2 * req->ecc.strength) + 1) * sizeof(u16) *
+ (2 + req->ecc.strength + 2);
+ /* Reserve space for lmu. */
+ size += (req->ecc.strength + 1) * sizeof(u16);
+ /* Reserve space for mu, dmu and delta. */
+ size = ALIGN(size, sizeof(s32));
+ size += (req->ecc.strength + 1) * sizeof(s32);
+
+ user = kzalloc(size, GFP_KERNEL);
+ if (!user)
+ return ERR_PTR(-ENOMEM);
+
+ user->pmecc = pmecc;
+
+ user->partial_syn = (s16 *)PTR_ALIGN(user + 1, sizeof(u16));
+ user->si = user->partial_syn + ((2 * req->ecc.strength) + 1);
+ user->lmu = user->si + ((2 * req->ecc.strength) + 1);
+ user->smu = user->lmu + (req->ecc.strength + 1);
+ user->mu = (s32 *)PTR_ALIGN(user->smu +
+ (((2 * req->ecc.strength) + 1) *
+ (req->ecc.strength + 2)),
+ sizeof(s32));
+ user->dmu = user->mu + req->ecc.strength + 1;
+ user->delta = user->dmu + req->ecc.strength + 1;
+
+ gf_tables = atmel_pmecc_get_gf_tables(req);
+ if (IS_ERR(gf_tables)) {
+ kfree(user);
+ return ERR_CAST(gf_tables);
+ }
+
+ user->gf_tables = gf_tables;
+
+ user->eccbytes = req->ecc.bytes / req->ecc.nsectors;
+
+ for (strength = 0; strength < pmecc->caps->nstrengths; strength++) {
+ if (pmecc->caps->strengths[strength] == req->ecc.strength)
+ break;
+ }
+
+ user->cache.cfg = PMECC_CFG_BCH_STRENGTH(strength) |
+ PMECC_CFG_NSECTORS(req->ecc.nsectors);
+
+ if (req->ecc.sectorsize == 1024)
+ user->cache.cfg |= PMECC_CFG_SECTOR1024;
+
+ user->cache.sarea = req->oobsize - 1;
+ user->cache.saddr = req->ecc.ooboffset;
+ user->cache.eaddr = req->ecc.ooboffset + req->ecc.bytes - 1;
+
+ return user;
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_create_user);
+
+void atmel_pmecc_destroy_user(struct atmel_pmecc_user *user)
+{
+ kfree(user);
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_destroy_user);
+
+static int get_strength(struct atmel_pmecc_user *user)
+{
+ const int *strengths = user->pmecc->caps->strengths;
+
+ return strengths[user->cache.cfg & PMECC_CFG_BCH_STRENGTH_MASK];
+}
+
+static int get_sectorsize(struct atmel_pmecc_user *user)
+{
+ return user->cache.cfg & PMECC_LOOKUP_TABLE_SIZE_1024 ? 1024 : 512;
+}
+
+static void atmel_pmecc_gen_syndrome(struct atmel_pmecc_user *user, int sector)
+{
+ int strength = get_strength(user);
+ u32 value;
+ int i;
+
+ /* Fill odd syndromes */
+ for (i = 0; i < strength; i++) {
+ value = readl_relaxed(user->pmecc->regs.base +
+ ATMEL_PMECC_REM(sector, i / 2));
+ if (i & 1)
+ value >>= 16;
+
+ user->partial_syn[(2 * i) + 1] = value;
+ }
+}
+
+static void atmel_pmecc_substitute(struct atmel_pmecc_user *user)
+{
+ int degree = get_sectorsize(user) == 512 ? 13 : 14;
+ int cw_len = BIT(degree) - 1;
+ int strength = get_strength(user);
+ s16 *alpha_to = user->gf_tables->alpha_to;
+ s16 *index_of = user->gf_tables->index_of;
+ s16 *partial_syn = user->partial_syn;
+ s16 *si;
+ int i, j;
+
+ /*
+ * si[] is a table that holds the current syndrome value,
+ * an element of that table belongs to the field
+ */
+ si = user->si;
+
+ memset(&si[1], 0, sizeof(s16) * ((2 * strength) - 1));
+
+ /* Computation 2t syndromes based on S(x) */
+ /* Odd syndromes */
+ for (i = 1; i < 2 * strength; i += 2) {
+ for (j = 0; j < degree; j++) {
+ if (partial_syn[i] & BIT(j))
+ si[i] = alpha_to[i * j] ^ si[i];
+ }
+ }
+ /* Even syndrome = (Odd syndrome) ** 2 */
+ for (i = 2, j = 1; j <= strength; i = ++j << 1) {
+ if (si[j] == 0) {
+ si[i] = 0;
+ } else {
+ s16 tmp;
+
+ tmp = index_of[si[j]];
+ tmp = (tmp * 2) % cw_len;
+ si[i] = alpha_to[tmp];
+ }
+ }
+}
+
+static void atmel_pmecc_get_sigma(struct atmel_pmecc_user *user)
+{
+ s16 *lmu = user->lmu;
+ s16 *si = user->si;
+ s32 *mu = user->mu;
+ s32 *dmu = user->dmu;
+ s32 *delta = user->delta;
+ int degree = get_sectorsize(user) == 512 ? 13 : 14;
+ int cw_len = BIT(degree) - 1;
+ int strength = get_strength(user);
+ int num = 2 * strength + 1;
+ s16 *index_of = user->gf_tables->index_of;
+ s16 *alpha_to = user->gf_tables->alpha_to;
+ int i, j, k;
+ u32 dmu_0_count, tmp;
+ s16 *smu = user->smu;
+
+ /* index of largest delta */
+ int ro;
+ int largest;
+ int diff;
+
+ dmu_0_count = 0;
+
+ /* First Row */
+
+ /* Mu */
+ mu[0] = -1;
+
+ memset(smu, 0, sizeof(s16) * num);
+ smu[0] = 1;
+
+ /* discrepancy set to 1 */
+ dmu[0] = 1;
+ /* polynom order set to 0 */
+ lmu[0] = 0;
+ delta[0] = (mu[0] * 2 - lmu[0]) >> 1;
+
+ /* Second Row */
+
+ /* Mu */
+ mu[1] = 0;
+ /* Sigma(x) set to 1 */
+ memset(&smu[num], 0, sizeof(s16) * num);
+ smu[num] = 1;
+
+ /* discrepancy set to S1 */
+ dmu[1] = si[1];
+
+ /* polynom order set to 0 */
+ lmu[1] = 0;
+
+ delta[1] = (mu[1] * 2 - lmu[1]) >> 1;
+
+ /* Init the Sigma(x) last row */
+ memset(&smu[(strength + 1) * num], 0, sizeof(s16) * num);
+
+ for (i = 1; i <= strength; i++) {
+ mu[i + 1] = i << 1;
+ /* Begin Computing Sigma (Mu+1) and L(mu) */
+ /* check if discrepancy is set to 0 */
+ if (dmu[i] == 0) {
+ dmu_0_count++;
+
+ tmp = ((strength - (lmu[i] >> 1) - 1) / 2);
+ if ((strength - (lmu[i] >> 1) - 1) & 0x1)
+ tmp += 2;
+ else
+ tmp += 1;
+
+ if (dmu_0_count == tmp) {
+ for (j = 0; j <= (lmu[i] >> 1) + 1; j++)
+ smu[(strength + 1) * num + j] =
+ smu[i * num + j];
+
+ lmu[strength + 1] = lmu[i];
+ return;
+ }
+
+ /* copy polynom */
+ for (j = 0; j <= lmu[i] >> 1; j++)
+ smu[(i + 1) * num + j] = smu[i * num + j];
+
+ /* copy previous polynom order to the next */
+ lmu[i + 1] = lmu[i];
+ } else {
+ ro = 0;
+ largest = -1;
+ /* find largest delta with dmu != 0 */
+ for (j = 0; j < i; j++) {
+ if ((dmu[j]) && (delta[j] > largest)) {
+ largest = delta[j];
+ ro = j;
+ }
+ }
+
+ /* compute difference */
+ diff = (mu[i] - mu[ro]);
+
+ /* Compute degree of the new smu polynomial */
+ if ((lmu[i] >> 1) > ((lmu[ro] >> 1) + diff))
+ lmu[i + 1] = lmu[i];
+ else
+ lmu[i + 1] = ((lmu[ro] >> 1) + diff) * 2;
+
+ /* Init smu[i+1] with 0 */
+ for (k = 0; k < num; k++)
+ smu[(i + 1) * num + k] = 0;
+
+ /* Compute smu[i+1] */
+ for (k = 0; k <= lmu[ro] >> 1; k++) {
+ s16 a, b, c;
+
+ if (!(smu[ro * num + k] && dmu[i]))
+ continue;
+
+ a = index_of[dmu[i]];
+ b = index_of[dmu[ro]];
+ c = index_of[smu[ro * num + k]];
+ tmp = a + (cw_len - b) + c;
+ a = alpha_to[tmp % cw_len];
+ smu[(i + 1) * num + (k + diff)] = a;
+ }
+
+ for (k = 0; k <= lmu[i] >> 1; k++)
+ smu[(i + 1) * num + k] ^= smu[i * num + k];
+ }
+
+ /* End Computing Sigma (Mu+1) and L(mu) */
+ /* In either case compute delta */
+ delta[i + 1] = (mu[i + 1] * 2 - lmu[i + 1]) >> 1;
+
+ /* Do not compute discrepancy for the last iteration */
+ if (i >= strength)
+ continue;
+
+ for (k = 0; k <= (lmu[i + 1] >> 1); k++) {
+ tmp = 2 * (i - 1);
+ if (k == 0) {
+ dmu[i + 1] = si[tmp + 3];
+ } else if (smu[(i + 1) * num + k] && si[tmp + 3 - k]) {
+ s16 a, b, c;
+
+ a = index_of[smu[(i + 1) * num + k]];
+ b = si[2 * (i - 1) + 3 - k];
+ c = index_of[b];
+ tmp = a + c;
+ tmp %= cw_len;
+ dmu[i + 1] = alpha_to[tmp] ^ dmu[i + 1];
+ }
+ }
+ }
+}
+
+static int atmel_pmecc_err_location(struct atmel_pmecc_user *user)
+{
+ int sector_size = get_sectorsize(user);
+ int degree = sector_size == 512 ? 13 : 14;
+ struct atmel_pmecc *pmecc = user->pmecc;
+ int strength = get_strength(user);
+ int ret, roots_nbr, i, err_nbr = 0;
+ int num = (2 * strength) + 1;
+ s16 *smu = user->smu;
+ u32 val;
+
+ writel(PMERRLOC_DISABLE, pmecc->regs.errloc + ATMEL_PMERRLOC_ELDIS);
+
+ for (i = 0; i <= user->lmu[strength + 1] >> 1; i++) {
+ writel_relaxed(smu[(strength + 1) * num + i],
+ pmecc->regs.errloc + ATMEL_PMERRLOC_SIGMA(i));
+ err_nbr++;
+ }
+
+ val = (err_nbr - 1) << 16;
+ if (sector_size == 1024)
+ val |= 1;
+
+ writel(val, pmecc->regs.errloc + ATMEL_PMERRLOC_ELCFG);
+ writel((sector_size * 8) + (degree * strength),
+ pmecc->regs.errloc + ATMEL_PMERRLOC_ELEN);
+
+ ret = readl_relaxed_poll_timeout(pmecc->regs.errloc +
+ ATMEL_PMERRLOC_ELISR,
+ val, val & PMERRLOC_CALC_DONE, 0,
+ PMECC_MAX_TIMEOUT_MS * 1000);
+ if (ret) {
+ dev_err(pmecc->dev,
+ "PMECC: Timeout to calculate error location.\n");
+ return ret;
+ }
+
+ roots_nbr = (val & PMERRLOC_ERR_NUM_MASK) >> 8;
+ /* Number of roots == degree of smu hence <= cap */
+ if (roots_nbr == user->lmu[strength + 1] >> 1)
+ return err_nbr - 1;
+
+ /*
+ * Number of roots does not match the degree of smu
+ * unable to correct error.
+ */
+ return -EBADMSG;
+}
+
+int atmel_pmecc_correct_sector(struct atmel_pmecc_user *user, int sector,
+ void *data, void *ecc)
+{
+ struct atmel_pmecc *pmecc = user->pmecc;
+ int sectorsize = get_sectorsize(user);
+ int eccbytes = user->eccbytes;
+ int i, nerrors;
+
+ if (!(user->isr & BIT(sector)))
+ return 0;
+
+ atmel_pmecc_gen_syndrome(user, sector);
+ atmel_pmecc_substitute(user);
+ atmel_pmecc_get_sigma(user);
+
+ nerrors = atmel_pmecc_err_location(user);
+ if (nerrors < 0)
+ return nerrors;
+
+ for (i = 0; i < nerrors; i++) {
+ const char *area;
+ int byte, bit;
+ u32 errpos;
+ u8 *ptr;
+
+ errpos = readl_relaxed(pmecc->regs.errloc +
+ ATMEL_PMERRLOC_EL(pmecc->caps->el_offset, i));
+ errpos--;
+
+ byte = errpos / 8;
+ bit = errpos % 8;
+
+ if (byte < sectorsize) {
+ ptr = data + byte;
+ area = "data";
+ } else if (byte < sectorsize + eccbytes) {
+ ptr = ecc + byte - sectorsize;
+ area = "ECC";
+ } else {
+ dev_dbg(pmecc->dev,
+ "Invalid errpos value (%d, max is %d)\n",
+ errpos, (sectorsize + eccbytes) * 8);
+ return -EINVAL;
+ }
+
+ dev_dbg(pmecc->dev,
+ "Bit flip in %s area, byte %d: 0x%02x -> 0x%02x\n",
+ area, byte, *ptr, (unsigned int)(*ptr ^ BIT(bit)));
+
+ *ptr ^= BIT(bit);
+ }
+
+ return nerrors;
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_correct_sector);
+
+bool atmel_pmecc_correct_erased_chunks(struct atmel_pmecc_user *user)
+{
+ return user->pmecc->caps->correct_erased_chunks;
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_correct_erased_chunks);
+
+void atmel_pmecc_get_generated_eccbytes(struct atmel_pmecc_user *user,
+ int sector, void *ecc)
+{
+ struct atmel_pmecc *pmecc = user->pmecc;
+ u8 *ptr = ecc;
+ int i;
+
+ for (i = 0; i < user->eccbytes; i++)
+ ptr[i] = readb_relaxed(pmecc->regs.base +
+ ATMEL_PMECC_ECC(sector, i));
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_get_generated_eccbytes);
+
+int atmel_pmecc_enable(struct atmel_pmecc_user *user, int op)
+{
+ struct atmel_pmecc *pmecc = user->pmecc;
+ u32 cfg;
+
+ if (op != NAND_ECC_READ && op != NAND_ECC_WRITE) {
+ dev_err(pmecc->dev, "Bad ECC operation!");
+ return -EINVAL;
+ }
+
+ mutex_lock(&user->pmecc->lock);
+
+ cfg = user->cache.cfg;
+ if (op == NAND_ECC_WRITE)
+ cfg |= PMECC_CFG_WRITE_OP;
+ else
+ cfg |= PMECC_CFG_AUTO_ENABLE;
+
+ writel(cfg, pmecc->regs.base + ATMEL_PMECC_CFG);
+ writel(user->cache.sarea, pmecc->regs.base + ATMEL_PMECC_SAREA);
+ writel(user->cache.saddr, pmecc->regs.base + ATMEL_PMECC_SADDR);
+ writel(user->cache.eaddr, pmecc->regs.base + ATMEL_PMECC_EADDR);
+
+ writel(PMECC_CTRL_ENABLE, pmecc->regs.base + ATMEL_PMECC_CTRL);
+ writel(PMECC_CTRL_DATA, pmecc->regs.base + ATMEL_PMECC_CTRL);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_enable);
+
+void atmel_pmecc_disable(struct atmel_pmecc_user *user)
+{
+ struct atmel_pmecc *pmecc = user->pmecc;
+
+ writel(PMECC_CTRL_RST, pmecc->regs.base + ATMEL_PMECC_CTRL);
+ writel(PMECC_CTRL_DISABLE, pmecc->regs.base + ATMEL_PMECC_CTRL);
+ mutex_unlock(&user->pmecc->lock);
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_disable);
+
+int atmel_pmecc_wait_rdy(struct atmel_pmecc_user *user)
+{
+ struct atmel_pmecc *pmecc = user->pmecc;
+ u32 status;
+ int ret;
+
+ ret = readl_relaxed_poll_timeout(pmecc->regs.base +
+ ATMEL_PMECC_SR,
+ status, !(status & PMECC_SR_BUSY), 0,
+ PMECC_MAX_TIMEOUT_MS * 1000);
+ if (ret) {
+ dev_err(pmecc->dev,
+ "Timeout while waiting for PMECC ready.\n");
+ return ret;
+ }
+
+ user->isr = readl_relaxed(pmecc->regs.base + ATMEL_PMECC_ISR);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(atmel_pmecc_wait_rdy);
+
+static struct atmel_pmecc *atmel_pmecc_create(struct platform_device *pdev,
+ const struct atmel_pmecc_caps *caps,
+ int pmecc_res_idx, int errloc_res_idx)
+{
+ struct device *dev = &pdev->dev;
+ struct atmel_pmecc *pmecc;
+ struct resource *res;
+
+ pmecc = devm_kzalloc(dev, sizeof(*pmecc), GFP_KERNEL);
+ if (!pmecc)
+ return ERR_PTR(-ENOMEM);
+
+ pmecc->caps = caps;
+ pmecc->dev = dev;
+ mutex_init(&pmecc->lock);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, pmecc_res_idx);
+ pmecc->regs.base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pmecc->regs.base))
+ return ERR_CAST(pmecc->regs.base);
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, errloc_res_idx);
+ pmecc->regs.errloc = devm_ioremap_resource(dev, res);
+ if (IS_ERR(pmecc->regs.errloc))
+ return ERR_CAST(pmecc->regs.errloc);
+
+ /* Disable all interrupts before registering the PMECC handler. */
+ writel(0xffffffff, pmecc->regs.base + ATMEL_PMECC_IDR);
+
+ /* Reset the ECC engine */
+ writel(PMECC_CTRL_RST, pmecc->regs.base + ATMEL_PMECC_CTRL);
+ writel(PMECC_CTRL_DISABLE, pmecc->regs.base + ATMEL_PMECC_CTRL);
+
+ return pmecc;
+}
+
+static void devm_atmel_pmecc_put(struct device *dev, void *res)
+{
+ struct atmel_pmecc **pmecc = res;
+
+ put_device((*pmecc)->dev);
+}
+
+static struct atmel_pmecc *atmel_pmecc_get_by_node(struct device *userdev,
+ struct device_node *np)
+{
+ struct platform_device *pdev;
+ struct atmel_pmecc *pmecc, **ptr;
+
+ pdev = of_find_device_by_node(np);
+ if (!pdev || !platform_get_drvdata(pdev))
+ return ERR_PTR(-EPROBE_DEFER);
+
+ ptr = devres_alloc(devm_atmel_pmecc_put, sizeof(*ptr), GFP_KERNEL);
+ if (!ptr)
+ return ERR_PTR(-ENOMEM);
+
+ get_device(&pdev->dev);
+ pmecc = platform_get_drvdata(pdev);
+
+ *ptr = pmecc;
+
+ devres_add(userdev, ptr);
+
+ return pmecc;
+}
+
+static const int atmel_pmecc_strengths[] = { 2, 4, 8, 12, 24, 32 };
+
+static struct atmel_pmecc_caps at91sam9g45_caps = {
+ .strengths = atmel_pmecc_strengths,
+ .nstrengths = 5,
+ .el_offset = 0x8c,
+};
+
+static struct atmel_pmecc_caps sama5d4_caps = {
+ .strengths = atmel_pmecc_strengths,
+ .nstrengths = 5,
+ .el_offset = 0x8c,
+ .correct_erased_chunks = true,
+};
+
+static struct atmel_pmecc_caps sama5d2_caps = {
+ .strengths = atmel_pmecc_strengths,
+ .nstrengths = 6,
+ .el_offset = 0xac,
+ .correct_erased_chunks = true,
+};
+
+static const struct of_device_id atmel_pmecc_legacy_match[] = {
+ { .compatible = "atmel,sama5d4-nand", &sama5d4_caps },
+ { .compatible = "atmel,sama5d2-nand", &sama5d2_caps },
+ { /* sentinel */ }
+};
+
+struct atmel_pmecc *devm_atmel_pmecc_get(struct device *userdev)
+{
+ struct atmel_pmecc *pmecc;
+ struct device_node *np;
+
+ if (!userdev)
+ return ERR_PTR(-EINVAL);
+
+ if (!userdev->of_node)
+ return NULL;
+
+ np = of_parse_phandle(userdev->of_node, "ecc-engine", 0);
+ if (np) {
+ pmecc = atmel_pmecc_get_by_node(userdev, np);
+ of_node_put(np);
+ } else {
+ /*
+ * Support old DT bindings: in this case the PMECC iomem
+ * resources are directly defined in the user pdev at position
+ * 1 and 2. Extract all relevant information from there.
+ */
+ struct platform_device *pdev = to_platform_device(userdev);
+ const struct atmel_pmecc_caps *caps;
+
+ /* No PMECC engine available. */
+ if (!of_property_read_bool(userdev->of_node,
+ "atmel,has-pmecc"))
+ return NULL;
+
+ caps = &at91sam9g45_caps;
+
+ /*
+ * Try to find the NFC subnode and extract the associated caps
+ * from there.
+ */
+ np = of_find_compatible_node(userdev->of_node, NULL,
+ "atmel,sama5d3-nfc");
+ if (np) {
+ const struct of_device_id *match;
+
+ match = of_match_node(atmel_pmecc_legacy_match, np);
+ if (match && match->data)
+ caps = match->data;
+
+ of_node_put(np);
+ }
+
+ pmecc = atmel_pmecc_create(pdev, caps, 1, 2);
+ }
+
+ return pmecc;
+}
+EXPORT_SYMBOL(devm_atmel_pmecc_get);
+
+static const struct of_device_id atmel_pmecc_match[] = {
+ { .compatible = "atmel,at91sam9g45-pmecc", &at91sam9g45_caps },
+ { .compatible = "atmel,sama5d4-pmecc", &sama5d4_caps },
+ { .compatible = "atmel,sama5d2-pmecc", &sama5d2_caps },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, atmel_pmecc_match);
+
+static int atmel_pmecc_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ const struct atmel_pmecc_caps *caps;
+ struct atmel_pmecc *pmecc;
+
+ caps = of_device_get_match_data(&pdev->dev);
+ if (!caps) {
+ dev_err(dev, "Invalid caps\n");
+ return -EINVAL;
+ }
+
+ pmecc = atmel_pmecc_create(pdev, caps, 0, 1);
+ if (IS_ERR(pmecc))
+ return PTR_ERR(pmecc);
+
+ platform_set_drvdata(pdev, pmecc);
+
+ return 0;
+}
+
+static struct platform_driver atmel_pmecc_driver = {
+ .driver = {
+ .name = "atmel-pmecc",
+ .of_match_table = of_match_ptr(atmel_pmecc_match),
+ },
+ .probe = atmel_pmecc_probe,
+};
+module_platform_driver(atmel_pmecc_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Boris Brezillon <boris.brezillon@free-electrons.com>");
+MODULE_DESCRIPTION("PMECC engine driver");
+MODULE_ALIAS("platform:atmel_pmecc");
--- /dev/null
+/*
+ * © Copyright 2016 ATMEL
+ * © Copyright 2016 Free Electrons
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * Derived from the atmel_nand.c driver which contained the following
+ * copyrights:
+ *
+ * Copyright © 2003 Rick Bronson
+ *
+ * Derived from drivers/mtd/nand/autcpu12.c
+ * Copyright © 2001 Thomas Gleixner (gleixner@autronix.de)
+ *
+ * Derived from drivers/mtd/spia.c
+ * Copyright © 2000 Steven J. Hill (sjhill@cotw.com)
+ *
+ *
+ * Add Hardware ECC support for AT91SAM9260 / AT91SAM9263
+ * Richard Genoud (richard.genoud@gmail.com), Adeneo Copyright © 2007
+ *
+ * Derived from Das U-Boot source code
+ * (u-boot-1.1.5/board/atmel/at91sam9263ek/nand.c)
+ * © Copyright 2006 ATMEL Rousset, Lacressonniere Nicolas
+ *
+ * Add Programmable Multibit ECC support for various AT91 SoC
+ * © Copyright 2012 ATMEL, Hong Xu
+ *
+ * Add Nand Flash Controller support for SAMA5 SoC
+ * © Copyright 2013 ATMEL, Josh Wu (josh.wu@atmel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef ATMEL_PMECC_H
+#define ATMEL_PMECC_H
+
+#define ATMEL_PMECC_MAXIMIZE_ECC_STRENGTH 0
+#define ATMEL_PMECC_SECTOR_SIZE_AUTO 0
+#define ATMEL_PMECC_OOBOFFSET_AUTO -1
+
+struct atmel_pmecc_user_req {
+ int pagesize;
+ int oobsize;
+ struct {
+ int strength;
+ int bytes;
+ int sectorsize;
+ int nsectors;
+ int ooboffset;
+ } ecc;
+};
+
+struct atmel_pmecc *devm_atmel_pmecc_get(struct device *dev);
+
+struct atmel_pmecc_user *
+atmel_pmecc_create_user(struct atmel_pmecc *pmecc,
+ struct atmel_pmecc_user_req *req);
+void atmel_pmecc_destroy_user(struct atmel_pmecc_user *user);
+
+int atmel_pmecc_enable(struct atmel_pmecc_user *user, int op);
+void atmel_pmecc_disable(struct atmel_pmecc_user *user);
+int atmel_pmecc_wait_rdy(struct atmel_pmecc_user *user);
+int atmel_pmecc_correct_sector(struct atmel_pmecc_user *user, int sector,
+ void *data, void *ecc);
+bool atmel_pmecc_correct_erased_chunks(struct atmel_pmecc_user *user);
+void atmel_pmecc_get_generated_eccbytes(struct atmel_pmecc_user *user,
+ int sector, void *ecc);
+
+#endif /* ATMEL_PMECC_H */
+++ /dev/null
-/*
- * Copyright © 2003 Rick Bronson
- *
- * Derived from drivers/mtd/nand/autcpu12.c
- * Copyright © 2001 Thomas Gleixner (gleixner@autronix.de)
- *
- * Derived from drivers/mtd/spia.c
- * Copyright © 2000 Steven J. Hill (sjhill@cotw.com)
- *
- *
- * Add Hardware ECC support for AT91SAM9260 / AT91SAM9263
- * Richard Genoud (richard.genoud@gmail.com), Adeneo Copyright © 2007
- *
- * Derived from Das U-Boot source code
- * (u-boot-1.1.5/board/atmel/at91sam9263ek/nand.c)
- * © Copyright 2006 ATMEL Rousset, Lacressonniere Nicolas
- *
- * Add Programmable Multibit ECC support for various AT91 SoC
- * © Copyright 2012 ATMEL, Hong Xu
- *
- * Add Nand Flash Controller support for SAMA5 SoC
- * © Copyright 2013 ATMEL, Josh Wu (josh.wu@atmel.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/clk.h>
-#include <linux/dma-mapping.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/platform_device.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_gpio.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/nand.h>
-#include <linux/mtd/partitions.h>
-
-#include <linux/delay.h>
-#include <linux/dmaengine.h>
-#include <linux/gpio.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/platform_data/atmel.h>
-
-static int use_dma = 1;
-module_param(use_dma, int, 0);
-
-static int on_flash_bbt = 0;
-module_param(on_flash_bbt, int, 0);
-
-/* Register access macros */
-#define ecc_readl(add, reg) \
- __raw_readl(add + ATMEL_ECC_##reg)
-#define ecc_writel(add, reg, value) \
- __raw_writel((value), add + ATMEL_ECC_##reg)
-
-#include "atmel_nand_ecc.h" /* Hardware ECC registers */
-#include "atmel_nand_nfc.h" /* Nand Flash Controller definition */
-
-struct atmel_nand_caps {
- bool pmecc_correct_erase_page;
- uint8_t pmecc_max_correction;
-};
-
-/*
- * oob layout for large page size
- * bad block info is on bytes 0 and 1
- * the bytes have to be consecutives to avoid
- * several NAND_CMD_RNDOUT during read
- *
- * oob layout for small page size
- * bad block info is on bytes 4 and 5
- * the bytes have to be consecutives to avoid
- * several NAND_CMD_RNDOUT during read
- */
-static int atmel_ooblayout_ecc_sp(struct mtd_info *mtd, int section,
- struct mtd_oob_region *oobregion)
-{
- if (section)
- return -ERANGE;
-
- oobregion->length = 4;
- oobregion->offset = 0;
-
- return 0;
-}
-
-static int atmel_ooblayout_free_sp(struct mtd_info *mtd, int section,
- struct mtd_oob_region *oobregion)
-{
- if (section)
- return -ERANGE;
-
- oobregion->offset = 6;
- oobregion->length = mtd->oobsize - oobregion->offset;
-
- return 0;
-}
-
-static const struct mtd_ooblayout_ops atmel_ooblayout_sp_ops = {
- .ecc = atmel_ooblayout_ecc_sp,
- .free = atmel_ooblayout_free_sp,
-};
-
-struct atmel_nfc {
- void __iomem *base_cmd_regs;
- void __iomem *hsmc_regs;
- void *sram_bank0;
- dma_addr_t sram_bank0_phys;
- bool use_nfc_sram;
- bool write_by_sram;
-
- struct clk *clk;
-
- bool is_initialized;
- struct completion comp_ready;
- struct completion comp_cmd_done;
- struct completion comp_xfer_done;
-
- /* Point to the sram bank which include readed data via NFC */
- void *data_in_sram;
- bool will_write_sram;
-};
-static struct atmel_nfc nand_nfc;
-
-struct atmel_nand_host {
- struct nand_chip nand_chip;
- void __iomem *io_base;
- dma_addr_t io_phys;
- struct atmel_nand_data board;
- struct device *dev;
- void __iomem *ecc;
-
- struct completion comp;
- struct dma_chan *dma_chan;
-
- struct atmel_nfc *nfc;
-
- const struct atmel_nand_caps *caps;
- bool has_pmecc;
- u8 pmecc_corr_cap;
- u16 pmecc_sector_size;
- bool has_no_lookup_table;
- u32 pmecc_lookup_table_offset;
- u32 pmecc_lookup_table_offset_512;
- u32 pmecc_lookup_table_offset_1024;
-
- int pmecc_degree; /* Degree of remainders */
- int pmecc_cw_len; /* Length of codeword */
-
- void __iomem *pmerrloc_base;
- void __iomem *pmerrloc_el_base;
- void __iomem *pmecc_rom_base;
-
- /* lookup table for alpha_to and index_of */
- void __iomem *pmecc_alpha_to;
- void __iomem *pmecc_index_of;
-
- /* data for pmecc computation */
- int16_t *pmecc_partial_syn;
- int16_t *pmecc_si;
- int16_t *pmecc_smu; /* Sigma table */
- int16_t *pmecc_lmu; /* polynomal order */
- int *pmecc_mu;
- int *pmecc_dmu;
- int *pmecc_delta;
-};
-
-/*
- * Enable NAND.
- */
-static void atmel_nand_enable(struct atmel_nand_host *host)
-{
- if (gpio_is_valid(host->board.enable_pin))
- gpio_set_value(host->board.enable_pin, 0);
-}
-
-/*
- * Disable NAND.
- */
-static void atmel_nand_disable(struct atmel_nand_host *host)
-{
- if (gpio_is_valid(host->board.enable_pin))
- gpio_set_value(host->board.enable_pin, 1);
-}
-
-/*
- * Hardware specific access to control-lines
- */
-static void atmel_nand_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- if (ctrl & NAND_CTRL_CHANGE) {
- if (ctrl & NAND_NCE)
- atmel_nand_enable(host);
- else
- atmel_nand_disable(host);
- }
- if (cmd == NAND_CMD_NONE)
- return;
-
- if (ctrl & NAND_CLE)
- writeb(cmd, host->io_base + (1 << host->board.cle));
- else
- writeb(cmd, host->io_base + (1 << host->board.ale));
-}
-
-/*
- * Read the Device Ready pin.
- */
-static int atmel_nand_device_ready(struct mtd_info *mtd)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- return gpio_get_value(host->board.rdy_pin) ^
- !!host->board.rdy_pin_active_low;
-}
-
-/* Set up for hardware ready pin and enable pin. */
-static int atmel_nand_set_enable_ready_pins(struct mtd_info *mtd)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- int res = 0;
-
- if (gpio_is_valid(host->board.rdy_pin)) {
- res = devm_gpio_request(host->dev,
- host->board.rdy_pin, "nand_rdy");
- if (res < 0) {
- dev_err(host->dev,
- "can't request rdy gpio %d\n",
- host->board.rdy_pin);
- return res;
- }
-
- res = gpio_direction_input(host->board.rdy_pin);
- if (res < 0) {
- dev_err(host->dev,
- "can't request input direction rdy gpio %d\n",
- host->board.rdy_pin);
- return res;
- }
-
- chip->dev_ready = atmel_nand_device_ready;
- }
-
- if (gpio_is_valid(host->board.enable_pin)) {
- res = devm_gpio_request(host->dev,
- host->board.enable_pin, "nand_enable");
- if (res < 0) {
- dev_err(host->dev,
- "can't request enable gpio %d\n",
- host->board.enable_pin);
- return res;
- }
-
- res = gpio_direction_output(host->board.enable_pin, 1);
- if (res < 0) {
- dev_err(host->dev,
- "can't request output direction enable gpio %d\n",
- host->board.enable_pin);
- return res;
- }
- }
-
- return res;
-}
-
-/*
- * Minimal-overhead PIO for data access.
- */
-static void atmel_read_buf8(struct mtd_info *mtd, u8 *buf, int len)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- if (host->nfc && host->nfc->use_nfc_sram && host->nfc->data_in_sram) {
- memcpy(buf, host->nfc->data_in_sram, len);
- host->nfc->data_in_sram += len;
- } else {
- __raw_readsb(nand_chip->IO_ADDR_R, buf, len);
- }
-}
-
-static void atmel_read_buf16(struct mtd_info *mtd, u8 *buf, int len)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- if (host->nfc && host->nfc->use_nfc_sram && host->nfc->data_in_sram) {
- memcpy(buf, host->nfc->data_in_sram, len);
- host->nfc->data_in_sram += len;
- } else {
- __raw_readsw(nand_chip->IO_ADDR_R, buf, len / 2);
- }
-}
-
-static void atmel_write_buf8(struct mtd_info *mtd, const u8 *buf, int len)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
-
- __raw_writesb(nand_chip->IO_ADDR_W, buf, len);
-}
-
-static void atmel_write_buf16(struct mtd_info *mtd, const u8 *buf, int len)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
-
- __raw_writesw(nand_chip->IO_ADDR_W, buf, len / 2);
-}
-
-static void dma_complete_func(void *completion)
-{
- complete(completion);
-}
-
-static int nfc_set_sram_bank(struct atmel_nand_host *host, unsigned int bank)
-{
- /* NFC only has two banks. Must be 0 or 1 */
- if (bank > 1)
- return -EINVAL;
-
- if (bank) {
- struct mtd_info *mtd = nand_to_mtd(&host->nand_chip);
-
- /* Only for a 2k-page or lower flash, NFC can handle 2 banks */
- if (mtd->writesize > 2048)
- return -EINVAL;
- nfc_writel(host->nfc->hsmc_regs, BANK, ATMEL_HSMC_NFC_BANK1);
- } else {
- nfc_writel(host->nfc->hsmc_regs, BANK, ATMEL_HSMC_NFC_BANK0);
- }
-
- return 0;
-}
-
-static uint nfc_get_sram_off(struct atmel_nand_host *host)
-{
- if (nfc_readl(host->nfc->hsmc_regs, BANK) & ATMEL_HSMC_NFC_BANK1)
- return NFC_SRAM_BANK1_OFFSET;
- else
- return 0;
-}
-
-static dma_addr_t nfc_sram_phys(struct atmel_nand_host *host)
-{
- if (nfc_readl(host->nfc->hsmc_regs, BANK) & ATMEL_HSMC_NFC_BANK1)
- return host->nfc->sram_bank0_phys + NFC_SRAM_BANK1_OFFSET;
- else
- return host->nfc->sram_bank0_phys;
-}
-
-static int atmel_nand_dma_op(struct mtd_info *mtd, void *buf, int len,
- int is_read)
-{
- struct dma_device *dma_dev;
- enum dma_ctrl_flags flags;
- dma_addr_t dma_src_addr, dma_dst_addr, phys_addr;
- struct dma_async_tx_descriptor *tx = NULL;
- dma_cookie_t cookie;
- struct nand_chip *chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- void *p = buf;
- int err = -EIO;
- enum dma_data_direction dir = is_read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
- struct atmel_nfc *nfc = host->nfc;
-
- if (buf >= high_memory)
- goto err_buf;
-
- dma_dev = host->dma_chan->device;
-
- flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
-
- phys_addr = dma_map_single(dma_dev->dev, p, len, dir);
- if (dma_mapping_error(dma_dev->dev, phys_addr)) {
- dev_err(host->dev, "Failed to dma_map_single\n");
- goto err_buf;
- }
-
- if (is_read) {
- if (nfc && nfc->data_in_sram)
- dma_src_addr = nfc_sram_phys(host) + (nfc->data_in_sram
- - (nfc->sram_bank0 + nfc_get_sram_off(host)));
- else
- dma_src_addr = host->io_phys;
-
- dma_dst_addr = phys_addr;
- } else {
- dma_src_addr = phys_addr;
-
- if (nfc && nfc->write_by_sram)
- dma_dst_addr = nfc_sram_phys(host);
- else
- dma_dst_addr = host->io_phys;
- }
-
- tx = dma_dev->device_prep_dma_memcpy(host->dma_chan, dma_dst_addr,
- dma_src_addr, len, flags);
- if (!tx) {
- dev_err(host->dev, "Failed to prepare DMA memcpy\n");
- goto err_dma;
- }
-
- init_completion(&host->comp);
- tx->callback = dma_complete_func;
- tx->callback_param = &host->comp;
-
- cookie = tx->tx_submit(tx);
- if (dma_submit_error(cookie)) {
- dev_err(host->dev, "Failed to do DMA tx_submit\n");
- goto err_dma;
- }
-
- dma_async_issue_pending(host->dma_chan);
- wait_for_completion(&host->comp);
-
- if (is_read && nfc && nfc->data_in_sram)
- /* After read data from SRAM, need to increase the position */
- nfc->data_in_sram += len;
-
- err = 0;
-
-err_dma:
- dma_unmap_single(dma_dev->dev, phys_addr, len, dir);
-err_buf:
- if (err != 0)
- dev_dbg(host->dev, "Fall back to CPU I/O\n");
- return err;
-}
-
-static void atmel_read_buf(struct mtd_info *mtd, u8 *buf, int len)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
-
- if (use_dma && len > mtd->oobsize)
- /* only use DMA for bigger than oob size: better performances */
- if (atmel_nand_dma_op(mtd, buf, len, 1) == 0)
- return;
-
- if (chip->options & NAND_BUSWIDTH_16)
- atmel_read_buf16(mtd, buf, len);
- else
- atmel_read_buf8(mtd, buf, len);
-}
-
-static void atmel_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
-
- if (use_dma && len > mtd->oobsize)
- /* only use DMA for bigger than oob size: better performances */
- if (atmel_nand_dma_op(mtd, (void *)buf, len, 0) == 0)
- return;
-
- if (chip->options & NAND_BUSWIDTH_16)
- atmel_write_buf16(mtd, buf, len);
- else
- atmel_write_buf8(mtd, buf, len);
-}
-
-/*
- * Return number of ecc bytes per sector according to sector size and
- * correction capability
- *
- * Following table shows what at91 PMECC supported:
- * Correction Capability Sector_512_bytes Sector_1024_bytes
- * ===================== ================ =================
- * 2-bits 4-bytes 4-bytes
- * 4-bits 7-bytes 7-bytes
- * 8-bits 13-bytes 14-bytes
- * 12-bits 20-bytes 21-bytes
- * 24-bits 39-bytes 42-bytes
- * 32-bits 52-bytes 56-bytes
- */
-static int pmecc_get_ecc_bytes(int cap, int sector_size)
-{
- int m = 12 + sector_size / 512;
- return (m * cap + 7) / 8;
-}
-
-static void __iomem *pmecc_get_alpha_to(struct atmel_nand_host *host)
-{
- int table_size;
-
- table_size = host->pmecc_sector_size == 512 ?
- PMECC_LOOKUP_TABLE_SIZE_512 : PMECC_LOOKUP_TABLE_SIZE_1024;
-
- return host->pmecc_rom_base + host->pmecc_lookup_table_offset +
- table_size * sizeof(int16_t);
-}
-
-static int pmecc_data_alloc(struct atmel_nand_host *host)
-{
- const int cap = host->pmecc_corr_cap;
- int size;
-
- size = (2 * cap + 1) * sizeof(int16_t);
- host->pmecc_partial_syn = devm_kzalloc(host->dev, size, GFP_KERNEL);
- host->pmecc_si = devm_kzalloc(host->dev, size, GFP_KERNEL);
- host->pmecc_lmu = devm_kzalloc(host->dev,
- (cap + 1) * sizeof(int16_t), GFP_KERNEL);
- host->pmecc_smu = devm_kzalloc(host->dev,
- (cap + 2) * size, GFP_KERNEL);
-
- size = (cap + 1) * sizeof(int);
- host->pmecc_mu = devm_kzalloc(host->dev, size, GFP_KERNEL);
- host->pmecc_dmu = devm_kzalloc(host->dev, size, GFP_KERNEL);
- host->pmecc_delta = devm_kzalloc(host->dev, size, GFP_KERNEL);
-
- if (!host->pmecc_partial_syn ||
- !host->pmecc_si ||
- !host->pmecc_lmu ||
- !host->pmecc_smu ||
- !host->pmecc_mu ||
- !host->pmecc_dmu ||
- !host->pmecc_delta)
- return -ENOMEM;
-
- return 0;
-}
-
-static void pmecc_gen_syndrome(struct mtd_info *mtd, int sector)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- int i;
- uint32_t value;
-
- /* Fill odd syndromes */
- for (i = 0; i < host->pmecc_corr_cap; i++) {
- value = pmecc_readl_rem_relaxed(host->ecc, sector, i / 2);
- if (i & 1)
- value >>= 16;
- value &= 0xffff;
- host->pmecc_partial_syn[(2 * i) + 1] = (int16_t)value;
- }
-}
-
-static void pmecc_substitute(struct mtd_info *mtd)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- int16_t __iomem *alpha_to = host->pmecc_alpha_to;
- int16_t __iomem *index_of = host->pmecc_index_of;
- int16_t *partial_syn = host->pmecc_partial_syn;
- const int cap = host->pmecc_corr_cap;
- int16_t *si;
- int i, j;
-
- /* si[] is a table that holds the current syndrome value,
- * an element of that table belongs to the field
- */
- si = host->pmecc_si;
-
- memset(&si[1], 0, sizeof(int16_t) * (2 * cap - 1));
-
- /* Computation 2t syndromes based on S(x) */
- /* Odd syndromes */
- for (i = 1; i < 2 * cap; i += 2) {
- for (j = 0; j < host->pmecc_degree; j++) {
- if (partial_syn[i] & ((unsigned short)0x1 << j))
- si[i] = readw_relaxed(alpha_to + i * j) ^ si[i];
- }
- }
- /* Even syndrome = (Odd syndrome) ** 2 */
- for (i = 2, j = 1; j <= cap; i = ++j << 1) {
- if (si[j] == 0) {
- si[i] = 0;
- } else {
- int16_t tmp;
-
- tmp = readw_relaxed(index_of + si[j]);
- tmp = (tmp * 2) % host->pmecc_cw_len;
- si[i] = readw_relaxed(alpha_to + tmp);
- }
- }
-
- return;
-}
-
-static void pmecc_get_sigma(struct mtd_info *mtd)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- int16_t *lmu = host->pmecc_lmu;
- int16_t *si = host->pmecc_si;
- int *mu = host->pmecc_mu;
- int *dmu = host->pmecc_dmu; /* Discrepancy */
- int *delta = host->pmecc_delta; /* Delta order */
- int cw_len = host->pmecc_cw_len;
- const int16_t cap = host->pmecc_corr_cap;
- const int num = 2 * cap + 1;
- int16_t __iomem *index_of = host->pmecc_index_of;
- int16_t __iomem *alpha_to = host->pmecc_alpha_to;
- int i, j, k;
- uint32_t dmu_0_count, tmp;
- int16_t *smu = host->pmecc_smu;
-
- /* index of largest delta */
- int ro;
- int largest;
- int diff;
-
- dmu_0_count = 0;
-
- /* First Row */
-
- /* Mu */
- mu[0] = -1;
-
- memset(smu, 0, sizeof(int16_t) * num);
- smu[0] = 1;
-
- /* discrepancy set to 1 */
- dmu[0] = 1;
- /* polynom order set to 0 */
- lmu[0] = 0;
- delta[0] = (mu[0] * 2 - lmu[0]) >> 1;
-
- /* Second Row */
-
- /* Mu */
- mu[1] = 0;
- /* Sigma(x) set to 1 */
- memset(&smu[num], 0, sizeof(int16_t) * num);
- smu[num] = 1;
-
- /* discrepancy set to S1 */
- dmu[1] = si[1];
-
- /* polynom order set to 0 */
- lmu[1] = 0;
-
- delta[1] = (mu[1] * 2 - lmu[1]) >> 1;
-
- /* Init the Sigma(x) last row */
- memset(&smu[(cap + 1) * num], 0, sizeof(int16_t) * num);
-
- for (i = 1; i <= cap; i++) {
- mu[i + 1] = i << 1;
- /* Begin Computing Sigma (Mu+1) and L(mu) */
- /* check if discrepancy is set to 0 */
- if (dmu[i] == 0) {
- dmu_0_count++;
-
- tmp = ((cap - (lmu[i] >> 1) - 1) / 2);
- if ((cap - (lmu[i] >> 1) - 1) & 0x1)
- tmp += 2;
- else
- tmp += 1;
-
- if (dmu_0_count == tmp) {
- for (j = 0; j <= (lmu[i] >> 1) + 1; j++)
- smu[(cap + 1) * num + j] =
- smu[i * num + j];
-
- lmu[cap + 1] = lmu[i];
- return;
- }
-
- /* copy polynom */
- for (j = 0; j <= lmu[i] >> 1; j++)
- smu[(i + 1) * num + j] = smu[i * num + j];
-
- /* copy previous polynom order to the next */
- lmu[i + 1] = lmu[i];
- } else {
- ro = 0;
- largest = -1;
- /* find largest delta with dmu != 0 */
- for (j = 0; j < i; j++) {
- if ((dmu[j]) && (delta[j] > largest)) {
- largest = delta[j];
- ro = j;
- }
- }
-
- /* compute difference */
- diff = (mu[i] - mu[ro]);
-
- /* Compute degree of the new smu polynomial */
- if ((lmu[i] >> 1) > ((lmu[ro] >> 1) + diff))
- lmu[i + 1] = lmu[i];
- else
- lmu[i + 1] = ((lmu[ro] >> 1) + diff) * 2;
-
- /* Init smu[i+1] with 0 */
- for (k = 0; k < num; k++)
- smu[(i + 1) * num + k] = 0;
-
- /* Compute smu[i+1] */
- for (k = 0; k <= lmu[ro] >> 1; k++) {
- int16_t a, b, c;
-
- if (!(smu[ro * num + k] && dmu[i]))
- continue;
- a = readw_relaxed(index_of + dmu[i]);
- b = readw_relaxed(index_of + dmu[ro]);
- c = readw_relaxed(index_of + smu[ro * num + k]);
- tmp = a + (cw_len - b) + c;
- a = readw_relaxed(alpha_to + tmp % cw_len);
- smu[(i + 1) * num + (k + diff)] = a;
- }
-
- for (k = 0; k <= lmu[i] >> 1; k++)
- smu[(i + 1) * num + k] ^= smu[i * num + k];
- }
-
- /* End Computing Sigma (Mu+1) and L(mu) */
- /* In either case compute delta */
- delta[i + 1] = (mu[i + 1] * 2 - lmu[i + 1]) >> 1;
-
- /* Do not compute discrepancy for the last iteration */
- if (i >= cap)
- continue;
-
- for (k = 0; k <= (lmu[i + 1] >> 1); k++) {
- tmp = 2 * (i - 1);
- if (k == 0) {
- dmu[i + 1] = si[tmp + 3];
- } else if (smu[(i + 1) * num + k] && si[tmp + 3 - k]) {
- int16_t a, b, c;
- a = readw_relaxed(index_of +
- smu[(i + 1) * num + k]);
- b = si[2 * (i - 1) + 3 - k];
- c = readw_relaxed(index_of + b);
- tmp = a + c;
- tmp %= cw_len;
- dmu[i + 1] = readw_relaxed(alpha_to + tmp) ^
- dmu[i + 1];
- }
- }
- }
-
- return;
-}
-
-static int pmecc_err_location(struct mtd_info *mtd)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- unsigned long end_time;
- const int cap = host->pmecc_corr_cap;
- const int num = 2 * cap + 1;
- int sector_size = host->pmecc_sector_size;
- int err_nbr = 0; /* number of error */
- int roots_nbr; /* number of roots */
- int i;
- uint32_t val;
- int16_t *smu = host->pmecc_smu;
-
- pmerrloc_writel(host->pmerrloc_base, ELDIS, PMERRLOC_DISABLE);
-
- for (i = 0; i <= host->pmecc_lmu[cap + 1] >> 1; i++) {
- pmerrloc_writel_sigma_relaxed(host->pmerrloc_base, i,
- smu[(cap + 1) * num + i]);
- err_nbr++;
- }
-
- val = (err_nbr - 1) << 16;
- if (sector_size == 1024)
- val |= 1;
-
- pmerrloc_writel(host->pmerrloc_base, ELCFG, val);
- pmerrloc_writel(host->pmerrloc_base, ELEN,
- sector_size * 8 + host->pmecc_degree * cap);
-
- end_time = jiffies + msecs_to_jiffies(PMECC_MAX_TIMEOUT_MS);
- while (!(pmerrloc_readl_relaxed(host->pmerrloc_base, ELISR)
- & PMERRLOC_CALC_DONE)) {
- if (unlikely(time_after(jiffies, end_time))) {
- dev_err(host->dev, "PMECC: Timeout to calculate error location.\n");
- return -1;
- }
- cpu_relax();
- }
-
- roots_nbr = (pmerrloc_readl_relaxed(host->pmerrloc_base, ELISR)
- & PMERRLOC_ERR_NUM_MASK) >> 8;
- /* Number of roots == degree of smu hence <= cap */
- if (roots_nbr == host->pmecc_lmu[cap + 1] >> 1)
- return err_nbr - 1;
-
- /* Number of roots does not match the degree of smu
- * unable to correct error */
- return -1;
-}
-
-static void pmecc_correct_data(struct mtd_info *mtd, uint8_t *buf, uint8_t *ecc,
- int sector_num, int extra_bytes, int err_nbr)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- int i = 0;
- int byte_pos, bit_pos, sector_size, pos;
- uint32_t tmp;
- uint8_t err_byte;
-
- sector_size = host->pmecc_sector_size;
-
- while (err_nbr) {
- tmp = pmerrloc_readl_el_relaxed(host->pmerrloc_el_base, i) - 1;
- byte_pos = tmp / 8;
- bit_pos = tmp % 8;
-
- if (byte_pos >= (sector_size + extra_bytes))
- BUG(); /* should never happen */
-
- if (byte_pos < sector_size) {
- err_byte = *(buf + byte_pos);
- *(buf + byte_pos) ^= (1 << bit_pos);
-
- pos = sector_num * host->pmecc_sector_size + byte_pos;
- dev_dbg(host->dev, "Bit flip in data area, byte_pos: %d, bit_pos: %d, 0x%02x -> 0x%02x\n",
- pos, bit_pos, err_byte, *(buf + byte_pos));
- } else {
- struct mtd_oob_region oobregion;
-
- /* Bit flip in OOB area */
- tmp = sector_num * nand_chip->ecc.bytes
- + (byte_pos - sector_size);
- err_byte = ecc[tmp];
- ecc[tmp] ^= (1 << bit_pos);
-
- mtd_ooblayout_ecc(mtd, 0, &oobregion);
- pos = tmp + oobregion.offset;
- dev_dbg(host->dev, "Bit flip in OOB, oob_byte_pos: %d, bit_pos: %d, 0x%02x -> 0x%02x\n",
- pos, bit_pos, err_byte, ecc[tmp]);
- }
-
- i++;
- err_nbr--;
- }
-
- return;
-}
-
-static int pmecc_correction(struct mtd_info *mtd, u32 pmecc_stat, uint8_t *buf,
- u8 *ecc)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- int i, err_nbr;
- uint8_t *buf_pos;
- int max_bitflips = 0;
-
- for (i = 0; i < nand_chip->ecc.steps; i++) {
- err_nbr = 0;
- if (pmecc_stat & 0x1) {
- buf_pos = buf + i * host->pmecc_sector_size;
-
- pmecc_gen_syndrome(mtd, i);
- pmecc_substitute(mtd);
- pmecc_get_sigma(mtd);
-
- err_nbr = pmecc_err_location(mtd);
- if (err_nbr >= 0) {
- pmecc_correct_data(mtd, buf_pos, ecc, i,
- nand_chip->ecc.bytes,
- err_nbr);
- } else if (!host->caps->pmecc_correct_erase_page) {
- u8 *ecc_pos = ecc + (i * nand_chip->ecc.bytes);
-
- /* Try to detect erased pages */
- err_nbr = nand_check_erased_ecc_chunk(buf_pos,
- host->pmecc_sector_size,
- ecc_pos,
- nand_chip->ecc.bytes,
- NULL, 0,
- nand_chip->ecc.strength);
- }
-
- if (err_nbr < 0) {
- dev_err(host->dev, "PMECC: Too many errors\n");
- mtd->ecc_stats.failed++;
- return -EIO;
- }
-
- mtd->ecc_stats.corrected += err_nbr;
- max_bitflips = max_t(int, max_bitflips, err_nbr);
- }
- pmecc_stat >>= 1;
- }
-
- return max_bitflips;
-}
-
-static void pmecc_enable(struct atmel_nand_host *host, int ecc_op)
-{
- u32 val;
-
- if (ecc_op != NAND_ECC_READ && ecc_op != NAND_ECC_WRITE) {
- dev_err(host->dev, "atmel_nand: wrong pmecc operation type!");
- return;
- }
-
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_RST);
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_DISABLE);
- val = pmecc_readl_relaxed(host->ecc, CFG);
-
- if (ecc_op == NAND_ECC_READ)
- pmecc_writel(host->ecc, CFG, (val & ~PMECC_CFG_WRITE_OP)
- | PMECC_CFG_AUTO_ENABLE);
- else
- pmecc_writel(host->ecc, CFG, (val | PMECC_CFG_WRITE_OP)
- & ~PMECC_CFG_AUTO_ENABLE);
-
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_ENABLE);
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_DATA);
-}
-
-static int atmel_nand_pmecc_read_page(struct mtd_info *mtd,
- struct nand_chip *chip, uint8_t *buf, int oob_required, int page)
-{
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- int eccsize = chip->ecc.size * chip->ecc.steps;
- uint8_t *oob = chip->oob_poi;
- uint32_t stat;
- unsigned long end_time;
- int bitflips = 0;
-
- if (!host->nfc || !host->nfc->use_nfc_sram)
- pmecc_enable(host, NAND_ECC_READ);
-
- chip->read_buf(mtd, buf, eccsize);
- chip->read_buf(mtd, oob, mtd->oobsize);
-
- end_time = jiffies + msecs_to_jiffies(PMECC_MAX_TIMEOUT_MS);
- while ((pmecc_readl_relaxed(host->ecc, SR) & PMECC_SR_BUSY)) {
- if (unlikely(time_after(jiffies, end_time))) {
- dev_err(host->dev, "PMECC: Timeout to get error status.\n");
- return -EIO;
- }
- cpu_relax();
- }
-
- stat = pmecc_readl_relaxed(host->ecc, ISR);
- if (stat != 0) {
- struct mtd_oob_region oobregion;
-
- mtd_ooblayout_ecc(mtd, 0, &oobregion);
- bitflips = pmecc_correction(mtd, stat, buf,
- &oob[oobregion.offset]);
- if (bitflips < 0)
- /* uncorrectable errors */
- return 0;
- }
-
- return bitflips;
-}
-
-static int atmel_nand_pmecc_write_page(struct mtd_info *mtd,
- struct nand_chip *chip, const uint8_t *buf, int oob_required,
- int page)
-{
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- struct mtd_oob_region oobregion = { };
- int i, j, section = 0;
- unsigned long end_time;
-
- if (!host->nfc || !host->nfc->write_by_sram) {
- pmecc_enable(host, NAND_ECC_WRITE);
- chip->write_buf(mtd, (u8 *)buf, mtd->writesize);
- }
-
- end_time = jiffies + msecs_to_jiffies(PMECC_MAX_TIMEOUT_MS);
- while ((pmecc_readl_relaxed(host->ecc, SR) & PMECC_SR_BUSY)) {
- if (unlikely(time_after(jiffies, end_time))) {
- dev_err(host->dev, "PMECC: Timeout to get ECC value.\n");
- return -EIO;
- }
- cpu_relax();
- }
-
- for (i = 0; i < chip->ecc.steps; i++) {
- for (j = 0; j < chip->ecc.bytes; j++) {
- if (!oobregion.length)
- mtd_ooblayout_ecc(mtd, section, &oobregion);
-
- chip->oob_poi[oobregion.offset] =
- pmecc_readb_ecc_relaxed(host->ecc, i, j);
- oobregion.length--;
- oobregion.offset++;
- section++;
- }
- }
- chip->write_buf(mtd, chip->oob_poi, mtd->oobsize);
-
- return 0;
-}
-
-static void atmel_pmecc_core_init(struct mtd_info *mtd)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- int eccbytes = mtd_ooblayout_count_eccbytes(mtd);
- uint32_t val = 0;
- struct mtd_oob_region oobregion;
-
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_RST);
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_DISABLE);
-
- switch (host->pmecc_corr_cap) {
- case 2:
- val = PMECC_CFG_BCH_ERR2;
- break;
- case 4:
- val = PMECC_CFG_BCH_ERR4;
- break;
- case 8:
- val = PMECC_CFG_BCH_ERR8;
- break;
- case 12:
- val = PMECC_CFG_BCH_ERR12;
- break;
- case 24:
- val = PMECC_CFG_BCH_ERR24;
- break;
- case 32:
- val = PMECC_CFG_BCH_ERR32;
- break;
- }
-
- if (host->pmecc_sector_size == 512)
- val |= PMECC_CFG_SECTOR512;
- else if (host->pmecc_sector_size == 1024)
- val |= PMECC_CFG_SECTOR1024;
-
- switch (nand_chip->ecc.steps) {
- case 1:
- val |= PMECC_CFG_PAGE_1SECTOR;
- break;
- case 2:
- val |= PMECC_CFG_PAGE_2SECTORS;
- break;
- case 4:
- val |= PMECC_CFG_PAGE_4SECTORS;
- break;
- case 8:
- val |= PMECC_CFG_PAGE_8SECTORS;
- break;
- }
-
- val |= (PMECC_CFG_READ_OP | PMECC_CFG_SPARE_DISABLE
- | PMECC_CFG_AUTO_DISABLE);
- pmecc_writel(host->ecc, CFG, val);
-
- pmecc_writel(host->ecc, SAREA, mtd->oobsize - 1);
- mtd_ooblayout_ecc(mtd, 0, &oobregion);
- pmecc_writel(host->ecc, SADDR, oobregion.offset);
- pmecc_writel(host->ecc, EADDR,
- oobregion.offset + eccbytes - 1);
- /* See datasheet about PMECC Clock Control Register */
- pmecc_writel(host->ecc, CLK, 2);
- pmecc_writel(host->ecc, IDR, 0xff);
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_ENABLE);
-}
-
-/*
- * Get minimum ecc requirements from NAND.
- * If pmecc-cap, pmecc-sector-size in DTS are not specified, this function
- * will set them according to minimum ecc requirement. Otherwise, use the
- * value in DTS file.
- * return 0 if success. otherwise return error code.
- */
-static int pmecc_choose_ecc(struct atmel_nand_host *host,
- int *cap, int *sector_size)
-{
- /* Get minimum ECC requirements */
- if (host->nand_chip.ecc_strength_ds) {
- *cap = host->nand_chip.ecc_strength_ds;
- *sector_size = host->nand_chip.ecc_step_ds;
- dev_info(host->dev, "minimum ECC: %d bits in %d bytes\n",
- *cap, *sector_size);
- } else {
- *cap = 2;
- *sector_size = 512;
- dev_info(host->dev, "can't detect min. ECC, assume 2 bits in 512 bytes\n");
- }
-
- /* If device tree doesn't specify, use NAND's minimum ECC parameters */
- if (host->pmecc_corr_cap == 0) {
- if (*cap > host->caps->pmecc_max_correction)
- return -EINVAL;
-
- /* use the most fitable ecc bits (the near bigger one ) */
- if (*cap <= 2)
- host->pmecc_corr_cap = 2;
- else if (*cap <= 4)
- host->pmecc_corr_cap = 4;
- else if (*cap <= 8)
- host->pmecc_corr_cap = 8;
- else if (*cap <= 12)
- host->pmecc_corr_cap = 12;
- else if (*cap <= 24)
- host->pmecc_corr_cap = 24;
- else if (*cap <= 32)
- host->pmecc_corr_cap = 32;
- else
- return -EINVAL;
- }
- if (host->pmecc_sector_size == 0) {
- /* use the most fitable sector size (the near smaller one ) */
- if (*sector_size >= 1024)
- host->pmecc_sector_size = 1024;
- else if (*sector_size >= 512)
- host->pmecc_sector_size = 512;
- else
- return -EINVAL;
- }
- return 0;
-}
-
-static inline int deg(unsigned int poly)
-{
- /* polynomial degree is the most-significant bit index */
- return fls(poly) - 1;
-}
-
-static int build_gf_tables(int mm, unsigned int poly,
- int16_t *index_of, int16_t *alpha_to)
-{
- unsigned int i, x = 1;
- const unsigned int k = 1 << deg(poly);
- unsigned int nn = (1 << mm) - 1;
-
- /* primitive polynomial must be of degree m */
- if (k != (1u << mm))
- return -EINVAL;
-
- for (i = 0; i < nn; i++) {
- alpha_to[i] = x;
- index_of[x] = i;
- if (i && (x == 1))
- /* polynomial is not primitive (a^i=1 with 0<i<2^m-1) */
- return -EINVAL;
- x <<= 1;
- if (x & k)
- x ^= poly;
- }
- alpha_to[nn] = 1;
- index_of[0] = 0;
-
- return 0;
-}
-
-static uint16_t *create_lookup_table(struct device *dev, int sector_size)
-{
- int degree = (sector_size == 512) ?
- PMECC_GF_DIMENSION_13 :
- PMECC_GF_DIMENSION_14;
- unsigned int poly = (sector_size == 512) ?
- PMECC_GF_13_PRIMITIVE_POLY :
- PMECC_GF_14_PRIMITIVE_POLY;
- int table_size = (sector_size == 512) ?
- PMECC_LOOKUP_TABLE_SIZE_512 :
- PMECC_LOOKUP_TABLE_SIZE_1024;
-
- int16_t *addr = devm_kzalloc(dev, 2 * table_size * sizeof(uint16_t),
- GFP_KERNEL);
- if (addr && build_gf_tables(degree, poly, addr, addr + table_size))
- return NULL;
-
- return addr;
-}
-
-static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
- struct atmel_nand_host *host)
-{
- struct nand_chip *nand_chip = &host->nand_chip;
- struct mtd_info *mtd = nand_to_mtd(nand_chip);
- struct resource *regs, *regs_pmerr, *regs_rom;
- uint16_t *galois_table;
- int cap, sector_size, err_no;
-
- err_no = pmecc_choose_ecc(host, &cap, §or_size);
- if (err_no) {
- dev_err(host->dev, "The NAND flash's ECC requirement are not support!");
- return err_no;
- }
-
- if (cap > host->pmecc_corr_cap ||
- sector_size != host->pmecc_sector_size)
- dev_info(host->dev, "WARNING: Be Caution! Using different PMECC parameters from Nand ONFI ECC reqirement.\n");
-
- cap = host->pmecc_corr_cap;
- sector_size = host->pmecc_sector_size;
- host->pmecc_lookup_table_offset = (sector_size == 512) ?
- host->pmecc_lookup_table_offset_512 :
- host->pmecc_lookup_table_offset_1024;
-
- dev_info(host->dev, "Initialize PMECC params, cap: %d, sector: %d\n",
- cap, sector_size);
-
- regs = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- if (!regs) {
- dev_warn(host->dev,
- "Can't get I/O resource regs for PMECC controller, rolling back on software ECC\n");
- nand_chip->ecc.mode = NAND_ECC_SOFT;
- nand_chip->ecc.algo = NAND_ECC_HAMMING;
- return 0;
- }
-
- host->ecc = devm_ioremap_resource(&pdev->dev, regs);
- if (IS_ERR(host->ecc)) {
- err_no = PTR_ERR(host->ecc);
- goto err;
- }
-
- regs_pmerr = platform_get_resource(pdev, IORESOURCE_MEM, 2);
- host->pmerrloc_base = devm_ioremap_resource(&pdev->dev, regs_pmerr);
- if (IS_ERR(host->pmerrloc_base)) {
- err_no = PTR_ERR(host->pmerrloc_base);
- goto err;
- }
- host->pmerrloc_el_base = host->pmerrloc_base + ATMEL_PMERRLOC_SIGMAx +
- (host->caps->pmecc_max_correction + 1) * 4;
-
- if (!host->has_no_lookup_table) {
- regs_rom = platform_get_resource(pdev, IORESOURCE_MEM, 3);
- host->pmecc_rom_base = devm_ioremap_resource(&pdev->dev,
- regs_rom);
- if (IS_ERR(host->pmecc_rom_base)) {
- dev_err(host->dev, "Can not get I/O resource for ROM, will build a lookup table in runtime!\n");
- host->has_no_lookup_table = true;
- }
- }
-
- if (host->has_no_lookup_table) {
- /* Build the look-up table in runtime */
- galois_table = create_lookup_table(host->dev, sector_size);
- if (!galois_table) {
- dev_err(host->dev, "Failed to build a lookup table in runtime!\n");
- err_no = -EINVAL;
- goto err;
- }
-
- host->pmecc_rom_base = (void __iomem *)galois_table;
- host->pmecc_lookup_table_offset = 0;
- }
-
- nand_chip->ecc.size = sector_size;
-
- /* set ECC page size and oob layout */
- switch (mtd->writesize) {
- case 512:
- case 1024:
- case 2048:
- case 4096:
- case 8192:
- if (sector_size > mtd->writesize) {
- dev_err(host->dev, "pmecc sector size is bigger than the page size!\n");
- err_no = -EINVAL;
- goto err;
- }
-
- host->pmecc_degree = (sector_size == 512) ?
- PMECC_GF_DIMENSION_13 : PMECC_GF_DIMENSION_14;
- host->pmecc_cw_len = (1 << host->pmecc_degree) - 1;
- host->pmecc_alpha_to = pmecc_get_alpha_to(host);
- host->pmecc_index_of = host->pmecc_rom_base +
- host->pmecc_lookup_table_offset;
-
- nand_chip->ecc.strength = cap;
- nand_chip->ecc.bytes = pmecc_get_ecc_bytes(cap, sector_size);
- nand_chip->ecc.steps = mtd->writesize / sector_size;
- nand_chip->ecc.total = nand_chip->ecc.bytes *
- nand_chip->ecc.steps;
- if (nand_chip->ecc.total >
- mtd->oobsize - PMECC_OOB_RESERVED_BYTES) {
- dev_err(host->dev, "No room for ECC bytes\n");
- err_no = -EINVAL;
- goto err;
- }
-
- mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
- break;
- default:
- dev_warn(host->dev,
- "Unsupported page size for PMECC, use Software ECC\n");
- /* page size not handled by HW ECC */
- /* switching back to soft ECC */
- nand_chip->ecc.mode = NAND_ECC_SOFT;
- nand_chip->ecc.algo = NAND_ECC_HAMMING;
- return 0;
- }
-
- /* Allocate data for PMECC computation */
- err_no = pmecc_data_alloc(host);
- if (err_no) {
- dev_err(host->dev,
- "Cannot allocate memory for PMECC computation!\n");
- goto err;
- }
-
- nand_chip->options |= NAND_NO_SUBPAGE_WRITE;
- nand_chip->ecc.read_page = atmel_nand_pmecc_read_page;
- nand_chip->ecc.write_page = atmel_nand_pmecc_write_page;
-
- atmel_pmecc_core_init(mtd);
-
- return 0;
-
-err:
- return err_no;
-}
-
-/*
- * Calculate HW ECC
- *
- * function called after a write
- *
- * mtd: MTD block structure
- * dat: raw data (unused)
- * ecc_code: buffer for ECC
- */
-static int atmel_nand_calculate(struct mtd_info *mtd,
- const u_char *dat, unsigned char *ecc_code)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- unsigned int ecc_value;
-
- /* get the first 2 ECC bytes */
- ecc_value = ecc_readl(host->ecc, PR);
-
- ecc_code[0] = ecc_value & 0xFF;
- ecc_code[1] = (ecc_value >> 8) & 0xFF;
-
- /* get the last 2 ECC bytes */
- ecc_value = ecc_readl(host->ecc, NPR) & ATMEL_ECC_NPARITY;
-
- ecc_code[2] = ecc_value & 0xFF;
- ecc_code[3] = (ecc_value >> 8) & 0xFF;
-
- return 0;
-}
-
-/*
- * HW ECC read page function
- *
- * mtd: mtd info structure
- * chip: nand chip info structure
- * buf: buffer to store read data
- * oob_required: caller expects OOB data read to chip->oob_poi
- */
-static int atmel_nand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
- uint8_t *buf, int oob_required, int page)
-{
- int eccsize = chip->ecc.size;
- int eccbytes = chip->ecc.bytes;
- uint8_t *p = buf;
- uint8_t *oob = chip->oob_poi;
- uint8_t *ecc_pos;
- int stat;
- unsigned int max_bitflips = 0;
- struct mtd_oob_region oobregion = {};
-
- /*
- * Errata: ALE is incorrectly wired up to the ECC controller
- * on the AP7000, so it will include the address cycles in the
- * ECC calculation.
- *
- * Workaround: Reset the parity registers before reading the
- * actual data.
- */
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- if (host->board.need_reset_workaround)
- ecc_writel(host->ecc, CR, ATMEL_ECC_RST);
-
- /* read the page */
- chip->read_buf(mtd, p, eccsize);
-
- /* move to ECC position if needed */
- mtd_ooblayout_ecc(mtd, 0, &oobregion);
- if (oobregion.offset != 0) {
- /*
- * This only works on large pages because the ECC controller
- * waits for NAND_CMD_RNDOUTSTART after the NAND_CMD_RNDOUT.
- * Anyway, for small pages, the first ECC byte is at offset
- * 0 in the OOB area.
- */
- chip->cmdfunc(mtd, NAND_CMD_RNDOUT,
- mtd->writesize + oobregion.offset, -1);
- }
-
- /* the ECC controller needs to read the ECC just after the data */
- ecc_pos = oob + oobregion.offset;
- chip->read_buf(mtd, ecc_pos, eccbytes);
-
- /* check if there's an error */
- stat = chip->ecc.correct(mtd, p, oob, NULL);
-
- if (stat < 0) {
- mtd->ecc_stats.failed++;
- } else {
- mtd->ecc_stats.corrected += stat;
- max_bitflips = max_t(unsigned int, max_bitflips, stat);
- }
-
- /* get back to oob start (end of page) */
- chip->cmdfunc(mtd, NAND_CMD_RNDOUT, mtd->writesize, -1);
-
- /* read the oob */
- chip->read_buf(mtd, oob, mtd->oobsize);
-
- return max_bitflips;
-}
-
-/*
- * HW ECC Correction
- *
- * function called after a read
- *
- * mtd: MTD block structure
- * dat: raw data read from the chip
- * read_ecc: ECC from the chip (unused)
- * isnull: unused
- *
- * Detect and correct a 1 bit error for a page
- */
-static int atmel_nand_correct(struct mtd_info *mtd, u_char *dat,
- u_char *read_ecc, u_char *isnull)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
- unsigned int ecc_status;
- unsigned int ecc_word, ecc_bit;
-
- /* get the status from the Status Register */
- ecc_status = ecc_readl(host->ecc, SR);
-
- /* if there's no error */
- if (likely(!(ecc_status & ATMEL_ECC_RECERR)))
- return 0;
-
- /* get error bit offset (4 bits) */
- ecc_bit = ecc_readl(host->ecc, PR) & ATMEL_ECC_BITADDR;
- /* get word address (12 bits) */
- ecc_word = ecc_readl(host->ecc, PR) & ATMEL_ECC_WORDADDR;
- ecc_word >>= 4;
-
- /* if there are multiple errors */
- if (ecc_status & ATMEL_ECC_MULERR) {
- /* check if it is a freshly erased block
- * (filled with 0xff) */
- if ((ecc_bit == ATMEL_ECC_BITADDR)
- && (ecc_word == (ATMEL_ECC_WORDADDR >> 4))) {
- /* the block has just been erased, return OK */
- return 0;
- }
- /* it doesn't seems to be a freshly
- * erased block.
- * We can't correct so many errors */
- dev_dbg(host->dev, "atmel_nand : multiple errors detected."
- " Unable to correct.\n");
- return -EBADMSG;
- }
-
- /* if there's a single bit error : we can correct it */
- if (ecc_status & ATMEL_ECC_ECCERR) {
- /* there's nothing much to do here.
- * the bit error is on the ECC itself.
- */
- dev_dbg(host->dev, "atmel_nand : one bit error on ECC code."
- " Nothing to correct\n");
- return 0;
- }
-
- dev_dbg(host->dev, "atmel_nand : one bit error on data."
- " (word offset in the page :"
- " 0x%x bit offset : 0x%x)\n",
- ecc_word, ecc_bit);
- /* correct the error */
- if (nand_chip->options & NAND_BUSWIDTH_16) {
- /* 16 bits words */
- ((unsigned short *) dat)[ecc_word] ^= (1 << ecc_bit);
- } else {
- /* 8 bits words */
- dat[ecc_word] ^= (1 << ecc_bit);
- }
- dev_dbg(host->dev, "atmel_nand : error corrected\n");
- return 1;
-}
-
-/*
- * Enable HW ECC : unused on most chips
- */
-static void atmel_nand_hwctl(struct mtd_info *mtd, int mode)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- if (host->board.need_reset_workaround)
- ecc_writel(host->ecc, CR, ATMEL_ECC_RST);
-}
-
-static int atmel_of_init_ecc(struct atmel_nand_host *host,
- struct device_node *np)
-{
- u32 offset[2];
- u32 val;
-
- host->has_pmecc = of_property_read_bool(np, "atmel,has-pmecc");
-
- /* Not using PMECC */
- if (!(host->nand_chip.ecc.mode == NAND_ECC_HW) || !host->has_pmecc)
- return 0;
-
- /* use PMECC, get correction capability, sector size and lookup
- * table offset.
- * If correction bits and sector size are not specified, then find
- * them from NAND ONFI parameters.
- */
- if (of_property_read_u32(np, "atmel,pmecc-cap", &val) == 0) {
- if (val > host->caps->pmecc_max_correction) {
- dev_err(host->dev,
- "Required ECC strength too high: %u max %u\n",
- val, host->caps->pmecc_max_correction);
- return -EINVAL;
- }
- if ((val != 2) && (val != 4) && (val != 8) &&
- (val != 12) && (val != 24) && (val != 32)) {
- dev_err(host->dev,
- "Required ECC strength not supported: %u\n",
- val);
- return -EINVAL;
- }
- host->pmecc_corr_cap = (u8)val;
- }
-
- if (of_property_read_u32(np, "atmel,pmecc-sector-size", &val) == 0) {
- if ((val != 512) && (val != 1024)) {
- dev_err(host->dev,
- "Required ECC sector size not supported: %u\n",
- val);
- return -EINVAL;
- }
- host->pmecc_sector_size = (u16)val;
- }
-
- if (of_property_read_u32_array(np, "atmel,pmecc-lookup-table-offset",
- offset, 2) != 0) {
- dev_err(host->dev, "Cannot get PMECC lookup table offset, will build a lookup table in runtime.\n");
- host->has_no_lookup_table = true;
- /* Will build a lookup table and initialize the offset later */
- return 0;
- }
-
- if (!offset[0] && !offset[1]) {
- dev_err(host->dev, "Invalid PMECC lookup table offset\n");
- return -EINVAL;
- }
-
- host->pmecc_lookup_table_offset_512 = offset[0];
- host->pmecc_lookup_table_offset_1024 = offset[1];
-
- return 0;
-}
-
-static int atmel_of_init_port(struct atmel_nand_host *host,
- struct device_node *np)
-{
- u32 val;
- struct atmel_nand_data *board = &host->board;
- enum of_gpio_flags flags = 0;
-
- host->caps = (struct atmel_nand_caps *)
- of_device_get_match_data(host->dev);
-
- if (of_property_read_u32(np, "atmel,nand-addr-offset", &val) == 0) {
- if (val >= 32) {
- dev_err(host->dev, "invalid addr-offset %u\n", val);
- return -EINVAL;
- }
- board->ale = val;
- }
-
- if (of_property_read_u32(np, "atmel,nand-cmd-offset", &val) == 0) {
- if (val >= 32) {
- dev_err(host->dev, "invalid cmd-offset %u\n", val);
- return -EINVAL;
- }
- board->cle = val;
- }
-
- board->has_dma = of_property_read_bool(np, "atmel,nand-has-dma");
-
- board->rdy_pin = of_get_gpio_flags(np, 0, &flags);
- board->rdy_pin_active_low = (flags == OF_GPIO_ACTIVE_LOW);
-
- board->enable_pin = of_get_gpio(np, 1);
- board->det_pin = of_get_gpio(np, 2);
-
- /* load the nfc driver if there is */
- of_platform_populate(np, NULL, NULL, host->dev);
-
- /*
- * Initialize ECC mode to NAND_ECC_SOFT so that we have a correct value
- * even if the nand-ecc-mode property is not defined.
- */
- host->nand_chip.ecc.mode = NAND_ECC_SOFT;
- host->nand_chip.ecc.algo = NAND_ECC_HAMMING;
-
- return 0;
-}
-
-static int atmel_hw_nand_init_params(struct platform_device *pdev,
- struct atmel_nand_host *host)
-{
- struct nand_chip *nand_chip = &host->nand_chip;
- struct mtd_info *mtd = nand_to_mtd(nand_chip);
- struct resource *regs;
-
- regs = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- if (!regs) {
- dev_err(host->dev,
- "Can't get I/O resource regs, use software ECC\n");
- nand_chip->ecc.mode = NAND_ECC_SOFT;
- nand_chip->ecc.algo = NAND_ECC_HAMMING;
- return 0;
- }
-
- host->ecc = devm_ioremap_resource(&pdev->dev, regs);
- if (IS_ERR(host->ecc))
- return PTR_ERR(host->ecc);
-
- /* ECC is calculated for the whole page (1 step) */
- nand_chip->ecc.size = mtd->writesize;
-
- /* set ECC page size and oob layout */
- switch (mtd->writesize) {
- case 512:
- mtd_set_ooblayout(mtd, &atmel_ooblayout_sp_ops);
- ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_528);
- break;
- case 1024:
- mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
- ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_1056);
- break;
- case 2048:
- mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
- ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_2112);
- break;
- case 4096:
- mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
- ecc_writel(host->ecc, MR, ATMEL_ECC_PAGESIZE_4224);
- break;
- default:
- /* page size not handled by HW ECC */
- /* switching back to soft ECC */
- nand_chip->ecc.mode = NAND_ECC_SOFT;
- nand_chip->ecc.algo = NAND_ECC_HAMMING;
- return 0;
- }
-
- /* set up for HW ECC */
- nand_chip->ecc.calculate = atmel_nand_calculate;
- nand_chip->ecc.correct = atmel_nand_correct;
- nand_chip->ecc.hwctl = atmel_nand_hwctl;
- nand_chip->ecc.read_page = atmel_nand_read_page;
- nand_chip->ecc.bytes = 4;
- nand_chip->ecc.strength = 1;
-
- return 0;
-}
-
-static inline u32 nfc_read_status(struct atmel_nand_host *host)
-{
- u32 err_flags = NFC_SR_DTOE | NFC_SR_UNDEF | NFC_SR_AWB | NFC_SR_ASE;
- u32 nfc_status = nfc_readl(host->nfc->hsmc_regs, SR);
-
- if (unlikely(nfc_status & err_flags)) {
- if (nfc_status & NFC_SR_DTOE)
- dev_err(host->dev, "NFC: Waiting Nand R/B Timeout Error\n");
- else if (nfc_status & NFC_SR_UNDEF)
- dev_err(host->dev, "NFC: Access Undefined Area Error\n");
- else if (nfc_status & NFC_SR_AWB)
- dev_err(host->dev, "NFC: Access memory While NFC is busy\n");
- else if (nfc_status & NFC_SR_ASE)
- dev_err(host->dev, "NFC: Access memory Size Error\n");
- }
-
- return nfc_status;
-}
-
-/* SMC interrupt service routine */
-static irqreturn_t hsmc_interrupt(int irq, void *dev_id)
-{
- struct atmel_nand_host *host = dev_id;
- u32 status, mask, pending;
- irqreturn_t ret = IRQ_NONE;
-
- status = nfc_read_status(host);
- mask = nfc_readl(host->nfc->hsmc_regs, IMR);
- pending = status & mask;
-
- if (pending & NFC_SR_XFR_DONE) {
- complete(&host->nfc->comp_xfer_done);
- nfc_writel(host->nfc->hsmc_regs, IDR, NFC_SR_XFR_DONE);
- ret = IRQ_HANDLED;
- }
- if (pending & NFC_SR_RB_EDGE) {
- complete(&host->nfc->comp_ready);
- nfc_writel(host->nfc->hsmc_regs, IDR, NFC_SR_RB_EDGE);
- ret = IRQ_HANDLED;
- }
- if (pending & NFC_SR_CMD_DONE) {
- complete(&host->nfc->comp_cmd_done);
- nfc_writel(host->nfc->hsmc_regs, IDR, NFC_SR_CMD_DONE);
- ret = IRQ_HANDLED;
- }
-
- return ret;
-}
-
-/* NFC(Nand Flash Controller) related functions */
-static void nfc_prepare_interrupt(struct atmel_nand_host *host, u32 flag)
-{
- if (flag & NFC_SR_XFR_DONE)
- init_completion(&host->nfc->comp_xfer_done);
-
- if (flag & NFC_SR_RB_EDGE)
- init_completion(&host->nfc->comp_ready);
-
- if (flag & NFC_SR_CMD_DONE)
- init_completion(&host->nfc->comp_cmd_done);
-
- /* Enable interrupt that need to wait for */
- nfc_writel(host->nfc->hsmc_regs, IER, flag);
-}
-
-static int nfc_wait_interrupt(struct atmel_nand_host *host, u32 flag)
-{
- int i, index = 0;
- struct completion *comp[3]; /* Support 3 interrupt completion */
-
- if (flag & NFC_SR_XFR_DONE)
- comp[index++] = &host->nfc->comp_xfer_done;
-
- if (flag & NFC_SR_RB_EDGE)
- comp[index++] = &host->nfc->comp_ready;
-
- if (flag & NFC_SR_CMD_DONE)
- comp[index++] = &host->nfc->comp_cmd_done;
-
- if (index == 0) {
- dev_err(host->dev, "Unknown interrupt flag: 0x%08x\n", flag);
- return -EINVAL;
- }
-
- for (i = 0; i < index; i++) {
- if (wait_for_completion_timeout(comp[i],
- msecs_to_jiffies(NFC_TIME_OUT_MS)))
- continue; /* wait for next completion */
- else
- goto err_timeout;
- }
-
- return 0;
-
-err_timeout:
- dev_err(host->dev, "Time out to wait for interrupt: 0x%08x\n", flag);
- /* Disable the interrupt as it is not handled by interrupt handler */
- nfc_writel(host->nfc->hsmc_regs, IDR, flag);
- return -ETIMEDOUT;
-}
-
-static int nfc_send_command(struct atmel_nand_host *host,
- unsigned int cmd, unsigned int addr, unsigned char cycle0)
-{
- unsigned long timeout;
- u32 flag = NFC_SR_CMD_DONE;
- flag |= cmd & NFCADDR_CMD_DATAEN ? NFC_SR_XFR_DONE : 0;
-
- dev_dbg(host->dev,
- "nfc_cmd: 0x%08x, addr1234: 0x%08x, cycle0: 0x%02x\n",
- cmd, addr, cycle0);
-
- timeout = jiffies + msecs_to_jiffies(NFC_TIME_OUT_MS);
- while (nfc_readl(host->nfc->hsmc_regs, SR) & NFC_SR_BUSY) {
- if (time_after(jiffies, timeout)) {
- dev_err(host->dev,
- "Time out to wait for NFC ready!\n");
- return -ETIMEDOUT;
- }
- }
-
- nfc_prepare_interrupt(host, flag);
- nfc_writel(host->nfc->hsmc_regs, CYCLE0, cycle0);
- nfc_cmd_addr1234_writel(cmd, addr, host->nfc->base_cmd_regs);
- return nfc_wait_interrupt(host, flag);
-}
-
-static int nfc_device_ready(struct mtd_info *mtd)
-{
- u32 status, mask;
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- status = nfc_read_status(host);
- mask = nfc_readl(host->nfc->hsmc_regs, IMR);
-
- /* The mask should be 0. If not we may lost interrupts */
- if (unlikely(mask & status))
- dev_err(host->dev, "Lost the interrupt flags: 0x%08x\n",
- mask & status);
-
- return status & NFC_SR_RB_EDGE;
-}
-
-static void nfc_select_chip(struct mtd_info *mtd, int chip)
-{
- struct nand_chip *nand_chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(nand_chip);
-
- if (chip == -1)
- nfc_writel(host->nfc->hsmc_regs, CTRL, NFC_CTRL_DISABLE);
- else
- nfc_writel(host->nfc->hsmc_regs, CTRL, NFC_CTRL_ENABLE);
-}
-
-static int nfc_make_addr(struct mtd_info *mtd, int command, int column,
- int page_addr, unsigned int *addr1234, unsigned int *cycle0)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
-
- int acycle = 0;
- unsigned char addr_bytes[8];
- int index = 0, bit_shift;
-
- BUG_ON(addr1234 == NULL || cycle0 == NULL);
-
- *cycle0 = 0;
- *addr1234 = 0;
-
- if (column != -1) {
- if (chip->options & NAND_BUSWIDTH_16 &&
- !nand_opcode_8bits(command))
- column >>= 1;
- addr_bytes[acycle++] = column & 0xff;
- if (mtd->writesize > 512)
- addr_bytes[acycle++] = (column >> 8) & 0xff;
- }
-
- if (page_addr != -1) {
- addr_bytes[acycle++] = page_addr & 0xff;
- addr_bytes[acycle++] = (page_addr >> 8) & 0xff;
- if (chip->chipsize > (128 << 20))
- addr_bytes[acycle++] = (page_addr >> 16) & 0xff;
- }
-
- if (acycle > 4)
- *cycle0 = addr_bytes[index++];
-
- for (bit_shift = 0; index < acycle; bit_shift += 8)
- *addr1234 += addr_bytes[index++] << bit_shift;
-
- /* return acycle in cmd register */
- return acycle << NFCADDR_CMD_ACYCLE_BIT_POS;
-}
-
-static void nfc_nand_command(struct mtd_info *mtd, unsigned int command,
- int column, int page_addr)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- unsigned long timeout;
- unsigned int nfc_addr_cmd = 0;
-
- unsigned int cmd1 = command << NFCADDR_CMD_CMD1_BIT_POS;
-
- /* Set default settings: no cmd2, no addr cycle. read from nand */
- unsigned int cmd2 = 0;
- unsigned int vcmd2 = 0;
- int acycle = NFCADDR_CMD_ACYCLE_NONE;
- int csid = NFCADDR_CMD_CSID_3;
- int dataen = NFCADDR_CMD_DATADIS;
- int nfcwr = NFCADDR_CMD_NFCRD;
- unsigned int addr1234 = 0;
- unsigned int cycle0 = 0;
- bool do_addr = true;
- host->nfc->data_in_sram = NULL;
-
- dev_dbg(host->dev, "%s: cmd = 0x%02x, col = 0x%08x, page = 0x%08x\n",
- __func__, command, column, page_addr);
-
- switch (command) {
- case NAND_CMD_RESET:
- nfc_addr_cmd = cmd1 | acycle | csid | dataen | nfcwr;
- nfc_send_command(host, nfc_addr_cmd, addr1234, cycle0);
- udelay(chip->chip_delay);
-
- nfc_nand_command(mtd, NAND_CMD_STATUS, -1, -1);
- timeout = jiffies + msecs_to_jiffies(NFC_TIME_OUT_MS);
- while (!(chip->read_byte(mtd) & NAND_STATUS_READY)) {
- if (time_after(jiffies, timeout)) {
- dev_err(host->dev,
- "Time out to wait status ready!\n");
- break;
- }
- }
- return;
- case NAND_CMD_STATUS:
- do_addr = false;
- break;
- case NAND_CMD_PARAM:
- case NAND_CMD_READID:
- do_addr = false;
- acycle = NFCADDR_CMD_ACYCLE_1;
- if (column != -1)
- addr1234 = column;
- break;
- case NAND_CMD_RNDOUT:
- cmd2 = NAND_CMD_RNDOUTSTART << NFCADDR_CMD_CMD2_BIT_POS;
- vcmd2 = NFCADDR_CMD_VCMD2;
- break;
- case NAND_CMD_READ0:
- case NAND_CMD_READOOB:
- if (command == NAND_CMD_READOOB) {
- column += mtd->writesize;
- command = NAND_CMD_READ0; /* only READ0 is valid */
- cmd1 = command << NFCADDR_CMD_CMD1_BIT_POS;
- }
- if (host->nfc->use_nfc_sram) {
- /* Enable Data transfer to sram */
- dataen = NFCADDR_CMD_DATAEN;
-
- /* Need enable PMECC now, since NFC will transfer
- * data in bus after sending nfc read command.
- */
- if (chip->ecc.mode == NAND_ECC_HW && host->has_pmecc)
- pmecc_enable(host, NAND_ECC_READ);
- }
-
- cmd2 = NAND_CMD_READSTART << NFCADDR_CMD_CMD2_BIT_POS;
- vcmd2 = NFCADDR_CMD_VCMD2;
- break;
- /* For prgramming command, the cmd need set to write enable */
- case NAND_CMD_PAGEPROG:
- case NAND_CMD_SEQIN:
- case NAND_CMD_RNDIN:
- nfcwr = NFCADDR_CMD_NFCWR;
- if (host->nfc->will_write_sram && command == NAND_CMD_SEQIN)
- dataen = NFCADDR_CMD_DATAEN;
- break;
- default:
- break;
- }
-
- if (do_addr)
- acycle = nfc_make_addr(mtd, command, column, page_addr,
- &addr1234, &cycle0);
-
- nfc_addr_cmd = cmd1 | cmd2 | vcmd2 | acycle | csid | dataen | nfcwr;
- nfc_send_command(host, nfc_addr_cmd, addr1234, cycle0);
-
- /*
- * Program and erase have their own busy handlers status, sequential
- * in, and deplete1 need no delay.
- */
- switch (command) {
- case NAND_CMD_CACHEDPROG:
- case NAND_CMD_PAGEPROG:
- case NAND_CMD_ERASE1:
- case NAND_CMD_ERASE2:
- case NAND_CMD_RNDIN:
- case NAND_CMD_STATUS:
- case NAND_CMD_RNDOUT:
- case NAND_CMD_SEQIN:
- case NAND_CMD_READID:
- return;
-
- case NAND_CMD_READ0:
- if (dataen == NFCADDR_CMD_DATAEN) {
- host->nfc->data_in_sram = host->nfc->sram_bank0 +
- nfc_get_sram_off(host);
- return;
- }
- /* fall through */
- default:
- nfc_prepare_interrupt(host, NFC_SR_RB_EDGE);
- nfc_wait_interrupt(host, NFC_SR_RB_EDGE);
- }
-}
-
-static int nfc_sram_write_page(struct mtd_info *mtd, struct nand_chip *chip,
- uint32_t offset, int data_len, const uint8_t *buf,
- int oob_required, int page, int cached, int raw)
-{
- int cfg, len;
- int status = 0;
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- void *sram = host->nfc->sram_bank0 + nfc_get_sram_off(host);
-
- /* Subpage write is not supported */
- if (offset || (data_len < mtd->writesize))
- return -EINVAL;
-
- len = mtd->writesize;
- /* Copy page data to sram that will write to nand via NFC */
- if (use_dma) {
- if (atmel_nand_dma_op(mtd, (void *)buf, len, 0) != 0)
- /* Fall back to use cpu copy */
- memcpy(sram, buf, len);
- } else {
- memcpy(sram, buf, len);
- }
-
- cfg = nfc_readl(host->nfc->hsmc_regs, CFG);
- if (unlikely(raw) && oob_required) {
- memcpy(sram + len, chip->oob_poi, mtd->oobsize);
- len += mtd->oobsize;
- nfc_writel(host->nfc->hsmc_regs, CFG, cfg | NFC_CFG_WSPARE);
- } else {
- nfc_writel(host->nfc->hsmc_regs, CFG, cfg & ~NFC_CFG_WSPARE);
- }
-
- if (chip->ecc.mode == NAND_ECC_HW && host->has_pmecc)
- /*
- * When use NFC sram, need set up PMECC before send
- * NAND_CMD_SEQIN command. Since when the nand command
- * is sent, nfc will do transfer from sram and nand.
- */
- pmecc_enable(host, NAND_ECC_WRITE);
-
- host->nfc->will_write_sram = true;
- chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page);
- host->nfc->will_write_sram = false;
-
- if (likely(!raw))
- /* Need to write ecc into oob */
- status = chip->ecc.write_page(mtd, chip, buf, oob_required,
- page);
-
- if (status < 0)
- return status;
-
- chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
- status = chip->waitfunc(mtd, chip);
-
- if ((status & NAND_STATUS_FAIL) && (chip->errstat))
- status = chip->errstat(mtd, chip, FL_WRITING, status, page);
-
- if (status & NAND_STATUS_FAIL)
- return -EIO;
-
- return 0;
-}
-
-static int nfc_sram_init(struct mtd_info *mtd)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
- struct atmel_nand_host *host = nand_get_controller_data(chip);
- int res = 0;
-
- /* Initialize the NFC CFG register */
- unsigned int cfg_nfc = 0;
-
- /* set page size and oob layout */
- switch (mtd->writesize) {
- case 512:
- cfg_nfc = NFC_CFG_PAGESIZE_512;
- break;
- case 1024:
- cfg_nfc = NFC_CFG_PAGESIZE_1024;
- break;
- case 2048:
- cfg_nfc = NFC_CFG_PAGESIZE_2048;
- break;
- case 4096:
- cfg_nfc = NFC_CFG_PAGESIZE_4096;
- break;
- case 8192:
- cfg_nfc = NFC_CFG_PAGESIZE_8192;
- break;
- default:
- dev_err(host->dev, "Unsupported page size for NFC.\n");
- res = -ENXIO;
- return res;
- }
-
- /* oob bytes size = (NFCSPARESIZE + 1) * 4
- * Max support spare size is 512 bytes. */
- cfg_nfc |= (((mtd->oobsize / 4) - 1) << NFC_CFG_NFC_SPARESIZE_BIT_POS
- & NFC_CFG_NFC_SPARESIZE);
- /* default set a max timeout */
- cfg_nfc |= NFC_CFG_RSPARE |
- NFC_CFG_NFC_DTOCYC | NFC_CFG_NFC_DTOMUL;
-
- nfc_writel(host->nfc->hsmc_regs, CFG, cfg_nfc);
-
- host->nfc->will_write_sram = false;
- nfc_set_sram_bank(host, 0);
-
- /* Use Write page with NFC SRAM only for PMECC or ECC NONE. */
- if (host->nfc->write_by_sram) {
- if ((chip->ecc.mode == NAND_ECC_HW && host->has_pmecc) ||
- chip->ecc.mode == NAND_ECC_NONE)
- chip->write_page = nfc_sram_write_page;
- else
- host->nfc->write_by_sram = false;
- }
-
- dev_info(host->dev, "Using NFC Sram read %s\n",
- host->nfc->write_by_sram ? "and write" : "");
- return 0;
-}
-
-static struct platform_driver atmel_nand_nfc_driver;
-/*
- * Probe for the NAND device.
- */
-static int atmel_nand_probe(struct platform_device *pdev)
-{
- struct atmel_nand_host *host;
- struct mtd_info *mtd;
- struct nand_chip *nand_chip;
- struct resource *mem;
- int res, irq;
-
- /* Allocate memory for the device structure (and zero it) */
- host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
- if (!host)
- return -ENOMEM;
-
- res = platform_driver_register(&atmel_nand_nfc_driver);
- if (res)
- dev_err(&pdev->dev, "atmel_nand: can't register NFC driver\n");
-
- mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- host->io_base = devm_ioremap_resource(&pdev->dev, mem);
- if (IS_ERR(host->io_base)) {
- res = PTR_ERR(host->io_base);
- goto err_nand_ioremap;
- }
- host->io_phys = (dma_addr_t)mem->start;
-
- nand_chip = &host->nand_chip;
- mtd = nand_to_mtd(nand_chip);
- host->dev = &pdev->dev;
- if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node) {
- nand_set_flash_node(nand_chip, pdev->dev.of_node);
- /* Only when CONFIG_OF is enabled of_node can be parsed */
- res = atmel_of_init_port(host, pdev->dev.of_node);
- if (res)
- goto err_nand_ioremap;
- } else {
- memcpy(&host->board, dev_get_platdata(&pdev->dev),
- sizeof(struct atmel_nand_data));
- nand_chip->ecc.mode = host->board.ecc_mode;
-
- /*
- * When using software ECC every supported avr32 board means
- * Hamming algorithm. If that ever changes we'll need to add
- * ecc_algo field to the struct atmel_nand_data.
- */
- if (nand_chip->ecc.mode == NAND_ECC_SOFT)
- nand_chip->ecc.algo = NAND_ECC_HAMMING;
-
- /* 16-bit bus width */
- if (host->board.bus_width_16)
- nand_chip->options |= NAND_BUSWIDTH_16;
- }
-
- /* link the private data structures */
- nand_set_controller_data(nand_chip, host);
- mtd->dev.parent = &pdev->dev;
-
- /* Set address of NAND IO lines */
- nand_chip->IO_ADDR_R = host->io_base;
- nand_chip->IO_ADDR_W = host->io_base;
-
- if (nand_nfc.is_initialized) {
- /* NFC driver is probed and initialized */
- host->nfc = &nand_nfc;
-
- nand_chip->select_chip = nfc_select_chip;
- nand_chip->dev_ready = nfc_device_ready;
- nand_chip->cmdfunc = nfc_nand_command;
-
- /* Initialize the interrupt for NFC */
- irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(host->dev, "Cannot get HSMC irq!\n");
- res = irq;
- goto err_nand_ioremap;
- }
-
- res = devm_request_irq(&pdev->dev, irq, hsmc_interrupt,
- 0, "hsmc", host);
- if (res) {
- dev_err(&pdev->dev, "Unable to request HSMC irq %d\n",
- irq);
- goto err_nand_ioremap;
- }
- } else {
- res = atmel_nand_set_enable_ready_pins(mtd);
- if (res)
- goto err_nand_ioremap;
-
- nand_chip->cmd_ctrl = atmel_nand_cmd_ctrl;
- }
-
- nand_chip->chip_delay = 40; /* 40us command delay time */
-
-
- nand_chip->read_buf = atmel_read_buf;
- nand_chip->write_buf = atmel_write_buf;
-
- platform_set_drvdata(pdev, host);
- atmel_nand_enable(host);
-
- if (gpio_is_valid(host->board.det_pin)) {
- res = devm_gpio_request(&pdev->dev,
- host->board.det_pin, "nand_det");
- if (res < 0) {
- dev_err(&pdev->dev,
- "can't request det gpio %d\n",
- host->board.det_pin);
- goto err_no_card;
- }
-
- res = gpio_direction_input(host->board.det_pin);
- if (res < 0) {
- dev_err(&pdev->dev,
- "can't request input direction det gpio %d\n",
- host->board.det_pin);
- goto err_no_card;
- }
-
- if (gpio_get_value(host->board.det_pin)) {
- dev_info(&pdev->dev, "No SmartMedia card inserted.\n");
- res = -ENXIO;
- goto err_no_card;
- }
- }
-
- if (!host->board.has_dma)
- use_dma = 0;
-
- if (use_dma) {
- dma_cap_mask_t mask;
-
- dma_cap_zero(mask);
- dma_cap_set(DMA_MEMCPY, mask);
- host->dma_chan = dma_request_channel(mask, NULL, NULL);
- if (!host->dma_chan) {
- dev_err(host->dev, "Failed to request DMA channel\n");
- use_dma = 0;
- }
- }
- if (use_dma)
- dev_info(host->dev, "Using %s for DMA transfers.\n",
- dma_chan_name(host->dma_chan));
- else
- dev_info(host->dev, "No DMA support for NAND access.\n");
-
- /* first scan to find the device and get the page size */
- res = nand_scan_ident(mtd, 1, NULL);
- if (res)
- goto err_scan_ident;
-
- if (host->board.on_flash_bbt || on_flash_bbt)
- nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
-
- if (nand_chip->bbt_options & NAND_BBT_USE_FLASH)
- dev_info(&pdev->dev, "Use On Flash BBT\n");
-
- if (IS_ENABLED(CONFIG_OF) && pdev->dev.of_node) {
- res = atmel_of_init_ecc(host, pdev->dev.of_node);
- if (res)
- goto err_hw_ecc;
- }
-
- if (nand_chip->ecc.mode == NAND_ECC_HW) {
- if (host->has_pmecc)
- res = atmel_pmecc_nand_init_params(pdev, host);
- else
- res = atmel_hw_nand_init_params(pdev, host);
-
- if (res != 0)
- goto err_hw_ecc;
- }
-
- /* initialize the nfc configuration register */
- if (host->nfc && host->nfc->use_nfc_sram) {
- res = nfc_sram_init(mtd);
- if (res) {
- host->nfc->use_nfc_sram = false;
- dev_err(host->dev, "Disable use nfc sram for data transfer.\n");
- }
- }
-
- /* second phase scan */
- res = nand_scan_tail(mtd);
- if (res)
- goto err_scan_tail;
-
- mtd->name = "atmel_nand";
- res = mtd_device_register(mtd, host->board.parts,
- host->board.num_parts);
- if (!res)
- return res;
-
-err_scan_tail:
- if (host->has_pmecc && host->nand_chip.ecc.mode == NAND_ECC_HW)
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_DISABLE);
-err_hw_ecc:
-err_scan_ident:
-err_no_card:
- atmel_nand_disable(host);
- if (host->dma_chan)
- dma_release_channel(host->dma_chan);
-err_nand_ioremap:
- return res;
-}
-
-/*
- * Remove a NAND device.
- */
-static int atmel_nand_remove(struct platform_device *pdev)
-{
- struct atmel_nand_host *host = platform_get_drvdata(pdev);
- struct mtd_info *mtd = nand_to_mtd(&host->nand_chip);
-
- nand_release(mtd);
-
- atmel_nand_disable(host);
-
- if (host->has_pmecc && host->nand_chip.ecc.mode == NAND_ECC_HW) {
- pmecc_writel(host->ecc, CTRL, PMECC_CTRL_DISABLE);
- pmerrloc_writel(host->pmerrloc_base, ELDIS,
- PMERRLOC_DISABLE);
- }
-
- if (host->dma_chan)
- dma_release_channel(host->dma_chan);
-
- platform_driver_unregister(&atmel_nand_nfc_driver);
-
- return 0;
-}
-
-/*
- * AT91RM9200 does not have PMECC or PMECC Errloc peripherals for
- * BCH ECC. Combined with the "atmel,has-pmecc", it is used to describe
- * devices from the SAM9 family that have those.
- */
-static const struct atmel_nand_caps at91rm9200_caps = {
- .pmecc_correct_erase_page = false,
- .pmecc_max_correction = 24,
-};
-
-static const struct atmel_nand_caps sama5d4_caps = {
- .pmecc_correct_erase_page = true,
- .pmecc_max_correction = 24,
-};
-
-/*
- * The PMECC Errloc controller starting in SAMA5D2 is not compatible,
- * as the increased correction strength requires more registers.
- */
-static const struct atmel_nand_caps sama5d2_caps = {
- .pmecc_correct_erase_page = true,
- .pmecc_max_correction = 32,
-};
-
-static const struct of_device_id atmel_nand_dt_ids[] = {
- { .compatible = "atmel,at91rm9200-nand", .data = &at91rm9200_caps },
- { .compatible = "atmel,sama5d4-nand", .data = &sama5d4_caps },
- { .compatible = "atmel,sama5d2-nand", .data = &sama5d2_caps },
- { /* sentinel */ }
-};
-
-MODULE_DEVICE_TABLE(of, atmel_nand_dt_ids);
-
-static int atmel_nand_nfc_probe(struct platform_device *pdev)
-{
- struct atmel_nfc *nfc = &nand_nfc;
- struct resource *nfc_cmd_regs, *nfc_hsmc_regs, *nfc_sram;
- int ret;
-
- nfc_cmd_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- nfc->base_cmd_regs = devm_ioremap_resource(&pdev->dev, nfc_cmd_regs);
- if (IS_ERR(nfc->base_cmd_regs))
- return PTR_ERR(nfc->base_cmd_regs);
-
- nfc_hsmc_regs = platform_get_resource(pdev, IORESOURCE_MEM, 1);
- nfc->hsmc_regs = devm_ioremap_resource(&pdev->dev, nfc_hsmc_regs);
- if (IS_ERR(nfc->hsmc_regs))
- return PTR_ERR(nfc->hsmc_regs);
-
- nfc_sram = platform_get_resource(pdev, IORESOURCE_MEM, 2);
- if (nfc_sram) {
- nfc->sram_bank0 = (void * __force)
- devm_ioremap_resource(&pdev->dev, nfc_sram);
- if (IS_ERR(nfc->sram_bank0)) {
- dev_warn(&pdev->dev, "Fail to ioremap the NFC sram with error: %ld. So disable NFC sram.\n",
- PTR_ERR(nfc->sram_bank0));
- } else {
- nfc->use_nfc_sram = true;
- nfc->sram_bank0_phys = (dma_addr_t)nfc_sram->start;
-
- if (pdev->dev.of_node)
- nfc->write_by_sram = of_property_read_bool(
- pdev->dev.of_node,
- "atmel,write-by-sram");
- }
- }
-
- nfc_writel(nfc->hsmc_regs, IDR, 0xffffffff);
- nfc_readl(nfc->hsmc_regs, SR); /* clear the NFC_SR */
-
- nfc->clk = devm_clk_get(&pdev->dev, NULL);
- if (!IS_ERR(nfc->clk)) {
- ret = clk_prepare_enable(nfc->clk);
- if (ret)
- return ret;
- } else {
- dev_warn(&pdev->dev, "NFC clock missing, update your Device Tree");
- }
-
- nfc->is_initialized = true;
- dev_info(&pdev->dev, "NFC is probed.\n");
-
- return 0;
-}
-
-static int atmel_nand_nfc_remove(struct platform_device *pdev)
-{
- struct atmel_nfc *nfc = &nand_nfc;
-
- if (!IS_ERR(nfc->clk))
- clk_disable_unprepare(nfc->clk);
-
- return 0;
-}
-
-static const struct of_device_id atmel_nand_nfc_match[] = {
- { .compatible = "atmel,sama5d3-nfc" },
- { /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, atmel_nand_nfc_match);
-
-static struct platform_driver atmel_nand_nfc_driver = {
- .driver = {
- .name = "atmel_nand_nfc",
- .of_match_table = of_match_ptr(atmel_nand_nfc_match),
- },
- .probe = atmel_nand_nfc_probe,
- .remove = atmel_nand_nfc_remove,
-};
-
-static struct platform_driver atmel_nand_driver = {
- .probe = atmel_nand_probe,
- .remove = atmel_nand_remove,
- .driver = {
- .name = "atmel_nand",
- .of_match_table = of_match_ptr(atmel_nand_dt_ids),
- },
-};
-
-module_platform_driver(atmel_nand_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Rick Bronson");
-MODULE_DESCRIPTION("NAND/SmartMedia driver for AT91 / AVR32");
-MODULE_ALIAS("platform:atmel_nand");
+++ /dev/null
-/*
- * Error Corrected Code Controller (ECC) - System peripherals regsters.
- * Based on AT91SAM9260 datasheet revision B.
- *
- * Copyright (C) 2007 Andrew Victor
- * Copyright (C) 2007 - 2012 Atmel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- */
-
-#ifndef ATMEL_NAND_ECC_H
-#define ATMEL_NAND_ECC_H
-
-#define ATMEL_ECC_CR 0x00 /* Control register */
-#define ATMEL_ECC_RST (1 << 0) /* Reset parity */
-
-#define ATMEL_ECC_MR 0x04 /* Mode register */
-#define ATMEL_ECC_PAGESIZE (3 << 0) /* Page Size */
-#define ATMEL_ECC_PAGESIZE_528 (0)
-#define ATMEL_ECC_PAGESIZE_1056 (1)
-#define ATMEL_ECC_PAGESIZE_2112 (2)
-#define ATMEL_ECC_PAGESIZE_4224 (3)
-
-#define ATMEL_ECC_SR 0x08 /* Status register */
-#define ATMEL_ECC_RECERR (1 << 0) /* Recoverable Error */
-#define ATMEL_ECC_ECCERR (1 << 1) /* ECC Single Bit Error */
-#define ATMEL_ECC_MULERR (1 << 2) /* Multiple Errors */
-
-#define ATMEL_ECC_PR 0x0c /* Parity register */
-#define ATMEL_ECC_BITADDR (0xf << 0) /* Bit Error Address */
-#define ATMEL_ECC_WORDADDR (0xfff << 4) /* Word Error Address */
-
-#define ATMEL_ECC_NPR 0x10 /* NParity register */
-#define ATMEL_ECC_NPARITY (0xffff << 0) /* NParity */
-
-/* PMECC Register Definitions */
-#define ATMEL_PMECC_CFG 0x000 /* Configuration Register */
-#define PMECC_CFG_BCH_ERR2 (0 << 0)
-#define PMECC_CFG_BCH_ERR4 (1 << 0)
-#define PMECC_CFG_BCH_ERR8 (2 << 0)
-#define PMECC_CFG_BCH_ERR12 (3 << 0)
-#define PMECC_CFG_BCH_ERR24 (4 << 0)
-#define PMECC_CFG_BCH_ERR32 (5 << 0)
-
-#define PMECC_CFG_SECTOR512 (0 << 4)
-#define PMECC_CFG_SECTOR1024 (1 << 4)
-
-#define PMECC_CFG_PAGE_1SECTOR (0 << 8)
-#define PMECC_CFG_PAGE_2SECTORS (1 << 8)
-#define PMECC_CFG_PAGE_4SECTORS (2 << 8)
-#define PMECC_CFG_PAGE_8SECTORS (3 << 8)
-
-#define PMECC_CFG_READ_OP (0 << 12)
-#define PMECC_CFG_WRITE_OP (1 << 12)
-
-#define PMECC_CFG_SPARE_ENABLE (1 << 16)
-#define PMECC_CFG_SPARE_DISABLE (0 << 16)
-
-#define PMECC_CFG_AUTO_ENABLE (1 << 20)
-#define PMECC_CFG_AUTO_DISABLE (0 << 20)
-
-#define ATMEL_PMECC_SAREA 0x004 /* Spare area size */
-#define ATMEL_PMECC_SADDR 0x008 /* PMECC starting address */
-#define ATMEL_PMECC_EADDR 0x00c /* PMECC ending address */
-#define ATMEL_PMECC_CLK 0x010 /* PMECC clock control */
-#define PMECC_CLK_133MHZ (2 << 0)
-
-#define ATMEL_PMECC_CTRL 0x014 /* PMECC control register */
-#define PMECC_CTRL_RST (1 << 0)
-#define PMECC_CTRL_DATA (1 << 1)
-#define PMECC_CTRL_USER (1 << 2)
-#define PMECC_CTRL_ENABLE (1 << 4)
-#define PMECC_CTRL_DISABLE (1 << 5)
-
-#define ATMEL_PMECC_SR 0x018 /* PMECC status register */
-#define PMECC_SR_BUSY (1 << 0)
-#define PMECC_SR_ENABLE (1 << 4)
-
-#define ATMEL_PMECC_IER 0x01c /* PMECC interrupt enable */
-#define PMECC_IER_ENABLE (1 << 0)
-#define ATMEL_PMECC_IDR 0x020 /* PMECC interrupt disable */
-#define PMECC_IER_DISABLE (1 << 0)
-#define ATMEL_PMECC_IMR 0x024 /* PMECC interrupt mask */
-#define PMECC_IER_MASK (1 << 0)
-#define ATMEL_PMECC_ISR 0x028 /* PMECC interrupt status */
-#define ATMEL_PMECC_ECCx 0x040 /* PMECC ECC x */
-#define ATMEL_PMECC_REMx 0x240 /* PMECC REM x */
-
-/* PMERRLOC Register Definitions */
-#define ATMEL_PMERRLOC_ELCFG 0x000 /* Error location config */
-#define PMERRLOC_ELCFG_SECTOR_512 (0 << 0)
-#define PMERRLOC_ELCFG_SECTOR_1024 (1 << 0)
-#define PMERRLOC_ELCFG_NUM_ERRORS(n) ((n) << 16)
-
-#define ATMEL_PMERRLOC_ELPRIM 0x004 /* Error location primitive */
-#define ATMEL_PMERRLOC_ELEN 0x008 /* Error location enable */
-#define ATMEL_PMERRLOC_ELDIS 0x00c /* Error location disable */
-#define PMERRLOC_DISABLE (1 << 0)
-
-#define ATMEL_PMERRLOC_ELSR 0x010 /* Error location status */
-#define PMERRLOC_ELSR_BUSY (1 << 0)
-#define ATMEL_PMERRLOC_ELIER 0x014 /* Error location int enable */
-#define ATMEL_PMERRLOC_ELIDR 0x018 /* Error location int disable */
-#define ATMEL_PMERRLOC_ELIMR 0x01c /* Error location int mask */
-#define ATMEL_PMERRLOC_ELISR 0x020 /* Error location int status */
-#define PMERRLOC_ERR_NUM_MASK (0x1f << 8)
-#define PMERRLOC_CALC_DONE (1 << 0)
-#define ATMEL_PMERRLOC_SIGMAx 0x028 /* Error location SIGMA x */
-
-/*
- * The ATMEL_PMERRLOC_ELx register location depends from the number of
- * bits corrected by the PMECC controller. Do not use it.
- */
-
-/* Register access macros for PMECC */
-#define pmecc_readl_relaxed(addr, reg) \
- readl_relaxed((addr) + ATMEL_PMECC_##reg)
-
-#define pmecc_writel(addr, reg, value) \
- writel((value), (addr) + ATMEL_PMECC_##reg)
-
-#define pmecc_readb_ecc_relaxed(addr, sector, n) \
- readb_relaxed((addr) + ATMEL_PMECC_ECCx + ((sector) * 0x40) + (n))
-
-#define pmecc_readl_rem_relaxed(addr, sector, n) \
- readl_relaxed((addr) + ATMEL_PMECC_REMx + ((sector) * 0x40) + ((n) * 4))
-
-#define pmerrloc_readl_relaxed(addr, reg) \
- readl_relaxed((addr) + ATMEL_PMERRLOC_##reg)
-
-#define pmerrloc_writel(addr, reg, value) \
- writel((value), (addr) + ATMEL_PMERRLOC_##reg)
-
-#define pmerrloc_writel_sigma_relaxed(addr, n, value) \
- writel_relaxed((value), (addr) + ATMEL_PMERRLOC_SIGMAx + ((n) * 4))
-
-#define pmerrloc_readl_sigma_relaxed(addr, n) \
- readl_relaxed((addr) + ATMEL_PMERRLOC_SIGMAx + ((n) * 4))
-
-#define pmerrloc_readl_el_relaxed(addr, n) \
- readl_relaxed((addr) + ((n) * 4))
-
-/* Galois field dimension */
-#define PMECC_GF_DIMENSION_13 13
-#define PMECC_GF_DIMENSION_14 14
-
-/* Primitive Polynomial used by PMECC */
-#define PMECC_GF_13_PRIMITIVE_POLY 0x201b
-#define PMECC_GF_14_PRIMITIVE_POLY 0x4443
-
-#define PMECC_LOOKUP_TABLE_SIZE_512 0x2000
-#define PMECC_LOOKUP_TABLE_SIZE_1024 0x4000
-
-/* Time out value for reading PMECC status register */
-#define PMECC_MAX_TIMEOUT_MS 100
-
-/* Reserved bytes in oob area */
-#define PMECC_OOB_RESERVED_BYTES 2
-
-#endif
+++ /dev/null
-/*
- * Atmel Nand Flash Controller (NFC) - System peripherals regsters.
- * Based on SAMA5D3 datasheet.
- *
- * © Copyright 2013 Atmel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or (at your
- * option) any later version.
- */
-
-#ifndef ATMEL_NAND_NFC_H
-#define ATMEL_NAND_NFC_H
-
-/*
- * HSMC NFC registers
- */
-#define ATMEL_HSMC_NFC_CFG 0x00 /* NFC Configuration Register */
-#define NFC_CFG_PAGESIZE (7 << 0)
-#define NFC_CFG_PAGESIZE_512 (0 << 0)
-#define NFC_CFG_PAGESIZE_1024 (1 << 0)
-#define NFC_CFG_PAGESIZE_2048 (2 << 0)
-#define NFC_CFG_PAGESIZE_4096 (3 << 0)
-#define NFC_CFG_PAGESIZE_8192 (4 << 0)
-#define NFC_CFG_WSPARE (1 << 8)
-#define NFC_CFG_RSPARE (1 << 9)
-#define NFC_CFG_NFC_DTOCYC (0xf << 16)
-#define NFC_CFG_NFC_DTOMUL (0x7 << 20)
-#define NFC_CFG_NFC_SPARESIZE (0x7f << 24)
-#define NFC_CFG_NFC_SPARESIZE_BIT_POS 24
-
-#define ATMEL_HSMC_NFC_CTRL 0x04 /* NFC Control Register */
-#define NFC_CTRL_ENABLE (1 << 0)
-#define NFC_CTRL_DISABLE (1 << 1)
-
-#define ATMEL_HSMC_NFC_SR 0x08 /* NFC Status Register */
-#define NFC_SR_BUSY (1 << 8)
-#define NFC_SR_XFR_DONE (1 << 16)
-#define NFC_SR_CMD_DONE (1 << 17)
-#define NFC_SR_DTOE (1 << 20)
-#define NFC_SR_UNDEF (1 << 21)
-#define NFC_SR_AWB (1 << 22)
-#define NFC_SR_ASE (1 << 23)
-#define NFC_SR_RB_EDGE (1 << 24)
-
-#define ATMEL_HSMC_NFC_IER 0x0c
-#define ATMEL_HSMC_NFC_IDR 0x10
-#define ATMEL_HSMC_NFC_IMR 0x14
-#define ATMEL_HSMC_NFC_CYCLE0 0x18 /* NFC Address Cycle Zero */
-#define ATMEL_HSMC_NFC_ADDR_CYCLE0 (0xff)
-
-#define ATMEL_HSMC_NFC_BANK 0x1c /* NFC Bank Register */
-#define ATMEL_HSMC_NFC_BANK0 (0 << 0)
-#define ATMEL_HSMC_NFC_BANK1 (1 << 0)
-
-#define nfc_writel(addr, reg, value) \
- writel((value), (addr) + ATMEL_HSMC_NFC_##reg)
-
-#define nfc_readl(addr, reg) \
- readl_relaxed((addr) + ATMEL_HSMC_NFC_##reg)
-
-/*
- * NFC Address Command definitions
- */
-#define NFCADDR_CMD_CMD1 (0xff << 2) /* Command for Cycle 1 */
-#define NFCADDR_CMD_CMD1_BIT_POS 2
-#define NFCADDR_CMD_CMD2 (0xff << 10) /* Command for Cycle 2 */
-#define NFCADDR_CMD_CMD2_BIT_POS 10
-#define NFCADDR_CMD_VCMD2 (0x1 << 18) /* Valid Cycle 2 Command */
-#define NFCADDR_CMD_ACYCLE (0x7 << 19) /* Number of Address required */
-#define NFCADDR_CMD_ACYCLE_NONE (0x0 << 19)
-#define NFCADDR_CMD_ACYCLE_1 (0x1 << 19)
-#define NFCADDR_CMD_ACYCLE_2 (0x2 << 19)
-#define NFCADDR_CMD_ACYCLE_3 (0x3 << 19)
-#define NFCADDR_CMD_ACYCLE_4 (0x4 << 19)
-#define NFCADDR_CMD_ACYCLE_5 (0x5 << 19)
-#define NFCADDR_CMD_ACYCLE_BIT_POS 19
-#define NFCADDR_CMD_CSID (0x7 << 22) /* Chip Select Identifier */
-#define NFCADDR_CMD_CSID_0 (0x0 << 22)
-#define NFCADDR_CMD_CSID_1 (0x1 << 22)
-#define NFCADDR_CMD_CSID_2 (0x2 << 22)
-#define NFCADDR_CMD_CSID_3 (0x3 << 22)
-#define NFCADDR_CMD_CSID_4 (0x4 << 22)
-#define NFCADDR_CMD_CSID_5 (0x5 << 22)
-#define NFCADDR_CMD_CSID_6 (0x6 << 22)
-#define NFCADDR_CMD_CSID_7 (0x7 << 22)
-#define NFCADDR_CMD_DATAEN (0x1 << 25) /* Data Transfer Enable */
-#define NFCADDR_CMD_DATADIS (0x0 << 25) /* Data Transfer Disable */
-#define NFCADDR_CMD_NFCRD (0x0 << 26) /* NFC Read Enable */
-#define NFCADDR_CMD_NFCWR (0x1 << 26) /* NFC Write Enable */
-#define NFCADDR_CMD_NFCBUSY (0x1 << 27) /* NFC Busy */
-
-#define nfc_cmd_addr1234_writel(cmd, addr1234, nfc_base) \
- writel((addr1234), (cmd) + nfc_base)
-
-#define nfc_cmd_readl(bitstatus, nfc_base) \
- readl_relaxed((bitstatus) + nfc_base)
-
-#define NFC_TIME_OUT_MS 100
-#define NFC_SRAM_BANK1_OFFSET 0x1200
-
-#endif
#define BRCMNAND_MIN_BLOCKSIZE (8 * 1024)
#define BRCMNAND_MIN_DEVSIZE (4ULL * 1024 * 1024)
+#define NAND_CTRL_RDY (INTFC_CTLR_READY | INTFC_FLASH_READY)
+#define NAND_POLL_STATUS_TIMEOUT_MS 100
+
/* Controller feature flags */
enum {
BRCMNAND_HAS_1K_SECTORS = BIT(0),
CS_SELECT_AUTO_DEVICE_ID_CFG = BIT(30),
};
+static int bcmnand_ctrl_poll_status(struct brcmnand_controller *ctrl,
+ u32 mask, u32 expected_val,
+ unsigned long timeout_ms)
+{
+ unsigned long limit;
+ u32 val;
+
+ if (!timeout_ms)
+ timeout_ms = NAND_POLL_STATUS_TIMEOUT_MS;
+
+ limit = jiffies + msecs_to_jiffies(timeout_ms);
+ do {
+ val = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
+ if ((val & mask) == expected_val)
+ return 0;
+
+ cpu_relax();
+ } while (time_after(limit, jiffies));
+
+ dev_warn(ctrl->dev, "timeout on status poll (expected %x got %x)\n",
+ expected_val, val & mask);
+
+ return -ETIMEDOUT;
+}
+
static inline void brcmnand_set_wp(struct brcmnand_controller *ctrl, bool en)
{
u32 val = en ? CS_SELECT_NAND_WP : 0;
if ((ctrl->features & BRCMNAND_HAS_WP) && wp_on == 1) {
static int old_wp = -1;
+ int ret;
if (old_wp != wp) {
dev_dbg(ctrl->dev, "WP %s\n", wp ? "on" : "off");
old_wp = wp;
}
+
+ /*
+ * make sure ctrl/flash ready before and after
+ * changing state of #WP pin
+ */
+ ret = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY |
+ NAND_STATUS_READY,
+ NAND_CTRL_RDY |
+ NAND_STATUS_READY, 0);
+ if (ret)
+ return;
+
brcmnand_set_wp(ctrl, wp);
+ chip->cmdfunc(mtd, NAND_CMD_STATUS, -1, -1);
+ /* NAND_STATUS_WP 0x00 = protected, 0x80 = not protected */
+ ret = bcmnand_ctrl_poll_status(ctrl,
+ NAND_CTRL_RDY |
+ NAND_STATUS_READY |
+ NAND_STATUS_WP,
+ NAND_CTRL_RDY |
+ NAND_STATUS_READY |
+ (wp ? 0 : NAND_STATUS_WP), 0);
+
+ if (ret)
+ dev_err_ratelimited(&host->pdev->dev,
+ "nand #WP expected %s\n",
+ wp ? "on" : "off");
}
}
static void brcmnand_send_cmd(struct brcmnand_host *host, int cmd)
{
struct brcmnand_controller *ctrl = host->ctrl;
- u32 intfc;
+ int ret;
dev_dbg(ctrl->dev, "send native cmd %d addr_lo 0x%x\n", cmd,
brcmnand_read_reg(ctrl, BRCMNAND_CMD_ADDRESS));
BUG_ON(ctrl->cmd_pending != 0);
ctrl->cmd_pending = cmd;
- intfc = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
- WARN_ON(!(intfc & INTFC_CTLR_READY));
+ ret = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0);
+ WARN_ON(ret);
mb(); /* flush previous writes */
brcmnand_write_reg(ctrl, BRCMNAND_CMD_START,
ret = gpio_request(GPIO_NAND_CS, "NAND CS");
if (ret) {
- pr_warning("CM-X270: failed to request NAND CS gpio\n");
+ pr_warn("CM-X270: failed to request NAND CS gpio\n");
return ret;
}
ret = gpio_request(GPIO_NAND_RB, "NAND R/B");
if (ret) {
- pr_warning("CM-X270: failed to request NAND R/B gpio\n");
+ pr_warn("CM-X270: failed to request NAND R/B gpio\n");
goto err_gpio_request;
}
"ti,davinci-nand-use-bbt"))
pdata->bbt_options = NAND_BBT_USE_FLASH;
+ /*
+ * Since kernel v4.8, this driver has been fixed to enable
+ * use of 4-bit hardware ECC with subpages and verified on
+ * TI's keystone EVMs (K2L, K2HK and K2E).
+ * However, in the interest of not breaking systems using
+ * existing UBI partitions, sub-page writes are not being
+ * (re)enabled. If you want to use subpage writes on Keystone
+ * platforms (i.e. do not have any existing UBI partitions),
+ * then use "ti,davinci-nand" as the compatible in your
+ * device-tree file.
+ */
if (of_device_is_compatible(pdev->dev.of_node,
"ti,keystone-nand")) {
pdata->options |= NAND_NO_SUBPAGE_WRITE;
* We define a macro here that combines all interrupts this driver uses into
* a single constant value, for convenience.
*/
-#define DENALI_IRQ_ALL (INTR_STATUS__DMA_CMD_COMP | \
- INTR_STATUS__ECC_TRANSACTION_DONE | \
- INTR_STATUS__ECC_ERR | \
- INTR_STATUS__PROGRAM_FAIL | \
- INTR_STATUS__LOAD_COMP | \
- INTR_STATUS__PROGRAM_COMP | \
- INTR_STATUS__TIME_OUT | \
- INTR_STATUS__ERASE_FAIL | \
- INTR_STATUS__RST_COMP | \
- INTR_STATUS__ERASE_COMP)
+#define DENALI_IRQ_ALL (INTR__DMA_CMD_COMP | \
+ INTR__ECC_TRANSACTION_DONE | \
+ INTR__ECC_ERR | \
+ INTR__PROGRAM_FAIL | \
+ INTR__LOAD_COMP | \
+ INTR__PROGRAM_COMP | \
+ INTR__TIME_OUT | \
+ INTR__ERASE_FAIL | \
+ INTR__RST_COMP | \
+ INTR__ERASE_COMP)
/*
* indicates whether or not the internal value for the flash bank is
*/
#define CHIP_SELECT_INVALID -1
-#define SUPPORT_8BITECC 1
-
/*
* This macro divides two integers and rounds fractional values up
* to the nearest integer value.
#define SPARE_ACCESS 0x41
#define MAIN_ACCESS 0x42
#define MAIN_SPARE_ACCESS 0x43
-#define PIPELINE_ACCESS 0x2000
#define DENALI_READ 0
#define DENALI_WRITE 0x100
-/* types of device accesses. We can issue commands and get status */
-#define COMMAND_CYCLE 0
-#define ADDR_CYCLE 1
-#define STATUS_CYCLE 2
-
/*
* this is a helper macro that allows us to
* format the bank into the proper bits for the controller
static void reset_bank(struct denali_nand_info *denali)
{
uint32_t irq_status;
- uint32_t irq_mask = INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT;
+ uint32_t irq_mask = INTR__RST_COMP | INTR__TIME_OUT;
clear_interrupts(denali);
irq_status = wait_for_irq(denali, irq_mask);
- if (irq_status & INTR_STATUS__TIME_OUT)
+ if (irq_status & INTR__TIME_OUT)
dev_err(denali->dev, "reset bank failed.\n");
}
int i;
for (i = 0; i < denali->max_banks; i++)
- iowrite32(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT,
+ iowrite32(INTR__RST_COMP | INTR__TIME_OUT,
denali->flash_reg + INTR_STATUS(i));
for (i = 0; i < denali->max_banks; i++) {
iowrite32(1 << i, denali->flash_reg + DEVICE_RESET);
while (!(ioread32(denali->flash_reg + INTR_STATUS(i)) &
- (INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT)))
+ (INTR__RST_COMP | INTR__TIME_OUT)))
cpu_relax();
if (ioread32(denali->flash_reg + INTR_STATUS(i)) &
- INTR_STATUS__TIME_OUT)
+ INTR__TIME_OUT)
dev_dbg(denali->dev,
"NAND Reset operation timed out on bank %d\n", i);
}
for (i = 0; i < denali->max_banks; i++)
- iowrite32(INTR_STATUS__RST_COMP | INTR_STATUS__TIME_OUT,
+ iowrite32(INTR__RST_COMP | INTR__TIME_OUT,
denali->flash_reg + INTR_STATUS(i));
return PASS;
static void get_toshiba_nand_para(struct denali_nand_info *denali)
{
- uint32_t tmp;
-
/*
* Workaround to fix a controller bug which reports a wrong
* spare area size for some kind of Toshiba NAND device
*/
if ((ioread32(denali->flash_reg + DEVICE_MAIN_AREA_SIZE) == 4096) &&
- (ioread32(denali->flash_reg + DEVICE_SPARE_AREA_SIZE) == 64)) {
+ (ioread32(denali->flash_reg + DEVICE_SPARE_AREA_SIZE) == 64))
iowrite32(216, denali->flash_reg + DEVICE_SPARE_AREA_SIZE);
- tmp = ioread32(denali->flash_reg + DEVICES_CONNECTED) *
- ioread32(denali->flash_reg + DEVICE_SPARE_AREA_SIZE);
- iowrite32(tmp,
- denali->flash_reg + LOGICAL_PAGE_SPARE_SIZE);
-#if SUPPORT_15BITECC
- iowrite32(15, denali->flash_reg + ECC_CORRECTION);
-#elif SUPPORT_8BITECC
- iowrite32(8, denali->flash_reg + ECC_CORRECTION);
-#endif
- }
}
static void get_hynix_nand_para(struct denali_nand_info *denali,
uint8_t device_id)
{
- uint32_t main_size, spare_size;
-
switch (device_id) {
case 0xD5: /* Hynix H27UAG8T2A, H27UBG8U5A or H27UCG8VFA */
case 0xD7: /* Hynix H27UDG8VEM, H27UCG8UDM or H27UCG8V5A */
iowrite32(128, denali->flash_reg + PAGES_PER_BLOCK);
iowrite32(4096, denali->flash_reg + DEVICE_MAIN_AREA_SIZE);
iowrite32(224, denali->flash_reg + DEVICE_SPARE_AREA_SIZE);
- main_size = 4096 *
- ioread32(denali->flash_reg + DEVICES_CONNECTED);
- spare_size = 224 *
- ioread32(denali->flash_reg + DEVICES_CONNECTED);
- iowrite32(main_size,
- denali->flash_reg + LOGICAL_PAGE_DATA_SIZE);
- iowrite32(spare_size,
- denali->flash_reg + LOGICAL_PAGE_SPARE_SIZE);
iowrite32(0, denali->flash_reg + DEVICE_WIDTH);
-#if SUPPORT_15BITECC
- iowrite32(15, denali->flash_reg + ECC_CORRECTION);
-#elif SUPPORT_8BITECC
- iowrite32(8, denali->flash_reg + ECC_CORRECTION);
-#endif
break;
default:
dev_warn(denali->dev,
static void detect_max_banks(struct denali_nand_info *denali)
{
uint32_t features = ioread32(denali->flash_reg + FEATURES);
- /*
- * Read the revision register, so we can calculate the max_banks
- * properly: the encoding changed from rev 5.0 to 5.1
- */
- u32 revision = MAKE_COMPARABLE_REVISION(
- ioread32(denali->flash_reg + REVISION));
- if (revision < REVISION_5_1)
- denali->max_banks = 2 << (features & FEATURES__N_BANKS);
- else
- denali->max_banks = 1 << (features & FEATURES__N_BANKS);
+ denali->max_banks = 1 << (features & FEATURES__N_BANKS);
+
+ /* the encoding changed from rev 5.0 to 5.1 */
+ if (denali->revision < 0x0501)
+ denali->max_banks <<= 1;
}
static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
spin_unlock(&denali->irq_lock);
return result;
}
-#define BANK(x) ((x) << 24)
static uint32_t wait_for_irq(struct denali_nand_info *denali, uint32_t irq_mask)
{
int access_type, int op)
{
int status = PASS;
- uint32_t page_count = 1;
- uint32_t addr, cmd, irq_status, irq_mask;
-
- if (op == DENALI_READ)
- irq_mask = INTR_STATUS__LOAD_COMP;
- else if (op == DENALI_WRITE)
- irq_mask = 0;
- else
- BUG();
+ uint32_t addr, cmd;
setup_ecc_for_xfer(denali, ecc_en, transfer_spare);
cmd = MODE_10 | addr;
index_addr(denali, cmd, access_type);
- /*
- * page 33 of the NAND controller spec indicates we should not
- * use the pipeline commands in Spare area only mode.
- * So we don't.
- */
- if (access_type == SPARE_ACCESS) {
- cmd = MODE_01 | addr;
- iowrite32(cmd, denali->flash_mem);
- } else {
- index_addr(denali, cmd,
- PIPELINE_ACCESS | op | page_count);
-
- /*
- * wait for command to be accepted
- * can always use status0 bit as the
- * mask is identical for each bank.
- */
- irq_status = wait_for_irq(denali, irq_mask);
-
- if (irq_status == 0) {
- dev_err(denali->dev,
- "cmd, page, addr on timeout (0x%x, 0x%x, 0x%x)\n",
- cmd, denali->page, addr);
- status = FAIL;
- } else {
- cmd = MODE_01 | addr;
- iowrite32(cmd, denali->flash_mem);
- }
- }
+ cmd = MODE_01 | addr;
+ iowrite32(cmd, denali->flash_mem);
}
return status;
}
{
struct denali_nand_info *denali = mtd_to_denali(mtd);
uint32_t irq_status;
- uint32_t irq_mask = INTR_STATUS__PROGRAM_COMP |
- INTR_STATUS__PROGRAM_FAIL;
+ uint32_t irq_mask = INTR__PROGRAM_COMP | INTR__PROGRAM_FAIL;
int status = 0;
denali->page = page;
static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
{
struct denali_nand_info *denali = mtd_to_denali(mtd);
- uint32_t irq_mask = INTR_STATUS__LOAD_COMP;
+ uint32_t irq_mask = INTR__LOAD_COMP;
uint32_t irq_status, addr, cmd;
denali->page = page;
}
}
-/*
- * this function examines buffers to see if they contain data that
- * indicate that the buffer is part of an erased region of flash.
- */
-static bool is_erased(uint8_t *buf, int len)
+static int denali_check_erased_page(struct mtd_info *mtd,
+ struct nand_chip *chip, uint8_t *buf,
+ unsigned long uncor_ecc_flags,
+ unsigned int max_bitflips)
{
- int i;
+ uint8_t *ecc_code = chip->buffers->ecccode;
+ int ecc_steps = chip->ecc.steps;
+ int ecc_size = chip->ecc.size;
+ int ecc_bytes = chip->ecc.bytes;
+ int i, ret, stat;
+
+ ret = mtd_ooblayout_get_eccbytes(mtd, ecc_code, chip->oob_poi, 0,
+ chip->ecc.total);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < ecc_steps; i++) {
+ if (!(uncor_ecc_flags & BIT(i)))
+ continue;
- for (i = 0; i < len; i++)
- if (buf[i] != 0xFF)
- return false;
- return true;
+ stat = nand_check_erased_ecc_chunk(buf, ecc_size,
+ ecc_code, ecc_bytes,
+ NULL, 0,
+ chip->ecc.strength);
+ if (stat < 0) {
+ mtd->ecc_stats.failed++;
+ } else {
+ mtd->ecc_stats.corrected += stat;
+ max_bitflips = max_t(unsigned int, max_bitflips, stat);
+ }
+
+ buf += ecc_size;
+ ecc_code += ecc_bytes;
+ }
+
+ return max_bitflips;
+}
+
+static int denali_hw_ecc_fixup(struct mtd_info *mtd,
+ struct denali_nand_info *denali,
+ unsigned long *uncor_ecc_flags)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ int bank = denali->flash_bank;
+ uint32_t ecc_cor;
+ unsigned int max_bitflips;
+
+ ecc_cor = ioread32(denali->flash_reg + ECC_COR_INFO(bank));
+ ecc_cor >>= ECC_COR_INFO__SHIFT(bank);
+
+ if (ecc_cor & ECC_COR_INFO__UNCOR_ERR) {
+ /*
+ * This flag is set when uncorrectable error occurs at least in
+ * one ECC sector. We can not know "how many sectors", or
+ * "which sector(s)". We need erase-page check for all sectors.
+ */
+ *uncor_ecc_flags = GENMASK(chip->ecc.steps - 1, 0);
+ return 0;
+ }
+
+ max_bitflips = ecc_cor & ECC_COR_INFO__MAX_ERRORS;
+
+ /*
+ * The register holds the maximum of per-sector corrected bitflips.
+ * This is suitable for the return value of the ->read_page() callback.
+ * Unfortunately, we can not know the total number of corrected bits in
+ * the page. Increase the stats by max_bitflips. (compromised solution)
+ */
+ mtd->ecc_stats.corrected += max_bitflips;
+
+ return max_bitflips;
}
+
#define ECC_SECTOR_SIZE 512
#define ECC_SECTOR(x) (((x) & ECC_ERROR_ADDRESS__SECTOR_NR) >> 12)
#define ECC_BYTE(x) (((x) & ECC_ERROR_ADDRESS__OFFSET))
#define ECC_CORRECTION_VALUE(x) ((x) & ERR_CORRECTION_INFO__BYTEMASK)
-#define ECC_ERROR_CORRECTABLE(x) (!((x) & ERR_CORRECTION_INFO__ERROR_TYPE))
+#define ECC_ERROR_UNCORRECTABLE(x) ((x) & ERR_CORRECTION_INFO__ERROR_TYPE)
#define ECC_ERR_DEVICE(x) (((x) & ERR_CORRECTION_INFO__DEVICE_NR) >> 8)
#define ECC_LAST_ERR(x) ((x) & ERR_CORRECTION_INFO__LAST_ERR_INFO)
-static bool handle_ecc(struct denali_nand_info *denali, uint8_t *buf,
- uint32_t irq_status, unsigned int *max_bitflips)
+static int denali_sw_ecc_fixup(struct mtd_info *mtd,
+ struct denali_nand_info *denali,
+ unsigned long *uncor_ecc_flags, uint8_t *buf)
{
- bool check_erased_page = false;
unsigned int bitflips = 0;
+ unsigned int max_bitflips = 0;
+ uint32_t err_addr, err_cor_info;
+ unsigned int err_byte, err_sector, err_device;
+ uint8_t err_cor_value;
+ unsigned int prev_sector = 0;
- if (irq_status & INTR_STATUS__ECC_ERR) {
- /* read the ECC errors. we'll ignore them for now */
- uint32_t err_address, err_correction_info, err_byte,
- err_sector, err_device, err_correction_value;
- denali_set_intr_modes(denali, false);
-
- do {
- err_address = ioread32(denali->flash_reg +
- ECC_ERROR_ADDRESS);
- err_sector = ECC_SECTOR(err_address);
- err_byte = ECC_BYTE(err_address);
-
- err_correction_info = ioread32(denali->flash_reg +
- ERR_CORRECTION_INFO);
- err_correction_value =
- ECC_CORRECTION_VALUE(err_correction_info);
- err_device = ECC_ERR_DEVICE(err_correction_info);
-
- if (ECC_ERROR_CORRECTABLE(err_correction_info)) {
- /*
- * If err_byte is larger than ECC_SECTOR_SIZE,
- * means error happened in OOB, so we ignore
- * it. It's no need for us to correct it
- * err_device is represented the NAND error
- * bits are happened in if there are more
- * than one NAND connected.
- */
- if (err_byte < ECC_SECTOR_SIZE) {
- struct mtd_info *mtd =
- nand_to_mtd(&denali->nand);
- int offset;
-
- offset = (err_sector *
- ECC_SECTOR_SIZE +
- err_byte) *
- denali->devnum +
- err_device;
- /* correct the ECC error */
- buf[offset] ^= err_correction_value;
- mtd->ecc_stats.corrected++;
- bitflips++;
- }
- } else {
- /*
- * if the error is not correctable, need to
- * look at the page to see if it is an erased
- * page. if so, then it's not a real ECC error
- */
- check_erased_page = true;
- }
- } while (!ECC_LAST_ERR(err_correction_info));
- /*
- * Once handle all ecc errors, controller will triger
- * a ECC_TRANSACTION_DONE interrupt, so here just wait
- * for a while for this interrupt
- */
- while (!(read_interrupt_status(denali) &
- INTR_STATUS__ECC_TRANSACTION_DONE))
- cpu_relax();
- clear_interrupts(denali);
- denali_set_intr_modes(denali, true);
- }
- *max_bitflips = bitflips;
- return check_erased_page;
+ /* read the ECC errors. we'll ignore them for now */
+ denali_set_intr_modes(denali, false);
+
+ do {
+ err_addr = ioread32(denali->flash_reg + ECC_ERROR_ADDRESS);
+ err_sector = ECC_SECTOR(err_addr);
+ err_byte = ECC_BYTE(err_addr);
+
+ err_cor_info = ioread32(denali->flash_reg + ERR_CORRECTION_INFO);
+ err_cor_value = ECC_CORRECTION_VALUE(err_cor_info);
+ err_device = ECC_ERR_DEVICE(err_cor_info);
+
+ /* reset the bitflip counter when crossing ECC sector */
+ if (err_sector != prev_sector)
+ bitflips = 0;
+
+ if (ECC_ERROR_UNCORRECTABLE(err_cor_info)) {
+ /*
+ * Check later if this is a real ECC error, or
+ * an erased sector.
+ */
+ *uncor_ecc_flags |= BIT(err_sector);
+ } else if (err_byte < ECC_SECTOR_SIZE) {
+ /*
+ * If err_byte is larger than ECC_SECTOR_SIZE, means error
+ * happened in OOB, so we ignore it. It's no need for
+ * us to correct it err_device is represented the NAND
+ * error bits are happened in if there are more than
+ * one NAND connected.
+ */
+ int offset;
+ unsigned int flips_in_byte;
+
+ offset = (err_sector * ECC_SECTOR_SIZE + err_byte) *
+ denali->devnum + err_device;
+
+ /* correct the ECC error */
+ flips_in_byte = hweight8(buf[offset] ^ err_cor_value);
+ buf[offset] ^= err_cor_value;
+ mtd->ecc_stats.corrected += flips_in_byte;
+ bitflips += flips_in_byte;
+
+ max_bitflips = max(max_bitflips, bitflips);
+ }
+
+ prev_sector = err_sector;
+ } while (!ECC_LAST_ERR(err_cor_info));
+
+ /*
+ * Once handle all ecc errors, controller will trigger a
+ * ECC_TRANSACTION_DONE interrupt, so here just wait for
+ * a while for this interrupt
+ */
+ while (!(read_interrupt_status(denali) & INTR__ECC_TRANSACTION_DONE))
+ cpu_relax();
+ clear_interrupts(denali);
+ denali_set_intr_modes(denali, true);
+
+ return max_bitflips;
}
/* programs the controller to either enable/disable DMA transfers */
ioread32(denali->flash_reg + DMA_ENABLE);
}
-/* setups the HW to perform the data DMA */
-static void denali_setup_dma(struct denali_nand_info *denali, int op)
+static void denali_setup_dma64(struct denali_nand_info *denali, int op)
+{
+ uint32_t mode;
+ const int page_count = 1;
+ uint64_t addr = denali->buf.dma_buf;
+
+ mode = MODE_10 | BANK(denali->flash_bank) | denali->page;
+
+ /* DMA is a three step process */
+
+ /*
+ * 1. setup transfer type, interrupt when complete,
+ * burst len = 64 bytes, the number of pages
+ */
+ index_addr(denali, mode, 0x01002000 | (64 << 16) | op | page_count);
+
+ /* 2. set memory low address */
+ index_addr(denali, mode, addr);
+
+ /* 3. set memory high address */
+ index_addr(denali, mode, addr >> 32);
+}
+
+static void denali_setup_dma32(struct denali_nand_info *denali, int op)
{
uint32_t mode;
const int page_count = 1;
index_addr(denali, mode | 0x14000, 0x2400);
}
+static void denali_setup_dma(struct denali_nand_info *denali, int op)
+{
+ if (denali->caps & DENALI_CAP_DMA_64BIT)
+ denali_setup_dma64(denali, op);
+ else
+ denali_setup_dma32(denali, op);
+}
+
/*
* writes a page. user specifies type, and this function handles the
* configuration details.
dma_addr_t addr = denali->buf.dma_buf;
size_t size = mtd->writesize + mtd->oobsize;
uint32_t irq_status;
- uint32_t irq_mask = INTR_STATUS__DMA_CMD_COMP |
- INTR_STATUS__PROGRAM_FAIL;
+ uint32_t irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL;
/*
* if it is a raw xfer, we want to disable ecc and send the spare area.
static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
uint8_t *buf, int oob_required, int page)
{
- unsigned int max_bitflips;
struct denali_nand_info *denali = mtd_to_denali(mtd);
-
dma_addr_t addr = denali->buf.dma_buf;
size_t size = mtd->writesize + mtd->oobsize;
-
uint32_t irq_status;
- uint32_t irq_mask = INTR_STATUS__ECC_TRANSACTION_DONE |
- INTR_STATUS__ECC_ERR;
- bool check_erased_page = false;
+ uint32_t irq_mask = denali->caps & DENALI_CAP_HW_ECC_FIXUP ?
+ INTR__DMA_CMD_COMP | INTR__ECC_UNCOR_ERR :
+ INTR__ECC_TRANSACTION_DONE | INTR__ECC_ERR;
+ unsigned long uncor_ecc_flags = 0;
+ int stat = 0;
if (page != denali->page) {
dev_err(denali->dev,
memcpy(buf, denali->buf.buf, mtd->writesize);
- check_erased_page = handle_ecc(denali, buf, irq_status, &max_bitflips);
+ if (denali->caps & DENALI_CAP_HW_ECC_FIXUP)
+ stat = denali_hw_ecc_fixup(mtd, denali, &uncor_ecc_flags);
+ else if (irq_status & INTR__ECC_ERR)
+ stat = denali_sw_ecc_fixup(mtd, denali, &uncor_ecc_flags, buf);
denali_enable_dma(denali, false);
- if (check_erased_page) {
+ if (stat < 0)
+ return stat;
+
+ if (uncor_ecc_flags) {
read_oob_data(mtd, chip->oob_poi, denali->page);
- /* check ECC failures that may have occurred on erased pages */
- if (check_erased_page) {
- if (!is_erased(buf, mtd->writesize))
- mtd->ecc_stats.failed++;
- if (!is_erased(buf, mtd->oobsize))
- mtd->ecc_stats.failed++;
- }
+ stat = denali_check_erased_page(mtd, chip, buf,
+ uncor_ecc_flags, stat);
}
- return max_bitflips;
+
+ return stat;
}
static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
struct denali_nand_info *denali = mtd_to_denali(mtd);
dma_addr_t addr = denali->buf.dma_buf;
size_t size = mtd->writesize + mtd->oobsize;
- uint32_t irq_mask = INTR_STATUS__DMA_CMD_COMP;
+ uint32_t irq_mask = INTR__DMA_CMD_COMP;
if (page != denali->page) {
dev_err(denali->dev,
index_addr(denali, cmd, 0x1);
/* wait for erase to complete or failure to occur */
- irq_status = wait_for_irq(denali, INTR_STATUS__ERASE_COMP |
- INTR_STATUS__ERASE_FAIL);
+ irq_status = wait_for_irq(denali, INTR__ERASE_COMP | INTR__ERASE_FAIL);
- return irq_status & INTR_STATUS__ERASE_FAIL ? NAND_STATUS_FAIL : PASS;
+ return irq_status & INTR__ERASE_FAIL ? NAND_STATUS_FAIL : PASS;
}
static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col,
/* Initialization code to bring the device up to a known good state */
static void denali_hw_init(struct denali_nand_info *denali)
{
+ /*
+ * The REVISION register may not be reliable. Platforms are allowed to
+ * override it.
+ */
+ if (!denali->revision)
+ denali->revision =
+ swab16(ioread32(denali->flash_reg + REVISION));
+
/*
* tell driver how many bit controller will skip before
* writing ECC code in OOB, this register may be already
denali->irq_status = 0;
}
+static int denali_multidev_fixup(struct denali_nand_info *denali)
+{
+ struct nand_chip *chip = &denali->nand;
+ struct mtd_info *mtd = nand_to_mtd(chip);
+
+ /*
+ * Support for multi device:
+ * When the IP configuration is x16 capable and two x8 chips are
+ * connected in parallel, DEVICES_CONNECTED should be set to 2.
+ * In this case, the core framework knows nothing about this fact,
+ * so we should tell it the _logical_ pagesize and anything necessary.
+ */
+ denali->devnum = ioread32(denali->flash_reg + DEVICES_CONNECTED);
+
+ /*
+ * On some SoCs, DEVICES_CONNECTED is not auto-detected.
+ * For those, DEVICES_CONNECTED is left to 0. Set 1 if it is the case.
+ */
+ if (denali->devnum == 0) {
+ denali->devnum = 1;
+ iowrite32(1, denali->flash_reg + DEVICES_CONNECTED);
+ }
+
+ if (denali->devnum == 1)
+ return 0;
+
+ if (denali->devnum != 2) {
+ dev_err(denali->dev, "unsupported number of devices %d\n",
+ denali->devnum);
+ return -EINVAL;
+ }
+
+ /* 2 chips in parallel */
+ mtd->size <<= 1;
+ mtd->erasesize <<= 1;
+ mtd->writesize <<= 1;
+ mtd->oobsize <<= 1;
+ chip->chipsize <<= 1;
+ chip->page_shift += 1;
+ chip->phys_erase_shift += 1;
+ chip->bbt_erase_shift += 1;
+ chip->chip_shift += 1;
+ chip->pagemask <<= 1;
+ chip->ecc.size <<= 1;
+ chip->ecc.bytes <<= 1;
+ chip->ecc.strength <<= 1;
+ denali->bbtskipbytes <<= 1;
+
+ return 0;
+}
+
int denali_init(struct denali_nand_info *denali)
{
- struct mtd_info *mtd = nand_to_mtd(&denali->nand);
+ struct nand_chip *chip = &denali->nand;
+ struct mtd_info *mtd = nand_to_mtd(chip);
int ret;
if (denali->platform == INTEL_CE4100) {
/* now that our ISR is registered, we can enable interrupts */
denali_set_intr_modes(denali, true);
- mtd->name = "denali-nand";
+ nand_set_flash_node(chip, denali->dev->of_node);
+ /* Fallback to the default name if DT did not give "label" property */
+ if (!mtd->name)
+ mtd->name = "denali-nand";
/* register the driver with the NAND core subsystem */
- denali->nand.select_chip = denali_select_chip;
- denali->nand.cmdfunc = denali_cmdfunc;
- denali->nand.read_byte = denali_read_byte;
- denali->nand.waitfunc = denali_waitfunc;
+ chip->select_chip = denali_select_chip;
+ chip->cmdfunc = denali_cmdfunc;
+ chip->read_byte = denali_read_byte;
+ chip->waitfunc = denali_waitfunc;
/*
* scan for NAND devices attached to the controller
goto failed_req_irq;
}
- /* Is 32-bit DMA supported? */
- ret = dma_set_mask(denali->dev, DMA_BIT_MASK(32));
+ ret = dma_set_mask(denali->dev,
+ DMA_BIT_MASK(denali->caps & DENALI_CAP_DMA_64BIT ?
+ 64 : 32));
if (ret) {
dev_err(denali->dev, "No usable DMA configuration\n");
goto failed_req_irq;
goto failed_req_irq;
}
- /*
- * support for multi nand
- * MTD known nothing about multi nand, so we should tell it
- * the real pagesize and anything necessery
- */
- denali->devnum = ioread32(denali->flash_reg + DEVICES_CONNECTED);
- denali->nand.chipsize <<= denali->devnum - 1;
- denali->nand.page_shift += denali->devnum - 1;
- denali->nand.pagemask = (denali->nand.chipsize >>
- denali->nand.page_shift) - 1;
- denali->nand.bbt_erase_shift += denali->devnum - 1;
- denali->nand.phys_erase_shift = denali->nand.bbt_erase_shift;
- denali->nand.chip_shift += denali->devnum - 1;
- mtd->writesize <<= denali->devnum - 1;
- mtd->oobsize <<= denali->devnum - 1;
- mtd->erasesize <<= denali->devnum - 1;
- mtd->size = denali->nand.numchips * denali->nand.chipsize;
- denali->bbtskipbytes *= denali->devnum;
-
/*
* second stage of the NAND scan
* this stage requires information regarding ECC and
*/
/* Bad block management */
- denali->nand.bbt_td = &bbt_main_descr;
- denali->nand.bbt_md = &bbt_mirror_descr;
+ chip->bbt_td = &bbt_main_descr;
+ chip->bbt_md = &bbt_mirror_descr;
/* skip the scan for now until we have OOB read and write support */
- denali->nand.bbt_options |= NAND_BBT_USE_FLASH;
- denali->nand.options |= NAND_SKIP_BBTSCAN;
- denali->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
+ chip->bbt_options |= NAND_BBT_USE_FLASH;
+ chip->options |= NAND_SKIP_BBTSCAN;
+ chip->ecc.mode = NAND_ECC_HW_SYNDROME;
/* no subpage writes on denali */
- denali->nand.options |= NAND_NO_SUBPAGE_WRITE;
+ chip->options |= NAND_NO_SUBPAGE_WRITE;
/*
* Denali Controller only support 15bit and 8bit ECC in MRST,
* so just let controller do 15bit ECC for MLC and 8bit ECC for
* SLC if possible.
* */
- if (!nand_is_slc(&denali->nand) &&
+ if (!nand_is_slc(chip) &&
(mtd->oobsize > (denali->bbtskipbytes +
ECC_15BITS * (mtd->writesize /
ECC_SECTOR_SIZE)))) {
/* if MLC OOB size is large enough, use 15bit ECC*/
- denali->nand.ecc.strength = 15;
- denali->nand.ecc.bytes = ECC_15BITS;
+ chip->ecc.strength = 15;
+ chip->ecc.bytes = ECC_15BITS;
iowrite32(15, denali->flash_reg + ECC_CORRECTION);
} else if (mtd->oobsize < (denali->bbtskipbytes +
ECC_8BITS * (mtd->writesize /
pr_err("Your NAND chip OOB is not large enough to contain 8bit ECC correction codes");
goto failed_req_irq;
} else {
- denali->nand.ecc.strength = 8;
- denali->nand.ecc.bytes = ECC_8BITS;
+ chip->ecc.strength = 8;
+ chip->ecc.bytes = ECC_8BITS;
iowrite32(8, denali->flash_reg + ECC_CORRECTION);
}
mtd_set_ooblayout(mtd, &denali_ooblayout_ops);
- denali->nand.ecc.bytes *= denali->devnum;
- denali->nand.ecc.strength *= denali->devnum;
/* override the default read operations */
- denali->nand.ecc.size = ECC_SECTOR_SIZE * denali->devnum;
- denali->nand.ecc.read_page = denali_read_page;
- denali->nand.ecc.read_page_raw = denali_read_page_raw;
- denali->nand.ecc.write_page = denali_write_page;
- denali->nand.ecc.write_page_raw = denali_write_page_raw;
- denali->nand.ecc.read_oob = denali_read_oob;
- denali->nand.ecc.write_oob = denali_write_oob;
- denali->nand.erase = denali_erase;
+ chip->ecc.size = ECC_SECTOR_SIZE;
+ chip->ecc.read_page = denali_read_page;
+ chip->ecc.read_page_raw = denali_read_page_raw;
+ chip->ecc.write_page = denali_write_page;
+ chip->ecc.write_page_raw = denali_write_page_raw;
+ chip->ecc.read_oob = denali_read_oob;
+ chip->ecc.write_oob = denali_write_oob;
+ chip->erase = denali_erase;
+
+ ret = denali_multidev_fixup(denali);
+ if (ret)
+ goto failed_req_irq;
ret = nand_scan_tail(mtd);
if (ret)
#ifndef __DENALI_H__
#define __DENALI_H__
+#include <linux/bitops.h>
#include <linux/mtd/nand.h>
#define DEVICE_RESET 0x0
#define REVISION 0x370
#define REVISION__VALUE 0xffff
-#define MAKE_COMPARABLE_REVISION(x) swab16((x) & REVISION__VALUE)
-#define REVISION_5_1 0x00000501
#define ONFI_DEVICE_FEATURES 0x380
#define ONFI_DEVICE_FEATURES__VALUE 0x003f
#define INTR_STATUS(__bank) (0x410 + ((__bank) * 0x50))
#define INTR_EN(__bank) (0x420 + ((__bank) * 0x50))
-
-#define INTR_STATUS__ECC_TRANSACTION_DONE 0x0001
-#define INTR_STATUS__ECC_ERR 0x0002
-#define INTR_STATUS__DMA_CMD_COMP 0x0004
-#define INTR_STATUS__TIME_OUT 0x0008
-#define INTR_STATUS__PROGRAM_FAIL 0x0010
-#define INTR_STATUS__ERASE_FAIL 0x0020
-#define INTR_STATUS__LOAD_COMP 0x0040
-#define INTR_STATUS__PROGRAM_COMP 0x0080
-#define INTR_STATUS__ERASE_COMP 0x0100
-#define INTR_STATUS__PIPE_CPYBCK_CMD_COMP 0x0200
-#define INTR_STATUS__LOCKED_BLK 0x0400
-#define INTR_STATUS__UNSUP_CMD 0x0800
-#define INTR_STATUS__INT_ACT 0x1000
-#define INTR_STATUS__RST_COMP 0x2000
-#define INTR_STATUS__PIPE_CMD_ERR 0x4000
-#define INTR_STATUS__PAGE_XFER_INC 0x8000
-
-#define INTR_EN__ECC_TRANSACTION_DONE 0x0001
-#define INTR_EN__ECC_ERR 0x0002
-#define INTR_EN__DMA_CMD_COMP 0x0004
-#define INTR_EN__TIME_OUT 0x0008
-#define INTR_EN__PROGRAM_FAIL 0x0010
-#define INTR_EN__ERASE_FAIL 0x0020
-#define INTR_EN__LOAD_COMP 0x0040
-#define INTR_EN__PROGRAM_COMP 0x0080
-#define INTR_EN__ERASE_COMP 0x0100
-#define INTR_EN__PIPE_CPYBCK_CMD_COMP 0x0200
-#define INTR_EN__LOCKED_BLK 0x0400
-#define INTR_EN__UNSUP_CMD 0x0800
-#define INTR_EN__INT_ACT 0x1000
-#define INTR_EN__RST_COMP 0x2000
-#define INTR_EN__PIPE_CMD_ERR 0x4000
-#define INTR_EN__PAGE_XFER_INC 0x8000
+/* bit[1:0] is used differently depending on IP version */
+#define INTR__ECC_UNCOR_ERR 0x0001 /* new IP */
+#define INTR__ECC_TRANSACTION_DONE 0x0001 /* old IP */
+#define INTR__ECC_ERR 0x0002 /* old IP */
+#define INTR__DMA_CMD_COMP 0x0004
+#define INTR__TIME_OUT 0x0008
+#define INTR__PROGRAM_FAIL 0x0010
+#define INTR__ERASE_FAIL 0x0020
+#define INTR__LOAD_COMP 0x0040
+#define INTR__PROGRAM_COMP 0x0080
+#define INTR__ERASE_COMP 0x0100
+#define INTR__PIPE_CPYBCK_CMD_COMP 0x0200
+#define INTR__LOCKED_BLK 0x0400
+#define INTR__UNSUP_CMD 0x0800
+#define INTR__INT_ACT 0x1000
+#define INTR__RST_COMP 0x2000
+#define INTR__PIPE_CMD_ERR 0x4000
+#define INTR__PAGE_XFER_INC 0x8000
#define PAGE_CNT(__bank) (0x430 + ((__bank) * 0x50))
#define ERR_PAGE_ADDR(__bank) (0x440 + ((__bank) * 0x50))
#define ERR_BLOCK_ADDR(__bank) (0x450 + ((__bank) * 0x50))
-#define DATA_INTR 0x550
-#define DATA_INTR__WRITE_SPACE_AV 0x0001
-#define DATA_INTR__READ_DATA_AV 0x0002
-
-#define DATA_INTR_EN 0x560
-#define DATA_INTR_EN__WRITE_SPACE_AV 0x0001
-#define DATA_INTR_EN__READ_DATA_AV 0x0002
-
-#define GPREG_0 0x570
-#define GPREG_0__VALUE 0xffff
-
-#define GPREG_1 0x580
-#define GPREG_1__VALUE 0xffff
-
-#define GPREG_2 0x590
-#define GPREG_2__VALUE 0xffff
-
-#define GPREG_3 0x5a0
-#define GPREG_3__VALUE 0xffff
-
#define ECC_THRESHOLD 0x600
#define ECC_THRESHOLD__VALUE 0x03ff
#define ERR_CORRECTION_INFO__ERROR_TYPE 0x4000
#define ERR_CORRECTION_INFO__LAST_ERR_INFO 0x8000
+#define ECC_COR_INFO(bank) (0x650 + (bank) / 2 * 0x10)
+#define ECC_COR_INFO__SHIFT(bank) ((bank) % 2 * 8)
+#define ECC_COR_INFO__MAX_ERRORS 0x007f
+#define ECC_COR_INFO__UNCOR_ERR 0x0080
+
#define DMA_ENABLE 0x700
#define DMA_ENABLE__FLAG 0x0001
#define IGNORE_ECC_DONE__FLAG 0x0001
#define DMA_INTR 0x720
+#define DMA_INTR_EN 0x730
#define DMA_INTR__TARGET_ERROR 0x0001
#define DMA_INTR__DESC_COMP_CHANNEL0 0x0002
#define DMA_INTR__DESC_COMP_CHANNEL1 0x0004
#define DMA_INTR__DESC_COMP_CHANNEL2 0x0008
#define DMA_INTR__DESC_COMP_CHANNEL3 0x0010
-#define DMA_INTR__MEMCOPY_DESC_COMP 0x0020
-
-#define DMA_INTR_EN 0x730
-#define DMA_INTR_EN__TARGET_ERROR 0x0001
-#define DMA_INTR_EN__DESC_COMP_CHANNEL0 0x0002
-#define DMA_INTR_EN__DESC_COMP_CHANNEL1 0x0004
-#define DMA_INTR_EN__DESC_COMP_CHANNEL2 0x0008
-#define DMA_INTR_EN__DESC_COMP_CHANNEL3 0x0010
-#define DMA_INTR_EN__MEMCOPY_DESC_COMP 0x0020
+#define DMA_INTR__MEMCOPY_DESC_COMP 0x0020
#define TARGET_ERR_ADDR_LO 0x740
#define TARGET_ERR_ADDR_LO__VALUE 0xffff
#define CHNL_ACTIVE__CHANNEL2 0x0004
#define CHNL_ACTIVE__CHANNEL3 0x0008
-#define ACTIVE_SRC_ID 0x800
-#define ACTIVE_SRC_ID__VALUE 0x00ff
-
-#define PTN_INTR 0x810
-#define PTN_INTR__CONFIG_ERROR 0x0001
-#define PTN_INTR__ACCESS_ERROR_BANK0 0x0002
-#define PTN_INTR__ACCESS_ERROR_BANK1 0x0004
-#define PTN_INTR__ACCESS_ERROR_BANK2 0x0008
-#define PTN_INTR__ACCESS_ERROR_BANK3 0x0010
-#define PTN_INTR__REG_ACCESS_ERROR 0x0020
-
-#define PTN_INTR_EN 0x820
-#define PTN_INTR_EN__CONFIG_ERROR 0x0001
-#define PTN_INTR_EN__ACCESS_ERROR_BANK0 0x0002
-#define PTN_INTR_EN__ACCESS_ERROR_BANK1 0x0004
-#define PTN_INTR_EN__ACCESS_ERROR_BANK2 0x0008
-#define PTN_INTR_EN__ACCESS_ERROR_BANK3 0x0010
-#define PTN_INTR_EN__REG_ACCESS_ERROR 0x0020
-
-#define PERM_SRC_ID(__bank) (0x830 + ((__bank) * 0x40))
-#define PERM_SRC_ID__SRCID 0x00ff
-#define PERM_SRC_ID__DIRECT_ACCESS_ACTIVE 0x0800
-#define PERM_SRC_ID__WRITE_ACTIVE 0x2000
-#define PERM_SRC_ID__READ_ACTIVE 0x4000
-#define PERM_SRC_ID__PARTITION_VALID 0x8000
-
-#define MIN_BLK_ADDR(__bank) (0x840 + ((__bank) * 0x40))
-#define MIN_BLK_ADDR__VALUE 0xffff
-
-#define MAX_BLK_ADDR(__bank) (0x850 + ((__bank) * 0x40))
-#define MAX_BLK_ADDR__VALUE 0xffff
-
-#define MIN_MAX_BANK(__bank) (0x860 + ((__bank) * 0x40))
-#define MIN_MAX_BANK__MIN_VALUE 0x0003
-#define MIN_MAX_BANK__MAX_VALUE 0x000c
-
-
-/* ffsdefs.h */
-#define CLEAR 0 /*use this to clear a field instead of "fail"*/
-#define SET 1 /*use this to set a field instead of "pass"*/
#define FAIL 1 /*failed flag*/
#define PASS 0 /*success flag*/
-#define ERR -1 /*error flag*/
-
-/* lld.h */
-#define GOOD_BLOCK 0
-#define DEFECTIVE_BLOCK 1
-#define READ_ERROR 2
#define CLK_X 5
#define CLK_MULTI 4
-/* KBV - Updated to LNW scratch register address */
-#define SCRATCH_REG_ADDR CONFIG_MTD_NAND_DENALI_SCRATCH_REG_ADDR
-#define SCRATCH_REG_SIZE 64
-
-#define GLOB_HWCTL_DEFAULT_BLKS 2048
-
-#define SUPPORT_15BITECC 1
-#define SUPPORT_8BITECC 1
-
-#define CUSTOM_CONF_PARAMS 0
-
#define ONFI_BLOOM_TIME 1
#define MODE5_WORKAROUND 0
#define MODE_10 0x08000000
#define MODE_11 0x0C000000
-
-#define DATA_TRANSFER_MODE 0
-#define PROTECTION_PER_BLOCK 1
-#define LOAD_WAIT_COUNT 2
-#define PROGRAM_WAIT_COUNT 3
-#define ERASE_WAIT_COUNT 4
-#define INT_MONITOR_CYCLE_COUNT 5
-#define READ_BUSY_PIN_ENABLED 6
-#define MULTIPLANE_OPERATION_SUPPORT 7
-#define PRE_FETCH_MODE 8
-#define CE_DONT_CARE_SUPPORT 9
-#define COPYBACK_SUPPORT 10
-#define CACHE_WRITE_SUPPORT 11
-#define CACHE_READ_SUPPORT 12
-#define NUM_PAGES_IN_BLOCK 13
-#define ECC_ENABLE_SELECT 14
-#define WRITE_ENABLE_2_READ_ENABLE 15
-#define ADDRESS_2_DATA 16
-#define READ_ENABLE_2_WRITE_ENABLE 17
-#define TWO_ROW_ADDRESS_CYCLES 18
-#define MULTIPLANE_ADDRESS_RESTRICT 19
-#define ACC_CLOCKS 20
-#define READ_WRITE_ENABLE_LOW_COUNT 21
-#define READ_WRITE_ENABLE_HIGH_COUNT 22
-
#define ECC_SECTOR_SIZE 512
struct nand_buf {
struct nand_buf buf;
struct device *dev;
int total_used_banks;
- uint32_t block; /* stored for future use */
- uint16_t page;
- void __iomem *flash_reg; /* Mapped io reg base address */
- void __iomem *flash_mem; /* Mapped io reg base address */
+ int page;
+ void __iomem *flash_reg; /* Register Interface */
+ void __iomem *flash_mem; /* Host Data/Command Interface */
/* elements used by ISR */
struct completion complete;
spinlock_t irq_lock;
uint32_t irq_status;
- int irq_debug_array[32];
int irq;
- uint32_t devnum; /* represent how many nands connected */
- uint32_t bbtskipbytes;
- uint32_t max_banks;
+ int devnum; /* represent how many nands connected */
+ int bbtskipbytes;
+ int max_banks;
+ unsigned int revision;
+ unsigned int caps;
};
+#define DENALI_CAP_HW_ECC_FIXUP BIT(0)
+#define DENALI_CAP_DMA_64BIT BIT(1)
+
extern int denali_init(struct denali_nand_info *denali);
extern void denali_remove(struct denali_nand_info *denali);
struct clk *clk;
};
-static const struct of_device_id denali_nand_dt_ids[] = {
- { .compatible = "denali,denali-nand-dt" },
- { /* sentinel */ }
- };
+struct denali_dt_data {
+ unsigned int revision;
+ unsigned int caps;
+};
-MODULE_DEVICE_TABLE(of, denali_nand_dt_ids);
+static const struct denali_dt_data denali_socfpga_data = {
+ .caps = DENALI_CAP_HW_ECC_FIXUP,
+};
-static u64 denali_dma_mask;
+static const struct of_device_id denali_nand_dt_ids[] = {
+ {
+ .compatible = "altr,socfpga-denali-nand",
+ .data = &denali_socfpga_data,
+ },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, denali_nand_dt_ids);
-static int denali_dt_probe(struct platform_device *ofdev)
+static int denali_dt_probe(struct platform_device *pdev)
{
struct resource *denali_reg, *nand_data;
struct denali_dt *dt;
+ const struct denali_dt_data *data;
struct denali_nand_info *denali;
int ret;
- const struct of_device_id *of_id;
- of_id = of_match_device(denali_nand_dt_ids, &ofdev->dev);
- if (of_id) {
- ofdev->id_entry = of_id->data;
- } else {
- pr_err("Failed to find the right device id.\n");
- return -ENOMEM;
- }
-
- dt = devm_kzalloc(&ofdev->dev, sizeof(*dt), GFP_KERNEL);
+ dt = devm_kzalloc(&pdev->dev, sizeof(*dt), GFP_KERNEL);
if (!dt)
return -ENOMEM;
denali = &dt->denali;
+ data = of_device_get_match_data(&pdev->dev);
+ if (data) {
+ denali->revision = data->revision;
+ denali->caps = data->caps;
+ }
+
denali->platform = DT;
- denali->dev = &ofdev->dev;
- denali->irq = platform_get_irq(ofdev, 0);
+ denali->dev = &pdev->dev;
+ denali->irq = platform_get_irq(pdev, 0);
if (denali->irq < 0) {
- dev_err(&ofdev->dev, "no irq defined\n");
+ dev_err(&pdev->dev, "no irq defined\n");
return denali->irq;
}
- denali_reg = platform_get_resource_byname(ofdev, IORESOURCE_MEM, "denali_reg");
- denali->flash_reg = devm_ioremap_resource(&ofdev->dev, denali_reg);
+ denali_reg = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+ "denali_reg");
+ denali->flash_reg = devm_ioremap_resource(&pdev->dev, denali_reg);
if (IS_ERR(denali->flash_reg))
return PTR_ERR(denali->flash_reg);
- nand_data = platform_get_resource_byname(ofdev, IORESOURCE_MEM, "nand_data");
- denali->flash_mem = devm_ioremap_resource(&ofdev->dev, nand_data);
+ nand_data = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+ "nand_data");
+ denali->flash_mem = devm_ioremap_resource(&pdev->dev, nand_data);
if (IS_ERR(denali->flash_mem))
return PTR_ERR(denali->flash_mem);
- if (!of_property_read_u32(ofdev->dev.of_node,
- "dma-mask", (u32 *)&denali_dma_mask)) {
- denali->dev->dma_mask = &denali_dma_mask;
- } else {
- denali->dev->dma_mask = NULL;
- }
-
- dt->clk = devm_clk_get(&ofdev->dev, NULL);
+ dt->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(dt->clk)) {
- dev_err(&ofdev->dev, "no clk available\n");
+ dev_err(&pdev->dev, "no clk available\n");
return PTR_ERR(dt->clk);
}
clk_prepare_enable(dt->clk);
if (ret)
goto out_disable_clk;
- platform_set_drvdata(ofdev, dt);
+ platform_set_drvdata(pdev, dt);
return 0;
out_disable_clk:
return ret;
}
-static int denali_dt_remove(struct platform_device *ofdev)
+static int denali_dt_remove(struct platform_device *pdev)
{
- struct denali_dt *dt = platform_get_drvdata(ofdev);
+ struct denali_dt *dt = platform_get_drvdata(pdev);
denali_remove(&dt->denali);
clk_disable_unprepare(dt->clk);
#include <linux/amba/bus.h>
#include <mtd/mtd-abi.h>
-#define FSMC_NAND_BW8 1
-#define FSMC_NAND_BW16 2
-
-#define FSMC_MAX_NOR_BANKS 4
-#define FSMC_MAX_NAND_BANKS 4
-
-#define FSMC_FLASH_WIDTH8 1
-#define FSMC_FLASH_WIDTH16 2
-
/* fsmc controller registers for NOR flash */
#define CTRL 0x0
/* ctrl register definitions */
};
/**
- * fsmc_nand_platform_data - platform specific NAND controller config
- * @nand_timings: timing setup for the physical NAND interface
- * @partitions: partition table for the platform, use a default fallback
- * if this is NULL
- * @nr_partitions: the number of partitions in the previous entry
- * @options: different options for the driver
- * @width: bus width
- * @bank: default bank
- * @select_bank: callback to select a certain bank, this is
- * platform-specific. If the controller only supports one bank
- * this may be set to NULL
+ * struct fsmc_nand_data - structure for FSMC NAND device state
+ *
+ * @pid: Part ID on the AMBA PrimeCell format
+ * @mtd: MTD info for a NAND flash.
+ * @nand: Chip related info for a NAND flash.
+ * @partitions: Partition info for a NAND Flash.
+ * @nr_partitions: Total number of partition of a NAND flash.
+ *
+ * @bank: Bank number for probed device.
+ * @clk: Clock structure for FSMC.
+ *
+ * @read_dma_chan: DMA channel for read access
+ * @write_dma_chan: DMA channel for write access to NAND
+ * @dma_access_complete: Completion structure
+ *
+ * @data_pa: NAND Physical port for Data.
+ * @data_va: NAND port for Data.
+ * @cmd_va: NAND port for Command.
+ * @addr_va: NAND port for Address.
+ * @regs_va: FSMC regs base address.
*/
-struct fsmc_nand_platform_data {
- struct fsmc_nand_timings *nand_timings;
- struct mtd_partition *partitions;
- unsigned int nr_partitions;
- unsigned int options;
- unsigned int width;
- unsigned int bank;
+struct fsmc_nand_data {
+ u32 pid;
+ struct nand_chip nand;
+ unsigned int bank;
+ struct device *dev;
enum access_mode mode;
+ struct clk *clk;
- void (*select_bank)(uint32_t bank, uint32_t busw);
+ /* DMA related objects */
+ struct dma_chan *read_dma_chan;
+ struct dma_chan *write_dma_chan;
+ struct completion dma_access_complete;
- /* priv structures for dma accesses */
- void *read_dma_priv;
- void *write_dma_priv;
+ struct fsmc_nand_timings *dev_timings;
+
+ dma_addr_t data_pa;
+ void __iomem *data_va;
+ void __iomem *cmd_va;
+ void __iomem *addr_va;
+ void __iomem *regs_va;
};
static int fsmc_ecc1_ooblayout_ecc(struct mtd_info *mtd, int section,
.free = fsmc_ecc4_ooblayout_free,
};
-/**
- * struct fsmc_nand_data - structure for FSMC NAND device state
- *
- * @pid: Part ID on the AMBA PrimeCell format
- * @mtd: MTD info for a NAND flash.
- * @nand: Chip related info for a NAND flash.
- * @partitions: Partition info for a NAND Flash.
- * @nr_partitions: Total number of partition of a NAND flash.
- *
- * @bank: Bank number for probed device.
- * @clk: Clock structure for FSMC.
- *
- * @read_dma_chan: DMA channel for read access
- * @write_dma_chan: DMA channel for write access to NAND
- * @dma_access_complete: Completion structure
- *
- * @data_pa: NAND Physical port for Data.
- * @data_va: NAND port for Data.
- * @cmd_va: NAND port for Command.
- * @addr_va: NAND port for Address.
- * @regs_va: FSMC regs base address.
- */
-struct fsmc_nand_data {
- u32 pid;
- struct nand_chip nand;
- struct mtd_partition *partitions;
- unsigned int nr_partitions;
-
- unsigned int bank;
- struct device *dev;
- enum access_mode mode;
- struct clk *clk;
-
- /* DMA related objects */
- struct dma_chan *read_dma_chan;
- struct dma_chan *write_dma_chan;
- struct completion dma_access_complete;
-
- struct fsmc_nand_timings *dev_timings;
-
- dma_addr_t data_pa;
- void __iomem *data_va;
- void __iomem *cmd_va;
- void __iomem *addr_va;
- void __iomem *regs_va;
-
- void (*select_chip)(uint32_t bank, uint32_t busw);
-};
-
static inline struct fsmc_nand_data *mtd_to_fsmc(struct mtd_info *mtd)
{
return container_of(mtd_to_nand(mtd), struct fsmc_nand_data, nand);
}
-/* Assert CS signal based on chipnr */
-static void fsmc_select_chip(struct mtd_info *mtd, int chipnr)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
- struct fsmc_nand_data *host;
-
- host = mtd_to_fsmc(mtd);
-
- switch (chipnr) {
- case -1:
- chip->cmd_ctrl(mtd, NAND_CMD_NONE, 0 | NAND_CTRL_CHANGE);
- break;
- case 0:
- case 1:
- case 2:
- case 3:
- if (host->select_chip)
- host->select_chip(chipnr,
- chip->options & NAND_BUSWIDTH_16);
- break;
-
- default:
- dev_err(host->dev, "unsupported chip-select %d\n", chipnr);
- }
-}
-
/*
* fsmc_cmd_ctrl - For facilitaing Hardware access
* This routine allows hardware specific access to control-lines(ALE,CLE)
}
static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
- struct device_node *np)
+ struct fsmc_nand_data *host,
+ struct nand_chip *nand)
{
- struct fsmc_nand_platform_data *pdata = dev_get_platdata(&pdev->dev);
+ struct device_node *np = pdev->dev.of_node;
u32 val;
int ret;
- /* Set default NAND width to 8 bits */
- pdata->width = 8;
+ nand->options = 0;
+
if (!of_property_read_u32(np, "bank-width", &val)) {
if (val == 2) {
- pdata->width = 16;
+ nand->options |= NAND_BUSWIDTH_16;
} else if (val != 1) {
dev_err(&pdev->dev, "invalid bank-width %u\n", val);
return -EINVAL;
}
}
+
if (of_get_property(np, "nand-skip-bbtscan", NULL))
- pdata->options = NAND_SKIP_BBTSCAN;
+ nand->options |= NAND_SKIP_BBTSCAN;
- pdata->nand_timings = devm_kzalloc(&pdev->dev,
- sizeof(*pdata->nand_timings), GFP_KERNEL);
- if (!pdata->nand_timings)
+ host->dev_timings = devm_kzalloc(&pdev->dev,
+ sizeof(*host->dev_timings), GFP_KERNEL);
+ if (!host->dev_timings)
return -ENOMEM;
- ret = of_property_read_u8_array(np, "timings", (u8 *)pdata->nand_timings,
- sizeof(*pdata->nand_timings));
+ ret = of_property_read_u8_array(np, "timings", (u8 *)host->dev_timings,
+ sizeof(*host->dev_timings));
if (ret) {
dev_info(&pdev->dev, "No timings in dts specified, using default timings!\n");
- pdata->nand_timings = NULL;
+ host->dev_timings = NULL;
}
/* Set default NAND bank to 0 */
- pdata->bank = 0;
+ host->bank = 0;
if (!of_property_read_u32(np, "bank", &val)) {
if (val > 3) {
dev_err(&pdev->dev, "invalid bank %u\n", val);
return -EINVAL;
}
- pdata->bank = val;
+ host->bank = val;
}
return 0;
}
*/
static int __init fsmc_nand_probe(struct platform_device *pdev)
{
- struct fsmc_nand_platform_data *pdata = dev_get_platdata(&pdev->dev);
- struct device_node __maybe_unused *np = pdev->dev.of_node;
struct fsmc_nand_data *host;
struct mtd_info *mtd;
struct nand_chip *nand;
u32 pid;
int i;
- pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
- if (!pdata)
- return -ENOMEM;
-
- pdev->dev.platform_data = pdata;
- ret = fsmc_nand_probe_config_dt(pdev, np);
- if (ret) {
- dev_err(&pdev->dev, "no platform data\n");
- return -ENODEV;
- }
-
/* Allocate memory for the device structure (and zero it) */
host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
if (!host)
return -ENOMEM;
+ nand = &host->nand;
+
+ ret = fsmc_nand_probe_config_dt(pdev, host, nand);
+ if (ret)
+ return ret;
+
res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
host->data_va = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(host->data_va))
if (IS_ERR(host->regs_va))
return PTR_ERR(host->regs_va);
- host->clk = clk_get(&pdev->dev, NULL);
+ host->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(host->clk)) {
dev_err(&pdev->dev, "failed to fetch block clock\n");
return PTR_ERR(host->clk);
ret = clk_prepare_enable(host->clk);
if (ret)
- goto err_clk_prepare_enable;
+ return ret;
/*
* This device ID is actually a common AMBA ID as used on the
AMBA_PART_BITS(pid), AMBA_MANF_BITS(pid),
AMBA_REV_BITS(pid), AMBA_CONFIG_BITS(pid));
- host->bank = pdata->bank;
- host->select_chip = pdata->select_bank;
- host->partitions = pdata->partitions;
- host->nr_partitions = pdata->nr_partitions;
host->dev = &pdev->dev;
- host->dev_timings = pdata->nand_timings;
- host->mode = pdata->mode;
if (host->mode == USE_DMA_ACCESS)
init_completion(&host->dma_access_complete);
/* Link all private pointers */
mtd = nand_to_mtd(&host->nand);
- nand = &host->nand;
nand_set_controller_data(nand, host);
- nand_set_flash_node(nand, np);
+ nand_set_flash_node(nand, pdev->dev.of_node);
mtd->dev.parent = &pdev->dev;
nand->IO_ADDR_R = host->data_va;
nand->ecc.mode = NAND_ECC_HW;
nand->ecc.hwctl = fsmc_enable_hwecc;
nand->ecc.size = 512;
- nand->options = pdata->options;
- nand->select_chip = fsmc_select_chip;
nand->badblockbits = 7;
- nand_set_flash_node(nand, np);
-
- if (pdata->width == FSMC_NAND_BW16)
- nand->options |= NAND_BUSWIDTH_16;
switch (host->mode) {
case USE_DMA_ACCESS:
dma_cap_zero(mask);
dma_cap_set(DMA_MEMCPY, mask);
- host->read_dma_chan = dma_request_channel(mask, filter,
- pdata->read_dma_priv);
+ host->read_dma_chan = dma_request_channel(mask, filter, NULL);
if (!host->read_dma_chan) {
dev_err(&pdev->dev, "Unable to get read dma channel\n");
goto err_req_read_chnl;
}
- host->write_dma_chan = dma_request_channel(mask, filter,
- pdata->write_dma_priv);
+ host->write_dma_chan = dma_request_channel(mask, filter, NULL);
if (!host->write_dma_chan) {
dev_err(&pdev->dev, "Unable to get write dma channel\n");
goto err_req_write_chnl;
if (ret)
goto err_probe;
- /*
- * The partition information can is accessed by (in the same precedence)
- *
- * command line through Bootloader,
- * platform data,
- * default partition information present in driver.
- */
- /*
- * Check for partition info passed
- */
mtd->name = "nand";
- ret = mtd_device_register(mtd, host->partitions, host->nr_partitions);
+ ret = mtd_device_register(mtd, NULL, 0);
if (ret)
goto err_probe;
dma_release_channel(host->read_dma_chan);
err_req_read_chnl:
clk_disable_unprepare(host->clk);
-err_clk_prepare_enable:
- clk_put(host->clk);
return ret;
}
dma_release_channel(host->read_dma_chan);
}
clk_disable_unprepare(host->clk);
- clk_put(host->clk);
}
return 0;
static SIMPLE_DEV_PM_OPS(fsmc_nand_pm_ops, fsmc_nand_suspend, fsmc_nand_resume);
-#ifdef CONFIG_OF
static const struct of_device_id fsmc_nand_id_table[] = {
{ .compatible = "st,spear600-fsmc-nand" },
{ .compatible = "stericsson,fsmc-nand" },
{}
};
MODULE_DEVICE_TABLE(of, fsmc_nand_id_table);
-#endif
static struct platform_driver fsmc_nand_driver = {
.remove = fsmc_nand_remove,
.driver = {
.name = "fsmc-nand",
- .of_match_table = of_match_ptr(fsmc_nand_id_table),
+ .of_match_table = fsmc_nand_id_table,
.pm = &fsmc_nand_pm_ops,
},
};
gpio_nand_dosync(gpiomtd);
if (ctrl & NAND_CTRL_CHANGE) {
- gpio_set_value(gpiomtd->plat.gpio_nce, !(ctrl & NAND_NCE));
+ if (gpio_is_valid(gpiomtd->plat.gpio_nce))
+ gpio_set_value(gpiomtd->plat.gpio_nce,
+ !(ctrl & NAND_NCE));
gpio_set_value(gpiomtd->plat.gpio_cle, !!(ctrl & NAND_CLE));
gpio_set_value(gpiomtd->plat.gpio_ale, !!(ctrl & NAND_ALE));
gpio_nand_dosync(gpiomtd);
if (gpio_is_valid(gpiomtd->plat.gpio_nwp))
gpio_set_value(gpiomtd->plat.gpio_nwp, 0);
- gpio_set_value(gpiomtd->plat.gpio_nce, 1);
+ if (gpio_is_valid(gpiomtd->plat.gpio_nce))
+ gpio_set_value(gpiomtd->plat.gpio_nce, 1);
return 0;
}
if (ret)
return ret;
- ret = devm_gpio_request(&pdev->dev, gpiomtd->plat.gpio_nce, "NAND NCE");
- if (ret)
- return ret;
- gpio_direction_output(gpiomtd->plat.gpio_nce, 1);
+ if (gpio_is_valid(gpiomtd->plat.gpio_nce)) {
+ ret = devm_gpio_request(&pdev->dev, gpiomtd->plat.gpio_nce,
+ "NAND NCE");
+ if (ret)
+ return ret;
+ gpio_direction_output(gpiomtd->plat.gpio_nce, 1);
+ }
if (gpio_is_valid(gpiomtd->plat.gpio_nwp)) {
ret = devm_gpio_request(&pdev->dev, gpiomtd->plat.gpio_nwp,
--- /dev/null
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Copyright (C) 2017 NextThing Co
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mtd/nand.h>
+
+static void amd_nand_decode_id(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+
+ nand_decode_ext_id(chip);
+
+ /*
+ * Check for Spansion/AMD ID + repeating 5th, 6th byte since
+ * some Spansion chips have erasesize that conflicts with size
+ * listed in nand_ids table.
+ * Data sheet (5 byte ID): Spansion S30ML-P ORNAND (p.39)
+ */
+ if (chip->id.data[4] != 0x00 && chip->id.data[5] == 0x00 &&
+ chip->id.data[6] == 0x00 && chip->id.data[7] == 0x00 &&
+ mtd->writesize == 512) {
+ mtd->erasesize = 128 * 1024;
+ mtd->erasesize <<= ((chip->id.data[3] & 0x03) << 1);
+ }
+}
+
+static int amd_nand_init(struct nand_chip *chip)
+{
+ if (nand_is_slc(chip))
+ chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
+
+ return 0;
+}
+
+const struct nand_manufacturer_ops amd_nand_manuf_ops = {
+ .detect = amd_nand_decode_id,
+ .init = amd_nand_init,
+};
};
EXPORT_SYMBOL_GPL(nand_ooblayout_lp_ops);
+/*
+ * Support the old "large page" layout used for 1-bit Hamming ECC where ECC
+ * are placed at a fixed offset.
+ */
+static int nand_ooblayout_ecc_lp_hamming(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
+
+ if (section)
+ return -ERANGE;
+
+ switch (mtd->oobsize) {
+ case 64:
+ oobregion->offset = 40;
+ break;
+ case 128:
+ oobregion->offset = 80;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ oobregion->length = ecc->total;
+ if (oobregion->offset + oobregion->length > mtd->oobsize)
+ return -ERANGE;
+
+ return 0;
+}
+
+static int nand_ooblayout_free_lp_hamming(struct mtd_info *mtd, int section,
+ struct mtd_oob_region *oobregion)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct nand_ecc_ctrl *ecc = &chip->ecc;
+ int ecc_offset = 0;
+
+ if (section < 0 || section > 1)
+ return -ERANGE;
+
+ switch (mtd->oobsize) {
+ case 64:
+ ecc_offset = 40;
+ break;
+ case 128:
+ ecc_offset = 80;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (section == 0) {
+ oobregion->offset = 2;
+ oobregion->length = ecc_offset - 2;
+ } else {
+ oobregion->offset = ecc_offset + ecc->total;
+ oobregion->length = mtd->oobsize - oobregion->offset;
+ }
+
+ return 0;
+}
+
+const struct mtd_ooblayout_ops nand_ooblayout_lp_hamming_ops = {
+ .ecc = nand_ooblayout_ecc_lp_hamming,
+ .free = nand_ooblayout_free_lp_hamming,
+};
+
static int check_offs_len(struct mtd_info *mtd,
loff_t ofs, uint64_t len)
{
*/
static int nand_block_bad(struct mtd_info *mtd, loff_t ofs)
{
- int page, res = 0, i = 0;
+ int page, page_end, res;
struct nand_chip *chip = mtd_to_nand(mtd);
- u16 bad;
+ u8 bad;
if (chip->bbt_options & NAND_BBT_SCANLASTPAGE)
ofs += mtd->erasesize - mtd->writesize;
page = (int)(ofs >> chip->page_shift) & chip->pagemask;
+ page_end = page + (chip->bbt_options & NAND_BBT_SCAN2NDPAGE ? 2 : 1);
- do {
- if (chip->options & NAND_BUSWIDTH_16) {
- chip->cmdfunc(mtd, NAND_CMD_READOOB,
- chip->badblockpos & 0xFE, page);
- bad = cpu_to_le16(chip->read_word(mtd));
- if (chip->badblockpos & 0x1)
- bad >>= 8;
- else
- bad &= 0xFF;
- } else {
- chip->cmdfunc(mtd, NAND_CMD_READOOB, chip->badblockpos,
- page);
- bad = chip->read_byte(mtd);
- }
+ for (; page < page_end; page++) {
+ res = chip->ecc.read_oob(mtd, chip, page);
+ if (res)
+ return res;
+
+ bad = chip->oob_poi[chip->badblockpos];
if (likely(chip->badblockbits == 8))
res = bad != 0xFF;
else
res = hweight8(bad) < chip->badblockbits;
- ofs += mtd->writesize;
- page = (int)(ofs >> chip->page_shift) & chip->pagemask;
- i++;
- } while (!res && i < 2 && (chip->bbt_options & NAND_BBT_SCAN2NDPAGE));
+ if (res)
+ return res;
+ }
- return res;
+ return 0;
}
/**
case NAND_CMD_ERASE2:
case NAND_CMD_SEQIN:
case NAND_CMD_STATUS:
+ case NAND_CMD_READID:
+ case NAND_CMD_SET_FEATURES:
return;
case NAND_CMD_RESET:
case NAND_CMD_ERASE2:
case NAND_CMD_SEQIN:
case NAND_CMD_STATUS:
+ case NAND_CMD_READID:
+ case NAND_CMD_SET_FEATURES:
return;
case NAND_CMD_RNDIN:
if (!aligned)
use_bufpoi = 1;
else if (chip->options & NAND_USE_BOUNCE_BUFFER)
- use_bufpoi = !virt_addr_valid(buf);
+ use_bufpoi = !virt_addr_valid(buf) ||
+ !IS_ALIGNED((unsigned long)buf,
+ chip->buf_align);
else
use_bufpoi = 0;
break;
}
- max_bitflips = max_t(unsigned int, max_bitflips, ret);
-
/* Transfer not aligned data */
if (use_bufpoi) {
if (!NAND_HAS_SUBPAGE_READ(chip) && !oob &&
}
buf += bytes;
+ max_bitflips = max_t(unsigned int, max_bitflips, ret);
} else {
memcpy(buf, chip->buffers->databuf + col, bytes);
buf += bytes;
}
/**
- * nand_write_page - [REPLACEABLE] write one page
+ * nand_write_page - write one page
* @mtd: MTD device structure
* @chip: NAND chip descriptor
* @offset: address offset within the page
if (part_pagewr)
use_bufpoi = 1;
else if (chip->options & NAND_USE_BOUNCE_BUFFER)
- use_bufpoi = !virt_addr_valid(buf);
+ use_bufpoi = !virt_addr_valid(buf) ||
+ !IS_ALIGNED((unsigned long)buf,
+ chip->buf_align);
else
use_bufpoi = 0;
/* We still need to erase leftover OOB data */
memset(chip->oob_poi, 0xff, mtd->oobsize);
}
- ret = chip->write_page(mtd, chip, column, bytes, wbuf,
- oob_required, page, cached,
- (ops->mode == MTD_OPS_RAW));
+
+ ret = nand_write_page(mtd, chip, column, bytes, wbuf,
+ oob_required, page, cached,
+ (ops->mode == MTD_OPS_RAW));
if (ret)
break;
}
/* Set default functions */
-static void nand_set_defaults(struct nand_chip *chip, int busw)
+static void nand_set_defaults(struct nand_chip *chip)
{
+ unsigned int busw = chip->options & NAND_BUSWIDTH_16;
+
/* check for proper chip_delay setup, set 20us if not */
if (!chip->chip_delay)
chip->chip_delay = 20;
nand_hw_control_init(chip->controller);
}
+ if (!chip->buf_align)
+ chip->buf_align = 1;
}
/* Sanitize ONFI strings so we can safely print them */
}
/* Parse the Extended Parameter Page. */
-static int nand_flash_detect_ext_param_page(struct mtd_info *mtd,
- struct nand_chip *chip, struct nand_onfi_params *p)
+static int nand_flash_detect_ext_param_page(struct nand_chip *chip,
+ struct nand_onfi_params *p)
{
+ struct mtd_info *mtd = nand_to_mtd(chip);
struct onfi_ext_param_page *ep;
struct onfi_ext_section *s;
struct onfi_ext_ecc_info *ecc;
return ret;
}
-static int nand_setup_read_retry_micron(struct mtd_info *mtd, int retry_mode)
-{
- struct nand_chip *chip = mtd_to_nand(mtd);
- uint8_t feature[ONFI_SUBFEATURE_PARAM_LEN] = {retry_mode};
-
- return chip->onfi_set_features(mtd, chip, ONFI_FEATURE_ADDR_READ_RETRY,
- feature);
-}
-
-/*
- * Configure chip properties from Micron vendor-specific ONFI table
- */
-static void nand_onfi_detect_micron(struct nand_chip *chip,
- struct nand_onfi_params *p)
-{
- struct nand_onfi_vendor_micron *micron = (void *)p->vendor;
-
- if (le16_to_cpu(p->vendor_revision) < 1)
- return;
-
- chip->read_retries = micron->read_retry_options;
- chip->setup_read_retry = nand_setup_read_retry_micron;
-}
-
/*
* Check if the NAND chip is ONFI compliant, returns 1 if it is, 0 otherwise.
*/
-static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip,
- int *busw)
+static int nand_flash_detect_onfi(struct nand_chip *chip)
{
+ struct mtd_info *mtd = nand_to_mtd(chip);
struct nand_onfi_params *p = &chip->onfi_params;
int i, j;
int val;
chip->blocks_per_die = le32_to_cpu(p->blocks_per_lun);
if (onfi_feature(chip) & ONFI_FEATURE_16_BIT_BUS)
- *busw = NAND_BUSWIDTH_16;
- else
- *busw = 0;
+ chip->options |= NAND_BUSWIDTH_16;
if (p->ecc_bits != 0xff) {
chip->ecc_strength_ds = p->ecc_bits;
chip->cmdfunc = nand_command_lp;
/* The Extended Parameter Page is supported since ONFI 2.1. */
- if (nand_flash_detect_ext_param_page(mtd, chip, p))
+ if (nand_flash_detect_ext_param_page(chip, p))
pr_warn("Failed to detect ONFI extended param page\n");
} else {
pr_warn("Could not retrieve ONFI ECC requirements\n");
}
- if (p->jedec_id == NAND_MFR_MICRON)
- nand_onfi_detect_micron(chip, p);
-
return 1;
}
/*
* Check if the NAND chip is JEDEC compliant, returns 1 if it is, 0 otherwise.
*/
-static int nand_flash_detect_jedec(struct mtd_info *mtd, struct nand_chip *chip,
- int *busw)
+static int nand_flash_detect_jedec(struct nand_chip *chip)
{
+ struct mtd_info *mtd = nand_to_mtd(chip);
struct nand_jedec_params *p = &chip->jedec_params;
struct jedec_ecc_info *ecc;
int val;
chip->bits_per_cell = p->bits_per_cell;
if (jedec_feature(chip) & JEDEC_FEATURE_16_BIT_BUS)
- *busw = NAND_BUSWIDTH_16;
- else
- *busw = 0;
+ chip->options |= NAND_BUSWIDTH_16;
/* ECC info */
ecc = &p->ecc_info[0];
* chip. The rest of the parameters must be decoded according to generic or
* manufacturer-specific "extended ID" decoding patterns.
*/
-static void nand_decode_ext_id(struct mtd_info *mtd, struct nand_chip *chip,
- u8 id_data[8], int *busw)
+void nand_decode_ext_id(struct nand_chip *chip)
{
- int extid, id_len;
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ int extid;
+ u8 *id_data = chip->id.data;
/* The 3rd id byte holds MLC / multichip data */
chip->bits_per_cell = nand_get_bits_per_cell(id_data[2]);
/* The 4th id byte is the important one */
extid = id_data[3];
- id_len = nand_id_len(id_data, 8);
-
- /*
- * Field definitions are in the following datasheets:
- * Old style (4,5 byte ID): Samsung K9GAG08U0M (p.32)
- * New Samsung (6 byte ID): Samsung K9GAG08U0F (p.44)
- * Hynix MLC (6 byte ID): Hynix H27UBG8T2B (p.22)
- *
- * Check for ID length, non-zero 6th byte, cell type, and Hynix/Samsung
- * ID to decide what to do.
- */
- if (id_len == 6 && id_data[0] == NAND_MFR_SAMSUNG &&
- !nand_is_slc(chip) && id_data[5] != 0x00) {
- /* Calc pagesize */
- mtd->writesize = 2048 << (extid & 0x03);
- extid >>= 2;
- /* Calc oobsize */
- switch (((extid >> 2) & 0x04) | (extid & 0x03)) {
- case 1:
- mtd->oobsize = 128;
- break;
- case 2:
- mtd->oobsize = 218;
- break;
- case 3:
- mtd->oobsize = 400;
- break;
- case 4:
- mtd->oobsize = 436;
- break;
- case 5:
- mtd->oobsize = 512;
- break;
- case 6:
- mtd->oobsize = 640;
- break;
- case 7:
- default: /* Other cases are "reserved" (unknown) */
- mtd->oobsize = 1024;
- break;
- }
- extid >>= 2;
- /* Calc blocksize */
- mtd->erasesize = (128 * 1024) <<
- (((extid >> 1) & 0x04) | (extid & 0x03));
- *busw = 0;
- } else if (id_len == 6 && id_data[0] == NAND_MFR_HYNIX &&
- !nand_is_slc(chip)) {
- unsigned int tmp;
-
- /* Calc pagesize */
- mtd->writesize = 2048 << (extid & 0x03);
- extid >>= 2;
- /* Calc oobsize */
- switch (((extid >> 2) & 0x04) | (extid & 0x03)) {
- case 0:
- mtd->oobsize = 128;
- break;
- case 1:
- mtd->oobsize = 224;
- break;
- case 2:
- mtd->oobsize = 448;
- break;
- case 3:
- mtd->oobsize = 64;
- break;
- case 4:
- mtd->oobsize = 32;
- break;
- case 5:
- mtd->oobsize = 16;
- break;
- default:
- mtd->oobsize = 640;
- break;
- }
- extid >>= 2;
- /* Calc blocksize */
- tmp = ((extid >> 1) & 0x04) | (extid & 0x03);
- if (tmp < 0x03)
- mtd->erasesize = (128 * 1024) << tmp;
- else if (tmp == 0x03)
- mtd->erasesize = 768 * 1024;
- else
- mtd->erasesize = (64 * 1024) << tmp;
- *busw = 0;
- } else {
- /* Calc pagesize */
- mtd->writesize = 1024 << (extid & 0x03);
- extid >>= 2;
- /* Calc oobsize */
- mtd->oobsize = (8 << (extid & 0x01)) *
- (mtd->writesize >> 9);
- extid >>= 2;
- /* Calc blocksize. Blocksize is multiples of 64KiB */
- mtd->erasesize = (64 * 1024) << (extid & 0x03);
- extid >>= 2;
- /* Get buswidth information */
- *busw = (extid & 0x01) ? NAND_BUSWIDTH_16 : 0;
-
- /*
- * Toshiba 24nm raw SLC (i.e., not BENAND) have 32B OOB per
- * 512B page. For Toshiba SLC, we decode the 5th/6th byte as
- * follows:
- * - ID byte 6, bits[2:0]: 100b -> 43nm, 101b -> 32nm,
- * 110b -> 24nm
- * - ID byte 5, bit[7]: 1 -> BENAND, 0 -> raw SLC
- */
- if (id_len >= 6 && id_data[0] == NAND_MFR_TOSHIBA &&
- nand_is_slc(chip) &&
- (id_data[5] & 0x7) == 0x6 /* 24nm */ &&
- !(id_data[4] & 0x80) /* !BENAND */) {
- mtd->oobsize = 32 * mtd->writesize >> 9;
- }
-
- }
+ /* Calc pagesize */
+ mtd->writesize = 1024 << (extid & 0x03);
+ extid >>= 2;
+ /* Calc oobsize */
+ mtd->oobsize = (8 << (extid & 0x01)) * (mtd->writesize >> 9);
+ extid >>= 2;
+ /* Calc blocksize. Blocksize is multiples of 64KiB */
+ mtd->erasesize = (64 * 1024) << (extid & 0x03);
+ extid >>= 2;
+ /* Get buswidth information */
+ if (extid & 0x1)
+ chip->options |= NAND_BUSWIDTH_16;
}
+EXPORT_SYMBOL_GPL(nand_decode_ext_id);
/*
* Old devices have chip data hardcoded in the device ID table. nand_decode_id
* decodes a matching ID table entry and assigns the MTD size parameters for
* the chip.
*/
-static void nand_decode_id(struct mtd_info *mtd, struct nand_chip *chip,
- struct nand_flash_dev *type, u8 id_data[8],
- int *busw)
+static void nand_decode_id(struct nand_chip *chip, struct nand_flash_dev *type)
{
- int maf_id = id_data[0];
+ struct mtd_info *mtd = nand_to_mtd(chip);
mtd->erasesize = type->erasesize;
mtd->writesize = type->pagesize;
mtd->oobsize = mtd->writesize / 32;
- *busw = type->options & NAND_BUSWIDTH_16;
/* All legacy ID NAND are small-page, SLC */
chip->bits_per_cell = 1;
-
- /*
- * Check for Spansion/AMD ID + repeating 5th, 6th byte since
- * some Spansion chips have erasesize that conflicts with size
- * listed in nand_ids table.
- * Data sheet (5 byte ID): Spansion S30ML-P ORNAND (p.39)
- */
- if (maf_id == NAND_MFR_AMD && id_data[4] != 0x00 && id_data[5] == 0x00
- && id_data[6] == 0x00 && id_data[7] == 0x00
- && mtd->writesize == 512) {
- mtd->erasesize = 128 * 1024;
- mtd->erasesize <<= ((id_data[3] & 0x03) << 1);
- }
}
/*
* heuristic patterns using various detected parameters (e.g., manufacturer,
* page size, cell-type information).
*/
-static void nand_decode_bbm_options(struct mtd_info *mtd,
- struct nand_chip *chip, u8 id_data[8])
+static void nand_decode_bbm_options(struct nand_chip *chip)
{
- int maf_id = id_data[0];
+ struct mtd_info *mtd = nand_to_mtd(chip);
/* Set the bad block position */
if (mtd->writesize > 512 || (chip->options & NAND_BUSWIDTH_16))
chip->badblockpos = NAND_LARGE_BADBLOCK_POS;
else
chip->badblockpos = NAND_SMALL_BADBLOCK_POS;
-
- /*
- * Bad block marker is stored in the last page of each block on Samsung
- * and Hynix MLC devices; stored in first two pages of each block on
- * Micron devices with 2KiB pages and on SLC Samsung, Hynix, Toshiba,
- * AMD/Spansion, and Macronix. All others scan only the first page.
- */
- if (!nand_is_slc(chip) &&
- (maf_id == NAND_MFR_SAMSUNG ||
- maf_id == NAND_MFR_HYNIX))
- chip->bbt_options |= NAND_BBT_SCANLASTPAGE;
- else if ((nand_is_slc(chip) &&
- (maf_id == NAND_MFR_SAMSUNG ||
- maf_id == NAND_MFR_HYNIX ||
- maf_id == NAND_MFR_TOSHIBA ||
- maf_id == NAND_MFR_AMD ||
- maf_id == NAND_MFR_MACRONIX)) ||
- (mtd->writesize == 2048 &&
- maf_id == NAND_MFR_MICRON))
- chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
}
static inline bool is_full_id_nand(struct nand_flash_dev *type)
return type->id_len;
}
-static bool find_full_id_nand(struct mtd_info *mtd, struct nand_chip *chip,
- struct nand_flash_dev *type, u8 *id_data, int *busw)
+static bool find_full_id_nand(struct nand_chip *chip,
+ struct nand_flash_dev *type)
{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ u8 *id_data = chip->id.data;
+
if (!strncmp(type->id, id_data, type->id_len)) {
mtd->writesize = type->pagesize;
mtd->erasesize = type->erasesize;
chip->onfi_timing_mode_default =
type->onfi_timing_mode_default;
- *busw = type->options & NAND_BUSWIDTH_16;
-
if (!mtd->name)
mtd->name = type->name;
return false;
}
+/*
+ * Manufacturer detection. Only used when the NAND is not ONFI or JEDEC
+ * compliant and does not have a full-id or legacy-id entry in the nand_ids
+ * table.
+ */
+static void nand_manufacturer_detect(struct nand_chip *chip)
+{
+ /*
+ * Try manufacturer detection if available and use
+ * nand_decode_ext_id() otherwise.
+ */
+ if (chip->manufacturer.desc && chip->manufacturer.desc->ops &&
+ chip->manufacturer.desc->ops->detect)
+ chip->manufacturer.desc->ops->detect(chip);
+ else
+ nand_decode_ext_id(chip);
+}
+
+/*
+ * Manufacturer initialization. This function is called for all NANDs including
+ * ONFI and JEDEC compliant ones.
+ * Manufacturer drivers should put all their specific initialization code in
+ * their ->init() hook.
+ */
+static int nand_manufacturer_init(struct nand_chip *chip)
+{
+ if (!chip->manufacturer.desc || !chip->manufacturer.desc->ops ||
+ !chip->manufacturer.desc->ops->init)
+ return 0;
+
+ return chip->manufacturer.desc->ops->init(chip);
+}
+
+/*
+ * Manufacturer cleanup. This function is called for all NANDs including
+ * ONFI and JEDEC compliant ones.
+ * Manufacturer drivers should put all their specific cleanup code in their
+ * ->cleanup() hook.
+ */
+static void nand_manufacturer_cleanup(struct nand_chip *chip)
+{
+ /* Release manufacturer private data */
+ if (chip->manufacturer.desc && chip->manufacturer.desc->ops &&
+ chip->manufacturer.desc->ops->cleanup)
+ chip->manufacturer.desc->ops->cleanup(chip);
+}
+
/*
* Get the flash and manufacturer id and lookup if the type is supported.
*/
-static int nand_get_flash_type(struct mtd_info *mtd, struct nand_chip *chip,
- int *maf_id, int *dev_id,
- struct nand_flash_dev *type)
+static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
{
+ const struct nand_manufacturer *manufacturer;
+ struct mtd_info *mtd = nand_to_mtd(chip);
int busw;
- int i, maf_idx;
- u8 id_data[8];
+ int i, ret;
+ u8 *id_data = chip->id.data;
+ u8 maf_id, dev_id;
/*
* Reset the chip, required by some chips (e.g. Micron MT29FxGxxxxx)
chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1);
/* Read manufacturer and device IDs */
- *maf_id = chip->read_byte(mtd);
- *dev_id = chip->read_byte(mtd);
+ maf_id = chip->read_byte(mtd);
+ dev_id = chip->read_byte(mtd);
/*
* Try again to make sure, as some systems the bus-hold or other
for (i = 0; i < 8; i++)
id_data[i] = chip->read_byte(mtd);
- if (id_data[0] != *maf_id || id_data[1] != *dev_id) {
+ if (id_data[0] != maf_id || id_data[1] != dev_id) {
pr_info("second ID read did not match %02x,%02x against %02x,%02x\n",
- *maf_id, *dev_id, id_data[0], id_data[1]);
+ maf_id, dev_id, id_data[0], id_data[1]);
return -ENODEV;
}
+ chip->id.len = nand_id_len(id_data, 8);
+
+ /* Try to identify manufacturer */
+ manufacturer = nand_get_manufacturer(maf_id);
+ chip->manufacturer.desc = manufacturer;
+
if (!type)
type = nand_flash_ids;
+ /*
+ * Save the NAND_BUSWIDTH_16 flag before letting auto-detection logic
+ * override it.
+ * This is required to make sure initial NAND bus width set by the
+ * NAND controller driver is coherent with the real NAND bus width
+ * (extracted by auto-detection code).
+ */
+ busw = chip->options & NAND_BUSWIDTH_16;
+
+ /*
+ * The flag is only set (never cleared), reset it to its default value
+ * before starting auto-detection.
+ */
+ chip->options &= ~NAND_BUSWIDTH_16;
+
for (; type->name != NULL; type++) {
if (is_full_id_nand(type)) {
- if (find_full_id_nand(mtd, chip, type, id_data, &busw))
+ if (find_full_id_nand(chip, type))
goto ident_done;
- } else if (*dev_id == type->dev_id) {
+ } else if (dev_id == type->dev_id) {
break;
}
}
chip->onfi_version = 0;
if (!type->name || !type->pagesize) {
/* Check if the chip is ONFI compliant */
- if (nand_flash_detect_onfi(mtd, chip, &busw))
+ if (nand_flash_detect_onfi(chip))
goto ident_done;
/* Check if the chip is JEDEC compliant */
- if (nand_flash_detect_jedec(mtd, chip, &busw))
+ if (nand_flash_detect_jedec(chip))
goto ident_done;
}
chip->chipsize = (uint64_t)type->chipsize << 20;
- if (!type->pagesize) {
- /* Decode parameters from extended ID */
- nand_decode_ext_id(mtd, chip, id_data, &busw);
- } else {
- nand_decode_id(mtd, chip, type, id_data, &busw);
- }
+ if (!type->pagesize)
+ nand_manufacturer_detect(chip);
+ else
+ nand_decode_id(chip, type);
+
/* Get chip options */
chip->options |= type->options;
- /*
- * Check if chip is not a Samsung device. Do not clear the
- * options for chips which do not have an extended id.
- */
- if (*maf_id != NAND_MFR_SAMSUNG && !type->pagesize)
- chip->options &= ~NAND_SAMSUNG_LP_OPTIONS;
ident_done:
- /* Try to identify manufacturer */
- for (maf_idx = 0; nand_manuf_ids[maf_idx].id != 0x0; maf_idx++) {
- if (nand_manuf_ids[maf_idx].id == *maf_id)
- break;
- }
-
if (chip->options & NAND_BUSWIDTH_AUTO) {
- WARN_ON(chip->options & NAND_BUSWIDTH_16);
- chip->options |= busw;
- nand_set_defaults(chip, busw);
+ WARN_ON(busw & NAND_BUSWIDTH_16);
+ nand_set_defaults(chip);
} else if (busw != (chip->options & NAND_BUSWIDTH_16)) {
/*
* Check, if buswidth is correct. Hardware drivers should set
* chip correct!
*/
pr_info("device found, Manufacturer ID: 0x%02x, Chip ID: 0x%02x\n",
- *maf_id, *dev_id);
- pr_info("%s %s\n", nand_manuf_ids[maf_idx].name, mtd->name);
- pr_warn("bus width %d instead %d bit\n",
- (chip->options & NAND_BUSWIDTH_16) ? 16 : 8,
- busw ? 16 : 8);
+ maf_id, dev_id);
+ pr_info("%s %s\n", nand_manufacturer_name(manufacturer),
+ mtd->name);
+ pr_warn("bus width %d instead of %d bits\n", busw ? 16 : 8,
+ (chip->options & NAND_BUSWIDTH_16) ? 16 : 8);
return -EINVAL;
}
- nand_decode_bbm_options(mtd, chip, id_data);
+ nand_decode_bbm_options(chip);
/* Calculate the address shift from the page size */
chip->page_shift = ffs(mtd->writesize) - 1;
if (mtd->writesize > 512 && chip->cmdfunc == nand_command)
chip->cmdfunc = nand_command_lp;
+ ret = nand_manufacturer_init(chip);
+ if (ret)
+ return ret;
+
pr_info("device found, Manufacturer ID: 0x%02x, Chip ID: 0x%02x\n",
- *maf_id, *dev_id);
+ maf_id, dev_id);
if (chip->onfi_version)
- pr_info("%s %s\n", nand_manuf_ids[maf_idx].name,
- chip->onfi_params.model);
+ pr_info("%s %s\n", nand_manufacturer_name(manufacturer),
+ chip->onfi_params.model);
else if (chip->jedec_version)
- pr_info("%s %s\n", nand_manuf_ids[maf_idx].name,
- chip->jedec_params.model);
+ pr_info("%s %s\n", nand_manufacturer_name(manufacturer),
+ chip->jedec_params.model);
else
- pr_info("%s %s\n", nand_manuf_ids[maf_idx].name,
- type->name);
+ pr_info("%s %s\n", nand_manufacturer_name(manufacturer),
+ type->name);
pr_info("%d MiB, %s, erase size: %d KiB, page size: %d, OOB size: %d\n",
(int)(chip->chipsize >> 20), nand_is_slc(chip) ? "SLC" : "MLC",
ecc_strength = of_get_nand_ecc_strength(dn);
ecc_step = of_get_nand_ecc_step_size(dn);
- if ((ecc_step >= 0 && !(ecc_strength >= 0)) ||
- (!(ecc_step >= 0) && ecc_strength >= 0)) {
- pr_err("must set both strength and step size in DT\n");
- return -EINVAL;
- }
-
if (ecc_mode >= 0)
chip->ecc.mode = ecc_mode;
return -EINVAL;
}
/* Set the default functions */
- nand_set_defaults(chip, chip->options & NAND_BUSWIDTH_16);
+ nand_set_defaults(chip);
/* Read the flash type */
- ret = nand_get_flash_type(mtd, chip, &nand_maf_id, &nand_dev_id, table);
+ ret = nand_detect(chip, table);
if (ret) {
if (!(chip->options & NAND_SCAN_SILENT_NODEV))
pr_warn("No NAND device found\n");
if (ret)
return ret;
+ nand_maf_id = chip->id.data[0];
+ nand_dev_id = chip->id.data[1];
+
chip->select_chip(mtd, -1);
/* Check for a chip array */
{
struct nand_chip *chip = mtd_to_nand(mtd);
struct nand_ecc_ctrl *ecc = &chip->ecc;
- struct nand_buffers *nbuf;
+ struct nand_buffers *nbuf = NULL;
int ret;
/* New bad blocks should be marked in OOB, flash-based BBT, or both */
}
if (!(chip->options & NAND_OWN_BUFFERS)) {
- nbuf = kzalloc(sizeof(*nbuf) + mtd->writesize
- + mtd->oobsize * 3, GFP_KERNEL);
+ nbuf = kzalloc(sizeof(*nbuf), GFP_KERNEL);
if (!nbuf)
return -ENOMEM;
- nbuf->ecccalc = (uint8_t *)(nbuf + 1);
- nbuf->ecccode = nbuf->ecccalc + mtd->oobsize;
- nbuf->databuf = nbuf->ecccode + mtd->oobsize;
+
+ nbuf->ecccalc = kmalloc(mtd->oobsize, GFP_KERNEL);
+ if (!nbuf->ecccalc) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+
+ nbuf->ecccode = kmalloc(mtd->oobsize, GFP_KERNEL);
+ if (!nbuf->ecccode) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+
+ nbuf->databuf = kmalloc(mtd->writesize + mtd->oobsize,
+ GFP_KERNEL);
+ if (!nbuf->databuf) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
chip->buffers = nbuf;
} else {
break;
case 64:
case 128:
- mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+ mtd_set_ooblayout(mtd, &nand_ooblayout_lp_hamming_ops);
break;
default:
WARN(1, "No oob scheme defined for oobsize %d\n",
}
}
- if (!chip->write_page)
- chip->write_page = nand_write_page;
-
/*
* Check ECC mode, default to software if 3byte/512byte hardware ECC is
* selected and we have 256 byte pagesize fallback to software ECC
/* Build bad block table */
return chip->scan_bbt(mtd);
err_free:
- if (!(chip->options & NAND_OWN_BUFFERS))
- kfree(chip->buffers);
+ if (nbuf) {
+ kfree(nbuf->databuf);
+ kfree(nbuf->ecccode);
+ kfree(nbuf->ecccalc);
+ kfree(nbuf);
+ }
return ret;
}
EXPORT_SYMBOL(nand_scan_tail);
/* Free bad block table memory */
kfree(chip->bbt);
- if (!(chip->options & NAND_OWN_BUFFERS))
+ if (!(chip->options & NAND_OWN_BUFFERS) && chip->buffers) {
+ kfree(chip->buffers->databuf);
+ kfree(chip->buffers->ecccode);
+ kfree(chip->buffers->ecccalc);
kfree(chip->buffers);
+ }
/* Free bad block descriptor memory */
if (chip->badblock_pattern && chip->badblock_pattern->options
& NAND_BBT_DYNAMICSTRUCT)
kfree(chip->badblock_pattern);
+
+ /* Free manufacturer priv data. */
+ nand_manufacturer_cleanup(chip);
}
EXPORT_SYMBOL_GPL(nand_cleanup);
--- /dev/null
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Copyright (C) 2017 NextThing Co
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mtd/nand.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+
+#define NAND_HYNIX_CMD_SET_PARAMS 0x36
+#define NAND_HYNIX_CMD_APPLY_PARAMS 0x16
+
+#define NAND_HYNIX_1XNM_RR_REPEAT 8
+
+/**
+ * struct hynix_read_retry - read-retry data
+ * @nregs: number of register to set when applying a new read-retry mode
+ * @regs: register offsets (NAND chip dependent)
+ * @values: array of values to set in registers. The array size is equal to
+ * (nregs * nmodes)
+ */
+struct hynix_read_retry {
+ int nregs;
+ const u8 *regs;
+ u8 values[0];
+};
+
+/**
+ * struct hynix_nand - private Hynix NAND struct
+ * @nand_technology: manufacturing process expressed in picometer
+ * @read_retry: read-retry information
+ */
+struct hynix_nand {
+ const struct hynix_read_retry *read_retry;
+};
+
+/**
+ * struct hynix_read_retry_otp - structure describing how the read-retry OTP
+ * area
+ * @nregs: number of hynix private registers to set before reading the reading
+ * the OTP area
+ * @regs: registers that should be configured
+ * @values: values that should be set in regs
+ * @page: the address to pass to the READ_PAGE command. Depends on the NAND
+ * chip
+ * @size: size of the read-retry OTP section
+ */
+struct hynix_read_retry_otp {
+ int nregs;
+ const u8 *regs;
+ const u8 *values;
+ int page;
+ int size;
+};
+
+static bool hynix_nand_has_valid_jedecid(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ u8 jedecid[6] = { };
+ int i = 0;
+
+ chip->cmdfunc(mtd, NAND_CMD_READID, 0x40, -1);
+ for (i = 0; i < 5; i++)
+ jedecid[i] = chip->read_byte(mtd);
+
+ return !strcmp("JEDEC", jedecid);
+}
+
+static int hynix_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ struct hynix_nand *hynix = nand_get_manufacturer_data(chip);
+ const u8 *values;
+ int status;
+ int i;
+
+ values = hynix->read_retry->values +
+ (retry_mode * hynix->read_retry->nregs);
+
+ /* Enter 'Set Hynix Parameters' mode */
+ chip->cmdfunc(mtd, NAND_HYNIX_CMD_SET_PARAMS, -1, -1);
+
+ /*
+ * Configure the NAND in the requested read-retry mode.
+ * This is done by setting pre-defined values in internal NAND
+ * registers.
+ *
+ * The set of registers is NAND specific, and the values are either
+ * predefined or extracted from an OTP area on the NAND (values are
+ * probably tweaked at production in this case).
+ */
+ for (i = 0; i < hynix->read_retry->nregs; i++) {
+ int column = hynix->read_retry->regs[i];
+
+ column |= column << 8;
+ chip->cmdfunc(mtd, NAND_CMD_NONE, column, -1);
+ chip->write_byte(mtd, values[i]);
+ }
+
+ /* Apply the new settings. */
+ chip->cmdfunc(mtd, NAND_HYNIX_CMD_APPLY_PARAMS, -1, -1);
+
+ status = chip->waitfunc(mtd, chip);
+ if (status & NAND_STATUS_FAIL)
+ return -EIO;
+
+ return 0;
+}
+
+/**
+ * hynix_get_majority - get the value that is occurring the most in a given
+ * set of values
+ * @in: the array of values to test
+ * @repeat: the size of the in array
+ * @out: pointer used to store the output value
+ *
+ * This function implements the 'majority check' logic that is supposed to
+ * overcome the unreliability of MLC NANDs when reading the OTP area storing
+ * the read-retry parameters.
+ *
+ * It's based on a pretty simple assumption: if we repeat the same value
+ * several times and then take the one that is occurring the most, we should
+ * find the correct value.
+ * Let's hope this dummy algorithm prevents us from losing the read-retry
+ * parameters.
+ */
+static int hynix_get_majority(const u8 *in, int repeat, u8 *out)
+{
+ int i, j, half = repeat / 2;
+
+ /*
+ * We only test the first half of the in array because we must ensure
+ * that the value is at least occurring repeat / 2 times.
+ *
+ * This loop is suboptimal since we may count the occurrences of the
+ * same value several time, but we are doing that on small sets, which
+ * makes it acceptable.
+ */
+ for (i = 0; i < half; i++) {
+ int cnt = 0;
+ u8 val = in[i];
+
+ /* Count all values that are matching the one at index i. */
+ for (j = i + 1; j < repeat; j++) {
+ if (in[j] == val)
+ cnt++;
+ }
+
+ /* We found a value occurring more than repeat / 2. */
+ if (cnt > half) {
+ *out = val;
+ return 0;
+ }
+ }
+
+ return -EIO;
+}
+
+static int hynix_read_rr_otp(struct nand_chip *chip,
+ const struct hynix_read_retry_otp *info,
+ void *buf)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ int i;
+
+ chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+
+ chip->cmdfunc(mtd, NAND_HYNIX_CMD_SET_PARAMS, -1, -1);
+
+ for (i = 0; i < info->nregs; i++) {
+ int column = info->regs[i];
+
+ column |= column << 8;
+ chip->cmdfunc(mtd, NAND_CMD_NONE, column, -1);
+ chip->write_byte(mtd, info->values[i]);
+ }
+
+ chip->cmdfunc(mtd, NAND_HYNIX_CMD_APPLY_PARAMS, -1, -1);
+
+ /* Sequence to enter OTP mode? */
+ chip->cmdfunc(mtd, 0x17, -1, -1);
+ chip->cmdfunc(mtd, 0x04, -1, -1);
+ chip->cmdfunc(mtd, 0x19, -1, -1);
+
+ /* Now read the page */
+ chip->cmdfunc(mtd, NAND_CMD_READ0, 0x0, info->page);
+ chip->read_buf(mtd, buf, info->size);
+
+ /* Put everything back to normal */
+ chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+ chip->cmdfunc(mtd, NAND_HYNIX_CMD_SET_PARAMS, 0x38, -1);
+ chip->write_byte(mtd, 0x0);
+ chip->cmdfunc(mtd, NAND_HYNIX_CMD_APPLY_PARAMS, -1, -1);
+ chip->cmdfunc(mtd, NAND_CMD_READ0, 0x0, -1);
+
+ return 0;
+}
+
+#define NAND_HYNIX_1XNM_RR_COUNT_OFFS 0
+#define NAND_HYNIX_1XNM_RR_REG_COUNT_OFFS 8
+#define NAND_HYNIX_1XNM_RR_SET_OFFS(x, setsize, inv) \
+ (16 + ((((x) * 2) + ((inv) ? 1 : 0)) * (setsize)))
+
+static int hynix_mlc_1xnm_rr_value(const u8 *buf, int nmodes, int nregs,
+ int mode, int reg, bool inv, u8 *val)
+{
+ u8 tmp[NAND_HYNIX_1XNM_RR_REPEAT];
+ int val_offs = (mode * nregs) + reg;
+ int set_size = nmodes * nregs;
+ int i, ret;
+
+ for (i = 0; i < NAND_HYNIX_1XNM_RR_REPEAT; i++) {
+ int set_offs = NAND_HYNIX_1XNM_RR_SET_OFFS(i, set_size, inv);
+
+ tmp[i] = buf[val_offs + set_offs];
+ }
+
+ ret = hynix_get_majority(tmp, NAND_HYNIX_1XNM_RR_REPEAT, val);
+ if (ret)
+ return ret;
+
+ if (inv)
+ *val = ~*val;
+
+ return 0;
+}
+
+static u8 hynix_1xnm_mlc_read_retry_regs[] = {
+ 0xcc, 0xbf, 0xaa, 0xab, 0xcd, 0xad, 0xae, 0xaf
+};
+
+static int hynix_mlc_1xnm_rr_init(struct nand_chip *chip,
+ const struct hynix_read_retry_otp *info)
+{
+ struct hynix_nand *hynix = nand_get_manufacturer_data(chip);
+ struct hynix_read_retry *rr = NULL;
+ int ret, i, j;
+ u8 nregs, nmodes;
+ u8 *buf;
+
+ buf = kmalloc(info->size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ ret = hynix_read_rr_otp(chip, info, buf);
+ if (ret)
+ goto out;
+
+ ret = hynix_get_majority(buf, NAND_HYNIX_1XNM_RR_REPEAT,
+ &nmodes);
+ if (ret)
+ goto out;
+
+ ret = hynix_get_majority(buf + NAND_HYNIX_1XNM_RR_REPEAT,
+ NAND_HYNIX_1XNM_RR_REPEAT,
+ &nregs);
+ if (ret)
+ goto out;
+
+ rr = kzalloc(sizeof(*rr) + (nregs * nmodes), GFP_KERNEL);
+ if (!rr) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < nmodes; i++) {
+ for (j = 0; j < nregs; j++) {
+ u8 *val = rr->values + (i * nregs);
+
+ ret = hynix_mlc_1xnm_rr_value(buf, nmodes, nregs, i, j,
+ false, val);
+ if (!ret)
+ continue;
+
+ ret = hynix_mlc_1xnm_rr_value(buf, nmodes, nregs, i, j,
+ true, val);
+ if (ret)
+ goto out;
+ }
+ }
+
+ rr->nregs = nregs;
+ rr->regs = hynix_1xnm_mlc_read_retry_regs;
+ hynix->read_retry = rr;
+ chip->setup_read_retry = hynix_nand_setup_read_retry;
+ chip->read_retries = nmodes;
+
+out:
+ kfree(buf);
+
+ if (ret)
+ kfree(rr);
+
+ return ret;
+}
+
+static const u8 hynix_mlc_1xnm_rr_otp_regs[] = { 0x38 };
+static const u8 hynix_mlc_1xnm_rr_otp_values[] = { 0x52 };
+
+static const struct hynix_read_retry_otp hynix_mlc_1xnm_rr_otps[] = {
+ {
+ .nregs = ARRAY_SIZE(hynix_mlc_1xnm_rr_otp_regs),
+ .regs = hynix_mlc_1xnm_rr_otp_regs,
+ .values = hynix_mlc_1xnm_rr_otp_values,
+ .page = 0x21f,
+ .size = 784
+ },
+ {
+ .nregs = ARRAY_SIZE(hynix_mlc_1xnm_rr_otp_regs),
+ .regs = hynix_mlc_1xnm_rr_otp_regs,
+ .values = hynix_mlc_1xnm_rr_otp_values,
+ .page = 0x200,
+ .size = 528,
+ },
+};
+
+static int hynix_nand_rr_init(struct nand_chip *chip)
+{
+ int i, ret = 0;
+ bool valid_jedecid;
+
+ valid_jedecid = hynix_nand_has_valid_jedecid(chip);
+
+ /*
+ * We only support read-retry for 1xnm NANDs, and those NANDs all
+ * expose a valid JEDEC ID.
+ */
+ if (valid_jedecid) {
+ u8 nand_tech = chip->id.data[5] >> 4;
+
+ /* 1xnm technology */
+ if (nand_tech == 4) {
+ for (i = 0; i < ARRAY_SIZE(hynix_mlc_1xnm_rr_otps);
+ i++) {
+ /*
+ * FIXME: Hynix recommend to copy the
+ * read-retry OTP area into a normal page.
+ */
+ ret = hynix_mlc_1xnm_rr_init(chip,
+ hynix_mlc_1xnm_rr_otps);
+ if (!ret)
+ break;
+ }
+ }
+ }
+
+ if (ret)
+ pr_warn("failed to initialize read-retry infrastructure");
+
+ return 0;
+}
+
+static void hynix_nand_extract_oobsize(struct nand_chip *chip,
+ bool valid_jedecid)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ u8 oobsize;
+
+ oobsize = ((chip->id.data[3] >> 2) & 0x3) |
+ ((chip->id.data[3] >> 4) & 0x4);
+
+ if (valid_jedecid) {
+ switch (oobsize) {
+ case 0:
+ mtd->oobsize = 2048;
+ break;
+ case 1:
+ mtd->oobsize = 1664;
+ break;
+ case 2:
+ mtd->oobsize = 1024;
+ break;
+ case 3:
+ mtd->oobsize = 640;
+ break;
+ default:
+ /*
+ * We should never reach this case, but if that
+ * happens, this probably means Hynix decided to use
+ * a different extended ID format, and we should find
+ * a way to support it.
+ */
+ WARN(1, "Invalid OOB size");
+ break;
+ }
+ } else {
+ switch (oobsize) {
+ case 0:
+ mtd->oobsize = 128;
+ break;
+ case 1:
+ mtd->oobsize = 224;
+ break;
+ case 2:
+ mtd->oobsize = 448;
+ break;
+ case 3:
+ mtd->oobsize = 64;
+ break;
+ case 4:
+ mtd->oobsize = 32;
+ break;
+ case 5:
+ mtd->oobsize = 16;
+ break;
+ case 6:
+ mtd->oobsize = 640;
+ break;
+ default:
+ /*
+ * We should never reach this case, but if that
+ * happens, this probably means Hynix decided to use
+ * a different extended ID format, and we should find
+ * a way to support it.
+ */
+ WARN(1, "Invalid OOB size");
+ break;
+ }
+ }
+}
+
+static void hynix_nand_extract_ecc_requirements(struct nand_chip *chip,
+ bool valid_jedecid)
+{
+ u8 ecc_level = (chip->id.data[4] >> 4) & 0x7;
+
+ if (valid_jedecid) {
+ /* Reference: H27UCG8T2E datasheet */
+ chip->ecc_step_ds = 1024;
+
+ switch (ecc_level) {
+ case 0:
+ chip->ecc_step_ds = 0;
+ chip->ecc_strength_ds = 0;
+ break;
+ case 1:
+ chip->ecc_strength_ds = 4;
+ break;
+ case 2:
+ chip->ecc_strength_ds = 24;
+ break;
+ case 3:
+ chip->ecc_strength_ds = 32;
+ break;
+ case 4:
+ chip->ecc_strength_ds = 40;
+ break;
+ case 5:
+ chip->ecc_strength_ds = 50;
+ break;
+ case 6:
+ chip->ecc_strength_ds = 60;
+ break;
+ default:
+ /*
+ * We should never reach this case, but if that
+ * happens, this probably means Hynix decided to use
+ * a different extended ID format, and we should find
+ * a way to support it.
+ */
+ WARN(1, "Invalid ECC requirements");
+ }
+ } else {
+ /*
+ * The ECC requirements field meaning depends on the
+ * NAND technology.
+ */
+ u8 nand_tech = chip->id.data[5] & 0x3;
+
+ if (nand_tech < 3) {
+ /* > 26nm, reference: H27UBG8T2A datasheet */
+ if (ecc_level < 5) {
+ chip->ecc_step_ds = 512;
+ chip->ecc_strength_ds = 1 << ecc_level;
+ } else if (ecc_level < 7) {
+ if (ecc_level == 5)
+ chip->ecc_step_ds = 2048;
+ else
+ chip->ecc_step_ds = 1024;
+ chip->ecc_strength_ds = 24;
+ } else {
+ /*
+ * We should never reach this case, but if that
+ * happens, this probably means Hynix decided
+ * to use a different extended ID format, and
+ * we should find a way to support it.
+ */
+ WARN(1, "Invalid ECC requirements");
+ }
+ } else {
+ /* <= 26nm, reference: H27UBG8T2B datasheet */
+ if (!ecc_level) {
+ chip->ecc_step_ds = 0;
+ chip->ecc_strength_ds = 0;
+ } else if (ecc_level < 5) {
+ chip->ecc_step_ds = 512;
+ chip->ecc_strength_ds = 1 << (ecc_level - 1);
+ } else {
+ chip->ecc_step_ds = 1024;
+ chip->ecc_strength_ds = 24 +
+ (8 * (ecc_level - 5));
+ }
+ }
+ }
+}
+
+static void hynix_nand_extract_scrambling_requirements(struct nand_chip *chip,
+ bool valid_jedecid)
+{
+ u8 nand_tech;
+
+ /* We need scrambling on all TLC NANDs*/
+ if (chip->bits_per_cell > 2)
+ chip->options |= NAND_NEED_SCRAMBLING;
+
+ /* And on MLC NANDs with sub-3xnm process */
+ if (valid_jedecid) {
+ nand_tech = chip->id.data[5] >> 4;
+
+ /* < 3xnm */
+ if (nand_tech > 0)
+ chip->options |= NAND_NEED_SCRAMBLING;
+ } else {
+ nand_tech = chip->id.data[5] & 0x3;
+
+ /* < 32nm */
+ if (nand_tech > 2)
+ chip->options |= NAND_NEED_SCRAMBLING;
+ }
+}
+
+static void hynix_nand_decode_id(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ bool valid_jedecid;
+ u8 tmp;
+
+ /*
+ * Exclude all SLC NANDs from this advanced detection scheme.
+ * According to the ranges defined in several datasheets, it might
+ * appear that even SLC NANDs could fall in this extended ID scheme.
+ * If that the case rework the test to let SLC NANDs go through the
+ * detection process.
+ */
+ if (chip->id.len < 6 || nand_is_slc(chip)) {
+ nand_decode_ext_id(chip);
+ return;
+ }
+
+ /* Extract pagesize */
+ mtd->writesize = 2048 << (chip->id.data[3] & 0x03);
+
+ tmp = (chip->id.data[3] >> 4) & 0x3;
+ /*
+ * When bit7 is set that means we start counting at 1MiB, otherwise
+ * we start counting at 128KiB and shift this value the content of
+ * ID[3][4:5].
+ * The only exception is when ID[3][4:5] == 3 and ID[3][7] == 0, in
+ * this case the erasesize is set to 768KiB.
+ */
+ if (chip->id.data[3] & 0x80)
+ mtd->erasesize = SZ_1M << tmp;
+ else if (tmp == 3)
+ mtd->erasesize = SZ_512K + SZ_256K;
+ else
+ mtd->erasesize = SZ_128K << tmp;
+
+ /*
+ * Modern Toggle DDR NANDs have a valid JEDECID even though they are
+ * not exposing a valid JEDEC parameter table.
+ * These NANDs use a different NAND ID scheme.
+ */
+ valid_jedecid = hynix_nand_has_valid_jedecid(chip);
+
+ hynix_nand_extract_oobsize(chip, valid_jedecid);
+ hynix_nand_extract_ecc_requirements(chip, valid_jedecid);
+ hynix_nand_extract_scrambling_requirements(chip, valid_jedecid);
+}
+
+static void hynix_nand_cleanup(struct nand_chip *chip)
+{
+ struct hynix_nand *hynix = nand_get_manufacturer_data(chip);
+
+ if (!hynix)
+ return;
+
+ kfree(hynix->read_retry);
+ kfree(hynix);
+ nand_set_manufacturer_data(chip, NULL);
+}
+
+static int hynix_nand_init(struct nand_chip *chip)
+{
+ struct hynix_nand *hynix;
+ int ret;
+
+ if (!nand_is_slc(chip))
+ chip->bbt_options |= NAND_BBT_SCANLASTPAGE;
+ else
+ chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
+
+ hynix = kzalloc(sizeof(*hynix), GFP_KERNEL);
+ if (!hynix)
+ return -ENOMEM;
+
+ nand_set_manufacturer_data(chip, hynix);
+
+ ret = hynix_nand_rr_init(chip);
+ if (ret)
+ hynix_nand_cleanup(chip);
+
+ return ret;
+}
+
+const struct nand_manufacturer_ops hynix_nand_manuf_ops = {
+ .detect = hynix_nand_decode_id,
+ .init = hynix_nand_init,
+ .cleanup = hynix_nand_cleanup,
+};
#include <linux/mtd/nand.h>
#include <linux/sizes.h>
-#define LP_OPTIONS NAND_SAMSUNG_LP_OPTIONS
+#define LP_OPTIONS 0
#define LP_OPTIONS16 (LP_OPTIONS | NAND_BUSWIDTH_16)
#define SP_OPTIONS NAND_NEED_READRDY
};
/* Manufacturer IDs */
-struct nand_manufacturers nand_manuf_ids[] = {
- {NAND_MFR_TOSHIBA, "Toshiba"},
+static const struct nand_manufacturer nand_manufacturers[] = {
+ {NAND_MFR_TOSHIBA, "Toshiba", &toshiba_nand_manuf_ops},
{NAND_MFR_ESMT, "ESMT"},
- {NAND_MFR_SAMSUNG, "Samsung"},
+ {NAND_MFR_SAMSUNG, "Samsung", &samsung_nand_manuf_ops},
{NAND_MFR_FUJITSU, "Fujitsu"},
{NAND_MFR_NATIONAL, "National"},
{NAND_MFR_RENESAS, "Renesas"},
{NAND_MFR_STMICRO, "ST Micro"},
- {NAND_MFR_HYNIX, "Hynix"},
- {NAND_MFR_MICRON, "Micron"},
- {NAND_MFR_AMD, "AMD/Spansion"},
- {NAND_MFR_MACRONIX, "Macronix"},
+ {NAND_MFR_HYNIX, "Hynix", &hynix_nand_manuf_ops},
+ {NAND_MFR_MICRON, "Micron", µn_nand_manuf_ops},
+ {NAND_MFR_AMD, "AMD/Spansion", &amd_nand_manuf_ops},
+ {NAND_MFR_MACRONIX, "Macronix", ¯onix_nand_manuf_ops},
{NAND_MFR_EON, "Eon"},
{NAND_MFR_SANDISK, "SanDisk"},
{NAND_MFR_INTEL, "Intel"},
{NAND_MFR_ATO, "ATO"},
{NAND_MFR_WINBOND, "Winbond"},
- {0x0, "Unknown"}
};
-EXPORT_SYMBOL(nand_manuf_ids);
-EXPORT_SYMBOL(nand_flash_ids);
+/**
+ * nand_get_manufacturer - Get manufacturer information from the manufacturer
+ * ID
+ * @id: manufacturer ID
+ *
+ * Returns a pointer a nand_manufacturer object if the manufacturer is defined
+ * in the NAND manufacturers database, NULL otherwise.
+ */
+const struct nand_manufacturer *nand_get_manufacturer(u8 id)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(nand_manufacturers); i++)
+ if (nand_manufacturers[i].id == id)
+ return &nand_manufacturers[i];
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Thomas Gleixner <tglx@linutronix.de>");
-MODULE_DESCRIPTION("Nand device & manufacturer IDs");
+ return NULL;
+}
--- /dev/null
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Copyright (C) 2017 NextThing Co
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mtd/nand.h>
+
+static int macronix_nand_init(struct nand_chip *chip)
+{
+ if (nand_is_slc(chip))
+ chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
+
+ return 0;
+}
+
+const struct nand_manufacturer_ops macronix_nand_manuf_ops = {
+ .init = macronix_nand_init,
+};
--- /dev/null
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Copyright (C) 2017 NextThing Co
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mtd/nand.h>
+
+struct nand_onfi_vendor_micron {
+ u8 two_plane_read;
+ u8 read_cache;
+ u8 read_unique_id;
+ u8 dq_imped;
+ u8 dq_imped_num_settings;
+ u8 dq_imped_feat_addr;
+ u8 rb_pulldown_strength;
+ u8 rb_pulldown_strength_feat_addr;
+ u8 rb_pulldown_strength_num_settings;
+ u8 otp_mode;
+ u8 otp_page_start;
+ u8 otp_data_prot_addr;
+ u8 otp_num_pages;
+ u8 otp_feat_addr;
+ u8 read_retry_options;
+ u8 reserved[72];
+ u8 param_revision;
+} __packed;
+
+static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
+{
+ struct nand_chip *chip = mtd_to_nand(mtd);
+ u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = {retry_mode};
+
+ return chip->onfi_set_features(mtd, chip, ONFI_FEATURE_ADDR_READ_RETRY,
+ feature);
+}
+
+/*
+ * Configure chip properties from Micron vendor-specific ONFI table
+ */
+static int micron_nand_onfi_init(struct nand_chip *chip)
+{
+ struct nand_onfi_params *p = &chip->onfi_params;
+ struct nand_onfi_vendor_micron *micron = (void *)p->vendor;
+
+ if (!chip->onfi_version)
+ return 0;
+
+ if (le16_to_cpu(p->vendor_revision) < 1)
+ return 0;
+
+ chip->read_retries = micron->read_retry_options;
+ chip->setup_read_retry = micron_nand_setup_read_retry;
+
+ return 0;
+}
+
+static int micron_nand_init(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+ int ret;
+
+ ret = micron_nand_onfi_init(chip);
+ if (ret)
+ return ret;
+
+ if (mtd->writesize == 2048)
+ chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
+
+ return 0;
+}
+
+const struct nand_manufacturer_ops micron_nand_manuf_ops = {
+ .init = micron_nand_init,
+};
--- /dev/null
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Copyright (C) 2017 NextThing Co
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mtd/nand.h>
+
+static void samsung_nand_decode_id(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+
+ /* New Samsung (6 byte ID): Samsung K9GAG08U0F (p.44) */
+ if (chip->id.len == 6 && !nand_is_slc(chip) &&
+ chip->id.data[5] != 0x00) {
+ u8 extid = chip->id.data[3];
+
+ /* Get pagesize */
+ mtd->writesize = 2048 << (extid & 0x03);
+
+ extid >>= 2;
+
+ /* Get oobsize */
+ switch (((extid >> 2) & 0x4) | (extid & 0x3)) {
+ case 1:
+ mtd->oobsize = 128;
+ break;
+ case 2:
+ mtd->oobsize = 218;
+ break;
+ case 3:
+ mtd->oobsize = 400;
+ break;
+ case 4:
+ mtd->oobsize = 436;
+ break;
+ case 5:
+ mtd->oobsize = 512;
+ break;
+ case 6:
+ mtd->oobsize = 640;
+ break;
+ default:
+ /*
+ * We should never reach this case, but if that
+ * happens, this probably means Samsung decided to use
+ * a different extended ID format, and we should find
+ * a way to support it.
+ */
+ WARN(1, "Invalid OOB size value");
+ break;
+ }
+
+ /* Get blocksize */
+ extid >>= 2;
+ mtd->erasesize = (128 * 1024) <<
+ (((extid >> 1) & 0x04) | (extid & 0x03));
+
+ /* Extract ECC requirements from 5th id byte*/
+ extid = (chip->id.data[4] >> 4) & 0x07;
+ if (extid < 5) {
+ chip->ecc_step_ds = 512;
+ chip->ecc_strength_ds = 1 << extid;
+ } else {
+ chip->ecc_step_ds = 1024;
+ switch (extid) {
+ case 5:
+ chip->ecc_strength_ds = 24;
+ break;
+ case 6:
+ chip->ecc_strength_ds = 40;
+ break;
+ case 7:
+ chip->ecc_strength_ds = 60;
+ break;
+ }
+ }
+ } else {
+ nand_decode_ext_id(chip);
+ }
+}
+
+static int samsung_nand_init(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+
+ if (mtd->writesize > 512)
+ chip->options |= NAND_SAMSUNG_LP_OPTIONS;
+
+ if (!nand_is_slc(chip))
+ chip->bbt_options |= NAND_BBT_SCANLASTPAGE;
+ else
+ chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
+
+ return 0;
+}
+
+const struct nand_manufacturer_ops samsung_nand_manuf_ops = {
+ .detect = samsung_nand_decode_id,
+ .init = samsung_nand_init,
+};
--- /dev/null
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Copyright (C) 2017 NextThing Co
+ *
+ * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/mtd/nand.h>
+
+static void toshiba_nand_decode_id(struct nand_chip *chip)
+{
+ struct mtd_info *mtd = nand_to_mtd(chip);
+
+ nand_decode_ext_id(chip);
+
+ /*
+ * Toshiba 24nm raw SLC (i.e., not BENAND) have 32B OOB per
+ * 512B page. For Toshiba SLC, we decode the 5th/6th byte as
+ * follows:
+ * - ID byte 6, bits[2:0]: 100b -> 43nm, 101b -> 32nm,
+ * 110b -> 24nm
+ * - ID byte 5, bit[7]: 1 -> BENAND, 0 -> raw SLC
+ */
+ if (chip->id.len >= 6 && nand_is_slc(chip) &&
+ (chip->id.data[5] & 0x7) == 0x6 /* 24nm */ &&
+ !(chip->id.data[4] & 0x80) /* !BENAND */)
+ mtd->oobsize = 32 * mtd->writesize >> 9;
+}
+
+static int toshiba_nand_init(struct nand_chip *chip)
+{
+ if (nand_is_slc(chip))
+ chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
+
+ return 0;
+}
+
+const struct nand_manufacturer_ops toshiba_nand_manuf_ops = {
+ .detect = toshiba_nand_decode_id,
+ .init = toshiba_nand_init,
+};
zero_ok = (*w == '0' ? 1 : 0);
page_no = simple_strtoul(w, &w, 0);
if (!zero_ok && !page_no) {
- NS_ERR("invalid weakpagess.\n");
+ NS_ERR("invalid weakpages.\n");
return -EINVAL;
}
max_writes = 3;
nand_chip->ecc.priv = NULL;
nand_set_flash_node(nand_chip, dev->of_node);
+ if (!mtd->name) {
+ mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+ "omap2-nand.%d", info->gpmc_cs);
+ if (!mtd->name) {
+ dev_err(&pdev->dev, "Failed to set MTD name\n");
+ return -ENOMEM;
+ }
+ }
+
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(nand_chip->IO_ADDR_R))
#include <asm/sizes.h>
#include <linux/platform_data/mtd-orion_nand.h>
+struct orion_nand_info {
+ struct nand_chip chip;
+ struct clk *clk;
+};
+
static void orion_nand_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
{
struct nand_chip *nc = mtd_to_nand(mtd);
static int __init orion_nand_probe(struct platform_device *pdev)
{
+ struct orion_nand_info *info;
struct mtd_info *mtd;
struct nand_chip *nc;
struct orion_nand_data *board;
struct resource *res;
- struct clk *clk;
void __iomem *io_base;
int ret = 0;
u32 val = 0;
- nc = devm_kzalloc(&pdev->dev,
- sizeof(struct nand_chip),
+ info = devm_kzalloc(&pdev->dev,
+ sizeof(struct orion_nand_info),
GFP_KERNEL);
- if (!nc)
+ if (!info)
return -ENOMEM;
+ nc = &info->chip;
mtd = nand_to_mtd(nc);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (board->dev_ready)
nc->dev_ready = board->dev_ready;
- platform_set_drvdata(pdev, mtd);
+ platform_set_drvdata(pdev, info);
/* Not all platforms can gate the clock, so it is not
an error if the clock does not exists. */
- clk = clk_get(&pdev->dev, NULL);
- if (!IS_ERR(clk)) {
- clk_prepare_enable(clk);
- clk_put(clk);
+ info->clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(info->clk)) {
+ ret = PTR_ERR(info->clk);
+ if (ret == -ENOENT) {
+ info->clk = NULL;
+ } else {
+ dev_err(&pdev->dev, "failed to get clock!\n");
+ return ret;
+ }
}
+ clk_prepare_enable(info->clk);
+
ret = nand_scan(mtd, 1);
if (ret)
goto no_dev;
return 0;
no_dev:
- if (!IS_ERR(clk)) {
- clk_disable_unprepare(clk);
- clk_put(clk);
- }
-
+ clk_disable_unprepare(info->clk);
return ret;
}
static int orion_nand_remove(struct platform_device *pdev)
{
- struct mtd_info *mtd = platform_get_drvdata(pdev);
- struct clk *clk;
+ struct orion_nand_info *info = platform_get_drvdata(pdev);
+ struct nand_chip *chip = &info->chip;
+ struct mtd_info *mtd = nand_to_mtd(chip);
nand_release(mtd);
- clk = clk_get(&pdev->dev, NULL);
- if (!IS_ERR(clk)) {
- clk_disable_unprepare(clk);
- clk_put(clk);
- }
+ clk_disable_unprepare(info->clk);
return 0;
}
int err = 0;
/* Allocate memory for the device structure (and zero it) */
- oxnas = devm_kzalloc(&pdev->dev, sizeof(struct nand_chip),
+ oxnas = devm_kzalloc(&pdev->dev, sizeof(*oxnas),
GFP_KERNEL);
if (!oxnas)
return -ENOMEM;
goto out_ahb_clk_unprepare;
nfc->reset = devm_reset_control_get_optional(dev, "ahb");
- if (!IS_ERR(nfc->reset)) {
- ret = reset_control_deassert(nfc->reset);
- if (ret) {
- dev_err(dev, "reset err %d\n", ret);
- goto out_mod_clk_unprepare;
- }
- } else if (PTR_ERR(nfc->reset) != -ENOENT) {
+ if (IS_ERR(nfc->reset)) {
ret = PTR_ERR(nfc->reset);
goto out_mod_clk_unprepare;
}
+ ret = reset_control_deassert(nfc->reset);
+ if (ret) {
+ dev_err(dev, "reset err %d\n", ret);
+ goto out_mod_clk_unprepare;
+ }
+
ret = sunxi_nfc_rst(nfc);
if (ret)
goto out_ahb_reset_reassert;
if (nfc->dmac)
dma_release_channel(nfc->dmac);
out_ahb_reset_reassert:
- if (!IS_ERR(nfc->reset))
- reset_control_assert(nfc->reset);
+ reset_control_assert(nfc->reset);
out_mod_clk_unprepare:
clk_disable_unprepare(nfc->mod_clk);
out_ahb_clk_unprepare:
sunxi_nand_chips_cleanup(nfc);
- if (!IS_ERR(nfc->reset))
- reset_control_assert(nfc->reset);
+ reset_control_assert(nfc->reset);
if (nfc->dmac)
dma_release_channel(nfc->dmac);
complete(arg);
}
-static int do_dma(struct tango_nfc *nfc, int dir, int cmd, const void *buf,
- int len, int page)
+static int do_dma(struct tango_nfc *nfc, enum dma_data_direction dir, int cmd,
+ const void *buf, int len, int page)
{
void __iomem *addr = nfc->reg_base + NFC_STATUS;
struct dma_chan *chan = nfc->chan;
struct dma_async_tx_descriptor *desc;
+ enum dma_transfer_direction tdir;
struct scatterlist sg;
struct completion tx_done;
int err = -EIO;
if (dma_map_sg(chan->device->dev, &sg, 1, dir) != 1)
return -EIO;
- desc = dmaengine_prep_slave_sg(chan, &sg, 1, dir, DMA_PREP_INTERRUPT);
+ tdir = dir == DMA_TO_DEVICE ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM;
+ desc = dmaengine_prep_slave_sg(chan, &sg, 1, tdir, DMA_PREP_INTERRUPT);
if (!desc)
goto dma_unmap;
if (!part)
return 0; /* No partitions found */
- pr_warning("Device tree uses obsolete partition map binding: %s\n",
- dp->full_name);
+ pr_warn("Device tree uses obsolete partition map binding: %s\n",
+ dp->full_name);
nr_parts = plen / sizeof(part[0]);
To compile this driver as a module, choose M here: the module
will be called intel-spi-platform.
+config SPI_STM32_QUADSPI
+ tristate "STM32 Quad SPI controller"
+ depends on ARCH_STM32
+ help
+ This enables support for the STM32 Quad SPI controller.
+ We only connect the NOR to this controller.
+
endif # MTD_SPI_NOR
obj-$(CONFIG_SPI_NXP_SPIFI) += nxp-spifi.o
obj-$(CONFIG_SPI_INTEL_SPI) += intel-spi.o
obj-$(CONFIG_SPI_INTEL_SPI_PLATFORM) += intel-spi-platform.o
+obj-$(CONFIG_SPI_STM32_QUADSPI) += stm32-quadspi.o
\ No newline at end of file
if (!host->buffer)
return -ENOMEM;
+ ret = clk_prepare_enable(host->clk);
+ if (ret)
+ return ret;
+
mutex_init(&host->lock);
- clk_prepare_enable(host->clk);
hisi_spi_nor_init(host);
ret = hisi_spi_nor_register_all(host);
if (ret)
* whole partition read-only to be on the safe side.
*/
if (intel_spi_is_protected(ispi, base, limit))
- ispi->writeable = 0;
+ ispi->writeable = false;
end = (limit << 12) + 4096;
if (end > part->size)
ispi->base = devm_ioremap_resource(dev, mem);
if (IS_ERR(ispi->base))
- return ispi->base;
+ return ERR_CAST(ispi->base);
ispi->dev = dev;
ispi->info = info;
#define MTK_NOR_MAX_RX_TX_SHIFT 6
/* can shift up to 56 bits (7 bytes) transfer by MTK_NOR_PRG_CMD */
#define MTK_NOR_MAX_SHIFT 7
+/* nor controller 4-byte address mode enable bit */
+#define MTK_NOR_4B_ADDR_EN BIT(4)
/* Helpers for accessing the program data / shift data registers */
#define MTK_NOR_PRG_REG(n) (MTK_NOR_PRGDATA0_REG + 4 * (n))
10000);
}
+static void mt8173_nor_set_addr_width(struct mt8173_nor *mt8173_nor)
+{
+ u8 val;
+ struct spi_nor *nor = &mt8173_nor->nor;
+
+ val = readb(mt8173_nor->base + MTK_NOR_DUAL_REG);
+
+ switch (nor->addr_width) {
+ case 3:
+ val &= ~MTK_NOR_4B_ADDR_EN;
+ break;
+ case 4:
+ val |= MTK_NOR_4B_ADDR_EN;
+ break;
+ default:
+ dev_warn(mt8173_nor->dev, "Unexpected address width %u.\n",
+ nor->addr_width);
+ break;
+ }
+
+ writeb(val, mt8173_nor->base + MTK_NOR_DUAL_REG);
+}
+
static void mt8173_nor_set_addr(struct mt8173_nor *mt8173_nor, u32 addr)
{
int i;
+ mt8173_nor_set_addr_width(mt8173_nor);
+
for (i = 0; i < 3; i++) {
writeb(addr & 0xff, mt8173_nor->base + MTK_NOR_RADR0_REG + i * 4);
addr >>= 8;
* Use dedicated 4byte address op codes
* to support memory size above 128Mib.
*/
+#define NO_CHIP_ERASE BIT(12) /* Chip does not support chip erase */
};
#define JEDEC_MFR(info) ((info)->id[0])
/* ESMT */
{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K | SPI_NOR_HAS_LOCK) },
+ { "f25l32qa", INFO(0x8c4116, 0, 64 * 1024, 64, SECT_4K | SPI_NOR_HAS_LOCK) },
+ { "f25l64qa", INFO(0x8c4117, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_HAS_LOCK) },
/* Everspin */
{ "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
{ "mx25l3205d", INFO(0xc22016, 0, 64 * 1024, 64, SECT_4K) },
{ "mx25l3255e", INFO(0xc29e16, 0, 64 * 1024, 64, SECT_4K) },
{ "mx25l6405d", INFO(0xc22017, 0, 64 * 1024, 128, SECT_4K) },
+ { "mx25u2033e", INFO(0xc22532, 0, 64 * 1024, 4, SECT_4K) },
+ { "mx25u4035", INFO(0xc22533, 0, 64 * 1024, 8, SECT_4K) },
+ { "mx25u8035", INFO(0xc22534, 0, 64 * 1024, 16, SECT_4K) },
{ "mx25u6435f", INFO(0xc22537, 0, 64 * 1024, 128, SECT_4K) },
{ "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) },
{ "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) },
{ "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, 0) },
- { "mx25u25635f", INFO(0xc22539, 0, 64 * 1024, 512, SECT_4K) },
+ { "mx25u25635f", INFO(0xc22539, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_4B_OPCODES) },
{ "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) },
{ "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_QUAD_READ) },
{ "mx66l1g55g", INFO(0xc2261b, 0, 64 * 1024, 2048, SPI_NOR_QUAD_READ) },
{ "n25q128a11", INFO(0x20bb18, 0, 64 * 1024, 256, SECT_4K | SPI_NOR_QUAD_READ) },
{ "n25q128a13", INFO(0x20ba18, 0, 64 * 1024, 256, SECT_4K | SPI_NOR_QUAD_READ) },
{ "n25q256a", INFO(0x20ba19, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_QUAD_READ) },
+ { "n25q256ax1", INFO(0x20bb19, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_QUAD_READ) },
{ "n25q512a", INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
{ "n25q512ax3", INFO(0x20ba20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
- { "n25q00", INFO(0x20ba21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
- { "n25q00a", INFO(0x20bb21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
+ { "n25q00", INFO(0x20ba21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
+ { "n25q00a", INFO(0x20bb21, 0, 64 * 1024, 2048, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ | NO_CHIP_ERASE) },
/* PMC */
{ "pm25lv512", INFO(0, 0, 32 * 1024, 2, SECT_4K_PMC) },
{ "w25x80", INFO(0xef3014, 0, 64 * 1024, 16, SECT_4K) },
{ "w25x16", INFO(0xef3015, 0, 64 * 1024, 32, SECT_4K) },
{ "w25x32", INFO(0xef3016, 0, 64 * 1024, 64, SECT_4K) },
+ { "w25q20cl", INFO(0xef4012, 0, 64 * 1024, 4, SECT_4K) },
+ { "w25q20bw", INFO(0xef5012, 0, 64 * 1024, 4, SECT_4K) },
+ { "w25q20ew", INFO(0xef6012, 0, 64 * 1024, 4, SECT_4K) },
{ "w25q32", INFO(0xef4016, 0, 64 * 1024, 64, SECT_4K) },
{
"w25q32dw", INFO(0xef6016, 0, 64 * 1024, 64,
nor->flags |= SNOR_F_USE_FSR;
if (info->flags & SPI_NOR_HAS_TB)
nor->flags |= SNOR_F_HAS_SR_TB;
+ if (info->flags & NO_CHIP_ERASE)
+ nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS
/* prefer "small sector" erase if possible */
--- /dev/null
+/*
+ * stm32_quadspi.c
+ *
+ * Copyright (C) 2017, Ludovic Barre
+ *
+ * License terms: GNU General Public License (GPL), version 2
+ */
+#include <linux/clk.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#define QUADSPI_CR 0x00
+#define CR_EN BIT(0)
+#define CR_ABORT BIT(1)
+#define CR_DMAEN BIT(2)
+#define CR_TCEN BIT(3)
+#define CR_SSHIFT BIT(4)
+#define CR_DFM BIT(6)
+#define CR_FSEL BIT(7)
+#define CR_FTHRES_SHIFT 8
+#define CR_FTHRES_MASK GENMASK(12, 8)
+#define CR_FTHRES(n) (((n) << CR_FTHRES_SHIFT) & CR_FTHRES_MASK)
+#define CR_TEIE BIT(16)
+#define CR_TCIE BIT(17)
+#define CR_FTIE BIT(18)
+#define CR_SMIE BIT(19)
+#define CR_TOIE BIT(20)
+#define CR_PRESC_SHIFT 24
+#define CR_PRESC_MASK GENMASK(31, 24)
+#define CR_PRESC(n) (((n) << CR_PRESC_SHIFT) & CR_PRESC_MASK)
+
+#define QUADSPI_DCR 0x04
+#define DCR_CSHT_SHIFT 8
+#define DCR_CSHT_MASK GENMASK(10, 8)
+#define DCR_CSHT(n) (((n) << DCR_CSHT_SHIFT) & DCR_CSHT_MASK)
+#define DCR_FSIZE_SHIFT 16
+#define DCR_FSIZE_MASK GENMASK(20, 16)
+#define DCR_FSIZE(n) (((n) << DCR_FSIZE_SHIFT) & DCR_FSIZE_MASK)
+
+#define QUADSPI_SR 0x08
+#define SR_TEF BIT(0)
+#define SR_TCF BIT(1)
+#define SR_FTF BIT(2)
+#define SR_SMF BIT(3)
+#define SR_TOF BIT(4)
+#define SR_BUSY BIT(5)
+#define SR_FLEVEL_SHIFT 8
+#define SR_FLEVEL_MASK GENMASK(13, 8)
+
+#define QUADSPI_FCR 0x0c
+#define FCR_CTCF BIT(1)
+
+#define QUADSPI_DLR 0x10
+
+#define QUADSPI_CCR 0x14
+#define CCR_INST_SHIFT 0
+#define CCR_INST_MASK GENMASK(7, 0)
+#define CCR_INST(n) (((n) << CCR_INST_SHIFT) & CCR_INST_MASK)
+#define CCR_IMODE_NONE (0U << 8)
+#define CCR_IMODE_1 (1U << 8)
+#define CCR_IMODE_2 (2U << 8)
+#define CCR_IMODE_4 (3U << 8)
+#define CCR_ADMODE_NONE (0U << 10)
+#define CCR_ADMODE_1 (1U << 10)
+#define CCR_ADMODE_2 (2U << 10)
+#define CCR_ADMODE_4 (3U << 10)
+#define CCR_ADSIZE_SHIFT 12
+#define CCR_ADSIZE_MASK GENMASK(13, 12)
+#define CCR_ADSIZE(n) (((n) << CCR_ADSIZE_SHIFT) & CCR_ADSIZE_MASK)
+#define CCR_ABMODE_NONE (0U << 14)
+#define CCR_ABMODE_1 (1U << 14)
+#define CCR_ABMODE_2 (2U << 14)
+#define CCR_ABMODE_4 (3U << 14)
+#define CCR_ABSIZE_8 (0U << 16)
+#define CCR_ABSIZE_16 (1U << 16)
+#define CCR_ABSIZE_24 (2U << 16)
+#define CCR_ABSIZE_32 (3U << 16)
+#define CCR_DCYC_SHIFT 18
+#define CCR_DCYC_MASK GENMASK(22, 18)
+#define CCR_DCYC(n) (((n) << CCR_DCYC_SHIFT) & CCR_DCYC_MASK)
+#define CCR_DMODE_NONE (0U << 24)
+#define CCR_DMODE_1 (1U << 24)
+#define CCR_DMODE_2 (2U << 24)
+#define CCR_DMODE_4 (3U << 24)
+#define CCR_FMODE_INDW (0U << 26)
+#define CCR_FMODE_INDR (1U << 26)
+#define CCR_FMODE_APM (2U << 26)
+#define CCR_FMODE_MM (3U << 26)
+
+#define QUADSPI_AR 0x18
+#define QUADSPI_ABR 0x1c
+#define QUADSPI_DR 0x20
+#define QUADSPI_PSMKR 0x24
+#define QUADSPI_PSMAR 0x28
+#define QUADSPI_PIR 0x2c
+#define QUADSPI_LPTR 0x30
+#define LPTR_DFT_TIMEOUT 0x10
+
+#define FSIZE_VAL(size) (__fls(size) - 1)
+
+#define STM32_MAX_MMAP_SZ SZ_256M
+#define STM32_MAX_NORCHIP 2
+
+#define STM32_QSPI_FIFO_TIMEOUT_US 30000
+#define STM32_QSPI_BUSY_TIMEOUT_US 100000
+
+struct stm32_qspi_flash {
+ struct spi_nor nor;
+ struct stm32_qspi *qspi;
+ u32 cs;
+ u32 fsize;
+ u32 presc;
+ u32 read_mode;
+ bool registered;
+};
+
+struct stm32_qspi {
+ struct device *dev;
+ void __iomem *io_base;
+ void __iomem *mm_base;
+ resource_size_t mm_size;
+ u32 nor_num;
+ struct clk *clk;
+ u32 clk_rate;
+ struct stm32_qspi_flash flash[STM32_MAX_NORCHIP];
+ struct completion cmd_completion;
+
+ /*
+ * to protect device configuration, could be different between
+ * 2 flash access (bk1, bk2)
+ */
+ struct mutex lock;
+};
+
+struct stm32_qspi_cmd {
+ u8 addr_width;
+ u8 dummy;
+ bool tx_data;
+ u8 opcode;
+ u32 framemode;
+ u32 qspimode;
+ u32 addr;
+ size_t len;
+ void *buf;
+};
+
+static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi)
+{
+ u32 cr;
+ int err = 0;
+
+ if (readl_relaxed(qspi->io_base + QUADSPI_SR) & SR_TCF)
+ return 0;
+
+ reinit_completion(&qspi->cmd_completion);
+ cr = readl_relaxed(qspi->io_base + QUADSPI_CR);
+ writel_relaxed(cr | CR_TCIE, qspi->io_base + QUADSPI_CR);
+
+ if (!wait_for_completion_interruptible_timeout(&qspi->cmd_completion,
+ msecs_to_jiffies(1000)))
+ err = -ETIMEDOUT;
+
+ writel_relaxed(cr, qspi->io_base + QUADSPI_CR);
+ return err;
+}
+
+static int stm32_qspi_wait_nobusy(struct stm32_qspi *qspi)
+{
+ u32 sr;
+
+ return readl_relaxed_poll_timeout(qspi->io_base + QUADSPI_SR, sr,
+ !(sr & SR_BUSY), 10,
+ STM32_QSPI_BUSY_TIMEOUT_US);
+}
+
+static void stm32_qspi_set_framemode(struct spi_nor *nor,
+ struct stm32_qspi_cmd *cmd, bool read)
+{
+ u32 dmode = CCR_DMODE_1;
+
+ cmd->framemode = CCR_IMODE_1;
+
+ if (read) {
+ switch (nor->flash_read) {
+ case SPI_NOR_NORMAL:
+ case SPI_NOR_FAST:
+ dmode = CCR_DMODE_1;
+ break;
+ case SPI_NOR_DUAL:
+ dmode = CCR_DMODE_2;
+ break;
+ case SPI_NOR_QUAD:
+ dmode = CCR_DMODE_4;
+ break;
+ }
+ }
+
+ cmd->framemode |= cmd->tx_data ? dmode : 0;
+ cmd->framemode |= cmd->addr_width ? CCR_ADMODE_1 : 0;
+}
+
+static void stm32_qspi_read_fifo(u8 *val, void __iomem *addr)
+{
+ *val = readb_relaxed(addr);
+}
+
+static void stm32_qspi_write_fifo(u8 *val, void __iomem *addr)
+{
+ writeb_relaxed(*val, addr);
+}
+
+static int stm32_qspi_tx_poll(struct stm32_qspi *qspi,
+ const struct stm32_qspi_cmd *cmd)
+{
+ void (*tx_fifo)(u8 *, void __iomem *);
+ u32 len = cmd->len, sr;
+ u8 *buf = cmd->buf;
+ int ret;
+
+ if (cmd->qspimode == CCR_FMODE_INDW)
+ tx_fifo = stm32_qspi_write_fifo;
+ else
+ tx_fifo = stm32_qspi_read_fifo;
+
+ while (len--) {
+ ret = readl_relaxed_poll_timeout(qspi->io_base + QUADSPI_SR,
+ sr, (sr & SR_FTF), 10,
+ STM32_QSPI_FIFO_TIMEOUT_US);
+ if (ret) {
+ dev_err(qspi->dev, "fifo timeout (stat:%#x)\n", sr);
+ break;
+ }
+ tx_fifo(buf++, qspi->io_base + QUADSPI_DR);
+ }
+
+ return ret;
+}
+
+static int stm32_qspi_tx_mm(struct stm32_qspi *qspi,
+ const struct stm32_qspi_cmd *cmd)
+{
+ memcpy_fromio(cmd->buf, qspi->mm_base + cmd->addr, cmd->len);
+ return 0;
+}
+
+static int stm32_qspi_tx(struct stm32_qspi *qspi,
+ const struct stm32_qspi_cmd *cmd)
+{
+ if (!cmd->tx_data)
+ return 0;
+
+ if (cmd->qspimode == CCR_FMODE_MM)
+ return stm32_qspi_tx_mm(qspi, cmd);
+
+ return stm32_qspi_tx_poll(qspi, cmd);
+}
+
+static int stm32_qspi_send(struct stm32_qspi_flash *flash,
+ const struct stm32_qspi_cmd *cmd)
+{
+ struct stm32_qspi *qspi = flash->qspi;
+ u32 ccr, dcr, cr;
+ int err;
+
+ err = stm32_qspi_wait_nobusy(qspi);
+ if (err)
+ goto abort;
+
+ dcr = readl_relaxed(qspi->io_base + QUADSPI_DCR) & ~DCR_FSIZE_MASK;
+ dcr |= DCR_FSIZE(flash->fsize);
+ writel_relaxed(dcr, qspi->io_base + QUADSPI_DCR);
+
+ cr = readl_relaxed(qspi->io_base + QUADSPI_CR);
+ cr &= ~CR_PRESC_MASK & ~CR_FSEL;
+ cr |= CR_PRESC(flash->presc);
+ cr |= flash->cs ? CR_FSEL : 0;
+ writel_relaxed(cr, qspi->io_base + QUADSPI_CR);
+
+ if (cmd->tx_data)
+ writel_relaxed(cmd->len - 1, qspi->io_base + QUADSPI_DLR);
+
+ ccr = cmd->framemode | cmd->qspimode;
+
+ if (cmd->dummy)
+ ccr |= CCR_DCYC(cmd->dummy);
+
+ if (cmd->addr_width)
+ ccr |= CCR_ADSIZE(cmd->addr_width - 1);
+
+ ccr |= CCR_INST(cmd->opcode);
+ writel_relaxed(ccr, qspi->io_base + QUADSPI_CCR);
+
+ if (cmd->addr_width && cmd->qspimode != CCR_FMODE_MM)
+ writel_relaxed(cmd->addr, qspi->io_base + QUADSPI_AR);
+
+ err = stm32_qspi_tx(qspi, cmd);
+ if (err)
+ goto abort;
+
+ if (cmd->qspimode != CCR_FMODE_MM) {
+ err = stm32_qspi_wait_cmd(qspi);
+ if (err)
+ goto abort;
+ writel_relaxed(FCR_CTCF, qspi->io_base + QUADSPI_FCR);
+ }
+
+ return err;
+
+abort:
+ cr = readl_relaxed(qspi->io_base + QUADSPI_CR) | CR_ABORT;
+ writel_relaxed(cr, qspi->io_base + QUADSPI_CR);
+
+ dev_err(qspi->dev, "%s abort err:%d\n", __func__, err);
+ return err;
+}
+
+static int stm32_qspi_read_reg(struct spi_nor *nor,
+ u8 opcode, u8 *buf, int len)
+{
+ struct stm32_qspi_flash *flash = nor->priv;
+ struct device *dev = flash->qspi->dev;
+ struct stm32_qspi_cmd cmd;
+
+ dev_dbg(dev, "read_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.opcode = opcode;
+ cmd.tx_data = true;
+ cmd.len = len;
+ cmd.buf = buf;
+ cmd.qspimode = CCR_FMODE_INDR;
+
+ stm32_qspi_set_framemode(nor, &cmd, false);
+
+ return stm32_qspi_send(flash, &cmd);
+}
+
+static int stm32_qspi_write_reg(struct spi_nor *nor, u8 opcode,
+ u8 *buf, int len)
+{
+ struct stm32_qspi_flash *flash = nor->priv;
+ struct device *dev = flash->qspi->dev;
+ struct stm32_qspi_cmd cmd;
+
+ dev_dbg(dev, "write_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.opcode = opcode;
+ cmd.tx_data = !!(buf && len > 0);
+ cmd.len = len;
+ cmd.buf = buf;
+ cmd.qspimode = CCR_FMODE_INDW;
+
+ stm32_qspi_set_framemode(nor, &cmd, false);
+
+ return stm32_qspi_send(flash, &cmd);
+}
+
+static ssize_t stm32_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
+ u_char *buf)
+{
+ struct stm32_qspi_flash *flash = nor->priv;
+ struct stm32_qspi *qspi = flash->qspi;
+ struct stm32_qspi_cmd cmd;
+ int err;
+
+ dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#x\n",
+ nor->read_opcode, buf, (u32)from, len);
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.opcode = nor->read_opcode;
+ cmd.addr_width = nor->addr_width;
+ cmd.addr = (u32)from;
+ cmd.tx_data = true;
+ cmd.dummy = nor->read_dummy;
+ cmd.len = len;
+ cmd.buf = buf;
+ cmd.qspimode = flash->read_mode;
+
+ stm32_qspi_set_framemode(nor, &cmd, true);
+ err = stm32_qspi_send(flash, &cmd);
+
+ return err ? err : len;
+}
+
+static ssize_t stm32_qspi_write(struct spi_nor *nor, loff_t to, size_t len,
+ const u_char *buf)
+{
+ struct stm32_qspi_flash *flash = nor->priv;
+ struct device *dev = flash->qspi->dev;
+ struct stm32_qspi_cmd cmd;
+ int err;
+
+ dev_dbg(dev, "write(%#.2x): buf:%p to:%#.8x len:%#x\n",
+ nor->program_opcode, buf, (u32)to, len);
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.opcode = nor->program_opcode;
+ cmd.addr_width = nor->addr_width;
+ cmd.addr = (u32)to;
+ cmd.tx_data = true;
+ cmd.len = len;
+ cmd.buf = (void *)buf;
+ cmd.qspimode = CCR_FMODE_INDW;
+
+ stm32_qspi_set_framemode(nor, &cmd, false);
+ err = stm32_qspi_send(flash, &cmd);
+
+ return err ? err : len;
+}
+
+static int stm32_qspi_erase(struct spi_nor *nor, loff_t offs)
+{
+ struct stm32_qspi_flash *flash = nor->priv;
+ struct device *dev = flash->qspi->dev;
+ struct stm32_qspi_cmd cmd;
+
+ dev_dbg(dev, "erase(%#.2x):offs:%#x\n", nor->erase_opcode, (u32)offs);
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.opcode = nor->erase_opcode;
+ cmd.addr_width = nor->addr_width;
+ cmd.addr = (u32)offs;
+ cmd.qspimode = CCR_FMODE_INDW;
+
+ stm32_qspi_set_framemode(nor, &cmd, false);
+
+ return stm32_qspi_send(flash, &cmd);
+}
+
+static irqreturn_t stm32_qspi_irq(int irq, void *dev_id)
+{
+ struct stm32_qspi *qspi = (struct stm32_qspi *)dev_id;
+ u32 cr, sr, fcr = 0;
+
+ cr = readl_relaxed(qspi->io_base + QUADSPI_CR);
+ sr = readl_relaxed(qspi->io_base + QUADSPI_SR);
+
+ if ((cr & CR_TCIE) && (sr & SR_TCF)) {
+ /* tx complete */
+ fcr |= FCR_CTCF;
+ complete(&qspi->cmd_completion);
+ } else {
+ dev_info_ratelimited(qspi->dev, "spurious interrupt\n");
+ }
+
+ writel_relaxed(fcr, qspi->io_base + QUADSPI_FCR);
+
+ return IRQ_HANDLED;
+}
+
+static int stm32_qspi_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+ struct stm32_qspi_flash *flash = nor->priv;
+ struct stm32_qspi *qspi = flash->qspi;
+
+ mutex_lock(&qspi->lock);
+ return 0;
+}
+
+static void stm32_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+ struct stm32_qspi_flash *flash = nor->priv;
+ struct stm32_qspi *qspi = flash->qspi;
+
+ mutex_unlock(&qspi->lock);
+}
+
+static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
+ struct device_node *np)
+{
+ u32 width, flash_read, presc, cs_num, max_rate = 0;
+ struct stm32_qspi_flash *flash;
+ struct mtd_info *mtd;
+ int ret;
+
+ of_property_read_u32(np, "reg", &cs_num);
+ if (cs_num >= STM32_MAX_NORCHIP)
+ return -EINVAL;
+
+ of_property_read_u32(np, "spi-max-frequency", &max_rate);
+ if (!max_rate)
+ return -EINVAL;
+
+ presc = DIV_ROUND_UP(qspi->clk_rate, max_rate) - 1;
+
+ if (of_property_read_u32(np, "spi-rx-bus-width", &width))
+ width = 1;
+
+ if (width == 4)
+ flash_read = SPI_NOR_QUAD;
+ else if (width == 2)
+ flash_read = SPI_NOR_DUAL;
+ else if (width == 1)
+ flash_read = SPI_NOR_NORMAL;
+ else
+ return -EINVAL;
+
+ flash = &qspi->flash[cs_num];
+ flash->qspi = qspi;
+ flash->cs = cs_num;
+ flash->presc = presc;
+
+ flash->nor.dev = qspi->dev;
+ spi_nor_set_flash_node(&flash->nor, np);
+ flash->nor.priv = flash;
+ mtd = &flash->nor.mtd;
+
+ flash->nor.read = stm32_qspi_read;
+ flash->nor.write = stm32_qspi_write;
+ flash->nor.erase = stm32_qspi_erase;
+ flash->nor.read_reg = stm32_qspi_read_reg;
+ flash->nor.write_reg = stm32_qspi_write_reg;
+ flash->nor.prepare = stm32_qspi_prep;
+ flash->nor.unprepare = stm32_qspi_unprep;
+
+ writel_relaxed(LPTR_DFT_TIMEOUT, qspi->io_base + QUADSPI_LPTR);
+
+ writel_relaxed(CR_PRESC(presc) | CR_FTHRES(3) | CR_TCEN | CR_SSHIFT
+ | CR_EN, qspi->io_base + QUADSPI_CR);
+
+ /*
+ * in stm32 qspi controller, QUADSPI_DCR register has a fsize field
+ * which define the size of nor flash.
+ * if fsize is NULL, the controller can't sent spi-nor command.
+ * set a temporary value just to discover the nor flash with
+ * "spi_nor_scan". After, the right value (mtd->size) can be set.
+ */
+ flash->fsize = FSIZE_VAL(SZ_1K);
+
+ ret = spi_nor_scan(&flash->nor, NULL, flash_read);
+ if (ret) {
+ dev_err(qspi->dev, "device scan failed\n");
+ return ret;
+ }
+
+ flash->fsize = FSIZE_VAL(mtd->size);
+
+ flash->read_mode = CCR_FMODE_MM;
+ if (mtd->size > qspi->mm_size)
+ flash->read_mode = CCR_FMODE_INDR;
+
+ writel_relaxed(DCR_CSHT(1), qspi->io_base + QUADSPI_DCR);
+
+ ret = mtd_device_register(mtd, NULL, 0);
+ if (ret) {
+ dev_err(qspi->dev, "mtd device parse failed\n");
+ return ret;
+ }
+
+ flash->registered = true;
+
+ dev_dbg(qspi->dev, "read mm:%s cs:%d bus:%d\n",
+ flash->read_mode == CCR_FMODE_MM ? "yes" : "no", cs_num, width);
+
+ return 0;
+}
+
+static void stm32_qspi_mtd_free(struct stm32_qspi *qspi)
+{
+ int i;
+
+ for (i = 0; i < STM32_MAX_NORCHIP; i++)
+ if (qspi->flash[i].registered)
+ mtd_device_unregister(&qspi->flash[i].nor.mtd);
+}
+
+static int stm32_qspi_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *flash_np;
+ struct reset_control *rstc;
+ struct stm32_qspi *qspi;
+ struct resource *res;
+ int ret, irq;
+
+ qspi = devm_kzalloc(dev, sizeof(*qspi), GFP_KERNEL);
+ if (!qspi)
+ return -ENOMEM;
+
+ qspi->nor_num = of_get_child_count(dev->of_node);
+ if (!qspi->nor_num || qspi->nor_num > STM32_MAX_NORCHIP)
+ return -ENODEV;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi");
+ qspi->io_base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(qspi->io_base))
+ return PTR_ERR(qspi->io_base);
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi_mm");
+ qspi->mm_base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(qspi->mm_base))
+ return PTR_ERR(qspi->mm_base);
+
+ qspi->mm_size = resource_size(res);
+
+ irq = platform_get_irq(pdev, 0);
+ ret = devm_request_irq(dev, irq, stm32_qspi_irq, 0,
+ dev_name(dev), qspi);
+ if (ret) {
+ dev_err(dev, "failed to request irq\n");
+ return ret;
+ }
+
+ init_completion(&qspi->cmd_completion);
+
+ qspi->clk = devm_clk_get(dev, NULL);
+ if (IS_ERR(qspi->clk))
+ return PTR_ERR(qspi->clk);
+
+ qspi->clk_rate = clk_get_rate(qspi->clk);
+ if (!qspi->clk_rate)
+ return -EINVAL;
+
+ ret = clk_prepare_enable(qspi->clk);
+ if (ret) {
+ dev_err(dev, "can not enable the clock\n");
+ return ret;
+ }
+
+ rstc = devm_reset_control_get(dev, NULL);
+ if (!IS_ERR(rstc)) {
+ reset_control_assert(rstc);
+ udelay(2);
+ reset_control_deassert(rstc);
+ }
+
+ qspi->dev = dev;
+ platform_set_drvdata(pdev, qspi);
+ mutex_init(&qspi->lock);
+
+ for_each_available_child_of_node(dev->of_node, flash_np) {
+ ret = stm32_qspi_flash_setup(qspi, flash_np);
+ if (ret) {
+ dev_err(dev, "unable to setup flash chip\n");
+ goto err_flash;
+ }
+ }
+
+ return 0;
+
+err_flash:
+ mutex_destroy(&qspi->lock);
+ stm32_qspi_mtd_free(qspi);
+
+ clk_disable_unprepare(qspi->clk);
+ return ret;
+}
+
+static int stm32_qspi_remove(struct platform_device *pdev)
+{
+ struct stm32_qspi *qspi = platform_get_drvdata(pdev);
+
+ /* disable qspi */
+ writel_relaxed(0, qspi->io_base + QUADSPI_CR);
+
+ stm32_qspi_mtd_free(qspi);
+ mutex_destroy(&qspi->lock);
+
+ clk_disable_unprepare(qspi->clk);
+ return 0;
+}
+
+static const struct of_device_id stm32_qspi_match[] = {
+ {.compatible = "st,stm32f469-qspi"},
+ {}
+};
+MODULE_DEVICE_TABLE(of, stm32_qspi_match);
+
+static struct platform_driver stm32_qspi_driver = {
+ .probe = stm32_qspi_probe,
+ .remove = stm32_qspi_remove,
+ .driver = {
+ .name = "stm32-quadspi",
+ .of_match_table = stm32_qspi_match,
+ },
+};
+module_platform_driver(stm32_qspi_driver);
+
+MODULE_AUTHOR("Ludovic Barre <ludovic.barre@st.com>");
+MODULE_DESCRIPTION("STMicroelectronics STM32 quad spi driver");
+MODULE_LICENSE("GPL v2");
static struct net_device *cops_dev;
MODULE_LICENSE("GPL");
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(board_type, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
+module_param_hw(board_type, int, other, 0);
static int __init cops_module_init(void)
{
MODULE_LICENSE("GPL");
module_param(debug, int, 0);
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(dma, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
+module_param_hw(dma, int, dma, 0);
static int __init ltpc_module_init(void)
static int clockm = 0;
module_param(node, int, 0);
-module_param(io, int, 0);
-module_param(irq, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
module_param_string(device, device, sizeof(device), 0);
module_param(timeout, int, 0);
module_param(backplane, int, 0);
static int irq;
static char device[9]; /* use eg. device=arc1 to change name */
-module_param(io, int, 0);
-module_param(irq, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
module_param_string(device, device, sizeof(device), 0);
MODULE_LICENSE("GPL");
static int shmem;
static char device[9]; /* use eg. device=arc1 to change name */
-module_param(io, int, 0);
-module_param(irq, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
module_param(shmem, int, 0);
module_param_string(device, device, sizeof(device), 0);
targets_added = 0;
for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) {
if (bond->params.arp_targets[i]) {
- nla_put_be32(skb, i, bond->params.arp_targets[i]);
+ if (nla_put_be32(skb, i, bond->params.arp_targets[i]))
+ goto nla_put_failure;
targets_added = 1;
}
}
goto err;
/* Get the TX virtio ring. This is a "guest side vring". */
- err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names,
- NULL);
+ err = virtio_find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names, NULL);
if (err)
goto err;
static u8 bcr[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
static int indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
-module_param_array(port, ulong, NULL, S_IRUGO);
+module_param_hw_array(port, ulong, ioport, NULL, S_IRUGO);
MODULE_PARM_DESC(port, "I/O port number");
-module_param_array(mem, ulong, NULL, S_IRUGO);
+module_param_hw_array(mem, ulong, iomem, NULL, S_IRUGO);
MODULE_PARM_DESC(mem, "I/O memory address");
-module_param_array(indirect, int, NULL, S_IRUGO);
+module_param_hw_array(indirect, int, ioport, NULL, S_IRUGO);
MODULE_PARM_DESC(indirect, "Indirect access via address and data port");
-module_param_array(irq, int, NULL, S_IRUGO);
+module_param_hw_array(irq, int, irq, NULL, S_IRUGO);
MODULE_PARM_DESC(irq, "IRQ number");
module_param_array(clk, int, NULL, S_IRUGO);
static int indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
static spinlock_t indirect_lock[MAXDEV]; /* lock for indirect access mode */
-module_param_array(port, ulong, NULL, S_IRUGO);
+module_param_hw_array(port, ulong, ioport, NULL, S_IRUGO);
MODULE_PARM_DESC(port, "I/O port number");
-module_param_array(mem, ulong, NULL, S_IRUGO);
+module_param_hw_array(mem, ulong, iomem, NULL, S_IRUGO);
MODULE_PARM_DESC(mem, "I/O memory address");
-module_param_array(indirect, int, NULL, S_IRUGO);
+module_param_hw_array(indirect, int, ioport, NULL, S_IRUGO);
MODULE_PARM_DESC(indirect, "Indirect access via address and data port");
-module_param_array(irq, int, NULL, S_IRUGO);
+module_param_hw_array(irq, int, irq, NULL, S_IRUGO);
MODULE_PARM_DESC(irq, "IRQ number");
module_param_array(clk, int, NULL, S_IRUGO);
return -ENOMEM;
ps = devm_kzalloc(&mdiodev->dev, sizeof(*ps), GFP_KERNEL);
+ if (!ps)
+ return -ENOMEM;
+
ps->netdev = dev_get_by_name(&init_net, pdata->netdev);
if (!ps->netdev)
return -EPROBE_DEFER;
#endif /* CONFIG_PM */
module_param(debug,int, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param(max_interrupt_work, int, 0);
MODULE_PARM_DESC(debug, "debug level (0-6)");
MODULE_PARM_DESC(irq, "IRQ number(s) (assigned)");
module_param_array(enable_wol, int, NULL, 0);
module_param(rx_copybreak, int, 0);
module_param(max_interrupt_work, int, 0);
-module_param(compaq_ioaddr, int, 0);
-module_param(compaq_irq, int, 0);
+module_param_hw(compaq_ioaddr, int, ioport, 0);
+module_param_hw(compaq_irq, int, irq, 0);
module_param(compaq_device_id, int, 0);
module_param(watchdog, int, 0);
module_param(global_use_mmio, int, 0);
static u32 ne_msg_enable;
#ifdef MODULE
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param_array(bad, int, NULL, 0);
module_param_named(msg_enable, ne_msg_enable, uint, (S_IRUSR|S_IRGRP|S_IROTH));
MODULE_PARM_DESC(io, "I/O base address(es),required");
static int io[MAX_ULTRA_CARDS];
static int irq[MAX_ULTRA_CARDS];
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param_named(msg_enable, ultra_msg_enable, uint, (S_IRUSR|S_IRGRP|S_IROTH));
MODULE_PARM_DESC(io, "I/O base address(es)");
MODULE_PARM_DESC(irq, "IRQ number(s) (assigned)");
static int mem[MAX_WD_CARDS];
static int mem_end[MAX_WD_CARDS]; /* for non std. mem size */
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
-module_param_array(mem, int, NULL, 0);
-module_param_array(mem_end, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
+module_param_hw_array(mem, int, iomem, NULL, 0);
+module_param_hw_array(mem_end, int, iomem, NULL, 0);
module_param_named(msg_enable, wd_msg_enable, uint, (S_IRUSR|S_IRGRP|S_IROTH));
MODULE_PARM_DESC(io, "I/O base address(es)");
MODULE_PARM_DESC(irq, "IRQ number(s) (ignored for PureData boards)");
static int dma[MAX_CARDS];
static int irq[MAX_CARDS];
-module_param_array(io, int, NULL, 0);
-module_param_array(dma, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(dma, int, dma, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param(lance_debug, int, 0);
MODULE_PARM_DESC(io, "LANCE/PCnet I/O base address(es),required");
MODULE_PARM_DESC(dma, "LANCE/PCnet ISA DMA channel (ignored for some devices)");
#ifdef MODULE
static struct net_device *dev_ni65;
-module_param(irq, int, 0);
-module_param(io, int, 0);
-module_param(dma, int, 0);
+module_param_hw(irq, int, irq, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(dma, int, dma, 0);
MODULE_PARM_DESC(irq, "ni6510 IRQ number (ignored for some cards)");
MODULE_PARM_DESC(io, "ni6510 I/O base address");
MODULE_PARM_DESC(dma, "ni6510 ISA DMA channel (ignored for some cards)");
count = 0U;
for (i = 0U, aq_vec = self->aq_vec[0];
- self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) {
+ aq_vec && self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) {
data += count;
aq_vec_get_sw_stats(aq_vec, data, &count);
}
goto err_exit;
for (i = AQ_DIMOF(self->aq_vec); i--;) {
- if (self->aq_vec[i])
+ if (self->aq_vec[i]) {
aq_vec_free(self->aq_vec[i]);
+ self->aq_vec[i] = NULL;
+ }
}
err_exit:;
err = pci_alloc_irq_vectors(alx->hw.pdev, num_vec, num_vec,
PCI_IRQ_MSIX);
- if (err) {
+ if (err < 0) {
netdev_warn(alx->dev, "Enabling MSI-X interrupts failed!\n");
return err;
}
ret = pci_alloc_irq_vectors(alx->hw.pdev, 1, 1,
PCI_IRQ_MSI | PCI_IRQ_LEGACY);
- if (ret)
+ if (ret < 0)
return ret;
alx->num_vec = 1;
INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]);
bp->ntp_fltr_count = 0;
- bp->ntp_fltr_bmap = kzalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+ bp->ntp_fltr_bmap = kcalloc(BITS_TO_LONGS(BNXT_NTP_FLTR_MAX_FLTR),
+ sizeof(long),
GFP_KERNEL);
if (!bp->ntp_fltr_bmap)
static void
bfa_ioc_get_adapter_manufacturer(struct bfa_ioc *ioc, char *manufacturer)
{
- memcpy(manufacturer, BFA_MFG_NAME, BFA_ADAPTER_MFG_NAME_LEN);
+ strncpy(manufacturer, BFA_MFG_NAME, BFA_ADAPTER_MFG_NAME_LEN);
}
static void
for (i = 0; i < BNAD_ETHTOOL_STATS_NUM; i++) {
BUG_ON(!(strlen(bnad_net_stats_strings[i]) <
ETH_GSTRING_LEN));
- memcpy(string, bnad_net_stats_strings[i],
- ETH_GSTRING_LEN);
+ strncpy(string, bnad_net_stats_strings[i],
+ ETH_GSTRING_LEN);
string += ETH_GSTRING_LEN;
}
bmap = bna_tx_rid_mask(&bnad->bna);
PAUSE_AUTONEG = 1 << 2
};
+enum {
+ FEC_AUTO = 1 << 0, /* IEEE 802.3 "automatic" */
+ FEC_RS = 1 << 1, /* Reed-Solomon */
+ FEC_BASER_RS = 1 << 2 /* BaseR/Reed-Solomon */
+};
+
struct port_stats {
u64 tx_octets; /* total # of octets in good frames */
u64 tx_frames; /* all good frames */
unsigned int speed; /* actual link speed */
unsigned char requested_fc; /* flow control user has requested */
unsigned char fc; /* actual link flow control */
+ unsigned char auto_fec; /* Forward Error Correction: */
+ unsigned char requested_fec; /* "automatic" (IEEE 802.3), */
+ unsigned char fec; /* requested, and actual in use */
unsigned char autoneg; /* autonegotiating? */
unsigned char link_ok; /* link up? */
unsigned char link_down_rc; /* link down reason */
struct link_config *lc)
{
struct fw_port_cmd c;
- unsigned int fc = 0, mdi = FW_PORT_CAP_MDI_V(FW_PORT_CAP_MDI_AUTO);
+ unsigned int mdi = FW_PORT_CAP_MDI_V(FW_PORT_CAP_MDI_AUTO);
+ unsigned int fc = 0, fec = 0, fw_fec = 0;
lc->link_ok = 0;
if (lc->requested_fc & PAUSE_RX)
if (lc->requested_fc & PAUSE_TX)
fc |= FW_PORT_CAP_FC_TX;
+ fec = lc->requested_fec & FEC_AUTO ? lc->auto_fec : lc->requested_fec;
+
+ if (fec & FEC_RS)
+ fw_fec |= FW_PORT_CAP_FEC_RS;
+ if (fec & FEC_BASER_RS)
+ fw_fec |= FW_PORT_CAP_FEC_BASER_RS;
+
memset(&c, 0, sizeof(c));
c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PORT_CMD) |
FW_CMD_REQUEST_F | FW_CMD_EXEC_F |
if (!(lc->supported & FW_PORT_CAP_ANEG)) {
c.u.l1cfg.rcap = cpu_to_be32((lc->supported & ADVERT_MASK) |
- fc);
+ fc | fw_fec);
lc->fc = lc->requested_fc & (PAUSE_RX | PAUSE_TX);
} else if (lc->autoneg == AUTONEG_DISABLE) {
- c.u.l1cfg.rcap = cpu_to_be32(lc->requested_speed | fc | mdi);
+ c.u.l1cfg.rcap = cpu_to_be32(lc->requested_speed | fc |
+ fw_fec | mdi);
lc->fc = lc->requested_fc & (PAUSE_RX | PAUSE_TX);
} else
- c.u.l1cfg.rcap = cpu_to_be32(lc->advertising | fc | mdi);
+ c.u.l1cfg.rcap = cpu_to_be32(lc->advertising | fc |
+ fw_fec | mdi);
return t4_wr_mbox(adap, mbox, &c, sizeof(c), NULL);
}
* Initializes the SW state maintained for each link, including the link's
* capabilities and default speed/flow-control/autonegotiation settings.
*/
-static void init_link_config(struct link_config *lc, unsigned int caps)
+static void init_link_config(struct link_config *lc, unsigned int pcaps,
+ unsigned int acaps)
{
- lc->supported = caps;
+ lc->supported = pcaps;
lc->lp_advertising = 0;
lc->requested_speed = 0;
lc->speed = 0;
lc->requested_fc = lc->fc = PAUSE_RX | PAUSE_TX;
+ lc->auto_fec = 0;
+
+ /* For Forward Error Control, we default to whatever the Firmware
+ * tells us the Link is currently advertising.
+ */
+ if (acaps & FW_PORT_CAP_FEC_RS)
+ lc->auto_fec |= FEC_RS;
+ if (acaps & FW_PORT_CAP_FEC_BASER_RS)
+ lc->auto_fec |= FEC_BASER_RS;
+ lc->requested_fec = FEC_AUTO;
+ lc->fec = lc->auto_fec;
+
if (lc->supported & FW_PORT_CAP_ANEG) {
lc->advertising = lc->supported & ADVERT_MASK;
lc->autoneg = AUTONEG_ENABLE;
pi->port_type = FW_PORT_CMD_PTYPE_G(ret);
pi->mod_type = FW_PORT_MOD_TYPE_NA;
- init_link_config(&pi->link_cfg, be16_to_cpu(c.u.info.pcap));
+ init_link_config(&pi->link_cfg, be16_to_cpu(c.u.info.pcap),
+ be16_to_cpu(c.u.info.acap));
return 0;
}
FW_PORT_CAP_ANEG = 0x0100,
FW_PORT_CAP_MDIX = 0x0200,
FW_PORT_CAP_MDIAUTO = 0x0400,
- FW_PORT_CAP_FEC = 0x0800,
- FW_PORT_CAP_TECHKR = 0x1000,
- FW_PORT_CAP_TECHKX4 = 0x2000,
+ FW_PORT_CAP_FEC_RS = 0x0800,
+ FW_PORT_CAP_FEC_BASER_RS = 0x1000,
+ FW_PORT_CAP_FEC_RESERVED = 0x2000,
FW_PORT_CAP_802_3_PAUSE = 0x4000,
FW_PORT_CAP_802_3_ASM_DIR = 0x8000,
};
static int dma;
static int dmasize = 16; /* or 64 */
-module_param(io, int, 0);
-module_param(irq, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
module_param(debug, int, 0);
module_param_string(media, media, sizeof(media), 0);
module_param(duplex, int, 0);
-module_param(dma , int, 0);
+module_param_hw(dma , int, dma, 0);
module_param(dmasize , int, 0);
module_param(use_dma , int, 0);
MODULE_PARM_DESC(io, "cs89x0 I/O base address");
static int io=0x0;/* EDIT THIS LINE FOR YOUR CONFIGURATION IF NEEDED */
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
module_param(de4x5_debug, int, 0);
module_param(dec_only, int, 0);
module_param(args, charp, 0);
#define HP100_DEVICES 5
/* Parameters set by insmod */
static int hp100_port[HP100_DEVICES] = { 0, [1 ... (HP100_DEVICES-1)] = -1 };
-module_param_array(hp100_port, int, NULL, 0);
+module_param_hw_array(hp100_port, int, ioport, NULL, 0);
/* List of devices */
static struct net_device *hp100_devlist[HP100_DEVICES];
}
if (err) {
- if (!(dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR))
- mlx4_warn(dev, "vhcr command:0x%x slave:%d failed with error:%d, status %d\n",
- vhcr->op, slave, vhcr->errno, err);
+ if (!(dev->persist->state & MLX4_DEVICE_STATE_INTERNAL_ERROR)) {
+ if (vhcr->op == MLX4_CMD_ALLOC_RES &&
+ (vhcr->in_modifier & 0xff) == RES_COUNTER &&
+ err == -EDQUOT)
+ mlx4_dbg(dev,
+ "Unable to allocate counter for slave %d (%d)\n",
+ slave, err);
+ else
+ mlx4_warn(dev, "vhcr command:0x%x slave:%d failed with error:%d, status %d\n",
+ vhcr->op, slave, vhcr->errno, err);
+ }
vhcr_cmd->status = mlx4_errno_to_status(err);
goto out_status;
}
qpn = priv->drop_qp.qpn;
else if (cmd->fs.ring_cookie & EN_ETHTOOL_QP_ATTACH) {
qpn = cmd->fs.ring_cookie & (EN_ETHTOOL_QP_ATTACH - 1);
+ if (qpn < priv->rss_map.base_qpn ||
+ qpn >= priv->rss_map.base_qpn + priv->rx_ring_num) {
+ en_warn(priv, "rxnfc: QP (0x%x) doesn't exist\n", qpn);
+ return -EINVAL;
+ }
} else {
if (cmd->fs.ring_cookie >= priv->rx_ring_num) {
en_warn(priv, "rxnfc: RX ring (%llu) doesn't exist\n",
en_dbg(DRV, priv, "Rx buffer scatter-list (effective-mtu:%d num_frags:%d):\n",
eff_mtu, priv->num_frags);
for (i = 0; i < priv->num_frags; i++) {
- en_err(priv,
+ en_dbg(DRV,
+ priv,
" frag:%d - size:%d stride:%d\n",
i,
priv->frag_info[i].frag_size,
struct mlx4_priv *priv = mlx4_priv(dev);
struct resource_allocator *res_alloc =
&priv->mfunc.master.res_tracker.res_alloc[res_type];
- int err = -EINVAL;
+ int err = -EDQUOT;
int allocated, free, reserved, guaranteed, from_free;
int from_rsvd;
params.is_first_pf = p_hwfn->first_on_engine;
params.num_pf_cids = iids.cids;
params.num_vf_cids = iids.vf_cids;
+ params.num_tids = iids.tids;
params.start_pq = qm_info->start_pq;
params.num_pf_pqs = qm_info->num_pqs - qm_info->num_vf_pqs;
params.num_vf_pqs = qm_info->num_vf_pqs;
NULL) +
qed_cxt_get_proto_cid_count(p_hwfn, PROTOCOLID_ETH,
NULL);
- norm_regsize = roundup(QED_PF_DEMS_SIZE * non_pwm_conn, 4096);
+ norm_regsize = roundup(QED_PF_DEMS_SIZE * non_pwm_conn, PAGE_SIZE);
min_addr_reg1 = norm_regsize / 4096;
pwm_regsize = db_bar_size - norm_regsize;
qed_free_stream_mem(cdev);
if (IS_QED_ETH_IF(cdev))
qed_sriov_disable(cdev, true);
+ }
+
+ qed_nic_stop(cdev);
- qed_nic_stop(cdev);
+ if (IS_PF(cdev))
qed_slowpath_irq_free(cdev);
- }
qed_disable_msix(cdev);
{
struct qede_dev *edev = netdev_priv(dev);
- if (IS_VF(edev)) {
- DP_NOTICE(edev, "VFs don't support XDP\n");
- return -EOPNOTSUPP;
- }
-
switch (xdp->command) {
case XDP_SETUP_PROG:
return qede_xdp_set(edev, xdp->prog);
#endif
};
+static const struct net_device_ops qede_netdev_vf_ops = {
+ .ndo_open = qede_open,
+ .ndo_stop = qede_close,
+ .ndo_start_xmit = qede_start_xmit,
+ .ndo_set_rx_mode = qede_set_rx_mode,
+ .ndo_set_mac_address = qede_set_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = qede_change_mtu,
+ .ndo_vlan_rx_add_vid = qede_vlan_rx_add_vid,
+ .ndo_vlan_rx_kill_vid = qede_vlan_rx_kill_vid,
+ .ndo_set_features = qede_set_features,
+ .ndo_get_stats64 = qede_get_stats64,
+ .ndo_udp_tunnel_add = qede_udp_tunnel_add,
+ .ndo_udp_tunnel_del = qede_udp_tunnel_del,
+ .ndo_features_check = qede_features_check,
+};
+
/* -------------------------------------------------------------------------
* START OF PROBE / REMOVE
* -------------------------------------------------------------------------
ndev->watchdog_timeo = TX_TIMEOUT;
- ndev->netdev_ops = &qede_netdev_ops;
+ if (IS_VF(edev))
+ ndev->netdev_ops = &qede_netdev_vf_ops;
+ else
+ ndev->netdev_ops = &qede_netdev_ops;
qede_set_ethtool_ops(ndev);
if (fp->type & QEDE_FASTPATH_RX)
qede_free_mem_rxq(edev, fp->rxq);
+ if (fp->type & QEDE_FASTPATH_XDP)
+ qede_free_mem_txq(edev, fp->xdp_tx);
+
if (fp->type & QEDE_FASTPATH_TX)
qede_free_mem_txq(edev, fp->txq);
}
sizeof(struct mpi_coredump_global_header);
mpi_coredump->mpi_global_header.imageSize =
sizeof(struct ql_mpi_coredump);
- memcpy(mpi_coredump->mpi_global_header.idString, "MPI Coredump",
+ strncpy(mpi_coredump->mpi_global_header.idString, "MPI Coredump",
sizeof(mpi_coredump->mpi_global_header.idString));
/* Get generic NIC reg dump */
sizeof(struct mpi_coredump_global_header);
mpi_coredump->mpi_global_header.imageSize =
sizeof(struct ql_reg_dump);
- memcpy(mpi_coredump->mpi_global_header.idString, "MPI Coredump",
+ strncpy(mpi_coredump->mpi_global_header.idString, "MPI Coredump",
sizeof(mpi_coredump->mpi_global_header.idString));
module_param(max_interrupt_work, int, 0);
module_param(debug, int, 0);
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param_array(xcvr, int, NULL, 0);
MODULE_PARM_DESC(max_interrupt_work, "ATP maximum events handled per interrupt");
MODULE_PARM_DESC(debug, "ATP debug level (0-7)");
static struct net_device *devSMC9194;
MODULE_LICENSE("GPL");
-module_param(io, int, 0);
-module_param(irq, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
module_param(ifport, int, 0);
MODULE_PARM_DESC(io, "SMC 99194 I/O base address");
MODULE_PARM_DESC(irq, "SMC 99194 IRQ number");
return -ENODEV;
}
-static void stmmac_default_data(struct plat_stmmacenet_data *plat)
+static void common_default_data(struct plat_stmmacenet_data *plat)
{
- plat->bus_id = 1;
- plat->phy_addr = 0;
- plat->interface = PHY_INTERFACE_MODE_GMII;
plat->clk_csr = 2; /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
plat->has_gmac = 1;
plat->force_sf_dma_mode = 1;
plat->mdio_bus_data->phy_reset = NULL;
plat->mdio_bus_data->phy_mask = 0;
- plat->dma_cfg->pbl = 32;
- plat->dma_cfg->pblx8 = true;
- /* TODO: AXI */
-
/* Set default value for multicast hash bins */
plat->multicast_filter_bins = HASH_TABLE_SIZE;
plat->rx_queues_cfg[0].pkt_route = 0x0;
}
+static void stmmac_default_data(struct plat_stmmacenet_data *plat)
+{
+ /* Set common default data first */
+ common_default_data(plat);
+
+ plat->bus_id = 1;
+ plat->phy_addr = 0;
+ plat->interface = PHY_INTERFACE_MODE_GMII;
+
+ plat->dma_cfg->pbl = 32;
+ plat->dma_cfg->pblx8 = true;
+ /* TODO: AXI */
+}
+
static int quark_default_data(struct plat_stmmacenet_data *plat,
struct stmmac_pci_info *info)
{
struct pci_dev *pdev = info->pdev;
int ret;
+ /* Set common default data first */
+ common_default_data(plat);
+
/*
* Refuse to load the driver and register net device if MAC controller
* does not connect to any PHY interface.
plat->bus_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
plat->phy_addr = ret;
plat->interface = PHY_INTERFACE_MODE_RMII;
- plat->clk_csr = 2;
- plat->has_gmac = 1;
- plat->force_sf_dma_mode = 1;
-
- plat->mdio_bus_data->phy_reset = NULL;
- plat->mdio_bus_data->phy_mask = 0;
plat->dma_cfg->pbl = 16;
plat->dma_cfg->pblx8 = true;
plat->dma_cfg->fixed_burst = 1;
/* AXI (TODO) */
- /* Set default value for multicast hash bins */
- plat->multicast_filter_bins = HASH_TABLE_SIZE;
-
- /* Set default value for unicast filter entries */
- plat->unicast_filter_entries = 1;
-
- /* Set the maxmtu to a default of JUMBO_LEN */
- plat->maxmtu = JUMBO_LEN;
-
return 0;
}
/* Bit definitions for the CPSW1_TS_SEQ_LTYPE register */
#define CPSW_V1_SEQ_ID_OFS_SHIFT 16
+#define CPSW_MAX_BLKS_TX 15
+#define CPSW_MAX_BLKS_TX_SHIFT 4
+#define CPSW_MAX_BLKS_RX 5
+
struct cpsw_host_regs {
u32 max_blks;
u32 blk_cnt;
switch (cpsw->version) {
case CPSW_VERSION_1:
slave_write(slave, TX_PRIORITY_MAPPING, CPSW1_TX_PRI_MAP);
+ /* Increase RX FIFO size to 5 for supporting fullduplex
+ * flow control mode
+ */
+ slave_write(slave,
+ (CPSW_MAX_BLKS_TX << CPSW_MAX_BLKS_TX_SHIFT) |
+ CPSW_MAX_BLKS_RX, CPSW1_MAX_BLKS);
break;
case CPSW_VERSION_2:
case CPSW_VERSION_3:
case CPSW_VERSION_4:
slave_write(slave, TX_PRIORITY_MAPPING, CPSW2_TX_PRI_MAP);
+ /* Increase RX FIFO size to 5 for supporting fullduplex
+ * flow control mode
+ */
+ slave_write(slave,
+ (CPSW_MAX_BLKS_TX << CPSW_MAX_BLKS_TX_SHIFT) |
+ CPSW_MAX_BLKS_RX, CPSW2_MAX_BLKS);
break;
}
module_param_array(mode, charp, NULL, 0);
MODULE_PARM_DESC(mode, "baycom operating mode");
-module_param_array(iobase, int, NULL, 0);
+module_param_hw_array(iobase, int, ioport, NULL, 0);
MODULE_PARM_DESC(iobase, "baycom io base address");
MODULE_AUTHOR("Thomas M. Sailer, sailer@ife.ee.ethz.ch, hb9jnx@hb9w.che.eu");
module_param_array(mode, charp, NULL, 0);
MODULE_PARM_DESC(mode, "baycom operating mode; eg. par96 or picpar");
-module_param_array(iobase, int, NULL, 0);
+module_param_hw_array(iobase, int, ioport, NULL, 0);
MODULE_PARM_DESC(iobase, "baycom io base address");
MODULE_AUTHOR("Thomas M. Sailer, sailer@ife.ee.ethz.ch, hb9jnx@hb9w.che.eu");
module_param_array(mode, charp, NULL, 0);
MODULE_PARM_DESC(mode, "baycom operating mode; * for software DCD");
-module_param_array(iobase, int, NULL, 0);
+module_param_hw_array(iobase, int, ioport, NULL, 0);
MODULE_PARM_DESC(iobase, "baycom io base address");
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq, "baycom irq number");
module_param_array(baud, int, NULL, 0);
MODULE_PARM_DESC(baud, "baycom baud rate (300 to 4800)");
module_param_array(mode, charp, NULL, 0);
MODULE_PARM_DESC(mode, "baycom operating mode; * for software DCD");
-module_param_array(iobase, int, NULL, 0);
+module_param_hw_array(iobase, int, ioport, NULL, 0);
MODULE_PARM_DESC(iobase, "baycom io base address");
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq, "baycom irq number");
MODULE_AUTHOR("Thomas M. Sailer, sailer@ife.ee.ethz.ch, hb9jnx@hb9w.che.eu");
MODULE_AUTHOR("Klaus Kudielka");
MODULE_DESCRIPTION("Driver for high-speed SCC boards");
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_LICENSE("GPL");
static void __exit dmascc_exit(void)
case SIOCYAMSMCS:
if (netif_running(dev))
return -EINVAL; /* Cannot change this parameter when up */
- if ((ym = kmalloc(sizeof(struct yamdrv_ioctl_mcs), GFP_KERNEL)) == NULL)
- return -ENOBUFS;
- if (copy_from_user(ym, ifr->ifr_data, sizeof(struct yamdrv_ioctl_mcs))) {
- kfree(ym);
- return -EFAULT;
- }
+ ym = memdup_user(ifr->ifr_data,
+ sizeof(struct yamdrv_ioctl_mcs));
+ if (IS_ERR(ym))
+ return PTR_ERR(ym);
if (ym->bitrate > YAM_MAXBITRATE) {
kfree(ym);
return -EINVAL;
return -EPERM;
}
- image = kmalloc(EEPROM_WORDS * sizeof(u32), GFP_KERNEL);
- oldimage = kmalloc(EEPROM_WORDS * sizeof(u32), GFP_KERNEL);
- if (!image || !oldimage) {
- error = -ENOMEM;
- goto wf_out;
- }
+ image = memdup_user(rq->ifr_data, EEPROM_BYTES);
+ if (IS_ERR(image))
+ return PTR_ERR(image);
- error = copy_from_user(image, rq->ifr_data, EEPROM_BYTES);
- if (error) {
- error = -EFAULT;
- goto wf_out;
+ oldimage = kmalloc(EEPROM_BYTES, GFP_KERNEL);
+ if (!oldimage) {
+ kfree(image);
+ return -ENOMEM;
}
if (rrpriv->fw_running){
MODULE_ALIAS("platform:" ALI_IRCC_DRIVER_NAME);
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_PARM_DESC(io, "Base I/O addresses");
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq, "IRQ lines");
-module_param_array(dma, int, NULL, 0);
+module_param_hw_array(dma, int, dma, NULL, 0);
MODULE_PARM_DESC(dma, "DMA channels");
module_init(ali_ircc_init);
module_param(qos_mtt_bits, int, 0);
MODULE_PARM_DESC(qos_mtt_bits, "Minimum Turn Time");
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_PARM_DESC(io, "Base I/O addresses");
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq, "IRQ lines");
-module_param_array(dma, int, NULL, 0);
+module_param_hw_array(dma, int, dma, NULL, 0);
MODULE_PARM_DESC(dma, "DMA channels");
module_param(dongle_id, int, 0);
MODULE_PARM_DESC(dongle_id, "Type-id of used dongle");
#define DMA_INVAL 255
static int ircc_dma = DMA_INVAL;
-module_param(ircc_dma, int, 0);
+module_param_hw(ircc_dma, int, dma, 0);
MODULE_PARM_DESC(ircc_dma, "DMA channel");
#define IRQ_INVAL 255
static int ircc_irq = IRQ_INVAL;
-module_param(ircc_irq, int, 0);
+module_param_hw(ircc_irq, int, irq, 0);
MODULE_PARM_DESC(ircc_irq, "IRQ line");
static int ircc_fir;
-module_param(ircc_fir, int, 0);
+module_param_hw(ircc_fir, int, ioport, 0);
MODULE_PARM_DESC(ircc_fir, "FIR Base Address");
static int ircc_sir;
-module_param(ircc_sir, int, 0);
+module_param_hw(ircc_sir, int, ioport, 0);
MODULE_PARM_DESC(ircc_sir, "SIR Base Address");
static int ircc_cfg;
-module_param(ircc_cfg, int, 0);
+module_param_hw(ircc_cfg, int, ioport, 0);
MODULE_PARM_DESC(ircc_cfg, "Configuration register base address");
static int ircc_transceiver;
module_param(qos_mtt_bits, int, 0);
MODULE_PARM_DESC(qos_mtt_bits, "Mimimum Turn Time");
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_PARM_DESC(io, "Base I/O addresses");
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq, "IRQ lines");
/*
&md->mux_handle, md, md->mii_bus);
if (rc) {
dev_info(md->dev, "mdiomux initialization failed\n");
- goto out;
+ goto out_register;
}
dev_info(md->dev, "iProc mdiomux registered\n");
return 0;
+
+out_register:
+ mdiobus_unregister(bus);
out:
mdiobus_free(bus);
return rc;
u16 n = 0, index, ndplen;
u8 ready2send = 0;
u32 delayed_ndp_size;
+ size_t padding_count;
/* When our NDP gets written in cdc_ncm_ndp(), then skb_out->len gets updated
* accordingly. Otherwise, we should check here.
* a ZLP after full sized NTBs.
*/
if (!(dev->driver_info->flags & FLAG_SEND_ZLP) &&
- skb_out->len > ctx->min_tx_pkt)
- memset(skb_put(skb_out, ctx->tx_max - skb_out->len), 0,
- ctx->tx_max - skb_out->len);
- else if (skb_out->len < ctx->tx_max && (skb_out->len % dev->maxpacket) == 0)
+ skb_out->len > ctx->min_tx_pkt) {
+ padding_count = ctx->tx_max - skb_out->len;
+ memset(skb_put(skb_out, padding_count), 0, padding_count);
+ } else if (skb_out->len < ctx->tx_max &&
+ (skb_out->len % dev->maxpacket) == 0) {
*skb_put(skb_out, 1) = 0; /* force short packet */
+ }
/* set final frame length */
nth16 = (struct usb_cdc_ncm_nth16 *)skb_out->data;
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/average.h>
+#include <net/route.h>
static int napi_weight = NAPI_POLL_WEIGHT;
module_param(napi_weight, int, 0444);
*/
DECLARE_EWMA(pkt_len, 0, 64)
-/* With mergeable buffers we align buffer address and use the low bits to
- * encode its true size. Buffer size is up to 1 page so we need to align to
- * square root of page size to ensure we reserve enough bits to encode the true
- * size.
- */
-#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2)
-
-/* Minimum alignment for mergeable packet buffers. */
-#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \
- 1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT)
-
#define VIRTNET_DRIVER_VERSION "1.0.0"
struct virtnet_stats {
/* RX: fragments + linear part + virtio header */
struct scatterlist sg[MAX_SKB_FRAGS + 2];
+ /* Min single buffer size for mergeable buffers case. */
+ unsigned int min_buf_len;
+
/* Name of this receive queue: input.$index */
char name[40];
};
netif_wake_subqueue(vi->dev, vq2txq(vq));
}
-static unsigned int mergeable_ctx_to_buf_truesize(unsigned long mrg_ctx)
-{
- unsigned int truesize = mrg_ctx & (MERGEABLE_BUFFER_ALIGN - 1);
- return (truesize + 1) * MERGEABLE_BUFFER_ALIGN;
-}
-
-static void *mergeable_ctx_to_buf_address(unsigned long mrg_ctx)
-{
- return (void *)(mrg_ctx & -MERGEABLE_BUFFER_ALIGN);
-
-}
-
-static unsigned long mergeable_buf_to_ctx(void *buf, unsigned int truesize)
-{
- unsigned int size = truesize / MERGEABLE_BUFFER_ALIGN;
- return (unsigned long)buf | (size - 1);
-}
-
/* Called from bottom half context */
static struct sk_buff *page_to_skb(struct virtnet_info *vi,
struct receive_queue *rq,
while (--*num_buf) {
unsigned int buflen;
- unsigned long ctx;
void *buf;
int off;
- ctx = (unsigned long)virtqueue_get_buf(rq->vq, &buflen);
- if (unlikely(!ctx))
+ buf = virtqueue_get_buf(rq->vq, &buflen);
+ if (unlikely(!buf))
goto err_buf;
- buf = mergeable_ctx_to_buf_address(ctx);
p = virt_to_head_page(buf);
off = buf - page_address(p);
static struct sk_buff *receive_mergeable(struct net_device *dev,
struct virtnet_info *vi,
struct receive_queue *rq,
- unsigned long ctx,
+ void *buf,
+ void *ctx,
unsigned int len)
{
- void *buf = mergeable_ctx_to_buf_address(ctx);
struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
struct page *page = virt_to_head_page(buf);
}
rcu_read_unlock();
- truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
+ if (unlikely(len > (unsigned long)ctx)) {
+ pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+ dev->name, len, (unsigned long)ctx);
+ dev->stats.rx_length_errors++;
+ goto err_skb;
+ }
+ truesize = (unsigned long)ctx;
head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
curr_skb = head_skb;
while (--num_buf) {
int num_skb_frags;
- ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
+ buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
if (unlikely(!ctx)) {
pr_debug("%s: rx error: %d buffers out of %d missing\n",
dev->name, num_buf,
goto err_buf;
}
- buf = mergeable_ctx_to_buf_address(ctx);
page = virt_to_head_page(buf);
+ if (unlikely(len > (unsigned long)ctx)) {
+ pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+ dev->name, len, (unsigned long)ctx);
+ dev->stats.rx_length_errors++;
+ goto err_skb;
+ }
+ truesize = (unsigned long)ctx;
num_skb_frags = skb_shinfo(curr_skb)->nr_frags;
if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) {
head_skb->truesize += nskb->truesize;
num_skb_frags = 0;
}
- truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
if (curr_skb != head_skb) {
head_skb->data_len += len;
head_skb->len += len;
err_skb:
put_page(page);
while (--num_buf) {
- ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
- if (unlikely(!ctx)) {
+ buf = virtqueue_get_buf(rq->vq, &len);
+ if (unlikely(!buf)) {
pr_debug("%s: rx error: %d buffers missing\n",
dev->name, num_buf);
dev->stats.rx_length_errors++;
break;
}
- page = virt_to_head_page(mergeable_ctx_to_buf_address(ctx));
+ page = virt_to_head_page(buf);
put_page(page);
}
err_buf:
}
static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
- void *buf, unsigned int len)
+ void *buf, unsigned int len, void **ctx)
{
struct net_device *dev = vi->dev;
struct sk_buff *skb;
pr_debug("%s: short packet %i\n", dev->name, len);
dev->stats.rx_length_errors++;
if (vi->mergeable_rx_bufs) {
- unsigned long ctx = (unsigned long)buf;
- void *base = mergeable_ctx_to_buf_address(ctx);
- put_page(virt_to_head_page(base));
+ put_page(virt_to_head_page(buf));
} else if (vi->big_packets) {
give_pages(rq, buf);
} else {
}
if (vi->mergeable_rx_bufs)
- skb = receive_mergeable(dev, vi, rq, (unsigned long)buf, len);
+ skb = receive_mergeable(dev, vi, rq, buf, ctx, len);
else if (vi->big_packets)
skb = receive_big(dev, vi, rq, buf, len);
else
return err;
}
-static unsigned int get_mergeable_buf_len(struct ewma_pkt_len *avg_pkt_len)
+static unsigned int get_mergeable_buf_len(struct receive_queue *rq,
+ struct ewma_pkt_len *avg_pkt_len)
{
const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
unsigned int len;
len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len),
- GOOD_PACKET_LEN, PAGE_SIZE - hdr_len);
- return ALIGN(len, MERGEABLE_BUFFER_ALIGN);
+ rq->min_buf_len - hdr_len, PAGE_SIZE - hdr_len);
+ return ALIGN(len, L1_CACHE_BYTES);
}
static int add_recvbuf_mergeable(struct virtnet_info *vi,
struct page_frag *alloc_frag = &rq->alloc_frag;
unsigned int headroom = virtnet_get_headroom(vi);
char *buf;
- unsigned long ctx;
+ void *ctx;
int err;
unsigned int len, hole;
- len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len);
+ len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len);
if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp)))
return -ENOMEM;
buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
buf += headroom; /* advance address leaving hole at front of pkt */
- ctx = mergeable_buf_to_ctx(buf, len);
+ ctx = (void *)(unsigned long)len;
get_page(alloc_frag->page);
alloc_frag->offset += len + headroom;
hole = alloc_frag->size - alloc_frag->offset;
}
sg_init_one(rq->sg, buf, len);
- err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, (void *)ctx, gfp);
+ err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
if (err < 0)
put_page(virt_to_head_page(buf));
void *buf;
struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
- while (received < budget &&
- (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
- bytes += receive_buf(vi, rq, buf, len);
- received++;
+ if (vi->mergeable_rx_bufs) {
+ void *ctx;
+
+ while (received < budget &&
+ (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
+ bytes += receive_buf(vi, rq, buf, len, ctx);
+ received++;
+ }
+ } else {
+ while (received < budget &&
+ (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+ bytes += receive_buf(vi, rq, buf, len, NULL);
+ received++;
+ }
}
if (rq->vq->num_free > virtqueue_get_vring_size(rq->vq) / 2) {
virtnet_freeze_down(dev);
_remove_vq_common(vi);
- dev->config->reset(dev);
virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
if (vi->mergeable_rx_bufs) {
- unsigned long ctx = (unsigned long)buf;
- void *base = mergeable_ctx_to_buf_address(ctx);
- put_page(virt_to_head_page(base));
+ put_page(virt_to_head_page(buf));
} else if (vi->big_packets) {
give_pages(&vi->rq[i], buf);
} else {
virtnet_free_queues(vi);
}
+/* How large should a single buffer be so a queue full of these can fit at
+ * least one full packet?
+ * Logic below assumes the mergeable buffer header is used.
+ */
+static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqueue *vq)
+{
+ const unsigned int hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+ unsigned int rq_size = virtqueue_get_vring_size(vq);
+ unsigned int packet_len = vi->big_packets ? IP_MAX_MTU : vi->dev->max_mtu;
+ unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len;
+ unsigned int min_buf_len = DIV_ROUND_UP(buf_len, rq_size);
+
+ return max(min_buf_len, hdr_len);
+}
+
static int virtnet_find_vqs(struct virtnet_info *vi)
{
vq_callback_t **callbacks;
int ret = -ENOMEM;
int i, total_vqs;
const char **names;
+ bool *ctx;
/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
* possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
names = kmalloc(total_vqs * sizeof(*names), GFP_KERNEL);
if (!names)
goto err_names;
+ if (vi->mergeable_rx_bufs) {
+ ctx = kzalloc(total_vqs * sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ goto err_ctx;
+ } else {
+ ctx = NULL;
+ }
/* Parameters for control virtqueue, if any */
if (vi->has_cvq) {
sprintf(vi->sq[i].name, "output.%d", i);
names[rxq2vq(i)] = vi->rq[i].name;
names[txq2vq(i)] = vi->sq[i].name;
+ if (ctx)
+ ctx[rxq2vq(i)] = true;
}
ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
- names, NULL);
+ names, ctx, NULL);
if (ret)
goto err_find;
for (i = 0; i < vi->max_queue_pairs; i++) {
vi->rq[i].vq = vqs[rxq2vq(i)];
+ vi->rq[i].min_buf_len = mergeable_min_buf_len(vi, vi->rq[i].vq);
vi->sq[i].vq = vqs[txq2vq(i)];
}
return 0;
err_find:
+ kfree(ctx);
+err_ctx:
kfree(names);
err_names:
kfree(callbacks);
BUG_ON(queue_index >= vi->max_queue_pairs);
avg = &vi->rq[queue_index].mrg_avg_pkt_len;
- return sprintf(buf, "%u\n", get_mergeable_buf_len(avg));
+ return sprintf(buf, "%u\n",
+ get_mergeable_buf_len(&vi->rq[queue_index], avg));
}
static struct rx_queue_attribute mergeable_rx_buffer_size_attribute =
static struct class *cosa_class;
#ifdef MODULE
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_PARM_DESC(io, "The I/O bases of the COSA or SRP cards");
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq, "The IRQ lines of the COSA or SRP cards");
-module_param_array(dma, int, NULL, 0);
+module_param_hw_array(dma, int, dma, NULL, 0);
MODULE_PARM_DESC(dma, "The DMA channels of the COSA or SRP cards");
MODULE_AUTHOR("Jan \"Yenya\" Kasprzak, <kas@fi.muni.cz>");
static int io = 0x200;
static int irq = 9;
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
MODULE_PARM_DESC(io, "The I/O base of the Comtrol Hostess SV11 card");
-module_param(dma, int, 0);
+module_param_hw(dma, int, dma, 0);
MODULE_PARM_DESC(dma, "Set this to 1 to use DMA1/DMA3 for TX/RX");
-module_param(irq, int, 0);
+module_param_hw(irq, int, irq, 0);
MODULE_PARM_DESC(irq, "The interrupt line setting for the Comtrol Hostess SV11 card");
MODULE_AUTHOR("Alan Cox");
#ifdef MODULE
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param_array(baud, int, NULL, 0);
module_param_array(rxl, int, NULL, 0);
module_param_array(mac, int, NULL, 0);
static int irq=5;
static bool slow=false;
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
MODULE_PARM_DESC(io, "The I/O base of the Sealevel card");
-module_param(txdma, int, 0);
+module_param_hw(txdma, int, dma, 0);
MODULE_PARM_DESC(txdma, "Transmit DMA channel");
-module_param(rxdma, int, 0);
+module_param_hw(rxdma, int, dma, 0);
MODULE_PARM_DESC(rxdma, "Receive DMA channel");
-module_param(irq, int, 0);
+module_param_hw(irq, int, irq, 0);
MODULE_PARM_DESC(irq, "The interrupt line setting for the SeaLevel card");
module_param(slow, bool, 0);
MODULE_PARM_DESC(slow, "Set this for an older Sealevel card such as the 4012");
unsigned long now;
now = jiffies;
- if (now - edc->timestart > timeframe) {
+ if (time_after(now, edc->timestart + timeframe)) {
edc->errorcount = 1;
edc->timestart = now;
} else if (++edc->errorcount > max_err) {
rxs->rs_moreaggr = (rxsp->status11 & AR_RxMoreAggr) ? 1 : 0;
rxs->rs_antenna = (MS(rxsp->status4, AR_RxAntenna) & 0x7);
rxs->enc_flags |= (rxsp->status4 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0;
- rxs->enc_flags |= (rxsp->status4 & AR_2040) ? RX_ENC_FLAG_40MHZ : 0;
+ rxs->bw = (rxsp->status4 & AR_2040) ? RATE_INFO_BW_40 : RATE_INFO_BW_20;
rxs->evm0 = rxsp->status6;
rxs->evm1 = rxsp->status7;
/* directly mapped flags for ieee80211_rx_status */
rs->enc_flags |=
(ads.ds_rxstatus3 & AR_GI) ? RX_ENC_FLAG_SHORT_GI : 0;
- rs->enc_flags |=
- (ads.ds_rxstatus3 & AR_2040) ? RX_ENC_FLAG_40MHZ : 0;
+ rs->bw = (ads.ds_rxstatus3 & AR_2040) ? RATE_INFO_BW_40 :
+ RATE_INFO_BW_20;
if (AR_SREV_9280_20_OR_LATER(ah))
rs->enc_flags |=
(ads.ds_rxstatus3 & AR_STBC) ?
"Direct support for ISA/PCI/MPI cards and support for PCMCIA when used with airo_cs.");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_SUPPORTED_DEVICE("Aironet 4500, 4800 and Cisco 340/350");
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param_array(rates, int, NULL, 0);
module_param_array(ssids, charp, NULL, 0);
module_param(auto_wep, int, 0);
if (rate_n_flags & RATE_MCS_HT_MSK)
rx_status.encoding = RX_ENC_HT;
if (rate_n_flags & RATE_MCS_HT40_MSK)
- rx_status.enc_flags |= RX_ENC_FLAG_40MHZ;
+ rx_status.bw = RATE_INFO_BW_40;
+ else
+ rx_status.bw = RATE_INFO_BW_20;
if (rate_n_flags & RATE_MCS_SGI_MSK)
rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI;
if (rate_n_flags & RATE_MCS_HT_MSK)
rx_status.encoding = RX_ENC_HT;
if (rate_n_flags & RATE_MCS_HT40_MSK)
- rx_status.enc_flags |= RX_ENC_FLAG_40MHZ;
+ rx_status.bw = RATE_INFO_BW_40;
+ else
+ rx_status.bw = RATE_INFO_BW_20;
if (rate_n_flags & RATE_MCS_SGI_MSK)
rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI;
if (rate_n_flags & RATE_MCS_GF_MSK)
rx_status.encoding = RX_ENC_HT;
}
if (info->control.rates[0].flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
- rx_status.enc_flags |= RX_ENC_FLAG_40MHZ;
+ rx_status.bw = RATE_INFO_BW_40;
+ else if (info->control.rates[0].flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+ rx_status.bw = RATE_INFO_BW_80;
+ else if (info->control.rates[0].flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
+ rx_status.bw = RATE_INFO_BW_160;
+ else
+ rx_status.bw = RATE_INFO_BW_20;
if (info->control.rates[0].flags & IEEE80211_TX_RC_SHORT_GI)
rx_status.enc_flags |= RX_ENC_FLAG_SHORT_GI;
/* TODO: simulate real signal strength (and optional packet loss) */
if (unlikely(elba > nvmdev->total_secs)) {
pr_err("nvm: L2P data from device is out of bounds!\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
/* Transform physical address to target address space */
return ret;
}
-static inline void nvme_nvm_rqtocmd(struct request *rq, struct nvm_rq *rqd,
- struct nvme_ns *ns, struct nvme_nvm_command *c)
+static inline void nvme_nvm_rqtocmd(struct nvm_rq *rqd, struct nvme_ns *ns,
+ struct nvme_nvm_command *c)
{
c->ph_rw.opcode = rqd->opcode;
c->ph_rw.nsid = cpu_to_le32(ns->ns_id);
if (!cmd)
return -ENOMEM;
- nvme_nvm_rqtocmd(rq, rqd, ns, cmd);
+ nvme_nvm_rqtocmd(rqd, ns, cmd);
rq = nvme_alloc_request(q, (struct nvme_command *)cmd, 0, NVME_QID_ANY);
if (IS_ERR(rq)) {
* can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events
* to fix up DMA configuration.
*/
-void of_dma_configure(struct device *dev, struct device_node *np)
+int of_dma_configure(struct device *dev, struct device_node *np)
{
u64 dma_addr, paddr, size;
int ret;
ret = of_dma_get_range(np, &dma_addr, &paddr, &size);
if (ret < 0) {
dma_addr = offset = 0;
- size = dev->coherent_dma_mask + 1;
+ size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
} else {
offset = PFN_DOWN(paddr - dma_addr);
if (!size) {
dev_err(dev, "Adjusted size 0x%llx invalid\n", size);
- return;
+ return -EINVAL;
}
dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset);
}
coherent ? " " : " not ");
iommu = of_iommu_configure(dev, np);
+ if (IS_ERR(iommu))
+ return PTR_ERR(iommu);
+
dev_dbg(dev, "device is%sbehind an iommu\n",
iommu ? " " : " not ");
arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(of_dma_configure);
+/**
+ * of_dma_deconfigure - Clean up DMA configuration
+ * @dev: Device for which to clean up DMA configuration
+ *
+ * Clean up all configuration performed by of_dma_configure_ops() and free all
+ * resources that have been allocated.
+ */
+void of_dma_deconfigure(struct device *dev)
+{
+ arch_teardown_dma_ops(dev);
+}
+
int of_device_register(struct platform_device *pdev)
{
device_initialize(&pdev->dev);
#include <linux/slab.h>
#include <linux/of_address.h>
#include <linux/of_device.h>
+#include <linux/of_iommu.h>
#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
}
EXPORT_SYMBOL(of_device_alloc);
-static void of_dma_deconfigure(struct device *dev)
-{
- arch_teardown_dma_ops(dev);
-}
-
/**
* of_platform_device_create_pdata - Alloc, initialize and register an of_device
* @np: pointer to node to create device for
dev->dev.bus = &platform_bus_type;
dev->dev.platform_data = platform_data;
- of_dma_configure(&dev->dev, dev->dev.of_node);
of_msi_configure(&dev->dev, dev->dev.of_node);
if (of_device_add(dev) != 0) {
- of_dma_deconfigure(&dev->dev);
platform_device_put(dev);
goto err_clear_flag;
}
dev_set_name(&dev->dev, "%s", bus_id);
else
of_device_make_bus_id(&dev->dev);
- of_dma_configure(&dev->dev, dev->dev.of_node);
/* Allow the HW Peripheral ID to be overridden */
prop = of_get_property(node, "arm,primecell-periphid", NULL);
amba_device_unregister(to_amba_device(dev));
#endif
- of_dma_deconfigure(dev);
of_node_clear_flag(dev->of_node, OF_POPULATED);
of_node_clear_flag(dev->of_node, OF_POPULATED_BUS);
return 0;
static char *dma[PARPORT_PC_MAX_PORTS];
MODULE_PARM_DESC(io, "Base I/O address (SPP regs)");
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_PARM_DESC(io_hi, "Base I/O address (ECR)");
-module_param_array(io_hi, int, NULL, 0);
+module_param_hw_array(io_hi, int, ioport, NULL, 0);
MODULE_PARM_DESC(irq, "IRQ line");
-module_param_array(irq, charp, NULL, 0);
+module_param_hw_array(irq, charp, irq, NULL, 0);
MODULE_PARM_DESC(dma, "DMA channel");
-module_param_array(dma, charp, NULL, 0);
+module_param_hw_array(dma, charp, dma, NULL, 0);
#if defined(CONFIG_PARPORT_PC_SUPERIO) || \
(defined(CONFIG_PARPORT_1284) && defined(CONFIG_PARPORT_PC_FIFO))
MODULE_PARM_DESC(verbose_probing, "Log chit-chat during initialisation");
MODULE_PARM_DESC(first_slot, "Hotswap bus first slot number");
module_param(last_slot, byte, 0);
MODULE_PARM_DESC(last_slot, "Hotswap bus last slot number");
-module_param(port, ushort, 0);
+module_param_hw(port, ushort, ioport, 0);
MODULE_PARM_DESC(port, "#ENUM signal I/O port");
module_param(enum_bit, uint, 0);
MODULE_PARM_DESC(enum_bit, "#ENUM signal bit (0-7)");
dev_set_msi_domain(&dev->dev, d);
}
-/**
- * pci_dma_configure - Setup DMA configuration
- * @dev: ptr to pci_dev struct of the PCI device
- *
- * Function to update PCI devices's DMA configuration using the same
- * info from the OF node or ACPI node of host bridge's parent (if any).
- */
-static void pci_dma_configure(struct pci_dev *dev)
-{
- struct device *bridge = pci_get_host_bridge_device(dev);
-
- if (IS_ENABLED(CONFIG_OF) &&
- bridge->parent && bridge->parent->of_node) {
- of_dma_configure(&dev->dev, bridge->parent->of_node);
- } else if (has_acpi_companion(bridge)) {
- struct acpi_device *adev = to_acpi_device_node(bridge->fwnode);
- enum dev_dma_attr attr = acpi_get_dma_attr(adev);
-
- if (attr == DEV_DMA_NOT_SUPPORTED)
- dev_warn(&dev->dev, "DMA not supported.\n");
- else
- acpi_dma_configure(&dev->dev, attr);
- }
-
- pci_put_host_bridge_device(bridge);
-}
-
void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
{
int ret;
dev->dev.dma_mask = &dev->dma_mask;
dev->dev.dma_parms = &dev->dma_parms;
dev->dev.coherent_dma_mask = 0xffffffffull;
- pci_dma_configure(dev);
pci_set_dma_max_seg_size(dev, 65536);
pci_set_dma_seg_boundary(dev, 0xffffffff);
static int cable_mode = -1;
static int wakeup = 0;
-module_param(i365_base, ulong, 0444);
+module_param_hw(i365_base, ulong, ioport, 0444);
module_param(ignore, int, 0444);
module_param(extra_sockets, int, 0444);
-module_param(irq_mask, int, 0444);
-module_param_array(irq_list, int, &irq_list_count, 0444);
-module_param(cs_irq, int, 0444);
+module_param_hw(irq_mask, int, other, 0444);
+module_param_hw_array(irq_list, int, irq, &irq_list_count, 0444);
+module_param_hw(cs_irq, int, irq, 0444);
module_param(async_clock, int, 0444);
module_param(cable_mode, int, 0444);
module_param(wakeup, int, 0444);
/* CCLK external clock time, in nanoseconds. 70 ns = 14.31818 MHz */
static int cycle_time = 70;
-module_param(tcic_base, ulong, 0444);
+module_param_hw(tcic_base, ulong, ioport, 0444);
module_param(ignore, int, 0444);
module_param(do_scan, int, 0444);
-module_param(irq_mask, int, 0444);
-module_param_array(irq_list, int, &irq_list_count, 0444);
-module_param(cs_irq, int, 0444);
+module_param_hw(irq_mask, int, other, 0444);
+module_param_hw_array(irq_list, int, irq, &irq_list_count, 0444);
+module_param_hw(cs_irq, int, irq, 0444);
module_param(poll_interval, int, 0444);
module_param(poll_quick, int, 0444);
module_param(cycle_time, int, 0444);
RAPL_CPU(INTEL_FAM6_ATOM_MERRIFIELD, rapl_defaults_tng),
RAPL_CPU(INTEL_FAM6_ATOM_MOOREFIELD, rapl_defaults_ann),
RAPL_CPU(INTEL_FAM6_ATOM_GOLDMONT, rapl_defaults_core),
+ RAPL_CPU(INTEL_FAM6_ATOM_GEMINI_LAKE, rapl_defaults_core),
RAPL_CPU(INTEL_FAM6_ATOM_DENVERTON, rapl_defaults_core),
RAPL_CPU(INTEL_FAM6_XEON_PHI_KNL, rapl_defaults_hsw_server),
To compile this driver as a module, choose M here: the module
will be called pwm-mtk-disp.
+config PWM_MEDIATEK
+ tristate "MediaTek PWM support"
+ depends on ARCH_MEDIATEK || COMPILE_TEST
+ help
+ Generic PWM framework driver for Mediatek ARM SoC.
+
+ To compile this driver as a module, choose M here: the module
+ will be called pwm-mxs.
+
config PWM_MXS
tristate "Freescale MXS PWM support"
depends on ARCH_MXS && OF
obj-$(CONFIG_PWM_LPSS_PCI) += pwm-lpss-pci.o
obj-$(CONFIG_PWM_LPSS_PLATFORM) += pwm-lpss-platform.o
obj-$(CONFIG_PWM_MESON) += pwm-meson.o
+obj-$(CONFIG_PWM_MEDIATEK) += pwm-mediatek.o
obj-$(CONFIG_PWM_MTK_DISP) += pwm-mtk-disp.o
obj-$(CONFIG_PWM_MXS) += pwm-mxs.o
obj-$(CONFIG_PWM_OMAP_DMTIMER) += pwm-omap-dmtimer.o
return container_of(chip, struct atmel_hlcdc_pwm, chip);
}
-static int atmel_hlcdc_pwm_config(struct pwm_chip *c,
- struct pwm_device *pwm,
- int duty_ns, int period_ns)
+static int atmel_hlcdc_pwm_apply(struct pwm_chip *c, struct pwm_device *pwm,
+ struct pwm_state *state)
{
struct atmel_hlcdc_pwm *chip = to_atmel_hlcdc_pwm(c);
struct atmel_hlcdc *hlcdc = chip->hlcdc;
- struct clk *new_clk = hlcdc->slow_clk;
- u64 pwmcval = duty_ns * 256;
- unsigned long clk_freq;
- u64 clk_period_ns;
- u32 pwmcfg;
- int pres;
-
- if (!chip->errata || !chip->errata->slow_clk_erratum) {
- clk_freq = clk_get_rate(new_clk);
- if (!clk_freq)
- return -EINVAL;
+ unsigned int status;
+ int ret;
- clk_period_ns = (u64)NSEC_PER_SEC * 256;
- do_div(clk_period_ns, clk_freq);
- }
+ if (state->enabled) {
+ struct clk *new_clk = hlcdc->slow_clk;
+ u64 pwmcval = state->duty_cycle * 256;
+ unsigned long clk_freq;
+ u64 clk_period_ns;
+ u32 pwmcfg;
+ int pres;
+
+ if (!chip->errata || !chip->errata->slow_clk_erratum) {
+ clk_freq = clk_get_rate(new_clk);
+ if (!clk_freq)
+ return -EINVAL;
+
+ clk_period_ns = (u64)NSEC_PER_SEC * 256;
+ do_div(clk_period_ns, clk_freq);
+ }
+
+ /* Errata: cannot use slow clk on some IP revisions */
+ if ((chip->errata && chip->errata->slow_clk_erratum) ||
+ clk_period_ns > state->period) {
+ new_clk = hlcdc->sys_clk;
+ clk_freq = clk_get_rate(new_clk);
+ if (!clk_freq)
+ return -EINVAL;
+
+ clk_period_ns = (u64)NSEC_PER_SEC * 256;
+ do_div(clk_period_ns, clk_freq);
+ }
+
+ for (pres = 0; pres <= ATMEL_HLCDC_PWMPS_MAX; pres++) {
+ /* Errata: cannot divide by 1 on some IP revisions */
+ if (!pres && chip->errata &&
+ chip->errata->div1_clk_erratum)
+ continue;
+
+ if ((clk_period_ns << pres) >= state->period)
+ break;
+ }
- /* Errata: cannot use slow clk on some IP revisions */
- if ((chip->errata && chip->errata->slow_clk_erratum) ||
- clk_period_ns > period_ns) {
- new_clk = hlcdc->sys_clk;
- clk_freq = clk_get_rate(new_clk);
- if (!clk_freq)
+ if (pres > ATMEL_HLCDC_PWMPS_MAX)
return -EINVAL;
- clk_period_ns = (u64)NSEC_PER_SEC * 256;
- do_div(clk_period_ns, clk_freq);
- }
+ pwmcfg = ATMEL_HLCDC_PWMPS(pres);
- for (pres = 0; pres <= ATMEL_HLCDC_PWMPS_MAX; pres++) {
- /* Errata: cannot divide by 1 on some IP revisions */
- if (!pres && chip->errata && chip->errata->div1_clk_erratum)
- continue;
+ if (new_clk != chip->cur_clk) {
+ u32 gencfg = 0;
+ int ret;
- if ((clk_period_ns << pres) >= period_ns)
- break;
- }
+ ret = clk_prepare_enable(new_clk);
+ if (ret)
+ return ret;
- if (pres > ATMEL_HLCDC_PWMPS_MAX)
- return -EINVAL;
+ clk_disable_unprepare(chip->cur_clk);
+ chip->cur_clk = new_clk;
- pwmcfg = ATMEL_HLCDC_PWMPS(pres);
+ if (new_clk == hlcdc->sys_clk)
+ gencfg = ATMEL_HLCDC_CLKPWMSEL;
- if (new_clk != chip->cur_clk) {
- u32 gencfg = 0;
- int ret;
+ ret = regmap_update_bits(hlcdc->regmap,
+ ATMEL_HLCDC_CFG(0),
+ ATMEL_HLCDC_CLKPWMSEL,
+ gencfg);
+ if (ret)
+ return ret;
+ }
- ret = clk_prepare_enable(new_clk);
- if (ret)
- return ret;
+ do_div(pwmcval, state->period);
- clk_disable_unprepare(chip->cur_clk);
- chip->cur_clk = new_clk;
+ /*
+ * The PWM duty cycle is configurable from 0/256 to 255/256 of
+ * the period cycle. Hence we can't set a duty cycle occupying
+ * the whole period cycle if we're asked to.
+ * Set it to 255 if pwmcval is greater than 256.
+ */
+ if (pwmcval > 255)
+ pwmcval = 255;
- if (new_clk == hlcdc->sys_clk)
- gencfg = ATMEL_HLCDC_CLKPWMSEL;
+ pwmcfg |= ATMEL_HLCDC_PWMCVAL(pwmcval);
- ret = regmap_update_bits(hlcdc->regmap, ATMEL_HLCDC_CFG(0),
- ATMEL_HLCDC_CLKPWMSEL, gencfg);
+ if (state->polarity == PWM_POLARITY_NORMAL)
+ pwmcfg |= ATMEL_HLCDC_PWMPOL;
+
+ ret = regmap_update_bits(hlcdc->regmap, ATMEL_HLCDC_CFG(6),
+ ATMEL_HLCDC_PWMCVAL_MASK |
+ ATMEL_HLCDC_PWMPS_MASK |
+ ATMEL_HLCDC_PWMPOL,
+ pwmcfg);
if (ret)
return ret;
- }
- do_div(pwmcval, period_ns);
-
- /*
- * The PWM duty cycle is configurable from 0/256 to 255/256 of the
- * period cycle. Hence we can't set a duty cycle occupying the
- * whole period cycle if we're asked to.
- * Set it to 255 if pwmcval is greater than 256.
- */
- if (pwmcval > 255)
- pwmcval = 255;
-
- pwmcfg |= ATMEL_HLCDC_PWMCVAL(pwmcval);
+ ret = regmap_write(hlcdc->regmap, ATMEL_HLCDC_EN,
+ ATMEL_HLCDC_PWM);
+ if (ret)
+ return ret;
- return regmap_update_bits(hlcdc->regmap, ATMEL_HLCDC_CFG(6),
- ATMEL_HLCDC_PWMCVAL_MASK |
- ATMEL_HLCDC_PWMPS_MASK,
- pwmcfg);
-}
+ ret = regmap_read_poll_timeout(hlcdc->regmap, ATMEL_HLCDC_SR,
+ status,
+ status & ATMEL_HLCDC_PWM,
+ 10, 0);
+ if (ret)
+ return ret;
+ } else {
+ ret = regmap_write(hlcdc->regmap, ATMEL_HLCDC_DIS,
+ ATMEL_HLCDC_PWM);
+ if (ret)
+ return ret;
-static int atmel_hlcdc_pwm_set_polarity(struct pwm_chip *c,
- struct pwm_device *pwm,
- enum pwm_polarity polarity)
-{
- struct atmel_hlcdc_pwm *chip = to_atmel_hlcdc_pwm(c);
- struct atmel_hlcdc *hlcdc = chip->hlcdc;
- u32 cfg = 0;
+ ret = regmap_read_poll_timeout(hlcdc->regmap, ATMEL_HLCDC_SR,
+ status,
+ !(status & ATMEL_HLCDC_PWM),
+ 10, 0);
+ if (ret)
+ return ret;
- if (polarity == PWM_POLARITY_NORMAL)
- cfg = ATMEL_HLCDC_PWMPOL;
+ clk_disable_unprepare(chip->cur_clk);
+ chip->cur_clk = NULL;
+ }
- return regmap_update_bits(hlcdc->regmap, ATMEL_HLCDC_CFG(6),
- ATMEL_HLCDC_PWMPOL, cfg);
+ return 0;
}
-static int atmel_hlcdc_pwm_enable(struct pwm_chip *c, struct pwm_device *pwm)
-{
- struct atmel_hlcdc_pwm *chip = to_atmel_hlcdc_pwm(c);
- struct atmel_hlcdc *hlcdc = chip->hlcdc;
- u32 status;
- int ret;
+static const struct pwm_ops atmel_hlcdc_pwm_ops = {
+ .apply = atmel_hlcdc_pwm_apply,
+ .owner = THIS_MODULE,
+};
- ret = regmap_write(hlcdc->regmap, ATMEL_HLCDC_EN, ATMEL_HLCDC_PWM);
- if (ret)
- return ret;
+static const struct atmel_hlcdc_pwm_errata atmel_hlcdc_pwm_at91sam9x5_errata = {
+ .slow_clk_erratum = true,
+};
- while (true) {
- ret = regmap_read(hlcdc->regmap, ATMEL_HLCDC_SR, &status);
- if (ret)
- return ret;
+static const struct atmel_hlcdc_pwm_errata atmel_hlcdc_pwm_sama5d3_errata = {
+ .div1_clk_erratum = true,
+};
- if ((status & ATMEL_HLCDC_PWM) != 0)
- break;
+#ifdef CONFIG_PM_SLEEP
+static int atmel_hlcdc_pwm_suspend(struct device *dev)
+{
+ struct atmel_hlcdc_pwm *chip = dev_get_drvdata(dev);
- usleep_range(1, 10);
- }
+ /* Keep the periph clock enabled if the PWM is still running. */
+ if (pwm_is_enabled(&chip->chip.pwms[0]))
+ clk_disable_unprepare(chip->hlcdc->periph_clk);
return 0;
}
-static void atmel_hlcdc_pwm_disable(struct pwm_chip *c,
- struct pwm_device *pwm)
+static int atmel_hlcdc_pwm_resume(struct device *dev)
{
- struct atmel_hlcdc_pwm *chip = to_atmel_hlcdc_pwm(c);
- struct atmel_hlcdc *hlcdc = chip->hlcdc;
- u32 status;
+ struct atmel_hlcdc_pwm *chip = dev_get_drvdata(dev);
+ struct pwm_state state;
int ret;
- ret = regmap_write(hlcdc->regmap, ATMEL_HLCDC_DIS, ATMEL_HLCDC_PWM);
- if (ret)
- return;
+ pwm_get_state(&chip->chip.pwms[0], &state);
- while (true) {
- ret = regmap_read(hlcdc->regmap, ATMEL_HLCDC_SR, &status);
+ /* Re-enable the periph clock it was stopped during suspend. */
+ if (!state.enabled) {
+ ret = clk_prepare_enable(chip->hlcdc->periph_clk);
if (ret)
- return;
-
- if ((status & ATMEL_HLCDC_PWM) == 0)
- break;
-
- usleep_range(1, 10);
+ return ret;
}
-}
-
-static const struct pwm_ops atmel_hlcdc_pwm_ops = {
- .config = atmel_hlcdc_pwm_config,
- .set_polarity = atmel_hlcdc_pwm_set_polarity,
- .enable = atmel_hlcdc_pwm_enable,
- .disable = atmel_hlcdc_pwm_disable,
- .owner = THIS_MODULE,
-};
-static const struct atmel_hlcdc_pwm_errata atmel_hlcdc_pwm_at91sam9x5_errata = {
- .slow_clk_erratum = true,
-};
+ return atmel_hlcdc_pwm_apply(&chip->chip, &chip->chip.pwms[0], &state);
+}
+#endif
-static const struct atmel_hlcdc_pwm_errata atmel_hlcdc_pwm_sama5d3_errata = {
- .div1_clk_erratum = true,
-};
+static SIMPLE_DEV_PM_OPS(atmel_hlcdc_pwm_pm_ops,
+ atmel_hlcdc_pwm_suspend, atmel_hlcdc_pwm_resume);
static const struct of_device_id atmel_hlcdc_dt_ids[] = {
{
.driver = {
.name = "atmel-hlcdc-pwm",
.of_match_table = atmel_hlcdc_pwm_dt_ids,
+ .pm = &atmel_hlcdc_pwm_pm_ops,
},
.probe = atmel_hlcdc_pwm_probe,
.remove = atmel_hlcdc_pwm_remove,
#define PWM_MAX_PRD 0xFFFF
#define PRD_MAX_PRES 10
+struct atmel_pwm_registers {
+ u8 period;
+ u8 period_upd;
+ u8 duty;
+ u8 duty_upd;
+};
+
struct atmel_pwm_chip {
struct pwm_chip chip;
struct clk *clk;
void __iomem *base;
+ const struct atmel_pwm_registers *regs;
unsigned int updated_pwms;
/* ISR is cleared when read, ensure only one thread does that */
struct mutex isr_lock;
-
- void (*config)(struct pwm_chip *chip, struct pwm_device *pwm,
- unsigned long dty, unsigned long prd);
};
static inline struct atmel_pwm_chip *to_atmel_pwm_chip(struct pwm_chip *chip)
writel_relaxed(val, chip->base + base + offset);
}
-static int atmel_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
- int duty_ns, int period_ns)
+static int atmel_pwm_calculate_cprd_and_pres(struct pwm_chip *chip,
+ const struct pwm_state *state,
+ unsigned long *cprd, u32 *pres)
{
struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
- unsigned long prd, dty;
- unsigned long long div;
- unsigned int pres = 0;
- u32 val;
- int ret;
-
- if (pwm_is_enabled(pwm) && (period_ns != pwm_get_period(pwm))) {
- dev_err(chip->dev, "cannot change PWM period while enabled\n");
- return -EBUSY;
- }
+ unsigned long long cycles = state->period;
/* Calculate the period cycles and prescale value */
- div = (unsigned long long)clk_get_rate(atmel_pwm->clk) * period_ns;
- do_div(div, NSEC_PER_SEC);
+ cycles *= clk_get_rate(atmel_pwm->clk);
+ do_div(cycles, NSEC_PER_SEC);
- while (div > PWM_MAX_PRD) {
- div >>= 1;
- pres++;
- }
+ for (*pres = 0; cycles > PWM_MAX_PRD; cycles >>= 1)
+ (*pres)++;
- if (pres > PRD_MAX_PRES) {
+ if (*pres > PRD_MAX_PRES) {
dev_err(chip->dev, "pres exceeds the maximum value\n");
return -EINVAL;
}
- /* Calculate the duty cycles */
- prd = div;
- div *= duty_ns;
- do_div(div, period_ns);
- dty = prd - div;
-
- ret = clk_enable(atmel_pwm->clk);
- if (ret) {
- dev_err(chip->dev, "failed to enable PWM clock\n");
- return ret;
- }
-
- /* It is necessary to preserve CPOL, inside CMR */
- val = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
- val = (val & ~PWM_CMR_CPRE_MSK) | (pres & PWM_CMR_CPRE_MSK);
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
- atmel_pwm->config(chip, pwm, dty, prd);
- mutex_lock(&atmel_pwm->isr_lock);
- atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
- atmel_pwm->updated_pwms &= ~(1 << pwm->hwpwm);
- mutex_unlock(&atmel_pwm->isr_lock);
-
- clk_disable(atmel_pwm->clk);
- return ret;
-}
-
-static void atmel_pwm_config_v1(struct pwm_chip *chip, struct pwm_device *pwm,
- unsigned long dty, unsigned long prd)
-{
- struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
- unsigned int val;
-
+ *cprd = cycles;
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CUPD, dty);
-
- val = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
- val &= ~PWM_CMR_UPD_CDTY;
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
-
- /*
- * If the PWM channel is enabled, only update CDTY by using the update
- * register, it needs to set bit 10 of CMR to 0
- */
- if (pwm_is_enabled(pwm))
- return;
- /*
- * If the PWM channel is disabled, write value to duty and period
- * registers directly.
- */
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CDTY, dty);
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV1_CPRD, prd);
+ return 0;
}
-static void atmel_pwm_config_v2(struct pwm_chip *chip, struct pwm_device *pwm,
- unsigned long dty, unsigned long prd)
+static void atmel_pwm_calculate_cdty(const struct pwm_state *state,
+ unsigned long cprd, unsigned long *cdty)
{
- struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
+ unsigned long long cycles = state->duty_cycle;
- if (pwm_is_enabled(pwm)) {
- /*
- * If the PWM channel is enabled, using the duty update register
- * to update the value.
- */
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV2_CDTYUPD, dty);
- } else {
- /*
- * If the PWM channel is disabled, write value to duty and
- * period registers directly.
- */
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV2_CDTY, dty);
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWMV2_CPRD, prd);
- }
+ cycles *= cprd;
+ do_div(cycles, state->period);
+ *cdty = cprd - cycles;
}
-static int atmel_pwm_set_polarity(struct pwm_chip *chip, struct pwm_device *pwm,
- enum pwm_polarity polarity)
+static void atmel_pwm_update_cdty(struct pwm_chip *chip, struct pwm_device *pwm,
+ unsigned long cdty)
{
struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
u32 val;
- int ret;
-
- val = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
- if (polarity == PWM_POLARITY_NORMAL)
- val &= ~PWM_CMR_CPOL;
- else
- val |= PWM_CMR_CPOL;
-
- ret = clk_enable(atmel_pwm->clk);
- if (ret) {
- dev_err(chip->dev, "failed to enable PWM clock\n");
- return ret;
+ if (atmel_pwm->regs->duty_upd ==
+ atmel_pwm->regs->period_upd) {
+ val = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
+ val &= ~PWM_CMR_UPD_CDTY;
+ atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
}
- atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
-
- clk_disable(atmel_pwm->clk);
-
- return 0;
+ atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm,
+ atmel_pwm->regs->duty_upd, cdty);
}
-static int atmel_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
+static void atmel_pwm_set_cprd_cdty(struct pwm_chip *chip,
+ struct pwm_device *pwm,
+ unsigned long cprd, unsigned long cdty)
{
struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
- int ret;
-
- ret = clk_enable(atmel_pwm->clk);
- if (ret) {
- dev_err(chip->dev, "failed to enable PWM clock\n");
- return ret;
- }
- atmel_pwm_writel(atmel_pwm, PWM_ENA, 1 << pwm->hwpwm);
-
- return 0;
+ atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm,
+ atmel_pwm->regs->duty, cdty);
+ atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm,
+ atmel_pwm->regs->period, cprd);
}
-static void atmel_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
+static void atmel_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm,
+ bool disable_clk)
{
struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
unsigned long timeout = jiffies + 2 * HZ;
time_before(jiffies, timeout))
usleep_range(10, 100);
- clk_disable(atmel_pwm->clk);
+ if (disable_clk)
+ clk_disable(atmel_pwm->clk);
+}
+
+static int atmel_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+ struct pwm_state *state)
+{
+ struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
+ struct pwm_state cstate;
+ unsigned long cprd, cdty;
+ u32 pres, val;
+ int ret;
+
+ pwm_get_state(pwm, &cstate);
+
+ if (state->enabled) {
+ if (cstate.enabled &&
+ cstate.polarity == state->polarity &&
+ cstate.period == state->period) {
+ cprd = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm,
+ atmel_pwm->regs->period);
+ atmel_pwm_calculate_cdty(state, cprd, &cdty);
+ atmel_pwm_update_cdty(chip, pwm, cdty);
+ return 0;
+ }
+
+ ret = atmel_pwm_calculate_cprd_and_pres(chip, state, &cprd,
+ &pres);
+ if (ret) {
+ dev_err(chip->dev,
+ "failed to calculate cprd and prescaler\n");
+ return ret;
+ }
+
+ atmel_pwm_calculate_cdty(state, cprd, &cdty);
+
+ if (cstate.enabled) {
+ atmel_pwm_disable(chip, pwm, false);
+ } else {
+ ret = clk_enable(atmel_pwm->clk);
+ if (ret) {
+ dev_err(chip->dev, "failed to enable clock\n");
+ return ret;
+ }
+ }
+
+ /* It is necessary to preserve CPOL, inside CMR */
+ val = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm, PWM_CMR);
+ val = (val & ~PWM_CMR_CPRE_MSK) | (pres & PWM_CMR_CPRE_MSK);
+ if (state->polarity == PWM_POLARITY_NORMAL)
+ val &= ~PWM_CMR_CPOL;
+ else
+ val |= PWM_CMR_CPOL;
+ atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
+ atmel_pwm_set_cprd_cdty(chip, pwm, cprd, cdty);
+ mutex_lock(&atmel_pwm->isr_lock);
+ atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
+ atmel_pwm->updated_pwms &= ~(1 << pwm->hwpwm);
+ mutex_unlock(&atmel_pwm->isr_lock);
+ atmel_pwm_writel(atmel_pwm, PWM_ENA, 1 << pwm->hwpwm);
+ } else if (cstate.enabled) {
+ atmel_pwm_disable(chip, pwm, true);
+ }
+
+ return 0;
}
static const struct pwm_ops atmel_pwm_ops = {
- .config = atmel_pwm_config,
- .set_polarity = atmel_pwm_set_polarity,
- .enable = atmel_pwm_enable,
- .disable = atmel_pwm_disable,
+ .apply = atmel_pwm_apply,
.owner = THIS_MODULE,
};
-struct atmel_pwm_data {
- void (*config)(struct pwm_chip *chip, struct pwm_device *pwm,
- unsigned long dty, unsigned long prd);
+static const struct atmel_pwm_registers atmel_pwm_regs_v1 = {
+ .period = PWMV1_CPRD,
+ .period_upd = PWMV1_CUPD,
+ .duty = PWMV1_CDTY,
+ .duty_upd = PWMV1_CUPD,
};
-static const struct atmel_pwm_data atmel_pwm_data_v1 = {
- .config = atmel_pwm_config_v1,
-};
-
-static const struct atmel_pwm_data atmel_pwm_data_v2 = {
- .config = atmel_pwm_config_v2,
+static const struct atmel_pwm_registers atmel_pwm_regs_v2 = {
+ .period = PWMV2_CPRD,
+ .period_upd = PWMV2_CPRDUPD,
+ .duty = PWMV2_CDTY,
+ .duty_upd = PWMV2_CDTYUPD,
};
static const struct platform_device_id atmel_pwm_devtypes[] = {
{
.name = "at91sam9rl-pwm",
- .driver_data = (kernel_ulong_t)&atmel_pwm_data_v1,
+ .driver_data = (kernel_ulong_t)&atmel_pwm_regs_v1,
}, {
.name = "sama5d3-pwm",
- .driver_data = (kernel_ulong_t)&atmel_pwm_data_v2,
+ .driver_data = (kernel_ulong_t)&atmel_pwm_regs_v2,
}, {
/* sentinel */
},
static const struct of_device_id atmel_pwm_dt_ids[] = {
{
.compatible = "atmel,at91sam9rl-pwm",
- .data = &atmel_pwm_data_v1,
+ .data = &atmel_pwm_regs_v1,
}, {
.compatible = "atmel,sama5d3-pwm",
- .data = &atmel_pwm_data_v2,
+ .data = &atmel_pwm_regs_v2,
+ }, {
+ .compatible = "atmel,sama5d2-pwm",
+ .data = &atmel_pwm_regs_v2,
}, {
/* sentinel */
},
};
MODULE_DEVICE_TABLE(of, atmel_pwm_dt_ids);
-static inline const struct atmel_pwm_data *
+static inline const struct atmel_pwm_registers *
atmel_pwm_get_driver_data(struct platform_device *pdev)
{
const struct platform_device_id *id;
id = platform_get_device_id(pdev);
- return (struct atmel_pwm_data *)id->driver_data;
+ return (struct atmel_pwm_registers *)id->driver_data;
}
static int atmel_pwm_probe(struct platform_device *pdev)
{
- const struct atmel_pwm_data *data;
+ const struct atmel_pwm_registers *regs;
struct atmel_pwm_chip *atmel_pwm;
struct resource *res;
int ret;
- data = atmel_pwm_get_driver_data(pdev);
- if (!data)
+ regs = atmel_pwm_get_driver_data(pdev);
+ if (!regs)
return -ENODEV;
atmel_pwm = devm_kzalloc(&pdev->dev, sizeof(*atmel_pwm), GFP_KERNEL);
atmel_pwm->chip.base = -1;
atmel_pwm->chip.npwm = 4;
- atmel_pwm->config = data->config;
+ atmel_pwm->regs = regs;
atmel_pwm->updated_pwms = 0;
mutex_init(&atmel_pwm->isr_lock);
--- /dev/null
+/*
+ * Mediatek Pulse Width Modulator driver
+ *
+ * Copyright (C) 2015 John Crispin <blogic@openwrt.org>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pwm.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+/* PWM registers and bits definitions */
+#define PWMCON 0x00
+#define PWMHDUR 0x04
+#define PWMLDUR 0x08
+#define PWMGDUR 0x0c
+#define PWMWAVENUM 0x28
+#define PWMDWIDTH 0x2c
+#define PWMTHRES 0x30
+
+enum {
+ MTK_CLK_MAIN = 0,
+ MTK_CLK_TOP,
+ MTK_CLK_PWM1,
+ MTK_CLK_PWM2,
+ MTK_CLK_PWM3,
+ MTK_CLK_PWM4,
+ MTK_CLK_PWM5,
+ MTK_CLK_MAX,
+};
+
+static const char * const mtk_pwm_clk_name[] = {
+ "main", "top", "pwm1", "pwm2", "pwm3", "pwm4", "pwm5"
+};
+
+/**
+ * struct mtk_pwm_chip - struct representing PWM chip
+ * @chip: linux PWM chip representation
+ * @regs: base address of PWM chip
+ * @clks: list of clocks
+ */
+struct mtk_pwm_chip {
+ struct pwm_chip chip;
+ void __iomem *regs;
+ struct clk *clks[MTK_CLK_MAX];
+};
+
+static inline struct mtk_pwm_chip *to_mtk_pwm_chip(struct pwm_chip *chip)
+{
+ return container_of(chip, struct mtk_pwm_chip, chip);
+}
+
+static inline u32 mtk_pwm_readl(struct mtk_pwm_chip *chip, unsigned int num,
+ unsigned int offset)
+{
+ return readl(chip->regs + 0x10 + (num * 0x40) + offset);
+}
+
+static inline void mtk_pwm_writel(struct mtk_pwm_chip *chip,
+ unsigned int num, unsigned int offset,
+ u32 value)
+{
+ writel(value, chip->regs + 0x10 + (num * 0x40) + offset);
+}
+
+static int mtk_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
+ int duty_ns, int period_ns)
+{
+ struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip);
+ struct clk *clk = pc->clks[MTK_CLK_PWM1 + pwm->hwpwm];
+ u32 resolution, clkdiv = 0;
+
+ resolution = NSEC_PER_SEC / clk_get_rate(clk);
+
+ while (period_ns / resolution > 8191) {
+ resolution *= 2;
+ clkdiv++;
+ }
+
+ if (clkdiv > 7)
+ return -EINVAL;
+
+ mtk_pwm_writel(pc, pwm->hwpwm, PWMCON, BIT(15) | BIT(3) | clkdiv);
+ mtk_pwm_writel(pc, pwm->hwpwm, PWMDWIDTH, period_ns / resolution);
+ mtk_pwm_writel(pc, pwm->hwpwm, PWMTHRES, duty_ns / resolution);
+
+ return 0;
+}
+
+static int mtk_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
+{
+ struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip);
+ u32 value;
+ int ret;
+
+ ret = clk_prepare(pc->clks[MTK_CLK_PWM1 + pwm->hwpwm]);
+ if (ret < 0)
+ return ret;
+
+ value = readl(pc->regs);
+ value |= BIT(pwm->hwpwm);
+ writel(value, pc->regs);
+
+ return 0;
+}
+
+static void mtk_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
+{
+ struct mtk_pwm_chip *pc = to_mtk_pwm_chip(chip);
+ u32 value;
+
+ value = readl(pc->regs);
+ value &= ~BIT(pwm->hwpwm);
+ writel(value, pc->regs);
+
+ clk_unprepare(pc->clks[MTK_CLK_PWM1 + pwm->hwpwm]);
+}
+
+static const struct pwm_ops mtk_pwm_ops = {
+ .config = mtk_pwm_config,
+ .enable = mtk_pwm_enable,
+ .disable = mtk_pwm_disable,
+ .owner = THIS_MODULE,
+};
+
+static int mtk_pwm_probe(struct platform_device *pdev)
+{
+ struct mtk_pwm_chip *pc;
+ struct resource *res;
+ unsigned int i;
+ int ret;
+
+ pc = devm_kzalloc(&pdev->dev, sizeof(*pc), GFP_KERNEL);
+ if (!pc)
+ return -ENOMEM;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ pc->regs = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(pc->regs))
+ return PTR_ERR(pc->regs);
+
+ for (i = 0; i < MTK_CLK_MAX; i++) {
+ pc->clks[i] = devm_clk_get(&pdev->dev, mtk_pwm_clk_name[i]);
+ if (IS_ERR(pc->clks[i]))
+ return PTR_ERR(pc->clks[i]);
+ }
+
+ ret = clk_prepare(pc->clks[MTK_CLK_TOP]);
+ if (ret < 0)
+ return ret;
+
+ ret = clk_prepare(pc->clks[MTK_CLK_MAIN]);
+ if (ret < 0)
+ goto disable_clk_top;
+
+ platform_set_drvdata(pdev, pc);
+
+ pc->chip.dev = &pdev->dev;
+ pc->chip.ops = &mtk_pwm_ops;
+ pc->chip.base = -1;
+ pc->chip.npwm = 5;
+
+ ret = pwmchip_add(&pc->chip);
+ if (ret < 0) {
+ dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret);
+ goto disable_clk_main;
+ }
+
+ return 0;
+
+disable_clk_main:
+ clk_unprepare(pc->clks[MTK_CLK_MAIN]);
+disable_clk_top:
+ clk_unprepare(pc->clks[MTK_CLK_TOP]);
+
+ return ret;
+}
+
+static int mtk_pwm_remove(struct platform_device *pdev)
+{
+ struct mtk_pwm_chip *pc = platform_get_drvdata(pdev);
+ unsigned int i;
+
+ for (i = 0; i < pc->chip.npwm; i++)
+ pwm_disable(&pc->chip.pwms[i]);
+
+ return pwmchip_remove(&pc->chip);
+}
+
+static const struct of_device_id mtk_pwm_of_match[] = {
+ { .compatible = "mediatek,mt7623-pwm" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, mtk_pwm_of_match);
+
+static struct platform_driver mtk_pwm_driver = {
+ .driver = {
+ .name = "mtk-pwm",
+ .of_match_table = mtk_pwm_of_match,
+ },
+ .probe = mtk_pwm_probe,
+ .remove = mtk_pwm_remove,
+};
+module_platform_driver(mtk_pwm_driver);
+
+MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
+MODULE_ALIAS("platform:mtk-pwm");
+MODULE_LICENSE("GPL");
#include <linux/regmap.h>
#include <linux/slab.h>
#include <linux/delay.h>
+#include <linux/pm_runtime.h>
/*
* Because the PCA9685 has only one prescaler per chip, changing the period of
struct pca9685 {
struct pwm_chip chip;
struct regmap *regmap;
- int active_cnt;
int duty_ns;
int period_ns;
#if IS_ENABLED(CONFIG_GPIOLIB)
pwm_set_chip_data(pwm, (void *)1);
mutex_unlock(&pca->lock);
+ pm_runtime_get_sync(pca->chip.dev);
return 0;
}
-static void pca9685_pwm_gpio_free(struct gpio_chip *gpio, unsigned int offset)
-{
- struct pca9685 *pca = gpiochip_get_data(gpio);
- struct pwm_device *pwm;
-
- mutex_lock(&pca->lock);
- pwm = &pca->chip.pwms[offset];
- pwm_set_chip_data(pwm, NULL);
- mutex_unlock(&pca->lock);
-}
-
static bool pca9685_pwm_is_gpio(struct pca9685 *pca, struct pwm_device *pwm)
{
bool is_gpio = false;
regmap_write(pca->regmap, LED_N_ON_H(pwm->hwpwm), on);
}
+static void pca9685_pwm_gpio_free(struct gpio_chip *gpio, unsigned int offset)
+{
+ struct pca9685 *pca = gpiochip_get_data(gpio);
+ struct pwm_device *pwm;
+
+ pca9685_pwm_gpio_set(gpio, offset, 0);
+ pm_runtime_put(pca->chip.dev);
+ mutex_lock(&pca->lock);
+ pwm = &pca->chip.pwms[offset];
+ pwm_set_chip_data(pwm, NULL);
+ mutex_unlock(&pca->lock);
+}
+
static int pca9685_pwm_gpio_get_direction(struct gpio_chip *chip,
unsigned int offset)
{
}
#endif
+static void pca9685_set_sleep_mode(struct pca9685 *pca, int sleep)
+{
+ regmap_update_bits(pca->regmap, PCA9685_MODE1,
+ MODE1_SLEEP, sleep ? MODE1_SLEEP : 0);
+ if (!sleep) {
+ /* Wait 500us for the oscillator to be back up */
+ udelay(500);
+ }
+}
+
static int pca9685_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
int duty_ns, int period_ns)
{
if (prescale >= PCA9685_PRESCALE_MIN &&
prescale <= PCA9685_PRESCALE_MAX) {
+ /*
+ * putting the chip briefly into SLEEP mode
+ * at this point won't interfere with the
+ * pm_runtime framework, because the pm_runtime
+ * state is guaranteed active here.
+ */
/* Put chip into sleep mode */
- regmap_update_bits(pca->regmap, PCA9685_MODE1,
- MODE1_SLEEP, MODE1_SLEEP);
+ pca9685_set_sleep_mode(pca, 1);
/* Change the chip-wide output frequency */
regmap_write(pca->regmap, PCA9685_PRESCALE, prescale);
/* Wake the chip up */
- regmap_update_bits(pca->regmap, PCA9685_MODE1,
- MODE1_SLEEP, 0x0);
-
- /* Wait 500us for the oscillator to be back up */
- udelay(500);
+ pca9685_set_sleep_mode(pca, 0);
pca->period_ns = period_ns;
} else {
if (pca9685_pwm_is_gpio(pca, pwm))
return -EBUSY;
-
- if (pca->active_cnt++ == 0)
- return regmap_update_bits(pca->regmap, PCA9685_MODE1,
- MODE1_SLEEP, 0x0);
+ pm_runtime_get_sync(chip->dev);
return 0;
}
static void pca9685_pwm_free(struct pwm_chip *chip, struct pwm_device *pwm)
{
- struct pca9685 *pca = to_pca(chip);
-
- if (--pca->active_cnt == 0)
- regmap_update_bits(pca->regmap, PCA9685_MODE1, MODE1_SLEEP,
- MODE1_SLEEP);
+ pca9685_pwm_disable(chip, pwm);
+ pm_runtime_put(chip->dev);
}
static const struct pwm_ops pca9685_pwm_ops = {
return ret;
ret = pca9685_pwm_gpio_probe(pca);
- if (ret < 0)
+ if (ret < 0) {
pwmchip_remove(&pca->chip);
+ return ret;
+ }
+
+ /* the chip comes out of power-up in the active state */
+ pm_runtime_set_active(&client->dev);
+ /*
+ * enable will put the chip into suspend, which is what we
+ * want as all outputs are disabled at this point
+ */
+ pm_runtime_enable(&client->dev);
- return ret;
+ return 0;
}
static int pca9685_pwm_remove(struct i2c_client *client)
{
struct pca9685 *pca = i2c_get_clientdata(client);
+ int ret;
- regmap_update_bits(pca->regmap, PCA9685_MODE1, MODE1_SLEEP,
- MODE1_SLEEP);
+ ret = pwmchip_remove(&pca->chip);
+ if (ret)
+ return ret;
+ pm_runtime_disable(&client->dev);
+ return 0;
+}
- return pwmchip_remove(&pca->chip);
+#ifdef CONFIG_PM
+static int pca9685_pwm_runtime_suspend(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct pca9685 *pca = i2c_get_clientdata(client);
+
+ pca9685_set_sleep_mode(pca, 1);
+ return 0;
}
+static int pca9685_pwm_runtime_resume(struct device *dev)
+{
+ struct i2c_client *client = to_i2c_client(dev);
+ struct pca9685 *pca = i2c_get_clientdata(client);
+
+ pca9685_set_sleep_mode(pca, 0);
+ return 0;
+}
+#endif
+
static const struct i2c_device_id pca9685_id[] = {
{ "pca9685", 0 },
{ /* sentinel */ },
MODULE_DEVICE_TABLE(of, pca9685_dt_ids);
#endif
+static const struct dev_pm_ops pca9685_pwm_pm = {
+ SET_RUNTIME_PM_OPS(pca9685_pwm_runtime_suspend,
+ pca9685_pwm_runtime_resume, NULL)
+};
+
static struct i2c_driver pca9685_i2c_driver = {
.driver = {
.name = "pca9685-pwm",
.acpi_match_table = ACPI_PTR(pca9685_acpi_ids),
.of_match_table = of_match_ptr(pca9685_dt_ids),
+ .pm = &pca9685_pwm_pm,
},
.probe = pca9685_pwm_probe,
.remove = pca9685_pwm_remove,
#include <linux/of_device.h>
#include <linux/pwm.h>
#include <linux/platform_device.h>
+#include <linux/pinctrl/consumer.h>
#include <linux/slab.h>
#include <linux/reset.h>
struct clk *clk;
struct reset_control*rst;
+ unsigned long clk_rate;
+
void __iomem *regs;
const struct tegra_pwm_soc *soc;
int duty_ns, int period_ns)
{
struct tegra_pwm_chip *pc = to_tegra_pwm_chip(chip);
- unsigned long long c = duty_ns;
- unsigned long rate, hz;
+ unsigned long long c = duty_ns, hz;
+ unsigned long rate;
u32 val = 0;
int err;
* nearest integer during division.
*/
c *= (1 << PWM_DUTY_WIDTH);
- c += period_ns / 2;
- do_div(c, period_ns);
+ c = DIV_ROUND_CLOSEST_ULL(c, period_ns);
val = (u32)c << PWM_DUTY_SHIFT;
* Compute the prescaler value for which (1 << PWM_DUTY_WIDTH)
* cycles at the PWM clock rate will take period_ns nanoseconds.
*/
- rate = clk_get_rate(pc->clk) >> PWM_DUTY_WIDTH;
- hz = NSEC_PER_SEC / period_ns;
+ rate = pc->clk_rate >> PWM_DUTY_WIDTH;
- rate = (rate + (hz / 2)) / hz;
+ /* Consider precision in PWM_SCALE_WIDTH rate calculation */
+ hz = DIV_ROUND_CLOSEST_ULL(100ULL * NSEC_PER_SEC, period_ns);
+ rate = DIV_ROUND_CLOSEST_ULL(100ULL * rate, hz);
/*
* Since the actual PWM divider is the register's frequency divider
if (IS_ERR(pwm->clk))
return PTR_ERR(pwm->clk);
+ /* Read PWM clock rate from source */
+ pwm->clk_rate = clk_get_rate(pwm->clk);
+
pwm->rst = devm_reset_control_get(&pdev->dev, "pwm");
if (IS_ERR(pwm->rst)) {
ret = PTR_ERR(pwm->rst);
return pwmchip_remove(&pc->chip);
}
+#ifdef CONFIG_PM_SLEEP
+static int tegra_pwm_suspend(struct device *dev)
+{
+ return pinctrl_pm_select_sleep_state(dev);
+}
+
+static int tegra_pwm_resume(struct device *dev)
+{
+ return pinctrl_pm_select_default_state(dev);
+}
+#endif
+
static const struct tegra_pwm_soc tegra20_pwm_soc = {
.num_channels = 4,
};
MODULE_DEVICE_TABLE(of, tegra_pwm_of_match);
+static const struct dev_pm_ops tegra_pwm_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(tegra_pwm_suspend, tegra_pwm_resume)
+};
+
static struct platform_driver tegra_pwm_driver = {
.driver = {
.name = "tegra-pwm",
.of_match_table = tegra_pwm_of_match,
+ .pm = &tegra_pwm_pm_ops,
},
.probe = tegra_pwm_probe,
.remove = tegra_pwm_remove,
static struct virtqueue *rp_find_vq(struct virtio_device *vdev,
unsigned int id,
void (*callback)(struct virtqueue *vq),
- const char *name)
+ const char *name, bool ctx)
{
struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
struct rproc *rproc = vdev_to_rproc(vdev);
* Create the new vq, and tell virtio we're not interested in
* the 'weak' smp barriers, since we're talking with a real device.
*/
- vq = vring_new_virtqueue(id, len, rvring->align, vdev, false, addr,
- rproc_virtio_notify, callback, name);
+ vq = vring_new_virtqueue(id, len, rvring->align, vdev, false, ctx,
+ addr, rproc_virtio_notify, callback, name);
if (!vq) {
dev_err(dev, "vring_new_virtqueue %s failed\n", name);
rproc_free_vring(rvring);
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
const char * const names[],
+ const bool * ctx,
struct irq_affinity *desc)
{
int i, ret;
for (i = 0; i < nvqs; ++i) {
- vqs[i] = rp_find_vq(vdev, i, callbacks[i], names[i]);
+ vqs[i] = rp_find_vq(vdev, i, callbacks[i], names[i],
+ ctx ? ctx[i] : false);
if (IS_ERR(vqs[i])) {
ret = PTR_ERR(vqs[i]);
goto error;
init_waitqueue_head(&vrp->sendq);
/* We expect two virtqueues, rx and tx (and in this order) */
- err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names, NULL);
+ err = virtio_find_vqs(vdev, 2, vqs, vq_cbs, names, NULL);
if (err)
goto free_vrp;
config RTC_DRV_SH
tristate "SuperH On-Chip RTC"
- depends on SUPERH && HAVE_CLK
+ depends on SUPERH || ARCH_RENESAS
help
Say Y here to enable support for the on-chip RTC found in
- most SuperH processors.
+ most SuperH processors. This RTC is also found in RZ/A SoCs.
To compile this driver as a module, choose M here: the
module will be called rtc-sh.
This driver can also be built as a module, if so, the module
will be called "rtc-stm32".
+config RTC_DRV_CPCAP
+ depends on MFD_CPCAP
+ tristate "Motorola CPCAP RTC"
+ help
+ Say y here for CPCAP rtc found on some Motorola phones
+ and tablets such as Droid 4.
+
comment "HID Sensor RTC drivers"
config RTC_DRV_HID_SENSOR_TIME
obj-$(CONFIG_RTC_DRV_BQ4802) += rtc-bq4802.o
obj-$(CONFIG_RTC_DRV_CMOS) += rtc-cmos.o
obj-$(CONFIG_RTC_DRV_COH901331) += rtc-coh901331.o
+obj-$(CONFIG_RTC_DRV_CPCAP) += rtc-cpcap.o
obj-$(CONFIG_RTC_DRV_DA9052) += rtc-da9052.o
obj-$(CONFIG_RTC_DRV_DA9055) += rtc-da9055.o
obj-$(CONFIG_RTC_DRV_DA9063) += rtc-da9063.o
};
MODULE_DEVICE_TABLE(i2c, bq32k_id);
+static const struct of_device_id bq32k_of_match[] = {
+ { .compatible = "ti,bq32000" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, bq32k_of_match);
+
static struct i2c_driver bq32k_driver = {
.driver = {
.name = "bq32k",
+ .of_match_table = of_match_ptr(bq32k_of_match),
},
.probe = bq32k_probe,
.remove = bq32k_remove,
#include <linux/pm.h>
#include <linux/of.h>
#include <linux/of_platform.h>
+#ifdef CONFIG_X86
+#include <asm/i8259.h>
+#endif
/* this is for "generic access to PC-style RTC" using CMOS_READ/CMOS_WRITE */
#include <linux/mc146818rtc.h>
{
cmos_wake_setup(&pnp->dev);
- if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0))
+ if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) {
+ unsigned int irq = 0;
+#ifdef CONFIG_X86
/* Some machines contain a PNP entry for the RTC, but
* don't define the IRQ. It should always be safe to
- * hardcode it in these cases
+ * hardcode it on systems with a legacy PIC.
*/
+ if (nr_legacy_irqs())
+ irq = 8;
+#endif
return cmos_do_probe(&pnp->dev,
- pnp_get_resource(pnp, IORESOURCE_IO, 0), 8);
- else
+ pnp_get_resource(pnp, IORESOURCE_IO, 0), irq);
+ } else {
return cmos_do_probe(&pnp->dev,
pnp_get_resource(pnp, IORESOURCE_IO, 0),
pnp_irq(pnp, 0));
+ }
}
static void cmos_pnp_remove(struct pnp_dev *pnp)
--- /dev/null
+/*
+ * Motorola CPCAP PMIC RTC driver
+ *
+ * Based on cpcap-regulator.c from Motorola Linux kernel tree
+ * Copyright (C) 2009 Motorola, Inc.
+ *
+ * Rewritten for mainline kernel
+ * - use DT
+ * - use regmap
+ * - use standard interrupt framework
+ * - use managed device resources
+ * - remove custom "secure clock daemon" helpers
+ *
+ * Copyright (C) 2017 Sebastian Reichel <sre@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+#include <linux/err.h>
+#include <linux/regmap.h>
+#include <linux/mfd/motorola-cpcap.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+
+#define SECS_PER_DAY 86400
+#define DAY_MASK 0x7FFF
+#define TOD1_MASK 0x00FF
+#define TOD2_MASK 0x01FF
+
+struct cpcap_time {
+ int day;
+ int tod1;
+ int tod2;
+};
+
+struct cpcap_rtc {
+ struct regmap *regmap;
+ struct rtc_device *rtc_dev;
+ u16 vendor;
+ int alarm_irq;
+ bool alarm_enabled;
+ int update_irq;
+ bool update_enabled;
+};
+
+static void cpcap2rtc_time(struct rtc_time *rtc, struct cpcap_time *cpcap)
+{
+ unsigned long int tod;
+ unsigned long int time;
+
+ tod = (cpcap->tod1 & TOD1_MASK) | ((cpcap->tod2 & TOD2_MASK) << 8);
+ time = tod + ((cpcap->day & DAY_MASK) * SECS_PER_DAY);
+
+ rtc_time_to_tm(time, rtc);
+}
+
+static void rtc2cpcap_time(struct cpcap_time *cpcap, struct rtc_time *rtc)
+{
+ unsigned long time;
+
+ rtc_tm_to_time(rtc, &time);
+
+ cpcap->day = time / SECS_PER_DAY;
+ time %= SECS_PER_DAY;
+ cpcap->tod2 = (time >> 8) & TOD2_MASK;
+ cpcap->tod1 = time & TOD1_MASK;
+}
+
+static int cpcap_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
+{
+ struct cpcap_rtc *rtc = dev_get_drvdata(dev);
+
+ if (rtc->alarm_enabled == enabled)
+ return 0;
+
+ if (enabled)
+ enable_irq(rtc->alarm_irq);
+ else
+ disable_irq(rtc->alarm_irq);
+
+ rtc->alarm_enabled = !!enabled;
+
+ return 0;
+}
+
+static int cpcap_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+ struct cpcap_rtc *rtc;
+ struct cpcap_time cpcap_tm;
+ int temp_tod2;
+ int ret;
+
+ rtc = dev_get_drvdata(dev);
+
+ ret = regmap_read(rtc->regmap, CPCAP_REG_TOD2, &temp_tod2);
+ ret |= regmap_read(rtc->regmap, CPCAP_REG_DAY, &cpcap_tm.day);
+ ret |= regmap_read(rtc->regmap, CPCAP_REG_TOD1, &cpcap_tm.tod1);
+ ret |= regmap_read(rtc->regmap, CPCAP_REG_TOD2, &cpcap_tm.tod2);
+
+ if (temp_tod2 > cpcap_tm.tod2)
+ ret |= regmap_read(rtc->regmap, CPCAP_REG_DAY, &cpcap_tm.day);
+
+ if (ret) {
+ dev_err(dev, "Failed to read time\n");
+ return -EIO;
+ }
+
+ cpcap2rtc_time(tm, &cpcap_tm);
+
+ return rtc_valid_tm(tm);
+}
+
+static int cpcap_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+ struct cpcap_rtc *rtc;
+ struct cpcap_time cpcap_tm;
+ int ret = 0;
+
+ rtc = dev_get_drvdata(dev);
+
+ rtc2cpcap_time(&cpcap_tm, tm);
+
+ if (rtc->alarm_enabled)
+ disable_irq(rtc->alarm_irq);
+ if (rtc->update_enabled)
+ disable_irq(rtc->update_irq);
+
+ if (rtc->vendor == CPCAP_VENDOR_ST) {
+ /* The TOD1 and TOD2 registers MUST be written in this order
+ * for the change to properly set.
+ */
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_TOD1,
+ TOD1_MASK, cpcap_tm.tod1);
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_TOD2,
+ TOD2_MASK, cpcap_tm.tod2);
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_DAY,
+ DAY_MASK, cpcap_tm.day);
+ } else {
+ /* Clearing the upper lower 8 bits of the TOD guarantees that
+ * the upper half of TOD (TOD2) will not increment for 0xFF RTC
+ * ticks (255 seconds). During this time we can safely write
+ * to DAY, TOD2, then TOD1 (in that order) and expect RTC to be
+ * synchronized to the exact time requested upon the final write
+ * to TOD1.
+ */
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_TOD1,
+ TOD1_MASK, 0);
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_DAY,
+ DAY_MASK, cpcap_tm.day);
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_TOD2,
+ TOD2_MASK, cpcap_tm.tod2);
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_TOD1,
+ TOD1_MASK, cpcap_tm.tod1);
+ }
+
+ if (rtc->update_enabled)
+ enable_irq(rtc->update_irq);
+ if (rtc->alarm_enabled)
+ enable_irq(rtc->alarm_irq);
+
+ return ret;
+}
+
+static int cpcap_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+ struct cpcap_rtc *rtc;
+ struct cpcap_time cpcap_tm;
+ int ret;
+
+ rtc = dev_get_drvdata(dev);
+
+ alrm->enabled = rtc->alarm_enabled;
+
+ ret = regmap_read(rtc->regmap, CPCAP_REG_DAYA, &cpcap_tm.day);
+ ret |= regmap_read(rtc->regmap, CPCAP_REG_TODA2, &cpcap_tm.tod2);
+ ret |= regmap_read(rtc->regmap, CPCAP_REG_TODA1, &cpcap_tm.tod1);
+
+ if (ret) {
+ dev_err(dev, "Failed to read time\n");
+ return -EIO;
+ }
+
+ cpcap2rtc_time(&alrm->time, &cpcap_tm);
+ return rtc_valid_tm(&alrm->time);
+}
+
+static int cpcap_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+ struct cpcap_rtc *rtc;
+ struct cpcap_time cpcap_tm;
+ int ret;
+
+ rtc = dev_get_drvdata(dev);
+
+ rtc2cpcap_time(&cpcap_tm, &alrm->time);
+
+ if (rtc->alarm_enabled)
+ disable_irq(rtc->alarm_irq);
+
+ ret = regmap_update_bits(rtc->regmap, CPCAP_REG_DAYA, DAY_MASK,
+ cpcap_tm.day);
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_TODA2, TOD2_MASK,
+ cpcap_tm.tod2);
+ ret |= regmap_update_bits(rtc->regmap, CPCAP_REG_TODA1, TOD1_MASK,
+ cpcap_tm.tod1);
+
+ if (!ret) {
+ enable_irq(rtc->alarm_irq);
+ rtc->alarm_enabled = true;
+ }
+
+ return ret;
+}
+
+static const struct rtc_class_ops cpcap_rtc_ops = {
+ .read_time = cpcap_rtc_read_time,
+ .set_time = cpcap_rtc_set_time,
+ .read_alarm = cpcap_rtc_read_alarm,
+ .set_alarm = cpcap_rtc_set_alarm,
+ .alarm_irq_enable = cpcap_rtc_alarm_irq_enable,
+};
+
+static irqreturn_t cpcap_rtc_alarm_irq(int irq, void *data)
+{
+ struct cpcap_rtc *rtc = data;
+
+ rtc_update_irq(rtc->rtc_dev, 1, RTC_AF | RTC_IRQF);
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t cpcap_rtc_update_irq(int irq, void *data)
+{
+ struct cpcap_rtc *rtc = data;
+
+ rtc_update_irq(rtc->rtc_dev, 1, RTC_UF | RTC_IRQF);
+ return IRQ_HANDLED;
+}
+
+static int cpcap_rtc_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct cpcap_rtc *rtc;
+ int err;
+
+ rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL);
+ if (!rtc)
+ return -ENOMEM;
+
+ rtc->regmap = dev_get_regmap(dev->parent, NULL);
+ if (!rtc->regmap)
+ return -ENODEV;
+
+ platform_set_drvdata(pdev, rtc);
+ rtc->rtc_dev = devm_rtc_device_register(dev, "cpcap_rtc",
+ &cpcap_rtc_ops, THIS_MODULE);
+
+ if (IS_ERR(rtc->rtc_dev))
+ return PTR_ERR(rtc->rtc_dev);
+
+ err = cpcap_get_vendor(dev, rtc->regmap, &rtc->vendor);
+ if (err)
+ return err;
+
+ rtc->alarm_irq = platform_get_irq(pdev, 0);
+ err = devm_request_threaded_irq(dev, rtc->alarm_irq, NULL,
+ cpcap_rtc_alarm_irq, IRQF_TRIGGER_NONE,
+ "rtc_alarm", rtc);
+ if (err) {
+ dev_err(dev, "Could not request alarm irq: %d\n", err);
+ return err;
+ }
+ disable_irq(rtc->alarm_irq);
+
+ /* Stock Android uses the 1 Hz interrupt for "secure clock daemon",
+ * which is not supported by the mainline kernel. The mainline kernel
+ * does not use the irq at the moment, but we explicitly request and
+ * disable it, so that its masked and does not wake up the processor
+ * every second.
+ */
+ rtc->update_irq = platform_get_irq(pdev, 1);
+ err = devm_request_threaded_irq(dev, rtc->update_irq, NULL,
+ cpcap_rtc_update_irq, IRQF_TRIGGER_NONE,
+ "rtc_1hz", rtc);
+ if (err) {
+ dev_err(dev, "Could not request update irq: %d\n", err);
+ return err;
+ }
+ disable_irq(rtc->update_irq);
+
+ err = device_init_wakeup(dev, 1);
+ if (err) {
+ dev_err(dev, "wakeup initialization failed (%d)\n", err);
+ /* ignore error and continue without wakeup support */
+ }
+
+ return 0;
+}
+
+static const struct of_device_id cpcap_rtc_of_match[] = {
+ { .compatible = "motorola,cpcap-rtc", },
+ {},
+};
+MODULE_DEVICE_TABLE(of, cpcap_rtc_of_match);
+
+static struct platform_driver cpcap_rtc_driver = {
+ .probe = cpcap_rtc_probe,
+ .driver = {
+ .name = "cpcap-rtc",
+ .of_match_table = cpcap_rtc_of_match,
+ },
+};
+
+module_platform_driver(cpcap_rtc_driver);
+
+MODULE_ALIAS("platform:cpcap-rtc");
+MODULE_DESCRIPTION("CPCAP RTC driver");
+MODULE_AUTHOR("Sebastian Reichel <sre@kernel.org>");
+MODULE_LICENSE("GPL");
#include <linux/i2c.h>
#include <linux/init.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/rtc/ds1307.h>
#include <linux/rtc.h>
#include <linux/slab.h>
ds_1340,
ds_1388,
ds_3231,
+ m41t0,
m41t00,
mcp794xx,
rx_8025,
# define DS1340_BIT_nEOSC 0x80
# define MCP794XX_BIT_ST 0x80
#define DS1307_REG_MIN 0x01 /* 00-59 */
+# define M41T0_BIT_OF 0x80
#define DS1307_REG_HOUR 0x02 /* 00-23, or 1-12{am,pm} */
# define DS1307_BIT_12HR 0x40 /* in REG_HOUR */
# define DS1307_BIT_PM 0x20 /* in REG_HOUR */
{ "ds1388", ds_1388 },
{ "ds1340", ds_1340 },
{ "ds3231", ds_3231 },
+ { "m41t0", m41t0 },
{ "m41t00", m41t00 },
{ "mcp7940x", mcp794xx },
{ "mcp7941x", mcp794xx },
};
MODULE_DEVICE_TABLE(i2c, ds1307_id);
+#ifdef CONFIG_OF
+static const struct of_device_id ds1307_of_match[] = {
+ {
+ .compatible = "dallas,ds1307",
+ .data = (void *)ds_1307
+ },
+ {
+ .compatible = "dallas,ds1337",
+ .data = (void *)ds_1337
+ },
+ {
+ .compatible = "dallas,ds1338",
+ .data = (void *)ds_1338
+ },
+ {
+ .compatible = "dallas,ds1339",
+ .data = (void *)ds_1339
+ },
+ {
+ .compatible = "dallas,ds1388",
+ .data = (void *)ds_1388
+ },
+ {
+ .compatible = "dallas,ds1340",
+ .data = (void *)ds_1340
+ },
+ {
+ .compatible = "maxim,ds3231",
+ .data = (void *)ds_3231
+ },
+ {
+ .compatible = "st,m41t0",
+ .data = (void *)m41t00
+ },
+ {
+ .compatible = "st,m41t00",
+ .data = (void *)m41t00
+ },
+ {
+ .compatible = "microchip,mcp7940x",
+ .data = (void *)mcp794xx
+ },
+ {
+ .compatible = "microchip,mcp7941x",
+ .data = (void *)mcp794xx
+ },
+ {
+ .compatible = "pericom,pt7c4338",
+ .data = (void *)ds_1307
+ },
+ {
+ .compatible = "epson,rx8025",
+ .data = (void *)rx_8025
+ },
+ {
+ .compatible = "isil,isl12057",
+ .data = (void *)ds_1337
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(of, ds1307_of_match);
+#endif
+
#ifdef CONFIG_ACPI
static const struct acpi_device_id ds1307_acpi_ids[] = {
{ .id = "DS1307", .driver_data = ds_1307 },
{ .id = "DS1388", .driver_data = ds_1388 },
{ .id = "DS1340", .driver_data = ds_1340 },
{ .id = "DS3231", .driver_data = ds_3231 },
+ { .id = "M41T0", .driver_data = m41t0 },
{ .id = "M41T00", .driver_data = m41t00 },
{ .id = "MCP7940X", .driver_data = mcp794xx },
{ .id = "MCP7941X", .driver_data = mcp794xx },
dev_dbg(dev, "%s: %7ph\n", "read", ds1307->regs);
+ /* if oscillator fail bit is set, no data can be trusted */
+ if (ds1307->type == m41t0 &&
+ ds1307->regs[DS1307_REG_MIN] & M41T0_BIT_OF) {
+ dev_warn_once(dev, "oscillator failed, set time!\n");
+ return -EINVAL;
+ }
+
t->tm_sec = bcd2bin(ds1307->regs[DS1307_REG_SECS] & 0x7f);
t->tm_min = bcd2bin(ds1307->regs[DS1307_REG_MIN] & 0x7f);
tmp = ds1307->regs[DS1307_REG_HOUR] & 0x3f;
i2c_set_clientdata(client, ds1307);
ds1307->client = client;
- if (id) {
+
+ if (client->dev.of_node) {
+ ds1307->type = (enum ds_type)
+ of_device_get_match_data(&client->dev);
+ chip = &chips[ds1307->type];
+ } else if (id) {
chip = &chips[id->driver_data];
ds1307->type = id->driver_data;
} else {
tmp = ds1307->regs[DS1307_REG_SECS];
switch (ds1307->type) {
case ds_1307:
+ case m41t0:
case m41t00:
/* clock halted? turn it on, so clock can tick. */
if (tmp & DS1307_BIT_CH) {
tmp = ds1307->regs[DS1307_REG_HOUR];
switch (ds1307->type) {
case ds_1340:
+ case m41t0:
case m41t00:
/*
* NOTE: ignores century bits; fix before deploying
static struct i2c_driver ds1307_driver = {
.driver = {
.name = "rtc-ds1307",
+ .of_match_table = of_match_ptr(ds1307_of_match),
.acpi_match_table = ACPI_PTR(ds1307_acpi_ids),
},
.probe = ds1307_probe,
if (get_user(new_margin, (int __user *)arg))
return -EFAULT;
+ /* the hardware's tick rate is 4096 Hz, so
+ * the counter value needs to be scaled accordingly
+ */
+ new_margin <<= 12;
if (new_margin < 1 || new_margin > 16777216)
return -EINVAL;
ds1374_wdt_ping();
/* fallthrough */
case WDIOC_GETTIMEOUT:
- return put_user(wdt_margin, (int __user *)arg);
+ /* when returning ... inverse is true */
+ return put_user((wdt_margin >> 12), (int __user *)arg);
case WDIOC_SETOPTIONS:
if (copy_from_user(&options, (int __user *)arg, sizeof(int)))
return -EFAULT;
if (options & WDIOS_DISABLECARD) {
pr_info("disable watchdog\n");
ds1374_wdt_disable();
+ return 0;
}
if (options & WDIOS_ENABLECARD) {
pr_info("enable watchdog\n");
ds1374_wdt_settimeout(wdt_margin);
ds1374_wdt_ping();
+ return 0;
}
-
return -EINVAL;
}
return -ENOTTY;
static struct i2c_driver ds1374_driver = {
.driver = {
.name = "rtc-ds1374",
+ .of_match_table = of_match_ptr(ds1374_of_match),
.pm = &ds1374_pm,
},
.probe = ds1374_probe,
};
MODULE_DEVICE_TABLE(i2c, ds1672_id);
+static const struct of_device_id ds1672_of_match[] = {
+ { .compatible = "dallas,ds1672" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, ds1672_of_match);
+
static struct i2c_driver ds1672_driver = {
.driver = {
.name = "rtc-ds1672",
- },
+ .of_match_table = of_match_ptr(ds1672_of_match),
+ },
.probe = &ds1672_probe,
.id_table = ds1672_id,
};
};
MODULE_DEVICE_TABLE(i2c, ds3232_id);
+static const struct of_device_id ds3232_of_match[] = {
+ { .compatible = "dallas,ds3232" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, ds3232_of_match);
+
static struct i2c_driver ds3232_driver = {
.driver = {
.name = "rtc-ds3232",
+ .of_match_table = of_match_ptr(ds3232_of_match),
.pm = &ds3232_pm_ops,
},
.probe = ds3232_i2c_probe,
rtc->rtc_base = devm_ioremap(dev, res->start,
resource_size(res));
+ if (!rtc->rtc_base)
+ return -ENOMEM;
ret = devm_request_irq(dev, rtc->rtc_irq, gemini_rtc_interrupt,
IRQF_SHARED, pdev->name, dev);
"hid-sensor-time", &hid_time_rtc_ops,
THIS_MODULE);
- if (IS_ERR_OR_NULL(time_state->rtc)) {
+ if (IS_ERR(time_state->rtc)) {
hid_device_io_stop(hsdev->hdev);
- ret = time_state->rtc ? PTR_ERR(time_state->rtc) : -ENODEV;
+ ret = PTR_ERR(time_state->rtc);
time_state->rtc = NULL;
dev_err(&pdev->dev, "rtc device register failed!\n");
goto err_rtc;
};
MODULE_DEVICE_TABLE(i2c, isl1208_id);
+static const struct of_device_id isl1208_of_match[] = {
+ { .compatible = "isil,isl1208" },
+ { .compatible = "isil,isl1218" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, isl1208_of_match);
+
static struct i2c_driver isl1208_driver = {
.driver = {
- .name = "rtc-isl1208",
- },
+ .name = "rtc-isl1208",
+ .of_match_table = of_match_ptr(isl1208_of_match),
+ },
.probe = isl1208_probe,
.remove = isl1208_remove,
.id_table = isl1208_id,
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/rtc.h>
#include <linux/slab.h>
#include <linux/mutex.h>
};
MODULE_DEVICE_TABLE(i2c, m41t80_id);
+static const struct of_device_id m41t80_of_match[] = {
+ {
+ .compatible = "st,m41t62",
+ .data = (void *)(M41T80_FEATURE_SQ | M41T80_FEATURE_SQ_ALT)
+ },
+ {
+ .compatible = "st,m41t65",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_WD)
+ },
+ {
+ .compatible = "st,m41t80",
+ .data = (void *)(M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "st,m41t81",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "st,m41t81s",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "st,m41t82",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "st,m41t83",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "st,m41t84",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "st,m41t85",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "st,m41t87",
+ .data = (void *)(M41T80_FEATURE_HT | M41T80_FEATURE_BL | M41T80_FEATURE_SQ)
+ },
+ {
+ .compatible = "microcrystal,rv4162",
+ .data = (void *)(M41T80_FEATURE_SQ | M41T80_FEATURE_WD | M41T80_FEATURE_SQ_ALT)
+ },
+ /* DT compatibility only, do not use compatibles below: */
+ {
+ .compatible = "st,rv4162",
+ .data = (void *)(M41T80_FEATURE_SQ | M41T80_FEATURE_WD | M41T80_FEATURE_SQ_ALT)
+ },
+ {
+ .compatible = "rv4162",
+ .data = (void *)(M41T80_FEATURE_SQ | M41T80_FEATURE_WD | M41T80_FEATURE_SQ_ALT)
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(of, m41t80_of_match);
+
struct m41t80_data {
- u8 features;
+ unsigned long features;
struct rtc_device *rtc;
};
if (!m41t80_data)
return -ENOMEM;
- m41t80_data->features = id->driver_data;
+ if (client->dev.of_node)
+ m41t80_data->features = (unsigned long)
+ of_device_get_match_data(&client->dev);
+ else
+ m41t80_data->features = id->driver_data;
i2c_set_clientdata(client, m41t80_data);
if (client->irq > 0) {
static struct i2c_driver m41t80_driver = {
.driver = {
.name = "rtc-m41t80",
+ .of_match_table = of_match_ptr(m41t80_of_match),
.pm = &m41t80_pm,
},
.probe = m41t80_probe,
return ret;
}
-static int __exit omap_rtc_remove(struct platform_device *pdev)
+static int omap_rtc_remove(struct platform_device *pdev)
{
struct omap_rtc *rtc = platform_get_drvdata(pdev);
u8 reg;
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int omap_rtc_suspend(struct device *dev)
+static int __maybe_unused omap_rtc_suspend(struct device *dev)
{
struct omap_rtc *rtc = dev_get_drvdata(dev);
return 0;
}
-static int omap_rtc_resume(struct device *dev)
+static int __maybe_unused omap_rtc_resume(struct device *dev)
{
struct omap_rtc *rtc = dev_get_drvdata(dev);
return 0;
}
-#endif
-#ifdef CONFIG_PM
-static int omap_rtc_runtime_suspend(struct device *dev)
+static int __maybe_unused omap_rtc_runtime_suspend(struct device *dev)
{
struct omap_rtc *rtc = dev_get_drvdata(dev);
return 0;
}
-static int omap_rtc_runtime_resume(struct device *dev)
-{
- return 0;
-}
-#endif
-
static const struct dev_pm_ops omap_rtc_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(omap_rtc_suspend, omap_rtc_resume)
- SET_RUNTIME_PM_OPS(omap_rtc_runtime_suspend,
- omap_rtc_runtime_resume, NULL)
+ SET_RUNTIME_PM_OPS(omap_rtc_runtime_suspend, NULL, NULL)
};
static void omap_rtc_shutdown(struct platform_device *pdev)
static struct platform_driver omap_rtc_driver = {
.probe = omap_rtc_probe,
- .remove = __exit_p(omap_rtc_remove),
+ .remove = omap_rtc_remove,
.shutdown = omap_rtc_shutdown,
.driver = {
.name = "omap_rtc",
#include <linux/bcd.h>
#include <linux/slab.h>
#include <linux/module.h>
+#include <linux/of_device.h>
/*
* Ricoh has a family of I2C based RTCs, which differ only slightly from
};
MODULE_DEVICE_TABLE(i2c, rs5c372_id);
+static const struct of_device_id rs5c372_of_match[] = {
+ {
+ .compatible = "ricoh,r2025sd",
+ .data = (void *)rtc_r2025sd
+ },
+ {
+ .compatible = "ricoh,r2221tl",
+ .data = (void *)rtc_r2221tl
+ },
+ {
+ .compatible = "ricoh,rs5c372a",
+ .data = (void *)rtc_rs5c372a
+ },
+ {
+ .compatible = "ricoh,rs5c372b",
+ .data = (void *)rtc_rs5c372b
+ },
+ {
+ .compatible = "ricoh,rv5c386",
+ .data = (void *)rtc_rv5c386
+ },
+ {
+ .compatible = "ricoh,rv5c387a",
+ .data = (void *)rtc_rv5c387a
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(of, rs5c372_of_match);
+
/* REVISIT: this assumes that:
* - we're in the 21st century, so it's safe to ignore the century
* bit for rv5c38[67] (REG_MONTH bit 7);
rs5c372->client = client;
i2c_set_clientdata(client, rs5c372);
- rs5c372->type = id->driver_data;
+ if (client->dev.of_node)
+ rs5c372->type = (enum rtc_type)
+ of_device_get_match_data(&client->dev);
+ else
+ rs5c372->type = id->driver_data;
/* we read registers 0x0f then 0x00-0x0f; skip the first one */
rs5c372->regs = &rs5c372->buf[1];
static struct i2c_driver rs5c372_driver = {
.driver = {
.name = "rtc-rs5c372",
+ .of_match_table = of_match_ptr(rs5c372_of_match),
},
.probe = rs5c372_probe,
.remove = rs5c372_remove,
};
MODULE_DEVICE_TABLE(i2c, rv3029_id);
+static const struct of_device_id rv3029_of_match[] = {
+ { .compatible = "rv3029" },
+ { .compatible = "rv3029c2" },
+ { .compatible = "mc,rv3029c2" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, rv3029_of_match);
+
static struct i2c_driver rv3029_driver = {
.driver = {
.name = "rtc-rv3029c2",
+ .of_match_table = of_match_ptr(rv3029_of_match),
},
.probe = rv3029_i2c_probe,
.id_table = rv3029_id,
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/of_device.h>
#include <linux/rtc.h>
#define RV8803_I2C_TRY_COUNT 4
mutex_init(&rv8803->flags_lock);
rv8803->client = client;
- rv8803->type = id->driver_data;
+ if (client->dev.of_node)
+ rv8803->type = (enum rv8803_type)
+ of_device_get_match_data(&client->dev);
+ else
+ rv8803->type = id->driver_data;
i2c_set_clientdata(client, rv8803);
flags = rv8803_read_reg(client, RV8803_FLAG);
};
MODULE_DEVICE_TABLE(i2c, rv8803_id);
+static const struct of_device_id rv8803_of_match[] = {
+ {
+ .compatible = "microcrystal,rv8803",
+ .data = (void *)rx_8900
+ },
+ {
+ .compatible = "epson,rx8900",
+ .data = (void *)rx_8900
+ },
+ { }
+};
+MODULE_DEVICE_TABLE(of, rv8803_of_match);
+
static struct i2c_driver rv8803_driver = {
.driver = {
.name = "rtc-rv8803",
+ .of_match_table = of_match_ptr(rv8803_of_match),
},
.probe = rv8803_probe,
.remove = rv8803_remove,
};
MODULE_DEVICE_TABLE(i2c, rx8010_id);
+static const struct of_device_id rx8010_of_match[] = {
+ { .compatible = "epson,rx8010" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, rx8010_of_match);
+
struct rx8010_data {
struct i2c_client *client;
struct rtc_device *rtc;
static struct i2c_driver rx8010_driver = {
.driver = {
.name = "rtc-rx8010",
+ .of_match_table = of_match_ptr(rx8010_of_match),
},
.probe = rx8010_probe,
.id_table = rx8010_id,
};
MODULE_DEVICE_TABLE(i2c, rx8581_id);
+static const struct of_device_id rx8581_of_match[] = {
+ { .compatible = "epson,rx8581" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, rx8581_of_match);
+
static struct i2c_driver rx8581_driver = {
.driver = {
.name = "rtc-rx8581",
+ .of_match_table = of_match_ptr(rx8581_of_match),
},
.probe = rx8581_probe,
.id_table = rx8581_id,
};
MODULE_DEVICE_TABLE(i2c, s35390a_id);
+static const struct of_device_id s35390a_of_match[] = {
+ { .compatible = "s35390a" },
+ { .compatible = "sii,s35390a" },
+ { }
+};
+MODULE_DEVICE_TABLE(of, s35390a_of_match);
+
struct s35390a {
struct i2c_client *client[8];
struct rtc_device *rtc;
static struct i2c_driver s35390a_driver = {
.driver = {
.name = "rtc-s35390a",
+ .of_match_table = of_match_ptr(s35390a_of_match),
},
.probe = s35390a_probe,
.remove = s35390a_remove,
#include <linux/log2.h>
#include <linux/clk.h>
#include <linux/slab.h>
+#ifdef CONFIG_SUPERH
#include <asm/rtc.h>
+#else
+/* Default values for RZ/A RTC */
+#define rtc_reg_size sizeof(u16)
+#define RTC_BIT_INVERTED 0 /* no chip bugs */
+#define RTC_CAP_4_DIGIT_YEAR (1 << 0)
+#define RTC_DEF_CAPABILITIES RTC_CAP_4_DIGIT_YEAR
+#endif
#define DRV_NAME "sh-rtc"
rtc->alarm_irq = platform_get_irq(pdev, 2);
res = platform_get_resource(pdev, IORESOURCE_IO, 0);
+ if (!res)
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (unlikely(res == NULL)) {
dev_err(&pdev->dev, "No IO resource\n");
return -ENOENT;
if (unlikely(!rtc->regbase))
return -EINVAL;
- clk_id = pdev->id;
- /* With a single device, the clock id is still "rtc0" */
- if (clk_id < 0)
- clk_id = 0;
+ if (!pdev->dev.of_node) {
+ clk_id = pdev->id;
+ /* With a single device, the clock id is still "rtc0" */
+ if (clk_id < 0)
+ clk_id = 0;
- snprintf(clk_name, sizeof(clk_name), "rtc%d", clk_id);
+ snprintf(clk_name, sizeof(clk_name), "rtc%d", clk_id);
+ } else
+ snprintf(clk_name, sizeof(clk_name), "fck");
rtc->clk = devm_clk_get(&pdev->dev, clk_name);
if (IS_ERR(rtc->clk)) {
clk_enable(rtc->clk);
rtc->capabilities = RTC_DEF_CAPABILITIES;
+
+#ifdef CONFIG_SUPERH
if (dev_get_platdata(&pdev->dev)) {
struct sh_rtc_platform_info *pinfo =
dev_get_platdata(&pdev->dev);
*/
rtc->capabilities |= pinfo->capabilities;
}
+#endif
if (rtc->carry_irq <= 0) {
/* register shared periodic/carry/alarm irq */
}
}
-#ifdef CONFIG_PM_SLEEP
-static int sh_rtc_suspend(struct device *dev)
+static int __maybe_unused sh_rtc_suspend(struct device *dev)
{
if (device_may_wakeup(dev))
sh_rtc_set_irq_wake(dev, 1);
return 0;
}
-static int sh_rtc_resume(struct device *dev)
+static int __maybe_unused sh_rtc_resume(struct device *dev)
{
if (device_may_wakeup(dev))
sh_rtc_set_irq_wake(dev, 0);
return 0;
}
-#endif
static SIMPLE_DEV_PM_OPS(sh_rtc_pm_ops, sh_rtc_suspend, sh_rtc_resume);
+static const struct of_device_id sh_rtc_of_match[] = {
+ { .compatible = "renesas,sh-rtc", },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sh_rtc_of_match);
+
static struct platform_driver sh_rtc_platform_driver = {
.driver = {
.name = DRV_NAME,
.pm = &sh_rtc_pm_ops,
+ .of_match_table = sh_rtc_of_match,
},
.remove = __exit_p(sh_rtc_remove),
};
of_property_read_u32(pdev->dev.of_node, "offset", &data->offset);
}
- if (!data->regmap) {
+ if (IS_ERR(data->regmap)) {
dev_err(&pdev->dev, "Can't find snvs syscon\n");
return -ENODEV;
}
#define WM8350_SET_TIME_RETRIES 5
#define WM8350_GET_TIME_RETRIES 5
-#define to_wm8350_from_rtc_dev(d) container_of(d, struct wm8350, rtc.pdev.dev)
-
/*
* Read current time and date in RTC
*/
static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
unsigned index,
void (*callback)(struct virtqueue *vq),
- const char *name)
+ const char *name, bool ctx)
{
struct kvm_device *kdev = to_kvmdev(vdev);
struct kvm_vqconfig *config;
goto out;
vq = vring_new_virtqueue(index, config->num, KVM_S390_VIRTIO_RING_ALIGN,
- vdev, true, (void *) config->address,
+ vdev, true, ctx, (void *) config->address,
kvm_notify, callback, name);
if (!vq) {
err = -ENOMEM;
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
const char * const names[],
+ const bool *ctx,
struct irq_affinity *desc)
{
struct kvm_device *kdev = to_kvmdev(vdev);
return -ENOENT;
for (i = 0; i < nvqs; ++i) {
- vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i]);
+ vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i],
+ ctx ? ctx[i] : false);
if (IS_ERR(vqs[i]))
goto error;
}
static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev,
int i, vq_callback_t *callback,
- const char *name,
+ const char *name, bool ctx,
struct ccw1 *ccw)
{
struct virtio_ccw_device *vcdev = to_vc_device(vdev);
}
vq = vring_new_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev,
- true, info->queue, virtio_ccw_kvm_notify,
+ true, ctx, info->queue, virtio_ccw_kvm_notify,
callback, name);
if (!vq) {
/* For now, we fail if we can't get the requested size. */
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
const char * const names[],
+ const bool *ctx,
struct irq_affinity *desc)
{
struct virtio_ccw_device *vcdev = to_vc_device(vdev);
for (i = 0; i < nvqs; ++i) {
vqs[i] = virtio_ccw_setup_vq(vdev, i, callbacks[i], names[i],
- ccw);
+ ctx ? ctx[i] : false, ccw);
if (IS_ERR(vqs[i])) {
ret = PTR_ERR(vqs[i]);
vqs[i] = NULL;
#if !defined(PCMCIA)
#if defined(MODULE)
static int io[] = {0, 0};
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_PARM_DESC(io,"base io address of controller");
static int irq[] = {0, 0};
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq,"interrupt for controller");
static int scsiid[] = {7, 7};
MODULE_PARM_DESC(isapnp, "enable PnP support (default=1)");
static int io[MAXBOARDS] = { 0x330, 0x334, 0, 0 };
-module_param_array(io, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
MODULE_PARM_DESC(io, "base IO address of controller (0x130,0x134,0x230,0x234,0x330,0x334, default=0x330,0x334)");
/* time AHA spends on the AT-bus during data transfer */
static int ncr_53c400a;
static int dtc_3181e;
static int hp_c2502;
-module_param(ncr_irq, int, 0);
-module_param(ncr_addr, int, 0);
+module_param_hw(ncr_irq, int, irq, 0);
+module_param_hw(ncr_addr, int, ioport, 0);
module_param(ncr_5380, int, 0);
module_param(ncr_53c400, int, 0);
module_param(ncr_53c400a, int, 0);
module_param(hp_c2502, int, 0);
static int irq[] = { -1, -1, -1, -1, -1, -1, -1, -1 };
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(irq, "IRQ number(s) (0=none, 254=auto [default])");
static int base[] = { 0, 0, 0, 0, 0, 0, 0, 0 };
-module_param_array(base, int, NULL, 0);
+module_param_hw_array(base, int, ioport, NULL, 0);
MODULE_PARM_DESC(base, "base address(es)");
static int card[] = { -1, -1, -1, -1, -1, -1, -1, -1 };
static int force_dma32 = 0;
/* parameters for modprobe/insmod */
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
module_param(disable, int, 0);
module_param(reserve_mode, int, 0);
module_param_array(reserve_list, int, NULL, 0);
static struct qlogicfas408_priv *cards;
static int iobase[MAX_QLOGICFAS];
static int irq[MAX_QLOGICFAS] = { [0 ... MAX_QLOGICFAS-1] = -1 };
-module_param_array(iobase, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(iobase, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
MODULE_PARM_DESC(iobase, "I/O address");
MODULE_PARM_DESC(irq, "IRQ");
}
/* Discover virtqueues and write information to configuration. */
- err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
- &desc);
+ err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
if (err)
goto out;
#include "dpaa_sys.h"
#include <soc/fsl/qman.h>
+#include <linux/dma-mapping.h>
#include <linux/iommu.h>
#if defined(CONFIG_FSL_PAMU)
ldlm_lock_slab = kmem_cache_create("ldlm_locks",
sizeof(struct ldlm_lock), 0,
SLAB_HWCACHE_ALIGN |
- SLAB_DESTROY_BY_RCU, NULL);
+ SLAB_TYPESAFE_BY_RCU, NULL);
if (!ldlm_lock_slab) {
kmem_cache_destroy(ldlm_resource_slab);
return -ENOMEM;
speakup_info.port_tts = 0;
}
-module_param_named(port, port_forced, int, 0444);
+module_param_hw_named(port, port_forced, int, ioport, 0444);
module_param_named(start, synth_acntpc.startup, short, 0444);
MODULE_PARM_DESC(port, "Set the port for the synthesizer (override probing).");
speakup_info.port_tts = 0;
}
-module_param_named(port, port_forced, int, 0444);
+module_param_hw_named(port, port_forced, int, ioport, 0444);
module_param_named(start, synth_dtlk.startup, short, 0444);
MODULE_PARM_DESC(port, "Set the port for the synthesizer (override probing).");
synth_port = 0;
}
-module_param_named(port, port_forced, int, 0444);
+module_param_hw_named(port, port_forced, int, ioport, 0444);
module_param_named(start, synth_keypc.startup, short, 0444);
MODULE_PARM_DESC(port, "Set the port for the synthesizer (override probing).");
/* These are required for each board */
MODULE_PARM_DESC(bus, "Enumeration of VMEbus to which the board is connected");
-module_param_array(bus, int, &bus_num, 0444);
+module_param_hw_array(bus, int, other, &bus_num, 0444);
MODULE_PARM_DESC(base, "Base VME address for PIO2 Registers");
-module_param_array(base, long, &base_num, 0444);
+module_param_hw_array(base, long, other, &base_num, 0444);
MODULE_PARM_DESC(vector, "VME IRQ Vector (Lower 4 bits masked)");
-module_param_array(vector, int, &vector_num, 0444);
+module_param_hw_array(vector, int, other, &vector_num, 0444);
MODULE_PARM_DESC(level, "VME IRQ Level");
-module_param_array(level, int, &level_num, 0444);
+module_param_hw_array(level, int, other, &level_num, 0444);
MODULE_PARM_DESC(variant, "Last 4 characters of PIO2 board variant");
module_param_array(variant, charp, &variant_num, 0444);
--- /dev/null
+# Generic Trusted Execution Environment Configuration
+config TEE
+ tristate "Trusted Execution Environment support"
+ select DMA_SHARED_BUFFER
+ select GENERIC_ALLOCATOR
+ help
+ This implements a generic interface towards a Trusted Execution
+ Environment (TEE).
+
+if TEE
+
+menu "TEE drivers"
+
+source "drivers/tee/optee/Kconfig"
+
+endmenu
+
+endif
--- /dev/null
+obj-$(CONFIG_TEE) += tee.o
+tee-objs += tee_core.o
+tee-objs += tee_shm.o
+tee-objs += tee_shm_pool.o
+obj-$(CONFIG_OPTEE) += optee/
--- /dev/null
+# OP-TEE Trusted Execution Environment Configuration
+config OPTEE
+ tristate "OP-TEE"
+ depends on HAVE_ARM_SMCCC
+ help
+ This implements the OP-TEE Trusted Execution Environment (TEE)
+ driver.
--- /dev/null
+obj-$(CONFIG_OPTEE) += optee.o
+optee-objs += core.o
+optee-objs += call.o
+optee-objs += rpc.o
+optee-objs += supp.o
--- /dev/null
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/arm-smccc.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include "optee_private.h"
+#include "optee_smc.h"
+
+struct optee_call_waiter {
+ struct list_head list_node;
+ struct completion c;
+};
+
+static void optee_cq_wait_init(struct optee_call_queue *cq,
+ struct optee_call_waiter *w)
+{
+ /*
+ * We're preparing to make a call to secure world. In case we can't
+ * allocate a thread in secure world we'll end up waiting in
+ * optee_cq_wait_for_completion().
+ *
+ * Normally if there's no contention in secure world the call will
+ * complete and we can cleanup directly with optee_cq_wait_final().
+ */
+ mutex_lock(&cq->mutex);
+
+ /*
+ * We add ourselves to the queue, but we don't wait. This
+ * guarantees that we don't lose a completion if secure world
+ * returns busy and another thread just exited and try to complete
+ * someone.
+ */
+ init_completion(&w->c);
+ list_add_tail(&w->list_node, &cq->waiters);
+
+ mutex_unlock(&cq->mutex);
+}
+
+static void optee_cq_wait_for_completion(struct optee_call_queue *cq,
+ struct optee_call_waiter *w)
+{
+ wait_for_completion(&w->c);
+
+ mutex_lock(&cq->mutex);
+
+ /* Move to end of list to get out of the way for other waiters */
+ list_del(&w->list_node);
+ reinit_completion(&w->c);
+ list_add_tail(&w->list_node, &cq->waiters);
+
+ mutex_unlock(&cq->mutex);
+}
+
+static void optee_cq_complete_one(struct optee_call_queue *cq)
+{
+ struct optee_call_waiter *w;
+
+ list_for_each_entry(w, &cq->waiters, list_node) {
+ if (!completion_done(&w->c)) {
+ complete(&w->c);
+ break;
+ }
+ }
+}
+
+static void optee_cq_wait_final(struct optee_call_queue *cq,
+ struct optee_call_waiter *w)
+{
+ /*
+ * We're done with the call to secure world. The thread in secure
+ * world that was used for this call is now available for some
+ * other task to use.
+ */
+ mutex_lock(&cq->mutex);
+
+ /* Get out of the list */
+ list_del(&w->list_node);
+
+ /* Wake up one eventual waiting task */
+ optee_cq_complete_one(cq);
+
+ /*
+ * If we're completed we've got a completion from another task that
+ * was just done with its call to secure world. Since yet another
+ * thread now is available in secure world wake up another eventual
+ * waiting task.
+ */
+ if (completion_done(&w->c))
+ optee_cq_complete_one(cq);
+
+ mutex_unlock(&cq->mutex);
+}
+
+/* Requires the filpstate mutex to be held */
+static struct optee_session *find_session(struct optee_context_data *ctxdata,
+ u32 session_id)
+{
+ struct optee_session *sess;
+
+ list_for_each_entry(sess, &ctxdata->sess_list, list_node)
+ if (sess->session_id == session_id)
+ return sess;
+
+ return NULL;
+}
+
+/**
+ * optee_do_call_with_arg() - Do an SMC to OP-TEE in secure world
+ * @ctx: calling context
+ * @parg: physical address of message to pass to secure world
+ *
+ * Does and SMC to OP-TEE in secure world and handles eventual resulting
+ * Remote Procedure Calls (RPC) from OP-TEE.
+ *
+ * Returns return code from secure world, 0 is OK
+ */
+u32 optee_do_call_with_arg(struct tee_context *ctx, phys_addr_t parg)
+{
+ struct optee *optee = tee_get_drvdata(ctx->teedev);
+ struct optee_call_waiter w;
+ struct optee_rpc_param param = { };
+ u32 ret;
+
+ param.a0 = OPTEE_SMC_CALL_WITH_ARG;
+ reg_pair_from_64(¶m.a1, ¶m.a2, parg);
+ /* Initialize waiter */
+ optee_cq_wait_init(&optee->call_queue, &w);
+ while (true) {
+ struct arm_smccc_res res;
+
+ optee->invoke_fn(param.a0, param.a1, param.a2, param.a3,
+ param.a4, param.a5, param.a6, param.a7,
+ &res);
+
+ if (res.a0 == OPTEE_SMC_RETURN_ETHREAD_LIMIT) {
+ /*
+ * Out of threads in secure world, wait for a thread
+ * become available.
+ */
+ optee_cq_wait_for_completion(&optee->call_queue, &w);
+ } else if (OPTEE_SMC_RETURN_IS_RPC(res.a0)) {
+ param.a0 = res.a0;
+ param.a1 = res.a1;
+ param.a2 = res.a2;
+ param.a3 = res.a3;
+ optee_handle_rpc(ctx, ¶m);
+ } else {
+ ret = res.a0;
+ break;
+ }
+ }
+
+ /*
+ * We're done with our thread in secure world, if there's any
+ * thread waiters wake up one.
+ */
+ optee_cq_wait_final(&optee->call_queue, &w);
+
+ return ret;
+}
+
+static struct tee_shm *get_msg_arg(struct tee_context *ctx, size_t num_params,
+ struct optee_msg_arg **msg_arg,
+ phys_addr_t *msg_parg)
+{
+ int rc;
+ struct tee_shm *shm;
+ struct optee_msg_arg *ma;
+
+ shm = tee_shm_alloc(ctx, OPTEE_MSG_GET_ARG_SIZE(num_params),
+ TEE_SHM_MAPPED);
+ if (IS_ERR(shm))
+ return shm;
+
+ ma = tee_shm_get_va(shm, 0);
+ if (IS_ERR(ma)) {
+ rc = PTR_ERR(ma);
+ goto out;
+ }
+
+ rc = tee_shm_get_pa(shm, 0, msg_parg);
+ if (rc)
+ goto out;
+
+ memset(ma, 0, OPTEE_MSG_GET_ARG_SIZE(num_params));
+ ma->num_params = num_params;
+ *msg_arg = ma;
+out:
+ if (rc) {
+ tee_shm_free(shm);
+ return ERR_PTR(rc);
+ }
+
+ return shm;
+}
+
+int optee_open_session(struct tee_context *ctx,
+ struct tee_ioctl_open_session_arg *arg,
+ struct tee_param *param)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ int rc;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess = NULL;
+
+ /* +2 for the meta parameters added below */
+ shm = get_msg_arg(ctx, arg->num_params + 2, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ msg_arg->cmd = OPTEE_MSG_CMD_OPEN_SESSION;
+ msg_arg->cancel_id = arg->cancel_id;
+
+ /*
+ * Initialize and add the meta parameters needed when opening a
+ * session.
+ */
+ msg_arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT |
+ OPTEE_MSG_ATTR_META;
+ msg_arg->params[1].attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT |
+ OPTEE_MSG_ATTR_META;
+ memcpy(&msg_arg->params[0].u.value, arg->uuid, sizeof(arg->uuid));
+ memcpy(&msg_arg->params[1].u.value, arg->uuid, sizeof(arg->clnt_uuid));
+ msg_arg->params[1].u.value.c = arg->clnt_login;
+
+ rc = optee_to_msg_param(msg_arg->params + 2, arg->num_params, param);
+ if (rc)
+ goto out;
+
+ sess = kzalloc(sizeof(*sess), GFP_KERNEL);
+ if (!sess) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ if (optee_do_call_with_arg(ctx, msg_parg)) {
+ msg_arg->ret = TEEC_ERROR_COMMUNICATION;
+ msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
+ }
+
+ if (msg_arg->ret == TEEC_SUCCESS) {
+ /* A new session has been created, add it to the list. */
+ sess->session_id = msg_arg->session;
+ mutex_lock(&ctxdata->mutex);
+ list_add(&sess->list_node, &ctxdata->sess_list);
+ mutex_unlock(&ctxdata->mutex);
+ } else {
+ kfree(sess);
+ }
+
+ if (optee_from_msg_param(param, arg->num_params, msg_arg->params + 2)) {
+ arg->ret = TEEC_ERROR_COMMUNICATION;
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+ /* Close session again to avoid leakage */
+ optee_close_session(ctx, msg_arg->session);
+ } else {
+ arg->session = msg_arg->session;
+ arg->ret = msg_arg->ret;
+ arg->ret_origin = msg_arg->ret_origin;
+ }
+out:
+ tee_shm_free(shm);
+
+ return rc;
+}
+
+int optee_close_session(struct tee_context *ctx, u32 session)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess;
+
+ /* Check that the session is valid and remove it from the list */
+ mutex_lock(&ctxdata->mutex);
+ sess = find_session(ctxdata, session);
+ if (sess)
+ list_del(&sess->list_node);
+ mutex_unlock(&ctxdata->mutex);
+ if (!sess)
+ return -EINVAL;
+ kfree(sess);
+
+ shm = get_msg_arg(ctx, 0, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ msg_arg->cmd = OPTEE_MSG_CMD_CLOSE_SESSION;
+ msg_arg->session = session;
+ optee_do_call_with_arg(ctx, msg_parg);
+
+ tee_shm_free(shm);
+ return 0;
+}
+
+int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
+ struct tee_param *param)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess;
+ int rc;
+
+ /* Check that the session is valid */
+ mutex_lock(&ctxdata->mutex);
+ sess = find_session(ctxdata, arg->session);
+ mutex_unlock(&ctxdata->mutex);
+ if (!sess)
+ return -EINVAL;
+
+ shm = get_msg_arg(ctx, arg->num_params, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+ msg_arg->cmd = OPTEE_MSG_CMD_INVOKE_COMMAND;
+ msg_arg->func = arg->func;
+ msg_arg->session = arg->session;
+ msg_arg->cancel_id = arg->cancel_id;
+
+ rc = optee_to_msg_param(msg_arg->params, arg->num_params, param);
+ if (rc)
+ goto out;
+
+ if (optee_do_call_with_arg(ctx, msg_parg)) {
+ msg_arg->ret = TEEC_ERROR_COMMUNICATION;
+ msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
+ }
+
+ if (optee_from_msg_param(param, arg->num_params, msg_arg->params)) {
+ msg_arg->ret = TEEC_ERROR_COMMUNICATION;
+ msg_arg->ret_origin = TEEC_ORIGIN_COMMS;
+ }
+
+ arg->ret = msg_arg->ret;
+ arg->ret_origin = msg_arg->ret_origin;
+out:
+ tee_shm_free(shm);
+ return rc;
+}
+
+int optee_cancel_req(struct tee_context *ctx, u32 cancel_id, u32 session)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_shm *shm;
+ struct optee_msg_arg *msg_arg;
+ phys_addr_t msg_parg;
+ struct optee_session *sess;
+
+ /* Check that the session is valid */
+ mutex_lock(&ctxdata->mutex);
+ sess = find_session(ctxdata, session);
+ mutex_unlock(&ctxdata->mutex);
+ if (!sess)
+ return -EINVAL;
+
+ shm = get_msg_arg(ctx, 0, &msg_arg, &msg_parg);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ msg_arg->cmd = OPTEE_MSG_CMD_CANCEL;
+ msg_arg->session = session;
+ msg_arg->cancel_id = cancel_id;
+ optee_do_call_with_arg(ctx, msg_parg);
+
+ tee_shm_free(shm);
+ return 0;
+}
+
+/**
+ * optee_enable_shm_cache() - Enables caching of some shared memory allocation
+ * in OP-TEE
+ * @optee: main service struct
+ */
+void optee_enable_shm_cache(struct optee *optee)
+{
+ struct optee_call_waiter w;
+
+ /* We need to retry until secure world isn't busy. */
+ optee_cq_wait_init(&optee->call_queue, &w);
+ while (true) {
+ struct arm_smccc_res res;
+
+ optee->invoke_fn(OPTEE_SMC_ENABLE_SHM_CACHE, 0, 0, 0, 0, 0, 0,
+ 0, &res);
+ if (res.a0 == OPTEE_SMC_RETURN_OK)
+ break;
+ optee_cq_wait_for_completion(&optee->call_queue, &w);
+ }
+ optee_cq_wait_final(&optee->call_queue, &w);
+}
+
+/**
+ * optee_disable_shm_cache() - Disables caching of some shared memory allocation
+ * in OP-TEE
+ * @optee: main service struct
+ */
+void optee_disable_shm_cache(struct optee *optee)
+{
+ struct optee_call_waiter w;
+
+ /* We need to retry until secure world isn't busy. */
+ optee_cq_wait_init(&optee->call_queue, &w);
+ while (true) {
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_disable_shm_cache_result result;
+ } res;
+
+ optee->invoke_fn(OPTEE_SMC_DISABLE_SHM_CACHE, 0, 0, 0, 0, 0, 0,
+ 0, &res.smccc);
+ if (res.result.status == OPTEE_SMC_RETURN_ENOTAVAIL)
+ break; /* All shm's freed */
+ if (res.result.status == OPTEE_SMC_RETURN_OK) {
+ struct tee_shm *shm;
+
+ shm = reg_pair_to_ptr(res.result.shm_upper32,
+ res.result.shm_lower32);
+ tee_shm_free(shm);
+ } else {
+ optee_cq_wait_for_completion(&optee->call_queue, &w);
+ }
+ }
+ optee_cq_wait_final(&optee->call_queue, &w);
+}
--- /dev/null
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/arm-smccc.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/tee_drv.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include "optee_private.h"
+#include "optee_smc.h"
+
+#define DRIVER_NAME "optee"
+
+#define OPTEE_SHM_NUM_PRIV_PAGES 1
+
+/**
+ * optee_from_msg_param() - convert from OPTEE_MSG parameters to
+ * struct tee_param
+ * @params: subsystem internal parameter representation
+ * @num_params: number of elements in the parameter arrays
+ * @msg_params: OPTEE_MSG parameters
+ * Returns 0 on success or <0 on failure
+ */
+int optee_from_msg_param(struct tee_param *params, size_t num_params,
+ const struct optee_msg_param *msg_params)
+{
+ int rc;
+ size_t n;
+ struct tee_shm *shm;
+ phys_addr_t pa;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_param *p = params + n;
+ const struct optee_msg_param *mp = msg_params + n;
+ u32 attr = mp->attr & OPTEE_MSG_ATTR_TYPE_MASK;
+
+ switch (attr) {
+ case OPTEE_MSG_ATTR_TYPE_NONE:
+ p->attr = TEE_IOCTL_PARAM_ATTR_TYPE_NONE;
+ memset(&p->u, 0, sizeof(p->u));
+ break;
+ case OPTEE_MSG_ATTR_TYPE_VALUE_INPUT:
+ case OPTEE_MSG_ATTR_TYPE_VALUE_OUTPUT:
+ case OPTEE_MSG_ATTR_TYPE_VALUE_INOUT:
+ p->attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT +
+ attr - OPTEE_MSG_ATTR_TYPE_VALUE_INPUT;
+ p->u.value.a = mp->u.value.a;
+ p->u.value.b = mp->u.value.b;
+ p->u.value.c = mp->u.value.c;
+ break;
+ case OPTEE_MSG_ATTR_TYPE_TMEM_INPUT:
+ case OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT:
+ case OPTEE_MSG_ATTR_TYPE_TMEM_INOUT:
+ p->attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT +
+ attr - OPTEE_MSG_ATTR_TYPE_TMEM_INPUT;
+ p->u.memref.size = mp->u.tmem.size;
+ shm = (struct tee_shm *)(unsigned long)
+ mp->u.tmem.shm_ref;
+ if (!shm) {
+ p->u.memref.shm_offs = 0;
+ p->u.memref.shm = NULL;
+ break;
+ }
+ rc = tee_shm_get_pa(shm, 0, &pa);
+ if (rc)
+ return rc;
+ p->u.memref.shm_offs = mp->u.tmem.buf_ptr - pa;
+ p->u.memref.shm = shm;
+
+ /* Check that the memref is covered by the shm object */
+ if (p->u.memref.size) {
+ size_t o = p->u.memref.shm_offs +
+ p->u.memref.size - 1;
+
+ rc = tee_shm_get_pa(shm, o, NULL);
+ if (rc)
+ return rc;
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+/**
+ * optee_to_msg_param() - convert from struct tee_params to OPTEE_MSG parameters
+ * @msg_params: OPTEE_MSG parameters
+ * @num_params: number of elements in the parameter arrays
+ * @params: subsystem itnernal parameter representation
+ * Returns 0 on success or <0 on failure
+ */
+int optee_to_msg_param(struct optee_msg_param *msg_params, size_t num_params,
+ const struct tee_param *params)
+{
+ int rc;
+ size_t n;
+ phys_addr_t pa;
+
+ for (n = 0; n < num_params; n++) {
+ const struct tee_param *p = params + n;
+ struct optee_msg_param *mp = msg_params + n;
+
+ switch (p->attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_NONE:
+ mp->attr = TEE_IOCTL_PARAM_ATTR_TYPE_NONE;
+ memset(&mp->u, 0, sizeof(mp->u));
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ mp->attr = OPTEE_MSG_ATTR_TYPE_VALUE_INPUT + p->attr -
+ TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT;
+ mp->u.value.a = p->u.value.a;
+ mp->u.value.b = p->u.value.b;
+ mp->u.value.c = p->u.value.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ mp->attr = OPTEE_MSG_ATTR_TYPE_TMEM_INPUT +
+ p->attr -
+ TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+ mp->u.tmem.shm_ref = (unsigned long)p->u.memref.shm;
+ mp->u.tmem.size = p->u.memref.size;
+ if (!p->u.memref.shm) {
+ mp->u.tmem.buf_ptr = 0;
+ break;
+ }
+ rc = tee_shm_get_pa(p->u.memref.shm,
+ p->u.memref.shm_offs, &pa);
+ if (rc)
+ return rc;
+ mp->u.tmem.buf_ptr = pa;
+ mp->attr |= OPTEE_MSG_ATTR_CACHE_PREDEFINED <<
+ OPTEE_MSG_ATTR_CACHE_SHIFT;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+static void optee_get_version(struct tee_device *teedev,
+ struct tee_ioctl_version_data *vers)
+{
+ struct tee_ioctl_version_data v = {
+ .impl_id = TEE_IMPL_ID_OPTEE,
+ .impl_caps = TEE_OPTEE_CAP_TZ,
+ .gen_caps = TEE_GEN_CAP_GP,
+ };
+ *vers = v;
+}
+
+static int optee_open(struct tee_context *ctx)
+{
+ struct optee_context_data *ctxdata;
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+
+ ctxdata = kzalloc(sizeof(*ctxdata), GFP_KERNEL);
+ if (!ctxdata)
+ return -ENOMEM;
+
+ if (teedev == optee->supp_teedev) {
+ bool busy = true;
+
+ mutex_lock(&optee->supp.ctx_mutex);
+ if (!optee->supp.ctx) {
+ busy = false;
+ optee->supp.ctx = ctx;
+ }
+ mutex_unlock(&optee->supp.ctx_mutex);
+ if (busy) {
+ kfree(ctxdata);
+ return -EBUSY;
+ }
+ }
+
+ mutex_init(&ctxdata->mutex);
+ INIT_LIST_HEAD(&ctxdata->sess_list);
+
+ ctx->data = ctxdata;
+ return 0;
+}
+
+static void optee_release(struct tee_context *ctx)
+{
+ struct optee_context_data *ctxdata = ctx->data;
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct tee_shm *shm;
+ struct optee_msg_arg *arg = NULL;
+ phys_addr_t parg;
+ struct optee_session *sess;
+ struct optee_session *sess_tmp;
+
+ if (!ctxdata)
+ return;
+
+ shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg), TEE_SHM_MAPPED);
+ if (!IS_ERR(shm)) {
+ arg = tee_shm_get_va(shm, 0);
+ /*
+ * If va2pa fails for some reason, we can't call
+ * optee_close_session(), only free the memory. Secure OS
+ * will leak sessions and finally refuse more sessions, but
+ * we will at least let normal world reclaim its memory.
+ */
+ if (!IS_ERR(arg))
+ tee_shm_va2pa(shm, arg, &parg);
+ }
+
+ list_for_each_entry_safe(sess, sess_tmp, &ctxdata->sess_list,
+ list_node) {
+ list_del(&sess->list_node);
+ if (!IS_ERR_OR_NULL(arg)) {
+ memset(arg, 0, sizeof(*arg));
+ arg->cmd = OPTEE_MSG_CMD_CLOSE_SESSION;
+ arg->session = sess->session_id;
+ optee_do_call_with_arg(ctx, parg);
+ }
+ kfree(sess);
+ }
+ kfree(ctxdata);
+
+ if (!IS_ERR(shm))
+ tee_shm_free(shm);
+
+ ctx->data = NULL;
+
+ if (teedev == optee->supp_teedev) {
+ mutex_lock(&optee->supp.ctx_mutex);
+ optee->supp.ctx = NULL;
+ mutex_unlock(&optee->supp.ctx_mutex);
+ }
+}
+
+static struct tee_driver_ops optee_ops = {
+ .get_version = optee_get_version,
+ .open = optee_open,
+ .release = optee_release,
+ .open_session = optee_open_session,
+ .close_session = optee_close_session,
+ .invoke_func = optee_invoke_func,
+ .cancel_req = optee_cancel_req,
+};
+
+static struct tee_desc optee_desc = {
+ .name = DRIVER_NAME "-clnt",
+ .ops = &optee_ops,
+ .owner = THIS_MODULE,
+};
+
+static struct tee_driver_ops optee_supp_ops = {
+ .get_version = optee_get_version,
+ .open = optee_open,
+ .release = optee_release,
+ .supp_recv = optee_supp_recv,
+ .supp_send = optee_supp_send,
+};
+
+static struct tee_desc optee_supp_desc = {
+ .name = DRIVER_NAME "-supp",
+ .ops = &optee_supp_ops,
+ .owner = THIS_MODULE,
+ .flags = TEE_DESC_PRIVILEGED,
+};
+
+static bool optee_msg_api_uid_is_optee_api(optee_invoke_fn *invoke_fn)
+{
+ struct arm_smccc_res res;
+
+ invoke_fn(OPTEE_SMC_CALLS_UID, 0, 0, 0, 0, 0, 0, 0, &res);
+
+ if (res.a0 == OPTEE_MSG_UID_0 && res.a1 == OPTEE_MSG_UID_1 &&
+ res.a2 == OPTEE_MSG_UID_2 && res.a3 == OPTEE_MSG_UID_3)
+ return true;
+ return false;
+}
+
+static bool optee_msg_api_revision_is_compatible(optee_invoke_fn *invoke_fn)
+{
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_calls_revision_result result;
+ } res;
+
+ invoke_fn(OPTEE_SMC_CALLS_REVISION, 0, 0, 0, 0, 0, 0, 0, &res.smccc);
+
+ if (res.result.major == OPTEE_MSG_REVISION_MAJOR &&
+ (int)res.result.minor >= OPTEE_MSG_REVISION_MINOR)
+ return true;
+ return false;
+}
+
+static bool optee_msg_exchange_capabilities(optee_invoke_fn *invoke_fn,
+ u32 *sec_caps)
+{
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_exchange_capabilities_result result;
+ } res;
+ u32 a1 = 0;
+
+ /*
+ * TODO This isn't enough to tell if it's UP system (from kernel
+ * point of view) or not, is_smp() returns the the information
+ * needed, but can't be called directly from here.
+ */
+ if (!IS_ENABLED(CONFIG_SMP) || nr_cpu_ids == 1)
+ a1 |= OPTEE_SMC_NSEC_CAP_UNIPROCESSOR;
+
+ invoke_fn(OPTEE_SMC_EXCHANGE_CAPABILITIES, a1, 0, 0, 0, 0, 0, 0,
+ &res.smccc);
+
+ if (res.result.status != OPTEE_SMC_RETURN_OK)
+ return false;
+
+ *sec_caps = res.result.capabilities;
+ return true;
+}
+
+static struct tee_shm_pool *
+optee_config_shm_memremap(optee_invoke_fn *invoke_fn, void **memremaped_shm)
+{
+ union {
+ struct arm_smccc_res smccc;
+ struct optee_smc_get_shm_config_result result;
+ } res;
+ struct tee_shm_pool *pool;
+ unsigned long vaddr;
+ phys_addr_t paddr;
+ size_t size;
+ phys_addr_t begin;
+ phys_addr_t end;
+ void *va;
+ struct tee_shm_pool_mem_info priv_info;
+ struct tee_shm_pool_mem_info dmabuf_info;
+
+ invoke_fn(OPTEE_SMC_GET_SHM_CONFIG, 0, 0, 0, 0, 0, 0, 0, &res.smccc);
+ if (res.result.status != OPTEE_SMC_RETURN_OK) {
+ pr_info("shm service not available\n");
+ return ERR_PTR(-ENOENT);
+ }
+
+ if (res.result.settings != OPTEE_SMC_SHM_CACHED) {
+ pr_err("only normal cached shared memory supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ begin = roundup(res.result.start, PAGE_SIZE);
+ end = rounddown(res.result.start + res.result.size, PAGE_SIZE);
+ paddr = begin;
+ size = end - begin;
+
+ if (size < 2 * OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE) {
+ pr_err("too small shared memory area\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ va = memremap(paddr, size, MEMREMAP_WB);
+ if (!va) {
+ pr_err("shared memory ioremap failed\n");
+ return ERR_PTR(-EINVAL);
+ }
+ vaddr = (unsigned long)va;
+
+ priv_info.vaddr = vaddr;
+ priv_info.paddr = paddr;
+ priv_info.size = OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE;
+ dmabuf_info.vaddr = vaddr + OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE;
+ dmabuf_info.paddr = paddr + OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE;
+ dmabuf_info.size = size - OPTEE_SHM_NUM_PRIV_PAGES * PAGE_SIZE;
+
+ pool = tee_shm_pool_alloc_res_mem(&priv_info, &dmabuf_info);
+ if (IS_ERR(pool)) {
+ memunmap(va);
+ goto out;
+ }
+
+ *memremaped_shm = va;
+out:
+ return pool;
+}
+
+/* Simple wrapper functions to be able to use a function pointer */
+static void optee_smccc_smc(unsigned long a0, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ unsigned long a4, unsigned long a5,
+ unsigned long a6, unsigned long a7,
+ struct arm_smccc_res *res)
+{
+ arm_smccc_smc(a0, a1, a2, a3, a4, a5, a6, a7, res);
+}
+
+static void optee_smccc_hvc(unsigned long a0, unsigned long a1,
+ unsigned long a2, unsigned long a3,
+ unsigned long a4, unsigned long a5,
+ unsigned long a6, unsigned long a7,
+ struct arm_smccc_res *res)
+{
+ arm_smccc_hvc(a0, a1, a2, a3, a4, a5, a6, a7, res);
+}
+
+static optee_invoke_fn *get_invoke_func(struct device_node *np)
+{
+ const char *method;
+
+ pr_info("probing for conduit method from DT.\n");
+
+ if (of_property_read_string(np, "method", &method)) {
+ pr_warn("missing \"method\" property\n");
+ return ERR_PTR(-ENXIO);
+ }
+
+ if (!strcmp("hvc", method))
+ return optee_smccc_hvc;
+ else if (!strcmp("smc", method))
+ return optee_smccc_smc;
+
+ pr_warn("invalid \"method\" property: %s\n", method);
+ return ERR_PTR(-EINVAL);
+}
+
+static struct optee *optee_probe(struct device_node *np)
+{
+ optee_invoke_fn *invoke_fn;
+ struct tee_shm_pool *pool;
+ struct optee *optee = NULL;
+ void *memremaped_shm = NULL;
+ struct tee_device *teedev;
+ u32 sec_caps;
+ int rc;
+
+ invoke_fn = get_invoke_func(np);
+ if (IS_ERR(invoke_fn))
+ return (void *)invoke_fn;
+
+ if (!optee_msg_api_uid_is_optee_api(invoke_fn)) {
+ pr_warn("api uid mismatch\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!optee_msg_api_revision_is_compatible(invoke_fn)) {
+ pr_warn("api revision mismatch\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!optee_msg_exchange_capabilities(invoke_fn, &sec_caps)) {
+ pr_warn("capabilities mismatch\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ /*
+ * We have no other option for shared memory, if secure world
+ * doesn't have any reserved memory we can use we can't continue.
+ */
+ if (!(sec_caps & OPTEE_SMC_SEC_CAP_HAVE_RESERVED_SHM))
+ return ERR_PTR(-EINVAL);
+
+ pool = optee_config_shm_memremap(invoke_fn, &memremaped_shm);
+ if (IS_ERR(pool))
+ return (void *)pool;
+
+ optee = kzalloc(sizeof(*optee), GFP_KERNEL);
+ if (!optee) {
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ optee->invoke_fn = invoke_fn;
+
+ teedev = tee_device_alloc(&optee_desc, NULL, pool, optee);
+ if (IS_ERR(teedev)) {
+ rc = PTR_ERR(teedev);
+ goto err;
+ }
+ optee->teedev = teedev;
+
+ teedev = tee_device_alloc(&optee_supp_desc, NULL, pool, optee);
+ if (IS_ERR(teedev)) {
+ rc = PTR_ERR(teedev);
+ goto err;
+ }
+ optee->supp_teedev = teedev;
+
+ rc = tee_device_register(optee->teedev);
+ if (rc)
+ goto err;
+
+ rc = tee_device_register(optee->supp_teedev);
+ if (rc)
+ goto err;
+
+ mutex_init(&optee->call_queue.mutex);
+ INIT_LIST_HEAD(&optee->call_queue.waiters);
+ optee_wait_queue_init(&optee->wait_queue);
+ optee_supp_init(&optee->supp);
+ optee->memremaped_shm = memremaped_shm;
+ optee->pool = pool;
+
+ optee_enable_shm_cache(optee);
+
+ pr_info("initialized driver\n");
+ return optee;
+err:
+ if (optee) {
+ /*
+ * tee_device_unregister() is safe to call even if the
+ * devices hasn't been registered with
+ * tee_device_register() yet.
+ */
+ tee_device_unregister(optee->supp_teedev);
+ tee_device_unregister(optee->teedev);
+ kfree(optee);
+ }
+ if (pool)
+ tee_shm_pool_free(pool);
+ if (memremaped_shm)
+ memunmap(memremaped_shm);
+ return ERR_PTR(rc);
+}
+
+static void optee_remove(struct optee *optee)
+{
+ /*
+ * Ask OP-TEE to free all cached shared memory objects to decrease
+ * reference counters and also avoid wild pointers in secure world
+ * into the old shared memory range.
+ */
+ optee_disable_shm_cache(optee);
+
+ /*
+ * The two devices has to be unregistered before we can free the
+ * other resources.
+ */
+ tee_device_unregister(optee->supp_teedev);
+ tee_device_unregister(optee->teedev);
+
+ tee_shm_pool_free(optee->pool);
+ if (optee->memremaped_shm)
+ memunmap(optee->memremaped_shm);
+ optee_wait_queue_exit(&optee->wait_queue);
+ optee_supp_uninit(&optee->supp);
+ mutex_destroy(&optee->call_queue.mutex);
+
+ kfree(optee);
+}
+
+static const struct of_device_id optee_match[] = {
+ { .compatible = "linaro,optee-tz" },
+ {},
+};
+
+static struct optee *optee_svc;
+
+static int __init optee_driver_init(void)
+{
+ struct device_node *fw_np;
+ struct device_node *np;
+ struct optee *optee;
+
+ /* Node is supposed to be below /firmware */
+ fw_np = of_find_node_by_name(NULL, "firmware");
+ if (!fw_np)
+ return -ENODEV;
+
+ np = of_find_matching_node(fw_np, optee_match);
+ of_node_put(fw_np);
+ if (!np)
+ return -ENODEV;
+
+ optee = optee_probe(np);
+ of_node_put(np);
+
+ if (IS_ERR(optee))
+ return PTR_ERR(optee);
+
+ optee_svc = optee;
+
+ return 0;
+}
+module_init(optee_driver_init);
+
+static void __exit optee_driver_exit(void)
+{
+ struct optee *optee = optee_svc;
+
+ optee_svc = NULL;
+ if (optee)
+ optee_remove(optee);
+}
+module_exit(optee_driver_exit);
+
+MODULE_AUTHOR("Linaro");
+MODULE_DESCRIPTION("OP-TEE driver");
+MODULE_SUPPORTED_DEVICE("");
+MODULE_VERSION("1.0");
+MODULE_LICENSE("GPL v2");
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _OPTEE_MSG_H
+#define _OPTEE_MSG_H
+
+#include <linux/bitops.h>
+#include <linux/types.h>
+
+/*
+ * This file defines the OP-TEE message protocol used to communicate
+ * with an instance of OP-TEE running in secure world.
+ *
+ * This file is divided into three sections.
+ * 1. Formatting of messages.
+ * 2. Requests from normal world
+ * 3. Requests from secure world, Remote Procedure Call (RPC), handled by
+ * tee-supplicant.
+ */
+
+/*****************************************************************************
+ * Part 1 - formatting of messages
+ *****************************************************************************/
+
+#define OPTEE_MSG_ATTR_TYPE_NONE 0x0
+#define OPTEE_MSG_ATTR_TYPE_VALUE_INPUT 0x1
+#define OPTEE_MSG_ATTR_TYPE_VALUE_OUTPUT 0x2
+#define OPTEE_MSG_ATTR_TYPE_VALUE_INOUT 0x3
+#define OPTEE_MSG_ATTR_TYPE_RMEM_INPUT 0x5
+#define OPTEE_MSG_ATTR_TYPE_RMEM_OUTPUT 0x6
+#define OPTEE_MSG_ATTR_TYPE_RMEM_INOUT 0x7
+#define OPTEE_MSG_ATTR_TYPE_TMEM_INPUT 0x9
+#define OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT 0xa
+#define OPTEE_MSG_ATTR_TYPE_TMEM_INOUT 0xb
+
+#define OPTEE_MSG_ATTR_TYPE_MASK GENMASK(7, 0)
+
+/*
+ * Meta parameter to be absorbed by the Secure OS and not passed
+ * to the Trusted Application.
+ *
+ * Currently only used with OPTEE_MSG_CMD_OPEN_SESSION.
+ */
+#define OPTEE_MSG_ATTR_META BIT(8)
+
+/*
+ * The temporary shared memory object is not physically contigous and this
+ * temp memref is followed by another fragment until the last temp memref
+ * that doesn't have this bit set.
+ */
+#define OPTEE_MSG_ATTR_FRAGMENT BIT(9)
+
+/*
+ * Memory attributes for caching passed with temp memrefs. The actual value
+ * used is defined outside the message protocol with the exception of
+ * OPTEE_MSG_ATTR_CACHE_PREDEFINED which means the attributes already
+ * defined for the memory range should be used. If optee_smc.h is used as
+ * bearer of this protocol OPTEE_SMC_SHM_* is used for values.
+ */
+#define OPTEE_MSG_ATTR_CACHE_SHIFT 16
+#define OPTEE_MSG_ATTR_CACHE_MASK GENMASK(2, 0)
+#define OPTEE_MSG_ATTR_CACHE_PREDEFINED 0
+
+/*
+ * Same values as TEE_LOGIN_* from TEE Internal API
+ */
+#define OPTEE_MSG_LOGIN_PUBLIC 0x00000000
+#define OPTEE_MSG_LOGIN_USER 0x00000001
+#define OPTEE_MSG_LOGIN_GROUP 0x00000002
+#define OPTEE_MSG_LOGIN_APPLICATION 0x00000004
+#define OPTEE_MSG_LOGIN_APPLICATION_USER 0x00000005
+#define OPTEE_MSG_LOGIN_APPLICATION_GROUP 0x00000006
+
+/**
+ * struct optee_msg_param_tmem - temporary memory reference parameter
+ * @buf_ptr: Address of the buffer
+ * @size: Size of the buffer
+ * @shm_ref: Temporary shared memory reference, pointer to a struct tee_shm
+ *
+ * Secure and normal world communicates pointers as physical address
+ * instead of the virtual address. This is because secure and normal world
+ * have completely independent memory mapping. Normal world can even have a
+ * hypervisor which need to translate the guest physical address (AKA IPA
+ * in ARM documentation) to a real physical address before passing the
+ * structure to secure world.
+ */
+struct optee_msg_param_tmem {
+ u64 buf_ptr;
+ u64 size;
+ u64 shm_ref;
+};
+
+/**
+ * struct optee_msg_param_rmem - registered memory reference parameter
+ * @offs: Offset into shared memory reference
+ * @size: Size of the buffer
+ * @shm_ref: Shared memory reference, pointer to a struct tee_shm
+ */
+struct optee_msg_param_rmem {
+ u64 offs;
+ u64 size;
+ u64 shm_ref;
+};
+
+/**
+ * struct optee_msg_param_value - opaque value parameter
+ *
+ * Value parameters are passed unchecked between normal and secure world.
+ */
+struct optee_msg_param_value {
+ u64 a;
+ u64 b;
+ u64 c;
+};
+
+/**
+ * struct optee_msg_param - parameter used together with struct optee_msg_arg
+ * @attr: attributes
+ * @tmem: parameter by temporary memory reference
+ * @rmem: parameter by registered memory reference
+ * @value: parameter by opaque value
+ *
+ * @attr & OPTEE_MSG_ATTR_TYPE_MASK indicates if tmem, rmem or value is used in
+ * the union. OPTEE_MSG_ATTR_TYPE_VALUE_* indicates value,
+ * OPTEE_MSG_ATTR_TYPE_TMEM_* indicates tmem and
+ * OPTEE_MSG_ATTR_TYPE_RMEM_* indicates rmem.
+ * OPTEE_MSG_ATTR_TYPE_NONE indicates that none of the members are used.
+ */
+struct optee_msg_param {
+ u64 attr;
+ union {
+ struct optee_msg_param_tmem tmem;
+ struct optee_msg_param_rmem rmem;
+ struct optee_msg_param_value value;
+ } u;
+};
+
+/**
+ * struct optee_msg_arg - call argument
+ * @cmd: Command, one of OPTEE_MSG_CMD_* or OPTEE_MSG_RPC_CMD_*
+ * @func: Trusted Application function, specific to the Trusted Application,
+ * used if cmd == OPTEE_MSG_CMD_INVOKE_COMMAND
+ * @session: In parameter for all OPTEE_MSG_CMD_* except
+ * OPTEE_MSG_CMD_OPEN_SESSION where it's an output parameter instead
+ * @cancel_id: Cancellation id, a unique value to identify this request
+ * @ret: return value
+ * @ret_origin: origin of the return value
+ * @num_params: number of parameters supplied to the OS Command
+ * @params: the parameters supplied to the OS Command
+ *
+ * All normal calls to Trusted OS uses this struct. If cmd requires further
+ * information than what these field holds it can be passed as a parameter
+ * tagged as meta (setting the OPTEE_MSG_ATTR_META bit in corresponding
+ * attrs field). All parameters tagged as meta has to come first.
+ *
+ * Temp memref parameters can be fragmented if supported by the Trusted OS
+ * (when optee_smc.h is bearer of this protocol this is indicated with
+ * OPTEE_SMC_SEC_CAP_UNREGISTERED_SHM). If a logical memref parameter is
+ * fragmented then has all but the last fragment the
+ * OPTEE_MSG_ATTR_FRAGMENT bit set in attrs. Even if a memref is fragmented
+ * it will still be presented as a single logical memref to the Trusted
+ * Application.
+ */
+struct optee_msg_arg {
+ u32 cmd;
+ u32 func;
+ u32 session;
+ u32 cancel_id;
+ u32 pad;
+ u32 ret;
+ u32 ret_origin;
+ u32 num_params;
+
+ /* num_params tells the actual number of element in params */
+ struct optee_msg_param params[0];
+};
+
+/**
+ * OPTEE_MSG_GET_ARG_SIZE - return size of struct optee_msg_arg
+ *
+ * @num_params: Number of parameters embedded in the struct optee_msg_arg
+ *
+ * Returns the size of the struct optee_msg_arg together with the number
+ * of embedded parameters.
+ */
+#define OPTEE_MSG_GET_ARG_SIZE(num_params) \
+ (sizeof(struct optee_msg_arg) + \
+ sizeof(struct optee_msg_param) * (num_params))
+
+/*****************************************************************************
+ * Part 2 - requests from normal world
+ *****************************************************************************/
+
+/*
+ * Return the following UID if using API specified in this file without
+ * further extensions:
+ * 384fb3e0-e7f8-11e3-af63-0002a5d5c51b.
+ * Represented in 4 32-bit words in OPTEE_MSG_UID_0, OPTEE_MSG_UID_1,
+ * OPTEE_MSG_UID_2, OPTEE_MSG_UID_3.
+ */
+#define OPTEE_MSG_UID_0 0x384fb3e0
+#define OPTEE_MSG_UID_1 0xe7f811e3
+#define OPTEE_MSG_UID_2 0xaf630002
+#define OPTEE_MSG_UID_3 0xa5d5c51b
+#define OPTEE_MSG_FUNCID_CALLS_UID 0xFF01
+
+/*
+ * Returns 2.0 if using API specified in this file without further
+ * extensions. Represented in 2 32-bit words in OPTEE_MSG_REVISION_MAJOR
+ * and OPTEE_MSG_REVISION_MINOR
+ */
+#define OPTEE_MSG_REVISION_MAJOR 2
+#define OPTEE_MSG_REVISION_MINOR 0
+#define OPTEE_MSG_FUNCID_CALLS_REVISION 0xFF03
+
+/*
+ * Get UUID of Trusted OS.
+ *
+ * Used by non-secure world to figure out which Trusted OS is installed.
+ * Note that returned UUID is the UUID of the Trusted OS, not of the API.
+ *
+ * Returns UUID in 4 32-bit words in the same way as
+ * OPTEE_MSG_FUNCID_CALLS_UID described above.
+ */
+#define OPTEE_MSG_OS_OPTEE_UUID_0 0x486178e0
+#define OPTEE_MSG_OS_OPTEE_UUID_1 0xe7f811e3
+#define OPTEE_MSG_OS_OPTEE_UUID_2 0xbc5e0002
+#define OPTEE_MSG_OS_OPTEE_UUID_3 0xa5d5c51b
+#define OPTEE_MSG_FUNCID_GET_OS_UUID 0x0000
+
+/*
+ * Get revision of Trusted OS.
+ *
+ * Used by non-secure world to figure out which version of the Trusted OS
+ * is installed. Note that the returned revision is the revision of the
+ * Trusted OS, not of the API.
+ *
+ * Returns revision in 2 32-bit words in the same way as
+ * OPTEE_MSG_CALLS_REVISION described above.
+ */
+#define OPTEE_MSG_FUNCID_GET_OS_REVISION 0x0001
+
+/*
+ * Do a secure call with struct optee_msg_arg as argument
+ * The OPTEE_MSG_CMD_* below defines what goes in struct optee_msg_arg::cmd
+ *
+ * OPTEE_MSG_CMD_OPEN_SESSION opens a session to a Trusted Application.
+ * The first two parameters are tagged as meta, holding two value
+ * parameters to pass the following information:
+ * param[0].u.value.a-b uuid of Trusted Application
+ * param[1].u.value.a-b uuid of Client
+ * param[1].u.value.c Login class of client OPTEE_MSG_LOGIN_*
+ *
+ * OPTEE_MSG_CMD_INVOKE_COMMAND invokes a command a previously opened
+ * session to a Trusted Application. struct optee_msg_arg::func is Trusted
+ * Application function, specific to the Trusted Application.
+ *
+ * OPTEE_MSG_CMD_CLOSE_SESSION closes a previously opened session to
+ * Trusted Application.
+ *
+ * OPTEE_MSG_CMD_CANCEL cancels a currently invoked command.
+ *
+ * OPTEE_MSG_CMD_REGISTER_SHM registers a shared memory reference. The
+ * information is passed as:
+ * [in] param[0].attr OPTEE_MSG_ATTR_TYPE_TMEM_INPUT
+ * [| OPTEE_MSG_ATTR_FRAGMENT]
+ * [in] param[0].u.tmem.buf_ptr physical address (of first fragment)
+ * [in] param[0].u.tmem.size size (of first fragment)
+ * [in] param[0].u.tmem.shm_ref holds shared memory reference
+ * ...
+ * The shared memory can optionally be fragmented, temp memrefs can follow
+ * each other with all but the last with the OPTEE_MSG_ATTR_FRAGMENT bit set.
+ *
+ * OPTEE_MSG_CMD_UNREGISTER_SHM unregisteres a previously registered shared
+ * memory reference. The information is passed as:
+ * [in] param[0].attr OPTEE_MSG_ATTR_TYPE_RMEM_INPUT
+ * [in] param[0].u.rmem.shm_ref holds shared memory reference
+ * [in] param[0].u.rmem.offs 0
+ * [in] param[0].u.rmem.size 0
+ */
+#define OPTEE_MSG_CMD_OPEN_SESSION 0
+#define OPTEE_MSG_CMD_INVOKE_COMMAND 1
+#define OPTEE_MSG_CMD_CLOSE_SESSION 2
+#define OPTEE_MSG_CMD_CANCEL 3
+#define OPTEE_MSG_CMD_REGISTER_SHM 4
+#define OPTEE_MSG_CMD_UNREGISTER_SHM 5
+#define OPTEE_MSG_FUNCID_CALL_WITH_ARG 0x0004
+
+/*****************************************************************************
+ * Part 3 - Requests from secure world, RPC
+ *****************************************************************************/
+
+/*
+ * All RPC is done with a struct optee_msg_arg as bearer of information,
+ * struct optee_msg_arg::arg holds values defined by OPTEE_MSG_RPC_CMD_* below
+ *
+ * RPC communication with tee-supplicant is reversed compared to normal
+ * client communication desribed above. The supplicant receives requests
+ * and sends responses.
+ */
+
+/*
+ * Load a TA into memory, defined in tee-supplicant
+ */
+#define OPTEE_MSG_RPC_CMD_LOAD_TA 0
+
+/*
+ * Reserved
+ */
+#define OPTEE_MSG_RPC_CMD_RPMB 1
+
+/*
+ * File system access, defined in tee-supplicant
+ */
+#define OPTEE_MSG_RPC_CMD_FS 2
+
+/*
+ * Get time
+ *
+ * Returns number of seconds and nano seconds since the Epoch,
+ * 1970-01-01 00:00:00 +0000 (UTC).
+ *
+ * [out] param[0].u.value.a Number of seconds
+ * [out] param[0].u.value.b Number of nano seconds.
+ */
+#define OPTEE_MSG_RPC_CMD_GET_TIME 3
+
+/*
+ * Wait queue primitive, helper for secure world to implement a wait queue.
+ *
+ * If secure world need to wait for a secure world mutex it issues a sleep
+ * request instead of spinning in secure world. Conversely is a wakeup
+ * request issued when a secure world mutex with a thread waiting thread is
+ * unlocked.
+ *
+ * Waiting on a key
+ * [in] param[0].u.value.a OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP
+ * [in] param[0].u.value.b wait key
+ *
+ * Waking up a key
+ * [in] param[0].u.value.a OPTEE_MSG_RPC_WAIT_QUEUE_WAKEUP
+ * [in] param[0].u.value.b wakeup key
+ */
+#define OPTEE_MSG_RPC_CMD_WAIT_QUEUE 4
+#define OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP 0
+#define OPTEE_MSG_RPC_WAIT_QUEUE_WAKEUP 1
+
+/*
+ * Suspend execution
+ *
+ * [in] param[0].value .a number of milliseconds to suspend
+ */
+#define OPTEE_MSG_RPC_CMD_SUSPEND 5
+
+/*
+ * Allocate a piece of shared memory
+ *
+ * Shared memory can optionally be fragmented, to support that additional
+ * spare param entries are allocated to make room for eventual fragments.
+ * The spare param entries has .attr = OPTEE_MSG_ATTR_TYPE_NONE when
+ * unused. All returned temp memrefs except the last should have the
+ * OPTEE_MSG_ATTR_FRAGMENT bit set in the attr field.
+ *
+ * [in] param[0].u.value.a type of memory one of
+ * OPTEE_MSG_RPC_SHM_TYPE_* below
+ * [in] param[0].u.value.b requested size
+ * [in] param[0].u.value.c required alignment
+ *
+ * [out] param[0].u.tmem.buf_ptr physical address (of first fragment)
+ * [out] param[0].u.tmem.size size (of first fragment)
+ * [out] param[0].u.tmem.shm_ref shared memory reference
+ * ...
+ * [out] param[n].u.tmem.buf_ptr physical address
+ * [out] param[n].u.tmem.size size
+ * [out] param[n].u.tmem.shm_ref shared memory reference (same value
+ * as in param[n-1].u.tmem.shm_ref)
+ */
+#define OPTEE_MSG_RPC_CMD_SHM_ALLOC 6
+/* Memory that can be shared with a non-secure user space application */
+#define OPTEE_MSG_RPC_SHM_TYPE_APPL 0
+/* Memory only shared with non-secure kernel */
+#define OPTEE_MSG_RPC_SHM_TYPE_KERNEL 1
+
+/*
+ * Free shared memory previously allocated with OPTEE_MSG_RPC_CMD_SHM_ALLOC
+ *
+ * [in] param[0].u.value.a type of memory one of
+ * OPTEE_MSG_RPC_SHM_TYPE_* above
+ * [in] param[0].u.value.b value of shared memory reference
+ * returned in param[0].u.tmem.shm_ref
+ * above
+ */
+#define OPTEE_MSG_RPC_CMD_SHM_FREE 7
+
+#endif /* _OPTEE_MSG_H */
--- /dev/null
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef OPTEE_PRIVATE_H
+#define OPTEE_PRIVATE_H
+
+#include <linux/arm-smccc.h>
+#include <linux/semaphore.h>
+#include <linux/tee_drv.h>
+#include <linux/types.h>
+#include "optee_msg.h"
+
+#define OPTEE_MAX_ARG_SIZE 1024
+
+/* Some Global Platform error codes used in this driver */
+#define TEEC_SUCCESS 0x00000000
+#define TEEC_ERROR_BAD_PARAMETERS 0xFFFF0006
+#define TEEC_ERROR_COMMUNICATION 0xFFFF000E
+#define TEEC_ERROR_OUT_OF_MEMORY 0xFFFF000C
+
+#define TEEC_ORIGIN_COMMS 0x00000002
+
+typedef void (optee_invoke_fn)(unsigned long, unsigned long, unsigned long,
+ unsigned long, unsigned long, unsigned long,
+ unsigned long, unsigned long,
+ struct arm_smccc_res *);
+
+struct optee_call_queue {
+ /* Serializes access to this struct */
+ struct mutex mutex;
+ struct list_head waiters;
+};
+
+struct optee_wait_queue {
+ /* Serializes access to this struct */
+ struct mutex mu;
+ struct list_head db;
+};
+
+/**
+ * struct optee_supp - supplicant synchronization struct
+ * @ctx the context of current connected supplicant.
+ * if !NULL the supplicant device is available for use,
+ * else busy
+ * @ctx_mutex: held while accessing @ctx
+ * @func: supplicant function id to call
+ * @ret: call return value
+ * @num_params: number of elements in @param
+ * @param: parameters for @func
+ * @req_posted: if true, a request has been posted to the supplicant
+ * @supp_next_send: if true, next step is for supplicant to send response
+ * @thrd_mutex: held by the thread doing a request to supplicant
+ * @supp_mutex: held by supplicant while operating on this struct
+ * @data_to_supp: supplicant is waiting on this for next request
+ * @data_from_supp: requesting thread is waiting on this to get the result
+ */
+struct optee_supp {
+ struct tee_context *ctx;
+ /* Serializes access of ctx */
+ struct mutex ctx_mutex;
+
+ u32 func;
+ u32 ret;
+ size_t num_params;
+ struct tee_param *param;
+
+ bool req_posted;
+ bool supp_next_send;
+ /* Serializes access to this struct for requesting thread */
+ struct mutex thrd_mutex;
+ /* Serializes access to this struct for supplicant threads */
+ struct mutex supp_mutex;
+ struct completion data_to_supp;
+ struct completion data_from_supp;
+};
+
+/**
+ * struct optee - main service struct
+ * @supp_teedev: supplicant device
+ * @teedev: client device
+ * @invoke_fn: function to issue smc or hvc
+ * @call_queue: queue of threads waiting to call @invoke_fn
+ * @wait_queue: queue of threads from secure world waiting for a
+ * secure world sync object
+ * @supp: supplicant synchronization struct for RPC to supplicant
+ * @pool: shared memory pool
+ * @memremaped_shm virtual address of memory in shared memory pool
+ */
+struct optee {
+ struct tee_device *supp_teedev;
+ struct tee_device *teedev;
+ optee_invoke_fn *invoke_fn;
+ struct optee_call_queue call_queue;
+ struct optee_wait_queue wait_queue;
+ struct optee_supp supp;
+ struct tee_shm_pool *pool;
+ void *memremaped_shm;
+};
+
+struct optee_session {
+ struct list_head list_node;
+ u32 session_id;
+};
+
+struct optee_context_data {
+ /* Serializes access to this struct */
+ struct mutex mutex;
+ struct list_head sess_list;
+};
+
+struct optee_rpc_param {
+ u32 a0;
+ u32 a1;
+ u32 a2;
+ u32 a3;
+ u32 a4;
+ u32 a5;
+ u32 a6;
+ u32 a7;
+};
+
+void optee_handle_rpc(struct tee_context *ctx, struct optee_rpc_param *param);
+
+void optee_wait_queue_init(struct optee_wait_queue *wq);
+void optee_wait_queue_exit(struct optee_wait_queue *wq);
+
+u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
+ struct tee_param *param);
+
+int optee_supp_read(struct tee_context *ctx, void __user *buf, size_t len);
+int optee_supp_write(struct tee_context *ctx, void __user *buf, size_t len);
+void optee_supp_init(struct optee_supp *supp);
+void optee_supp_uninit(struct optee_supp *supp);
+
+int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
+ struct tee_param *param);
+int optee_supp_send(struct tee_context *ctx, u32 ret, u32 num_params,
+ struct tee_param *param);
+
+u32 optee_do_call_with_arg(struct tee_context *ctx, phys_addr_t parg);
+int optee_open_session(struct tee_context *ctx,
+ struct tee_ioctl_open_session_arg *arg,
+ struct tee_param *param);
+int optee_close_session(struct tee_context *ctx, u32 session);
+int optee_invoke_func(struct tee_context *ctx, struct tee_ioctl_invoke_arg *arg,
+ struct tee_param *param);
+int optee_cancel_req(struct tee_context *ctx, u32 cancel_id, u32 session);
+
+void optee_enable_shm_cache(struct optee *optee);
+void optee_disable_shm_cache(struct optee *optee);
+
+int optee_from_msg_param(struct tee_param *params, size_t num_params,
+ const struct optee_msg_param *msg_params);
+int optee_to_msg_param(struct optee_msg_param *msg_params, size_t num_params,
+ const struct tee_param *params);
+
+/*
+ * Small helpers
+ */
+
+static inline void *reg_pair_to_ptr(u32 reg0, u32 reg1)
+{
+ return (void *)(unsigned long)(((u64)reg0 << 32) | reg1);
+}
+
+static inline void reg_pair_from_64(u32 *reg0, u32 *reg1, u64 val)
+{
+ *reg0 = val >> 32;
+ *reg1 = val;
+}
+
+#endif /*OPTEE_PRIVATE_H*/
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef OPTEE_SMC_H
+#define OPTEE_SMC_H
+
+#include <linux/arm-smccc.h>
+#include <linux/bitops.h>
+
+#define OPTEE_SMC_STD_CALL_VAL(func_num) \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS, (func_num))
+#define OPTEE_SMC_FAST_CALL_VAL(func_num) \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS, (func_num))
+
+/*
+ * Function specified by SMC Calling convention.
+ */
+#define OPTEE_SMC_FUNCID_CALLS_COUNT 0xFF00
+#define OPTEE_SMC_CALLS_COUNT \
+ ARM_SMCCC_CALL_VAL(OPTEE_SMC_FAST_CALL, SMCCC_SMC_32, \
+ SMCCC_OWNER_TRUSTED_OS_END, \
+ OPTEE_SMC_FUNCID_CALLS_COUNT)
+
+/*
+ * Normal cached memory (write-back), shareable for SMP systems and not
+ * shareable for UP systems.
+ */
+#define OPTEE_SMC_SHM_CACHED 1
+
+/*
+ * a0..a7 is used as register names in the descriptions below, on arm32
+ * that translates to r0..r7 and on arm64 to w0..w7. In both cases it's
+ * 32-bit registers.
+ */
+
+/*
+ * Function specified by SMC Calling convention
+ *
+ * Return one of the following UIDs if using API specified in this file
+ * without further extentions:
+ * 65cb6b93-af0c-4617-8ed6-644a8d1140f8
+ * see also OPTEE_SMC_UID_* in optee_msg.h
+ */
+#define OPTEE_SMC_FUNCID_CALLS_UID OPTEE_MSG_FUNCID_CALLS_UID
+#define OPTEE_SMC_CALLS_UID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS_END, \
+ OPTEE_SMC_FUNCID_CALLS_UID)
+
+/*
+ * Function specified by SMC Calling convention
+ *
+ * Returns 2.0 if using API specified in this file without further extentions.
+ * see also OPTEE_MSG_REVISION_* in optee_msg.h
+ */
+#define OPTEE_SMC_FUNCID_CALLS_REVISION OPTEE_MSG_FUNCID_CALLS_REVISION
+#define OPTEE_SMC_CALLS_REVISION \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_TRUSTED_OS_END, \
+ OPTEE_SMC_FUNCID_CALLS_REVISION)
+
+struct optee_smc_calls_revision_result {
+ unsigned long major;
+ unsigned long minor;
+ unsigned long reserved0;
+ unsigned long reserved1;
+};
+
+/*
+ * Get UUID of Trusted OS.
+ *
+ * Used by non-secure world to figure out which Trusted OS is installed.
+ * Note that returned UUID is the UUID of the Trusted OS, not of the API.
+ *
+ * Returns UUID in a0-4 in the same way as OPTEE_SMC_CALLS_UID
+ * described above.
+ */
+#define OPTEE_SMC_FUNCID_GET_OS_UUID OPTEE_MSG_FUNCID_GET_OS_UUID
+#define OPTEE_SMC_CALL_GET_OS_UUID \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_GET_OS_UUID)
+
+/*
+ * Get revision of Trusted OS.
+ *
+ * Used by non-secure world to figure out which version of the Trusted OS
+ * is installed. Note that the returned revision is the revision of the
+ * Trusted OS, not of the API.
+ *
+ * Returns revision in a0-1 in the same way as OPTEE_SMC_CALLS_REVISION
+ * described above.
+ */
+#define OPTEE_SMC_FUNCID_GET_OS_REVISION OPTEE_MSG_FUNCID_GET_OS_REVISION
+#define OPTEE_SMC_CALL_GET_OS_REVISION \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_GET_OS_REVISION)
+
+/*
+ * Call with struct optee_msg_arg as argument
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC*CALL_WITH_ARG
+ * a1 Upper 32bit of a 64bit physical pointer to a struct optee_msg_arg
+ * a2 Lower 32bit of a 64bit physical pointer to a struct optee_msg_arg
+ * a3 Cache settings, not used if physical pointer is in a predefined shared
+ * memory area else per OPTEE_SMC_SHM_*
+ * a4-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 Return value, OPTEE_SMC_RETURN_*
+ * a1-3 Not used
+ * a4-7 Preserved
+ *
+ * OPTEE_SMC_RETURN_ETHREAD_LIMIT return register usage:
+ * a0 Return value, OPTEE_SMC_RETURN_ETHREAD_LIMIT
+ * a1-3 Preserved
+ * a4-7 Preserved
+ *
+ * RPC return register usage:
+ * a0 Return value, OPTEE_SMC_RETURN_IS_RPC(val)
+ * a1-2 RPC parameters
+ * a3-7 Resume information, must be preserved
+ *
+ * Possible return values:
+ * OPTEE_SMC_RETURN_UNKNOWN_FUNCTION Trusted OS does not recognize this
+ * function.
+ * OPTEE_SMC_RETURN_OK Call completed, result updated in
+ * the previously supplied struct
+ * optee_msg_arg.
+ * OPTEE_SMC_RETURN_ETHREAD_LIMIT Number of Trusted OS threads exceeded,
+ * try again later.
+ * OPTEE_SMC_RETURN_EBADADDR Bad physcial pointer to struct
+ * optee_msg_arg.
+ * OPTEE_SMC_RETURN_EBADCMD Bad/unknown cmd in struct optee_msg_arg
+ * OPTEE_SMC_RETURN_IS_RPC() Call suspended by RPC call to normal
+ * world.
+ */
+#define OPTEE_SMC_FUNCID_CALL_WITH_ARG OPTEE_MSG_FUNCID_CALL_WITH_ARG
+#define OPTEE_SMC_CALL_WITH_ARG \
+ OPTEE_SMC_STD_CALL_VAL(OPTEE_SMC_FUNCID_CALL_WITH_ARG)
+
+/*
+ * Get Shared Memory Config
+ *
+ * Returns the Secure/Non-secure shared memory config.
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_GET_SHM_CONFIG
+ * a1-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Have config return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1 Physical address of start of SHM
+ * a2 Size of of SHM
+ * a3 Cache settings of memory, as defined by the
+ * OPTEE_SMC_SHM_* values above
+ * a4-7 Preserved
+ *
+ * Not available register usage:
+ * a0 OPTEE_SMC_RETURN_ENOTAVAIL
+ * a1-3 Not used
+ * a4-7 Preserved
+ */
+#define OPTEE_SMC_FUNCID_GET_SHM_CONFIG 7
+#define OPTEE_SMC_GET_SHM_CONFIG \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_GET_SHM_CONFIG)
+
+struct optee_smc_get_shm_config_result {
+ unsigned long status;
+ unsigned long start;
+ unsigned long size;
+ unsigned long settings;
+};
+
+/*
+ * Exchanges capabilities between normal world and secure world
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_EXCHANGE_CAPABILITIES
+ * a1 bitfield of normal world capabilities OPTEE_SMC_NSEC_CAP_*
+ * a2-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1 bitfield of secure world capabilities OPTEE_SMC_SEC_CAP_*
+ * a2-7 Preserved
+ *
+ * Error return register usage:
+ * a0 OPTEE_SMC_RETURN_ENOTAVAIL, can't use the capabilities from normal world
+ * a1 bitfield of secure world capabilities OPTEE_SMC_SEC_CAP_*
+ * a2-7 Preserved
+ */
+/* Normal world works as a uniprocessor system */
+#define OPTEE_SMC_NSEC_CAP_UNIPROCESSOR BIT(0)
+/* Secure world has reserved shared memory for normal world to use */
+#define OPTEE_SMC_SEC_CAP_HAVE_RESERVED_SHM BIT(0)
+/* Secure world can communicate via previously unregistered shared memory */
+#define OPTEE_SMC_SEC_CAP_UNREGISTERED_SHM BIT(1)
+#define OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES 9
+#define OPTEE_SMC_EXCHANGE_CAPABILITIES \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_EXCHANGE_CAPABILITIES)
+
+struct optee_smc_exchange_capabilities_result {
+ unsigned long status;
+ unsigned long capabilities;
+ unsigned long reserved0;
+ unsigned long reserved1;
+};
+
+/*
+ * Disable and empties cache of shared memory objects
+ *
+ * Secure world can cache frequently used shared memory objects, for
+ * example objects used as RPC arguments. When secure world is idle this
+ * function returns one shared memory reference to free. To disable the
+ * cache and free all cached objects this function has to be called until
+ * it returns OPTEE_SMC_RETURN_ENOTAVAIL.
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_DISABLE_SHM_CACHE
+ * a1-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1 Upper 32bit of a 64bit Shared memory cookie
+ * a2 Lower 32bit of a 64bit Shared memory cookie
+ * a3-7 Preserved
+ *
+ * Cache empty return register usage:
+ * a0 OPTEE_SMC_RETURN_ENOTAVAIL
+ * a1-7 Preserved
+ *
+ * Not idle return register usage:
+ * a0 OPTEE_SMC_RETURN_EBUSY
+ * a1-7 Preserved
+ */
+#define OPTEE_SMC_FUNCID_DISABLE_SHM_CACHE 10
+#define OPTEE_SMC_DISABLE_SHM_CACHE \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_DISABLE_SHM_CACHE)
+
+struct optee_smc_disable_shm_cache_result {
+ unsigned long status;
+ unsigned long shm_upper32;
+ unsigned long shm_lower32;
+ unsigned long reserved0;
+};
+
+/*
+ * Enable cache of shared memory objects
+ *
+ * Secure world can cache frequently used shared memory objects, for
+ * example objects used as RPC arguments. When secure world is idle this
+ * function returns OPTEE_SMC_RETURN_OK and the cache is enabled. If
+ * secure world isn't idle OPTEE_SMC_RETURN_EBUSY is returned.
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_ENABLE_SHM_CACHE
+ * a1-6 Not used
+ * a7 Hypervisor Client ID register
+ *
+ * Normal return register usage:
+ * a0 OPTEE_SMC_RETURN_OK
+ * a1-7 Preserved
+ *
+ * Not idle return register usage:
+ * a0 OPTEE_SMC_RETURN_EBUSY
+ * a1-7 Preserved
+ */
+#define OPTEE_SMC_FUNCID_ENABLE_SHM_CACHE 11
+#define OPTEE_SMC_ENABLE_SHM_CACHE \
+ OPTEE_SMC_FAST_CALL_VAL(OPTEE_SMC_FUNCID_ENABLE_SHM_CACHE)
+
+/*
+ * Resume from RPC (for example after processing an IRQ)
+ *
+ * Call register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC
+ * a1-3 Value of a1-3 when OPTEE_SMC_CALL_WITH_ARG returned
+ * OPTEE_SMC_RETURN_RPC in a0
+ *
+ * Return register usage is the same as for OPTEE_SMC_*CALL_WITH_ARG above.
+ *
+ * Possible return values
+ * OPTEE_SMC_RETURN_UNKNOWN_FUNCTION Trusted OS does not recognize this
+ * function.
+ * OPTEE_SMC_RETURN_OK Original call completed, result
+ * updated in the previously supplied.
+ * struct optee_msg_arg
+ * OPTEE_SMC_RETURN_RPC Call suspended by RPC call to normal
+ * world.
+ * OPTEE_SMC_RETURN_ERESUME Resume failed, the opaque resume
+ * information was corrupt.
+ */
+#define OPTEE_SMC_FUNCID_RETURN_FROM_RPC 3
+#define OPTEE_SMC_CALL_RETURN_FROM_RPC \
+ OPTEE_SMC_STD_CALL_VAL(OPTEE_SMC_FUNCID_RETURN_FROM_RPC)
+
+#define OPTEE_SMC_RETURN_RPC_PREFIX_MASK 0xFFFF0000
+#define OPTEE_SMC_RETURN_RPC_PREFIX 0xFFFF0000
+#define OPTEE_SMC_RETURN_RPC_FUNC_MASK 0x0000FFFF
+
+#define OPTEE_SMC_RETURN_GET_RPC_FUNC(ret) \
+ ((ret) & OPTEE_SMC_RETURN_RPC_FUNC_MASK)
+
+#define OPTEE_SMC_RPC_VAL(func) ((func) | OPTEE_SMC_RETURN_RPC_PREFIX)
+
+/*
+ * Allocate memory for RPC parameter passing. The memory is used to hold a
+ * struct optee_msg_arg.
+ *
+ * "Call" register usage:
+ * a0 This value, OPTEE_SMC_RETURN_RPC_ALLOC
+ * a1 Size in bytes of required argument memory
+ * a2 Not used
+ * a3 Resume information, must be preserved
+ * a4-5 Not used
+ * a6-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1 Upper 32bits of 64bit physical pointer to allocated
+ * memory, (a1 == 0 && a2 == 0) if size was 0 or if memory can't
+ * be allocated.
+ * a2 Lower 32bits of 64bit physical pointer to allocated
+ * memory, (a1 == 0 && a2 == 0) if size was 0 or if memory can't
+ * be allocated
+ * a3 Preserved
+ * a4 Upper 32bits of 64bit Shared memory cookie used when freeing
+ * the memory or doing an RPC
+ * a5 Lower 32bits of 64bit Shared memory cookie used when freeing
+ * the memory or doing an RPC
+ * a6-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_ALLOC 0
+#define OPTEE_SMC_RETURN_RPC_ALLOC \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_ALLOC)
+
+/*
+ * Free memory previously allocated by OPTEE_SMC_RETURN_RPC_ALLOC
+ *
+ * "Call" register usage:
+ * a0 This value, OPTEE_SMC_RETURN_RPC_FREE
+ * a1 Upper 32bits of 64bit shared memory cookie belonging to this
+ * argument memory
+ * a2 Lower 32bits of 64bit shared memory cookie belonging to this
+ * argument memory
+ * a3-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1-2 Not used
+ * a3-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_FREE 2
+#define OPTEE_SMC_RETURN_RPC_FREE \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_FREE)
+
+/*
+ * Deliver an IRQ in normal world.
+ *
+ * "Call" register usage:
+ * a0 OPTEE_SMC_RETURN_RPC_IRQ
+ * a1-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_IRQ 4
+#define OPTEE_SMC_RETURN_RPC_IRQ \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_IRQ)
+
+/*
+ * Do an RPC request. The supplied struct optee_msg_arg tells which
+ * request to do and the parameters for the request. The following fields
+ * are used (the rest are unused):
+ * - cmd the Request ID
+ * - ret return value of the request, filled in by normal world
+ * - num_params number of parameters for the request
+ * - params the parameters
+ * - param_attrs attributes of the parameters
+ *
+ * "Call" register usage:
+ * a0 OPTEE_SMC_RETURN_RPC_CMD
+ * a1 Upper 32bit of a 64bit Shared memory cookie holding a
+ * struct optee_msg_arg, must be preserved, only the data should
+ * be updated
+ * a2 Lower 32bit of a 64bit Shared memory cookie holding a
+ * struct optee_msg_arg, must be preserved, only the data should
+ * be updated
+ * a3-7 Resume information, must be preserved
+ *
+ * "Return" register usage:
+ * a0 SMC Function ID, OPTEE_SMC_CALL_RETURN_FROM_RPC.
+ * a1-2 Not used
+ * a3-7 Preserved
+ */
+#define OPTEE_SMC_RPC_FUNC_CMD 5
+#define OPTEE_SMC_RETURN_RPC_CMD \
+ OPTEE_SMC_RPC_VAL(OPTEE_SMC_RPC_FUNC_CMD)
+
+/* Returned in a0 */
+#define OPTEE_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF
+
+/* Returned in a0 only from Trusted OS functions */
+#define OPTEE_SMC_RETURN_OK 0x0
+#define OPTEE_SMC_RETURN_ETHREAD_LIMIT 0x1
+#define OPTEE_SMC_RETURN_EBUSY 0x2
+#define OPTEE_SMC_RETURN_ERESUME 0x3
+#define OPTEE_SMC_RETURN_EBADADDR 0x4
+#define OPTEE_SMC_RETURN_EBADCMD 0x5
+#define OPTEE_SMC_RETURN_ENOMEM 0x6
+#define OPTEE_SMC_RETURN_ENOTAVAIL 0x7
+#define OPTEE_SMC_RETURN_IS_RPC(ret) __optee_smc_return_is_rpc((ret))
+
+static inline bool __optee_smc_return_is_rpc(u32 ret)
+{
+ return ret != OPTEE_SMC_RETURN_UNKNOWN_FUNCTION &&
+ (ret & OPTEE_SMC_RETURN_RPC_PREFIX_MASK) ==
+ OPTEE_SMC_RETURN_RPC_PREFIX;
+}
+
+#endif /* OPTEE_SMC_H */
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include "optee_private.h"
+#include "optee_smc.h"
+
+struct wq_entry {
+ struct list_head link;
+ struct completion c;
+ u32 key;
+};
+
+void optee_wait_queue_init(struct optee_wait_queue *priv)
+{
+ mutex_init(&priv->mu);
+ INIT_LIST_HEAD(&priv->db);
+}
+
+void optee_wait_queue_exit(struct optee_wait_queue *priv)
+{
+ mutex_destroy(&priv->mu);
+}
+
+static void handle_rpc_func_cmd_get_time(struct optee_msg_arg *arg)
+{
+ struct timespec64 ts;
+
+ if (arg->num_params != 1)
+ goto bad;
+ if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) !=
+ OPTEE_MSG_ATTR_TYPE_VALUE_OUTPUT)
+ goto bad;
+
+ getnstimeofday64(&ts);
+ arg->params[0].u.value.a = ts.tv_sec;
+ arg->params[0].u.value.b = ts.tv_nsec;
+
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+}
+
+static struct wq_entry *wq_entry_get(struct optee_wait_queue *wq, u32 key)
+{
+ struct wq_entry *w;
+
+ mutex_lock(&wq->mu);
+
+ list_for_each_entry(w, &wq->db, link)
+ if (w->key == key)
+ goto out;
+
+ w = kmalloc(sizeof(*w), GFP_KERNEL);
+ if (w) {
+ init_completion(&w->c);
+ w->key = key;
+ list_add_tail(&w->link, &wq->db);
+ }
+out:
+ mutex_unlock(&wq->mu);
+ return w;
+}
+
+static void wq_sleep(struct optee_wait_queue *wq, u32 key)
+{
+ struct wq_entry *w = wq_entry_get(wq, key);
+
+ if (w) {
+ wait_for_completion(&w->c);
+ mutex_lock(&wq->mu);
+ list_del(&w->link);
+ mutex_unlock(&wq->mu);
+ kfree(w);
+ }
+}
+
+static void wq_wakeup(struct optee_wait_queue *wq, u32 key)
+{
+ struct wq_entry *w = wq_entry_get(wq, key);
+
+ if (w)
+ complete(&w->c);
+}
+
+static void handle_rpc_func_cmd_wq(struct optee *optee,
+ struct optee_msg_arg *arg)
+{
+ if (arg->num_params != 1)
+ goto bad;
+
+ if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) !=
+ OPTEE_MSG_ATTR_TYPE_VALUE_INPUT)
+ goto bad;
+
+ switch (arg->params[0].u.value.a) {
+ case OPTEE_MSG_RPC_WAIT_QUEUE_SLEEP:
+ wq_sleep(&optee->wait_queue, arg->params[0].u.value.b);
+ break;
+ case OPTEE_MSG_RPC_WAIT_QUEUE_WAKEUP:
+ wq_wakeup(&optee->wait_queue, arg->params[0].u.value.b);
+ break;
+ default:
+ goto bad;
+ }
+
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+}
+
+static void handle_rpc_func_cmd_wait(struct optee_msg_arg *arg)
+{
+ u32 msec_to_wait;
+
+ if (arg->num_params != 1)
+ goto bad;
+
+ if ((arg->params[0].attr & OPTEE_MSG_ATTR_TYPE_MASK) !=
+ OPTEE_MSG_ATTR_TYPE_VALUE_INPUT)
+ goto bad;
+
+ msec_to_wait = arg->params[0].u.value.a;
+
+ /* set task's state to interruptible sleep */
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ /* take a nap */
+ msleep(msec_to_wait);
+
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+}
+
+static void handle_rpc_supp_cmd(struct tee_context *ctx,
+ struct optee_msg_arg *arg)
+{
+ struct tee_param *params;
+
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+
+ params = kmalloc_array(arg->num_params, sizeof(struct tee_param),
+ GFP_KERNEL);
+ if (!params) {
+ arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
+ return;
+ }
+
+ if (optee_from_msg_param(params, arg->num_params, arg->params)) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ goto out;
+ }
+
+ arg->ret = optee_supp_thrd_req(ctx, arg->cmd, arg->num_params, params);
+
+ if (optee_to_msg_param(arg->params, arg->num_params, params))
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+out:
+ kfree(params);
+}
+
+static struct tee_shm *cmd_alloc_suppl(struct tee_context *ctx, size_t sz)
+{
+ u32 ret;
+ struct tee_param param;
+ struct optee *optee = tee_get_drvdata(ctx->teedev);
+ struct tee_shm *shm;
+
+ param.attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT;
+ param.u.value.a = OPTEE_MSG_RPC_SHM_TYPE_APPL;
+ param.u.value.b = sz;
+ param.u.value.c = 0;
+
+ ret = optee_supp_thrd_req(ctx, OPTEE_MSG_RPC_CMD_SHM_ALLOC, 1, ¶m);
+ if (ret)
+ return ERR_PTR(-ENOMEM);
+
+ mutex_lock(&optee->supp.ctx_mutex);
+ /* Increases count as secure world doesn't have a reference */
+ shm = tee_shm_get_from_id(optee->supp.ctx, param.u.value.c);
+ mutex_unlock(&optee->supp.ctx_mutex);
+ return shm;
+}
+
+static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx,
+ struct optee_msg_arg *arg)
+{
+ phys_addr_t pa;
+ struct tee_shm *shm;
+ size_t sz;
+ size_t n;
+
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+
+ if (!arg->num_params ||
+ arg->params[0].attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+
+ for (n = 1; n < arg->num_params; n++) {
+ if (arg->params[n].attr != OPTEE_MSG_ATTR_TYPE_NONE) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+ }
+
+ sz = arg->params[0].u.value.b;
+ switch (arg->params[0].u.value.a) {
+ case OPTEE_MSG_RPC_SHM_TYPE_APPL:
+ shm = cmd_alloc_suppl(ctx, sz);
+ break;
+ case OPTEE_MSG_RPC_SHM_TYPE_KERNEL:
+ shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED);
+ break;
+ default:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+
+ if (IS_ERR(shm)) {
+ arg->ret = TEEC_ERROR_OUT_OF_MEMORY;
+ return;
+ }
+
+ if (tee_shm_get_pa(shm, 0, &pa)) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ goto bad;
+ }
+
+ arg->params[0].attr = OPTEE_MSG_ATTR_TYPE_TMEM_OUTPUT;
+ arg->params[0].u.tmem.buf_ptr = pa;
+ arg->params[0].u.tmem.size = sz;
+ arg->params[0].u.tmem.shm_ref = (unsigned long)shm;
+ arg->ret = TEEC_SUCCESS;
+ return;
+bad:
+ tee_shm_free(shm);
+}
+
+static void cmd_free_suppl(struct tee_context *ctx, struct tee_shm *shm)
+{
+ struct tee_param param;
+
+ param.attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT;
+ param.u.value.a = OPTEE_MSG_RPC_SHM_TYPE_APPL;
+ param.u.value.b = tee_shm_get_id(shm);
+ param.u.value.c = 0;
+
+ /*
+ * Match the tee_shm_get_from_id() in cmd_alloc_suppl() as secure
+ * world has released its reference.
+ *
+ * It's better to do this before sending the request to supplicant
+ * as we'd like to let the process doing the initial allocation to
+ * do release the last reference too in order to avoid stacking
+ * many pending fput() on the client process. This could otherwise
+ * happen if secure world does many allocate and free in a single
+ * invoke.
+ */
+ tee_shm_put(shm);
+
+ optee_supp_thrd_req(ctx, OPTEE_MSG_RPC_CMD_SHM_FREE, 1, ¶m);
+}
+
+static void handle_rpc_func_cmd_shm_free(struct tee_context *ctx,
+ struct optee_msg_arg *arg)
+{
+ struct tee_shm *shm;
+
+ arg->ret_origin = TEEC_ORIGIN_COMMS;
+
+ if (arg->num_params != 1 ||
+ arg->params[0].attr != OPTEE_MSG_ATTR_TYPE_VALUE_INPUT) {
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ return;
+ }
+
+ shm = (struct tee_shm *)(unsigned long)arg->params[0].u.value.b;
+ switch (arg->params[0].u.value.a) {
+ case OPTEE_MSG_RPC_SHM_TYPE_APPL:
+ cmd_free_suppl(ctx, shm);
+ break;
+ case OPTEE_MSG_RPC_SHM_TYPE_KERNEL:
+ tee_shm_free(shm);
+ break;
+ default:
+ arg->ret = TEEC_ERROR_BAD_PARAMETERS;
+ }
+ arg->ret = TEEC_SUCCESS;
+}
+
+static void handle_rpc_func_cmd(struct tee_context *ctx, struct optee *optee,
+ struct tee_shm *shm)
+{
+ struct optee_msg_arg *arg;
+
+ arg = tee_shm_get_va(shm, 0);
+ if (IS_ERR(arg)) {
+ pr_err("%s: tee_shm_get_va %p failed\n", __func__, shm);
+ return;
+ }
+
+ switch (arg->cmd) {
+ case OPTEE_MSG_RPC_CMD_GET_TIME:
+ handle_rpc_func_cmd_get_time(arg);
+ break;
+ case OPTEE_MSG_RPC_CMD_WAIT_QUEUE:
+ handle_rpc_func_cmd_wq(optee, arg);
+ break;
+ case OPTEE_MSG_RPC_CMD_SUSPEND:
+ handle_rpc_func_cmd_wait(arg);
+ break;
+ case OPTEE_MSG_RPC_CMD_SHM_ALLOC:
+ handle_rpc_func_cmd_shm_alloc(ctx, arg);
+ break;
+ case OPTEE_MSG_RPC_CMD_SHM_FREE:
+ handle_rpc_func_cmd_shm_free(ctx, arg);
+ break;
+ default:
+ handle_rpc_supp_cmd(ctx, arg);
+ }
+}
+
+/**
+ * optee_handle_rpc() - handle RPC from secure world
+ * @ctx: context doing the RPC
+ * @param: value of registers for the RPC
+ *
+ * Result of RPC is written back into @param.
+ */
+void optee_handle_rpc(struct tee_context *ctx, struct optee_rpc_param *param)
+{
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct tee_shm *shm;
+ phys_addr_t pa;
+
+ switch (OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)) {
+ case OPTEE_SMC_RPC_FUNC_ALLOC:
+ shm = tee_shm_alloc(ctx, param->a1, TEE_SHM_MAPPED);
+ if (!IS_ERR(shm) && !tee_shm_get_pa(shm, 0, &pa)) {
+ reg_pair_from_64(¶m->a1, ¶m->a2, pa);
+ reg_pair_from_64(¶m->a4, ¶m->a5,
+ (unsigned long)shm);
+ } else {
+ param->a1 = 0;
+ param->a2 = 0;
+ param->a4 = 0;
+ param->a5 = 0;
+ }
+ break;
+ case OPTEE_SMC_RPC_FUNC_FREE:
+ shm = reg_pair_to_ptr(param->a1, param->a2);
+ tee_shm_free(shm);
+ break;
+ case OPTEE_SMC_RPC_FUNC_IRQ:
+ /*
+ * An IRQ was raised while secure world was executing,
+ * since all IRQs are handled in Linux a dummy RPC is
+ * performed to let Linux take the IRQ through the normal
+ * vector.
+ */
+ break;
+ case OPTEE_SMC_RPC_FUNC_CMD:
+ shm = reg_pair_to_ptr(param->a1, param->a2);
+ handle_rpc_func_cmd(ctx, optee, shm);
+ break;
+ default:
+ pr_warn("Unknown RPC func 0x%x\n",
+ (u32)OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0));
+ break;
+ }
+
+ param->a0 = OPTEE_SMC_CALL_RETURN_FROM_RPC;
+}
--- /dev/null
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include "optee_private.h"
+
+void optee_supp_init(struct optee_supp *supp)
+{
+ memset(supp, 0, sizeof(*supp));
+ mutex_init(&supp->ctx_mutex);
+ mutex_init(&supp->thrd_mutex);
+ mutex_init(&supp->supp_mutex);
+ init_completion(&supp->data_to_supp);
+ init_completion(&supp->data_from_supp);
+}
+
+void optee_supp_uninit(struct optee_supp *supp)
+{
+ mutex_destroy(&supp->ctx_mutex);
+ mutex_destroy(&supp->thrd_mutex);
+ mutex_destroy(&supp->supp_mutex);
+}
+
+/**
+ * optee_supp_thrd_req() - request service from supplicant
+ * @ctx: context doing the request
+ * @func: function requested
+ * @num_params: number of elements in @param array
+ * @param: parameters for function
+ *
+ * Returns result of operation to be passed to secure world
+ */
+u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
+ struct tee_param *param)
+{
+ bool interruptable;
+ struct optee *optee = tee_get_drvdata(ctx->teedev);
+ struct optee_supp *supp = &optee->supp;
+ u32 ret;
+
+ /*
+ * Other threads blocks here until we've copied our answer from
+ * supplicant.
+ */
+ while (mutex_lock_interruptible(&supp->thrd_mutex)) {
+ /* See comment below on when the RPC can be interrupted. */
+ mutex_lock(&supp->ctx_mutex);
+ interruptable = !supp->ctx;
+ mutex_unlock(&supp->ctx_mutex);
+ if (interruptable)
+ return TEEC_ERROR_COMMUNICATION;
+ }
+
+ /*
+ * We have exclusive access now since the supplicant at this
+ * point is either doing a
+ * wait_for_completion_interruptible(&supp->data_to_supp) or is in
+ * userspace still about to do the ioctl() to enter
+ * optee_supp_recv() below.
+ */
+
+ supp->func = func;
+ supp->num_params = num_params;
+ supp->param = param;
+ supp->req_posted = true;
+
+ /* Let supplicant get the data */
+ complete(&supp->data_to_supp);
+
+ /*
+ * Wait for supplicant to process and return result, once we've
+ * returned from wait_for_completion(data_from_supp) we have
+ * exclusive access again.
+ */
+ while (wait_for_completion_interruptible(&supp->data_from_supp)) {
+ mutex_lock(&supp->ctx_mutex);
+ interruptable = !supp->ctx;
+ if (interruptable) {
+ /*
+ * There's no supplicant available and since the
+ * supp->ctx_mutex currently is held none can
+ * become available until the mutex released
+ * again.
+ *
+ * Interrupting an RPC to supplicant is only
+ * allowed as a way of slightly improving the user
+ * experience in case the supplicant hasn't been
+ * started yet. During normal operation the supplicant
+ * will serve all requests in a timely manner and
+ * interrupting then wouldn't make sense.
+ */
+ supp->ret = TEEC_ERROR_COMMUNICATION;
+ init_completion(&supp->data_to_supp);
+ }
+ mutex_unlock(&supp->ctx_mutex);
+ if (interruptable)
+ break;
+ }
+
+ ret = supp->ret;
+ supp->param = NULL;
+ supp->req_posted = false;
+
+ /* We're done, let someone else talk to the supplicant now. */
+ mutex_unlock(&supp->thrd_mutex);
+
+ return ret;
+}
+
+/**
+ * optee_supp_recv() - receive request for supplicant
+ * @ctx: context receiving the request
+ * @func: requested function in supplicant
+ * @num_params: number of elements allocated in @param, updated with number
+ * used elements
+ * @param: space for parameters for @func
+ *
+ * Returns 0 on success or <0 on failure
+ */
+int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
+ struct tee_param *param)
+{
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct optee_supp *supp = &optee->supp;
+ int rc;
+
+ /*
+ * In case two threads in one supplicant is calling this function
+ * simultaneously we need to protect the data with a mutex which
+ * we'll release before returning.
+ */
+ mutex_lock(&supp->supp_mutex);
+
+ if (supp->supp_next_send) {
+ /*
+ * optee_supp_recv() has been called again without
+ * a optee_supp_send() in between. Supplicant has
+ * probably been restarted before it was able to
+ * write back last result. Abort last request and
+ * wait for a new.
+ */
+ if (supp->req_posted) {
+ supp->ret = TEEC_ERROR_COMMUNICATION;
+ supp->supp_next_send = false;
+ complete(&supp->data_from_supp);
+ }
+ }
+
+ /*
+ * This is where supplicant will be hanging most of the
+ * time, let's make this interruptable so we can easily
+ * restart supplicant if needed.
+ */
+ if (wait_for_completion_interruptible(&supp->data_to_supp)) {
+ rc = -ERESTARTSYS;
+ goto out;
+ }
+
+ /* We have exlusive access to the data */
+
+ if (*num_params < supp->num_params) {
+ /*
+ * Not enough room for parameters, tell supplicant
+ * it failed and abort last request.
+ */
+ supp->ret = TEEC_ERROR_COMMUNICATION;
+ rc = -EINVAL;
+ complete(&supp->data_from_supp);
+ goto out;
+ }
+
+ *func = supp->func;
+ *num_params = supp->num_params;
+ memcpy(param, supp->param,
+ sizeof(struct tee_param) * supp->num_params);
+
+ /* Allow optee_supp_send() below to do its work */
+ supp->supp_next_send = true;
+
+ rc = 0;
+out:
+ mutex_unlock(&supp->supp_mutex);
+ return rc;
+}
+
+/**
+ * optee_supp_send() - send result of request from supplicant
+ * @ctx: context sending result
+ * @ret: return value of request
+ * @num_params: number of parameters returned
+ * @param: returned parameters
+ *
+ * Returns 0 on success or <0 on failure.
+ */
+int optee_supp_send(struct tee_context *ctx, u32 ret, u32 num_params,
+ struct tee_param *param)
+{
+ struct tee_device *teedev = ctx->teedev;
+ struct optee *optee = tee_get_drvdata(teedev);
+ struct optee_supp *supp = &optee->supp;
+ size_t n;
+ int rc = 0;
+
+ /*
+ * We still have exclusive access to the data since that's how we
+ * left it when returning from optee_supp_read().
+ */
+
+ /* See comment on mutex in optee_supp_read() above */
+ mutex_lock(&supp->supp_mutex);
+
+ if (!supp->supp_next_send) {
+ /*
+ * Something strange is going on, supplicant shouldn't
+ * enter optee_supp_send() in this state
+ */
+ rc = -ENOENT;
+ goto out;
+ }
+
+ if (num_params != supp->num_params) {
+ /*
+ * Something is wrong, let supplicant restart. Next call to
+ * optee_supp_recv() will give an error to the requesting
+ * thread and release it.
+ */
+ rc = -EINVAL;
+ goto out;
+ }
+
+ /* Update out and in/out parameters */
+ for (n = 0; n < num_params; n++) {
+ struct tee_param *p = supp->param + n;
+
+ switch (p->attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ p->u.value.a = param[n].u.value.a;
+ p->u.value.b = param[n].u.value.b;
+ p->u.value.c = param[n].u.value.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ p->u.memref.size = param[n].u.memref.size;
+ break;
+ default:
+ break;
+ }
+ }
+ supp->ret = ret;
+
+ /* Allow optee_supp_recv() above to do its work */
+ supp->supp_next_send = false;
+
+ /* Let the requesting thread continue */
+ complete(&supp->data_from_supp);
+out:
+ mutex_unlock(&supp->supp_mutex);
+ return rc;
+}
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/fs.h>
+#include <linux/idr.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include <linux/uaccess.h>
+#include "tee_private.h"
+
+#define TEE_NUM_DEVICES 32
+
+#define TEE_IOCTL_PARAM_SIZE(x) (sizeof(struct tee_param) * (x))
+
+/*
+ * Unprivileged devices in the lower half range and privileged devices in
+ * the upper half range.
+ */
+static DECLARE_BITMAP(dev_mask, TEE_NUM_DEVICES);
+static DEFINE_SPINLOCK(driver_lock);
+
+static struct class *tee_class;
+static dev_t tee_devt;
+
+static int tee_open(struct inode *inode, struct file *filp)
+{
+ int rc;
+ struct tee_device *teedev;
+ struct tee_context *ctx;
+
+ teedev = container_of(inode->i_cdev, struct tee_device, cdev);
+ if (!tee_device_get(teedev))
+ return -EINVAL;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx) {
+ rc = -ENOMEM;
+ goto err;
+ }
+
+ ctx->teedev = teedev;
+ INIT_LIST_HEAD(&ctx->list_shm);
+ filp->private_data = ctx;
+ rc = teedev->desc->ops->open(ctx);
+ if (rc)
+ goto err;
+
+ return 0;
+err:
+ kfree(ctx);
+ tee_device_put(teedev);
+ return rc;
+}
+
+static int tee_release(struct inode *inode, struct file *filp)
+{
+ struct tee_context *ctx = filp->private_data;
+ struct tee_device *teedev = ctx->teedev;
+ struct tee_shm *shm;
+
+ ctx->teedev->desc->ops->release(ctx);
+ mutex_lock(&ctx->teedev->mutex);
+ list_for_each_entry(shm, &ctx->list_shm, link)
+ shm->ctx = NULL;
+ mutex_unlock(&ctx->teedev->mutex);
+ kfree(ctx);
+ tee_device_put(teedev);
+ return 0;
+}
+
+static int tee_ioctl_version(struct tee_context *ctx,
+ struct tee_ioctl_version_data __user *uvers)
+{
+ struct tee_ioctl_version_data vers;
+
+ ctx->teedev->desc->ops->get_version(ctx->teedev, &vers);
+ if (copy_to_user(uvers, &vers, sizeof(vers)))
+ return -EFAULT;
+ return 0;
+}
+
+static int tee_ioctl_shm_alloc(struct tee_context *ctx,
+ struct tee_ioctl_shm_alloc_data __user *udata)
+{
+ long ret;
+ struct tee_ioctl_shm_alloc_data data;
+ struct tee_shm *shm;
+
+ if (copy_from_user(&data, udata, sizeof(data)))
+ return -EFAULT;
+
+ /* Currently no input flags are supported */
+ if (data.flags)
+ return -EINVAL;
+
+ data.id = -1;
+
+ shm = tee_shm_alloc(ctx, data.size, TEE_SHM_MAPPED | TEE_SHM_DMA_BUF);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ data.id = shm->id;
+ data.flags = shm->flags;
+ data.size = shm->size;
+
+ if (copy_to_user(udata, &data, sizeof(data)))
+ ret = -EFAULT;
+ else
+ ret = tee_shm_get_fd(shm);
+
+ /*
+ * When user space closes the file descriptor the shared memory
+ * should be freed or if tee_shm_get_fd() failed then it will
+ * be freed immediately.
+ */
+ tee_shm_put(shm);
+ return ret;
+}
+
+static int params_from_user(struct tee_context *ctx, struct tee_param *params,
+ size_t num_params,
+ struct tee_ioctl_param __user *uparams)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_shm *shm;
+ struct tee_ioctl_param ip;
+
+ if (copy_from_user(&ip, uparams + n, sizeof(ip)))
+ return -EFAULT;
+
+ /* All unused attribute bits has to be zero */
+ if (ip.attr & ~TEE_IOCTL_PARAM_ATTR_TYPE_MASK)
+ return -EINVAL;
+
+ params[n].attr = ip.attr;
+ switch (ip.attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_NONE:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ params[n].u.value.a = ip.a;
+ params[n].u.value.b = ip.b;
+ params[n].u.value.c = ip.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ /*
+ * If we fail to get a pointer to a shared memory
+ * object (and increase the ref count) from an
+ * identifier we return an error. All pointers that
+ * has been added in params have an increased ref
+ * count. It's the callers responibility to do
+ * tee_shm_put() on all resolved pointers.
+ */
+ shm = tee_shm_get_from_id(ctx, ip.c);
+ if (IS_ERR(shm))
+ return PTR_ERR(shm);
+
+ params[n].u.memref.shm_offs = ip.a;
+ params[n].u.memref.size = ip.b;
+ params[n].u.memref.shm = shm;
+ break;
+ default:
+ /* Unknown attribute */
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+static int params_to_user(struct tee_ioctl_param __user *uparams,
+ size_t num_params, struct tee_param *params)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_ioctl_param __user *up = uparams + n;
+ struct tee_param *p = params + n;
+
+ switch (p->attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ if (put_user(p->u.value.a, &up->a) ||
+ put_user(p->u.value.b, &up->b) ||
+ put_user(p->u.value.c, &up->c))
+ return -EFAULT;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ if (put_user((u64)p->u.memref.size, &up->b))
+ return -EFAULT;
+ default:
+ break;
+ }
+ }
+ return 0;
+}
+
+static bool param_is_memref(struct tee_param *param)
+{
+ switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static int tee_ioctl_open_session(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ int rc;
+ size_t n;
+ struct tee_ioctl_buf_data buf;
+ struct tee_ioctl_open_session_arg __user *uarg;
+ struct tee_ioctl_open_session_arg arg;
+ struct tee_ioctl_param __user *uparams = NULL;
+ struct tee_param *params = NULL;
+ bool have_session = false;
+
+ if (!ctx->teedev->desc->ops->open_session)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_ioctl_open_session_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ if (sizeof(arg) + TEE_IOCTL_PARAM_SIZE(arg.num_params) != buf.buf_len)
+ return -EINVAL;
+
+ if (arg.num_params) {
+ params = kcalloc(arg.num_params, sizeof(struct tee_param),
+ GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+ uparams = uarg->params;
+ rc = params_from_user(ctx, params, arg.num_params, uparams);
+ if (rc)
+ goto out;
+ }
+
+ rc = ctx->teedev->desc->ops->open_session(ctx, &arg, params);
+ if (rc)
+ goto out;
+ have_session = true;
+
+ if (put_user(arg.session, &uarg->session) ||
+ put_user(arg.ret, &uarg->ret) ||
+ put_user(arg.ret_origin, &uarg->ret_origin)) {
+ rc = -EFAULT;
+ goto out;
+ }
+ rc = params_to_user(uparams, arg.num_params, params);
+out:
+ /*
+ * If we've succeeded to open the session but failed to communicate
+ * it back to user space, close the session again to avoid leakage.
+ */
+ if (rc && have_session && ctx->teedev->desc->ops->close_session)
+ ctx->teedev->desc->ops->close_session(ctx, arg.session);
+
+ if (params) {
+ /* Decrease ref count for all valid shared memory pointers */
+ for (n = 0; n < arg.num_params; n++)
+ if (param_is_memref(params + n) &&
+ params[n].u.memref.shm)
+ tee_shm_put(params[n].u.memref.shm);
+ kfree(params);
+ }
+
+ return rc;
+}
+
+static int tee_ioctl_invoke(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ int rc;
+ size_t n;
+ struct tee_ioctl_buf_data buf;
+ struct tee_ioctl_invoke_arg __user *uarg;
+ struct tee_ioctl_invoke_arg arg;
+ struct tee_ioctl_param __user *uparams = NULL;
+ struct tee_param *params = NULL;
+
+ if (!ctx->teedev->desc->ops->invoke_func)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_ioctl_invoke_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ if (sizeof(arg) + TEE_IOCTL_PARAM_SIZE(arg.num_params) != buf.buf_len)
+ return -EINVAL;
+
+ if (arg.num_params) {
+ params = kcalloc(arg.num_params, sizeof(struct tee_param),
+ GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+ uparams = uarg->params;
+ rc = params_from_user(ctx, params, arg.num_params, uparams);
+ if (rc)
+ goto out;
+ }
+
+ rc = ctx->teedev->desc->ops->invoke_func(ctx, &arg, params);
+ if (rc)
+ goto out;
+
+ if (put_user(arg.ret, &uarg->ret) ||
+ put_user(arg.ret_origin, &uarg->ret_origin)) {
+ rc = -EFAULT;
+ goto out;
+ }
+ rc = params_to_user(uparams, arg.num_params, params);
+out:
+ if (params) {
+ /* Decrease ref count for all valid shared memory pointers */
+ for (n = 0; n < arg.num_params; n++)
+ if (param_is_memref(params + n) &&
+ params[n].u.memref.shm)
+ tee_shm_put(params[n].u.memref.shm);
+ kfree(params);
+ }
+ return rc;
+}
+
+static int tee_ioctl_cancel(struct tee_context *ctx,
+ struct tee_ioctl_cancel_arg __user *uarg)
+{
+ struct tee_ioctl_cancel_arg arg;
+
+ if (!ctx->teedev->desc->ops->cancel_req)
+ return -EINVAL;
+
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ return ctx->teedev->desc->ops->cancel_req(ctx, arg.cancel_id,
+ arg.session);
+}
+
+static int
+tee_ioctl_close_session(struct tee_context *ctx,
+ struct tee_ioctl_close_session_arg __user *uarg)
+{
+ struct tee_ioctl_close_session_arg arg;
+
+ if (!ctx->teedev->desc->ops->close_session)
+ return -EINVAL;
+
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ return ctx->teedev->desc->ops->close_session(ctx, arg.session);
+}
+
+static int params_to_supp(struct tee_context *ctx,
+ struct tee_ioctl_param __user *uparams,
+ size_t num_params, struct tee_param *params)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_ioctl_param ip;
+ struct tee_param *p = params + n;
+
+ ip.attr = p->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK;
+ switch (p->attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ ip.a = p->u.value.a;
+ ip.b = p->u.value.b;
+ ip.c = p->u.value.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ ip.b = p->u.memref.size;
+ if (!p->u.memref.shm) {
+ ip.a = 0;
+ ip.c = (u64)-1; /* invalid shm id */
+ break;
+ }
+ ip.a = p->u.memref.shm_offs;
+ ip.c = p->u.memref.shm->id;
+ break;
+ default:
+ ip.a = 0;
+ ip.b = 0;
+ ip.c = 0;
+ break;
+ }
+
+ if (copy_to_user(uparams + n, &ip, sizeof(ip)))
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
+static int tee_ioctl_supp_recv(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ int rc;
+ struct tee_ioctl_buf_data buf;
+ struct tee_iocl_supp_recv_arg __user *uarg;
+ struct tee_param *params;
+ u32 num_params;
+ u32 func;
+
+ if (!ctx->teedev->desc->ops->supp_recv)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_iocl_supp_recv_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (get_user(num_params, &uarg->num_params))
+ return -EFAULT;
+
+ if (sizeof(*uarg) + TEE_IOCTL_PARAM_SIZE(num_params) != buf.buf_len)
+ return -EINVAL;
+
+ params = kcalloc(num_params, sizeof(struct tee_param), GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+
+ rc = ctx->teedev->desc->ops->supp_recv(ctx, &func, &num_params, params);
+ if (rc)
+ goto out;
+
+ if (put_user(func, &uarg->func) ||
+ put_user(num_params, &uarg->num_params)) {
+ rc = -EFAULT;
+ goto out;
+ }
+
+ rc = params_to_supp(ctx, uarg->params, num_params, params);
+out:
+ kfree(params);
+ return rc;
+}
+
+static int params_from_supp(struct tee_param *params, size_t num_params,
+ struct tee_ioctl_param __user *uparams)
+{
+ size_t n;
+
+ for (n = 0; n < num_params; n++) {
+ struct tee_param *p = params + n;
+ struct tee_ioctl_param ip;
+
+ if (copy_from_user(&ip, uparams + n, sizeof(ip)))
+ return -EFAULT;
+
+ /* All unused attribute bits has to be zero */
+ if (ip.attr & ~TEE_IOCTL_PARAM_ATTR_TYPE_MASK)
+ return -EINVAL;
+
+ p->attr = ip.attr;
+ switch (ip.attr) {
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT:
+ /* Only out and in/out values can be updated */
+ p->u.value.a = ip.a;
+ p->u.value.b = ip.b;
+ p->u.value.c = ip.c;
+ break;
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT:
+ case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT:
+ /*
+ * Only the size of the memref can be updated.
+ * Since we don't have access to the original
+ * parameters here, only store the supplied size.
+ * The driver will copy the updated size into the
+ * original parameters.
+ */
+ p->u.memref.shm = NULL;
+ p->u.memref.shm_offs = 0;
+ p->u.memref.size = ip.b;
+ break;
+ default:
+ memset(&p->u, 0, sizeof(p->u));
+ break;
+ }
+ }
+ return 0;
+}
+
+static int tee_ioctl_supp_send(struct tee_context *ctx,
+ struct tee_ioctl_buf_data __user *ubuf)
+{
+ long rc;
+ struct tee_ioctl_buf_data buf;
+ struct tee_iocl_supp_send_arg __user *uarg;
+ struct tee_param *params;
+ u32 num_params;
+ u32 ret;
+
+ /* Not valid for this driver */
+ if (!ctx->teedev->desc->ops->supp_send)
+ return -EINVAL;
+
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+
+ if (buf.buf_len > TEE_MAX_ARG_SIZE ||
+ buf.buf_len < sizeof(struct tee_iocl_supp_send_arg))
+ return -EINVAL;
+
+ uarg = u64_to_user_ptr(buf.buf_ptr);
+ if (get_user(ret, &uarg->ret) ||
+ get_user(num_params, &uarg->num_params))
+ return -EFAULT;
+
+ if (sizeof(*uarg) + TEE_IOCTL_PARAM_SIZE(num_params) > buf.buf_len)
+ return -EINVAL;
+
+ params = kcalloc(num_params, sizeof(struct tee_param), GFP_KERNEL);
+ if (!params)
+ return -ENOMEM;
+
+ rc = params_from_supp(params, num_params, uarg->params);
+ if (rc)
+ goto out;
+
+ rc = ctx->teedev->desc->ops->supp_send(ctx, ret, num_params, params);
+out:
+ kfree(params);
+ return rc;
+}
+
+static long tee_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+ struct tee_context *ctx = filp->private_data;
+ void __user *uarg = (void __user *)arg;
+
+ switch (cmd) {
+ case TEE_IOC_VERSION:
+ return tee_ioctl_version(ctx, uarg);
+ case TEE_IOC_SHM_ALLOC:
+ return tee_ioctl_shm_alloc(ctx, uarg);
+ case TEE_IOC_OPEN_SESSION:
+ return tee_ioctl_open_session(ctx, uarg);
+ case TEE_IOC_INVOKE:
+ return tee_ioctl_invoke(ctx, uarg);
+ case TEE_IOC_CANCEL:
+ return tee_ioctl_cancel(ctx, uarg);
+ case TEE_IOC_CLOSE_SESSION:
+ return tee_ioctl_close_session(ctx, uarg);
+ case TEE_IOC_SUPPL_RECV:
+ return tee_ioctl_supp_recv(ctx, uarg);
+ case TEE_IOC_SUPPL_SEND:
+ return tee_ioctl_supp_send(ctx, uarg);
+ default:
+ return -EINVAL;
+ }
+}
+
+static const struct file_operations tee_fops = {
+ .owner = THIS_MODULE,
+ .open = tee_open,
+ .release = tee_release,
+ .unlocked_ioctl = tee_ioctl,
+ .compat_ioctl = tee_ioctl,
+};
+
+static void tee_release_device(struct device *dev)
+{
+ struct tee_device *teedev = container_of(dev, struct tee_device, dev);
+
+ spin_lock(&driver_lock);
+ clear_bit(teedev->id, dev_mask);
+ spin_unlock(&driver_lock);
+ mutex_destroy(&teedev->mutex);
+ idr_destroy(&teedev->idr);
+ kfree(teedev);
+}
+
+/**
+ * tee_device_alloc() - Allocate a new struct tee_device instance
+ * @teedesc: Descriptor for this driver
+ * @dev: Parent device for this device
+ * @pool: Shared memory pool, NULL if not used
+ * @driver_data: Private driver data for this device
+ *
+ * Allocates a new struct tee_device instance. The device is
+ * removed by tee_device_unregister().
+ *
+ * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure
+ */
+struct tee_device *tee_device_alloc(const struct tee_desc *teedesc,
+ struct device *dev,
+ struct tee_shm_pool *pool,
+ void *driver_data)
+{
+ struct tee_device *teedev;
+ void *ret;
+ int rc;
+ int offs = 0;
+
+ if (!teedesc || !teedesc->name || !teedesc->ops ||
+ !teedesc->ops->get_version || !teedesc->ops->open ||
+ !teedesc->ops->release || !pool)
+ return ERR_PTR(-EINVAL);
+
+ teedev = kzalloc(sizeof(*teedev), GFP_KERNEL);
+ if (!teedev) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err;
+ }
+
+ if (teedesc->flags & TEE_DESC_PRIVILEGED)
+ offs = TEE_NUM_DEVICES / 2;
+
+ spin_lock(&driver_lock);
+ teedev->id = find_next_zero_bit(dev_mask, TEE_NUM_DEVICES, offs);
+ if (teedev->id < TEE_NUM_DEVICES)
+ set_bit(teedev->id, dev_mask);
+ spin_unlock(&driver_lock);
+
+ if (teedev->id >= TEE_NUM_DEVICES) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err;
+ }
+
+ snprintf(teedev->name, sizeof(teedev->name), "tee%s%d",
+ teedesc->flags & TEE_DESC_PRIVILEGED ? "priv" : "",
+ teedev->id - offs);
+
+ teedev->dev.class = tee_class;
+ teedev->dev.release = tee_release_device;
+ teedev->dev.parent = dev;
+
+ teedev->dev.devt = MKDEV(MAJOR(tee_devt), teedev->id);
+
+ rc = dev_set_name(&teedev->dev, "%s", teedev->name);
+ if (rc) {
+ ret = ERR_PTR(rc);
+ goto err_devt;
+ }
+
+ cdev_init(&teedev->cdev, &tee_fops);
+ teedev->cdev.owner = teedesc->owner;
+ teedev->cdev.kobj.parent = &teedev->dev.kobj;
+
+ dev_set_drvdata(&teedev->dev, driver_data);
+ device_initialize(&teedev->dev);
+
+ /* 1 as tee_device_unregister() does one final tee_device_put() */
+ teedev->num_users = 1;
+ init_completion(&teedev->c_no_users);
+ mutex_init(&teedev->mutex);
+ idr_init(&teedev->idr);
+
+ teedev->desc = teedesc;
+ teedev->pool = pool;
+
+ return teedev;
+err_devt:
+ unregister_chrdev_region(teedev->dev.devt, 1);
+err:
+ pr_err("could not register %s driver\n",
+ teedesc->flags & TEE_DESC_PRIVILEGED ? "privileged" : "client");
+ if (teedev && teedev->id < TEE_NUM_DEVICES) {
+ spin_lock(&driver_lock);
+ clear_bit(teedev->id, dev_mask);
+ spin_unlock(&driver_lock);
+ }
+ kfree(teedev);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tee_device_alloc);
+
+static ssize_t implementation_id_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct tee_device *teedev = container_of(dev, struct tee_device, dev);
+ struct tee_ioctl_version_data vers;
+
+ teedev->desc->ops->get_version(teedev, &vers);
+ return scnprintf(buf, PAGE_SIZE, "%d\n", vers.impl_id);
+}
+static DEVICE_ATTR_RO(implementation_id);
+
+static struct attribute *tee_dev_attrs[] = {
+ &dev_attr_implementation_id.attr,
+ NULL
+};
+
+static const struct attribute_group tee_dev_group = {
+ .attrs = tee_dev_attrs,
+};
+
+/**
+ * tee_device_register() - Registers a TEE device
+ * @teedev: Device to register
+ *
+ * tee_device_unregister() need to be called to remove the @teedev if
+ * this function fails.
+ *
+ * @returns < 0 on failure
+ */
+int tee_device_register(struct tee_device *teedev)
+{
+ int rc;
+
+ if (teedev->flags & TEE_DEVICE_FLAG_REGISTERED) {
+ dev_err(&teedev->dev, "attempt to register twice\n");
+ return -EINVAL;
+ }
+
+ rc = cdev_add(&teedev->cdev, teedev->dev.devt, 1);
+ if (rc) {
+ dev_err(&teedev->dev,
+ "unable to cdev_add() %s, major %d, minor %d, err=%d\n",
+ teedev->name, MAJOR(teedev->dev.devt),
+ MINOR(teedev->dev.devt), rc);
+ return rc;
+ }
+
+ rc = device_add(&teedev->dev);
+ if (rc) {
+ dev_err(&teedev->dev,
+ "unable to device_add() %s, major %d, minor %d, err=%d\n",
+ teedev->name, MAJOR(teedev->dev.devt),
+ MINOR(teedev->dev.devt), rc);
+ goto err_device_add;
+ }
+
+ rc = sysfs_create_group(&teedev->dev.kobj, &tee_dev_group);
+ if (rc) {
+ dev_err(&teedev->dev,
+ "failed to create sysfs attributes, err=%d\n", rc);
+ goto err_sysfs_create_group;
+ }
+
+ teedev->flags |= TEE_DEVICE_FLAG_REGISTERED;
+ return 0;
+
+err_sysfs_create_group:
+ device_del(&teedev->dev);
+err_device_add:
+ cdev_del(&teedev->cdev);
+ return rc;
+}
+EXPORT_SYMBOL_GPL(tee_device_register);
+
+void tee_device_put(struct tee_device *teedev)
+{
+ mutex_lock(&teedev->mutex);
+ /* Shouldn't put in this state */
+ if (!WARN_ON(!teedev->desc)) {
+ teedev->num_users--;
+ if (!teedev->num_users) {
+ teedev->desc = NULL;
+ complete(&teedev->c_no_users);
+ }
+ }
+ mutex_unlock(&teedev->mutex);
+}
+
+bool tee_device_get(struct tee_device *teedev)
+{
+ mutex_lock(&teedev->mutex);
+ if (!teedev->desc) {
+ mutex_unlock(&teedev->mutex);
+ return false;
+ }
+ teedev->num_users++;
+ mutex_unlock(&teedev->mutex);
+ return true;
+}
+
+/**
+ * tee_device_unregister() - Removes a TEE device
+ * @teedev: Device to unregister
+ *
+ * This function should be called to remove the @teedev even if
+ * tee_device_register() hasn't been called yet. Does nothing if
+ * @teedev is NULL.
+ */
+void tee_device_unregister(struct tee_device *teedev)
+{
+ if (!teedev)
+ return;
+
+ if (teedev->flags & TEE_DEVICE_FLAG_REGISTERED) {
+ sysfs_remove_group(&teedev->dev.kobj, &tee_dev_group);
+ cdev_del(&teedev->cdev);
+ device_del(&teedev->dev);
+ }
+
+ tee_device_put(teedev);
+ wait_for_completion(&teedev->c_no_users);
+
+ /*
+ * No need to take a mutex any longer now since teedev->desc was
+ * set to NULL before teedev->c_no_users was completed.
+ */
+
+ teedev->pool = NULL;
+
+ put_device(&teedev->dev);
+}
+EXPORT_SYMBOL_GPL(tee_device_unregister);
+
+/**
+ * tee_get_drvdata() - Return driver_data pointer
+ * @teedev: Device containing the driver_data pointer
+ * @returns the driver_data pointer supplied to tee_register().
+ */
+void *tee_get_drvdata(struct tee_device *teedev)
+{
+ return dev_get_drvdata(&teedev->dev);
+}
+EXPORT_SYMBOL_GPL(tee_get_drvdata);
+
+static int __init tee_init(void)
+{
+ int rc;
+
+ tee_class = class_create(THIS_MODULE, "tee");
+ if (IS_ERR(tee_class)) {
+ pr_err("couldn't create class\n");
+ return PTR_ERR(tee_class);
+ }
+
+ rc = alloc_chrdev_region(&tee_devt, 0, TEE_NUM_DEVICES, "tee");
+ if (rc) {
+ pr_err("failed to allocate char dev region\n");
+ class_destroy(tee_class);
+ tee_class = NULL;
+ }
+
+ return rc;
+}
+
+static void __exit tee_exit(void)
+{
+ class_destroy(tee_class);
+ tee_class = NULL;
+ unregister_chrdev_region(tee_devt, TEE_NUM_DEVICES);
+}
+
+subsys_initcall(tee_init);
+module_exit(tee_exit);
+
+MODULE_AUTHOR("Linaro");
+MODULE_DESCRIPTION("TEE Driver");
+MODULE_VERSION("1.0");
+MODULE_LICENSE("GPL v2");
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#ifndef TEE_PRIVATE_H
+#define TEE_PRIVATE_H
+
+#include <linux/cdev.h>
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/kref.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+struct tee_device;
+
+/**
+ * struct tee_shm - shared memory object
+ * @teedev: device used to allocate the object
+ * @ctx: context using the object, if NULL the context is gone
+ * @link link element
+ * @paddr: physical address of the shared memory
+ * @kaddr: virtual address of the shared memory
+ * @size: size of shared memory
+ * @dmabuf: dmabuf used to for exporting to user space
+ * @flags: defined by TEE_SHM_* in tee_drv.h
+ * @id: unique id of a shared memory object on this device
+ */
+struct tee_shm {
+ struct tee_device *teedev;
+ struct tee_context *ctx;
+ struct list_head link;
+ phys_addr_t paddr;
+ void *kaddr;
+ size_t size;
+ struct dma_buf *dmabuf;
+ u32 flags;
+ int id;
+};
+
+struct tee_shm_pool_mgr;
+
+/**
+ * struct tee_shm_pool_mgr_ops - shared memory pool manager operations
+ * @alloc: called when allocating shared memory
+ * @free: called when freeing shared memory
+ */
+struct tee_shm_pool_mgr_ops {
+ int (*alloc)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm,
+ size_t size);
+ void (*free)(struct tee_shm_pool_mgr *poolmgr, struct tee_shm *shm);
+};
+
+/**
+ * struct tee_shm_pool_mgr - shared memory manager
+ * @ops: operations
+ * @private_data: private data for the shared memory manager
+ */
+struct tee_shm_pool_mgr {
+ const struct tee_shm_pool_mgr_ops *ops;
+ void *private_data;
+};
+
+/**
+ * struct tee_shm_pool - shared memory pool
+ * @private_mgr: pool manager for shared memory only between kernel
+ * and secure world
+ * @dma_buf_mgr: pool manager for shared memory exported to user space
+ * @destroy: called when destroying the pool
+ * @private_data: private data for the pool
+ */
+struct tee_shm_pool {
+ struct tee_shm_pool_mgr private_mgr;
+ struct tee_shm_pool_mgr dma_buf_mgr;
+ void (*destroy)(struct tee_shm_pool *pool);
+ void *private_data;
+};
+
+#define TEE_DEVICE_FLAG_REGISTERED 0x1
+#define TEE_MAX_DEV_NAME_LEN 32
+
+/**
+ * struct tee_device - TEE Device representation
+ * @name: name of device
+ * @desc: description of device
+ * @id: unique id of device
+ * @flags: represented by TEE_DEVICE_FLAG_REGISTERED above
+ * @dev: embedded basic device structure
+ * @cdev: embedded cdev
+ * @num_users: number of active users of this device
+ * @c_no_user: completion used when unregistering the device
+ * @mutex: mutex protecting @num_users and @idr
+ * @idr: register of shared memory object allocated on this device
+ * @pool: shared memory pool
+ */
+struct tee_device {
+ char name[TEE_MAX_DEV_NAME_LEN];
+ const struct tee_desc *desc;
+ int id;
+ unsigned int flags;
+
+ struct device dev;
+ struct cdev cdev;
+
+ size_t num_users;
+ struct completion c_no_users;
+ struct mutex mutex; /* protects num_users and idr */
+
+ struct idr idr;
+ struct tee_shm_pool *pool;
+};
+
+int tee_shm_init(void);
+
+int tee_shm_get_fd(struct tee_shm *shm);
+
+bool tee_device_get(struct tee_device *teedev);
+void tee_device_put(struct tee_device *teedev);
+
+#endif /*TEE_PRIVATE_H*/
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/fdtable.h>
+#include <linux/idr.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include "tee_private.h"
+
+static void tee_shm_release(struct tee_shm *shm)
+{
+ struct tee_device *teedev = shm->teedev;
+ struct tee_shm_pool_mgr *poolm;
+
+ mutex_lock(&teedev->mutex);
+ idr_remove(&teedev->idr, shm->id);
+ if (shm->ctx)
+ list_del(&shm->link);
+ mutex_unlock(&teedev->mutex);
+
+ if (shm->flags & TEE_SHM_DMA_BUF)
+ poolm = &teedev->pool->dma_buf_mgr;
+ else
+ poolm = &teedev->pool->private_mgr;
+
+ poolm->ops->free(poolm, shm);
+ kfree(shm);
+
+ tee_device_put(teedev);
+}
+
+static struct sg_table *tee_shm_op_map_dma_buf(struct dma_buf_attachment
+ *attach, enum dma_data_direction dir)
+{
+ return NULL;
+}
+
+static void tee_shm_op_unmap_dma_buf(struct dma_buf_attachment *attach,
+ struct sg_table *table,
+ enum dma_data_direction dir)
+{
+}
+
+static void tee_shm_op_release(struct dma_buf *dmabuf)
+{
+ struct tee_shm *shm = dmabuf->priv;
+
+ tee_shm_release(shm);
+}
+
+static void *tee_shm_op_map_atomic(struct dma_buf *dmabuf, unsigned long pgnum)
+{
+ return NULL;
+}
+
+static void *tee_shm_op_map(struct dma_buf *dmabuf, unsigned long pgnum)
+{
+ return NULL;
+}
+
+static int tee_shm_op_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+ struct tee_shm *shm = dmabuf->priv;
+ size_t size = vma->vm_end - vma->vm_start;
+
+ return remap_pfn_range(vma, vma->vm_start, shm->paddr >> PAGE_SHIFT,
+ size, vma->vm_page_prot);
+}
+
+static struct dma_buf_ops tee_shm_dma_buf_ops = {
+ .map_dma_buf = tee_shm_op_map_dma_buf,
+ .unmap_dma_buf = tee_shm_op_unmap_dma_buf,
+ .release = tee_shm_op_release,
+ .map_atomic = tee_shm_op_map_atomic,
+ .map = tee_shm_op_map,
+ .mmap = tee_shm_op_mmap,
+};
+
+/**
+ * tee_shm_alloc() - Allocate shared memory
+ * @ctx: Context that allocates the shared memory
+ * @size: Requested size of shared memory
+ * @flags: Flags setting properties for the requested shared memory.
+ *
+ * Memory allocated as global shared memory is automatically freed when the
+ * TEE file pointer is closed. The @flags field uses the bits defined by
+ * TEE_SHM_* in <linux/tee_drv.h>. TEE_SHM_MAPPED must currently always be
+ * set. If TEE_SHM_DMA_BUF global shared memory will be allocated and
+ * associated with a dma-buf handle, else driver private memory.
+ */
+struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags)
+{
+ struct tee_device *teedev = ctx->teedev;
+ struct tee_shm_pool_mgr *poolm = NULL;
+ struct tee_shm *shm;
+ void *ret;
+ int rc;
+
+ if (!(flags & TEE_SHM_MAPPED)) {
+ dev_err(teedev->dev.parent,
+ "only mapped allocations supported\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF))) {
+ dev_err(teedev->dev.parent, "invalid shm flags 0x%x", flags);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!tee_device_get(teedev))
+ return ERR_PTR(-EINVAL);
+
+ if (!teedev->pool) {
+ /* teedev has been detached from driver */
+ ret = ERR_PTR(-EINVAL);
+ goto err_dev_put;
+ }
+
+ shm = kzalloc(sizeof(*shm), GFP_KERNEL);
+ if (!shm) {
+ ret = ERR_PTR(-ENOMEM);
+ goto err_dev_put;
+ }
+
+ shm->flags = flags;
+ shm->teedev = teedev;
+ shm->ctx = ctx;
+ if (flags & TEE_SHM_DMA_BUF)
+ poolm = &teedev->pool->dma_buf_mgr;
+ else
+ poolm = &teedev->pool->private_mgr;
+
+ rc = poolm->ops->alloc(poolm, shm, size);
+ if (rc) {
+ ret = ERR_PTR(rc);
+ goto err_kfree;
+ }
+
+ mutex_lock(&teedev->mutex);
+ shm->id = idr_alloc(&teedev->idr, shm, 1, 0, GFP_KERNEL);
+ mutex_unlock(&teedev->mutex);
+ if (shm->id < 0) {
+ ret = ERR_PTR(shm->id);
+ goto err_pool_free;
+ }
+
+ if (flags & TEE_SHM_DMA_BUF) {
+ DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+
+ exp_info.ops = &tee_shm_dma_buf_ops;
+ exp_info.size = shm->size;
+ exp_info.flags = O_RDWR;
+ exp_info.priv = shm;
+
+ shm->dmabuf = dma_buf_export(&exp_info);
+ if (IS_ERR(shm->dmabuf)) {
+ ret = ERR_CAST(shm->dmabuf);
+ goto err_rem;
+ }
+ }
+ mutex_lock(&teedev->mutex);
+ list_add_tail(&shm->link, &ctx->list_shm);
+ mutex_unlock(&teedev->mutex);
+
+ return shm;
+err_rem:
+ mutex_lock(&teedev->mutex);
+ idr_remove(&teedev->idr, shm->id);
+ mutex_unlock(&teedev->mutex);
+err_pool_free:
+ poolm->ops->free(poolm, shm);
+err_kfree:
+ kfree(shm);
+err_dev_put:
+ tee_device_put(teedev);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tee_shm_alloc);
+
+/**
+ * tee_shm_get_fd() - Increase reference count and return file descriptor
+ * @shm: Shared memory handle
+ * @returns user space file descriptor to shared memory
+ */
+int tee_shm_get_fd(struct tee_shm *shm)
+{
+ u32 req_flags = TEE_SHM_MAPPED | TEE_SHM_DMA_BUF;
+ int fd;
+
+ if ((shm->flags & req_flags) != req_flags)
+ return -EINVAL;
+
+ fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC);
+ if (fd >= 0)
+ get_dma_buf(shm->dmabuf);
+ return fd;
+}
+
+/**
+ * tee_shm_free() - Free shared memory
+ * @shm: Handle to shared memory to free
+ */
+void tee_shm_free(struct tee_shm *shm)
+{
+ /*
+ * dma_buf_put() decreases the dmabuf reference counter and will
+ * call tee_shm_release() when the last reference is gone.
+ *
+ * In the case of driver private memory we call tee_shm_release
+ * directly instead as it doesn't have a reference counter.
+ */
+ if (shm->flags & TEE_SHM_DMA_BUF)
+ dma_buf_put(shm->dmabuf);
+ else
+ tee_shm_release(shm);
+}
+EXPORT_SYMBOL_GPL(tee_shm_free);
+
+/**
+ * tee_shm_va2pa() - Get physical address of a virtual address
+ * @shm: Shared memory handle
+ * @va: Virtual address to tranlsate
+ * @pa: Returned physical address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa)
+{
+ /* Check that we're in the range of the shm */
+ if ((char *)va < (char *)shm->kaddr)
+ return -EINVAL;
+ if ((char *)va >= ((char *)shm->kaddr + shm->size))
+ return -EINVAL;
+
+ return tee_shm_get_pa(
+ shm, (unsigned long)va - (unsigned long)shm->kaddr, pa);
+}
+EXPORT_SYMBOL_GPL(tee_shm_va2pa);
+
+/**
+ * tee_shm_pa2va() - Get virtual address of a physical address
+ * @shm: Shared memory handle
+ * @pa: Physical address to tranlsate
+ * @va: Returned virtual address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va)
+{
+ /* Check that we're in the range of the shm */
+ if (pa < shm->paddr)
+ return -EINVAL;
+ if (pa >= (shm->paddr + shm->size))
+ return -EINVAL;
+
+ if (va) {
+ void *v = tee_shm_get_va(shm, pa - shm->paddr);
+
+ if (IS_ERR(v))
+ return PTR_ERR(v);
+ *va = v;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tee_shm_pa2va);
+
+/**
+ * tee_shm_get_va() - Get virtual address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @returns virtual address of the shared memory + offs if offs is within
+ * the bounds of this shared memory, else an ERR_PTR
+ */
+void *tee_shm_get_va(struct tee_shm *shm, size_t offs)
+{
+ if (offs >= shm->size)
+ return ERR_PTR(-EINVAL);
+ return (char *)shm->kaddr + offs;
+}
+EXPORT_SYMBOL_GPL(tee_shm_get_va);
+
+/**
+ * tee_shm_get_pa() - Get physical address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @pa: Physical address to return
+ * @returns 0 if offs is within the bounds of this shared memory, else an
+ * error code.
+ */
+int tee_shm_get_pa(struct tee_shm *shm, size_t offs, phys_addr_t *pa)
+{
+ if (offs >= shm->size)
+ return -EINVAL;
+ if (pa)
+ *pa = shm->paddr + offs;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tee_shm_get_pa);
+
+/**
+ * tee_shm_get_from_id() - Find shared memory object and increase reference
+ * count
+ * @ctx: Context owning the shared memory
+ * @id: Id of shared memory object
+ * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure
+ */
+struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id)
+{
+ struct tee_device *teedev;
+ struct tee_shm *shm;
+
+ if (!ctx)
+ return ERR_PTR(-EINVAL);
+
+ teedev = ctx->teedev;
+ mutex_lock(&teedev->mutex);
+ shm = idr_find(&teedev->idr, id);
+ if (!shm || shm->ctx != ctx)
+ shm = ERR_PTR(-EINVAL);
+ else if (shm->flags & TEE_SHM_DMA_BUF)
+ get_dma_buf(shm->dmabuf);
+ mutex_unlock(&teedev->mutex);
+ return shm;
+}
+EXPORT_SYMBOL_GPL(tee_shm_get_from_id);
+
+/**
+ * tee_shm_get_id() - Get id of a shared memory object
+ * @shm: Shared memory handle
+ * @returns id
+ */
+int tee_shm_get_id(struct tee_shm *shm)
+{
+ return shm->id;
+}
+EXPORT_SYMBOL_GPL(tee_shm_get_id);
+
+/**
+ * tee_shm_put() - Decrease reference count on a shared memory handle
+ * @shm: Shared memory handle
+ */
+void tee_shm_put(struct tee_shm *shm)
+{
+ if (shm->flags & TEE_SHM_DMA_BUF)
+ dma_buf_put(shm->dmabuf);
+}
+EXPORT_SYMBOL_GPL(tee_shm_put);
--- /dev/null
+/*
+ * Copyright (c) 2015, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/genalloc.h>
+#include <linux/slab.h>
+#include <linux/tee_drv.h>
+#include "tee_private.h"
+
+static int pool_op_gen_alloc(struct tee_shm_pool_mgr *poolm,
+ struct tee_shm *shm, size_t size)
+{
+ unsigned long va;
+ struct gen_pool *genpool = poolm->private_data;
+ size_t s = roundup(size, 1 << genpool->min_alloc_order);
+
+ va = gen_pool_alloc(genpool, s);
+ if (!va)
+ return -ENOMEM;
+
+ memset((void *)va, 0, s);
+ shm->kaddr = (void *)va;
+ shm->paddr = gen_pool_virt_to_phys(genpool, va);
+ shm->size = s;
+ return 0;
+}
+
+static void pool_op_gen_free(struct tee_shm_pool_mgr *poolm,
+ struct tee_shm *shm)
+{
+ gen_pool_free(poolm->private_data, (unsigned long)shm->kaddr,
+ shm->size);
+ shm->kaddr = NULL;
+}
+
+static const struct tee_shm_pool_mgr_ops pool_ops_generic = {
+ .alloc = pool_op_gen_alloc,
+ .free = pool_op_gen_free,
+};
+
+static void pool_res_mem_destroy(struct tee_shm_pool *pool)
+{
+ gen_pool_destroy(pool->private_mgr.private_data);
+ gen_pool_destroy(pool->dma_buf_mgr.private_data);
+}
+
+static int pool_res_mem_mgr_init(struct tee_shm_pool_mgr *mgr,
+ struct tee_shm_pool_mem_info *info,
+ int min_alloc_order)
+{
+ size_t page_mask = PAGE_SIZE - 1;
+ struct gen_pool *genpool = NULL;
+ int rc;
+
+ /*
+ * Start and end must be page aligned
+ */
+ if ((info->vaddr & page_mask) || (info->paddr & page_mask) ||
+ (info->size & page_mask))
+ return -EINVAL;
+
+ genpool = gen_pool_create(min_alloc_order, -1);
+ if (!genpool)
+ return -ENOMEM;
+
+ gen_pool_set_algo(genpool, gen_pool_best_fit, NULL);
+ rc = gen_pool_add_virt(genpool, info->vaddr, info->paddr, info->size,
+ -1);
+ if (rc) {
+ gen_pool_destroy(genpool);
+ return rc;
+ }
+
+ mgr->private_data = genpool;
+ mgr->ops = &pool_ops_generic;
+ return 0;
+}
+
+/**
+ * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved
+ * memory range
+ * @priv_info: Information for driver private shared memory pool
+ * @dmabuf_info: Information for dma-buf shared memory pool
+ *
+ * Start and end of pools will must be page aligned.
+ *
+ * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied
+ * in @dmabuf, others will use the range provided by @priv.
+ *
+ * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure.
+ */
+struct tee_shm_pool *
+tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info,
+ struct tee_shm_pool_mem_info *dmabuf_info)
+{
+ struct tee_shm_pool *pool = NULL;
+ int ret;
+
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ /*
+ * Create the pool for driver private shared memory
+ */
+ ret = pool_res_mem_mgr_init(&pool->private_mgr, priv_info,
+ 3 /* 8 byte aligned */);
+ if (ret)
+ goto err;
+
+ /*
+ * Create the pool for dma_buf shared memory
+ */
+ ret = pool_res_mem_mgr_init(&pool->dma_buf_mgr, dmabuf_info,
+ PAGE_SHIFT);
+ if (ret)
+ goto err;
+
+ pool->destroy = pool_res_mem_destroy;
+ return pool;
+err:
+ if (ret == -ENOMEM)
+ pr_err("%s: can't allocate memory for res_mem shared memory pool\n", __func__);
+ if (pool && pool->private_mgr.private_data)
+ gen_pool_destroy(pool->private_mgr.private_data);
+ kfree(pool);
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(tee_shm_pool_alloc_res_mem);
+
+/**
+ * tee_shm_pool_free() - Free a shared memory pool
+ * @pool: The shared memory pool to free
+ *
+ * There must be no remaining shared memory allocated from this pool when
+ * this function is called.
+ */
+void tee_shm_pool_free(struct tee_shm_pool *pool)
+{
+ pool->destroy(pool);
+ kfree(pool);
+}
+EXPORT_SYMBOL_GPL(tee_shm_pool_free);
static long maddr[NR_CARDS];
static int irq[NR_CARDS];
-module_param_array(maddr, long, NULL, 0);
-module_param_array(irq, int, NULL, 0);
+module_param_hw_array(maddr, long, iomem, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
#endif /* CONFIG_ISA */
module_param_array(type, uint, NULL, 0);
MODULE_PARM_DESC(type, "card type: C218=2, C320=4");
-module_param_array(baseaddr, ulong, NULL, 0);
+module_param_hw_array(baseaddr, ulong, ioport, NULL, 0);
MODULE_PARM_DESC(baseaddr, "base address");
module_param_array(numports, uint, NULL, 0);
MODULE_PARM_DESC(numports, "numports (ignored for C218)");
MODULE_AUTHOR("Casper Yang");
MODULE_DESCRIPTION("MOXA Smartio/Industio Family Multiport Board Device Driver");
-module_param_array(ioaddr, ulong, NULL, 0);
+module_param_hw_array(ioaddr, ulong, ioport, NULL, 0);
MODULE_PARM_DESC(ioaddr, "ISA io addresses to look for a moxa board");
module_param(ttymajor, int, 0);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Theodore Ts'o");
MODULE_DESCRIPTION("Comtrol RocketPort driver");
-module_param(board1, ulong, 0);
+module_param_hw(board1, ulong, ioport, 0);
MODULE_PARM_DESC(board1, "I/O port for (ISA) board #1");
-module_param(board2, ulong, 0);
+module_param_hw(board2, ulong, ioport, 0);
MODULE_PARM_DESC(board2, "I/O port for (ISA) board #2");
-module_param(board3, ulong, 0);
+module_param_hw(board3, ulong, ioport, 0);
MODULE_PARM_DESC(board3, "I/O port for (ISA) board #3");
-module_param(board4, ulong, 0);
+module_param_hw(board4, ulong, ioport, 0);
MODULE_PARM_DESC(board4, "I/O port for (ISA) board #4");
-module_param(controller, ulong, 0);
+module_param_hw(controller, ulong, ioport, 0);
MODULE_PARM_DESC(controller, "I/O port for (ISA) rocketport controller");
module_param(support_low_speed, bool, 0);
MODULE_PARM_DESC(support_low_speed, "1 means support 50 baud, 0 means support 460400 baud");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Generic 8250/16x50 serial driver");
-module_param(share_irqs, uint, 0644);
+module_param_hw(share_irqs, uint, other, 0644);
MODULE_PARM_DESC(share_irqs, "Share IRQs with other non-8250/16x50 devices (unsafe)");
module_param(nr_uarts, uint, 0644);
MODULE_PARM_DESC(skip_txen_test, "Skip checking for the TXEN bug at init time");
#ifdef CONFIG_SERIAL_8250_RSA
-module_param_array(probe_rsa, ulong, &probe_rsa_count, 0444);
+module_param_hw_array(probe_rsa, ulong, ioport, &probe_rsa_count, 0444);
MODULE_PARM_DESC(probe_rsa, "Probe I/O ports for RSA");
#endif
MODULE_ALIAS_CHARDEV_MAJOR(TTY_MAJOR);
module_param(break_on_load, bool, 0);
module_param(ttymajor, int, 0);
-module_param_array(io, int, NULL, 0);
-module_param_array(irq, int, NULL, 0);
-module_param_array(dma, int, NULL, 0);
+module_param_hw_array(io, int, ioport, NULL, 0);
+module_param_hw_array(irq, int, irq, NULL, 0);
+module_param_hw_array(dma, int, dma, NULL, 0);
module_param(debug_level, int, 0);
module_param_array(maxframe, int, NULL, 0);
module_param_array(txdmabufs, int, NULL, 0);
obj-$(CONFIG_HDMI) += hdmi.o
obj-$(CONFIG_VT) += console/
+obj-$(CONFIG_FB_STI) += console/
obj-$(CONFIG_LOGO) += logo/
obj-y += backlight/
config VGA_CONSOLE
bool "VGA text console" if EXPERT || !X86
- depends on !4xx && !8xx && !SPARC && !M68K && !PARISC && !FRV && \
+ depends on !4xx && !PPC_8xx && !SPARC && !M68K && !PARISC && !FRV && \
!SUPERH && !BLACKFIN && !AVR32 && !MN10300 && !CRIS && \
(!ARM || ARCH_FOOTBRIDGE || ARCH_INTEGRATOR || ARCH_NETWINDER) && \
!ARM64 && !ARC && !MICROBLAZE && !OPENRISC
select FB_CFB_FILLRECT
select FB_CFB_COPYAREA
select FB_CFB_IMAGEBLIT
- select STI_CONSOLE
- select VT
default y
---help---
STI refers to the HP "Standard Text Interface" which is a set of
#ifdef HAS_VIDC20
#include <mach/acornfb.h>
-#define MAX_SIZE 2*1024*1024
+#define MAX_SIZE (2*1024*1024)
/* VIDC20 has a different set of rules from the VIDC:
* hcr : must be multiple of 4
if (memcmp(¤t_vidc, &vidc, sizeof(vidc))) {
current_vidc = vidc;
- vidc_writel(VIDC20_CTRL| vidc.control);
+ vidc_writel(VIDC20_CTRL | vidc.control);
vidc_writel(0xd0000000 | vidc.pll_ctl);
vidc_writel(0x80000000 | vidc.h_cycle);
vidc_writel(0x81000000 | vidc.h_sync_width);
pal.p = 0;
vidc_writel(0x10000000);
for (i = 0; i < 256; i += 1) {
- pal.vidc20.red = current_par.palette[ i & 31].vidc20.red;
+ pal.vidc20.red = current_par.palette[i & 31].vidc20.red;
pal.vidc20.green = current_par.palette[(i >> 1) & 31].vidc20.green;
pal.vidc20.blue = current_par.palette[(i >> 2) & 31].vidc20.blue;
vidc_writel(pal.p);
base = dma_alloc_wc(current_par.dev, size, &handle,
GFP_KERNEL);
if (base == NULL) {
- printk(KERN_ERR "acornfb: unable to allocate screen "
- "memory\n");
+ printk(KERN_ERR "acornfb: unable to allocate screen memory\n");
return -ENOMEM;
}
v_sync = h_sync / (fb_info.var.yres + fb_info.var.upper_margin +
fb_info.var.lower_margin + fb_info.var.vsync_len);
- printk(KERN_INFO "Acornfb: %dkB %cRAM, %s, using %dx%d, "
- "%d.%03dkHz, %dHz\n",
+ printk(KERN_INFO "Acornfb: %dkB %cRAM, %s, using %dx%d, %d.%03dkHz, %dHz\n",
fb_info.fix.smem_len / 1024,
current_par.using_vram ? 'V' : 'D',
VIDC_NAME, fb_info.var.xres, fb_info.var.yres,
if (err)
return err;
- framesize = fb->panel->mode.xres * fb->panel->mode.yres *
- fb->panel->bpp / 8;
+ framesize = PAGE_ALIGN(fb->panel->mode.xres * fb->panel->mode.yres *
+ fb->panel->bpp / 8);
fb->fb.screen_base = dma_alloc_coherent(&fb->dev->dev, framesize,
&dma, GFP_KERNEL);
if (!fb->fb.screen_base)
MODULE_PARM_DESC(nosplash, "Disable doing the splash screen");
module_param(arcfb_enable, uint, 0);
MODULE_PARM_DESC(arcfb_enable, "Enable communication with Arc board");
-module_param(dio_addr, ulong, 0);
+module_param_hw(dio_addr, ulong, ioport, 0);
MODULE_PARM_DESC(dio_addr, "IO address for data, eg: 0x480");
-module_param(cio_addr, ulong, 0);
+module_param_hw(cio_addr, ulong, ioport, 0);
MODULE_PARM_DESC(cio_addr, "IO address for control, eg: 0x400");
-module_param(c2io_addr, ulong, 0);
+module_param_hw(c2io_addr, ulong, ioport, 0);
MODULE_PARM_DESC(c2io_addr, "IO address for secondary control, eg: 0x408");
module_param(splashval, ulong, 0);
MODULE_PARM_DESC(splashval, "Splash pattern: 0xFF is black, 0x00 is green");
module_param(tuhold, ulong, 0);
MODULE_PARM_DESC(tuhold, "Time to hold between strobing data to Arc board");
-module_param(irq, uint, 0);
+module_param_hw(irq, uint, irq, 0);
MODULE_PARM_DESC(irq, "IRQ for the Arc board");
module_init(arcfb_init);
err |= sysfs_create_bin_file(&rinfo->pdev->dev.kobj,
&edid2_attr);
if (err)
- pr_warning("%s() Creating sysfs files failed, continuing\n",
- __func__);
+ pr_warn("%s() Creating sysfs files failed, continuing\n",
+ __func__);
/* save current mode regs before we switch into the new one
* so we can restore this upon __exit
for (i = specs->modedb_len + num; i < specs->modedb_len + num + svd_n; i++) {
int idx = svd[i - specs->modedb_len - num];
if (!idx || idx >= ARRAY_SIZE(cea_modes)) {
- pr_warning("Reserved SVD code %d\n", idx);
+ pr_warn("Reserved SVD code %d\n", idx);
} else if (!cea_modes[idx].xres) {
- pr_warning("Unimplemented SVD code %d\n", idx);
+ pr_warn("Unimplemented SVD code %d\n", idx);
} else {
memcpy(&m[i], cea_modes + idx, sizeof(m[i]));
pr_debug("Adding SVD #%d: %ux%u@%u\n", idx,
static int i810fb_cursor(struct fb_info *info, struct fb_cursor *cursor);
static int i810fb_init_pci(struct pci_dev *dev,
const struct pci_device_id *entry);
-static void __exit i810fb_remove_pci(struct pci_dev *dev);
+static void i810fb_remove_pci(struct pci_dev *dev);
static int i810fb_resume(struct pci_dev *dev);
static int i810fb_suspend(struct pci_dev *dev, pm_message_t state);
.name = "i810fb",
.id_table = i810fb_pci_tbl,
.probe = i810fb_init_pci,
- .remove = __exit_p(i810fb_remove_pci),
+ .remove = i810fb_remove_pci,
.suspend = i810fb_suspend,
.resume = i810fb_resume,
};
}
-static void __exit i810fb_remove_pci(struct pci_dev *dev)
+static void i810fb_remove_pci(struct pci_dev *dev)
{
struct fb_info *info = pci_get_drvdata(dev);
struct i810fb_par *par = info->par;
#define IMXFB_LSCR1_DEFAULT 0x00120300
+#define LCDC_LAUSCR 0x80
+#define LAUSCR_AUS_MODE (1<<31)
+
/* Used fb-mode. Can be set on kernel command line, therefore file-static. */
static const char *fb_mode;
dma_addr_t dbar2;
u_int pcr;
+ u_int lauscr;
u_int pwmr;
u_int lscr1;
u_int dmacr;
pcr |= imxfb_mode->pcr & ~(0x3f | (7 << 25));
fbi->pcr = pcr;
+ /*
+ * The LCDC AUS Mode Control Register does not exist on imx1.
+ */
+ if (!is_imx1_fb(fbi) && imxfb_mode->aus_mode)
+ fbi->lauscr = LAUSCR_AUS_MODE;
/*
* Copy the RGB parameters for this display
if (fbi->dmacr)
writel(fbi->dmacr, fbi->regs + LCDC_DMACR);
+ if (fbi->lauscr)
+ writel(fbi->lauscr, fbi->regs + LCDC_LAUSCR);
+
return 0;
}
imxfb_mode->bpp = bpp;
imxfb_mode->pcr = pcr;
+ /*
+ * fsl,aus-mode is optional
+ */
+ imxfb_mode->aus_mode = of_property_read_bool(np, "fsl,aus-mode");
+
return 0;
}
module_param(nosplash, uint, 0);
MODULE_PARM_DESC(nosplash, "Disable doing the splash screen");
-module_param(dio_addr, ulong, 0);
+module_param_hw(dio_addr, ulong, ioport, 0);
MODULE_PARM_DESC(dio_addr, "IO address for data, eg: 0x480");
-module_param(cio_addr, ulong, 0);
+module_param_hw(cio_addr, ulong, ioport, 0);
MODULE_PARM_DESC(cio_addr, "IO address for control, eg: 0x400");
-module_param(c2io_addr, ulong, 0);
+module_param_hw(c2io_addr, ulong, ioport, 0);
MODULE_PARM_DESC(c2io_addr, "IO address for secondary control, eg: 0x408");
module_param(splashval, ulong, 0);
MODULE_PARM_DESC(splashval, "Splash pattern: 0x00 is black, 0x01 is white");
{
unsigned long wait = md->hw_guard_end - jiffies;
- if ((long)wait > 0 && wait <= md->hw_guard_wait) {
+ if ((long)wait > 0 && time_before_eq(wait, md->hw_guard_wait)) {
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(wait);
}
return 0;
}
+static void dss_uninit_ports(struct platform_device *pdev);
+
static int dss_init_ports(struct platform_device *pdev)
{
struct device_node *parent = pdev->dev.of_node;
struct device_node *port;
- int r;
+ int r, ret = 0;
if (parent == NULL)
return 0;
switch (port_type) {
case OMAP_DISPLAY_TYPE_DPI:
- dpi_init_port(pdev, port);
+ ret = dpi_init_port(pdev, port);
break;
case OMAP_DISPLAY_TYPE_SDI:
- sdi_init_port(pdev, port);
+ ret = sdi_init_port(pdev, port);
break;
default:
break;
}
- } while ((port = omapdss_of_get_next_port(parent, port)) != NULL);
+ } while (!ret &&
+ (port = omapdss_of_get_next_port(parent, port)) != NULL);
- return 0;
+ if (ret)
+ dss_uninit_ports(pdev);
+
+ return ret;
}
static void dss_uninit_ports(struct platform_device *pdev)
return err;
}
-static int __exit pmagaafb_remove(struct device *dev)
+static int pmagaafb_remove(struct device *dev)
{
struct tc_dev *tdev = to_tc_dev(dev);
struct fb_info *info = dev_get_drvdata(dev);
.name = "pmagaafb",
.bus = &tc_bus_type,
.probe = pmagaafb_probe,
- .remove = __exit_p(pmagaafb_remove),
+ .remove = pmagaafb_remove,
},
};
return err;
}
-static int __exit pmagbafb_remove(struct device *dev)
+static int pmagbafb_remove(struct device *dev)
{
struct tc_dev *tdev = to_tc_dev(dev);
struct fb_info *info = dev_get_drvdata(dev);
.name = "pmagbafb",
.bus = &tc_bus_type,
.probe = pmagbafb_probe,
- .remove = __exit_p(pmagbafb_remove),
+ .remove = pmagbafb_remove,
},
};
return err;
}
-static int __exit pmagbbfb_remove(struct device *dev)
+static int pmagbbfb_remove(struct device *dev)
{
struct tc_dev *tdev = to_tc_dev(dev);
struct fb_info *info = dev_get_drvdata(dev);
.name = "pmagbbfb",
.bus = &tc_bus_type,
.probe = pmagbbfb_probe,
- .remove = __exit_p(pmagbbfb_remove),
+ .remove = pmagbbfb_remove,
},
};
lcd_writel(ofb->fbi, FBR1, ofb->fbi->fdadr[DMA_OV1] | 0x3);
if (wait_for_completion_timeout(&ofb->branch_done, 1 * HZ) == 0)
- pr_warning("%s: timeout disabling overlay1\n", __func__);
+ pr_warn("%s: timeout disabling overlay1\n", __func__);
lcd_writel(ofb->fbi, LCCR5, lccr5);
}
lcd_writel(ofb->fbi, FBR4, ofb->fbi->fdadr[DMA_OV2_Cr] | 0x3);
if (wait_for_completion_timeout(&ofb->branch_done, 1 * HZ) == 0)
- pr_warning("%s: timeout disabling overlay2\n", __func__);
+ pr_warn("%s: timeout disabling overlay2\n", __func__);
}
static struct pxafb_layer_ops ofb_ops[] = {
lcd_writel(fbi, LCCR0, fbi->reg_lccr0 | LCCR0_ENB);
if (wait_for_completion_timeout(&fbi->command_done, HZ/2) == 0) {
- pr_warning("%s: timeout waiting for command done\n",
- __func__);
+ pr_warn("%s: timeout waiting for command done\n", __func__);
ret = -ETIMEDOUT;
}
info->fbmem = ioremap(res->start, resource_size(res));
if (info->fbmem == NULL) {
dev_err(dev, "cannot remap framebuffer\n");
+ ret = -ENXIO;
goto err_mem_res;
}
static int dlfb_select_std_channel(struct dlfb_data *dev)
{
int ret;
- u8 set_def_chn[] = { 0x57, 0xCD, 0xDC, 0xA7,
+ void *buf;
+ static const u8 set_def_chn[] = {
+ 0x57, 0xCD, 0xDC, 0xA7,
0x1C, 0x88, 0x5E, 0x15,
0x60, 0xFE, 0xC6, 0x97,
0x16, 0x3D, 0x47, 0xF2 };
+ buf = kmemdup(set_def_chn, sizeof(set_def_chn), GFP_KERNEL);
+
+ if (!buf)
+ return -ENOMEM;
+
ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
NR_USB_REQUEST_CHANNEL,
(USB_DIR_OUT | USB_TYPE_VENDOR), 0, 0,
- set_def_chn, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT);
+ buf, sizeof(set_def_chn), USB_CTRL_SET_TIMEOUT);
+
+ kfree(buf);
+
return ret;
}
* frame buffer.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/console.h>
#include <linux/kernel.h>
#include <linux/errno.h>
video[KPARAM_MEM] = val;
}
+ video[KPARAM_WIDTH] = xenbus_read_unsigned(dev->otherend, "width",
+ video[KPARAM_WIDTH]);
+ video[KPARAM_HEIGHT] = xenbus_read_unsigned(dev->otherend, "height",
+ video[KPARAM_HEIGHT]);
+
/* If requested res does not fit in available memory, use default */
fb_size = video[KPARAM_MEM] * 1024 * 1024;
if (video[KPARAM_WIDTH] * video[KPARAM_HEIGHT] * XENFB_DEPTH / 8
> fb_size) {
+ pr_warn("display parameters %d,%d,%d invalid, use defaults\n",
+ video[KPARAM_MEM], video[KPARAM_WIDTH],
+ video[KPARAM_HEIGHT]);
video[KPARAM_WIDTH] = XENFB_WIDTH;
video[KPARAM_HEIGHT] = XENFB_HEIGHT;
fb_size = XENFB_DEFAULT_FB_LEN;
return 0;
}
-late_initcall(fb_logo_late_init);
+late_initcall_sync(fb_logo_late_init);
/* logo's are marked __initdata. Use __ref to tell
* modpost that it is intended that this function uses data
* optionally stat.
*/
nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
- err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names,
- NULL);
+ err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
if (err)
return err;
static const char * const names[] = { "events", "status" };
int err;
- err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names,
- NULL);
+ err = virtio_find_vqs(vi->vdev, 2, vqs, cbs, names, NULL);
if (err)
return err;
vi->evt = vqs[0];
static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
void (*callback)(struct virtqueue *vq),
- const char *name)
+ const char *name, bool ctx)
{
struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
struct virtio_mmio_vq_info *info;
/* Create the vring */
vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev,
- true, true, vm_notify, callback, name);
+ true, true, ctx, vm_notify, callback, name);
if (!vq) {
err = -ENOMEM;
goto error_new_virtqueue;
struct virtqueue *vqs[],
vq_callback_t *callbacks[],
const char * const names[],
+ const bool *ctx,
struct irq_affinity *desc)
{
struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
return err;
for (i = 0; i < nvqs; ++i) {
- vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i]);
+ vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i],
+ ctx ? ctx[i] : false);
if (IS_ERR(vqs[i])) {
vm_del_vqs(vdev);
return PTR_ERR(vqs[i]);
static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
+ bool ctx,
u16 msix_vec)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
if (!info)
return ERR_PTR(-ENOMEM);
- vq = vp_dev->setup_vq(vp_dev, info, index, callback, name,
+ vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx,
msix_vec);
if (IS_ERR(vq))
goto out_info;
static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
const char * const names[], bool per_vq_vectors,
+ const bool *ctx,
struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
else
msix_vec = VP_MSIX_VQ_VECTOR;
vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ ctx ? ctx[i] : false,
msix_vec);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
- const char * const names[])
+ const char * const names[], const bool *ctx)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i, err;
continue;
}
vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ ctx ? ctx[i] : false,
VIRTIO_MSI_NO_VECTOR);
if (IS_ERR(vqs[i])) {
err = PTR_ERR(vqs[i]);
/* the config->find_vqs() implementation */
int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
- const char * const names[], struct irq_affinity *desc)
+ const char * const names[], const bool *ctx,
+ struct irq_affinity *desc)
{
int err;
/* Try MSI-X with one vector per queue. */
- err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, desc);
+ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, ctx, desc);
if (!err)
return 0;
/* Fallback: MSI-X with one vector for config, one shared for queues. */
- err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, desc);
+ err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, ctx, desc);
if (!err)
return 0;
/* Finally fall back to regular interrupts. */
- return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
+ return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx);
}
const char *vp_bus_name(struct virtio_device *vdev)
unsigned idx,
void (*callback)(struct virtqueue *vq),
const char *name,
+ bool ctx,
u16 msix_vec);
void (*del_vq)(struct virtio_pci_vq_info *info);
/* the config->find_vqs() implementation */
int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
- const char * const names[], struct irq_affinity *desc);
+ const char * const names[], const bool *ctx,
+ struct irq_affinity *desc);
const char *vp_bus_name(struct virtio_device *vdev);
/* Setup the affinity for a virtqueue:
unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
+ bool ctx,
u16 msix_vec)
{
struct virtqueue *vq;
/* create the vring */
vq = vring_create_virtqueue(index, num,
VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
- true, false, vp_notify, callback, name);
+ true, false, ctx,
+ vp_notify, callback, name);
if (!vq)
return ERR_PTR(-ENOMEM);
unsigned index,
void (*callback)(struct virtqueue *vq),
const char *name,
+ bool ctx,
u16 msix_vec)
{
struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
/* create the vring */
vq = vring_create_virtqueue(index, num,
SMP_CACHE_BYTES, &vp_dev->vdev,
- true, true, vp_notify, callback, name);
+ true, true, ctx,
+ vp_notify, callback, name);
if (!vq)
return ERR_PTR(-ENOMEM);
}
static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
- struct virtqueue *vqs[], vq_callback_t *callbacks[],
- const char * const names[], struct irq_affinity *desc)
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char * const names[], const bool *ctx,
+ struct irq_affinity *desc)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
struct virtqueue *vq;
- int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, desc);
+ int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
if (rc)
return rc;
unsigned int out_sgs,
unsigned int in_sgs,
void *data,
+ void *ctx,
gfp_t gfp)
{
struct vring_virtqueue *vq = to_vvq(_vq);
START_USE(vq);
BUG_ON(data == NULL);
+ BUG_ON(ctx && vq->indirect);
if (unlikely(vq->broken)) {
END_USE(vq);
vq->desc_state[head].data = data;
if (indirect)
vq->desc_state[head].indir_desc = desc;
+ if (ctx)
+ vq->desc_state[head].indir_desc = ctx;
/* Put entry in available array (but don't update avail->idx until they
* do sync). */
for (sg = sgs[i]; sg; sg = sg_next(sg))
total_sg++;
}
- return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
+ return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs,
+ data, NULL, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
void *data,
gfp_t gfp)
{
- return virtqueue_add(vq, &sg, num, 1, 0, data, gfp);
+ return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
void *data,
gfp_t gfp)
{
- return virtqueue_add(vq, &sg, num, 0, 1, data, gfp);
+ return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, gfp);
}
EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
+/**
+ * virtqueue_add_inbuf_ctx - expose input buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg writable by other side
+ * @data: the token identifying the buffer.
+ * @ctx: extra context for the token
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
+ struct scatterlist *sg, unsigned int num,
+ void *data,
+ void *ctx,
+ gfp_t gfp)
+{
+ return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
+
/**
* virtqueue_kick_prepare - first half of split virtqueue_kick call.
* @vq: the struct virtqueue
}
EXPORT_SYMBOL_GPL(virtqueue_kick);
-static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
+static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
+ void **ctx)
{
unsigned int i, j;
__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
/* Plus final descriptor */
vq->vq.num_free++;
- /* Free the indirect table, if any, now that it's unmapped. */
- if (vq->desc_state[head].indir_desc) {
+ if (vq->indirect) {
struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
- u32 len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
+ u32 len;
+
+ /* Free the indirect table, if any, now that it's unmapped. */
+ if (!indir_desc)
+ return;
+
+ len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
BUG_ON(!(vq->vring.desc[head].flags &
cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
for (j = 0; j < len / sizeof(struct vring_desc); j++)
vring_unmap_one(vq, &indir_desc[j]);
- kfree(vq->desc_state[head].indir_desc);
+ kfree(indir_desc);
vq->desc_state[head].indir_desc = NULL;
+ } else if (ctx) {
+ *ctx = vq->desc_state[head].indir_desc;
}
}
* Returns NULL if there are no used buffers, or the "data" token
* handed to virtqueue_add_*().
*/
-void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
+ void **ctx)
{
struct vring_virtqueue *vq = to_vvq(_vq);
void *ret;
/* detach_buf clears data, so grab it now. */
ret = vq->desc_state[i].data;
- detach_buf(vq, i);
+ detach_buf(vq, i, ctx);
vq->last_used_idx++;
/* If we expect an interrupt for the next entry, tell host
* by writing event index and flush out the write before
END_USE(vq);
return ret;
}
-EXPORT_SYMBOL_GPL(virtqueue_get_buf);
+EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
+void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+ return virtqueue_get_buf_ctx(_vq, len, NULL);
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_buf);
/**
* virtqueue_disable_cb - disable callbacks
* @vq: the struct virtqueue we're talking about.
continue;
/* detach_buf clears data, so grab it now. */
buf = vq->desc_state[i].data;
- detach_buf(vq, i);
+ detach_buf(vq, i, NULL);
vq->avail_idx_shadow--;
vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
END_USE(vq);
struct vring vring,
struct virtio_device *vdev,
bool weak_barriers,
+ bool context,
bool (*notify)(struct virtqueue *),
void (*callback)(struct virtqueue *),
const char *name)
vq->last_add_time_valid = false;
#endif
- vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+ vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
+ !context;
vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
/* No callback? Tell other side not to bother us. */
struct virtio_device *vdev,
bool weak_barriers,
bool may_reduce_num,
+ bool context,
bool (*notify)(struct virtqueue *),
void (*callback)(struct virtqueue *),
const char *name)
queue_size_in_bytes = vring_size(num, vring_align);
vring_init(&vring, num, queue, vring_align);
- vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers,
+ vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
notify, callback, name);
if (!vq) {
vring_free_queue(vdev, queue_size_in_bytes, queue,
unsigned int vring_align,
struct virtio_device *vdev,
bool weak_barriers,
+ bool context,
void *pages,
bool (*notify)(struct virtqueue *vq),
void (*callback)(struct virtqueue *vq),
{
struct vring vring;
vring_init(&vring, num, pages, vring_align);
- return __vring_new_virtqueue(index, vring, vdev, weak_barriers,
+ return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
notify, callback, name);
}
EXPORT_SYMBOL_GPL(vring_new_virtqueue);
MODULE_SUPPORTED_DEVICE("sma cpu5 watchdog");
MODULE_LICENSE("GPL");
-module_param(port, int, 0);
+module_param_hw(port, int, ioport, 0);
MODULE_PARM_DESC(port, "base address of watchdog card, default is 0x91");
module_param(verbose, int, 0);
#define WDT_TIMER_CFG 0xf3
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
MODULE_PARM_DESC(io, "Eurotech WDT io port (default=0x3f0)");
-module_param(irq, int, 0);
+module_param_hw(irq, int, irq, 0);
MODULE_PARM_DESC(irq, "Eurotech WDT irq (default=10)");
module_param(ev, charp, 0);
MODULE_PARM_DESC(ev, "Eurotech WDT event type (default is `int')");
MODULE_DESCRIPTION("PC87413 WDT driver");
MODULE_LICENSE("GPL");
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
MODULE_PARM_DESC(io, MODNAME " I/O port (default: "
__MODULE_STRING(IO_DEFAULT) ").");
"When set to 0 driver ISA PnP support will be disabled");
#endif
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
MODULE_PARM_DESC(io, "io port");
module_param(timeout, int, 0);
MODULE_PARM_DESC(timeout, "range is 0-255 minutes, default is 1");
static DEFINE_SPINLOCK(wdt_lock);
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
MODULE_PARM_DESC(io, "WDT io port (default=0x240)");
-module_param(irq, int, 0);
+module_param_hw(irq, int, irq, 0);
MODULE_PARM_DESC(irq, "WDT irq (default=11)");
/* Support for the Fan Tachometer on the WDT501-P */
#include "delayed-ref.h"
#include "locking.h"
+enum merge_mode {
+ MERGE_IDENTICAL_KEYS = 1,
+ MERGE_IDENTICAL_PARENTS,
+};
+
/* Just an arbitrary number so we can be sure this happened */
#define BACKREF_FOUND_SHARED 6
* slot==nritems. In that case, go to the next leaf before we continue.
*/
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
- if (time_seq == (u64)-1)
+ if (time_seq == SEQ_LAST)
ret = btrfs_next_leaf(root, path);
else
ret = btrfs_next_old_leaf(root, path, time_seq);
eie = NULL;
}
next:
- if (time_seq == (u64)-1)
+ if (time_seq == SEQ_LAST)
ret = btrfs_next_item(root, path);
else
ret = btrfs_next_old_item(root, path, time_seq);
if (path->search_commit_root)
root_level = btrfs_header_level(root->commit_root);
- else if (time_seq == (u64)-1)
+ else if (time_seq == SEQ_LAST)
root_level = btrfs_header_level(root->node);
else
root_level = btrfs_old_root_level(root, time_seq);
}
path->lowest_level = level;
- if (time_seq == (u64)-1)
+ if (time_seq == SEQ_LAST)
ret = btrfs_search_slot(NULL, root, &ref->key_for_search, path,
0, 0);
else
/*
* merge backrefs and adjust counts accordingly
*
- * mode = 1: merge identical keys, if key is set
- * FIXME: if we add more keys in __add_prelim_ref, we can merge more here.
- * additionally, we could even add a key range for the blocks we
- * looked into to merge even more (-> replace unresolved refs by those
- * having a parent).
- * mode = 2: merge identical parents
+ * FIXME: For MERGE_IDENTICAL_KEYS, if we add more keys in __add_prelim_ref
+ * then we can merge more here. Additionally, we could even add a key
+ * range for the blocks we looked into to merge even more (-> replace
+ * unresolved refs by those having a parent).
*/
-static void __merge_refs(struct list_head *head, int mode)
+static void __merge_refs(struct list_head *head, enum merge_mode mode)
{
struct __prelim_ref *pos1;
if (!ref_for_same_block(ref1, ref2))
continue;
- if (mode == 1) {
+ if (mode == MERGE_IDENTICAL_KEYS) {
if (!ref1->parent && ref2->parent)
swap(ref1, ref2);
} else {
*
* NOTE: This can return values > 0
*
- * If time_seq is set to (u64)-1, it will not search delayed_refs, and behave
+ * If time_seq is set to SEQ_LAST, it will not search delayed_refs, and behave
* much like trans == NULL case, the difference only lies in it will not
* commit root.
* The special case is for qgroup to search roots in commit_transaction().
path->skip_locking = 1;
}
- if (time_seq == (u64)-1)
+ if (time_seq == SEQ_LAST)
path->skip_locking = 1;
/*
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
if (trans && likely(trans->type != __TRANS_DUMMY) &&
- time_seq != (u64)-1) {
+ time_seq != SEQ_LAST) {
#else
- if (trans && time_seq != (u64)-1) {
+ if (trans && time_seq != SEQ_LAST) {
#endif
/*
* look if there are updates for this ref queued and lock the
head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
if (head) {
if (!mutex_trylock(&head->mutex)) {
- atomic_inc(&head->node.refs);
+ refcount_inc(&head->node.refs);
spin_unlock(&delayed_refs->lock);
btrfs_release_path(path);
if (ret)
goto out;
- __merge_refs(&prefs, 1);
+ __merge_refs(&prefs, MERGE_IDENTICAL_KEYS);
ret = __resolve_indirect_refs(fs_info, path, time_seq, &prefs,
extent_item_pos, total_refs,
if (ret)
goto out;
- __merge_refs(&prefs, 2);
+ __merge_refs(&prefs, MERGE_IDENTICAL_PARENTS);
while (!list_empty(&prefs)) {
ref = list_first_entry(&prefs, struct __prelim_ref, list);
*/
u64 delalloc_bytes;
+ /*
+ * Total number of bytes pending delalloc that fall within a file
+ * range that is either a hole or beyond EOF (and no prealloc extent
+ * exists in the range). This is always <= delalloc_bytes.
+ */
+ u64 new_delalloc_bytes;
+
/*
* total number of bytes pending defrag, used by stat to check whether
* it needs COW.
struct compressed_bio {
/* number of bios pending for this compressed extent */
- atomic_t pending_bios;
+ refcount_t pending_bios;
/* the pages with the compressed data on them */
struct page **compressed_pages;
/* if there are more bios still pending for this compressed
* extent, just exit
*/
- if (!atomic_dec_and_test(&cb->pending_bios))
+ if (!refcount_dec_and_test(&cb->pending_bios))
goto out;
inode = cb->inode;
/* if there are more bios still pending for this compressed
* extent, just exit
*/
- if (!atomic_dec_and_test(&cb->pending_bios))
+ if (!refcount_dec_and_test(&cb->pending_bios))
goto out;
/* ok, we're the last bio for this extent, step one is to
cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS);
if (!cb)
return -ENOMEM;
- atomic_set(&cb->pending_bios, 0);
+ refcount_set(&cb->pending_bios, 0);
cb->errors = 0;
cb->inode = inode;
cb->start = start;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
- atomic_inc(&cb->pending_bios);
+ refcount_set(&cb->pending_bios, 1);
/* create and submit bios for the compressed pages */
bytes_left = compressed_len;
* we inc the count. Otherwise, the cb might get
* freed before we're done setting it up
*/
- atomic_inc(&cb->pending_bios);
+ refcount_inc(&cb->pending_bios);
ret = btrfs_bio_wq_end_io(fs_info, bio,
BTRFS_WQ_ENDIO_DATA);
BUG_ON(ret); /* -ENOMEM */
if (!cb)
goto out;
- atomic_set(&cb->pending_bios, 0);
+ refcount_set(&cb->pending_bios, 0);
cb->errors = 0;
cb->inode = inode;
cb->mirror_num = mirror_num;
bio_set_op_attrs (comp_bio, REQ_OP_READ, 0);
comp_bio->bi_private = cb;
comp_bio->bi_end_io = end_compressed_bio_read;
- atomic_inc(&cb->pending_bios);
+ refcount_set(&cb->pending_bios, 1);
for (pg_index = 0; pg_index < nr_pages; pg_index++) {
page = cb->compressed_pages[pg_index];
* we inc the count. Otherwise, the cb might get
* freed before we're done setting it up
*/
- atomic_inc(&cb->pending_bios);
+ refcount_inc(&cb->pending_bios);
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
ret = btrfs_lookup_bio_sums(inode, comp_bio,
static noinline int
tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int dst_slot, int src_slot,
- int nr_items, gfp_t flags)
+ int nr_items)
{
struct tree_mod_elem *tm = NULL;
struct tree_mod_elem **tm_list = NULL;
if (!tree_mod_need_log(fs_info, eb))
return 0;
- tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), flags);
+ tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), GFP_NOFS);
if (!tm_list)
return -ENOMEM;
- tm = kzalloc(sizeof(*tm), flags);
+ tm = kzalloc(sizeof(*tm), GFP_NOFS);
if (!tm) {
ret = -ENOMEM;
goto free_tms;
for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot,
- MOD_LOG_KEY_REMOVE_WHILE_MOVING, flags);
+ MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS);
if (!tm_list[i]) {
ret = -ENOMEM;
goto free_tms;
static noinline int
tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
struct extent_buffer *old_root,
- struct extent_buffer *new_root, gfp_t flags,
+ struct extent_buffer *new_root,
int log_removal)
{
struct tree_mod_elem *tm = NULL;
if (log_removal && btrfs_header_level(old_root) > 0) {
nritems = btrfs_header_nritems(old_root);
tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *),
- flags);
+ GFP_NOFS);
if (!tm_list) {
ret = -ENOMEM;
goto free_tms;
}
for (i = 0; i < nritems; i++) {
tm_list[i] = alloc_tree_mod_elem(old_root, i,
- MOD_LOG_KEY_REMOVE_WHILE_FREEING, flags);
+ MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
if (!tm_list[i]) {
ret = -ENOMEM;
goto free_tms;
}
}
- tm = kzalloc(sizeof(*tm), flags);
+ tm = kzalloc(sizeof(*tm), GFP_NOFS);
if (!tm) {
ret = -ENOMEM;
goto free_tms;
{
int ret;
ret = tree_mod_log_insert_move(fs_info, dst, dst_offset, src_offset,
- nr_items, GFP_NOFS);
+ nr_items);
BUG_ON(ret < 0);
}
{
int ret;
ret = tree_mod_log_insert_root(root->fs_info, root->node,
- new_root_node, GFP_NOFS, log_removal);
+ new_root_node, log_removal);
BUG_ON(ret < 0);
}
#include <linux/security.h>
#include <linux/sizes.h>
#include <linux/dynamic_debug.h>
+#include <linux/refcount.h>
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
struct btrfs_work work;
struct btrfs_block_group_cache *block_group;
u64 progress;
- atomic_t count;
+ refcount_t count;
};
/* Once caching_thread() finds this much free space, it will wake up waiters. */
unsigned check_crcs:1;
};
+/*
+ * Tree to record all locked full stripes of a RAID5/6 block group
+ */
+struct btrfs_full_stripe_locks_tree {
+ struct rb_root root;
+ struct mutex lock;
+};
+
struct btrfs_block_group_cache {
struct btrfs_key key;
struct btrfs_block_group_item item;
* Protected by free_space_lock.
*/
int needs_free_space;
+
+ /* Record locked full stripes for RAID5/6 block group */
+ struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
};
/* delayed seq elem */
#define SEQ_LIST_INIT(name) { .list = LIST_HEAD_INIT((name).list), .seq = 0 }
+#define SEQ_LAST ((u64)-1)
+
enum btrfs_orphan_cleanup_state {
ORPHAN_CLEANUP_STARTED = 1,
ORPHAN_CLEANUP_DONE = 2,
#define BTRFS_FS_BTREE_ERR 11
#define BTRFS_FS_LOG1_ERR 12
#define BTRFS_FS_LOG2_ERR 13
+/*
+ * Indicate that a whole-filesystem exclusive operation is running
+ * (device replace, resize, device add/delete, balance)
+ */
+#define BTRFS_FS_EXCL_OP 14
struct btrfs_fs_info {
u8 fsid[BTRFS_FSID_SIZE];
/* device replace state */
struct btrfs_dev_replace dev_replace;
- atomic_t mutually_exclusive_operation_running;
-
struct percpu_counter bio_counter;
wait_queue_head_t replace_wait;
dev_t anon_dev;
spinlock_t root_item_lock;
- atomic_t refs;
+ refcount_t refs;
struct mutex delalloc_mutex;
spinlock_t delalloc_lock;
struct btrfs_device *dev);
int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
struct btrfs_scrub_progress *progress);
+static inline void btrfs_init_full_stripe_locks_tree(
+ struct btrfs_full_stripe_locks_tree *locks_root)
+{
+ locks_root->root = RB_ROOT;
+ mutex_init(&locks_root->lock);
+}
/* dev-replace.c */
void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
struct btrfs_key *start, struct btrfs_key *end);
int btrfs_reada_wait(void *handle);
void btrfs_reada_detach(void *handle);
-int btree_readahead_hook(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb, int err);
+int btree_readahead_hook(struct extent_buffer *eb, int err);
static inline int is_fstree(u64 rootid)
{
{
delayed_node->root = root;
delayed_node->inode_id = inode_id;
- atomic_set(&delayed_node->refs, 0);
+ refcount_set(&delayed_node->refs, 0);
delayed_node->ins_root = RB_ROOT;
delayed_node->del_root = RB_ROOT;
mutex_init(&delayed_node->mutex);
node = READ_ONCE(btrfs_inode->delayed_node);
if (node) {
- atomic_inc(&node->refs);
+ refcount_inc(&node->refs);
return node;
}
node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
if (node) {
if (btrfs_inode->delayed_node) {
- atomic_inc(&node->refs); /* can be accessed */
+ refcount_inc(&node->refs); /* can be accessed */
BUG_ON(btrfs_inode->delayed_node != node);
spin_unlock(&root->inode_lock);
return node;
}
btrfs_inode->delayed_node = node;
/* can be accessed and cached in the inode */
- atomic_add(2, &node->refs);
+ refcount_add(2, &node->refs);
spin_unlock(&root->inode_lock);
return node;
}
btrfs_init_delayed_node(node, root, ino);
/* cached in the btrfs inode and can be accessed */
- atomic_add(2, &node->refs);
+ refcount_set(&node->refs, 2);
ret = radix_tree_preload(GFP_NOFS);
if (ret) {
} else {
list_add_tail(&node->n_list, &root->node_list);
list_add_tail(&node->p_list, &root->prepare_list);
- atomic_inc(&node->refs); /* inserted into list */
+ refcount_inc(&node->refs); /* inserted into list */
root->nodes++;
set_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags);
}
spin_lock(&root->lock);
if (test_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags)) {
root->nodes--;
- atomic_dec(&node->refs); /* not in the list */
+ refcount_dec(&node->refs); /* not in the list */
list_del_init(&node->n_list);
if (!list_empty(&node->p_list))
list_del_init(&node->p_list);
p = delayed_root->node_list.next;
node = list_entry(p, struct btrfs_delayed_node, n_list);
- atomic_inc(&node->refs);
+ refcount_inc(&node->refs);
out:
spin_unlock(&delayed_root->lock);
p = node->n_list.next;
next = list_entry(p, struct btrfs_delayed_node, n_list);
- atomic_inc(&next->refs);
+ refcount_inc(&next->refs);
out:
spin_unlock(&delayed_root->lock);
btrfs_dequeue_delayed_node(delayed_root, delayed_node);
mutex_unlock(&delayed_node->mutex);
- if (atomic_dec_and_test(&delayed_node->refs)) {
+ if (refcount_dec_and_test(&delayed_node->refs)) {
bool free = false;
struct btrfs_root *root = delayed_node->root;
spin_lock(&root->inode_lock);
- if (atomic_read(&delayed_node->refs) == 0) {
+ if (refcount_read(&delayed_node->refs) == 0) {
radix_tree_delete(&root->delayed_nodes_tree,
delayed_node->inode_id);
free = true;
p = delayed_root->prepare_list.next;
list_del_init(p);
node = list_entry(p, struct btrfs_delayed_node, p_list);
- atomic_inc(&node->refs);
+ refcount_inc(&node->refs);
out:
spin_unlock(&delayed_root->lock);
item->ins_or_del = 0;
item->bytes_reserved = 0;
item->delayed_node = NULL;
- atomic_set(&item->refs, 1);
+ refcount_set(&item->refs, 1);
}
return item;
}
{
if (item) {
__btrfs_remove_delayed_item(item);
- if (atomic_dec_and_test(&item->refs))
+ if (refcount_dec_and_test(&item->refs))
kfree(item);
}
}
mutex_lock(&delayed_node->mutex);
item = __btrfs_first_delayed_insertion_item(delayed_node);
while (item) {
- atomic_inc(&item->refs);
+ refcount_inc(&item->refs);
list_add_tail(&item->readdir_list, ins_list);
item = __btrfs_next_delayed_item(item);
}
item = __btrfs_first_delayed_deletion_item(delayed_node);
while (item) {
- atomic_inc(&item->refs);
+ refcount_inc(&item->refs);
list_add_tail(&item->readdir_list, del_list);
item = __btrfs_next_delayed_item(item);
}
* insert/delete delayed items in this period. So we also needn't
* requeue or dequeue this delayed node.
*/
- atomic_dec(&delayed_node->refs);
+ refcount_dec(&delayed_node->refs);
return true;
}
list_for_each_entry_safe(curr, next, ins_list, readdir_list) {
list_del(&curr->readdir_list);
- if (atomic_dec_and_test(&curr->refs))
+ if (refcount_dec_and_test(&curr->refs))
kfree(curr);
}
list_for_each_entry_safe(curr, next, del_list, readdir_list) {
list_del(&curr->readdir_list);
- if (atomic_dec_and_test(&curr->refs))
+ if (refcount_dec_and_test(&curr->refs))
kfree(curr);
}
list_del(&curr->readdir_list);
ret = (curr->key.offset == index);
- if (atomic_dec_and_test(&curr->refs))
+ if (refcount_dec_and_test(&curr->refs))
kfree(curr);
if (ret)
list_del(&curr->readdir_list);
if (curr->key.offset < ctx->pos) {
- if (atomic_dec_and_test(&curr->refs))
+ if (refcount_dec_and_test(&curr->refs))
kfree(curr);
continue;
}
over = !dir_emit(ctx, name, name_len,
location.objectid, d_type);
- if (atomic_dec_and_test(&curr->refs))
+ if (refcount_dec_and_test(&curr->refs))
kfree(curr);
if (over)
inode_id = delayed_nodes[n - 1]->inode_id + 1;
for (i = 0; i < n; i++)
- atomic_inc(&delayed_nodes[i]->refs);
+ refcount_inc(&delayed_nodes[i]->refs);
spin_unlock(&root->inode_lock);
for (i = 0; i < n; i++) {
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/atomic.h>
-
+#include <linux/refcount.h>
#include "ctree.h"
/* types of the delayed item */
struct rb_root del_root;
struct mutex mutex;
struct btrfs_inode_item inode_item;
- atomic_t refs;
+ refcount_t refs;
u64 index_cnt;
unsigned long flags;
int count;
struct list_head readdir_list; /* used for readdir items */
u64 bytes_reserved;
struct btrfs_delayed_node *delayed_node;
- atomic_t refs;
+ refcount_t refs;
int ins_or_del;
u32 data_len;
char data[0];
if (mutex_trylock(&head->mutex))
return 0;
- atomic_inc(&head->node.refs);
+ refcount_inc(&head->node.refs);
spin_unlock(&delayed_refs->lock);
mutex_lock(&head->mutex);
delayed_refs = &trans->transaction->delayed_refs;
/* first set the basic ref node struct up */
- atomic_set(&ref->refs, 1);
+ refcount_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
ref->ref_mod = count_mod;
delayed_refs = &trans->transaction->delayed_refs;
/* first set the basic ref node struct up */
- atomic_set(&ref->refs, 1);
+ refcount_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
ref->ref_mod = 1;
seq = atomic64_read(&fs_info->tree_mod_seq);
/* first set the basic ref node struct up */
- atomic_set(&ref->refs, 1);
+ refcount_set(&ref->refs, 1);
ref->bytenr = bytenr;
ref->num_bytes = num_bytes;
ref->ref_mod = 1;
#ifndef __DELAYED_REF__
#define __DELAYED_REF__
+#include <linux/refcount.h>
+
/* these are the possible values of struct btrfs_delayed_ref_node->action */
#define BTRFS_ADD_DELAYED_REF 1 /* add one backref to the tree */
#define BTRFS_DROP_DELAYED_REF 2 /* delete one backref from the tree */
u64 seq;
/* ref count on this data structure */
- atomic_t refs;
+ refcount_t refs;
/*
* how many refs is this entry adding or deleting. For
static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
{
- WARN_ON(atomic_read(&ref->refs) == 0);
- if (atomic_dec_and_test(&ref->refs)) {
+ WARN_ON(refcount_read(&ref->refs) == 0);
+ if (refcount_dec_and_test(&ref->refs)) {
WARN_ON(ref->in_tree);
switch (ref->type) {
case BTRFS_TREE_BLOCK_REF_KEY:
mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
mutex_unlock(&uuid_mutex);
+ btrfs_rm_dev_replace_blocked(fs_info);
if (tgt_device)
btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+ btrfs_rm_dev_replace_unblocked(fs_info);
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return scrub_ret;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
srcdev = dev_replace->srcdev;
- args->status.progress_1000 = div_u64(dev_replace->cursor_left,
+ args->status.progress_1000 = div64_u64(dev_replace->cursor_left,
div_u64(btrfs_device_get_total_bytes(srcdev), 1000));
break;
}
}
btrfs_dev_replace_unlock(dev_replace, 1);
- WARN_ON(atomic_xchg(
- &fs_info->mutually_exclusive_operation_running, 1));
+ WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl");
return PTR_ERR_OR_ZERO(task);
}
(unsigned int)progress);
}
btrfs_dev_replace_continue_on_mount(fs_info);
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
return 0;
}
err:
if (reads_done &&
test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
- btree_readahead_hook(fs_info, eb, ret);
+ btree_readahead_hook(eb, ret);
if (ret) {
/*
eb->read_mirror = failed_mirror;
atomic_dec(&eb->io_pages);
if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
- btree_readahead_hook(eb->fs_info, eb, -EIO);
+ btree_readahead_hook(eb, -EIO);
return -EIO; /* we fixed nothing */
}
atomic_set(&root->log_writers, 0);
atomic_set(&root->log_batch, 0);
atomic_set(&root->orphan_inodes, 0);
- atomic_set(&root->refs, 1);
+ refcount_set(&root->refs, 1);
atomic_set(&root->will_be_snapshoted, 0);
atomic64_set(&root->qgroup_meta_rsv, 0);
root->log_transid = 0;
*/
static int write_dev_flush(struct btrfs_device *device, int wait)
{
+ struct request_queue *q = bdev_get_queue(device->bdev);
struct bio *bio;
int ret = 0;
- if (device->nobarriers)
+ if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
return 0;
if (wait) {
head = rb_entry(node, struct btrfs_delayed_ref_head,
href_node);
if (!mutex_trylock(&head->mutex)) {
- atomic_inc(&head->node.refs);
+ refcount_inc(&head->node.refs);
spin_unlock(&delayed_refs->lock);
mutex_lock(&head->mutex);
t = list_first_entry(&fs_info->trans_list,
struct btrfs_transaction, list);
if (t->state >= TRANS_STATE_COMMIT_START) {
- atomic_inc(&t->use_count);
+ refcount_inc(&t->use_count);
spin_unlock(&fs_info->trans_lock);
btrfs_wait_for_commit(fs_info, t->transid);
btrfs_put_transaction(t);
*/
static inline struct btrfs_root *btrfs_grab_fs_root(struct btrfs_root *root)
{
- if (atomic_inc_not_zero(&root->refs))
+ if (refcount_inc_not_zero(&root->refs))
return root;
return NULL;
}
static inline void btrfs_put_fs_root(struct btrfs_root *root)
{
- if (atomic_dec_and_test(&root->refs))
+ if (refcount_dec_and_test(&root->refs))
kfree(root);
}
if (atomic_dec_and_test(&cache->count)) {
WARN_ON(cache->pinned > 0);
WARN_ON(cache->reserved > 0);
+
+ /*
+ * If not empty, someone is still holding mutex of
+ * full_stripe_lock, which can only be released by caller.
+ * And it will definitely cause use-after-free when caller
+ * tries to release full stripe lock.
+ *
+ * No better way to resolve, but only to warn.
+ */
+ WARN_ON(!RB_EMPTY_ROOT(&cache->full_stripe_locks_root.root));
kfree(cache->free_space_ctl);
kfree(cache);
}
}
ctl = cache->caching_ctl;
- atomic_inc(&ctl->count);
+ refcount_inc(&ctl->count);
spin_unlock(&cache->lock);
return ctl;
}
static void put_caching_control(struct btrfs_caching_control *ctl)
{
- if (atomic_dec_and_test(&ctl->count))
+ if (refcount_dec_and_test(&ctl->count))
kfree(ctl);
}
init_waitqueue_head(&caching_ctl->wait);
caching_ctl->block_group = cache;
caching_ctl->progress = cache->key.objectid;
- atomic_set(&caching_ctl->count, 1);
+ refcount_set(&caching_ctl->count, 1);
btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
caching_thread, NULL, NULL);
struct btrfs_caching_control *ctl;
ctl = cache->caching_ctl;
- atomic_inc(&ctl->count);
+ refcount_inc(&ctl->count);
prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
spin_unlock(&cache->lock);
}
down_write(&fs_info->commit_root_sem);
- atomic_inc(&caching_ctl->count);
+ refcount_inc(&caching_ctl->count);
list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
up_write(&fs_info->commit_root_sem);
head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
if (head) {
if (!mutex_trylock(&head->mutex)) {
- atomic_inc(&head->node.refs);
+ refcount_inc(&head->node.refs);
spin_unlock(&delayed_refs->lock);
btrfs_release_path(path);
struct btrfs_delayed_ref_node *ref;
ref = &head->node;
- atomic_inc(&ref->refs);
+ refcount_inc(&ref->refs);
spin_unlock(&delayed_refs->lock);
/*
goto again;
}
out:
- assert_qgroups_uptodate(trans);
trans->can_flush_pending_bgs = can_flush_pending_bgs;
return 0;
}
}
if (!mutex_trylock(&head->mutex)) {
- atomic_inc(&head->node.refs);
+ refcount_inc(&head->node.refs);
spin_unlock(&delayed_refs->lock);
btrfs_release_path(path);
/*
* don't bother trying to write stuff out _if_
* a) we're not cached,
- * b) we're with nospace_cache mount option.
+ * b) we're with nospace_cache mount option,
+ * c) we're with v2 space_cache (FREE_SPACE_TREE).
*/
dcs = BTRFS_DC_WRITTEN;
spin_unlock(&block_group->lock);
btrfs_init_free_space_ctl(cache);
atomic_set(&cache->trimming, 0);
mutex_init(&cache->free_space_lock);
+ btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);
return cache;
}
&fs_info->caching_block_groups, list)
if (ctl->block_group == block_group) {
caching_ctl = ctl;
- atomic_inc(&caching_ctl->count);
+ refcount_inc(&caching_ctl->count);
break;
}
}
spin_lock(&fs_info->trans_lock);
trans = fs_info->running_transaction;
if (trans)
- atomic_inc(&trans->use_count);
+ refcount_inc(&trans->use_count);
spin_unlock(&fs_info->trans_lock);
ret = find_free_dev_extent_start(trans, device, minlen, start,
pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n",
state->start, state->end, state->state,
extent_state_in_tree(state),
- atomic_read(&state->refs));
+ refcount_read(&state->refs));
list_del(&state->leak_list);
kmem_cache_free(extent_state_cache, state);
}
state->failrec = NULL;
RB_CLEAR_NODE(&state->rb_node);
btrfs_leak_debug_add(&state->leak_list, &states);
- atomic_set(&state->refs, 1);
+ refcount_set(&state->refs, 1);
init_waitqueue_head(&state->wq);
trace_alloc_extent_state(state, mask, _RET_IP_);
return state;
{
if (!state)
return;
- if (atomic_dec_and_test(&state->refs)) {
+ if (refcount_dec_and_test(&state->refs)) {
WARN_ON(extent_state_in_tree(state));
btrfs_leak_debug_del(&state->leak_list);
trace_free_extent_state(state, _RET_IP_);
if (cached && extent_state_in_tree(cached) &&
cached->start <= start && cached->end > start) {
if (clear)
- atomic_dec(&cached->refs);
+ refcount_dec(&cached->refs);
state = cached;
goto hit_next;
}
if (state->state & bits) {
start = state->start;
- atomic_inc(&state->refs);
+ refcount_inc(&state->refs);
wait_on_state(tree, state);
free_extent_state(state);
goto again;
if (cached_ptr && !(*cached_ptr)) {
if (!flags || (state->state & flags)) {
*cached_ptr = state;
- atomic_inc(&state->refs);
+ refcount_inc(&state->refs);
}
}
}
if (!found) {
*start = state->start;
*cached_state = state;
- atomic_inc(&state->refs);
+ refcount_inc(&state->refs);
}
found++;
*end = state->end;
u64 map_length = 0;
u64 sector;
struct btrfs_bio *bbio = NULL;
- struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
int ret;
ASSERT(!(fs_info->sb->s_flags & MS_RDONLY));
BUG_ON(!mirror_num);
- /* we can't repair anything in raid56 yet */
- if (btrfs_is_parity_mirror(map_tree, logical, length, mirror_num))
- return 0;
-
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
if (!bio)
return -EIO;
* read repair operation.
*/
btrfs_bio_counter_inc_blocked(fs_info);
- ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
- &map_length, &bbio, mirror_num);
- if (ret) {
- btrfs_bio_counter_dec(fs_info);
- bio_put(bio);
- return -EIO;
+ if (btrfs_is_parity_mirror(fs_info, logical, length, mirror_num)) {
+ /*
+ * Note that we don't use BTRFS_MAP_WRITE because it's supposed
+ * to update all raid stripes, but here we just want to correct
+ * bad stripe, thus BTRFS_MAP_READ is abused to only get the bad
+ * stripe's dev and sector.
+ */
+ ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
+ &map_length, &bbio, 0);
+ if (ret) {
+ btrfs_bio_counter_dec(fs_info);
+ bio_put(bio);
+ return -EIO;
+ }
+ ASSERT(bbio->mirror_num == 1);
+ } else {
+ ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
+ &map_length, &bbio, mirror_num);
+ if (ret) {
+ btrfs_bio_counter_dec(fs_info);
+ bio_put(bio);
+ return -EIO;
+ }
+ BUG_ON(mirror_num != bbio->mirror_num);
}
- BUG_ON(mirror_num != bbio->mirror_num);
- sector = bbio->stripes[mirror_num-1].physical >> 9;
+
+ sector = bbio->stripes[bbio->mirror_num - 1].physical >> 9;
bio->bi_iter.bi_sector = sector;
- dev = bbio->stripes[mirror_num-1].dev;
+ dev = bbio->stripes[bbio->mirror_num - 1].dev;
btrfs_put_bbio(bbio);
if (!dev || !dev->bdev || !dev->writeable) {
btrfs_bio_counter_dec(fs_info);
em = *em_cached;
if (extent_map_in_tree(em) && start >= em->start &&
start < extent_map_end(em)) {
- atomic_inc(&em->refs);
+ refcount_inc(&em->refs);
return em;
}
em = get_extent(BTRFS_I(inode), page, pg_offset, start, len, 0);
if (em_cached && !IS_ERR_OR_NULL(em)) {
BUG_ON(*em_cached);
- atomic_inc(&em->refs);
+ refcount_inc(&em->refs);
*em_cached = em;
}
return em;
#define __EXTENTIO__
#include <linux/rbtree.h>
+#include <linux/refcount.h>
#include "ulist.h"
/* bits for the extent state */
#define EXTENT_DEFRAG (1U << 6)
#define EXTENT_BOUNDARY (1U << 9)
#define EXTENT_NODATASUM (1U << 10)
-#define EXTENT_DO_ACCOUNTING (1U << 11)
+#define EXTENT_CLEAR_META_RESV (1U << 11)
#define EXTENT_FIRST_DELALLOC (1U << 12)
#define EXTENT_NEED_WAIT (1U << 13)
#define EXTENT_DAMAGED (1U << 14)
#define EXTENT_NORESERVE (1U << 15)
#define EXTENT_QGROUP_RESERVED (1U << 16)
#define EXTENT_CLEAR_DATA_RESV (1U << 17)
+#define EXTENT_DELALLOC_NEW (1U << 18)
#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
+#define EXTENT_DO_ACCOUNTING (EXTENT_CLEAR_META_RESV | \
+ EXTENT_CLEAR_DATA_RESV)
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
/*
/* ADD NEW ELEMENTS AFTER THIS */
wait_queue_head_t wq;
- atomic_t refs;
+ refcount_t refs;
unsigned state;
struct io_failure_record *failrec;
em->flags = 0;
em->compress_type = BTRFS_COMPRESS_NONE;
em->generation = 0;
- atomic_set(&em->refs, 1);
+ refcount_set(&em->refs, 1);
INIT_LIST_HEAD(&em->list);
return em;
}
{
if (!em)
return;
- WARN_ON(atomic_read(&em->refs) == 0);
- if (atomic_dec_and_test(&em->refs)) {
+ WARN_ON(refcount_read(&em->refs) == 0);
+ if (refcount_dec_and_test(&em->refs)) {
WARN_ON(extent_map_in_tree(em));
WARN_ON(!list_empty(&em->list));
if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
struct extent_map *em,
int modified)
{
- atomic_inc(&em->refs);
+ refcount_inc(&em->refs);
em->mod_start = em->start;
em->mod_len = em->len;
if (strict && !(end > em->start && start < extent_map_end(em)))
return NULL;
- atomic_inc(&em->refs);
+ refcount_inc(&em->refs);
return em;
}
#define __EXTENTMAP__
#include <linux/rbtree.h>
+#include <linux/refcount.h>
#define EXTENT_MAP_LAST_BYTE ((u64)-4)
#define EXTENT_MAP_HOLE ((u64)-3)
*/
struct map_lookup *map_lookup;
};
- atomic_t refs;
+ refcount_t refs;
unsigned int compress_type;
struct list_head list;
};
}
+static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
+ const u64 start,
+ const u64 len,
+ struct extent_state **cached_state)
+{
+ u64 search_start = start;
+ const u64 end = start + len - 1;
+
+ while (search_start < end) {
+ const u64 search_len = end - search_start + 1;
+ struct extent_map *em;
+ u64 em_len;
+ int ret = 0;
+
+ em = btrfs_get_extent(inode, NULL, 0, search_start,
+ search_len, 0);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ if (em->block_start != EXTENT_MAP_HOLE)
+ goto next;
+
+ em_len = em->len;
+ if (em->start < search_start)
+ em_len -= search_start - em->start;
+ if (em_len > search_len)
+ em_len = search_len;
+
+ ret = set_extent_bit(&inode->io_tree, search_start,
+ search_start + em_len - 1,
+ EXTENT_DELALLOC_NEW,
+ NULL, cached_state, GFP_NOFS);
+next:
+ search_start = extent_map_end(em);
+ free_extent_map(em);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
/*
* This function locks the extent and properly waits for data=ordered extents
* to finish before allowing the pages to be modified if need.
+ round_up(pos + write_bytes - start_pos,
fs_info->sectorsize) - 1;
- if (start_pos < inode->vfs_inode.i_size) {
+ if (start_pos < inode->vfs_inode.i_size ||
+ (inode->flags & BTRFS_INODE_PREALLOC)) {
struct btrfs_ordered_extent *ordered;
+ unsigned int clear_bits;
+
lock_extent_bits(&inode->io_tree, start_pos, last_pos,
cached_state);
ordered = btrfs_lookup_ordered_range(inode, start_pos,
}
if (ordered)
btrfs_put_ordered_extent(ordered);
-
+ ret = btrfs_find_new_delalloc_bytes(inode, start_pos,
+ last_pos - start_pos + 1,
+ cached_state);
+ clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG;
+ if (ret)
+ clear_bits |= EXTENT_DELALLOC_NEW | EXTENT_LOCKED;
clear_extent_bit(&inode->io_tree, start_pos,
- last_pos, EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
- 0, 0, cached_state, GFP_NOFS);
+ last_pos, clear_bits,
+ (clear_bits & EXTENT_LOCKED) ? 1 : 0,
+ 0, cached_state, GFP_NOFS);
+ if (ret)
+ return ret;
*lockstart = start_pos;
*lockend = last_pos;
ret = 1;
int ret = 0;
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, *start, *len, 0);
- if (IS_ERR_OR_NULL(em)) {
- if (!em)
- ret = -ENOMEM;
- else
- ret = PTR_ERR(em);
- return ret;
- }
+ if (IS_ERR(em))
+ return PTR_ERR(em);
/* Hole or vacuum extent(only exists in no-hole mode) */
if (em->block_start == EXTENT_MAP_HOLE) {
while (1) {
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
alloc_end - cur_offset, 0);
- if (IS_ERR_OR_NULL(em)) {
- if (!em)
- ret = -ENOMEM;
- else
- ret = PTR_ERR(em);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
break;
}
last_byte = min(extent_map_end(em), alloc_end);
}
ret = btrfs_qgroup_reserve_data(inode, cur_offset,
last_byte - cur_offset);
- if (ret < 0)
+ if (ret < 0) {
+ free_extent_map(em);
break;
+ }
} else {
/*
* Do not need to reserve unwritten extent for this
io_ctl->orig = io_ctl->cur;
io_ctl->size = PAGE_SIZE;
if (clear)
- memset(io_ctl->cur, 0, PAGE_SIZE);
+ clear_page(io_ctl->cur);
}
static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl)
u64 ram_bytes, int compress_type,
int type);
+static void __endio_write_update_ordered(struct inode *inode,
+ const u64 offset, const u64 bytes,
+ const bool uptodate);
+
+/*
+ * Cleanup all submitted ordered extents in specified range to handle errors
+ * from the fill_dellaloc() callback.
+ *
+ * NOTE: caller must ensure that when an error happens, it can not call
+ * extent_clear_unlock_delalloc() to clear both the bits EXTENT_DO_ACCOUNTING
+ * and EXTENT_DELALLOC simultaneously, because that causes the reserved metadata
+ * to be released, which we want to happen only when finishing the ordered
+ * extent (btrfs_finish_ordered_io()). Also note that the caller of the
+ * fill_delalloc() callback already does proper cleanup for the first page of
+ * the range, that is, it invokes the callback writepage_end_io_hook() for the
+ * range of the first page.
+ */
+static inline void btrfs_cleanup_ordered_extents(struct inode *inode,
+ const u64 offset,
+ const u64 bytes)
+{
+ return __endio_write_update_ordered(inode, offset + PAGE_SIZE,
+ bytes - PAGE_SIZE, false);
+}
+
static int btrfs_dirty_inode(struct inode *inode);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
}
if (ret <= 0) {
unsigned long clear_flags = EXTENT_DELALLOC |
- EXTENT_DEFRAG;
+ EXTENT_DELALLOC_NEW | EXTENT_DEFRAG;
unsigned long page_error_op;
clear_flags |= (ret < 0) ? EXTENT_DO_ACCOUNTING : 0;
PAGE_SET_WRITEBACK |
page_error_op |
PAGE_END_WRITEBACK);
- btrfs_free_reserved_data_space_noquota(inode, start,
- end - start + 1);
+ if (ret == 0)
+ btrfs_free_reserved_data_space_noquota(inode,
+ start,
+ end - start + 1);
goto free_pages_out;
}
}
async_extent->start +
async_extent->ram_size - 1,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DELALLOC_NEW |
EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK |
u64 num_bytes;
unsigned long ram_size;
u64 disk_num_bytes;
- u64 cur_alloc_size;
+ u64 cur_alloc_size = 0;
u64 blocksize = fs_info->sectorsize;
struct btrfs_key ins;
struct extent_map *em;
+ unsigned clear_bits;
+ unsigned long page_ops;
+ bool extent_reserved = false;
int ret = 0;
if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
extent_clear_unlock_delalloc(inode, start, end,
delalloc_end, NULL,
EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DELALLOC_NEW |
EXTENT_DEFRAG, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK);
start + num_bytes - 1, 0);
while (disk_num_bytes > 0) {
- unsigned long op;
-
cur_alloc_size = disk_num_bytes;
ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
fs_info->sectorsize, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
goto out_unlock;
+ cur_alloc_size = ins.offset;
+ extent_reserved = true;
ram_size = ins.offset;
em = create_io_em(inode, start, ins.offset, /* len */
goto out_reserve;
free_extent_map(em);
- cur_alloc_size = ins.offset;
ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
ram_size, cur_alloc_size, 0);
if (ret)
BTRFS_DATA_RELOC_TREE_OBJECTID) {
ret = btrfs_reloc_clone_csums(inode, start,
cur_alloc_size);
+ /*
+ * Only drop cache here, and process as normal.
+ *
+ * We must not allow extent_clear_unlock_delalloc()
+ * at out_unlock label to free meta of this ordered
+ * extent, as its meta should be freed by
+ * btrfs_finish_ordered_io().
+ *
+ * So we must continue until @start is increased to
+ * skip current ordered extent.
+ */
if (ret)
- goto out_drop_extent_cache;
+ btrfs_drop_extent_cache(BTRFS_I(inode), start,
+ start + ram_size - 1, 0);
}
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
- if (disk_num_bytes < cur_alloc_size)
- break;
-
/* we're not doing compressed IO, don't unlock the first
* page (which the caller expects to stay locked), don't
* clear any dirty bits and don't set any writeback bits
* Do set the Private2 bit so we know this page was properly
* setup for writepage
*/
- op = unlock ? PAGE_UNLOCK : 0;
- op |= PAGE_SET_PRIVATE2;
+ page_ops = unlock ? PAGE_UNLOCK : 0;
+ page_ops |= PAGE_SET_PRIVATE2;
extent_clear_unlock_delalloc(inode, start,
start + ram_size - 1,
delalloc_end, locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC,
- op);
- disk_num_bytes -= cur_alloc_size;
+ page_ops);
+ if (disk_num_bytes < cur_alloc_size)
+ disk_num_bytes = 0;
+ else
+ disk_num_bytes -= cur_alloc_size;
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
start += cur_alloc_size;
+ extent_reserved = false;
+
+ /*
+ * btrfs_reloc_clone_csums() error, since start is increased
+ * extent_clear_unlock_delalloc() at out_unlock label won't
+ * free metadata of current ordered extent, we're OK to exit.
+ */
+ if (ret)
+ goto out_unlock;
}
out:
return ret;
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_unlock:
+ clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
+ page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
+ PAGE_END_WRITEBACK;
+ /*
+ * If we reserved an extent for our delalloc range (or a subrange) and
+ * failed to create the respective ordered extent, then it means that
+ * when we reserved the extent we decremented the extent's size from
+ * the data space_info's bytes_may_use counter and incremented the
+ * space_info's bytes_reserved counter by the same amount. We must make
+ * sure extent_clear_unlock_delalloc() does not try to decrement again
+ * the data space_info's bytes_may_use counter, therefore we do not pass
+ * it the flag EXTENT_CLEAR_DATA_RESV.
+ */
+ if (extent_reserved) {
+ extent_clear_unlock_delalloc(inode, start,
+ start + cur_alloc_size,
+ start + cur_alloc_size,
+ locked_page,
+ clear_bits,
+ page_ops);
+ start += cur_alloc_size;
+ if (start >= end)
+ goto out;
+ }
extent_clear_unlock_delalloc(inode, start, end, delalloc_end,
locked_page,
- EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
- EXTENT_DELALLOC | EXTENT_DEFRAG,
- PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
- PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
+ clear_bits | EXTENT_CLEAR_DATA_RESV,
+ page_ops);
goto out;
}
BUG_ON(ret); /* -ENOMEM */
if (root->root_key.objectid ==
- BTRFS_DATA_RELOC_TREE_OBJECTID) {
+ BTRFS_DATA_RELOC_TREE_OBJECTID)
+ /*
+ * Error handled later, as we must prevent
+ * extent_clear_unlock_delalloc() in error handler
+ * from freeing metadata of created ordered extent.
+ */
ret = btrfs_reloc_clone_csums(inode, cur_offset,
num_bytes);
- if (ret) {
- if (!nolock && nocow)
- btrfs_end_write_no_snapshoting(root);
- goto error;
- }
- }
extent_clear_unlock_delalloc(inode, cur_offset,
cur_offset + num_bytes - 1, end,
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
+
+ /*
+ * btrfs_reloc_clone_csums() error, now we're OK to call error
+ * handler, as metadata for created ordered extent will only
+ * be freed by btrfs_finish_ordered_io().
+ */
+ if (ret)
+ goto error;
if (cur_offset > end)
break;
}
ret = cow_file_range_async(inode, locked_page, start, end,
page_started, nr_written);
}
+ if (ret)
+ btrfs_cleanup_ordered_extents(inode, start, end - start + 1);
return ret;
}
btrfs_add_delalloc_inodes(root, inode);
spin_unlock(&BTRFS_I(inode)->lock);
}
+
+ if (!(state->state & EXTENT_DELALLOC_NEW) &&
+ (*bits & EXTENT_DELALLOC_NEW)) {
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->new_delalloc_bytes += state->end + 1 -
+ state->start;
+ spin_unlock(&BTRFS_I(inode)->lock);
+ }
}
/*
if (*bits & EXTENT_FIRST_DELALLOC) {
*bits &= ~EXTENT_FIRST_DELALLOC;
- } else if (!(*bits & EXTENT_DO_ACCOUNTING)) {
+ } else if (!(*bits & EXTENT_CLEAR_META_RESV)) {
spin_lock(&inode->lock);
inode->outstanding_extents -= num_extents;
spin_unlock(&inode->lock);
* don't need to call dellalloc_release_metadata if there is an
* error.
*/
- if (*bits & EXTENT_DO_ACCOUNTING &&
+ if (*bits & EXTENT_CLEAR_META_RESV &&
root != fs_info->tree_root)
btrfs_delalloc_release_metadata(inode, len);
if (btrfs_is_testing(fs_info))
return;
- if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
- && do_list && !(state->state & EXTENT_NORESERVE)
- && (*bits & (EXTENT_DO_ACCOUNTING |
- EXTENT_CLEAR_DATA_RESV)))
+ if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID &&
+ do_list && !(state->state & EXTENT_NORESERVE) &&
+ (*bits & EXTENT_CLEAR_DATA_RESV))
btrfs_free_reserved_data_space_noquota(
&inode->vfs_inode,
state->start, len);
btrfs_del_delalloc_inode(root, inode);
spin_unlock(&inode->lock);
}
+
+ if ((state->state & EXTENT_DELALLOC_NEW) &&
+ (*bits & EXTENT_DELALLOC_NEW)) {
+ spin_lock(&inode->lock);
+ ASSERT(inode->new_delalloc_bytes >= len);
+ inode->new_delalloc_bytes -= len;
+ spin_unlock(&inode->lock);
+ }
}
/*
u64 logical_len = ordered_extent->len;
bool nolock;
bool truncated = false;
+ bool range_locked = false;
+ bool clear_new_delalloc_bytes = false;
+
+ if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
+ !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
+ !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
+ clear_new_delalloc_bytes = true;
nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
goto out;
}
+ range_locked = true;
lock_extent_bits(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset + ordered_extent->len - 1,
&cached_state);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
- goto out_unlock;
+ goto out;
}
trans->block_rsv = &fs_info->delalloc_block_rsv;
trans->transid);
if (ret < 0) {
btrfs_abort_transaction(trans, ret);
- goto out_unlock;
+ goto out;
}
add_pending_csums(trans, inode, &ordered_extent->list);
ret = btrfs_update_inode_fallback(trans, root, inode);
if (ret) { /* -ENOMEM or corruption */
btrfs_abort_transaction(trans, ret);
- goto out_unlock;
+ goto out;
}
ret = 0;
-out_unlock:
- unlock_extent_cached(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset +
- ordered_extent->len - 1, &cached_state, GFP_NOFS);
out:
+ if (range_locked || clear_new_delalloc_bytes) {
+ unsigned int clear_bits = 0;
+
+ if (range_locked)
+ clear_bits |= EXTENT_LOCKED;
+ if (clear_new_delalloc_bytes)
+ clear_bits |= EXTENT_DELALLOC_NEW;
+ clear_extent_bit(&BTRFS_I(inode)->io_tree,
+ ordered_extent->file_offset,
+ ordered_extent->file_offset +
+ ordered_extent->len - 1,
+ clear_bits,
+ (clear_bits & EXTENT_LOCKED) ? 1 : 0,
+ 0, &cached_state, GFP_NOFS);
+ }
+
if (root != fs_info->tree_root)
btrfs_delalloc_release_metadata(BTRFS_I(inode),
ordered_extent->len);
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
item_end +=
btrfs_file_extent_num_bytes(leaf, fi);
+
+ trace_btrfs_truncate_show_fi_regular(
+ BTRFS_I(inode), leaf, fi,
+ found_key.offset);
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
item_end += btrfs_file_extent_inline_len(leaf,
path->slots[0], fi);
+
+ trace_btrfs_truncate_show_fi_inline(
+ BTRFS_I(inode), leaf, fi, path->slots[0],
+ found_key.offset);
}
item_end--;
}
btrfs_free_path(path);
- if (err == 0) {
- /* only inline file may have last_size != new_size */
- if (new_size >= fs_info->sectorsize ||
- new_size > fs_info->max_inline)
- ASSERT(last_size == new_size);
- }
-
if (be_nice && bytes_deleted > SZ_32M) {
unsigned long updates = trans->delayed_ref_updates;
if (updates) {
*
* This also copies inline extents directly into the page.
*/
-
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
struct page *page,
size_t pg_offset, u64 start, u64 len,
found_type == BTRFS_FILE_EXTENT_PREALLOC) {
extent_end = extent_start +
btrfs_file_extent_num_bytes(leaf, item);
+
+ trace_btrfs_get_extent_show_fi_regular(inode, leaf, item,
+ extent_start);
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
size_t size;
size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_end = ALIGN(extent_start + size,
fs_info->sectorsize);
+
+ trace_btrfs_get_extent_show_fi_inline(inode, leaf, item,
+ path->slots[0],
+ extent_start);
}
next:
if (start >= extent_end) {
em = btrfs_get_extent(inode, page, pg_offset, start, len, create);
if (IS_ERR(em))
return em;
- if (em) {
- /*
- * if our em maps to
- * - a hole or
- * - a pre-alloc extent,
- * there might actually be delalloc bytes behind it.
- */
- if (em->block_start != EXTENT_MAP_HOLE &&
- !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- return em;
- else
- hole_em = em;
- }
+ /*
+ * If our em maps to:
+ * - a hole or
+ * - a pre-alloc extent,
+ * there might actually be delalloc bytes behind it.
+ */
+ if (em->block_start != EXTENT_MAP_HOLE &&
+ !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+ return em;
+ else
+ hole_em = em;
/* check to see if we've wrapped (len == -1 or similar) */
end = start + len;
bio_put(bio);
}
-static void btrfs_endio_direct_write_update_ordered(struct inode *inode,
- const u64 offset,
- const u64 bytes,
- const int uptodate)
+static void __endio_write_update_ordered(struct inode *inode,
+ const u64 offset, const u64 bytes,
+ const bool uptodate)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ordered_extent *ordered = NULL;
+ struct btrfs_workqueue *wq;
+ btrfs_work_func_t func;
u64 ordered_offset = offset;
u64 ordered_bytes = bytes;
int ret;
+ if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ wq = fs_info->endio_freespace_worker;
+ func = btrfs_freespace_write_helper;
+ } else {
+ wq = fs_info->endio_write_workers;
+ func = btrfs_endio_write_helper;
+ }
+
again:
ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
&ordered_offset,
if (!ret)
goto out_test;
- btrfs_init_work(&ordered->work, btrfs_endio_write_helper,
- finish_ordered_fn, NULL, NULL);
- btrfs_queue_work(fs_info->endio_write_workers, &ordered->work);
+ btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL);
+ btrfs_queue_work(wq, &ordered->work);
out_test:
/*
* our bio might span multiple ordered extents. If we haven't
struct btrfs_dio_private *dip = bio->bi_private;
struct bio *dio_bio = dip->dio_bio;
- btrfs_endio_direct_write_update_ordered(dip->inode,
- dip->logical_offset,
- dip->bytes,
- !bio->bi_error);
+ __endio_write_update_ordered(dip->inode, dip->logical_offset,
+ dip->bytes, !bio->bi_error);
kfree(dip);
io_bio = NULL;
} else {
if (write)
- btrfs_endio_direct_write_update_ordered(inode,
+ __endio_write_update_ordered(inode,
file_offset,
dio_bio->bi_iter.bi_size,
- 0);
+ false);
else
unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
file_offset + dio_bio->bi_iter.bi_size - 1);
*/
if (dio_data.unsubmitted_oe_range_start <
dio_data.unsubmitted_oe_range_end)
- btrfs_endio_direct_write_update_ordered(inode,
+ __endio_write_update_ordered(inode,
dio_data.unsubmitted_oe_range_start,
dio_data.unsubmitted_oe_range_end -
dio_data.unsubmitted_oe_range_start,
- 0);
+ false);
} else if (ret >= 0 && (size_t)ret < count)
btrfs_delalloc_release_space(inode, offset,
count - (size_t)ret);
if (!inode_evicting)
clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DELALLOC_NEW |
EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, 1, 0, &cached_state,
GFP_NOFS);
if (!inode_evicting) {
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY |
- EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 1,
+ EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
&cached_state, GFP_NOFS);
__btrfs_releasepage(page, GFP_NOFS);
ei->last_sub_trans = 0;
ei->logged_trans = 0;
ei->delalloc_bytes = 0;
+ ei->new_delalloc_bytes = 0;
ei->defrag_bytes = 0;
ei->disk_i_size = 0;
ei->flags = 0;
WARN_ON(BTRFS_I(inode)->outstanding_extents);
WARN_ON(BTRFS_I(inode)->reserved_extents);
WARN_ON(BTRFS_I(inode)->delalloc_bytes);
+ WARN_ON(BTRFS_I(inode)->new_delalloc_bytes);
WARN_ON(BTRFS_I(inode)->csum_bytes);
WARN_ON(BTRFS_I(inode)->defrag_bytes);
stat->dev = BTRFS_I(inode)->root->anon_dev;
spin_lock(&BTRFS_I(inode)->lock);
- delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
+ delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes;
spin_unlock(&BTRFS_I(inode)->lock);
stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
ALIGN(delalloc_bytes, blocksize)) >> 9;
if (ret)
return ret;
- if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
mnt_drop_write_file(file);
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
}
kfree(vol_args);
out:
mutex_unlock(&fs_info->volume_mutex);
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
mnt_drop_write_file(file);
return ret;
}
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1))
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
mutex_lock(&fs_info->volume_mutex);
kfree(vol_args);
out:
mutex_unlock(&fs_info->volume_mutex);
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
return ret;
}
if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
return -EOPNOTSUPP;
- if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
goto out;
}
ret = btrfs_rm_device(fs_info, vol_args->name, 0);
}
mutex_unlock(&fs_info->volume_mutex);
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
if (!ret) {
if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
if (ret)
return ret;
- if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
goto out_drop_write;
}
btrfs_info(fs_info, "disk deleted %s", vol_args->name);
kfree(vol_args);
out:
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
out_drop_write:
mnt_drop_write_file(file);
ret = -EROFS;
goto out;
}
- if (atomic_xchg(
- &fs_info->mutually_exclusive_operation_running, 1)) {
+ if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
} else {
ret = btrfs_dev_replace_by_ioctl(fs_info, p);
- atomic_set(
- &fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
}
break;
case BTRFS_IOCTL_DEV_REPLACE_CMD_STATUS:
return ret;
again:
- if (!atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+ if (!test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
need_unlock = true;
}
locked:
- BUG_ON(!atomic_read(&fs_info->mutually_exclusive_operation_running));
+ BUG_ON(!test_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
if (arg) {
bargs = memdup_user(arg, sizeof(*bargs));
do_balance:
/*
- * Ownership of bctl and mutually_exclusive_operation_running
+ * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP
* goes to to btrfs_balance. bctl is freed in __cancel_balance,
* or, if restriper was paused all the way until unmount, in
- * free_fs_info. mutually_exclusive_operation_running is
- * cleared in __cancel_balance.
+ * free_fs_info. The flag is cleared in __cancel_balance.
*/
need_unlock = false;
mutex_unlock(&fs_info->balance_mutex);
mutex_unlock(&fs_info->volume_mutex);
if (need_unlock)
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
out:
mnt_drop_write_file(file);
return ret;
set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);
/* one ref for the tree */
- atomic_set(&entry->refs, 1);
+ refcount_set(&entry->refs, 1);
init_waitqueue_head(&entry->wait);
INIT_LIST_HEAD(&entry->list);
INIT_LIST_HEAD(&entry->root_extent_list);
out:
if (!ret && cached && entry) {
*cached = entry;
- atomic_inc(&entry->refs);
+ refcount_inc(&entry->refs);
}
spin_unlock_irqrestore(&tree->lock, flags);
return ret == 0;
out:
if (!ret && cached && entry) {
*cached = entry;
- atomic_inc(&entry->refs);
+ refcount_inc(&entry->refs);
}
spin_unlock_irqrestore(&tree->lock, flags);
return ret == 0;
if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
continue;
list_add(&ordered->log_list, logged_list);
- atomic_inc(&ordered->refs);
+ refcount_inc(&ordered->refs);
}
spin_unlock_irq(&tree->lock);
}
trace_btrfs_ordered_extent_put(entry->inode, entry);
- if (atomic_dec_and_test(&entry->refs)) {
+ if (refcount_dec_and_test(&entry->refs)) {
ASSERT(list_empty(&entry->log_list));
ASSERT(list_empty(&entry->trans_list));
ASSERT(list_empty(&entry->root_extent_list));
spin_lock(&fs_info->trans_lock);
trans = fs_info->running_transaction;
if (trans)
- atomic_inc(&trans->use_count);
+ refcount_inc(&trans->use_count);
spin_unlock(&fs_info->trans_lock);
ASSERT(trans);
list_move_tail(&ordered->root_extent_list,
&root->ordered_extents);
- atomic_inc(&ordered->refs);
+ refcount_inc(&ordered->refs);
spin_unlock(&root->ordered_extent_lock);
btrfs_init_work(&ordered->flush_work,
if (!offset_in_entry(entry, file_offset))
entry = NULL;
if (entry)
- atomic_inc(&entry->refs);
+ refcount_inc(&entry->refs);
out:
spin_unlock_irq(&tree->lock);
return entry;
}
out:
if (entry)
- atomic_inc(&entry->refs);
+ refcount_inc(&entry->refs);
spin_unlock_irq(&tree->lock);
return entry;
}
goto out;
entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
- atomic_inc(&entry->refs);
+ refcount_inc(&entry->refs);
out:
spin_unlock_irq(&tree->lock);
return entry;
int compress_type;
/* reference count */
- atomic_t refs;
+ refcount_t refs;
/* the inode we belong to */
struct inode *inode;
* - check all ioctl parameters
*/
-/*
- * one struct for each qgroup, organized in fs_info->qgroup_tree.
- */
-struct btrfs_qgroup {
- u64 qgroupid;
-
- /*
- * state
- */
- u64 rfer; /* referenced */
- u64 rfer_cmpr; /* referenced compressed */
- u64 excl; /* exclusive */
- u64 excl_cmpr; /* exclusive compressed */
-
- /*
- * limits
- */
- u64 lim_flags; /* which limits are set */
- u64 max_rfer;
- u64 max_excl;
- u64 rsv_rfer;
- u64 rsv_excl;
-
- /*
- * reservation tracking
- */
- u64 reserved;
-
- /*
- * lists
- */
- struct list_head groups; /* groups this group is member of */
- struct list_head members; /* groups that are members of this group */
- struct list_head dirty; /* dirty groups */
- struct rb_node node; /* tree of qgroups */
-
- /*
- * temp variables for accounting operations
- * Refer to qgroup_shared_accounting() for details.
- */
- u64 old_refcnt;
- u64 new_refcnt;
-};
-
static void btrfs_qgroup_update_old_refcnt(struct btrfs_qgroup *qg, u64 seq,
int mod)
{
qgroup->excl += sign * num_bytes;
qgroup->excl_cmpr += sign * num_bytes;
if (sign > 0) {
+ trace_qgroup_update_reserve(fs_info, qgroup, -(s64)num_bytes);
if (qgroup->reserved < num_bytes)
report_reserved_underflow(fs_info, qgroup, num_bytes);
else
WARN_ON(sign < 0 && qgroup->excl < num_bytes);
qgroup->excl += sign * num_bytes;
if (sign > 0) {
+ trace_qgroup_update_reserve(fs_info, qgroup,
+ -(s64)num_bytes);
if (qgroup->reserved < num_bytes)
report_reserved_underflow(fs_info, qgroup,
num_bytes);
if (!ret) {
/*
- * Use (u64)-1 as time_seq to do special search, which
+ * Use SEQ_LAST as time_seq to do special search, which
* doesn't lock tree or delayed_refs and search current
* root. It's safe inside commit_transaction().
*/
ret = btrfs_find_all_roots(trans, fs_info,
- record->bytenr, (u64)-1, &new_roots);
+ record->bytenr, SEQ_LAST, &new_roots);
if (ret < 0)
goto cleanup;
if (qgroup_to_skip)
struct btrfs_fs_info *fs_info = root->fs_info;
u64 ref_root = root->root_key.objectid;
int ret = 0;
+ int retried = 0;
struct ulist_node *unode;
struct ulist_iterator uiter;
if (num_bytes == 0)
return 0;
-
+retry:
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
if (!quota_root)
qg = unode_aux_to_qgroup(unode);
if (enforce && !qgroup_check_limits(qg, num_bytes)) {
+ /*
+ * Commit the tree and retry, since we may have
+ * deletions which would free up space.
+ */
+ if (!retried && qg->reserved > 0) {
+ struct btrfs_trans_handle *trans;
+
+ spin_unlock(&fs_info->qgroup_lock);
+ ret = btrfs_start_delalloc_inodes(root, 0);
+ if (ret)
+ return ret;
+ btrfs_wait_ordered_extents(root, -1, 0, (u64)-1);
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ ret = btrfs_commit_transaction(trans);
+ if (ret)
+ return ret;
+ retried++;
+ goto retry;
+ }
ret = -EDQUOT;
goto out;
}
qg = unode_aux_to_qgroup(unode);
+ trace_qgroup_update_reserve(fs_info, qg, num_bytes);
qg->reserved += num_bytes;
}
qg = unode_aux_to_qgroup(unode);
+ trace_qgroup_update_reserve(fs_info, qg, -(s64)num_bytes);
if (qg->reserved < num_bytes)
report_reserved_underflow(fs_info, qg, num_bytes);
else
spin_unlock(&fs_info->qgroup_lock);
}
-void assert_qgroups_uptodate(struct btrfs_trans_handle *trans)
-{
- if (list_empty(&trans->qgroup_ref_list) && !trans->delayed_ref_elem.seq)
- return;
- btrfs_err(trans->fs_info,
- "qgroups not uptodate in trans handle %p: list is%s empty, seq is %#x.%x",
- trans, list_empty(&trans->qgroup_ref_list) ? "" : " not",
- (u32)(trans->delayed_ref_elem.seq >> 32),
- (u32)trans->delayed_ref_elem.seq);
- BUG();
-}
-
/*
* returns < 0 on error, 0 when more leafs are to be scanned.
* returns 1 when done.
if (ret < 0)
goto out;
- if (free) {
- btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
- BTRFS_I(inode)->root->objectid,
- changeset.bytes_changed);
+ if (free)
trace_op = QGROUP_FREE;
- }
trace_btrfs_qgroup_release_data(inode, start, len,
changeset.bytes_changed, trace_op);
+ if (free)
+ btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
+ BTRFS_I(inode)->root->objectid,
+ changeset.bytes_changed);
out:
ulist_release(&changeset.range_changed);
return ret;
return 0;
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
+ trace_qgroup_meta_reserve(root, (s64)num_bytes);
ret = qgroup_reserve(root, num_bytes, enforce);
if (ret < 0)
return ret;
reserved = atomic64_xchg(&root->qgroup_meta_rsv, 0);
if (reserved == 0)
return;
+ trace_qgroup_meta_reserve(root, -(s64)reserved);
btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved);
}
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
WARN_ON(atomic64_read(&root->qgroup_meta_rsv) < num_bytes);
atomic64_sub(num_bytes, &root->qgroup_meta_rsv);
+ trace_qgroup_meta_reserve(root, -(s64)num_bytes);
btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes);
}
struct ulist *old_roots;
};
+/*
+ * one struct for each qgroup, organized in fs_info->qgroup_tree.
+ */
+struct btrfs_qgroup {
+ u64 qgroupid;
+
+ /*
+ * state
+ */
+ u64 rfer; /* referenced */
+ u64 rfer_cmpr; /* referenced compressed */
+ u64 excl; /* exclusive */
+ u64 excl_cmpr; /* exclusive compressed */
+
+ /*
+ * limits
+ */
+ u64 lim_flags; /* which limits are set */
+ u64 max_rfer;
+ u64 max_excl;
+ u64 rsv_rfer;
+ u64 rsv_excl;
+
+ /*
+ * reservation tracking
+ */
+ u64 reserved;
+
+ /*
+ * lists
+ */
+ struct list_head groups; /* groups this group is member of */
+ struct list_head members; /* groups that are members of this group */
+ struct list_head dirty; /* dirty groups */
+ struct rb_node node; /* tree of qgroups */
+
+ /*
+ * temp variables for accounting operations
+ * Refer to qgroup_shared_accounting() for details.
+ */
+ u64 old_refcnt;
+ u64 new_refcnt;
+};
+
/*
* For qgroup event trace points only
*/
struct btrfs_qgroup_inherit *inherit);
void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
u64 ref_root, u64 num_bytes);
-/*
- * TODO: Add proper trace point for it, as btrfs_qgroup_free() is
- * called by everywhere, can't provide good trace for delayed ref case.
- */
static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info,
u64 ref_root, u64 num_bytes)
{
- btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes);
trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes);
+ btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes);
}
-void assert_qgroups_uptodate(struct btrfs_trans_handle *trans);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
int generic_bio_cnt;
- atomic_t refs;
+ refcount_t refs;
atomic_t stripes_pending;
if (bio_list_empty(&rbio->bio_list)) {
if (!list_empty(&rbio->hash_list)) {
list_del_init(&rbio->hash_list);
- atomic_dec(&rbio->refs);
+ refcount_dec(&rbio->refs);
BUG_ON(!list_empty(&rbio->plug_list));
}
}
/* bump our ref if we were not in the list before */
if (!test_and_set_bit(RBIO_CACHE_BIT, &rbio->flags))
- atomic_inc(&rbio->refs);
+ refcount_inc(&rbio->refs);
if (!list_empty(&rbio->stripe_cache)){
list_move(&rbio->stripe_cache, &table->stripe_cache);
test_bit(RBIO_CACHE_BIT, &cur->flags) &&
!test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
list_del_init(&cur->hash_list);
- atomic_dec(&cur->refs);
+ refcount_dec(&cur->refs);
steal_rbio(cur, rbio);
cache_drop = cur;
}
}
lockit:
- atomic_inc(&rbio->refs);
+ refcount_inc(&rbio->refs);
list_add(&rbio->hash_list, &h->hash_list);
out:
spin_unlock_irqrestore(&h->lock, flags);
}
list_del_init(&rbio->hash_list);
- atomic_dec(&rbio->refs);
+ refcount_dec(&rbio->refs);
/*
* we use the plug list to hold all the rbios
list_del_init(&rbio->plug_list);
list_add(&next->hash_list, &h->hash_list);
- atomic_inc(&next->refs);
+ refcount_inc(&next->refs);
spin_unlock(&rbio->bio_list_lock);
spin_unlock_irqrestore(&h->lock, flags);
{
int i;
- WARN_ON(atomic_read(&rbio->refs) < 0);
- if (!atomic_dec_and_test(&rbio->refs))
+ if (!refcount_dec_and_test(&rbio->refs))
return;
WARN_ON(!list_empty(&rbio->stripe_cache));
rbio->stripe_npages = stripe_npages;
rbio->faila = -1;
rbio->failb = -1;
- atomic_set(&rbio->refs, 1);
+ refcount_set(&rbio->refs, 1);
atomic_set(&rbio->error, 0);
atomic_set(&rbio->stripes_pending, 0);
struct btrfs_raid_bio *rbio;
int ret;
+ if (generic_io) {
+ ASSERT(bbio->mirror_num == mirror_num);
+ btrfs_io_bio(bio)->mirror_num = mirror_num;
+ }
+
rbio = alloc_rbio(fs_info, bbio, stripe_len);
if (IS_ERR(rbio)) {
if (generic_io)
/*
* The following code is used to scrub/replace the parity stripe
*
+ * Caller must have already increased bio_counter for getting @bbio.
+ *
* Note: We need make sure all the pages that add into the scrub/replace
* raid bio are correct and not be changed during the scrub/replace. That
* is those pages just hold metadata or file data with checksum.
ASSERT(rbio->stripe_npages == stripe_nsectors);
bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors);
+ /*
+ * We have already increased bio_counter when getting bbio, record it
+ * so we can free it at rbio_orig_end_io().
+ */
+ rbio->generic_bio_cnt = 1;
+
return rbio;
}
return NULL;
}
+ /*
+ * When we get bbio, we have already increased bio_counter, record it
+ * so we can free it at rbio_orig_end_io()
+ */
+ rbio->generic_bio_cnt = 1;
+
return rbio;
}
return;
}
-int btree_readahead_hook(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb, int err)
+int btree_readahead_hook(struct extent_buffer *eb, int err)
{
+ struct btrfs_fs_info *fs_info = eb->fs_info;
int ret = 0;
struct reada_extent *re;
return ret;
}
-static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
- struct btrfs_device *dev, u64 logical,
+static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
struct btrfs_bio *bbio)
{
+ struct btrfs_fs_info *fs_info = dev->fs_info;
int ret;
struct reada_zone *zone;
struct btrfs_block_group_cache *cache = NULL;
if (!zone)
return NULL;
+ ret = radix_tree_preload(GFP_KERNEL);
+ if (ret) {
+ kfree(zone);
+ return NULL;
+ }
+
zone->start = start;
zone->end = end;
INIT_LIST_HEAD(&zone->list);
zone = NULL;
}
spin_unlock(&fs_info->reada_lock);
+ radix_tree_preload_end();
return zone;
}
struct btrfs_bio *bbio = NULL;
struct btrfs_device *dev;
struct btrfs_device *prev_dev;
- u32 blocksize;
u64 length;
int real_stripes;
int nzones = 0;
if (!re)
return NULL;
- blocksize = fs_info->nodesize;
re->logical = logical;
re->top = *top;
INIT_LIST_HEAD(&re->extctl);
/*
* map block
*/
- length = blocksize;
+ length = fs_info->nodesize;
ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
&length, &bbio, 0);
- if (ret || !bbio || length < blocksize)
+ if (ret || !bbio || length < fs_info->nodesize)
goto error;
if (bbio->num_stripes > BTRFS_MAX_MIRRORS) {
if (!dev->bdev)
continue;
- zone = reada_find_zone(fs_info, dev, logical, bbio);
+ zone = reada_find_zone(dev, logical, bbio);
if (!zone)
continue;
goto error;
}
+ ret = radix_tree_preload(GFP_KERNEL);
+ if (ret)
+ goto error;
+
/* insert extent in reada_tree + all per-device trees, all or nothing */
btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
spin_lock(&fs_info->reada_lock);
re_exist->refcnt++;
spin_unlock(&fs_info->reada_lock);
btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
+ radix_tree_preload_end();
goto error;
}
if (ret) {
spin_unlock(&fs_info->reada_lock);
btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
+ radix_tree_preload_end();
goto error;
}
+ radix_tree_preload_end();
prev_dev = NULL;
dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(
&fs_info->dev_replace);
return 1;
}
-static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
- struct btrfs_device *dev)
+static int reada_start_machine_dev(struct btrfs_device *dev)
{
+ struct btrfs_fs_info *fs_info = dev->fs_info;
struct reada_extent *re = NULL;
int mirror_num = 0;
struct extent_buffer *eb = NULL;
list_for_each_entry(device, &fs_devices->devices, dev_list) {
if (atomic_read(&device->reada_in_flight) <
MAX_IN_FLIGHT)
- enqueued += reada_start_machine_dev(fs_info,
- device);
+ enqueued += reada_start_machine_dev(device);
}
mutex_unlock(&fs_devices->device_list_mutex);
total += enqueued;
struct btrfs_root *root)
{
struct btrfs_root_item *item = &root->root_item;
- struct timespec ct = current_fs_time(root->fs_info->sb);
+ struct timespec ct;
+ ktime_get_real_ts(&ct);
spin_lock(&root->root_item_lock);
btrfs_set_root_ctransid(item, trans->transid);
btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec);
#define SCRUB_MAX_PAGES_PER_BLOCK 16 /* 64k per node/leaf/sector */
struct scrub_recover {
- atomic_t refs;
+ refcount_t refs;
struct btrfs_bio *bbio;
u64 map_length;
};
struct scrub_page *pagev[SCRUB_MAX_PAGES_PER_BLOCK];
int page_count;
atomic_t outstanding_pages;
- atomic_t refs; /* free mem on transition to zero */
+ refcount_t refs; /* free mem on transition to zero */
struct scrub_ctx *sctx;
struct scrub_parity *sparity;
struct {
int nsectors;
- int stripe_len;
+ u64 stripe_len;
- atomic_t refs;
+ refcount_t refs;
struct list_head spages;
* doesn't free the scrub context before or while the workers are
* doing the wakeup() call.
*/
- atomic_t refs;
+ refcount_t refs;
};
struct scrub_fixup_nodatasum {
struct btrfs_device *dev;
};
+struct full_stripe_lock {
+ struct rb_node node;
+ u64 logical;
+ u64 refs;
+ struct mutex mutex;
+};
+
static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
{
- atomic_inc(&sctx->refs);
+ refcount_inc(&sctx->refs);
atomic_inc(&sctx->bios_in_flight);
}
scrub_pause_off(fs_info);
}
+/*
+ * Insert new full stripe lock into full stripe locks tree
+ *
+ * Return pointer to existing or newly inserted full_stripe_lock structure if
+ * everything works well.
+ * Return ERR_PTR(-ENOMEM) if we failed to allocate memory
+ *
+ * NOTE: caller must hold full_stripe_locks_root->lock before calling this
+ * function
+ */
+static struct full_stripe_lock *insert_full_stripe_lock(
+ struct btrfs_full_stripe_locks_tree *locks_root,
+ u64 fstripe_logical)
+{
+ struct rb_node **p;
+ struct rb_node *parent = NULL;
+ struct full_stripe_lock *entry;
+ struct full_stripe_lock *ret;
+
+ WARN_ON(!mutex_is_locked(&locks_root->lock));
+
+ p = &locks_root->root.rb_node;
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct full_stripe_lock, node);
+ if (fstripe_logical < entry->logical) {
+ p = &(*p)->rb_left;
+ } else if (fstripe_logical > entry->logical) {
+ p = &(*p)->rb_right;
+ } else {
+ entry->refs++;
+ return entry;
+ }
+ }
+
+ /* Insert new lock */
+ ret = kmalloc(sizeof(*ret), GFP_KERNEL);
+ if (!ret)
+ return ERR_PTR(-ENOMEM);
+ ret->logical = fstripe_logical;
+ ret->refs = 1;
+ mutex_init(&ret->mutex);
+
+ rb_link_node(&ret->node, parent, p);
+ rb_insert_color(&ret->node, &locks_root->root);
+ return ret;
+}
+
+/*
+ * Search for a full stripe lock of a block group
+ *
+ * Return pointer to existing full stripe lock if found
+ * Return NULL if not found
+ */
+static struct full_stripe_lock *search_full_stripe_lock(
+ struct btrfs_full_stripe_locks_tree *locks_root,
+ u64 fstripe_logical)
+{
+ struct rb_node *node;
+ struct full_stripe_lock *entry;
+
+ WARN_ON(!mutex_is_locked(&locks_root->lock));
+
+ node = locks_root->root.rb_node;
+ while (node) {
+ entry = rb_entry(node, struct full_stripe_lock, node);
+ if (fstripe_logical < entry->logical)
+ node = node->rb_left;
+ else if (fstripe_logical > entry->logical)
+ node = node->rb_right;
+ else
+ return entry;
+ }
+ return NULL;
+}
+
+/*
+ * Helper to get full stripe logical from a normal bytenr.
+ *
+ * Caller must ensure @cache is a RAID56 block group.
+ */
+static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
+ u64 bytenr)
+{
+ u64 ret;
+
+ /*
+ * Due to chunk item size limit, full stripe length should not be
+ * larger than U32_MAX. Just a sanity check here.
+ */
+ WARN_ON_ONCE(cache->full_stripe_len >= U32_MAX);
+
+ /*
+ * round_down() can only handle power of 2, while RAID56 full
+ * stripe length can be 64KiB * n, so we need to manually round down.
+ */
+ ret = div64_u64(bytenr - cache->key.objectid, cache->full_stripe_len) *
+ cache->full_stripe_len + cache->key.objectid;
+ return ret;
+}
+
+/*
+ * Lock a full stripe to avoid concurrency of recovery and read
+ *
+ * It's only used for profiles with parities (RAID5/6), for other profiles it
+ * does nothing.
+ *
+ * Return 0 if we locked full stripe covering @bytenr, with a mutex held.
+ * So caller must call unlock_full_stripe() at the same context.
+ *
+ * Return <0 if encounters error.
+ */
+static int lock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
+ bool *locked_ret)
+{
+ struct btrfs_block_group_cache *bg_cache;
+ struct btrfs_full_stripe_locks_tree *locks_root;
+ struct full_stripe_lock *existing;
+ u64 fstripe_start;
+ int ret = 0;
+
+ *locked_ret = false;
+ bg_cache = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!bg_cache) {
+ ASSERT(0);
+ return -ENOENT;
+ }
+
+ /* Profiles not based on parity don't need full stripe lock */
+ if (!(bg_cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK))
+ goto out;
+ locks_root = &bg_cache->full_stripe_locks_root;
+
+ fstripe_start = get_full_stripe_logical(bg_cache, bytenr);
+
+ /* Now insert the full stripe lock */
+ mutex_lock(&locks_root->lock);
+ existing = insert_full_stripe_lock(locks_root, fstripe_start);
+ mutex_unlock(&locks_root->lock);
+ if (IS_ERR(existing)) {
+ ret = PTR_ERR(existing);
+ goto out;
+ }
+ mutex_lock(&existing->mutex);
+ *locked_ret = true;
+out:
+ btrfs_put_block_group(bg_cache);
+ return ret;
+}
+
+/*
+ * Unlock a full stripe.
+ *
+ * NOTE: Caller must ensure it's the same context calling corresponding
+ * lock_full_stripe().
+ *
+ * Return 0 if we unlock full stripe without problem.
+ * Return <0 for error
+ */
+static int unlock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
+ bool locked)
+{
+ struct btrfs_block_group_cache *bg_cache;
+ struct btrfs_full_stripe_locks_tree *locks_root;
+ struct full_stripe_lock *fstripe_lock;
+ u64 fstripe_start;
+ bool freeit = false;
+ int ret = 0;
+
+ /* If we didn't acquire full stripe lock, no need to continue */
+ if (!locked)
+ return 0;
+
+ bg_cache = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!bg_cache) {
+ ASSERT(0);
+ return -ENOENT;
+ }
+ if (!(bg_cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK))
+ goto out;
+
+ locks_root = &bg_cache->full_stripe_locks_root;
+ fstripe_start = get_full_stripe_logical(bg_cache, bytenr);
+
+ mutex_lock(&locks_root->lock);
+ fstripe_lock = search_full_stripe_lock(locks_root, fstripe_start);
+ /* Unpaired unlock_full_stripe() detected */
+ if (!fstripe_lock) {
+ WARN_ON(1);
+ ret = -ENOENT;
+ mutex_unlock(&locks_root->lock);
+ goto out;
+ }
+
+ if (fstripe_lock->refs == 0) {
+ WARN_ON(1);
+ btrfs_warn(fs_info, "full stripe lock at %llu refcount underflow",
+ fstripe_lock->logical);
+ } else {
+ fstripe_lock->refs--;
+ }
+
+ if (fstripe_lock->refs == 0) {
+ rb_erase(&fstripe_lock->node, &locks_root->root);
+ freeit = true;
+ }
+ mutex_unlock(&locks_root->lock);
+
+ mutex_unlock(&fstripe_lock->mutex);
+ if (freeit)
+ kfree(fstripe_lock);
+out:
+ btrfs_put_block_group(bg_cache);
+ return ret;
+}
+
/*
* used for workers that require transaction commits (i.e., for the
* NOCOW case)
{
struct btrfs_fs_info *fs_info = sctx->fs_info;
- atomic_inc(&sctx->refs);
+ refcount_inc(&sctx->refs);
/*
* increment scrubs_running to prevent cancel requests from
* completing as long as a worker is running. we must also
static void scrub_put_ctx(struct scrub_ctx *sctx)
{
- if (atomic_dec_and_test(&sctx->refs))
+ if (refcount_dec_and_test(&sctx->refs))
scrub_free_ctx(sctx);
}
sctx = kzalloc(sizeof(*sctx), GFP_KERNEL);
if (!sctx)
goto nomem;
- atomic_set(&sctx->refs, 1);
+ refcount_set(&sctx->refs, 1);
sctx->is_dev_replace = is_dev_replace;
sctx->pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO;
sctx->curr = -1;
static inline void scrub_get_recover(struct scrub_recover *recover)
{
- atomic_inc(&recover->refs);
+ refcount_inc(&recover->refs);
}
-static inline void scrub_put_recover(struct scrub_recover *recover)
+static inline void scrub_put_recover(struct btrfs_fs_info *fs_info,
+ struct scrub_recover *recover)
{
- if (atomic_dec_and_test(&recover->refs)) {
+ if (refcount_dec_and_test(&recover->refs)) {
+ btrfs_bio_counter_dec(fs_info);
btrfs_put_bbio(recover->bbio);
kfree(recover);
}
int mirror_index;
int page_num;
int success;
+ bool full_stripe_locked;
static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
have_csum = sblock_to_check->pagev[0]->have_csum;
dev = sblock_to_check->pagev[0]->dev;
+ /*
+ * For RAID5/6, race can happen for a different device scrub thread.
+ * For data corruption, Parity and Data threads will both try
+ * to recovery the data.
+ * Race can lead to doubly added csum error, or even unrecoverable
+ * error.
+ */
+ ret = lock_full_stripe(fs_info, logical, &full_stripe_locked);
+ if (ret < 0) {
+ spin_lock(&sctx->stat_lock);
+ if (ret == -ENOMEM)
+ sctx->stat.malloc_errors++;
+ sctx->stat.read_errors++;
+ sctx->stat.uncorrectable_errors++;
+ spin_unlock(&sctx->stat_lock);
+ return ret;
+ }
+
if (sctx->is_dev_replace && !is_metadata && !have_csum) {
sblocks_for_recheck = NULL;
goto nodatasum_case;
sblock->pagev[page_index]->sblock = NULL;
recover = sblock->pagev[page_index]->recover;
if (recover) {
- scrub_put_recover(recover);
+ scrub_put_recover(fs_info, recover);
sblock->pagev[page_index]->recover =
NULL;
}
kfree(sblocks_for_recheck);
}
+ ret = unlock_full_stripe(fs_info, logical, full_stripe_locked);
+ if (ret < 0)
+ return ret;
return 0;
}
* with a length of PAGE_SIZE, each returned stripe
* represents one mirror
*/
+ btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
- logical, &mapped_length, &bbio, 0, 1);
+ logical, &mapped_length, &bbio);
if (ret || !bbio || mapped_length < sublen) {
btrfs_put_bbio(bbio);
+ btrfs_bio_counter_dec(fs_info);
return -EIO;
}
recover = kzalloc(sizeof(struct scrub_recover), GFP_NOFS);
if (!recover) {
btrfs_put_bbio(bbio);
+ btrfs_bio_counter_dec(fs_info);
return -ENOMEM;
}
- atomic_set(&recover->refs, 1);
+ refcount_set(&recover->refs, 1);
recover->bbio = bbio;
recover->map_length = mapped_length;
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
spin_unlock(&sctx->stat_lock);
- scrub_put_recover(recover);
+ scrub_put_recover(fs_info, recover);
return -ENOMEM;
}
scrub_page_get(page);
scrub_get_recover(recover);
page->recover = recover;
}
- scrub_put_recover(recover);
+ scrub_put_recover(fs_info, recover);
length -= sublen;
logical += sublen;
page_index++;
bio_add_page(bio, page->page, PAGE_SIZE, 0);
if (!retry_failed_mirror && scrub_is_page_on_raid56(page)) {
- if (scrub_submit_raid56_bio_wait(fs_info, bio, page))
+ if (scrub_submit_raid56_bio_wait(fs_info, bio, page)) {
+ page->io_error = 1;
sblock->no_io_error_seen = 0;
+ }
} else {
bio->bi_iter.bi_sector = page->physical >> 9;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
- if (btrfsic_submit_bio_wait(bio))
+ if (btrfsic_submit_bio_wait(bio)) {
+ page->io_error = 1;
sblock->no_io_error_seen = 0;
+ }
}
bio_put(bio);
if (spage->io_error) {
void *mapped_buffer = kmap_atomic(spage->page);
- memset(mapped_buffer, 0, PAGE_SIZE);
+ clear_page(mapped_buffer);
flush_dcache_page(spage->page);
kunmap_atomic(mapped_buffer);
}
static void scrub_block_get(struct scrub_block *sblock)
{
- atomic_inc(&sblock->refs);
+ refcount_inc(&sblock->refs);
}
static void scrub_block_put(struct scrub_block *sblock)
{
- if (atomic_dec_and_test(&sblock->refs)) {
+ if (refcount_dec_and_test(&sblock->refs)) {
int i;
if (sblock->sparity)
int ret;
int i;
+ btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
- &length, &bbio, 0, 1);
+ &length, &bbio);
if (ret || !bbio || !bbio->raid_map)
goto bbio_out;
rbio_out:
bio_put(bio);
bbio_out:
+ btrfs_bio_counter_dec(fs_info);
btrfs_put_bbio(bbio);
spin_lock(&sctx->stat_lock);
sctx->stat.malloc_errors++;
/* one ref inside this function, plus one for each page added to
* a bio later on */
- atomic_set(&sblock->refs, 1);
+ refcount_set(&sblock->refs, 1);
sblock->sctx = sctx;
sblock->no_io_error_seen = 1;
unsigned long *bitmap,
u64 start, u64 len)
{
- u32 offset;
+ u64 offset;
int nsectors;
int sectorsize = sparity->sctx->fs_info->sectorsize;
}
start -= sparity->logic_start;
- start = div_u64_rem(start, sparity->stripe_len, &offset);
- offset /= sectorsize;
+ start = div64_u64_rem(start, sparity->stripe_len, &offset);
+ offset = div_u64(offset, sectorsize);
nsectors = (int)len / sectorsize;
if (offset + nsectors <= sparity->nsectors) {
/* one ref inside this function, plus one for each page added to
* a bio later on */
- atomic_set(&sblock->refs, 1);
+ refcount_set(&sblock->refs, 1);
sblock->sctx = sctx;
sblock->no_io_error_seen = 1;
sblock->sparity = sparity;
for (i = 0; i < nr_data_stripes(map); i++) {
*offset = last_offset + i * map->stripe_len;
- stripe_nr = div_u64(*offset, map->stripe_len);
+ stripe_nr = div64_u64(*offset, map->stripe_len);
stripe_nr = div_u64(stripe_nr, nr_data_stripes(map));
/* Work out the disk rotation on this stripe-set */
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct bio *bio;
struct btrfs_raid_bio *rbio;
- struct scrub_page *spage;
struct btrfs_bio *bbio = NULL;
u64 length;
int ret;
goto out;
length = sparity->logic_end - sparity->logic_start;
+
+ btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_sblock(fs_info, BTRFS_MAP_WRITE, sparity->logic_start,
- &length, &bbio, 0, 1);
+ &length, &bbio);
if (ret || !bbio || !bbio->raid_map)
goto bbio_out;
if (!rbio)
goto rbio_out;
- list_for_each_entry(spage, &sparity->spages, list)
- raid56_add_scrub_pages(rbio, spage->page, spage->logical);
-
scrub_pending_bio_inc(sctx);
raid56_parity_submit_scrub_rbio(rbio);
return;
rbio_out:
bio_put(bio);
bbio_out:
+ btrfs_bio_counter_dec(fs_info);
btrfs_put_bbio(bbio);
bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
sparity->nsectors);
static void scrub_parity_get(struct scrub_parity *sparity)
{
- atomic_inc(&sparity->refs);
+ refcount_inc(&sparity->refs);
}
static void scrub_parity_put(struct scrub_parity *sparity)
{
- if (!atomic_dec_and_test(&sparity->refs))
+ if (!refcount_dec_and_test(&sparity->refs))
return;
scrub_parity_check_and_repair(sparity);
sparity->scrub_dev = sdev;
sparity->logic_start = logic_start;
sparity->logic_end = logic_end;
- atomic_set(&sparity->refs, 1);
+ refcount_set(&sparity->refs, 1);
INIT_LIST_HEAD(&sparity->spages);
sparity->dbitmap = sparity->bitmap;
sparity->ebitmap = (void *)sparity->bitmap + bitmap_len;
physical = map->stripes[num].physical;
offset = 0;
- nstripes = div_u64(length, map->stripe_len);
+ nstripes = div64_u64(length, map->stripe_len);
if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
offset = map->stripe_len * num;
increment = map->stripe_len * map->num_stripes;
while (key.offset < ekey->offset + left_len) {
ei = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
right_type = btrfs_file_extent_type(eb, ei);
- if (right_type != BTRFS_FILE_EXTENT_REG) {
+ if (right_type != BTRFS_FILE_EXTENT_REG &&
+ right_type != BTRFS_FILE_EXTENT_INLINE) {
ret = 0;
goto out;
}
right_disknr = btrfs_file_extent_disk_bytenr(eb, ei);
- right_len = btrfs_file_extent_num_bytes(eb, ei);
+ if (right_type == BTRFS_FILE_EXTENT_INLINE) {
+ right_len = btrfs_file_extent_inline_len(eb, slot, ei);
+ right_len = PAGE_ALIGN(right_len);
+ } else {
+ right_len = btrfs_file_extent_num_bytes(eb, ei);
+ }
right_offset = btrfs_file_extent_offset(eb, ei);
right_gen = btrfs_file_extent_generation(eb, ei);
goto out;
}
+ /*
+ * We just wanted to see if when we have an inline extent, what
+ * follows it is a regular extent (wanted to check the above
+ * condition for inline extents too). This should normally not
+ * happen but it's possible for example when we have an inline
+ * compressed extent representing data with a size matching
+ * the page size (currently the same as sector size).
+ */
+ if (right_type == BTRFS_FILE_EXTENT_INLINE) {
+ ret = 0;
+ goto out;
+ }
+
left_offset_fixed = left_offset;
if (key.offset < ekey->offset) {
/* Fix the right offset for 2a and 7. */
}
if (fs_info->fs_devices->missing_devices >
- fs_info->num_tolerated_disk_barrier_failures &&
- !(*flags & MS_RDONLY)) {
+ fs_info->num_tolerated_disk_barrier_failures) {
btrfs_warn(fs_info,
"too many missing devices, writeable remount is not allowed");
ret = -EACCES;
{
memset(trans, 0, sizeof(*trans));
trans->transid = 1;
- INIT_LIST_HEAD(&trans->qgroup_ref_list);
trans->type = __TRANS_DUMMY;
}
void btrfs_put_transaction(struct btrfs_transaction *transaction)
{
- WARN_ON(atomic_read(&transaction->use_count) == 0);
- if (atomic_dec_and_test(&transaction->use_count)) {
+ WARN_ON(refcount_read(&transaction->use_count) == 0);
+ if (refcount_dec_and_test(&transaction->use_count)) {
BUG_ON(!list_empty(&transaction->list));
WARN_ON(!RB_EMPTY_ROOT(&transaction->delayed_refs.href_root));
if (transaction->delayed_refs.pending_csums)
spin_unlock(&fs_info->trans_lock);
return -EBUSY;
}
- atomic_inc(&cur_trans->use_count);
+ refcount_inc(&cur_trans->use_count);
atomic_inc(&cur_trans->num_writers);
extwriter_counter_inc(cur_trans, type);
spin_unlock(&fs_info->trans_lock);
* One for this trans handle, one so it will live on until we
* commit the transaction.
*/
- atomic_set(&cur_trans->use_count, 2);
+ refcount_set(&cur_trans->use_count, 2);
atomic_set(&cur_trans->pending_ordered, 0);
cur_trans->flags = 0;
cur_trans->start_time = get_seconds();
spin_lock(&fs_info->trans_lock);
cur_trans = fs_info->running_transaction;
if (cur_trans && is_transaction_blocked(cur_trans)) {
- atomic_inc(&cur_trans->use_count);
+ refcount_inc(&cur_trans->use_count);
spin_unlock(&fs_info->trans_lock);
wait_event(fs_info->transaction_wait,
h->type = type;
h->can_flush_pending_bgs = true;
- INIT_LIST_HEAD(&h->qgroup_ref_list);
INIT_LIST_HEAD(&h->new_bgs);
smp_mb();
list_for_each_entry(t, &fs_info->trans_list, list) {
if (t->transid == transid) {
cur_trans = t;
- atomic_inc(&cur_trans->use_count);
+ refcount_inc(&cur_trans->use_count);
ret = 0;
break;
}
if (t->state == TRANS_STATE_COMPLETED)
break;
cur_trans = t;
- atomic_inc(&cur_trans->use_count);
+ refcount_inc(&cur_trans->use_count);
break;
}
}
wake_up_process(info->transaction_kthread);
err = -EIO;
}
- assert_qgroups_uptodate(trans);
kmem_cache_free(btrfs_trans_handle_cachep, trans);
if (must_run_delayed_refs) {
/* take transaction reference */
cur_trans = trans->transaction;
- atomic_inc(&cur_trans->use_count);
+ refcount_inc(&cur_trans->use_count);
btrfs_end_transaction(trans);
spin_lock(&fs_info->trans_lock);
if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
spin_unlock(&fs_info->trans_lock);
- atomic_inc(&cur_trans->use_count);
+ refcount_inc(&cur_trans->use_count);
ret = btrfs_end_transaction(trans);
wait_for_commit(cur_trans);
prev_trans = list_entry(cur_trans->list.prev,
struct btrfs_transaction, list);
if (prev_trans->state != TRANS_STATE_COMPLETED) {
- atomic_inc(&prev_trans->use_count);
+ refcount_inc(&prev_trans->use_count);
spin_unlock(&fs_info->trans_lock);
wait_for_commit(prev_trans);
goto scrub_continue;
}
- /* Reocrd old roots for later qgroup accounting */
- ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
- if (ret) {
- mutex_unlock(&fs_info->reloc_mutex);
- goto scrub_continue;
- }
-
/*
* make sure none of the code above managed to slip in a
* delayed item
*/
btrfs_free_log_root_tree(trans, fs_info);
+ /*
+ * commit_fs_roots() can call btrfs_save_ino_cache(), which generates
+ * new delayed refs. Must handle them or qgroup can be wrong.
+ */
+ ret = btrfs_run_delayed_refs(trans, fs_info, (unsigned long)-1);
+ if (ret) {
+ mutex_unlock(&fs_info->tree_log_mutex);
+ mutex_unlock(&fs_info->reloc_mutex);
+ goto scrub_continue;
+ }
+
+ ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
+ if (ret) {
+ mutex_unlock(&fs_info->tree_log_mutex);
+ mutex_unlock(&fs_info->reloc_mutex);
+ goto scrub_continue;
+ }
+
/*
* Since fs roots are all committed, we can get a quite accurate
* new_roots. So let's do quota accounting.
switch_commit_roots(cur_trans, fs_info);
- assert_qgroups_uptodate(trans);
ASSERT(list_empty(&cur_trans->dirty_bgs));
ASSERT(list_empty(&cur_trans->io_bgs));
update_super_roots(fs_info);
#ifndef __BTRFS_TRANSACTION__
#define __BTRFS_TRANSACTION__
+
+#include <linux/refcount.h>
#include "btrfs_inode.h"
#include "delayed-ref.h"
#include "ctree.h"
* transaction can end
*/
atomic_t num_writers;
- atomic_t use_count;
+ refcount_t use_count;
atomic_t pending_ordered;
unsigned long flags;
unsigned int type;
struct btrfs_root *root;
struct btrfs_fs_info *fs_info;
- struct seq_list delayed_ref_elem;
- struct list_head qgroup_ref_list;
struct list_head new_bgs;
};
if (em->generation <= test_gen)
continue;
/* Need a ref to keep it from getting evicted from cache */
- atomic_inc(&em->refs);
+ refcount_inc(&em->refs);
set_bit(EXTENT_FLAG_LOGGING, &em->flags);
list_add_tail(&em->list, &extents);
num++;
static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
+static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
+ enum btrfs_map_op op,
+ u64 logical, u64 *length,
+ struct btrfs_bio **bbio_ret,
+ int mirror_num, int need_raid_map);
DEFINE_MUTEX(uuid_mutex);
static LIST_HEAD(fs_uuids);
q = bdev_get_queue(bdev);
if (blk_queue_discard(q))
device->can_discard = 1;
+ if (!blk_queue_nonrot(q))
+ fs_devices->rotating = 1;
device->bdev = bdev;
device->in_fs_metadata = 0;
device->mode = flags;
- if (!blk_queue_nonrot(bdev_get_queue(bdev)))
- fs_devices->rotating = 1;
-
fs_devices->open_devices++;
if (device->writeable &&
device->devid != BTRFS_DEV_REPLACE_DEVID) {
fs_info->free_chunk_space += device->total_bytes;
spin_unlock(&fs_info->free_chunk_lock);
- if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+ if (!blk_queue_nonrot(q))
fs_info->fs_devices->rotating = 1;
tmp = btrfs_super_total_bytes(fs_info->super_copy);
return ret;
}
+static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info,
+ u64 logical, u64 length)
+{
+ struct extent_map_tree *em_tree;
+ struct extent_map *em;
+
+ em_tree = &fs_info->mapping_tree.map_tree;
+ read_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, logical, length);
+ read_unlock(&em_tree->lock);
+
+ if (!em) {
+ btrfs_crit(fs_info, "unable to find logical %llu length %llu",
+ logical, length);
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (em->start > logical || em->start + em->len < logical) {
+ btrfs_crit(fs_info,
+ "found a bad mapping, wanted %llu-%llu, found %llu-%llu",
+ logical, length, em->start, em->start + em->len);
+ free_extent_map(em);
+ return ERR_PTR(-EINVAL);
+ }
+
+ /* callers are responsible for dropping em's ref. */
+ return em;
+}
+
int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 chunk_offset)
{
- struct extent_map_tree *em_tree;
struct extent_map *em;
struct map_lookup *map;
u64 dev_extent_len = 0;
int i, ret = 0;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
- em_tree = &fs_info->mapping_tree.map_tree;
-
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, chunk_offset, 1);
- read_unlock(&em_tree->lock);
-
- if (!em || em->start > chunk_offset ||
- em->start + em->len < chunk_offset) {
+ em = get_chunk_map(fs_info, chunk_offset, 1);
+ if (IS_ERR(em)) {
/*
* This is a logic error, but we don't want to just rely on the
* user having built with ASSERT enabled, so if ASSERT doesn't
* do anything we still error out.
*/
ASSERT(0);
- if (em)
- free_extent_map(em);
- return -EINVAL;
+ return PTR_ERR(em);
}
map = em->map_lookup;
mutex_lock(&fs_info->chunk_mutex);
if (ret)
btrfs_handle_fs_error(fs_info, ret, NULL);
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
}
/* Non-zero return value signifies invalidity */
struct btrfs_ioctl_balance_args *bargs)
{
struct btrfs_fs_info *fs_info = bctl->fs_info;
+ u64 meta_target, data_target;
u64 allowed;
int mixed = 0;
int ret;
}
} while (read_seqretry(&fs_info->profiles_lock, seq));
- if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
- btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
+ /* if we're not converting, the target field is uninitialized */
+ meta_target = (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
+ bctl->meta.target : fs_info->avail_metadata_alloc_bits;
+ data_target = (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
+ bctl->data.target : fs_info->avail_data_alloc_bits;
+ if (btrfs_get_num_tolerated_disk_barrier_failures(meta_target) <
+ btrfs_get_num_tolerated_disk_barrier_failures(data_target)) {
btrfs_warn(fs_info,
"metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
- bctl->meta.target, bctl->data.target);
+ meta_target, data_target);
}
if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
__cancel_balance(fs_info);
else {
kfree(bctl);
- atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+ clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
}
return ret;
}
btrfs_balance_sys(leaf, item, &disk_bargs);
btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
- WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
+ WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
stripe_size = div_u64(stripe_size, dev_stripes);
/* align to BTRFS_STRIPE_LEN */
- stripe_size = div_u64(stripe_size, raid_stripe_len);
+ stripe_size = div64_u64(stripe_size, raid_stripe_len);
stripe_size *= raid_stripe_len;
map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
ret = add_extent_mapping(em_tree, em, 0);
if (!ret) {
list_add_tail(&em->list, &trans->transaction->pending_chunks);
- atomic_inc(&em->refs);
+ refcount_inc(&em->refs);
}
write_unlock(&em_tree->lock);
if (ret) {
struct btrfs_device *device;
struct btrfs_chunk *chunk;
struct btrfs_stripe *stripe;
- struct extent_map_tree *em_tree;
struct extent_map *em;
struct map_lookup *map;
size_t item_size;
int i = 0;
int ret = 0;
- em_tree = &fs_info->mapping_tree.map_tree;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, chunk_offset, chunk_size);
- read_unlock(&em_tree->lock);
-
- if (!em) {
- btrfs_crit(fs_info, "unable to find logical %Lu len %Lu",
- chunk_offset, chunk_size);
- return -EINVAL;
- }
-
- if (em->start != chunk_offset || em->len != chunk_size) {
- btrfs_crit(fs_info,
- "found a bad mapping, wanted %Lu-%Lu, found %Lu-%Lu",
- chunk_offset, chunk_size, em->start, em->len);
- free_extent_map(em);
- return -EINVAL;
- }
+ em = get_chunk_map(fs_info, chunk_offset, chunk_size);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
map = em->map_lookup;
item_size = btrfs_chunk_item_size(map->num_stripes);
{
struct extent_map *em;
struct map_lookup *map;
- struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
int readonly = 0;
int miss_ndevs = 0;
int i;
- read_lock(&map_tree->map_tree.lock);
- em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1);
- read_unlock(&map_tree->map_tree.lock);
- if (!em)
+ em = get_chunk_map(fs_info, chunk_offset, 1);
+ if (IS_ERR(em))
return 1;
map = em->map_lookup;
int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
{
- struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
struct extent_map *em;
struct map_lookup *map;
- struct extent_map_tree *em_tree = &map_tree->map_tree;
int ret;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, logical, len);
- read_unlock(&em_tree->lock);
-
- /*
- * We could return errors for these cases, but that could get ugly and
- * we'd probably do the same thing which is just not do anything else
- * and exit, so return 1 so the callers don't try to use other copies.
- */
- if (!em) {
- btrfs_crit(fs_info, "No mapping for %Lu-%Lu", logical,
- logical+len);
- return 1;
- }
-
- if (em->start > logical || em->start + em->len < logical) {
- btrfs_crit(fs_info, "Invalid mapping for %Lu-%Lu, got %Lu-%Lu",
- logical, logical+len, em->start,
- em->start + em->len);
- free_extent_map(em);
+ em = get_chunk_map(fs_info, logical, len);
+ if (IS_ERR(em))
+ /*
+ * We could return errors for these cases, but that could get
+ * ugly and we'd probably do the same thing which is just not do
+ * anything else and exit, so return 1 so the callers don't try
+ * to use other copies.
+ */
return 1;
- }
map = em->map_lookup;
if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
free_extent_map(em);
btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
- if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))
+ if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace) &&
+ fs_info->dev_replace.tgtdev)
ret++;
btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
{
struct extent_map *em;
struct map_lookup *map;
- struct extent_map_tree *em_tree = &map_tree->map_tree;
unsigned long len = fs_info->sectorsize;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, logical, len);
- read_unlock(&em_tree->lock);
- BUG_ON(!em);
+ em = get_chunk_map(fs_info, logical, len);
+ WARN_ON(IS_ERR(em));
- BUG_ON(em->start > logical || em->start + em->len < logical);
map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
len = map->stripe_len * nr_data_stripes(map);
return len;
}
-int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
+int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
u64 logical, u64 len, int mirror_num)
{
struct extent_map *em;
struct map_lookup *map;
- struct extent_map_tree *em_tree = &map_tree->map_tree;
int ret = 0;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, logical, len);
- read_unlock(&em_tree->lock);
- BUG_ON(!em);
+ em = get_chunk_map(fs_info, logical, len);
+ WARN_ON(IS_ERR(em));
- BUG_ON(em->start > logical || em->start + em->len < logical);
map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
ret = 1;
GFP_NOFS|__GFP_NOFAIL);
atomic_set(&bbio->error, 0);
- atomic_set(&bbio->refs, 1);
+ refcount_set(&bbio->refs, 1);
return bbio;
}
void btrfs_get_bbio(struct btrfs_bio *bbio)
{
- WARN_ON(!atomic_read(&bbio->refs));
- atomic_inc(&bbio->refs);
+ WARN_ON(!refcount_read(&bbio->refs));
+ refcount_inc(&bbio->refs);
}
void btrfs_put_bbio(struct btrfs_bio *bbio)
{
if (!bbio)
return;
- if (atomic_dec_and_test(&bbio->refs))
+ if (refcount_dec_and_test(&bbio->refs))
kfree(bbio);
}
+/* can REQ_OP_DISCARD be sent with other REQ like REQ_OP_WRITE? */
+/*
+ * Please note that, discard won't be sent to target device of device
+ * replace.
+ */
+static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
+ u64 logical, u64 length,
+ struct btrfs_bio **bbio_ret)
+{
+ struct extent_map *em;
+ struct map_lookup *map;
+ struct btrfs_bio *bbio;
+ u64 offset;
+ u64 stripe_nr;
+ u64 stripe_nr_end;
+ u64 stripe_end_offset;
+ u64 stripe_cnt;
+ u64 stripe_len;
+ u64 stripe_offset;
+ u64 num_stripes;
+ u32 stripe_index;
+ u32 factor = 0;
+ u32 sub_stripes = 0;
+ u64 stripes_per_dev = 0;
+ u32 remaining_stripes = 0;
+ u32 last_stripe = 0;
+ int ret = 0;
+ int i;
+
+ /* discard always return a bbio */
+ ASSERT(bbio_ret);
+
+ em = get_chunk_map(fs_info, logical, length);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ map = em->map_lookup;
+ /* we don't discard raid56 yet */
+ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+
+ offset = logical - em->start;
+ length = min_t(u64, em->len - offset, length);
+
+ stripe_len = map->stripe_len;
+ /*
+ * stripe_nr counts the total number of stripes we have to stride
+ * to get to this block
+ */
+ stripe_nr = div64_u64(offset, stripe_len);
+
+ /* stripe_offset is the offset of this block in its stripe */
+ stripe_offset = offset - stripe_nr * stripe_len;
+
+ stripe_nr_end = round_up(offset + length, map->stripe_len);
+ stripe_nr_end = div64_u64(stripe_nr_end, map->stripe_len);
+ stripe_cnt = stripe_nr_end - stripe_nr;
+ stripe_end_offset = stripe_nr_end * map->stripe_len -
+ (offset + length);
+ /*
+ * after this, stripe_nr is the number of stripes on this
+ * device we have to walk to find the data, and stripe_index is
+ * the number of our device in the stripe array
+ */
+ num_stripes = 1;
+ stripe_index = 0;
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID10)) {
+ if (map->type & BTRFS_BLOCK_GROUP_RAID0)
+ sub_stripes = 1;
+ else
+ sub_stripes = map->sub_stripes;
+
+ factor = map->num_stripes / sub_stripes;
+ num_stripes = min_t(u64, map->num_stripes,
+ sub_stripes * stripe_cnt);
+ stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
+ stripe_index *= sub_stripes;
+ stripes_per_dev = div_u64_rem(stripe_cnt, factor,
+ &remaining_stripes);
+ div_u64_rem(stripe_nr_end - 1, factor, &last_stripe);
+ last_stripe *= sub_stripes;
+ } else if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_DUP)) {
+ num_stripes = map->num_stripes;
+ } else {
+ stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
+ &stripe_index);
+ }
+
+ bbio = alloc_btrfs_bio(num_stripes, 0);
+ if (!bbio) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < num_stripes; i++) {
+ bbio->stripes[i].physical =
+ map->stripes[stripe_index].physical +
+ stripe_offset + stripe_nr * map->stripe_len;
+ bbio->stripes[i].dev = map->stripes[stripe_index].dev;
+
+ if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+ BTRFS_BLOCK_GROUP_RAID10)) {
+ bbio->stripes[i].length = stripes_per_dev *
+ map->stripe_len;
+
+ if (i / sub_stripes < remaining_stripes)
+ bbio->stripes[i].length +=
+ map->stripe_len;
+
+ /*
+ * Special for the first stripe and
+ * the last stripe:
+ *
+ * |-------|...|-------|
+ * |----------|
+ * off end_off
+ */
+ if (i < sub_stripes)
+ bbio->stripes[i].length -=
+ stripe_offset;
+
+ if (stripe_index >= last_stripe &&
+ stripe_index <= (last_stripe +
+ sub_stripes - 1))
+ bbio->stripes[i].length -=
+ stripe_end_offset;
+
+ if (i == sub_stripes - 1)
+ stripe_offset = 0;
+ } else {
+ bbio->stripes[i].length = length;
+ }
+
+ stripe_index++;
+ if (stripe_index == map->num_stripes) {
+ stripe_index = 0;
+ stripe_nr++;
+ }
+ }
+
+ *bbio_ret = bbio;
+ bbio->map_type = map->type;
+ bbio->num_stripes = num_stripes;
+out:
+ free_extent_map(em);
+ return ret;
+}
+
+/*
+ * In dev-replace case, for repair case (that's the only case where the mirror
+ * is selected explicitly when calling btrfs_map_block), blocks left of the
+ * left cursor can also be read from the target drive.
+ *
+ * For REQ_GET_READ_MIRRORS, the target drive is added as the last one to the
+ * array of stripes.
+ * For READ, it also needs to be supported using the same mirror number.
+ *
+ * If the requested block is not left of the left cursor, EIO is returned. This
+ * can happen because btrfs_num_copies() returns one more in the dev-replace
+ * case.
+ */
+static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info,
+ u64 logical, u64 length,
+ u64 srcdev_devid, int *mirror_num,
+ u64 *physical)
+{
+ struct btrfs_bio *bbio = NULL;
+ int num_stripes;
+ int index_srcdev = 0;
+ int found = 0;
+ u64 physical_of_found = 0;
+ int i;
+ int ret = 0;
+
+ ret = __btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
+ logical, &length, &bbio, 0, 0);
+ if (ret) {
+ ASSERT(bbio == NULL);
+ return ret;
+ }
+
+ num_stripes = bbio->num_stripes;
+ if (*mirror_num > num_stripes) {
+ /*
+ * BTRFS_MAP_GET_READ_MIRRORS does not contain this mirror,
+ * that means that the requested area is not left of the left
+ * cursor
+ */
+ btrfs_put_bbio(bbio);
+ return -EIO;
+ }
+
+ /*
+ * process the rest of the function using the mirror_num of the source
+ * drive. Therefore look it up first. At the end, patch the device
+ * pointer to the one of the target drive.
+ */
+ for (i = 0; i < num_stripes; i++) {
+ if (bbio->stripes[i].dev->devid != srcdev_devid)
+ continue;
+
+ /*
+ * In case of DUP, in order to keep it simple, only add the
+ * mirror with the lowest physical address
+ */
+ if (found &&
+ physical_of_found <= bbio->stripes[i].physical)
+ continue;
+
+ index_srcdev = i;
+ found = 1;
+ physical_of_found = bbio->stripes[i].physical;
+ }
+
+ btrfs_put_bbio(bbio);
+
+ ASSERT(found);
+ if (!found)
+ return -EIO;
+
+ *mirror_num = index_srcdev + 1;
+ *physical = physical_of_found;
+ return ret;
+}
+
+static void handle_ops_on_dev_replace(enum btrfs_map_op op,
+ struct btrfs_bio **bbio_ret,
+ struct btrfs_dev_replace *dev_replace,
+ int *num_stripes_ret, int *max_errors_ret)
+{
+ struct btrfs_bio *bbio = *bbio_ret;
+ u64 srcdev_devid = dev_replace->srcdev->devid;
+ int tgtdev_indexes = 0;
+ int num_stripes = *num_stripes_ret;
+ int max_errors = *max_errors_ret;
+ int i;
+
+ if (op == BTRFS_MAP_WRITE) {
+ int index_where_to_add;
+
+ /*
+ * duplicate the write operations while the dev replace
+ * procedure is running. Since the copying of the old disk to
+ * the new disk takes place at run time while the filesystem is
+ * mounted writable, the regular write operations to the old
+ * disk have to be duplicated to go to the new disk as well.
+ *
+ * Note that device->missing is handled by the caller, and that
+ * the write to the old disk is already set up in the stripes
+ * array.
+ */
+ index_where_to_add = num_stripes;
+ for (i = 0; i < num_stripes; i++) {
+ if (bbio->stripes[i].dev->devid == srcdev_devid) {
+ /* write to new disk, too */
+ struct btrfs_bio_stripe *new =
+ bbio->stripes + index_where_to_add;
+ struct btrfs_bio_stripe *old =
+ bbio->stripes + i;
+
+ new->physical = old->physical;
+ new->length = old->length;
+ new->dev = dev_replace->tgtdev;
+ bbio->tgtdev_map[i] = index_where_to_add;
+ index_where_to_add++;
+ max_errors++;
+ tgtdev_indexes++;
+ }
+ }
+ num_stripes = index_where_to_add;
+ } else if (op == BTRFS_MAP_GET_READ_MIRRORS) {
+ int index_srcdev = 0;
+ int found = 0;
+ u64 physical_of_found = 0;
+
+ /*
+ * During the dev-replace procedure, the target drive can also
+ * be used to read data in case it is needed to repair a corrupt
+ * block elsewhere. This is possible if the requested area is
+ * left of the left cursor. In this area, the target drive is a
+ * full copy of the source drive.
+ */
+ for (i = 0; i < num_stripes; i++) {
+ if (bbio->stripes[i].dev->devid == srcdev_devid) {
+ /*
+ * In case of DUP, in order to keep it simple,
+ * only add the mirror with the lowest physical
+ * address
+ */
+ if (found &&
+ physical_of_found <=
+ bbio->stripes[i].physical)
+ continue;
+ index_srcdev = i;
+ found = 1;
+ physical_of_found = bbio->stripes[i].physical;
+ }
+ }
+ if (found) {
+ struct btrfs_bio_stripe *tgtdev_stripe =
+ bbio->stripes + num_stripes;
+
+ tgtdev_stripe->physical = physical_of_found;
+ tgtdev_stripe->length =
+ bbio->stripes[index_srcdev].length;
+ tgtdev_stripe->dev = dev_replace->tgtdev;
+ bbio->tgtdev_map[index_srcdev] = num_stripes;
+
+ tgtdev_indexes++;
+ num_stripes++;
+ }
+ }
+
+ *num_stripes_ret = num_stripes;
+ *max_errors_ret = max_errors;
+ bbio->num_tgtdevs = tgtdev_indexes;
+ *bbio_ret = bbio;
+}
+
+static bool need_full_stripe(enum btrfs_map_op op)
+{
+ return (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS);
+}
+
static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
enum btrfs_map_op op,
u64 logical, u64 *length,
{
struct extent_map *em;
struct map_lookup *map;
- struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
- struct extent_map_tree *em_tree = &map_tree->map_tree;
u64 offset;
u64 stripe_offset;
- u64 stripe_end_offset;
u64 stripe_nr;
- u64 stripe_nr_orig;
- u64 stripe_nr_end;
u64 stripe_len;
u32 stripe_index;
int i;
u64 physical_to_patch_in_first_stripe = 0;
u64 raid56_full_stripe_start = (u64)-1;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, logical, *length);
- read_unlock(&em_tree->lock);
-
- if (!em) {
- btrfs_crit(fs_info, "unable to find logical %llu len %llu",
- logical, *length);
- return -EINVAL;
- }
+ if (op == BTRFS_MAP_DISCARD)
+ return __btrfs_map_block_for_discard(fs_info, logical,
+ *length, bbio_ret);
- if (em->start > logical || em->start + em->len < logical) {
- btrfs_crit(fs_info,
- "found a bad mapping, wanted %Lu, found %Lu-%Lu",
- logical, em->start, em->start + em->len);
- free_extent_map(em);
- return -EINVAL;
- }
+ em = get_chunk_map(fs_info, logical, *length);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
map = em->map_lookup;
offset = logical - em->start;
raid56_full_stripe_start *= full_stripe_len;
}
- if (op == BTRFS_MAP_DISCARD) {
- /* we don't discard raid56 yet */
- if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
- ret = -EOPNOTSUPP;
- goto out;
- }
- *length = min_t(u64, em->len - offset, *length);
- } else if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+ if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
u64 max_len;
/* For writes to RAID[56], allow a full stripeset across all disks.
For other RAID types and for RAID[56] reads, just allow a single
btrfs_dev_replace_set_lock_blocking(dev_replace);
if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
- op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
- op != BTRFS_MAP_GET_READ_MIRRORS && dev_replace->tgtdev != NULL) {
- /*
- * in dev-replace case, for repair case (that's the only
- * case where the mirror is selected explicitly when
- * calling btrfs_map_block), blocks left of the left cursor
- * can also be read from the target drive.
- * For REQ_GET_READ_MIRRORS, the target drive is added as
- * the last one to the array of stripes. For READ, it also
- * needs to be supported using the same mirror number.
- * If the requested block is not left of the left cursor,
- * EIO is returned. This can happen because btrfs_num_copies()
- * returns one more in the dev-replace case.
- */
- u64 tmp_length = *length;
- struct btrfs_bio *tmp_bbio = NULL;
- int tmp_num_stripes;
- u64 srcdev_devid = dev_replace->srcdev->devid;
- int index_srcdev = 0;
- int found = 0;
- u64 physical_of_found = 0;
-
- ret = __btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
- logical, &tmp_length, &tmp_bbio, 0, 0);
- if (ret) {
- WARN_ON(tmp_bbio != NULL);
- goto out;
- }
-
- tmp_num_stripes = tmp_bbio->num_stripes;
- if (mirror_num > tmp_num_stripes) {
- /*
- * BTRFS_MAP_GET_READ_MIRRORS does not contain this
- * mirror, that means that the requested area
- * is not left of the left cursor
- */
- ret = -EIO;
- btrfs_put_bbio(tmp_bbio);
- goto out;
- }
-
- /*
- * process the rest of the function using the mirror_num
- * of the source drive. Therefore look it up first.
- * At the end, patch the device pointer to the one of the
- * target drive.
- */
- for (i = 0; i < tmp_num_stripes; i++) {
- if (tmp_bbio->stripes[i].dev->devid != srcdev_devid)
- continue;
-
- /*
- * In case of DUP, in order to keep it simple, only add
- * the mirror with the lowest physical address
- */
- if (found &&
- physical_of_found <= tmp_bbio->stripes[i].physical)
- continue;
-
- index_srcdev = i;
- found = 1;
- physical_of_found = tmp_bbio->stripes[i].physical;
- }
-
- btrfs_put_bbio(tmp_bbio);
-
- if (!found) {
- WARN_ON(1);
- ret = -EIO;
+ !need_full_stripe(op) && dev_replace->tgtdev != NULL) {
+ ret = get_extra_mirror_from_replace(fs_info, logical, *length,
+ dev_replace->srcdev->devid,
+ &mirror_num,
+ &physical_to_patch_in_first_stripe);
+ if (ret)
goto out;
- }
-
- mirror_num = index_srcdev + 1;
- patch_the_first_stripe_for_dev_replace = 1;
- physical_to_patch_in_first_stripe = physical_of_found;
+ else
+ patch_the_first_stripe_for_dev_replace = 1;
} else if (mirror_num > map->num_stripes) {
mirror_num = 0;
}
num_stripes = 1;
stripe_index = 0;
- stripe_nr_orig = stripe_nr;
- stripe_nr_end = ALIGN(offset + *length, map->stripe_len);
- stripe_nr_end = div_u64(stripe_nr_end, map->stripe_len);
- stripe_end_offset = stripe_nr_end * map->stripe_len -
- (offset + *length);
-
if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
- if (op == BTRFS_MAP_DISCARD)
- num_stripes = min_t(u64, map->num_stripes,
- stripe_nr_end - stripe_nr_orig);
stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
&stripe_index);
- if (op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
- op != BTRFS_MAP_GET_READ_MIRRORS)
+ if (op != BTRFS_MAP_WRITE && op != BTRFS_MAP_GET_READ_MIRRORS)
mirror_num = 1;
} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
- if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD ||
- op == BTRFS_MAP_GET_READ_MIRRORS)
+ if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
num_stripes = map->num_stripes;
else if (mirror_num)
stripe_index = mirror_num - 1;
}
} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
- if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD ||
- op == BTRFS_MAP_GET_READ_MIRRORS) {
+ if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS) {
num_stripes = map->num_stripes;
} else if (mirror_num) {
stripe_index = mirror_num - 1;
if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
num_stripes = map->sub_stripes;
- else if (op == BTRFS_MAP_DISCARD)
- num_stripes = min_t(u64, map->sub_stripes *
- (stripe_nr_end - stripe_nr_orig),
- map->num_stripes);
else if (mirror_num)
stripe_index += mirror_num - 1;
else {
(op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS ||
mirror_num > 1)) {
/* push stripe_nr back to the start of the full stripe */
- stripe_nr = div_u64(raid56_full_stripe_start,
+ stripe_nr = div64_u64(raid56_full_stripe_start,
stripe_len * nr_data_stripes(map));
/* RAID[56] write or recovery. Return all stripes */
/* We distribute the parity blocks across stripes */
div_u64_rem(stripe_nr + stripe_index, map->num_stripes,
&stripe_index);
- if ((op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
- op != BTRFS_MAP_GET_READ_MIRRORS) && mirror_num <= 1)
+ if ((op != BTRFS_MAP_WRITE &&
+ op != BTRFS_MAP_GET_READ_MIRRORS) &&
+ mirror_num <= 1)
mirror_num = 1;
}
} else {
}
num_alloc_stripes = num_stripes;
- if (dev_replace_is_ongoing) {
- if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD)
+ if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) {
+ if (op == BTRFS_MAP_WRITE)
num_alloc_stripes <<= 1;
if (op == BTRFS_MAP_GET_READ_MIRRORS)
num_alloc_stripes++;
ret = -ENOMEM;
goto out;
}
- if (dev_replace_is_ongoing)
+ if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
bbio->tgtdev_map = (int *)(bbio->stripes + num_alloc_stripes);
/* build raid_map */
- if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK &&
- need_raid_map &&
- ((op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS) ||
- mirror_num > 1)) {
+ if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK && need_raid_map &&
+ (need_full_stripe(op) || mirror_num > 1)) {
u64 tmp;
unsigned rot;
RAID6_Q_STRIPE;
}
- if (op == BTRFS_MAP_DISCARD) {
- u32 factor = 0;
- u32 sub_stripes = 0;
- u64 stripes_per_dev = 0;
- u32 remaining_stripes = 0;
- u32 last_stripe = 0;
- if (map->type &
- (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) {
- if (map->type & BTRFS_BLOCK_GROUP_RAID0)
- sub_stripes = 1;
- else
- sub_stripes = map->sub_stripes;
-
- factor = map->num_stripes / sub_stripes;
- stripes_per_dev = div_u64_rem(stripe_nr_end -
- stripe_nr_orig,
- factor,
- &remaining_stripes);
- div_u64_rem(stripe_nr_end - 1, factor, &last_stripe);
- last_stripe *= sub_stripes;
- }
-
- for (i = 0; i < num_stripes; i++) {
- bbio->stripes[i].physical =
- map->stripes[stripe_index].physical +
- stripe_offset + stripe_nr * map->stripe_len;
- bbio->stripes[i].dev = map->stripes[stripe_index].dev;
-
- if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
- BTRFS_BLOCK_GROUP_RAID10)) {
- bbio->stripes[i].length = stripes_per_dev *
- map->stripe_len;
-
- if (i / sub_stripes < remaining_stripes)
- bbio->stripes[i].length +=
- map->stripe_len;
-
- /*
- * Special for the first stripe and
- * the last stripe:
- *
- * |-------|...|-------|
- * |----------|
- * off end_off
- */
- if (i < sub_stripes)
- bbio->stripes[i].length -=
- stripe_offset;
-
- if (stripe_index >= last_stripe &&
- stripe_index <= (last_stripe +
- sub_stripes - 1))
- bbio->stripes[i].length -=
- stripe_end_offset;
-
- if (i == sub_stripes - 1)
- stripe_offset = 0;
- } else
- bbio->stripes[i].length = *length;
-
- stripe_index++;
- if (stripe_index == map->num_stripes) {
- /* This could only happen for RAID0/10 */
- stripe_index = 0;
- stripe_nr++;
- }
- }
- } else {
- for (i = 0; i < num_stripes; i++) {
- bbio->stripes[i].physical =
- map->stripes[stripe_index].physical +
- stripe_offset +
- stripe_nr * map->stripe_len;
- bbio->stripes[i].dev =
- map->stripes[stripe_index].dev;
- stripe_index++;
- }
+ for (i = 0; i < num_stripes; i++) {
+ bbio->stripes[i].physical =
+ map->stripes[stripe_index].physical +
+ stripe_offset +
+ stripe_nr * map->stripe_len;
+ bbio->stripes[i].dev =
+ map->stripes[stripe_index].dev;
+ stripe_index++;
}
- if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
+ if (need_full_stripe(op))
max_errors = btrfs_chunk_max_errors(map);
if (bbio->raid_map)
sort_parity_stripes(bbio, num_stripes);
- tgtdev_indexes = 0;
- if (dev_replace_is_ongoing &&
- (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD) &&
- dev_replace->tgtdev != NULL) {
- int index_where_to_add;
- u64 srcdev_devid = dev_replace->srcdev->devid;
-
- /*
- * duplicate the write operations while the dev replace
- * procedure is running. Since the copying of the old disk
- * to the new disk takes place at run time while the
- * filesystem is mounted writable, the regular write
- * operations to the old disk have to be duplicated to go
- * to the new disk as well.
- * Note that device->missing is handled by the caller, and
- * that the write to the old disk is already set up in the
- * stripes array.
- */
- index_where_to_add = num_stripes;
- for (i = 0; i < num_stripes; i++) {
- if (bbio->stripes[i].dev->devid == srcdev_devid) {
- /* write to new disk, too */
- struct btrfs_bio_stripe *new =
- bbio->stripes + index_where_to_add;
- struct btrfs_bio_stripe *old =
- bbio->stripes + i;
-
- new->physical = old->physical;
- new->length = old->length;
- new->dev = dev_replace->tgtdev;
- bbio->tgtdev_map[i] = index_where_to_add;
- index_where_to_add++;
- max_errors++;
- tgtdev_indexes++;
- }
- }
- num_stripes = index_where_to_add;
- } else if (dev_replace_is_ongoing &&
- op == BTRFS_MAP_GET_READ_MIRRORS &&
- dev_replace->tgtdev != NULL) {
- u64 srcdev_devid = dev_replace->srcdev->devid;
- int index_srcdev = 0;
- int found = 0;
- u64 physical_of_found = 0;
-
- /*
- * During the dev-replace procedure, the target drive can
- * also be used to read data in case it is needed to repair
- * a corrupt block elsewhere. This is possible if the
- * requested area is left of the left cursor. In this area,
- * the target drive is a full copy of the source drive.
- */
- for (i = 0; i < num_stripes; i++) {
- if (bbio->stripes[i].dev->devid == srcdev_devid) {
- /*
- * In case of DUP, in order to keep it
- * simple, only add the mirror with the
- * lowest physical address
- */
- if (found &&
- physical_of_found <=
- bbio->stripes[i].physical)
- continue;
- index_srcdev = i;
- found = 1;
- physical_of_found = bbio->stripes[i].physical;
- }
- }
- if (found) {
- struct btrfs_bio_stripe *tgtdev_stripe =
- bbio->stripes + num_stripes;
-
- tgtdev_stripe->physical = physical_of_found;
- tgtdev_stripe->length =
- bbio->stripes[index_srcdev].length;
- tgtdev_stripe->dev = dev_replace->tgtdev;
- bbio->tgtdev_map[index_srcdev] = num_stripes;
-
- tgtdev_indexes++;
- num_stripes++;
- }
+ if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL &&
+ need_full_stripe(op)) {
+ handle_ops_on_dev_replace(op, &bbio, dev_replace, &num_stripes,
+ &max_errors);
}
*bbio_ret = bbio;
bbio->num_stripes = num_stripes;
bbio->max_errors = max_errors;
bbio->mirror_num = mirror_num;
- bbio->num_tgtdevs = tgtdev_indexes;
/*
* this is the case that REQ_READ && dev_replace_is_ongoing &&
/* For Scrub/replace */
int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
u64 logical, u64 *length,
- struct btrfs_bio **bbio_ret, int mirror_num,
- int need_raid_map)
+ struct btrfs_bio **bbio_ret)
{
- return __btrfs_map_block(fs_info, op, logical, length, bbio_ret,
- mirror_num, need_raid_map);
+ return __btrfs_map_block(fs_info, op, logical, length, bbio_ret, 0, 1);
}
int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
u64 chunk_start, u64 physical, u64 devid,
u64 **logical, int *naddrs, int *stripe_len)
{
- struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
- struct extent_map_tree *em_tree = &map_tree->map_tree;
struct extent_map *em;
struct map_lookup *map;
u64 *buf;
u64 rmap_len;
int i, j, nr = 0;
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, chunk_start, 1);
- read_unlock(&em_tree->lock);
-
- if (!em) {
- btrfs_err(fs_info, "couldn't find em for chunk %Lu",
- chunk_start);
+ em = get_chunk_map(fs_info, chunk_start, 1);
+ if (IS_ERR(em))
return -EIO;
- }
- if (em->start != chunk_start) {
- btrfs_err(fs_info, "bad chunk start, em=%Lu, wanted=%Lu",
- em->start, chunk_start);
- free_extent_map(em);
- return -EIO;
- }
map = em->map_lookup;
-
length = em->len;
rmap_len = map->stripe_len;
continue;
stripe_nr = physical - map->stripes[i].physical;
- stripe_nr = div_u64(stripe_nr, map->stripe_len);
+ stripe_nr = div64_u64(stripe_nr, map->stripe_len);
if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
stripe_nr = stripe_nr * map->num_stripes + i;
struct list_head resized_list;
/* for sending down flush barriers */
- int nobarriers;
struct bio *flush_bio;
struct completion flush_wait;
typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
struct btrfs_bio {
- atomic_t refs;
+ refcount_t refs;
atomic_t stripes_pending;
struct btrfs_fs_info *fs_info;
u64 map_type; /* get from map_lookup->type */
struct btrfs_bio **bbio_ret, int mirror_num);
int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
u64 logical, u64 *length,
- struct btrfs_bio **bbio_ret, int mirror_num,
- int need_raid_map);
+ struct btrfs_bio **bbio_ret);
int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
u64 chunk_start, u64 physical, u64 devid,
u64 **logical, int *naddrs, int *stripe_len);
void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info,
struct btrfs_device *tgtdev);
void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path);
-int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
+int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
u64 logical, u64 len, int mirror_num);
unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
struct btrfs_mapping_tree *map_tree,
bool remove_page;
dout("writepages_finish %p rc %d\n", inode, rc);
- if (rc < 0)
+ if (rc < 0) {
mapping_set_error(mapping, rc);
+ ceph_set_error_write(ci);
+ } else {
+ ceph_clear_error_write(ci);
+ }
/*
* We lost the cache cap, need to truncate the page before
clear_bdi_congested(inode_to_bdi(inode),
BLK_RW_ASYNC);
- if (rc < 0)
- SetPageError(page);
-
ceph_put_snap_context(page_snap_context(page));
page->private = 0;
ClearPagePrivate(page);
err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
wr_req->r_mtime = ci->vfs_inode.i_mtime;
+ wr_req->r_abort_on_full = true;
err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
if (!err)
void *p;
size_t extra_len;
struct timespec zerotime = {0};
+ struct ceph_osd_client *osdc = &arg->session->s_mdsc->fsc->client->osdc;
dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
" seq %u/%u tid %llu/%llu mseq %u follows %lld size %llu/%llu"
ceph_encode_64(&p, arg->inline_data ? 0 : CEPH_INLINE_NONE);
/* inline data size */
ceph_encode_32(&p, 0);
- /* osd_epoch_barrier (version 5) */
- ceph_encode_32(&p, 0);
+ /*
+ * osd_epoch_barrier (version 5)
+ * The epoch_barrier is protected osdc->lock, so READ_ONCE here in
+ * case it was recently changed
+ */
+ ceph_encode_32(&p, READ_ONCE(osdc->epoch_barrier));
/* oldest_flush_tid (version 6) */
ceph_encode_64(&p, arg->oldest_flush_tid);
first_tid = cf->tid + 1;
capsnap = container_of(cf, struct ceph_cap_snap, cap_flush);
- atomic_inc(&capsnap->nref);
+ refcount_inc(&capsnap->nref);
spin_unlock(&ci->i_ceph_lock);
dout("__flush_snaps %p capsnap %p tid %llu %s\n",
inode, capsnap, cf->tid,
ceph_cap_string(capsnap->dirty));
- atomic_inc(&capsnap->nref);
+ refcount_inc(&capsnap->nref);
spin_unlock(&ci->i_ceph_lock);
ret = __send_flush_snap(inode, session, capsnap, cap->mseq,
p += inline_len;
}
+ if (le16_to_cpu(msg->hdr.version) >= 5) {
+ struct ceph_osd_client *osdc = &mdsc->fsc->client->osdc;
+ u32 epoch_barrier;
+
+ ceph_decode_32_safe(&p, end, epoch_barrier, bad);
+ ceph_osdc_update_epoch_barrier(osdc, epoch_barrier);
+ }
+
if (le16_to_cpu(msg->hdr.version) >= 8) {
u64 flush_tid;
u32 caller_uid, caller_gid;
- u32 osd_epoch_barrier;
u32 pool_ns_len;
- /* version >= 5 */
- ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
+
/* version >= 6 */
ceph_decode_64_safe(&p, end, flush_tid, bad);
/* version >= 7 */
{
int i;
struct ceph_fs_client *fsc = s->private;
+ struct ceph_mdsmap *mdsmap;
if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL)
return 0;
- seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch);
- seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root);
- seq_printf(s, "session_timeout %d\n",
- fsc->mdsc->mdsmap->m_session_timeout);
- seq_printf(s, "session_autoclose %d\n",
- fsc->mdsc->mdsmap->m_session_autoclose);
- for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) {
- struct ceph_entity_addr *addr =
- &fsc->mdsc->mdsmap->m_info[i].addr;
- int state = fsc->mdsc->mdsmap->m_info[i].state;
-
+ mdsmap = fsc->mdsc->mdsmap;
+ seq_printf(s, "epoch %d\n", mdsmap->m_epoch);
+ seq_printf(s, "root %d\n", mdsmap->m_root);
+ seq_printf(s, "max_mds %d\n", mdsmap->m_max_mds);
+ seq_printf(s, "session_timeout %d\n", mdsmap->m_session_timeout);
+ seq_printf(s, "session_autoclose %d\n", mdsmap->m_session_autoclose);
+ for (i = 0; i < mdsmap->m_num_mds; i++) {
+ struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr;
+ int state = mdsmap->m_info[i].state;
seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
ceph_pr_addr(&addr->in_addr),
ceph_mds_state_name(state));
struct ceph_mds_client *mdsc = fsc->mdsc;
int i;
int err;
- u32 ftype;
+ unsigned frag = -1;
struct ceph_mds_reply_info_parsed *rinfo;
dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos);
/* do we have the correct frag content buffered? */
if (need_send_readdir(fi, ctx->pos)) {
struct ceph_mds_request *req;
- unsigned frag;
int op = ceph_snap(inode) == CEPH_SNAPDIR ?
CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
}
if (is_hash_order(ctx->pos)) {
- frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
- NULL, NULL);
+ /* fragtree isn't always accurate. choose frag
+ * based on previous reply when possible. */
+ if (frag == (unsigned)-1)
+ frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
+ NULL, NULL);
} else {
frag = fpos_frag(ctx->pos);
}
ceph_mdsc_put_request(req);
return -ENOMEM;
}
+ } else if (is_hash_order(ctx->pos)) {
+ req->r_args.readdir.offset_hash =
+ cpu_to_le32(fpos_hash(ctx->pos));
}
+
req->r_dir_release_cnt = fi->dir_release_count;
req->r_dir_ordered_cnt = fi->dir_ordered_count;
req->r_readdir_cache_idx = fi->readdir_cache_idx;
struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
struct ceph_vino vino;
ino_t ino;
+ u32 ftype;
BUG_ON(rde->offset < ctx->pos);
ctx->pos++;
}
+ ceph_mdsc_put_request(fi->last_readdir);
+ fi->last_readdir = NULL;
+
if (fi->next_offset > 2) {
- ceph_mdsc_put_request(fi->last_readdir);
- fi->last_readdir = NULL;
+ frag = fi->frag;
goto more;
}
/* more frags? */
if (!ceph_frag_is_rightmost(fi->frag)) {
- unsigned frag = ceph_frag_next(fi->frag);
+ frag = ceph_frag_next(fi->frag);
if (is_hash_order(ctx->pos)) {
loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag),
fi->next_offset, true);
#include "mds_client.h"
#include "cache.h"
+static __le32 ceph_flags_sys2wire(u32 flags)
+{
+ u32 wire_flags = 0;
+
+ switch (flags & O_ACCMODE) {
+ case O_RDONLY:
+ wire_flags |= CEPH_O_RDONLY;
+ break;
+ case O_WRONLY:
+ wire_flags |= CEPH_O_WRONLY;
+ break;
+ case O_RDWR:
+ wire_flags |= CEPH_O_RDWR;
+ break;
+ }
+
+#define ceph_sys2wire(a) if (flags & a) { wire_flags |= CEPH_##a; flags &= ~a; }
+
+ ceph_sys2wire(O_CREAT);
+ ceph_sys2wire(O_EXCL);
+ ceph_sys2wire(O_TRUNC);
+ ceph_sys2wire(O_DIRECTORY);
+ ceph_sys2wire(O_NOFOLLOW);
+
+#undef ceph_sys2wire
+
+ if (flags)
+ dout("unused open flags: %x", flags);
+
+ return cpu_to_le32(wire_flags);
+}
+
/*
* Ceph file operations
*
if (IS_ERR(req))
goto out;
req->r_fmode = ceph_flags_to_mode(flags);
- req->r_args.open.flags = cpu_to_le32(flags);
+ req->r_args.open.flags = ceph_flags_sys2wire(flags);
req->r_args.open.mode = cpu_to_le32(create_mode);
out:
return req;
spin_lock(&ci->i_ceph_lock);
wanted = __ceph_caps_file_wanted(ci);
if (__ceph_is_any_real_caps(ci) &&
- (!(wanted & CEPH_CAP_ANY_WR) == 0 || ci->i_auth_cap)) {
+ (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
int issued = __ceph_caps_issued(ci, NULL);
spin_unlock(&ci->i_ceph_lock);
dout("renew caps %p want %s issued %s updating mds_wanted\n",
req->r_callback = ceph_aio_complete_req;
req->r_inode = inode;
req->r_priv = aio_req;
+ req->r_abort_on_full = true;
ret = ceph_osdc_start_request(req->r_osdc, req, false);
out:
out:
ceph_osdc_put_request(req);
- if (ret == 0) {
- pos += len;
- written += len;
-
- if (pos > i_size_read(inode)) {
- check_caps = ceph_inode_set_size(inode, pos);
- if (check_caps)
- ceph_check_caps(ceph_inode(inode),
- CHECK_CAPS_AUTHONLY,
- NULL);
- }
- } else
+ if (ret != 0) {
+ ceph_set_error_write(ci);
break;
+ }
+
+ ceph_clear_error_write(ci);
+ pos += len;
+ written += len;
+ if (pos > i_size_read(inode)) {
+ check_caps = ceph_inode_set_size(inode, pos);
+ if (check_caps)
+ ceph_check_caps(ceph_inode(inode),
+ CHECK_CAPS_AUTHONLY,
+ NULL);
+ }
+
}
if (ret != -EOLDSNAPC && written > 0) {
}
retry_snap:
+ /* FIXME: not complete since it doesn't account for being at quota */
if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) {
err = -ENOSPC;
goto out;
inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
- (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+ (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) ||
+ (ci->i_ceph_flags & CEPH_I_ERROR_WRITE)) {
struct ceph_snap_context *snapc;
struct iov_iter data;
inode_unlock(inode);
if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags))
return readdir_prepopulate_inodes_only(req, session);
- if (rinfo->hash_order && req->r_path2) {
- last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
- req->r_path2, strlen(req->r_path2));
- last_hash = ceph_frag_value(last_hash);
+ if (rinfo->hash_order) {
+ if (req->r_path2) {
+ last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
+ req->r_path2,
+ strlen(req->r_path2));
+ last_hash = ceph_frag_value(last_hash);
+ } else if (rinfo->offset_hash) {
+ /* mds understands offset_hash */
+ WARN_ON_ONCE(req->r_readdir_offset != 2);
+ last_hash = le32_to_cpu(rhead->args.readdir.offset_hash);
+ }
}
if (rinfo->dir_dir &&
}
if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 &&
- !(rinfo->hash_order && req->r_path2)) {
+ !(rinfo->hash_order && last_hash)) {
/* note dir version at start of readdir so we can tell
* if any dentries get dropped */
req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);
info->dir_end = !!(flags & CEPH_READDIR_FRAG_END);
info->dir_complete = !!(flags & CEPH_READDIR_FRAG_COMPLETE);
info->hash_order = !!(flags & CEPH_READDIR_HASH_ORDER);
+ info->offset_hash = !!(flags & CEPH_READDIR_OFFSET_HASH);
}
if (num == 0)
goto done;
static struct ceph_mds_session *get_session(struct ceph_mds_session *s)
{
- if (atomic_inc_not_zero(&s->s_ref)) {
+ if (refcount_inc_not_zero(&s->s_ref)) {
dout("mdsc get_session %p %d -> %d\n", s,
- atomic_read(&s->s_ref)-1, atomic_read(&s->s_ref));
+ refcount_read(&s->s_ref)-1, refcount_read(&s->s_ref));
return s;
} else {
dout("mdsc get_session %p 0 -- FAIL", s);
void ceph_put_mds_session(struct ceph_mds_session *s)
{
dout("mdsc put_session %p %d -> %d\n", s,
- atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
- if (atomic_dec_and_test(&s->s_ref)) {
+ refcount_read(&s->s_ref), refcount_read(&s->s_ref)-1);
+ if (refcount_dec_and_test(&s->s_ref)) {
if (s->s_auth.authorizer)
ceph_auth_destroy_authorizer(s->s_auth.authorizer);
kfree(s);
return NULL;
session = mdsc->sessions[mds];
dout("lookup_mds_session %p %d\n", session,
- atomic_read(&session->s_ref));
+ refcount_read(&session->s_ref));
get_session(session);
return session;
}
{
struct ceph_mds_session *s;
- if (mds >= mdsc->mdsmap->m_max_mds)
+ if (mds >= mdsc->mdsmap->m_num_mds)
return ERR_PTR(-EINVAL);
s = kzalloc(sizeof(*s), GFP_NOFS);
INIT_LIST_HEAD(&s->s_caps);
s->s_nr_caps = 0;
s->s_trim_caps = 0;
- atomic_set(&s->s_ref, 1);
+ refcount_set(&s->s_ref, 1);
INIT_LIST_HEAD(&s->s_waiting);
INIT_LIST_HEAD(&s->s_unsafe);
s->s_num_cap_releases = 0;
}
mdsc->sessions[mds] = s;
atomic_inc(&mdsc->num_sessions);
- atomic_inc(&s->s_ref); /* one ref to sessions[], one to caller */
+ refcount_inc(&s->s_ref); /* one ref to sessions[], one to caller */
ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
struct ceph_mds_session *ts;
int i, mds = session->s_mds;
- if (mds >= mdsc->mdsmap->m_max_mds)
+ if (mds >= mdsc->mdsmap->m_num_mds)
return;
mi = &mdsc->mdsmap->m_info[mds];
struct ceph_msg *msg = NULL;
struct ceph_mds_cap_release *head;
struct ceph_mds_cap_item *item;
+ struct ceph_osd_client *osdc = &mdsc->fsc->client->osdc;
struct ceph_cap *cap;
LIST_HEAD(tmp_list);
int num_cap_releases;
+ __le32 barrier, *cap_barrier;
+
+ down_read(&osdc->lock);
+ barrier = cpu_to_le32(osdc->epoch_barrier);
+ up_read(&osdc->lock);
spin_lock(&session->s_cap_lock);
again:
head = msg->front.iov_base;
head->num = cpu_to_le32(0);
msg->front.iov_len = sizeof(*head);
+
+ msg->hdr.version = cpu_to_le16(2);
+ msg->hdr.compat_version = cpu_to_le16(1);
}
+
cap = list_first_entry(&tmp_list, struct ceph_cap,
session_caps);
list_del(&cap->session_caps);
ceph_put_cap(mdsc, cap);
if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
+ // Append cap_barrier field
+ cap_barrier = msg->front.iov_base + msg->front.iov_len;
+ *cap_barrier = barrier;
+ msg->front.iov_len += sizeof(*cap_barrier);
+
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
ceph_con_send(&session->s_con, msg);
spin_unlock(&session->s_cap_lock);
if (msg) {
+ // Append cap_barrier field
+ cap_barrier = msg->front.iov_base + msg->front.iov_len;
+ *cap_barrier = barrier;
+ msg->front.iov_len += sizeof(*cap_barrier);
+
msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
ceph_con_send(&session->s_con, msg);
if (req->r_pagelist) {
struct ceph_pagelist *pagelist = req->r_pagelist;
- atomic_inc(&pagelist->refcnt);
+ refcount_inc(&pagelist->refcnt);
ceph_msg_data_add_pagelist(msg, pagelist);
msg->hdr.data_len = cpu_to_le32(pagelist->length);
} else {
seq = le64_to_cpu(h->seq);
mutex_lock(&mdsc->mutex);
- if (op == CEPH_SESSION_CLOSE)
+ if (op == CEPH_SESSION_CLOSE) {
+ get_session(session);
__unregister_session(mdsc, session);
+ }
/* FIXME: this ttl calculation is generous */
session->s_ttl = jiffies + HZ*mdsc->mdsmap->m_session_autoclose;
mutex_unlock(&mdsc->mutex);
kick_requests(mdsc, mds);
mutex_unlock(&mdsc->mutex);
}
+ if (op == CEPH_SESSION_CLOSE)
+ ceph_put_mds_session(session);
return;
bad:
dout("check_new_map new %u old %u\n",
newmap->m_epoch, oldmap->m_epoch);
- for (i = 0; i < oldmap->m_max_mds && i < mdsc->max_sessions; i++) {
+ for (i = 0; i < oldmap->m_num_mds && i < mdsc->max_sessions; i++) {
if (mdsc->sessions[i] == NULL)
continue;
s = mdsc->sessions[i];
ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
ceph_session_state_name(s->s_state));
- if (i >= newmap->m_max_mds ||
+ if (i >= newmap->m_num_mds ||
memcmp(ceph_mdsmap_get_addr(oldmap, i),
ceph_mdsmap_get_addr(newmap, i),
sizeof(struct ceph_entity_addr))) {
if (s->s_state == CEPH_MDS_SESSION_OPENING) {
/* the session never opened, just close it
* out now */
+ get_session(s);
+ __unregister_session(mdsc, s);
__wake_requests(mdsc, &s->s_waiting);
+ ceph_put_mds_session(s);
+ } else if (i >= newmap->m_num_mds) {
+ /* force close session for stopped mds */
+ get_session(s);
__unregister_session(mdsc, s);
+ __wake_requests(mdsc, &s->s_waiting);
+ kick_requests(mdsc, i);
+ mutex_unlock(&mdsc->mutex);
+
+ mutex_lock(&s->s_mutex);
+ cleanup_session_requests(mdsc, s);
+ remove_session_caps(s);
+ mutex_unlock(&s->s_mutex);
+
+ ceph_put_mds_session(s);
+
+ mutex_lock(&mdsc->mutex);
} else {
/* just close it */
mutex_unlock(&mdsc->mutex);
}
}
- for (i = 0; i < newmap->m_max_mds && i < mdsc->max_sessions; i++) {
+ for (i = 0; i < newmap->m_num_mds && i < mdsc->max_sessions; i++) {
s = mdsc->sessions[i];
if (!s)
continue;
struct ceph_mds_session *s = con->private;
if (get_session(s)) {
- dout("mdsc con_get %p ok (%d)\n", s, atomic_read(&s->s_ref));
+ dout("mdsc con_get %p ok (%d)\n", s, refcount_read(&s->s_ref));
return con;
}
dout("mdsc con_get %p FAIL\n", s);
{
struct ceph_mds_session *s = con->private;
- dout("mdsc con_put %p (%d)\n", s, atomic_read(&s->s_ref) - 1);
+ dout("mdsc con_put %p (%d)\n", s, refcount_read(&s->s_ref) - 1);
ceph_put_mds_session(s);
}
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
+#include <linux/refcount.h>
#include <linux/ceph/types.h>
#include <linux/ceph/messenger.h>
struct ceph_mds_reply_dirfrag *dir_dir;
size_t dir_buf_size;
int dir_nr;
- bool dir_complete;
bool dir_end;
+ bool dir_complete;
bool hash_order;
+ bool offset_hash;
struct ceph_mds_reply_dir_entry *dir_entries;
};
/*
* cap releases are batched and sent to the MDS en masse.
+ *
+ * Account for per-message overhead of mds_cap_release header
+ * and __le32 for osd epoch barrier trailing field.
*/
-#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - \
+#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - sizeof(u32) - \
sizeof(struct ceph_mds_cap_release)) / \
- sizeof(struct ceph_mds_cap_item))
+ sizeof(struct ceph_mds_cap_item))
/*
unsigned long s_renew_requested; /* last time we sent a renew req */
u64 s_renew_seq;
- atomic_t s_ref;
+ refcount_t s_ref;
struct list_head s_waiting; /* waiting requests */
struct list_head s_unsafe; /* unsafe requests */
};
static inline struct ceph_mds_session *
ceph_get_mds_session(struct ceph_mds_session *s)
{
- atomic_inc(&s->s_ref);
+ refcount_inc(&s->s_ref);
return s;
}
int i;
/* special case for one mds */
- if (1 == m->m_max_mds && m->m_info[0].state > 0)
+ if (1 == m->m_num_mds && m->m_info[0].state > 0)
return 0;
/* count */
- for (i = 0; i < m->m_max_mds; i++)
+ for (i = 0; i < m->m_num_mds; i++)
if (m->m_info[i].state > 0)
n++;
if (n == 0)
m->m_session_autoclose = ceph_decode_32(p);
m->m_max_file_size = ceph_decode_64(p);
m->m_max_mds = ceph_decode_32(p);
+ m->m_num_mds = m->m_max_mds;
- m->m_info = kcalloc(m->m_max_mds, sizeof(*m->m_info), GFP_NOFS);
+ m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS);
if (m->m_info == NULL)
goto nomem;
ceph_pr_addr(&addr.in_addr),
ceph_mds_state_name(state));
- if (mds < 0 || mds >= m->m_max_mds || state <= 0)
+ if (mds < 0 || state <= 0)
continue;
+ if (mds >= m->m_num_mds) {
+ int new_num = max(mds + 1, m->m_num_mds * 2);
+ void *new_m_info = krealloc(m->m_info,
+ new_num * sizeof(*m->m_info),
+ GFP_NOFS | __GFP_ZERO);
+ if (!new_m_info)
+ goto nomem;
+ m->m_info = new_m_info;
+ m->m_num_mds = new_num;
+ }
+
info = &m->m_info[mds];
info->global_id = global_id;
info->state = state;
info->export_targets = NULL;
}
}
+ if (m->m_num_mds > m->m_max_mds) {
+ /* find max up mds */
+ for (i = m->m_num_mds; i >= m->m_max_mds; i--) {
+ if (i == 0 || m->m_info[i-1].state > 0)
+ break;
+ }
+ m->m_num_mds = i;
+ }
/* pg_pools */
ceph_decode_32_safe(p, end, n, bad);
for (i = 0; i < n; i++) {
s32 mds = ceph_decode_32(p);
- if (mds >= 0 && mds < m->m_max_mds) {
+ if (mds >= 0 && mds < m->m_num_mds) {
if (m->m_info[mds].laggy)
num_laggy++;
}
}
m->m_num_laggy = num_laggy;
+
+ if (n > m->m_num_mds) {
+ void *new_m_info = krealloc(m->m_info,
+ n * sizeof(*m->m_info),
+ GFP_NOFS | __GFP_ZERO);
+ if (!new_m_info)
+ goto nomem;
+ m->m_info = new_m_info;
+ }
+ m->m_num_mds = n;
}
/* inc */
{
int i;
- for (i = 0; i < m->m_max_mds; i++)
+ for (i = 0; i < m->m_num_mds; i++)
kfree(m->m_info[i].export_targets);
kfree(m->m_info);
kfree(m->m_data_pg_pools);
return false;
if (m->m_num_laggy > 0)
return false;
- for (i = 0; i < m->m_max_mds; i++) {
+ for (i = 0; i < m->m_num_mds; i++) {
if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE)
nr_active++;
}
capsnap->need_flush ? "" : "no_flush");
ihold(inode);
- atomic_set(&capsnap->nref, 1);
+ refcount_set(&capsnap->nref, 1);
INIT_LIST_HEAD(&capsnap->ci_item);
capsnap->follows = old_snapc->seq;
struct ceph_options *opt)
{
struct ceph_fs_client *fsc;
- const u64 supported_features =
- CEPH_FEATURE_FLOCK | CEPH_FEATURE_DIRLAYOUTHASH |
- CEPH_FEATURE_MDSENC | CEPH_FEATURE_MDS_INLINE_DATA;
- const u64 required_features = 0;
int page_count;
size_t size;
int err = -ENOMEM;
if (!fsc)
return ERR_PTR(-ENOMEM);
- fsc->client = ceph_create_client(opt, fsc, supported_features,
- required_features);
+ fsc->client = ceph_create_client(opt, fsc);
if (IS_ERR(fsc->client)) {
err = PTR_ERR(fsc->client);
goto fail;
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/posix_acl.h>
+#include <linux/refcount.h>
#include <linux/ceph/libceph.h>
* data before flushing the snapped state (tracked here) back to the MDS.
*/
struct ceph_cap_snap {
- atomic_t nref;
+ refcount_t nref;
struct list_head ci_item;
struct ceph_cap_flush cap_flush;
static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
{
- if (atomic_dec_and_test(&capsnap->nref)) {
+ if (refcount_dec_and_test(&capsnap->nref)) {
if (capsnap->xattr_blob)
ceph_buffer_put(capsnap->xattr_blob);
kfree(capsnap);
#define CEPH_I_CAP_DROPPED (1 << 8) /* caps were forcibly dropped */
#define CEPH_I_KICK_FLUSH (1 << 9) /* kick flushing caps */
#define CEPH_I_FLUSH_SNAPS (1 << 10) /* need flush snapss */
+#define CEPH_I_ERROR_WRITE (1 << 11) /* have seen write errors */
+
+/*
+ * We set the ERROR_WRITE bit when we start seeing write errors on an inode
+ * and then clear it when they start succeeding. Note that we do a lockless
+ * check first, and only take the lock if it looks like it needs to be changed.
+ * The write submission code just takes this as a hint, so we're not too
+ * worried if a few slip through in either direction.
+ */
+static inline void ceph_set_error_write(struct ceph_inode_info *ci)
+{
+ if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE)) {
+ spin_lock(&ci->i_ceph_lock);
+ ci->i_ceph_flags |= CEPH_I_ERROR_WRITE;
+ spin_unlock(&ci->i_ceph_lock);
+ }
+}
+
+static inline void ceph_clear_error_write(struct ceph_inode_info *ci)
+{
+ if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE) {
+ spin_lock(&ci->i_ceph_lock);
+ ci->i_ceph_flags &= ~CEPH_I_ERROR_WRITE;
+ spin_unlock(&ci->i_ceph_lock);
+ }
+}
static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
long long release_count,
if (update_xattr) {
int err = 0;
+
if (xattr && (flags & XATTR_CREATE))
err = -EEXIST;
else if (!xattr && (flags & XATTR_REPLACE))
if (err) {
kfree(name);
kfree(val);
+ kfree(*newxattr);
return err;
}
if (update_xattr < 0) {
if (xattr)
__remove_xattr(ci, xattr);
kfree(name);
+ kfree(*newxattr);
return 0;
}
}
#include <linux/pipe_fs_i.h>
#include <linux/swap.h>
#include <linux/splice.h>
+#include <linux/sched.h>
MODULE_ALIAS_MISCDEV(FUSE_MINOR);
MODULE_ALIAS("devname:fuse");
INIT_LIST_HEAD(&req->list);
INIT_LIST_HEAD(&req->intr_entry);
init_waitqueue_head(&req->waitq);
- atomic_set(&req->count, 1);
+ refcount_set(&req->count, 1);
req->pages = pages;
req->page_descs = page_descs;
req->max_pages = npages;
void __fuse_get_request(struct fuse_req *req)
{
- atomic_inc(&req->count);
+ refcount_inc(&req->count);
}
/* Must be called with > 1 refcount */
static void __fuse_put_request(struct fuse_req *req)
{
- BUG_ON(atomic_read(&req->count) < 2);
- atomic_dec(&req->count);
+ refcount_dec(&req->count);
}
-static void fuse_req_init_context(struct fuse_req *req)
+static void fuse_req_init_context(struct fuse_conn *fc, struct fuse_req *req)
{
req->in.h.uid = from_kuid_munged(&init_user_ns, current_fsuid());
req->in.h.gid = from_kgid_munged(&init_user_ns, current_fsgid());
- req->in.h.pid = current->pid;
+ req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
}
void fuse_set_initialized(struct fuse_conn *fc)
goto out;
}
- fuse_req_init_context(req);
+ fuse_req_init_context(fc, req);
__set_bit(FR_WAITING, &req->flags);
if (for_background)
__set_bit(FR_BACKGROUND, &req->flags);
if (!req)
req = get_reserved_req(fc, file);
- fuse_req_init_context(req);
+ fuse_req_init_context(fc, req);
__set_bit(FR_WAITING, &req->flags);
__clear_bit(FR_BACKGROUND, &req->flags);
return req;
void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
{
- if (atomic_dec_and_test(&req->count)) {
+ if (refcount_dec_and_test(&req->count)) {
if (test_bit(FR_BACKGROUND, &req->flags)) {
/*
* We get here in the unlikely case that a background
struct fuse_in *in;
unsigned reqsize;
+ if (task_active_pid_ns(current) != fc->pid_ns)
+ return -EIO;
+
restart:
spin_lock(&fiq->waitq.lock);
err = -EAGAIN;
struct fuse_req *req;
struct fuse_out_header oh;
+ if (task_active_pid_ns(current) != fc->pid_ns)
+ return -EIO;
+
if (nbytes < sizeof(struct fuse_out_header))
return -EINVAL;
}
INIT_LIST_HEAD(&ff->write_entry);
- atomic_set(&ff->count, 1);
+ refcount_set(&ff->count, 1);
RB_CLEAR_NODE(&ff->polled_node);
init_waitqueue_head(&ff->poll_wait);
static struct fuse_file *fuse_file_get(struct fuse_file *ff)
{
- atomic_inc(&ff->count);
+ refcount_inc(&ff->count);
return ff;
}
static void fuse_file_put(struct fuse_file *ff, bool sync)
{
- if (atomic_dec_and_test(&ff->count)) {
+ if (refcount_dec_and_test(&ff->count)) {
struct fuse_req *req = ff->reserved_req;
if (ff->fc->no_open) {
void fuse_sync_release(struct fuse_file *ff, int flags)
{
- WARN_ON(atomic_read(&ff->count) != 1);
+ WARN_ON(refcount_read(&ff->count) > 1);
fuse_prepare_release(ff, flags, FUSE_RELEASE);
/*
* iput(NULL) is a no-op and since the refcount is 1 and everything's
return generic_file_mmap(file, vma);
}
-static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,
+static int convert_fuse_file_lock(struct fuse_conn *fc,
+ const struct fuse_file_lock *ffl,
struct file_lock *fl)
{
switch (ffl->type) {
fl->fl_start = ffl->start;
fl->fl_end = ffl->end;
- fl->fl_pid = ffl->pid;
+
+ /*
+ * Convert pid into the caller's pid namespace. If the pid
+ * does not map into the namespace fl_pid will get set to 0.
+ */
+ rcu_read_lock();
+ fl->fl_pid = pid_vnr(find_pid_ns(ffl->pid, fc->pid_ns));
+ rcu_read_unlock();
break;
default:
args.out.args[0].value = &outarg;
err = fuse_simple_request(fc, &args);
if (!err)
- err = convert_fuse_file_lock(&outarg.lk, fl);
+ err = convert_fuse_file_lock(fc, &outarg.lk, fl);
return err;
}
FUSE_ARGS(args);
struct fuse_lk_in inarg;
int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
- pid_t pid = fl->fl_type != F_UNLCK ? current->tgid : 0;
+ struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL;
+ pid_t pid_nr = pid_nr_ns(pid, fc->pid_ns);
int err;
if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
}
/* Unlock on close is handled by the flush method */
- if (fl->fl_flags & FL_CLOSE)
+ if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
return 0;
- fuse_lk_fill(&args, file, fl, opcode, pid, flock, &inarg);
+ if (pid && pid_nr == 0)
+ return -EOVERFLOW;
+
+ fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
err = fuse_simple_request(fc, &args);
/* locking is restartable */
#include <linux/workqueue.h>
#include <linux/kref.h>
#include <linux/xattr.h>
+#include <linux/pid_namespace.h>
+#include <linux/refcount.h>
/** Max number of pages that can be used in a single read request */
#define FUSE_MAX_PAGES_PER_REQ 32
u64 nodeid;
/** Refcount */
- atomic_t count;
+ refcount_t count;
/** FOPEN_* flags returned by open */
u32 open_flags;
struct list_head intr_entry;
/** refcount */
- atomic_t count;
+ refcount_t count;
/** Unique ID for the interrupt request */
u64 intr_unique;
spinlock_t lock;
/** Refcount */
- atomic_t count;
+ refcount_t count;
/** Number of fuse_dev's */
atomic_t dev_count;
/** The group id for this mount */
kgid_t group_id;
+ /** The pid namespace for this mount */
+ struct pid_namespace *pid_ns;
+
/** Maximum read size */
unsigned max_read;
#include <linux/sched.h>
#include <linux/exportfs.h>
#include <linux/posix_acl.h>
+#include <linux/pid_namespace.h>
MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Filesystem in Userspace");
memset(fc, 0, sizeof(*fc));
spin_lock_init(&fc->lock);
init_rwsem(&fc->killsb);
- atomic_set(&fc->count, 1);
+ refcount_set(&fc->count, 1);
atomic_set(&fc->dev_count, 1);
init_waitqueue_head(&fc->blocked_waitq);
init_waitqueue_head(&fc->reserved_req_waitq);
fc->connected = 1;
fc->attr_version = 1;
get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
+ fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(fuse_conn_init);
void fuse_conn_put(struct fuse_conn *fc)
{
- if (atomic_dec_and_test(&fc->count)) {
+ if (refcount_dec_and_test(&fc->count)) {
if (fc->destroy_req)
fuse_request_free(fc->destroy_req);
+ put_pid_ns(fc->pid_ns);
fc->release(fc);
}
}
struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
{
- atomic_inc(&fc->count);
+ refcount_inc(&fc->count);
return fc;
}
EXPORT_SYMBOL_GPL(fuse_conn_get);
jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
sizeof(struct journal_head),
0, /* offset */
- SLAB_TEMPORARY | SLAB_DESTROY_BY_RCU,
+ SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU,
NULL); /* ctor */
retval = 0;
if (!jbd2_journal_head_cache) {
jffs2_add_ino_cache(c, f->inocache);
}
if (!f->inocache) {
- JFFS2_ERROR("requestied to read an nonexistent ino %u\n", ino);
+ JFFS2_ERROR("requested to read a nonexistent ino %u\n", ino);
return -ENOENT;
}
if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
goto out_nobind;
+ host->h_nlmclnt_ops = nlm_init->nlmclnt_ops;
return host;
out_nobind:
nlmclnt_release_host(host);
* @host: address of a valid nlm_host context representing the NLM server
* @cmd: fcntl-style file lock operation to perform
* @fl: address of arguments for the lock operation
+ * @data: address of data to be sent to callback operations
*
*/
-int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
+int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl, void *data)
{
struct nlm_rqst *call;
int status;
+ const struct nlmclnt_operations *nlmclnt_ops = host->h_nlmclnt_ops;
call = nlm_alloc_call(host);
if (call == NULL)
return -ENOMEM;
+ if (nlmclnt_ops && nlmclnt_ops->nlmclnt_alloc_call)
+ nlmclnt_ops->nlmclnt_alloc_call(data);
+
nlmclnt_locks_init_private(fl, host);
if (!fl->fl_u.nfs_fl.owner) {
/* lockowner allocation has failed */
}
/* Set up the argument struct */
nlmclnt_setlockargs(call, fl);
+ call->a_callback_data = data;
if (IS_SETLK(cmd) || IS_SETLKW(cmd)) {
if (fl->fl_type != F_UNLCK) {
void nlmclnt_release_call(struct nlm_rqst *call)
{
+ const struct nlmclnt_operations *nlmclnt_ops = call->a_host->h_nlmclnt_ops;
+
if (!atomic_dec_and_test(&call->a_count))
return;
+ if (nlmclnt_ops && nlmclnt_ops->nlmclnt_release_call)
+ nlmclnt_ops->nlmclnt_release_call(call->a_callback_data);
nlmclnt_release_host(call->a_host);
nlmclnt_release_lockargs(call);
kfree(call);
return status;
}
+static void nlmclnt_unlock_prepare(struct rpc_task *task, void *data)
+{
+ struct nlm_rqst *req = data;
+ const struct nlmclnt_operations *nlmclnt_ops = req->a_host->h_nlmclnt_ops;
+ bool defer_call = false;
+
+ if (nlmclnt_ops && nlmclnt_ops->nlmclnt_unlock_prepare)
+ defer_call = nlmclnt_ops->nlmclnt_unlock_prepare(task, req->a_callback_data);
+
+ if (!defer_call)
+ rpc_call_start(task);
+}
+
static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
{
struct nlm_rqst *req = data;
}
static const struct rpc_call_ops nlmclnt_unlock_ops = {
+ .rpc_call_prepare = nlmclnt_unlock_prepare,
.rpc_call_done = nlmclnt_unlock_callback,
.rpc_release = nlmclnt_rpc_release,
};
{
int err = 0;
struct svc_rqst *rqstp = vrqstp;
+ struct net *net = &init_net;
+ struct lockd_net *ln = net_generic(net, lockd_net_id);
/* try_to_freeze() is called from svc_recv() */
set_freezable();
if (nlmsvc_ops)
nlmsvc_invalidate_all();
nlm_shutdown_hosts();
+ cancel_delayed_work_sync(&ln->grace_period_end);
+ locks_end_grace(&ln->lockd_manager);
return 0;
}
if (ln->nlmsvc_users) {
if (--ln->nlmsvc_users == 0) {
nlm_shutdown_hosts_net(net);
- cancel_delayed_work_sync(&ln->grace_period_end);
- locks_end_grace(&ln->lockd_manager);
svc_shutdown_net(serv, net);
dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net);
}
if (!(block = nlmsvc_find_block(cookie)))
return;
- if (block) {
- if (status == nlm_lck_denied_grace_period) {
- /* Try again in a couple of seconds */
- nlmsvc_insert_block(block, 10 * HZ);
- } else {
- /* Lock is now held by client, or has been rejected.
- * In both cases, the block should be removed. */
- nlmsvc_unlink_block(block);
- }
+ if (status == nlm_lck_denied_grace_period) {
+ /* Try again in a couple of seconds */
+ nlmsvc_insert_block(block, 10 * HZ);
+ } else {
+ /*
+ * Lock is now held by client, or has been rejected.
+ * In both cases, the block should be removed.
+ */
+ nlmsvc_unlink_block(block);
}
nlmsvc_release_block(block);
}
.fl_owner = filp,
.fl_pid = current->tgid,
.fl_file = filp,
- .fl_flags = FL_FLOCK,
+ .fl_flags = FL_FLOCK | FL_CLOSE,
.fl_type = F_UNLCK,
.fl_end = OFFSET_MAX,
};
depends on NFS_V4_1 && BLK_DEV_DM
default NFS_V4
-config PNFS_OBJLAYOUT
- tristate
- depends on NFS_V4_1 && SCSI_OSD_ULD
- default NFS_V4
-
config PNFS_FLEXFILE_LAYOUT
tristate
depends on NFS_V4_1 && NFS_V3
nfsv4-$(CONFIG_NFS_V4_2) += nfs42proc.o
obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
-obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/
set_freezable();
- while (!kthread_should_stop()) {
+ while (!kthread_freezable_should_stop(NULL)) {
+
+ if (signal_pending(current))
+ flush_signals(current);
/*
* Listen for a request on the socket
*/
continue;
svc_process(rqstp);
}
+ svc_exit_thread(rqstp);
+ module_put_and_exit(0);
return 0;
}
set_freezable();
- while (!kthread_should_stop()) {
- if (try_to_freeze())
- continue;
+ while (!kthread_freezable_should_stop(NULL)) {
+
+ if (signal_pending(current))
+ flush_signals(current);
prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
spin_lock_bh(&serv->sv_cb_lock);
error);
} else {
spin_unlock_bh(&serv->sv_cb_lock);
- schedule();
+ if (!kthread_should_stop())
+ schedule();
finish_wait(&serv->sv_cb_waitq, &wq);
}
- flush_signals(current);
}
+ svc_exit_thread(rqstp);
+ module_put_and_exit(0);
return 0;
}
static struct svc_serv_ops nfs40_cb_sv_ops = {
.svo_function = nfs4_callback_svc,
.svo_enqueue_xprt = svc_xprt_do_enqueue,
- .svo_setup = svc_set_num_threads,
+ .svo_setup = svc_set_num_threads_sync,
.svo_module = THIS_MODULE,
};
#if defined(CONFIG_NFS_V4_1)
static struct svc_serv_ops nfs41_cb_sv_ops = {
.svo_function = nfs41_callback_svc,
.svo_enqueue_xprt = svc_xprt_do_enqueue,
- .svo_setup = svc_set_num_threads,
+ .svo_setup = svc_set_num_threads_sync,
.svo_module = THIS_MODULE,
};
printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n",
cb_info->users);
- serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops);
+ serv = svc_create_pooled(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops);
if (!serv) {
printk(KERN_ERR "nfs_callback_create_svc: create service failed\n");
return ERR_PTR(-ENOMEM);
if (!inode)
continue;
if (!nfs_sb_active(inode->i_sb)) {
- rcu_read_lock();
+ rcu_read_unlock();
spin_unlock(&clp->cl_lock);
iput(inode);
spin_lock(&clp->cl_lock);
+ rcu_read_lock();
goto restart;
}
return inode;
if (!inode)
continue;
if (!nfs_sb_active(inode->i_sb)) {
- rcu_read_lock();
+ rcu_read_unlock();
spin_unlock(&clp->cl_lock);
iput(inode);
spin_lock(&clp->cl_lock);
+ rcu_read_lock();
goto restart;
}
return inode;
static u32 do_callback_layoutrecall(struct nfs_client *clp,
struct cb_layoutrecallargs *args)
{
- u32 res;
-
- dprintk("%s enter, type=%i\n", __func__, args->cbl_recall_type);
if (args->cbl_recall_type == RETURN_FILE)
- res = initiate_file_draining(clp, args);
- else
- res = initiate_bulk_draining(clp, args);
- dprintk("%s returning %i\n", __func__, res);
- return res;
-
+ return initiate_file_draining(clp, args);
+ return initiate_bulk_draining(clp, args);
}
__be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args,
void *dummy, struct cb_process_state *cps)
{
- u32 res;
-
- dprintk("%s: -->\n", __func__);
+ u32 res = NFS4ERR_OP_NOT_IN_SESSION;
if (cps->clp)
res = do_callback_layoutrecall(cps->clp, args);
- else
- res = NFS4ERR_OP_NOT_IN_SESSION;
-
- dprintk("%s: exit with status = %d\n", __func__, res);
return cpu_to_be32(res);
}
struct nfs_client *clp = cps->clp;
struct nfs_server *server = NULL;
- dprintk("%s: -->\n", __func__);
-
if (!clp) {
res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
goto out;
goto found;
}
rcu_read_unlock();
- dprintk("%s: layout type %u not found\n",
- __func__, dev->cbd_layout_type);
continue;
}
out:
kfree(args->devs);
- dprintk("%s: exit with status = %u\n",
- __func__, be32_to_cpu(res));
return res;
}
validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
const struct cb_sequenceargs * args)
{
- dprintk("%s enter. slotid %u seqid %u, slot table seqid: %u\n",
- __func__, args->csa_slotid, args->csa_sequenceid, slot->seq_nr);
-
if (args->csa_slotid > tbl->server_highest_slotid)
return htonl(NFS4ERR_BADSLOT);
/* Replay */
if (args->csa_sequenceid == slot->seq_nr) {
- dprintk("%s seqid %u is a replay\n",
- __func__, args->csa_sequenceid);
if (nfs4_test_locked_slot(tbl, slot->slot_nr))
return htonl(NFS4ERR_DELAY);
/* Signal process_op to set this error on next op */
for (j = 0; j < rclist->rcl_nrefcalls; j++) {
ref = &rclist->rcl_refcalls[j];
-
- dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u "
- "slotid %u\n", __func__,
- ((u32 *)&rclist->rcl_sessionid.data)[0],
- ((u32 *)&rclist->rcl_sessionid.data)[1],
- ((u32 *)&rclist->rcl_sessionid.data)[2],
- ((u32 *)&rclist->rcl_sessionid.data)[3],
- ref->rc_sequenceid, ref->rc_slotid);
-
status = nfs4_slot_wait_on_seqid(tbl, ref->rc_slotid,
ref->rc_sequenceid, HZ >> 1) < 0;
if (status)
res->csr_status = status;
trace_nfs4_cb_sequence(args, res, status);
- dprintk("%s: exit with status = %d res->csr_status %d\n", __func__,
- ntohl(status), ntohl(res->csr_status));
return status;
}
return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
}
hdr->nops = ntohl(*p);
- dprintk("%s: minorversion %d nops %d\n", __func__,
- hdr->minorversion, hdr->nops);
return 0;
}
status = decode_fh(xdr, &args->fh);
if (unlikely(status != 0))
- goto out;
- status = decode_bitmap(xdr, args->bitmap);
-out:
- dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
- return status;
+ return status;
+ return decode_bitmap(xdr, args->bitmap);
}
static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_recallargs *args)
status = decode_delegation_stateid(xdr, &args->stateid);
if (unlikely(status != 0))
- goto out;
+ return status;
p = read_buf(xdr, 4);
- if (unlikely(p == NULL)) {
- status = htonl(NFS4ERR_RESOURCE);
- goto out;
- }
+ if (unlikely(p == NULL))
+ return htonl(NFS4ERR_RESOURCE);
args->truncate = ntohl(*p);
- status = decode_fh(xdr, &args->fh);
-out:
- dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
- return status;
+ return decode_fh(xdr, &args->fh);
}
#if defined(CONFIG_NFS_V4_1)
uint32_t iomode;
p = read_buf(xdr, 4 * sizeof(uint32_t));
- if (unlikely(p == NULL)) {
- status = htonl(NFS4ERR_BADXDR);
- goto out;
- }
+ if (unlikely(p == NULL))
+ return htonl(NFS4ERR_BADXDR);
args->cbl_layout_type = ntohl(*p++);
/* Depite the spec's xdr, iomode really belongs in the FILE switch,
args->cbl_range.iomode = iomode;
status = decode_fh(xdr, &args->cbl_fh);
if (unlikely(status != 0))
- goto out;
+ return status;
p = read_buf(xdr, 2 * sizeof(uint64_t));
- if (unlikely(p == NULL)) {
- status = htonl(NFS4ERR_BADXDR);
- goto out;
- }
+ if (unlikely(p == NULL))
+ return htonl(NFS4ERR_BADXDR);
p = xdr_decode_hyper(p, &args->cbl_range.offset);
p = xdr_decode_hyper(p, &args->cbl_range.length);
- status = decode_layout_stateid(xdr, &args->cbl_stateid);
- if (unlikely(status != 0))
- goto out;
+ return decode_layout_stateid(xdr, &args->cbl_stateid);
} else if (args->cbl_recall_type == RETURN_FSID) {
p = read_buf(xdr, 2 * sizeof(uint64_t));
- if (unlikely(p == NULL)) {
- status = htonl(NFS4ERR_BADXDR);
- goto out;
- }
+ if (unlikely(p == NULL))
+ return htonl(NFS4ERR_BADXDR);
p = xdr_decode_hyper(p, &args->cbl_fsid.major);
p = xdr_decode_hyper(p, &args->cbl_fsid.minor);
- } else if (args->cbl_recall_type != RETURN_ALL) {
- status = htonl(NFS4ERR_BADXDR);
- goto out;
- }
- dprintk("%s: ltype 0x%x iomode %d changed %d recall_type %d\n",
- __func__,
- args->cbl_layout_type, iomode,
- args->cbl_layoutchanged, args->cbl_recall_type);
-out:
- dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
- return status;
+ } else if (args->cbl_recall_type != RETURN_ALL)
+ return htonl(NFS4ERR_BADXDR);
+ return 0;
}
static
status = decode_sessionid(xdr, &args->csa_sessionid);
if (status)
- goto out;
+ return status;
- status = htonl(NFS4ERR_RESOURCE);
p = read_buf(xdr, 5 * sizeof(uint32_t));
if (unlikely(p == NULL))
- goto out;
+ return htonl(NFS4ERR_RESOURCE);
args->csa_addr = svc_addr(rqstp);
args->csa_sequenceid = ntohl(*p++);
sizeof(*args->csa_rclists),
GFP_KERNEL);
if (unlikely(args->csa_rclists == NULL))
- goto out;
+ return htonl(NFS4ERR_RESOURCE);
for (i = 0; i < args->csa_nrclists; i++) {
status = decode_rc_list(xdr, &args->csa_rclists[i]);
}
}
}
- status = 0;
-
- dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u slotid %u "
- "highestslotid %u cachethis %d nrclists %u\n",
- __func__,
- ((u32 *)&args->csa_sessionid)[0],
- ((u32 *)&args->csa_sessionid)[1],
- ((u32 *)&args->csa_sessionid)[2],
- ((u32 *)&args->csa_sessionid)[3],
- args->csa_sequenceid, args->csa_slotid,
- args->csa_highestslotid, args->csa_cachethis,
- args->csa_nrclists);
-out:
- dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
- return status;
+ return 0;
out_free:
for (i = 0; i < args->csa_nrclists; i++)
kfree(args->csa_rclists[i].rcl_refcalls);
kfree(args->csa_rclists);
- goto out;
+ return status;
}
static __be32 decode_recallany_args(struct svc_rqst *rqstp,
status = decode_fh(xdr, &args->cbnl_fh);
if (unlikely(status != 0))
- goto out;
- status = decode_lockowner(xdr, args);
-out:
- dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
- return status;
+ return status;
+ return decode_lockowner(xdr, args);
}
#endif /* CONFIG_NFS_V4_1 */
status = encode_attr_mtime(xdr, res->bitmap, &res->mtime);
*savep = htonl((unsigned int)((char *)xdr->p - (char *)(savep+1)));
out:
- dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
return status;
}
__be32 status = res->csr_status;
if (unlikely(status != 0))
- goto out;
+ return status;
status = encode_sessionid(xdr, &res->csr_sessionid);
if (status)
- goto out;
+ return status;
p = xdr_reserve_space(xdr, 4 * sizeof(uint32_t));
if (unlikely(p == NULL))
*p++ = htonl(res->csr_slotid);
*p++ = htonl(res->csr_highestslotid);
*p++ = htonl(res->csr_target_highestslotid);
-out:
- dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
- return status;
+ return 0;
}
static __be32
long maxlen;
__be32 res;
- dprintk("%s: start\n", __func__);
status = decode_op_hdr(xdr_in, &op_nr);
if (unlikely(status))
return status;
- dprintk("%s: minorversion=%d nop=%d op_nr=%u\n",
- __func__, cps->minorversion, nop, op_nr);
-
switch (cps->minorversion) {
case 0:
status = preprocess_nfs4_op(op_nr, &op);
return res;
if (op->encode_res != NULL && status == 0)
status = op->encode_res(rqstp, xdr_out, resp);
- dprintk("%s: done, status = %d\n", __func__, ntohl(status));
return status;
}
};
unsigned int nops = 0;
- dprintk("%s: start\n", __func__);
-
xdr_init_decode(&xdr_in, &rqstp->rq_arg, rqstp->rq_arg.head[0].iov_base);
p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len);
*hdr_res.nops = htonl(nops);
nfs4_cb_free_slot(&cps);
nfs_put_client(cps.clp);
- dprintk("%s: done, status = %u\n", __func__, ntohl(status));
return rpc_success;
out_invalidcred:
static void pnfs_init_server(struct nfs_server *server)
{
rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
+ rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
}
#else
*/
void nfs_free_client(struct nfs_client *clp)
{
- dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version);
-
nfs_fscache_release_client_cookie(clp);
/* -EIO all pending I/O */
kfree(clp->cl_hostname);
kfree(clp->cl_acceptor);
kfree(clp);
-
- dprintk("<-- nfs_free_client()\n");
}
EXPORT_SYMBOL_GPL(nfs_free_client);
if (!clp)
return;
- dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
nn = net_generic(clp->cl_net, nfs_net_id);
if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
}
smp_rmb();
-
- dprintk("<-- %s found nfs_client %p for %s\n",
- __func__, clp, cl_init->hostname ?: "");
return clp;
}
return NULL;
}
- dprintk("--> nfs_get_client(%s,v%u)\n",
- cl_init->hostname, rpc_ops->version);
-
/* see if the client already exists */
do {
spin_lock(&nn->nfs_client_lock);
new = rpc_ops->alloc_client(cl_init);
} while (!IS_ERR(new));
- dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
- cl_init->hostname, PTR_ERR(new));
return new;
}
EXPORT_SYMBOL_GPL(nfs_get_client);
.noresvport = server->flags & NFS_MOUNT_NORESVPORT ?
1 : 0,
.net = clp->cl_net,
+ .nlmclnt_ops = clp->cl_nfs_mod->rpc_ops->nlmclnt_ops,
};
if (nlm_init.nfs_version > 3)
{
int error;
- if (clp->cl_cons_state == NFS_CS_READY) {
- /* the client is already initialised */
- dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp);
+ /* the client is already initialised */
+ if (clp->cl_cons_state == NFS_CS_READY)
return clp;
- }
/*
* Create a client RPC handle for doing FSSTAT with UNIX auth only
* - RFC 2623, sec 2.3.2
*/
error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX);
- if (error < 0)
- goto error;
- nfs_mark_client_ready(clp, NFS_CS_READY);
+ nfs_mark_client_ready(clp, error == 0 ? NFS_CS_READY : error);
+ if (error < 0) {
+ nfs_put_client(clp);
+ clp = ERR_PTR(error);
+ }
return clp;
-
-error:
- nfs_mark_client_ready(clp, error);
- nfs_put_client(clp);
- dprintk("<-- nfs_init_client() = xerror %d\n", error);
- return ERR_PTR(error);
}
EXPORT_SYMBOL_GPL(nfs_init_client);
struct nfs_client *clp;
int error;
- dprintk("--> nfs_init_server()\n");
-
nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
data->timeo, data->retrans);
if (data->flags & NFS_MOUNT_NORESVPORT)
/* Allocate or find a client reference we can use */
clp = nfs_get_client(&cl_init);
- if (IS_ERR(clp)) {
- dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
+ if (IS_ERR(clp))
return PTR_ERR(clp);
- }
server->nfs_client = clp;
server->mountd_protocol = data->mount_server.protocol;
server->namelen = data->namlen;
- dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp);
return 0;
error:
server->nfs_client = NULL;
nfs_put_client(clp);
- dprintk("<-- nfs_init_server() = xerror %d\n", error);
return error;
}
struct nfs_client *clp = server->nfs_client;
int error;
- dprintk("--> nfs_probe_fsinfo()\n");
-
if (clp->rpc_ops->set_capabilities != NULL) {
error = clp->rpc_ops->set_capabilities(server, mntfh);
if (error < 0)
- goto out_error;
+ return error;
}
fsinfo.fattr = fattr;
memset(fsinfo.layouttype, 0, sizeof(fsinfo.layouttype));
error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo);
if (error < 0)
- goto out_error;
+ return error;
nfs_server_set_fsinfo(server, &fsinfo);
server->namelen = pathinfo.max_namelen;
}
- dprintk("<-- nfs_probe_fsinfo() = 0\n");
return 0;
-
-out_error:
- dprintk("nfs_probe_fsinfo: error = %d\n", -error);
- return error;
}
EXPORT_SYMBOL_GPL(nfs_probe_fsinfo);
*/
void nfs_free_server(struct nfs_server *server)
{
- dprintk("--> nfs_free_server()\n");
-
nfs_server_remove_lists(server);
if (server->destroy != NULL)
nfs_free_iostats(server->io_stats);
kfree(server);
nfs_release_automount_timer();
- dprintk("<-- nfs_free_server()\n");
}
EXPORT_SYMBOL_GPL(nfs_free_server);
struct nfs_fattr *fattr_fsinfo;
int error;
- dprintk("--> nfs_clone_server(,%llx:%llx,)\n",
- (unsigned long long) fattr->fsid.major,
- (unsigned long long) fattr->fsid.minor);
-
server = nfs_alloc_server();
if (!server)
return ERR_PTR(-ENOMEM);
if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
server->namelen = NFS4_MAXNAMLEN;
- dprintk("Cloned FSID: %llx:%llx\n",
- (unsigned long long) server->fsid.major,
- (unsigned long long) server->fsid.minor);
-
error = nfs_start_lockd(server);
if (error < 0)
goto out_free_server;
server->mount_time = jiffies;
nfs_free_fattr(fattr_fsinfo);
- dprintk("<-- nfs_clone_server() = %p\n", server);
return server;
out_free_server:
nfs_free_fattr(fattr_fsinfo);
nfs_free_server(server);
- dprintk("<-- nfs_clone_server() = error %d\n", error);
return ERR_PTR(error);
}
EXPORT_SYMBOL_GPL(nfs_clone_server);
const struct file_operations nfs_dir_operations = {
.llseek = nfs_llseek_dir,
.read = generic_read_dir,
- .iterate_shared = nfs_readdir,
+ .iterate = nfs_readdir,
.open = nfs_opendir,
.release = nfs_closedir,
.fsync = nfs_fsync_dir,
};
struct nfs_cache_array {
- atomic_t refcount;
int size;
int eof_index;
u64 last_cookie;
unsigned int eof:1;
} nfs_readdir_descriptor_t;
-/*
- * The caller is responsible for calling nfs_readdir_release_array(page)
- */
-static
-struct nfs_cache_array *nfs_readdir_get_array(struct page *page)
-{
- void *ptr;
- if (page == NULL)
- return ERR_PTR(-EIO);
- ptr = kmap(page);
- if (ptr == NULL)
- return ERR_PTR(-ENOMEM);
- return ptr;
-}
-
-static
-void nfs_readdir_release_array(struct page *page)
-{
- kunmap(page);
-}
-
/*
* we are freeing strings created by nfs_add_to_readdir_array()
*/
int i;
array = kmap_atomic(page);
- if (atomic_dec_and_test(&array->refcount))
- for (i = 0; i < array->size; i++)
- kfree(array->array[i].string.name);
- kunmap_atomic(array);
-}
-
-static bool grab_page(struct page *page)
-{
- struct nfs_cache_array *array = kmap_atomic(page);
- bool res = atomic_inc_not_zero(&array->refcount);
+ for (i = 0; i < array->size; i++)
+ kfree(array->array[i].string.name);
kunmap_atomic(array);
- return res;
}
/*
static
int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
{
- struct nfs_cache_array *array = nfs_readdir_get_array(page);
+ struct nfs_cache_array *array = kmap(page);
struct nfs_cache_array_entry *cache_entry;
int ret;
- if (IS_ERR(array))
- return PTR_ERR(array);
-
cache_entry = &array->array[array->size];
/* Check that this entry lies within the page bounds */
if (entry->eof != 0)
array->eof_index = array->size;
out:
- nfs_readdir_release_array(page);
+ kunmap(page);
return ret;
}
struct nfs_cache_array *array;
int status;
- array = nfs_readdir_get_array(desc->page);
- if (IS_ERR(array)) {
- status = PTR_ERR(array);
- goto out;
- }
+ array = kmap(desc->page);
if (*desc->dir_cookie == 0)
status = nfs_readdir_search_for_pos(array, desc);
desc->current_index += array->size;
desc->page_index++;
}
- nfs_readdir_release_array(desc->page);
-out:
+ kunmap(desc->page);
return status;
}
out_nopages:
if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
- array = nfs_readdir_get_array(page);
- if (!IS_ERR(array)) {
- array->eof_index = array->size;
- status = 0;
- nfs_readdir_release_array(page);
- } else
- status = PTR_ERR(array);
+ array = kmap(page);
+ array->eof_index = array->size;
+ status = 0;
+ kunmap(page);
}
put_page(scratch);
goto out;
}
- array = nfs_readdir_get_array(page);
- if (IS_ERR(array)) {
- status = PTR_ERR(array);
- goto out_label_free;
- }
+ array = kmap(page);
memset(array, 0, sizeof(struct nfs_cache_array));
- atomic_set(&array->refcount, 1);
array->eof_index = -1;
status = nfs_readdir_alloc_pages(pages, array_size);
nfs_readdir_free_pages(pages, array_size);
out_release_array:
- nfs_readdir_release_array(page);
-out_label_free:
+ kunmap(page);
nfs4_label_free(entry.label);
out:
nfs_free_fattr(entry.fattr);
static
void cache_page_release(nfs_readdir_descriptor_t *desc)
{
- nfs_readdir_clear_array(desc->page);
+ if (!desc->page->mapping)
+ nfs_readdir_clear_array(desc->page);
put_page(desc->page);
desc->page = NULL;
}
static
struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
{
- struct page *page;
-
- for (;;) {
- page = read_cache_page(desc->file->f_mapping,
+ return read_cache_page(desc->file->f_mapping,
desc->page_index, (filler_t *)nfs_readdir_filler, desc);
- if (IS_ERR(page) || grab_page(page))
- break;
- put_page(page);
- }
- return page;
}
/*
struct nfs_cache_array *array = NULL;
struct nfs_open_dir_context *ctx = file->private_data;
- array = nfs_readdir_get_array(desc->page);
- if (IS_ERR(array)) {
- res = PTR_ERR(array);
- goto out;
- }
-
+ array = kmap(desc->page);
for (i = desc->cache_entry_index; i < array->size; i++) {
struct nfs_cache_array_entry *ent;
if (array->eof_index >= 0)
desc->eof = 1;
- nfs_readdir_release_array(desc->page);
-out:
+ kunmap(desc->page);
cache_page_release(desc);
dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
(unsigned long long)*desc->dir_cookie, res);
static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
{
+ struct inode *inode = file_inode(filp);
struct nfs_open_dir_context *dir_ctx = filp->private_data;
dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
filp, offset, whence);
+ inode_lock(inode);
switch (whence) {
case 1:
offset += filp->f_pos;
if (offset >= 0)
break;
default:
- return -EINVAL;
+ offset = -EINVAL;
+ goto out;
}
if (offset != filp->f_pos) {
filp->f_pos = offset;
dir_ctx->dir_cookie = 0;
dir_ctx->duped = 0;
}
+out:
+ inode_unlock(inode);
return offset;
}
nfs_direct_req_release(dreq);
}
-static void nfs_direct_readpage_release(struct nfs_page *req)
-{
- dprintk("NFS: direct read done (%s/%llu %d@%lld)\n",
- req->wb_context->dentry->d_sb->s_id,
- (unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)),
- req->wb_bytes,
- (long long)req_offset(req));
- nfs_release_request(req);
-}
-
static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
{
unsigned long bytes = 0;
set_page_dirty(page);
bytes += req->wb_bytes;
nfs_list_remove_request(req);
- nfs_direct_readpage_release(req);
+ nfs_release_request(req);
}
out_put:
if (put_dreq(dreq))
int status = data->task.tk_status;
nfs_init_cinfo_from_dreq(&cinfo, dreq);
- if (status < 0) {
- dprintk("NFS: %5u commit failed with error %d.\n",
- data->task.tk_pid, status);
- dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
- } else if (nfs_direct_cmp_commit_data_verf(dreq, data)) {
- dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid);
+ if (status < 0 || nfs_direct_cmp_commit_data_verf(dreq, data))
dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
- }
- dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status);
while (!list_empty(&data->pages)) {
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
inode->i_ino, (long long)page_offset(page));
nfs_fscache_wait_on_page_write(nfsi, page);
- return nfs_wb_launder_page(inode, page);
+ return nfs_wb_page(inode, page);
}
static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
if (!IS_ERR(l_ctx)) {
status = nfs_iocounter_wait(l_ctx);
nfs_put_lock_context(l_ctx);
- if (status < 0)
+ /* NOTE: special case
+ * If we're signalled while cleaning up locks on process exit, we
+ * still need to complete the unlock.
+ */
+ if (status < 0 && !(fl->fl_flags & FL_CLOSE))
return status;
}
- /* NOTE: special case
- * If we're signalled while cleaning up locks on process exit, we
- * still need to complete the unlock.
- */
/*
* Use local locking if mounted with "-onolock" or with appropriate
* "-olocal_lock="
if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
is_local = 1;
- /* We're simulating flock() locks using posix locks on the server */
- if (fl->fl_type == F_UNLCK)
+ /*
+ * VFS doesn't require the open mode to match a flock() lock's type.
+ * NFS, however, may simulate flock() locking with posix locking which
+ * requires the open mode to match the lock type.
+ */
+ switch (fl->fl_type) {
+ case F_UNLCK:
return do_unlk(filp, cmd, fl, is_local);
+ case F_RDLCK:
+ if (!(filp->f_mode & FMODE_READ))
+ return -EBADF;
+ break;
+ case F_WRLCK:
+ if (!(filp->f_mode & FMODE_WRITE))
+ return -EBADF;
+ }
+
return do_setlk(filp, cmd, fl, is_local);
}
EXPORT_SYMBOL_GPL(nfs_flock);
fl = FILELAYOUT_LSEG(lseg);
status = filelayout_check_deviceid(lo, fl, gfp_flags);
- if (status)
+ if (status) {
+ pnfs_put_lseg(lseg);
lseg = ERR_PTR(status);
+ }
out:
- if (IS_ERR(lseg))
- pnfs_put_lseg(lseg);
return lseg;
}
filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
+ pnfs_generic_pg_check_layout(pgio);
if (!pgio->pg_lseg) {
pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
req->wb_context,
struct nfs_commit_info cinfo;
int status;
+ pnfs_generic_pg_check_layout(pgio);
if (!pgio->pg_lseg) {
pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
req->wb_context,
int ds_idx;
retry:
+ pnfs_generic_pg_check_layout(pgio);
/* Use full layout for now */
if (!pgio->pg_lseg)
ff_layout_pg_get_read(pgio, req, false);
int status;
retry:
+ pnfs_generic_pg_check_layout(pgio);
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
if (!ds)
- return PNFS_NOT_ATTEMPTED;
+ goto out_failed;
ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
hdr->inode);
if (IS_ERR(ds_clnt))
- return PNFS_NOT_ATTEMPTED;
+ goto out_failed;
ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
if (!ds_cred)
- return PNFS_NOT_ATTEMPTED;
+ goto out_failed;
vers = nfs4_ff_layout_ds_version(lseg, idx);
sync, RPC_TASK_SOFTCONN);
put_rpccred(ds_cred);
return PNFS_ATTEMPTED;
+
+out_failed:
+ if (ff_layout_avoid_mds_available_ds(lseg))
+ return PNFS_TRY_AGAIN;
+ return PNFS_NOT_ATTEMPTED;
}
static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
return 0;
}
+static int
+ff_layout_set_layoutdriver(struct nfs_server *server,
+ const struct nfs_fh *dummy)
+{
+#if IS_ENABLED(CONFIG_NFS_V4_2)
+ server->caps |= NFS_CAP_LAYOUTSTATS;
+#endif
+ return 0;
+}
+
static struct pnfs_layoutdriver_type flexfilelayout_type = {
.id = LAYOUT_FLEX_FILES,
.name = "LAYOUT_FLEX_FILES",
.owner = THIS_MODULE,
+ .set_layoutdriver = ff_layout_set_layoutdriver,
.alloc_layout_hdr = ff_layout_alloc_layout_hdr,
.free_layout_hdr = ff_layout_free_layout_hdr,
.alloc_lseg = ff_layout_alloc_lseg,
if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE)
ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE;
- if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) {
+ /*
+ * check for valid major/minor combination.
+ * currently we support dataserver which talk:
+ * v3, v4.0, v4.1, v4.2
+ */
+ if (!((ds_versions[i].version == 3 && ds_versions[i].minor_version == 0) ||
+ (ds_versions[i].version == 4 && ds_versions[i].minor_version < 3))) {
dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__,
i, ds_versions[i].version,
ds_versions[i].minor_version);
mirror->mirror_ds->ds_versions[0].minor_version);
/* connect success, check rsize/wsize limit */
- if (ds->ds_clp) {
+ if (!status) {
max_payload =
nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
NULL);
if (need_atime || nfs_need_revalidate_inode(inode)) {
struct nfs_server *server = NFS_SERVER(inode);
- nfs_readdirplus_parent_cache_miss(path->dentry);
+ if (!(server->flags & NFS_MOUNT_NOAC))
+ nfs_readdirplus_parent_cache_miss(path->dentry);
+ else
+ nfs_readdirplus_parent_cache_hit(path->dentry);
err = __nfs_revalidate_inode(server, inode);
} else
nfs_readdirplus_parent_cache_hit(path->dentry);
u32 ds_commit_idx);
int nfs_write_need_commit(struct nfs_pgio_header *);
void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
-int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf);
int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
int how, struct nfs_commit_info *cinfo);
void nfs_retry_commit(struct list_head *page_list,
{
switch (err) {
case -ERESTARTSYS:
+ case -EACCES:
+ case -EDQUOT:
+ case -EFBIG:
case -EIO:
case -ENOSPC:
case -EROFS:
+ case -ESTALE:
case -E2BIG:
return true;
default:
struct nfs_fh *fh = NULL;
struct nfs_fattr *fattr = NULL;
- dprintk("--> nfs_d_automount()\n");
-
- mnt = ERR_PTR(-ESTALE);
if (IS_ROOT(path->dentry))
- goto out_nofree;
+ return ERR_PTR(-ESTALE);
mnt = ERR_PTR(-ENOMEM);
fh = nfs_alloc_fhandle();
if (fh == NULL || fattr == NULL)
goto out;
- dprintk("%s: enter\n", __func__);
-
mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr);
if (IS_ERR(mnt))
goto out;
- dprintk("%s: done, success\n", __func__);
mntget(mnt); /* prevent immediate expiration */
mnt_set_expiry(mnt, &nfs_automount_list);
schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
out:
nfs_free_fattr(fattr);
nfs_free_fhandle(fh);
-out_nofree:
- if (IS_ERR(mnt))
- dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt));
- else
- dprintk("<-- %s() = %p\n", __func__, mnt);
return mnt;
}
.fattr = fattr,
.authflavor = authflavor,
};
- struct vfsmount *mnt = ERR_PTR(-ENOMEM);
+ struct vfsmount *mnt;
char *page = (char *) __get_free_page(GFP_USER);
char *devname;
- dprintk("--> nfs_do_submount()\n");
-
- dprintk("%s: submounting on %pd2\n", __func__,
- dentry);
if (page == NULL)
- goto out;
+ return ERR_PTR(-ENOMEM);
+
devname = nfs_devname(dentry, page, PAGE_SIZE);
- mnt = (struct vfsmount *)devname;
if (IS_ERR(devname))
- goto free_page;
- mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
-free_page:
- free_page((unsigned long)page);
-out:
- dprintk("%s: done\n", __func__);
+ mnt = (struct vfsmount *)devname;
+ else
+ mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
- dprintk("<-- nfs_do_submount() = %p\n", mnt);
+ free_page((unsigned long)page);
return mnt;
}
EXPORT_SYMBOL_GPL(nfs_do_submount);
msg->rpc_proc = &nfs3_procedures[NFS3PROC_COMMIT];
}
+static void nfs3_nlm_alloc_call(void *data)
+{
+ struct nfs_lock_context *l_ctx = data;
+ if (l_ctx && test_bit(NFS_CONTEXT_UNLOCK, &l_ctx->open_context->flags)) {
+ get_nfs_open_context(l_ctx->open_context);
+ nfs_get_lock_context(l_ctx->open_context);
+ }
+}
+
+static bool nfs3_nlm_unlock_prepare(struct rpc_task *task, void *data)
+{
+ struct nfs_lock_context *l_ctx = data;
+ if (l_ctx && test_bit(NFS_CONTEXT_UNLOCK, &l_ctx->open_context->flags))
+ return nfs_async_iocounter_wait(task, l_ctx);
+ return false;
+
+}
+
+static void nfs3_nlm_release_call(void *data)
+{
+ struct nfs_lock_context *l_ctx = data;
+ struct nfs_open_context *ctx;
+ if (l_ctx && test_bit(NFS_CONTEXT_UNLOCK, &l_ctx->open_context->flags)) {
+ ctx = l_ctx->open_context;
+ nfs_put_lock_context(l_ctx);
+ put_nfs_open_context(ctx);
+ }
+}
+
+const struct nlmclnt_operations nlmclnt_fl_close_lock_ops = {
+ .nlmclnt_alloc_call = nfs3_nlm_alloc_call,
+ .nlmclnt_unlock_prepare = nfs3_nlm_unlock_prepare,
+ .nlmclnt_release_call = nfs3_nlm_release_call,
+};
+
static int
nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
{
struct inode *inode = file_inode(filp);
+ struct nfs_lock_context *l_ctx = NULL;
+ struct nfs_open_context *ctx = nfs_file_open_context(filp);
+ int status;
- return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
+ if (fl->fl_flags & FL_CLOSE) {
+ l_ctx = nfs_get_lock_context(ctx);
+ if (IS_ERR(l_ctx))
+ l_ctx = NULL;
+ else
+ set_bit(NFS_CONTEXT_UNLOCK, &ctx->flags);
+ }
+
+ status = nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl, l_ctx);
+
+ if (l_ctx)
+ nfs_put_lock_context(l_ctx);
+
+ return status;
}
static int nfs3_have_delegation(struct inode *inode, fmode_t flags)
.dir_inode_ops = &nfs3_dir_inode_operations,
.file_inode_ops = &nfs3_file_inode_operations,
.file_ops = &nfs_file_operations,
+ .nlmclnt_ops = &nlmclnt_fl_close_lock_ops,
.getroot = nfs3_proc_get_root,
.submount = nfs_submount,
.try_mount = nfs_try_mount,
if (status)
return status;
+ res->commit_res.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS);
+ if (!res->commit_res.verf)
+ return -ENOMEM;
status = nfs4_call_sync(server->client, server, &msg,
&args->seq_args, &res->seq_res, 0);
if (status == -ENOTSUPP)
server->caps &= ~NFS_CAP_COPY;
if (status)
- return status;
+ goto out;
- if (res->write_res.verifier.committed != NFS_FILE_SYNC) {
- status = nfs_commit_file(dst, &res->write_res.verifier.verifier);
- if (status)
- return status;
+ if (!nfs_write_verifier_cmp(&res->write_res.verifier.verifier,
+ &res->commit_res.verf->verifier)) {
+ status = -EAGAIN;
+ goto out;
}
truncate_pagecache_range(dst_inode, pos_dst,
pos_dst + res->write_res.count);
- return res->write_res.count;
+ status = res->write_res.count;
+out:
+ kfree(res->commit_res.verf);
+ return status;
}
ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
if (err == -ENOTSUPP) {
err = -EOPNOTSUPP;
break;
+ } if (err == -EAGAIN) {
+ dst_exception.retry = 1;
+ continue;
}
err2 = nfs4_handle_exception(server, err, &src_exception);
pnfs_mark_layout_stateid_invalid(lo, &head);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
+ nfs_commit_inode(inode, 0);
} else
spin_unlock(&inode->i_lock);
break;
case -EOPNOTSUPP:
NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
}
-
- dprintk("%s server returns %d\n", __func__, task->tk_status);
}
static void
encode_putfh_maxsz + \
encode_savefh_maxsz + \
encode_putfh_maxsz + \
- encode_copy_maxsz)
+ encode_copy_maxsz + \
+ encode_commit_maxsz)
#define NFS4_dec_copy_sz (compound_decode_hdr_maxsz + \
decode_putfh_maxsz + \
decode_savefh_maxsz + \
decode_putfh_maxsz + \
- decode_copy_maxsz)
+ decode_copy_maxsz + \
+ decode_commit_maxsz)
#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \
encode_putfh_maxsz + \
encode_deallocate_maxsz + \
encode_nops(&hdr);
}
+static void encode_copy_commit(struct xdr_stream *xdr,
+ struct nfs42_copy_args *args,
+ struct compound_hdr *hdr)
+{
+ __be32 *p;
+
+ encode_op_hdr(xdr, OP_COMMIT, decode_commit_maxsz, hdr);
+ p = reserve_space(xdr, 12);
+ p = xdr_encode_hyper(p, args->dst_pos);
+ *p = cpu_to_be32(args->count);
+}
+
/*
* Encode COPY request
*/
encode_savefh(xdr, &hdr);
encode_putfh(xdr, args->dst_fh, &hdr);
encode_copy(xdr, args, &hdr);
+ encode_copy_commit(xdr, args, &hdr);
encode_nops(&hdr);
}
if (status)
goto out;
status = decode_copy(xdr, res);
+ if (status)
+ goto out;
+ status = decode_commit(xdr, &res->commit_res);
out:
return status;
}
struct nfs_client *old;
int error;
- if (clp->cl_cons_state == NFS_CS_READY) {
+ if (clp->cl_cons_state == NFS_CS_READY)
/* the client is initialised already */
- dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
return clp;
- }
/* Check NFS protocol revision and initialize RPC op vector */
clp->rpc_ops = &nfs_v4_clientops;
error:
nfs_mark_client_ready(clp, error);
nfs_put_client(clp);
- dprintk("<-- nfs4_init_client() = xerror %d\n", error);
return ERR_PTR(error);
}
return memcmp(v1->data, v2->data, sizeof(v1->data)) == 0;
}
+static int nfs4_match_client(struct nfs_client *pos, struct nfs_client *new,
+ struct nfs_client **prev, struct nfs_net *nn)
+{
+ int status;
+
+ if (pos->rpc_ops != new->rpc_ops)
+ return 1;
+
+ if (pos->cl_minorversion != new->cl_minorversion)
+ return 1;
+
+ /* If "pos" isn't marked ready, we can't trust the
+ * remaining fields in "pos", especially the client
+ * ID and serverowner fields. Wait for CREATE_SESSION
+ * to finish. */
+ if (pos->cl_cons_state > NFS_CS_READY) {
+ atomic_inc(&pos->cl_count);
+ spin_unlock(&nn->nfs_client_lock);
+
+ nfs_put_client(*prev);
+ *prev = pos;
+
+ status = nfs_wait_client_init_complete(pos);
+ spin_lock(&nn->nfs_client_lock);
+
+ if (status < 0)
+ return status;
+ }
+
+ if (pos->cl_cons_state != NFS_CS_READY)
+ return 1;
+
+ if (pos->cl_clientid != new->cl_clientid)
+ return 1;
+
+ /* NFSv4.1 always uses the uniform string, however someone
+ * might switch the uniquifier string on us.
+ */
+ if (!nfs4_match_client_owner_id(pos, new))
+ return 1;
+
+ return 0;
+}
+
/**
* nfs40_walk_client_list - Find server that recognizes a client ID
*
spin_lock(&nn->nfs_client_lock);
list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
- if (pos->rpc_ops != new->rpc_ops)
- continue;
-
- if (pos->cl_minorversion != new->cl_minorversion)
- continue;
-
- /* If "pos" isn't marked ready, we can't trust the
- * remaining fields in "pos" */
- if (pos->cl_cons_state > NFS_CS_READY) {
- atomic_inc(&pos->cl_count);
- spin_unlock(&nn->nfs_client_lock);
-
- nfs_put_client(prev);
- prev = pos;
-
- status = nfs_wait_client_init_complete(pos);
- if (status < 0)
- goto out;
- status = -NFS4ERR_STALE_CLIENTID;
- spin_lock(&nn->nfs_client_lock);
- }
- if (pos->cl_cons_state != NFS_CS_READY)
- continue;
-
- if (pos->cl_clientid != new->cl_clientid)
- continue;
-
- if (!nfs4_match_client_owner_id(pos, new))
+ status = nfs4_match_client(pos, new, &prev, nn);
+ if (status < 0)
+ goto out_unlock;
+ if (status != 0)
continue;
/*
* We just sent a new SETCLIENTID, which should have
prev = NULL;
*result = pos;
- dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
- __func__, pos, atomic_read(&pos->cl_count));
goto out;
case -ERESTARTSYS:
case -ETIMEDOUT:
*/
nfs4_schedule_path_down_recovery(pos);
default:
+ spin_lock(&nn->nfs_client_lock);
goto out;
}
spin_lock(&nn->nfs_client_lock);
}
+out_unlock:
spin_unlock(&nn->nfs_client_lock);
/* No match found. The server lost our clientid */
out:
nfs_put_client(prev);
- dprintk("NFS: <-- %s status = %d\n", __func__, status);
return status;
}
#ifdef CONFIG_NFS_V4_1
-/*
- * Returns true if the client IDs match
- */
-static bool nfs4_match_clientids(u64 a, u64 b)
-{
- if (a != b) {
- dprintk("NFS: --> %s client ID %llx does not match %llx\n",
- __func__, a, b);
- return false;
- }
- dprintk("NFS: --> %s client ID %llx matches %llx\n",
- __func__, a, b);
- return true;
-}
-
/*
* Returns true if the server major ids match
*/
struct nfs41_server_owner *o2)
{
if (o1->major_id_sz != o2->major_id_sz)
- goto out_major_mismatch;
- if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0)
- goto out_major_mismatch;
-
- dprintk("NFS: --> %s server owner major IDs match\n", __func__);
- return true;
-
-out_major_mismatch:
- dprintk("NFS: --> %s server owner major IDs do not match\n",
- __func__);
- return false;
-}
-
-/*
- * Returns true if server minor ids match
- */
-static bool
-nfs4_check_serverowner_minor_id(struct nfs41_server_owner *o1,
- struct nfs41_server_owner *o2)
-{
- /* Check eir_server_owner so_minor_id */
- if (o1->minor_id != o2->minor_id)
- goto out_minor_mismatch;
-
- dprintk("NFS: --> %s server owner minor IDs match\n", __func__);
- return true;
-
-out_minor_mismatch:
- dprintk("NFS: --> %s server owner minor IDs do not match\n", __func__);
- return false;
+ return false;
+ return memcmp(o1->major_id, o2->major_id, o1->major_id_sz) == 0;
}
/*
struct nfs41_server_scope *s2)
{
if (s1->server_scope_sz != s2->server_scope_sz)
- goto out_scope_mismatch;
- if (memcmp(s1->server_scope, s2->server_scope,
- s1->server_scope_sz) != 0)
- goto out_scope_mismatch;
-
- dprintk("NFS: --> %s server scopes match\n", __func__);
- return true;
-
-out_scope_mismatch:
- dprintk("NFS: --> %s server scopes do not match\n",
- __func__);
- return false;
+ return false;
+ return memcmp(s1->server_scope, s2->server_scope,
+ s1->server_scope_sz) == 0;
}
/**
struct rpc_xprt *xprt)
{
/* Check eir_clientid */
- if (!nfs4_match_clientids(clp->cl_clientid, res->clientid))
+ if (clp->cl_clientid != res->clientid)
goto out_err;
/* Check eir_server_owner so_major_id */
goto out_err;
/* Check eir_server_owner so_minor_id */
- if (!nfs4_check_serverowner_minor_id(clp->cl_serverowner,
- res->server_owner))
+ if (clp->cl_serverowner->minor_id != res->server_owner->minor_id)
goto out_err;
/* Check eir_server_scope */
if (pos == new)
goto found;
- if (pos->rpc_ops != new->rpc_ops)
- continue;
-
- if (pos->cl_minorversion != new->cl_minorversion)
- continue;
-
- /* If "pos" isn't marked ready, we can't trust the
- * remaining fields in "pos", especially the client
- * ID and serverowner fields. Wait for CREATE_SESSION
- * to finish. */
- if (pos->cl_cons_state > NFS_CS_READY) {
- atomic_inc(&pos->cl_count);
- spin_unlock(&nn->nfs_client_lock);
-
- nfs_put_client(prev);
- prev = pos;
-
- status = nfs_wait_client_init_complete(pos);
- spin_lock(&nn->nfs_client_lock);
- if (status < 0)
- break;
- status = -NFS4ERR_STALE_CLIENTID;
- }
- if (pos->cl_cons_state != NFS_CS_READY)
- continue;
-
- if (!nfs4_match_clientids(pos->cl_clientid, new->cl_clientid))
+ status = nfs4_match_client(pos, new, &prev, nn);
+ if (status < 0)
+ goto out;
+ if (status != 0)
continue;
/*
new->cl_serverowner))
continue;
- /* Unlike NFSv4.0, we know that NFSv4.1 always uses the
- * uniform string, however someone might switch the
- * uniquifier string on us.
- */
- if (!nfs4_match_client_owner_id(pos, new))
- continue;
found:
atomic_inc(&pos->cl_count);
*result = pos;
status = 0;
- dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
- __func__, pos, atomic_read(&pos->cl_count));
break;
}
+out:
spin_unlock(&nn->nfs_client_lock);
- dprintk("NFS: <-- %s status = %d\n", __func__, status);
nfs_put_client(prev);
return status;
}
.timeparms = timeparms,
};
struct nfs_client *clp;
- int error;
-
- dprintk("--> nfs4_set_client()\n");
if (server->flags & NFS_MOUNT_NORESVPORT)
set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
/* Allocate or find a client reference we can use */
clp = nfs_get_client(&cl_init);
- if (IS_ERR(clp)) {
- error = PTR_ERR(clp);
- goto error;
- }
+ if (IS_ERR(clp))
+ return PTR_ERR(clp);
- if (server->nfs_client == clp) {
- error = -ELOOP;
- goto error;
- }
+ if (server->nfs_client == clp)
+ return -ELOOP;
/*
* Query for the lease time on clientid setup or renewal
set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
server->nfs_client = clp;
- dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
return 0;
-error:
- dprintk("<-- nfs4_set_client() = xerror %d\n", error);
- return error;
}
/*
.net = mds_clp->cl_net,
.timeparms = &ds_timeout,
};
- struct nfs_client *clp;
char buf[INET6_ADDRSTRLEN + 1];
if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
* (section 13.1 RFC 5661).
*/
nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
- clp = nfs_get_client(&cl_init);
-
- dprintk("<-- %s %p\n", __func__, clp);
- return clp;
+ return nfs_get_client(&cl_init);
}
EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
struct rpc_timeout timeparms;
int error;
- dprintk("--> nfs4_init_server()\n");
-
nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
data->timeo, data->retrans);
data->minorversion,
data->net);
if (error < 0)
- goto error;
+ return error;
if (data->rsize)
server->rsize = nfs_block_size(data->rsize, NULL);
server->acregmax = data->acregmax * HZ;
server->acdirmin = data->acdirmin * HZ;
server->acdirmax = data->acdirmax * HZ;
+ server->port = data->nfs_server.port;
- server->port = data->nfs_server.port;
-
- error = nfs_init_server_rpcclient(server, &timeparms,
- data->selected_flavor);
-
-error:
- /* Done */
- dprintk("<-- nfs4_init_server() = %d\n", error);
- return error;
+ return nfs_init_server_rpcclient(server, &timeparms,
+ data->selected_flavor);
}
/*
bool auth_probe;
int error;
- dprintk("--> nfs4_create_server()\n");
-
server = nfs_alloc_server();
if (!server)
return ERR_PTR(-ENOMEM);
if (error < 0)
goto error;
- dprintk("<-- nfs4_create_server() = %p\n", server);
return server;
error:
nfs_free_server(server);
- dprintk("<-- nfs4_create_server() = error %d\n", error);
return ERR_PTR(error);
}
bool auth_probe;
int error;
- dprintk("--> nfs4_create_referral_server()\n");
-
server = nfs_alloc_server();
if (!server)
return ERR_PTR(-ENOMEM);
if (error < 0)
goto error;
- dprintk("<-- nfs_create_referral_server() = %p\n", server);
return server;
error:
nfs_free_server(server);
- dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
return ERR_PTR(error);
}
struct sockaddr *localaddr = (struct sockaddr *)&address;
int error;
- dprintk("--> %s: move FSID %llx:%llx to \"%s\")\n", __func__,
- (unsigned long long)server->fsid.major,
- (unsigned long long)server->fsid.minor,
- hostname);
-
error = rpc_switch_client_transport(clnt, &xargs, clnt->cl_timeout);
- if (error != 0) {
- dprintk("<-- %s(): rpc_switch_client_transport returned %d\n",
- __func__, error);
- goto out;
- }
+ if (error != 0)
+ return error;
error = rpc_localaddr(clnt, localaddr, sizeof(address));
- if (error != 0) {
- dprintk("<-- %s(): rpc_localaddr returned %d\n",
- __func__, error);
- goto out;
- }
+ if (error != 0)
+ return error;
- error = -EAFNOSUPPORT;
- if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0) {
- dprintk("<-- %s(): rpc_ntop returned %d\n",
- __func__, error);
- goto out;
- }
+ if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0)
+ return -EAFNOSUPPORT;
nfs_server_remove_lists(server);
error = nfs4_set_client(server, hostname, sap, salen, buf,
nfs_put_client(clp);
if (error != 0) {
nfs_server_insert_lists(server);
- dprintk("<-- %s(): nfs4_set_client returned %d\n",
- __func__, error);
- goto out;
+ return error;
}
if (server->nfs_client->cl_hostname == NULL)
server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL);
nfs_server_insert_lists(server);
- error = nfs_probe_destination(server);
- if (error < 0)
- goto out;
-
- dprintk("<-- %s() succeeded\n", __func__);
-
-out:
- return error;
+ return nfs_probe_destination(server);
}
struct nfs_fsinfo fsinfo;
int ret = -ENOMEM;
- dprintk("--> nfs4_get_rootfh()\n");
-
fsinfo.fattr = nfs_alloc_fattr();
if (fsinfo.fattr == NULL)
goto out;
memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
out:
nfs_free_fattr(fsinfo.fattr);
- dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
return ret;
}
out:
free_page((unsigned long) page);
free_page((unsigned long) page2);
- dprintk("%s: done\n", __func__);
return mnt;
}
int err;
/* BUG_ON(IS_ROOT(dentry)); */
- dprintk("%s: enter\n", __func__);
-
page = alloc_page(GFP_KERNEL);
if (page == NULL)
- goto out;
+ return mnt;
fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
if (fs_locations == NULL)
out_free:
__free_page(page);
kfree(fs_locations);
-out:
- dprintk("%s: done\n", __func__);
return mnt;
}
session = slot->table->session;
if (slot->interrupted) {
- slot->interrupted = 0;
+ if (res->sr_status != -NFS4ERR_DELAY)
+ slot->interrupted = 0;
interrupted = true;
}
if (status != 0)
return status;
}
- if (!(o_res->f_attr->valid & NFS_ATTR_FATTR))
+ if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) {
+ nfs4_sequence_free_slot(&o_res->seq_res);
nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label);
+ }
return 0;
}
.rpc_resp = &res,
};
int status;
+ int i;
bitmask[0] = FATTR4_WORD0_SUPPORTED_ATTRS |
FATTR4_WORD0_FH_EXPIRE_TYPE |
server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
server->cache_consistency_bitmask[2] = 0;
+
+ /* Avoid a regression due to buggy server */
+ for (i = 0; i < ARRAY_SIZE(res.exclcreat_bitmask); i++)
+ res.exclcreat_bitmask[i] &= res.attr_bitmask[i];
memcpy(server->exclcreat_bitmask, res.exclcreat_bitmask,
sizeof(server->exclcreat_bitmask));
+
server->acl_bitmask = res.acl_bitmask;
server->fh_expire_type = res.fh_expire_type;
}
return 0;
if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
hdr->args.lock_context,
- hdr->rw_ops->rw_mode) == -EIO)
+ hdr->rw_mode) == -EIO)
return -EIO;
if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags)))
return -EIO;
if (!atomic_inc_not_zero(&clp->cl_count))
return -EIO;
data = kmalloc(sizeof(*data), GFP_NOFS);
- if (data == NULL)
+ if (data == NULL) {
+ nfs_put_client(clp);
return -ENOMEM;
+ }
data->client = clp;
data->timestamp = jiffies;
return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT,
struct nfs_locku_res res;
struct nfs4_lock_state *lsp;
struct nfs_open_context *ctx;
+ struct nfs_lock_context *l_ctx;
struct file_lock fl;
struct nfs_server *server;
unsigned long timestamp;
atomic_inc(&lsp->ls_count);
/* Ensure we don't close file until we're done freeing locks! */
p->ctx = get_nfs_open_context(ctx);
+ p->l_ctx = nfs_get_lock_context(ctx);
memcpy(&p->fl, fl, sizeof(p->fl));
p->server = NFS_SERVER(inode);
return p;
struct nfs4_unlockdata *calldata = data;
nfs_free_seqid(calldata->arg.seqid);
nfs4_put_lock_state(calldata->lsp);
+ nfs_put_lock_context(calldata->l_ctx);
put_nfs_open_context(calldata->ctx);
kfree(calldata);
}
{
struct nfs4_unlockdata *calldata = data;
+ if (test_bit(NFS_CONTEXT_UNLOCK, &calldata->l_ctx->open_context->flags) &&
+ nfs_async_iocounter_wait(task, calldata->l_ctx))
+ return;
+
if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
goto out_wait;
nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid);
* canceled lock is passed in, and it won't be an unlock.
*/
fl->fl_type = F_UNLCK;
+ if (fl->fl_flags & FL_CLOSE)
+ set_bit(NFS_CONTEXT_UNLOCK, &ctx->flags);
data = nfs4_alloc_unlockdata(fl, ctx, lsp, seqid);
if (data == NULL) {
ctx = nfs_file_open_context(filp);
state = ctx->state;
- if (request->fl_start < 0 || request->fl_end < 0)
- return -EINVAL;
-
if (IS_GETLK(cmd)) {
if (state != NULL)
return nfs4_proc_getlk(state, F_GETLK, request);
!test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
return -ENOLCK;
- /*
- * Don't rely on the VFS having checked the file open mode,
- * since it won't do this for flock() locks.
- */
- switch (request->fl_type) {
- case F_RDLCK:
- if (!(filp->f_mode & FMODE_READ))
- return -EBADF;
- break;
- case F_WRLCK:
- if (!(filp->f_mode & FMODE_WRITE))
- return -EBADF;
- }
-
status = nfs4_set_lock_state(state, request);
if (status != 0)
return status;
};
struct rpc_task *task;
- dprintk("--> %s\n", __func__);
-
nfs4_copy_sessionid(&args.sessionid, &clp->cl_session->sess_id);
if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
args.dir = NFS4_CDFC4_FORE;
if (memcmp(res.sessionid.data,
clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) {
dprintk("NFS: %s: Session ID mismatch\n", __func__);
- status = -EIO;
- goto out;
+ return -EIO;
}
if ((res.dir & args.dir) != res.dir || res.dir == 0) {
dprintk("NFS: %s: Unexpected direction from server\n",
__func__);
- status = -EIO;
- goto out;
+ return -EIO;
}
if (res.use_conn_in_rdma_mode != args.use_conn_in_rdma_mode) {
dprintk("NFS: %s: Server returned RDMA mode = true\n",
__func__);
- status = -EIO;
- goto out;
+ return -EIO;
}
}
-out:
- dprintk("<-- %s status= %d\n", __func__, status);
+
return status;
}
};
struct nfs41_exchange_id_data *calldata;
struct rpc_task *task;
- int status = -EIO;
+ int status;
if (!atomic_inc_not_zero(&clp->cl_count))
- goto out;
+ return -EIO;
- status = -ENOMEM;
calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
- if (!calldata)
- goto out;
+ if (!calldata) {
+ nfs_put_client(clp);
+ return -ENOMEM;
+ }
if (!xprt)
nfs4_init_boot_verifier(clp, &verifier);
if (status)
goto out_calldata;
- dprintk("NFS call exchange_id auth=%s, '%s'\n",
- clp->cl_rpcclient->cl_auth->au_ops->au_name,
- clp->cl_owner_id);
-
calldata->res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
GFP_NOFS);
status = -ENOMEM;
rpc_put_task(task);
out:
- if (clp->cl_implid != NULL)
- dprintk("NFS reply exchange_id: Server Implementation ID: "
- "domain: %s, name: %s, date: %llu,%u\n",
- clp->cl_implid->domain, clp->cl_implid->name,
- clp->cl_implid->date.seconds,
- clp->cl_implid->date.nseconds);
- dprintk("NFS reply exchange_id: %d\n", status);
return status;
out_impl_id:
nfs4_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0);
nfs4_set_sequence_privileged(&args.la_seq_args);
- dprintk("--> %s\n", __func__);
task = rpc_run_task(&task_setup);
if (IS_ERR(task))
- status = PTR_ERR(task);
- else {
- status = task->tk_status;
- rpc_put_task(task);
- }
- dprintk("<-- %s return %d\n", __func__, status);
+ return PTR_ERR(task);
+ status = task->tk_status;
+ rpc_put_task(task);
return status;
}
/* fall through */
case -NFS4ERR_RETRY_UNCACHED_REP:
return -EAGAIN;
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_DEADSESSION:
+ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ nfs4_schedule_session_recovery(clp->cl_session,
+ task->tk_status);
+ break;
default:
nfs4_schedule_lease_recovery(clp);
}
if (status == 0)
status = task->tk_status;
rpc_put_task(task);
- return 0;
out:
dprintk("<-- %s status=%d\n", __func__, status);
return status;
*/
pnfs_mark_layout_stateid_invalid(lo, &head);
spin_unlock(&inode->i_lock);
+ nfs_commit_inode(inode, 0);
pnfs_free_lseg_list(&head);
status = -EAGAIN;
goto out;
nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot);
}
-static void nfs4_reclaim_complete(struct nfs_client *clp,
+static int nfs4_reclaim_complete(struct nfs_client *clp,
const struct nfs4_state_recovery_ops *ops,
struct rpc_cred *cred)
{
/* Notify the server we're done reclaiming our state */
if (ops->reclaim_complete)
- (void)ops->reclaim_complete(clp, cred);
+ return ops->reclaim_complete(clp, cred);
+ return 0;
}
static void nfs4_clear_reclaim_server(struct nfs_server *server)
{
const struct nfs4_state_recovery_ops *ops;
struct rpc_cred *cred;
+ int err;
if (!nfs4_state_clear_reclaim_reboot(clp))
return;
ops = clp->cl_mvops->reboot_recovery_ops;
cred = nfs4_get_clid_cred(clp);
- nfs4_reclaim_complete(clp, ops, cred);
+ err = nfs4_reclaim_complete(clp, ops, cred);
put_rpccred(cred);
+ if (err == -NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
+ set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
}
static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp)
static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
const struct nfs4_label *label,
+ const umode_t *umask,
const struct nfs_server *server,
- bool excl_check, const umode_t *umask)
+ const uint32_t attrmask[])
{
char owner_name[IDMAP_NAMESZ];
char owner_group[IDMAP_NAMESZ];
/*
* We reserve enough space to write the entire attribute buffer at once.
*/
- if (iap->ia_valid & ATTR_SIZE) {
+ if ((iap->ia_valid & ATTR_SIZE) && (attrmask[0] & FATTR4_WORD0_SIZE)) {
bmval[0] |= FATTR4_WORD0_SIZE;
len += 8;
}
- if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK))
- umask = NULL;
if (iap->ia_valid & ATTR_MODE) {
- if (umask) {
+ if (umask && (attrmask[2] & FATTR4_WORD2_MODE_UMASK)) {
bmval[2] |= FATTR4_WORD2_MODE_UMASK;
len += 8;
- } else {
+ } else if (attrmask[1] & FATTR4_WORD1_MODE) {
bmval[1] |= FATTR4_WORD1_MODE;
len += 4;
}
}
- if (iap->ia_valid & ATTR_UID) {
+ if ((iap->ia_valid & ATTR_UID) && (attrmask[1] & FATTR4_WORD1_OWNER)) {
owner_namelen = nfs_map_uid_to_name(server, iap->ia_uid, owner_name, IDMAP_NAMESZ);
if (owner_namelen < 0) {
dprintk("nfs: couldn't resolve uid %d to string\n",
bmval[1] |= FATTR4_WORD1_OWNER;
len += 4 + (XDR_QUADLEN(owner_namelen) << 2);
}
- if (iap->ia_valid & ATTR_GID) {
+ if ((iap->ia_valid & ATTR_GID) &&
+ (attrmask[1] & FATTR4_WORD1_OWNER_GROUP)) {
owner_grouplen = nfs_map_gid_to_group(server, iap->ia_gid, owner_group, IDMAP_NAMESZ);
if (owner_grouplen < 0) {
dprintk("nfs: couldn't resolve gid %d to string\n",
bmval[1] |= FATTR4_WORD1_OWNER_GROUP;
len += 4 + (XDR_QUADLEN(owner_grouplen) << 2);
}
- if (iap->ia_valid & ATTR_ATIME_SET) {
- bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
- len += 16;
- } else if (iap->ia_valid & ATTR_ATIME) {
- bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
- len += 4;
- }
- if (iap->ia_valid & ATTR_MTIME_SET) {
- bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
- len += 16;
- } else if (iap->ia_valid & ATTR_MTIME) {
- bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
- len += 4;
+ if (attrmask[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
+ if (iap->ia_valid & ATTR_ATIME_SET) {
+ bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
+ len += 16;
+ } else if (iap->ia_valid & ATTR_ATIME) {
+ bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
+ len += 4;
+ }
}
-
- if (excl_check) {
- const u32 *excl_bmval = server->exclcreat_bitmask;
- bmval[0] &= excl_bmval[0];
- bmval[1] &= excl_bmval[1];
- bmval[2] &= excl_bmval[2];
-
- if (!(excl_bmval[2] & FATTR4_WORD2_SECURITY_LABEL))
- label = NULL;
+ if (attrmask[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
+ if (iap->ia_valid & ATTR_MTIME_SET) {
+ bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
+ len += 16;
+ } else if (iap->ia_valid & ATTR_MTIME) {
+ bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
+ len += 4;
+ }
}
- if (label) {
+ if (label && (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL)) {
len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2);
bmval[2] |= FATTR4_WORD2_SECURITY_LABEL;
}
}
encode_string(xdr, create->name->len, create->name->name);
- encode_attrs(xdr, create->attrs, create->label, create->server, false,
- &create->umask);
+ encode_attrs(xdr, create->attrs, create->label, &create->umask,
+ create->server, create->server->attr_bitmask);
}
static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct compound_hdr *hdr)
switch(arg->createmode) {
case NFS4_CREATE_UNCHECKED:
*p = cpu_to_be32(NFS4_CREATE_UNCHECKED);
- encode_attrs(xdr, arg->u.attrs, arg->label, arg->server, false,
- &arg->umask);
+ encode_attrs(xdr, arg->u.attrs, arg->label, &arg->umask,
+ arg->server, arg->server->attr_bitmask);
break;
case NFS4_CREATE_GUARDED:
*p = cpu_to_be32(NFS4_CREATE_GUARDED);
- encode_attrs(xdr, arg->u.attrs, arg->label, arg->server, false,
- &arg->umask);
+ encode_attrs(xdr, arg->u.attrs, arg->label, &arg->umask,
+ arg->server, arg->server->attr_bitmask);
break;
case NFS4_CREATE_EXCLUSIVE:
*p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE);
case NFS4_CREATE_EXCLUSIVE4_1:
*p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1);
encode_nfs4_verifier(xdr, &arg->u.verifier);
- encode_attrs(xdr, arg->u.attrs, arg->label, arg->server, true,
- &arg->umask);
+ encode_attrs(xdr, arg->u.attrs, arg->label, &arg->umask,
+ arg->server, arg->server->exclcreat_bitmask);
}
}
{
encode_op_hdr(xdr, OP_SETATTR, decode_setattr_maxsz, hdr);
encode_nfs4_stateid(xdr, &arg->stateid);
- encode_attrs(xdr, arg->iap, arg->label, server, false, NULL);
+ encode_attrs(xdr, arg->iap, arg->label, NULL, server,
+ server->attr_bitmask);
}
static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclientid *setclientid, struct compound_hdr *hdr)
*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
- if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) {
- NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
- NFS_I(inode)->layout, xdr, args);
- } else {
- encode_uint32(xdr, args->layoutupdate_len);
- if (args->layoutupdate_pages) {
- xdr_write_pages(xdr, args->layoutupdate_pages, 0,
- args->layoutupdate_len);
- }
- }
+ encode_uint32(xdr, args->layoutupdate_len);
+ if (args->layoutupdate_pages)
+ xdr_write_pages(xdr, args->layoutupdate_pages, 0,
+ args->layoutupdate_len);
return 0;
}
const struct nfs4_layoutreturn_args *args,
struct compound_hdr *hdr)
{
- const struct pnfs_layoutdriver_type *lr_ops = NFS_SERVER(args->inode)->pnfs_curr_ld;
__be32 *p;
encode_op_hdr(xdr, OP_LAYOUTRETURN, decode_layoutreturn_maxsz, hdr);
spin_unlock(&args->inode->i_lock);
if (args->ld_private->ops && args->ld_private->ops->encode)
args->ld_private->ops->encode(xdr, args, args->ld_private);
- else if (lr_ops->encode_layoutreturn)
- lr_ops->encode_layoutreturn(xdr, args);
else
encode_uint32(xdr, 0);
}
unsigned int i;
p = xdr_inline_decode(xdr, 4);
+ if (!p)
+ return -EIO;
bitmap_words = be32_to_cpup(p++);
if (bitmap_words > NFS4_OP_MAP_NUM_WORDS)
return -EIO;
+++ /dev/null
-#
-# Makefile for the pNFS Objects Layout Driver kernel module
-#
-objlayoutdriver-y := objio_osd.o pnfs_osd_xdr_cli.o objlayout.o
-obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayoutdriver.o
+++ /dev/null
-/*
- * pNFS Objects layout implementation over open-osd initiator library
- *
- * Copyright (C) 2009 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/module.h>
-#include <scsi/osd_ore.h>
-
-#include "objlayout.h"
-#include "../internal.h"
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-
-struct objio_dev_ent {
- struct nfs4_deviceid_node id_node;
- struct ore_dev od;
-};
-
-static void
-objio_free_deviceid_node(struct nfs4_deviceid_node *d)
-{
- struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
-
- dprintk("%s: free od=%p\n", __func__, de->od.od);
- osduld_put_device(de->od.od);
- kfree_rcu(d, rcu);
-}
-
-struct objio_segment {
- struct pnfs_layout_segment lseg;
-
- struct ore_layout layout;
- struct ore_components oc;
-};
-
-static inline struct objio_segment *
-OBJIO_LSEG(struct pnfs_layout_segment *lseg)
-{
- return container_of(lseg, struct objio_segment, lseg);
-}
-
-struct objio_state {
- /* Generic layer */
- struct objlayout_io_res oir;
-
- bool sync;
- /*FIXME: Support for extra_bytes at ore_get_rw_state() */
- struct ore_io_state *ios;
-};
-
-/* Send and wait for a get_device_info of devices in the layout,
- then look them up with the osd_initiator library */
-struct nfs4_deviceid_node *
-objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
- gfp_t gfp_flags)
-{
- struct pnfs_osd_deviceaddr *deviceaddr;
- struct objio_dev_ent *ode = NULL;
- struct osd_dev *od;
- struct osd_dev_info odi;
- bool retry_flag = true;
- __be32 *p;
- int err;
-
- deviceaddr = kzalloc(sizeof(*deviceaddr), gfp_flags);
- if (!deviceaddr)
- return NULL;
-
- p = page_address(pdev->pages[0]);
- pnfs_osd_xdr_decode_deviceaddr(deviceaddr, p);
-
- odi.systemid_len = deviceaddr->oda_systemid.len;
- if (odi.systemid_len > sizeof(odi.systemid)) {
- dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n",
- __func__, sizeof(odi.systemid));
- err = -EINVAL;
- goto out;
- } else if (odi.systemid_len)
- memcpy(odi.systemid, deviceaddr->oda_systemid.data,
- odi.systemid_len);
- odi.osdname_len = deviceaddr->oda_osdname.len;
- odi.osdname = (u8 *)deviceaddr->oda_osdname.data;
-
- if (!odi.osdname_len && !odi.systemid_len) {
- dprintk("%s: !odi.osdname_len && !odi.systemid_len\n",
- __func__);
- err = -ENODEV;
- goto out;
- }
-
-retry_lookup:
- od = osduld_info_lookup(&odi);
- if (IS_ERR(od)) {
- err = PTR_ERR(od);
- dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
- if (err == -ENODEV && retry_flag) {
- err = objlayout_autologin(deviceaddr);
- if (likely(!err)) {
- retry_flag = false;
- goto retry_lookup;
- }
- }
- goto out;
- }
-
- dprintk("Adding new dev_id(%llx:%llx)\n",
- _DEVID_LO(&pdev->dev_id), _DEVID_HI(&pdev->dev_id));
-
- ode = kzalloc(sizeof(*ode), gfp_flags);
- if (!ode) {
- dprintk("%s: -ENOMEM od=%p\n", __func__, od);
- goto out;
- }
-
- nfs4_init_deviceid_node(&ode->id_node, server, &pdev->dev_id);
- kfree(deviceaddr);
-
- ode->od.od = od;
- return &ode->id_node;
-
-out:
- kfree(deviceaddr);
- return NULL;
-}
-
-static void copy_single_comp(struct ore_components *oc, unsigned c,
- struct pnfs_osd_object_cred *src_comp)
-{
- struct ore_comp *ocomp = &oc->comps[c];
-
- WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */
- WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred));
-
- ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id;
- ocomp->obj.id = src_comp->oc_object_id.oid_object_id;
-
- memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
-}
-
-static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
- struct objio_segment **pseg)
-{
-/* This is the in memory structure of the objio_segment
- *
- * struct __alloc_objio_segment {
- * struct objio_segment olseg;
- * struct ore_dev *ods[numdevs];
- * struct ore_comp comps[numdevs];
- * } *aolseg;
- * NOTE: The code as above compiles and runs perfectly. It is elegant,
- * type safe and compact. At some Past time Linus has decided he does not
- * like variable length arrays, For the sake of this principal we uglify
- * the code as below.
- */
- struct objio_segment *lseg;
- size_t lseg_size = sizeof(*lseg) +
- numdevs * sizeof(lseg->oc.ods[0]) +
- numdevs * sizeof(*lseg->oc.comps);
-
- lseg = kzalloc(lseg_size, gfp_flags);
- if (unlikely(!lseg)) {
- dprintk("%s: Failed allocation numdevs=%d size=%zd\n", __func__,
- numdevs, lseg_size);
- return -ENOMEM;
- }
-
- lseg->oc.numdevs = numdevs;
- lseg->oc.single_comp = EC_MULTPLE_COMPS;
- lseg->oc.ods = (void *)(lseg + 1);
- lseg->oc.comps = (void *)(lseg->oc.ods + numdevs);
-
- *pseg = lseg;
- return 0;
-}
-
-int objio_alloc_lseg(struct pnfs_layout_segment **outp,
- struct pnfs_layout_hdr *pnfslay,
- struct pnfs_layout_range *range,
- struct xdr_stream *xdr,
- gfp_t gfp_flags)
-{
- struct nfs_server *server = NFS_SERVER(pnfslay->plh_inode);
- struct objio_segment *objio_seg;
- struct pnfs_osd_xdr_decode_layout_iter iter;
- struct pnfs_osd_layout layout;
- struct pnfs_osd_object_cred src_comp;
- unsigned cur_comp;
- int err;
-
- err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
- if (unlikely(err))
- return err;
-
- err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg);
- if (unlikely(err))
- return err;
-
- objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit;
- objio_seg->layout.group_width = layout.olo_map.odm_group_width;
- objio_seg->layout.group_depth = layout.olo_map.odm_group_depth;
- objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
- objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm;
-
- err = ore_verify_layout(layout.olo_map.odm_num_comps,
- &objio_seg->layout);
- if (unlikely(err))
- goto err;
-
- objio_seg->oc.first_dev = layout.olo_comps_index;
- cur_comp = 0;
- while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
- struct nfs4_deviceid_node *d;
- struct objio_dev_ent *ode;
-
- copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
-
- d = nfs4_find_get_deviceid(server,
- &src_comp.oc_object_id.oid_device_id,
- pnfslay->plh_lc_cred, gfp_flags);
- if (!d) {
- err = -ENXIO;
- goto err;
- }
-
- ode = container_of(d, struct objio_dev_ent, id_node);
- objio_seg->oc.ods[cur_comp++] = &ode->od;
- }
- /* pnfs_osd_xdr_decode_layout_comp returns false on error */
- if (unlikely(err))
- goto err;
-
- *outp = &objio_seg->lseg;
- return 0;
-
-err:
- kfree(objio_seg);
- dprintk("%s: Error: return %d\n", __func__, err);
- *outp = NULL;
- return err;
-}
-
-void objio_free_lseg(struct pnfs_layout_segment *lseg)
-{
- int i;
- struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
-
- for (i = 0; i < objio_seg->oc.numdevs; i++) {
- struct ore_dev *od = objio_seg->oc.ods[i];
- struct objio_dev_ent *ode;
-
- if (!od)
- break;
- ode = container_of(od, typeof(*ode), od);
- nfs4_put_deviceid_node(&ode->id_node);
- }
- kfree(objio_seg);
-}
-
-static int
-objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, bool is_reading,
- struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase,
- loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags,
- struct objio_state **outp)
-{
- struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
- struct ore_io_state *ios;
- int ret;
- struct __alloc_objio_state {
- struct objio_state objios;
- struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs];
- } *aos;
-
- aos = kzalloc(sizeof(*aos), gfp_flags);
- if (unlikely(!aos))
- return -ENOMEM;
-
- objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs,
- aos->ioerrs, rpcdata, pnfs_layout_type);
-
- ret = ore_get_rw_state(&objio_seg->layout, &objio_seg->oc, is_reading,
- offset, count, &ios);
- if (unlikely(ret)) {
- kfree(aos);
- return ret;
- }
-
- ios->pages = pages;
- ios->pgbase = pgbase;
- ios->private = aos;
- BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT);
-
- aos->objios.sync = 0;
- aos->objios.ios = ios;
- *outp = &aos->objios;
- return 0;
-}
-
-void objio_free_result(struct objlayout_io_res *oir)
-{
- struct objio_state *objios = container_of(oir, struct objio_state, oir);
-
- ore_put_io_state(objios->ios);
- kfree(objios);
-}
-
-static enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
-{
- switch (oep) {
- case OSD_ERR_PRI_NO_ERROR:
- return (enum pnfs_osd_errno)0;
-
- case OSD_ERR_PRI_CLEAR_PAGES:
- BUG_ON(1);
- return 0;
-
- case OSD_ERR_PRI_RESOURCE:
- return PNFS_OSD_ERR_RESOURCE;
- case OSD_ERR_PRI_BAD_CRED:
- return PNFS_OSD_ERR_BAD_CRED;
- case OSD_ERR_PRI_NO_ACCESS:
- return PNFS_OSD_ERR_NO_ACCESS;
- case OSD_ERR_PRI_UNREACHABLE:
- return PNFS_OSD_ERR_UNREACHABLE;
- case OSD_ERR_PRI_NOT_FOUND:
- return PNFS_OSD_ERR_NOT_FOUND;
- case OSD_ERR_PRI_NO_SPACE:
- return PNFS_OSD_ERR_NO_SPACE;
- default:
- WARN_ON(1);
- /* fallthrough */
- case OSD_ERR_PRI_EIO:
- return PNFS_OSD_ERR_EIO;
- }
-}
-
-static void __on_dev_error(struct ore_io_state *ios,
- struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep,
- u64 dev_offset, u64 dev_len)
-{
- struct objio_state *objios = ios->private;
- struct pnfs_osd_objid pooid;
- struct objio_dev_ent *ode = container_of(od, typeof(*ode), od);
- /* FIXME: what to do with more-then-one-group layouts. We need to
- * translate from ore_io_state index to oc->comps index
- */
- unsigned comp = dev_index;
-
- pooid.oid_device_id = ode->id_node.deviceid;
- pooid.oid_partition_id = ios->oc->comps[comp].obj.partition;
- pooid.oid_object_id = ios->oc->comps[comp].obj.id;
-
- objlayout_io_set_result(&objios->oir, comp,
- &pooid, osd_pri_2_pnfs_err(oep),
- dev_offset, dev_len, !ios->reading);
-}
-
-/*
- * read
- */
-static void _read_done(struct ore_io_state *ios, void *private)
-{
- struct objio_state *objios = private;
- ssize_t status;
- int ret = ore_check_io(ios, &__on_dev_error);
-
- /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
-
- if (likely(!ret))
- status = ios->length;
- else
- status = ret;
-
- objlayout_read_done(&objios->oir, status, objios->sync);
-}
-
-int objio_read_pagelist(struct nfs_pgio_header *hdr)
-{
- struct objio_state *objios;
- int ret;
-
- ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
- hdr->lseg, hdr->args.pages, hdr->args.pgbase,
- hdr->args.offset, hdr->args.count, hdr,
- GFP_KERNEL, &objios);
- if (unlikely(ret))
- return ret;
-
- objios->ios->done = _read_done;
- dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
- hdr->args.offset, hdr->args.count);
- ret = ore_read(objios->ios);
- if (unlikely(ret))
- objio_free_result(&objios->oir);
- return ret;
-}
-
-/*
- * write
- */
-static void _write_done(struct ore_io_state *ios, void *private)
-{
- struct objio_state *objios = private;
- ssize_t status;
- int ret = ore_check_io(ios, &__on_dev_error);
-
- /* FIXME: _io_free(ios) can we dealocate the libosd resources; */
-
- if (likely(!ret)) {
- /* FIXME: should be based on the OSD's persistence model
- * See OSD2r05 Section 4.13 Data persistence model */
- objios->oir.committed = NFS_FILE_SYNC;
- status = ios->length;
- } else {
- status = ret;
- }
-
- objlayout_write_done(&objios->oir, status, objios->sync);
-}
-
-static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
-{
- struct objio_state *objios = priv;
- struct nfs_pgio_header *hdr = objios->oir.rpcdata;
- struct address_space *mapping = hdr->inode->i_mapping;
- pgoff_t index = offset / PAGE_SIZE;
- struct page *page;
- loff_t i_size = i_size_read(hdr->inode);
-
- if (offset >= i_size) {
- *uptodate = true;
- dprintk("%s: g_zero_page index=0x%lx\n", __func__, index);
- return ZERO_PAGE(0);
- }
-
- page = find_get_page(mapping, index);
- if (!page) {
- page = find_or_create_page(mapping, index, GFP_NOFS);
- if (unlikely(!page)) {
- dprintk("%s: grab_cache_page Failed index=0x%lx\n",
- __func__, index);
- return NULL;
- }
- unlock_page(page);
- }
- *uptodate = PageUptodate(page);
- dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
- return page;
-}
-
-static void __r4w_put_page(void *priv, struct page *page)
-{
- dprintk("%s: index=0x%lx\n", __func__,
- (page == ZERO_PAGE(0)) ? -1UL : page->index);
- if (ZERO_PAGE(0) != page)
- put_page(page);
- return;
-}
-
-static const struct _ore_r4w_op _r4w_op = {
- .get_page = &__r4w_get_page,
- .put_page = &__r4w_put_page,
-};
-
-int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
-{
- struct objio_state *objios;
- int ret;
-
- ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
- hdr->lseg, hdr->args.pages, hdr->args.pgbase,
- hdr->args.offset, hdr->args.count, hdr, GFP_NOFS,
- &objios);
- if (unlikely(ret))
- return ret;
-
- objios->sync = 0 != (how & FLUSH_SYNC);
- objios->ios->r4w = &_r4w_op;
-
- if (!objios->sync)
- objios->ios->done = _write_done;
-
- dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
- hdr->args.offset, hdr->args.count);
- ret = ore_write(objios->ios);
- if (unlikely(ret)) {
- objio_free_result(&objios->oir);
- return ret;
- }
-
- if (objios->sync)
- _write_done(objios->ios, objios);
-
- return 0;
-}
-
-/*
- * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
- * of bytes (maximum @req->wb_bytes) that can be coalesced.
- */
-static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
- struct nfs_page *prev, struct nfs_page *req)
-{
- struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio);
- unsigned int size;
-
- size = pnfs_generic_pg_test(pgio, prev, req);
-
- if (!size || mirror->pg_count + req->wb_bytes >
- (unsigned long)pgio->pg_layout_private)
- return 0;
-
- return min(size, req->wb_bytes);
-}
-
-static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
-{
- pnfs_generic_pg_init_read(pgio, req);
- if (unlikely(pgio->pg_lseg == NULL))
- return; /* Not pNFS */
-
- pgio->pg_layout_private = (void *)
- OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
-}
-
-static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
- unsigned long *stripe_end)
-{
- u32 stripe_off;
- unsigned stripe_size;
-
- if (layout->raid_algorithm == PNFS_OSD_RAID_0)
- return true;
-
- stripe_size = layout->stripe_unit *
- (layout->group_width - layout->parity);
-
- div_u64_rem(offset, stripe_size, &stripe_off);
- if (!stripe_off)
- return true;
-
- *stripe_end = stripe_size - stripe_off;
- return false;
-}
-
-static void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
-{
- unsigned long stripe_end = 0;
- u64 wb_size;
-
- if (pgio->pg_dreq == NULL)
- wb_size = i_size_read(pgio->pg_inode) - req_offset(req);
- else
- wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
-
- pnfs_generic_pg_init_write(pgio, req, wb_size);
- if (unlikely(pgio->pg_lseg == NULL))
- return; /* Not pNFS */
-
- if (req->wb_offset ||
- !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE,
- &OBJIO_LSEG(pgio->pg_lseg)->layout,
- &stripe_end)) {
- pgio->pg_layout_private = (void *)stripe_end;
- } else {
- pgio->pg_layout_private = (void *)
- OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
- }
-}
-
-static const struct nfs_pageio_ops objio_pg_read_ops = {
- .pg_init = objio_init_read,
- .pg_test = objio_pg_test,
- .pg_doio = pnfs_generic_pg_readpages,
- .pg_cleanup = pnfs_generic_pg_cleanup,
-};
-
-static const struct nfs_pageio_ops objio_pg_write_ops = {
- .pg_init = objio_init_write,
- .pg_test = objio_pg_test,
- .pg_doio = pnfs_generic_pg_writepages,
- .pg_cleanup = pnfs_generic_pg_cleanup,
-};
-
-static struct pnfs_layoutdriver_type objlayout_type = {
- .id = LAYOUT_OSD2_OBJECTS,
- .name = "LAYOUT_OSD2_OBJECTS",
- .flags = PNFS_LAYOUTRET_ON_SETATTR |
- PNFS_LAYOUTRET_ON_ERROR,
-
- .max_deviceinfo_size = PAGE_SIZE,
- .owner = THIS_MODULE,
- .alloc_layout_hdr = objlayout_alloc_layout_hdr,
- .free_layout_hdr = objlayout_free_layout_hdr,
-
- .alloc_lseg = objlayout_alloc_lseg,
- .free_lseg = objlayout_free_lseg,
-
- .read_pagelist = objlayout_read_pagelist,
- .write_pagelist = objlayout_write_pagelist,
- .pg_read_ops = &objio_pg_read_ops,
- .pg_write_ops = &objio_pg_write_ops,
-
- .sync = pnfs_generic_sync,
-
- .free_deviceid_node = objio_free_deviceid_node,
-
- .encode_layoutcommit = objlayout_encode_layoutcommit,
- .encode_layoutreturn = objlayout_encode_layoutreturn,
-};
-
-MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");
-MODULE_AUTHOR("Benny Halevy <bhalevy@panasas.com>");
-MODULE_LICENSE("GPL");
-
-static int __init
-objlayout_init(void)
-{
- int ret = pnfs_register_layoutdriver(&objlayout_type);
-
- if (ret)
- printk(KERN_INFO
- "NFS: %s: Registering OSD pNFS Layout Driver failed: error=%d\n",
- __func__, ret);
- else
- printk(KERN_INFO "NFS: %s: Registered OSD pNFS Layout Driver\n",
- __func__);
- return ret;
-}
-
-static void __exit
-objlayout_exit(void)
-{
- pnfs_unregister_layoutdriver(&objlayout_type);
- printk(KERN_INFO "NFS: %s: Unregistered OSD pNFS Layout Driver\n",
- __func__);
-}
-
-MODULE_ALIAS("nfs-layouttype4-2");
-
-module_init(objlayout_init);
-module_exit(objlayout_exit);
+++ /dev/null
-/*
- * pNFS Objects layout driver high level definitions
- *
- * Copyright (C) 2007 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/kmod.h>
-#include <linux/moduleparam.h>
-#include <linux/ratelimit.h>
-#include <scsi/osd_initiator.h>
-#include "objlayout.h"
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-/*
- * Create a objlayout layout structure for the given inode and return it.
- */
-struct pnfs_layout_hdr *
-objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
-{
- struct objlayout *objlay;
-
- objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
- if (!objlay)
- return NULL;
- spin_lock_init(&objlay->lock);
- INIT_LIST_HEAD(&objlay->err_list);
- dprintk("%s: Return %p\n", __func__, objlay);
- return &objlay->pnfs_layout;
-}
-
-/*
- * Free an objlayout layout structure
- */
-void
-objlayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
-{
- struct objlayout *objlay = OBJLAYOUT(lo);
-
- dprintk("%s: objlay %p\n", __func__, objlay);
-
- WARN_ON(!list_empty(&objlay->err_list));
- kfree(objlay);
-}
-
-/*
- * Unmarshall layout and store it in pnfslay.
- */
-struct pnfs_layout_segment *
-objlayout_alloc_lseg(struct pnfs_layout_hdr *pnfslay,
- struct nfs4_layoutget_res *lgr,
- gfp_t gfp_flags)
-{
- int status = -ENOMEM;
- struct xdr_stream stream;
- struct xdr_buf buf = {
- .pages = lgr->layoutp->pages,
- .page_len = lgr->layoutp->len,
- .buflen = lgr->layoutp->len,
- .len = lgr->layoutp->len,
- };
- struct page *scratch;
- struct pnfs_layout_segment *lseg;
-
- dprintk("%s: Begin pnfslay %p\n", __func__, pnfslay);
-
- scratch = alloc_page(gfp_flags);
- if (!scratch)
- goto err_nofree;
-
- xdr_init_decode(&stream, &buf, NULL);
- xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
-
- status = objio_alloc_lseg(&lseg, pnfslay, &lgr->range, &stream, gfp_flags);
- if (unlikely(status)) {
- dprintk("%s: objio_alloc_lseg Return err %d\n", __func__,
- status);
- goto err;
- }
-
- __free_page(scratch);
-
- dprintk("%s: Return %p\n", __func__, lseg);
- return lseg;
-
-err:
- __free_page(scratch);
-err_nofree:
- dprintk("%s: Err Return=>%d\n", __func__, status);
- return ERR_PTR(status);
-}
-
-/*
- * Free a layout segement
- */
-void
-objlayout_free_lseg(struct pnfs_layout_segment *lseg)
-{
- dprintk("%s: freeing layout segment %p\n", __func__, lseg);
-
- if (unlikely(!lseg))
- return;
-
- objio_free_lseg(lseg);
-}
-
-/*
- * I/O Operations
- */
-static inline u64
-end_offset(u64 start, u64 len)
-{
- u64 end;
-
- end = start + len;
- return end >= start ? end : NFS4_MAX_UINT64;
-}
-
-static void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
- struct page ***p_pages, unsigned *p_pgbase,
- u64 offset, unsigned long count)
-{
- u64 lseg_end_offset;
-
- BUG_ON(offset < lseg->pls_range.offset);
- lseg_end_offset = end_offset(lseg->pls_range.offset,
- lseg->pls_range.length);
- BUG_ON(offset >= lseg_end_offset);
- WARN_ON(offset + count > lseg_end_offset);
-
- if (*p_pgbase > PAGE_SIZE) {
- dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase);
- *p_pages += *p_pgbase >> PAGE_SHIFT;
- *p_pgbase &= ~PAGE_MASK;
- }
-}
-
-/*
- * I/O done common code
- */
-static void
-objlayout_iodone(struct objlayout_io_res *oir)
-{
- if (likely(oir->status >= 0)) {
- objio_free_result(oir);
- } else {
- struct objlayout *objlay = oir->objlay;
-
- spin_lock(&objlay->lock);
- objlay->delta_space_valid = OBJ_DSU_INVALID;
- list_add(&objlay->err_list, &oir->err_list);
- spin_unlock(&objlay->lock);
- }
-}
-
-/*
- * objlayout_io_set_result - Set an osd_error code on a specific osd comp.
- *
- * The @index component IO failed (error returned from target). Register
- * the error for later reporting at layout-return.
- */
-void
-objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
- struct pnfs_osd_objid *pooid, int osd_error,
- u64 offset, u64 length, bool is_write)
-{
- struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index];
-
- BUG_ON(index >= oir->num_comps);
- if (osd_error) {
- ioerr->oer_component = *pooid;
- ioerr->oer_comp_offset = offset;
- ioerr->oer_comp_length = length;
- ioerr->oer_iswrite = is_write;
- ioerr->oer_errno = osd_error;
-
- dprintk("%s: err[%d]: errno=%d is_write=%d dev(%llx:%llx) "
- "par=0x%llx obj=0x%llx offset=0x%llx length=0x%llx\n",
- __func__, index, ioerr->oer_errno,
- ioerr->oer_iswrite,
- _DEVID_LO(&ioerr->oer_component.oid_device_id),
- _DEVID_HI(&ioerr->oer_component.oid_device_id),
- ioerr->oer_component.oid_partition_id,
- ioerr->oer_component.oid_object_id,
- ioerr->oer_comp_offset,
- ioerr->oer_comp_length);
- } else {
- /* User need not call if no error is reported */
- ioerr->oer_errno = 0;
- }
-}
-
-/* Function scheduled on rpc workqueue to call ->nfs_readlist_complete().
- * This is because the osd completion is called with ints-off from
- * the block layer
- */
-static void _rpc_read_complete(struct work_struct *work)
-{
- struct rpc_task *task;
- struct nfs_pgio_header *hdr;
-
- dprintk("%s enter\n", __func__);
- task = container_of(work, struct rpc_task, u.tk_work);
- hdr = container_of(task, struct nfs_pgio_header, task);
-
- pnfs_ld_read_done(hdr);
-}
-
-void
-objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
-{
- struct nfs_pgio_header *hdr = oir->rpcdata;
-
- oir->status = hdr->task.tk_status = status;
- if (status >= 0)
- hdr->res.count = status;
- else
- hdr->pnfs_error = status;
- objlayout_iodone(oir);
- /* must not use oir after this point */
-
- dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__,
- status, hdr->res.eof, sync);
-
- if (sync)
- pnfs_ld_read_done(hdr);
- else {
- INIT_WORK(&hdr->task.u.tk_work, _rpc_read_complete);
- schedule_work(&hdr->task.u.tk_work);
- }
-}
-
-/*
- * Perform sync or async reads.
- */
-enum pnfs_try_status
-objlayout_read_pagelist(struct nfs_pgio_header *hdr)
-{
- struct inode *inode = hdr->inode;
- loff_t offset = hdr->args.offset;
- size_t count = hdr->args.count;
- int err;
- loff_t eof;
-
- eof = i_size_read(inode);
- if (unlikely(offset + count > eof)) {
- if (offset >= eof) {
- err = 0;
- hdr->res.count = 0;
- hdr->res.eof = 1;
- /*FIXME: do we need to call pnfs_ld_read_done() */
- goto out;
- }
- count = eof - offset;
- }
-
- hdr->res.eof = (offset + count) >= eof;
- _fix_verify_io_params(hdr->lseg, &hdr->args.pages,
- &hdr->args.pgbase,
- hdr->args.offset, hdr->args.count);
-
- dprintk("%s: inode(%lx) offset 0x%llx count 0x%zx eof=%d\n",
- __func__, inode->i_ino, offset, count, hdr->res.eof);
-
- err = objio_read_pagelist(hdr);
- out:
- if (unlikely(err)) {
- hdr->pnfs_error = err;
- dprintk("%s: Returned Error %d\n", __func__, err);
- return PNFS_NOT_ATTEMPTED;
- }
- return PNFS_ATTEMPTED;
-}
-
-/* Function scheduled on rpc workqueue to call ->nfs_writelist_complete().
- * This is because the osd completion is called with ints-off from
- * the block layer
- */
-static void _rpc_write_complete(struct work_struct *work)
-{
- struct rpc_task *task;
- struct nfs_pgio_header *hdr;
-
- dprintk("%s enter\n", __func__);
- task = container_of(work, struct rpc_task, u.tk_work);
- hdr = container_of(task, struct nfs_pgio_header, task);
-
- pnfs_ld_write_done(hdr);
-}
-
-void
-objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
-{
- struct nfs_pgio_header *hdr = oir->rpcdata;
-
- oir->status = hdr->task.tk_status = status;
- if (status >= 0) {
- hdr->res.count = status;
- hdr->verf.committed = oir->committed;
- } else {
- hdr->pnfs_error = status;
- }
- objlayout_iodone(oir);
- /* must not use oir after this point */
-
- dprintk("%s: Return status %zd committed %d sync=%d\n", __func__,
- status, hdr->verf.committed, sync);
-
- if (sync)
- pnfs_ld_write_done(hdr);
- else {
- INIT_WORK(&hdr->task.u.tk_work, _rpc_write_complete);
- schedule_work(&hdr->task.u.tk_work);
- }
-}
-
-/*
- * Perform sync or async writes.
- */
-enum pnfs_try_status
-objlayout_write_pagelist(struct nfs_pgio_header *hdr, int how)
-{
- int err;
-
- _fix_verify_io_params(hdr->lseg, &hdr->args.pages,
- &hdr->args.pgbase,
- hdr->args.offset, hdr->args.count);
-
- err = objio_write_pagelist(hdr, how);
- if (unlikely(err)) {
- hdr->pnfs_error = err;
- dprintk("%s: Returned Error %d\n", __func__, err);
- return PNFS_NOT_ATTEMPTED;
- }
- return PNFS_ATTEMPTED;
-}
-
-void
-objlayout_encode_layoutcommit(struct pnfs_layout_hdr *pnfslay,
- struct xdr_stream *xdr,
- const struct nfs4_layoutcommit_args *args)
-{
- struct objlayout *objlay = OBJLAYOUT(pnfslay);
- struct pnfs_osd_layoutupdate lou;
- __be32 *start;
-
- dprintk("%s: Begin\n", __func__);
-
- spin_lock(&objlay->lock);
- lou.dsu_valid = (objlay->delta_space_valid == OBJ_DSU_VALID);
- lou.dsu_delta = objlay->delta_space_used;
- objlay->delta_space_used = 0;
- objlay->delta_space_valid = OBJ_DSU_INIT;
- lou.olu_ioerr_flag = !list_empty(&objlay->err_list);
- spin_unlock(&objlay->lock);
-
- start = xdr_reserve_space(xdr, 4);
-
- BUG_ON(pnfs_osd_xdr_encode_layoutupdate(xdr, &lou));
-
- *start = cpu_to_be32((xdr->p - start - 1) * 4);
-
- dprintk("%s: Return delta_space_used %lld err %d\n", __func__,
- lou.dsu_delta, lou.olu_ioerr_flag);
-}
-
-static int
-err_prio(u32 oer_errno)
-{
- switch (oer_errno) {
- case 0:
- return 0;
-
- case PNFS_OSD_ERR_RESOURCE:
- return OSD_ERR_PRI_RESOURCE;
- case PNFS_OSD_ERR_BAD_CRED:
- return OSD_ERR_PRI_BAD_CRED;
- case PNFS_OSD_ERR_NO_ACCESS:
- return OSD_ERR_PRI_NO_ACCESS;
- case PNFS_OSD_ERR_UNREACHABLE:
- return OSD_ERR_PRI_UNREACHABLE;
- case PNFS_OSD_ERR_NOT_FOUND:
- return OSD_ERR_PRI_NOT_FOUND;
- case PNFS_OSD_ERR_NO_SPACE:
- return OSD_ERR_PRI_NO_SPACE;
- default:
- WARN_ON(1);
- /* fallthrough */
- case PNFS_OSD_ERR_EIO:
- return OSD_ERR_PRI_EIO;
- }
-}
-
-static void
-merge_ioerr(struct pnfs_osd_ioerr *dest_err,
- const struct pnfs_osd_ioerr *src_err)
-{
- u64 dest_end, src_end;
-
- if (!dest_err->oer_errno) {
- *dest_err = *src_err;
- /* accumulated device must be blank */
- memset(&dest_err->oer_component.oid_device_id, 0,
- sizeof(dest_err->oer_component.oid_device_id));
-
- return;
- }
-
- if (dest_err->oer_component.oid_partition_id !=
- src_err->oer_component.oid_partition_id)
- dest_err->oer_component.oid_partition_id = 0;
-
- if (dest_err->oer_component.oid_object_id !=
- src_err->oer_component.oid_object_id)
- dest_err->oer_component.oid_object_id = 0;
-
- if (dest_err->oer_comp_offset > src_err->oer_comp_offset)
- dest_err->oer_comp_offset = src_err->oer_comp_offset;
-
- dest_end = end_offset(dest_err->oer_comp_offset,
- dest_err->oer_comp_length);
- src_end = end_offset(src_err->oer_comp_offset,
- src_err->oer_comp_length);
- if (dest_end < src_end)
- dest_end = src_end;
-
- dest_err->oer_comp_length = dest_end - dest_err->oer_comp_offset;
-
- if ((src_err->oer_iswrite == dest_err->oer_iswrite) &&
- (err_prio(src_err->oer_errno) > err_prio(dest_err->oer_errno))) {
- dest_err->oer_errno = src_err->oer_errno;
- } else if (src_err->oer_iswrite) {
- dest_err->oer_iswrite = true;
- dest_err->oer_errno = src_err->oer_errno;
- }
-}
-
-static void
-encode_accumulated_error(struct objlayout *objlay, __be32 *p)
-{
- struct objlayout_io_res *oir, *tmp;
- struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
-
- list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
- unsigned i;
-
- for (i = 0; i < oir->num_comps; i++) {
- struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
-
- if (!ioerr->oer_errno)
- continue;
-
- printk(KERN_ERR "NFS: %s: err[%d]: errno=%d "
- "is_write=%d dev(%llx:%llx) par=0x%llx "
- "obj=0x%llx offset=0x%llx length=0x%llx\n",
- __func__, i, ioerr->oer_errno,
- ioerr->oer_iswrite,
- _DEVID_LO(&ioerr->oer_component.oid_device_id),
- _DEVID_HI(&ioerr->oer_component.oid_device_id),
- ioerr->oer_component.oid_partition_id,
- ioerr->oer_component.oid_object_id,
- ioerr->oer_comp_offset,
- ioerr->oer_comp_length);
-
- merge_ioerr(&accumulated_err, ioerr);
- }
- list_del(&oir->err_list);
- objio_free_result(oir);
- }
-
- pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
-}
-
-void
-objlayout_encode_layoutreturn(struct xdr_stream *xdr,
- const struct nfs4_layoutreturn_args *args)
-{
- struct pnfs_layout_hdr *pnfslay = args->layout;
- struct objlayout *objlay = OBJLAYOUT(pnfslay);
- struct objlayout_io_res *oir, *tmp;
- __be32 *start;
-
- dprintk("%s: Begin\n", __func__);
- start = xdr_reserve_space(xdr, 4);
- BUG_ON(!start);
-
- spin_lock(&objlay->lock);
-
- list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
- __be32 *last_xdr = NULL, *p;
- unsigned i;
- int res = 0;
-
- for (i = 0; i < oir->num_comps; i++) {
- struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
-
- if (!ioerr->oer_errno)
- continue;
-
- dprintk("%s: err[%d]: errno=%d is_write=%d "
- "dev(%llx:%llx) par=0x%llx obj=0x%llx "
- "offset=0x%llx length=0x%llx\n",
- __func__, i, ioerr->oer_errno,
- ioerr->oer_iswrite,
- _DEVID_LO(&ioerr->oer_component.oid_device_id),
- _DEVID_HI(&ioerr->oer_component.oid_device_id),
- ioerr->oer_component.oid_partition_id,
- ioerr->oer_component.oid_object_id,
- ioerr->oer_comp_offset,
- ioerr->oer_comp_length);
-
- p = pnfs_osd_xdr_ioerr_reserve_space(xdr);
- if (unlikely(!p)) {
- res = -E2BIG;
- break; /* accumulated_error */
- }
-
- last_xdr = p;
- pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]);
- }
-
- /* TODO: use xdr_write_pages */
- if (unlikely(res)) {
- /* no space for even one error descriptor */
- BUG_ON(!last_xdr);
-
- /* we've encountered a situation with lots and lots of
- * errors and no space to encode them all. Use the last
- * available slot to report the union of all the
- * remaining errors.
- */
- encode_accumulated_error(objlay, last_xdr);
- goto loop_done;
- }
- list_del(&oir->err_list);
- objio_free_result(oir);
- }
-loop_done:
- spin_unlock(&objlay->lock);
-
- *start = cpu_to_be32((xdr->p - start - 1) * 4);
- dprintk("%s: Return\n", __func__);
-}
-
-enum {
- OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
- OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,
- OSD_LOGIN_UPCALL_PATHLEN = 256
-};
-
-static char osd_login_prog[OSD_LOGIN_UPCALL_PATHLEN] = "/sbin/osd_login";
-
-module_param_string(osd_login_prog, osd_login_prog, sizeof(osd_login_prog),
- 0600);
-MODULE_PARM_DESC(osd_login_prog, "Path to the osd_login upcall program");
-
-struct __auto_login {
- char uri[OBJLAYOUT_MAX_URI_LEN];
- char osdname[OBJLAYOUT_MAX_OSDNAME_LEN];
- char systemid_hex[OBJLAYOUT_MAX_SYSID_HEX_LEN];
-};
-
-static int __objlayout_upcall(struct __auto_login *login)
-{
- static char *envp[] = { "HOME=/",
- "TERM=linux",
- "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
- NULL
- };
- char *argv[8];
- int ret;
-
- if (unlikely(!osd_login_prog[0])) {
- dprintk("%s: osd_login_prog is disabled\n", __func__);
- return -EACCES;
- }
-
- dprintk("%s uri: %s\n", __func__, login->uri);
- dprintk("%s osdname %s\n", __func__, login->osdname);
- dprintk("%s systemid_hex %s\n", __func__, login->systemid_hex);
-
- argv[0] = (char *)osd_login_prog;
- argv[1] = "-u";
- argv[2] = login->uri;
- argv[3] = "-o";
- argv[4] = login->osdname;
- argv[5] = "-s";
- argv[6] = login->systemid_hex;
- argv[7] = NULL;
-
- ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
- /*
- * Disable the upcall mechanism if we're getting an ENOENT or
- * EACCES error. The admin can re-enable it on the fly by using
- * sysfs to set the objlayoutdriver.osd_login_prog module parameter once
- * the problem has been fixed.
- */
- if (ret == -ENOENT || ret == -EACCES) {
- printk(KERN_ERR "PNFS-OBJ: %s was not found please set "
- "objlayoutdriver.osd_login_prog kernel parameter!\n",
- osd_login_prog);
- osd_login_prog[0] = '\0';
- }
- dprintk("%s %s return value: %d\n", __func__, osd_login_prog, ret);
-
- return ret;
-}
-
-/* Assume dest is all zeros */
-static void __copy_nfsS_and_zero_terminate(struct nfs4_string s,
- char *dest, int max_len,
- const char *var_name)
-{
- if (!s.len)
- return;
-
- if (s.len >= max_len) {
- pr_warn_ratelimited(
- "objlayout_autologin: %s: s.len(%d) >= max_len(%d)",
- var_name, s.len, max_len);
- s.len = max_len - 1; /* space for null terminator */
- }
-
- memcpy(dest, s.data, s.len);
-}
-
-/* Assume sysid is all zeros */
-static void _sysid_2_hex(struct nfs4_string s,
- char sysid[OBJLAYOUT_MAX_SYSID_HEX_LEN])
-{
- int i;
- char *cur;
-
- if (!s.len)
- return;
-
- if (s.len != OSD_SYSTEMID_LEN) {
- pr_warn_ratelimited(
- "objlayout_autologin: systemid_len(%d) != OSD_SYSTEMID_LEN",
- s.len);
- if (s.len > OSD_SYSTEMID_LEN)
- s.len = OSD_SYSTEMID_LEN;
- }
-
- cur = sysid;
- for (i = 0; i < s.len; i++)
- cur = hex_byte_pack(cur, s.data[i]);
-}
-
-int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr)
-{
- int rc;
- struct __auto_login login;
-
- if (!deviceaddr->oda_targetaddr.ota_netaddr.r_addr.len)
- return -ENODEV;
-
- memset(&login, 0, sizeof(login));
- __copy_nfsS_and_zero_terminate(
- deviceaddr->oda_targetaddr.ota_netaddr.r_addr,
- login.uri, sizeof(login.uri), "URI");
-
- __copy_nfsS_and_zero_terminate(
- deviceaddr->oda_osdname,
- login.osdname, sizeof(login.osdname), "OSDNAME");
-
- _sysid_2_hex(deviceaddr->oda_systemid, login.systemid_hex);
-
- rc = __objlayout_upcall(&login);
- if (rc > 0) /* script returns positive values */
- rc = -ENODEV;
-
- return rc;
-}
+++ /dev/null
-/*
- * Data types and function declerations for interfacing with the
- * pNFS standard object layout driver.
- *
- * Copyright (C) 2007 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _OBJLAYOUT_H
-#define _OBJLAYOUT_H
-
-#include <linux/nfs_fs.h>
-#include <linux/pnfs_osd_xdr.h>
-#include "../pnfs.h"
-
-/*
- * per-inode layout
- */
-struct objlayout {
- struct pnfs_layout_hdr pnfs_layout;
-
- /* for layout_commit */
- enum osd_delta_space_valid_enum {
- OBJ_DSU_INIT = 0,
- OBJ_DSU_VALID,
- OBJ_DSU_INVALID,
- } delta_space_valid;
- s64 delta_space_used; /* consumed by write ops */
-
- /* for layout_return */
- spinlock_t lock;
- struct list_head err_list;
-};
-
-static inline struct objlayout *
-OBJLAYOUT(struct pnfs_layout_hdr *lo)
-{
- return container_of(lo, struct objlayout, pnfs_layout);
-}
-
-/*
- * per-I/O operation state
- * embedded in objects provider io_state data structure
- */
-struct objlayout_io_res {
- struct objlayout *objlay;
-
- void *rpcdata;
- int status; /* res */
- int committed; /* res */
-
- /* Error reporting (layout_return) */
- struct list_head err_list;
- unsigned num_comps;
- /* Pointer to array of error descriptors of size num_comps.
- * It should contain as many entries as devices in the osd_layout
- * that participate in the I/O. It is up to the io_engine to allocate
- * needed space and set num_comps.
- */
- struct pnfs_osd_ioerr *ioerrs;
-};
-
-static inline
-void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps,
- struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
- struct pnfs_layout_hdr *pnfs_layout_type)
-{
- oir->objlay = OBJLAYOUT(pnfs_layout_type);
- oir->rpcdata = rpcdata;
- INIT_LIST_HEAD(&oir->err_list);
- oir->num_comps = num_comps;
- oir->ioerrs = ioerrs;
-}
-
-/*
- * Raid engine I/O API
- */
-extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
- struct pnfs_layout_hdr *pnfslay,
- struct pnfs_layout_range *range,
- struct xdr_stream *xdr,
- gfp_t gfp_flags);
-extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
-
-/* objio_free_result will free these @oir structs received from
- * objlayout_{read,write}_done
- */
-extern void objio_free_result(struct objlayout_io_res *oir);
-
-extern int objio_read_pagelist(struct nfs_pgio_header *rdata);
-extern int objio_write_pagelist(struct nfs_pgio_header *wdata, int how);
-
-/*
- * callback API
- */
-extern void objlayout_io_set_result(struct objlayout_io_res *oir,
- unsigned index, struct pnfs_osd_objid *pooid,
- int osd_error, u64 offset, u64 length, bool is_write);
-
-static inline void
-objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used)
-{
- /* If one of the I/Os errored out and the delta_space_used was
- * invalid we render the complete report as invalid. Protocol mandate
- * the DSU be accurate or not reported.
- */
- spin_lock(&objlay->lock);
- if (objlay->delta_space_valid != OBJ_DSU_INVALID) {
- objlay->delta_space_valid = OBJ_DSU_VALID;
- objlay->delta_space_used += space_used;
- }
- spin_unlock(&objlay->lock);
-}
-
-extern void objlayout_read_done(struct objlayout_io_res *oir,
- ssize_t status, bool sync);
-extern void objlayout_write_done(struct objlayout_io_res *oir,
- ssize_t status, bool sync);
-
-/*
- * exported generic objects function vectors
- */
-
-extern struct pnfs_layout_hdr *objlayout_alloc_layout_hdr(struct inode *, gfp_t gfp_flags);
-extern void objlayout_free_layout_hdr(struct pnfs_layout_hdr *);
-
-extern struct pnfs_layout_segment *objlayout_alloc_lseg(
- struct pnfs_layout_hdr *,
- struct nfs4_layoutget_res *,
- gfp_t gfp_flags);
-extern void objlayout_free_lseg(struct pnfs_layout_segment *);
-
-extern enum pnfs_try_status objlayout_read_pagelist(
- struct nfs_pgio_header *);
-
-extern enum pnfs_try_status objlayout_write_pagelist(
- struct nfs_pgio_header *,
- int how);
-
-extern void objlayout_encode_layoutcommit(
- struct pnfs_layout_hdr *,
- struct xdr_stream *,
- const struct nfs4_layoutcommit_args *);
-
-extern void objlayout_encode_layoutreturn(
- struct xdr_stream *,
- const struct nfs4_layoutreturn_args *);
-
-extern int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr);
-
-#endif /* _OBJLAYOUT_H */
+++ /dev/null
-/*
- * Object-Based pNFS Layout XDR layer
- *
- * Copyright (C) 2007 Panasas Inc. [year of first publication]
- * All rights reserved.
- *
- * Benny Halevy <bhalevy@panasas.com>
- * Boaz Harrosh <ooo@electrozaur.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * See the file COPYING included with this distribution for more details.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- * 3. Neither the name of the Panasas company nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/pnfs_osd_xdr.h>
-
-#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-
-/*
- * The following implementation is based on RFC5664
- */
-
-/*
- * struct pnfs_osd_objid {
- * struct nfs4_deviceid oid_device_id;
- * u64 oid_partition_id;
- * u64 oid_object_id;
- * }; // xdr size 32 bytes
- */
-static __be32 *
-_osd_xdr_decode_objid(__be32 *p, struct pnfs_osd_objid *objid)
-{
- p = xdr_decode_opaque_fixed(p, objid->oid_device_id.data,
- sizeof(objid->oid_device_id.data));
-
- p = xdr_decode_hyper(p, &objid->oid_partition_id);
- p = xdr_decode_hyper(p, &objid->oid_object_id);
- return p;
-}
-/*
- * struct pnfs_osd_opaque_cred {
- * u32 cred_len;
- * void *cred;
- * }; // xdr size [variable]
- * The return pointers are from the xdr buffer
- */
-static int
-_osd_xdr_decode_opaque_cred(struct pnfs_osd_opaque_cred *opaque_cred,
- struct xdr_stream *xdr)
-{
- __be32 *p = xdr_inline_decode(xdr, 1);
-
- if (!p)
- return -EINVAL;
-
- opaque_cred->cred_len = be32_to_cpu(*p++);
-
- p = xdr_inline_decode(xdr, opaque_cred->cred_len);
- if (!p)
- return -EINVAL;
-
- opaque_cred->cred = p;
- return 0;
-}
-
-/*
- * struct pnfs_osd_object_cred {
- * struct pnfs_osd_objid oc_object_id;
- * u32 oc_osd_version;
- * u32 oc_cap_key_sec;
- * struct pnfs_osd_opaque_cred oc_cap_key
- * struct pnfs_osd_opaque_cred oc_cap;
- * }; // xdr size 32 + 4 + 4 + [variable] + [variable]
- */
-static int
-_osd_xdr_decode_object_cred(struct pnfs_osd_object_cred *comp,
- struct xdr_stream *xdr)
-{
- __be32 *p = xdr_inline_decode(xdr, 32 + 4 + 4);
- int ret;
-
- if (!p)
- return -EIO;
-
- p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
- comp->oc_osd_version = be32_to_cpup(p++);
- comp->oc_cap_key_sec = be32_to_cpup(p);
-
- ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap_key, xdr);
- if (unlikely(ret))
- return ret;
-
- ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap, xdr);
- return ret;
-}
-
-/*
- * struct pnfs_osd_data_map {
- * u32 odm_num_comps;
- * u64 odm_stripe_unit;
- * u32 odm_group_width;
- * u32 odm_group_depth;
- * u32 odm_mirror_cnt;
- * u32 odm_raid_algorithm;
- * }; // xdr size 4 + 8 + 4 + 4 + 4 + 4
- */
-static inline int
-_osd_data_map_xdr_sz(void)
-{
- return 4 + 8 + 4 + 4 + 4 + 4;
-}
-
-static __be32 *
-_osd_xdr_decode_data_map(__be32 *p, struct pnfs_osd_data_map *data_map)
-{
- data_map->odm_num_comps = be32_to_cpup(p++);
- p = xdr_decode_hyper(p, &data_map->odm_stripe_unit);
- data_map->odm_group_width = be32_to_cpup(p++);
- data_map->odm_group_depth = be32_to_cpup(p++);
- data_map->odm_mirror_cnt = be32_to_cpup(p++);
- data_map->odm_raid_algorithm = be32_to_cpup(p++);
- dprintk("%s: odm_num_comps=%u odm_stripe_unit=%llu odm_group_width=%u "
- "odm_group_depth=%u odm_mirror_cnt=%u odm_raid_algorithm=%u\n",
- __func__,
- data_map->odm_num_comps,
- (unsigned long long)data_map->odm_stripe_unit,
- data_map->odm_group_width,
- data_map->odm_group_depth,
- data_map->odm_mirror_cnt,
- data_map->odm_raid_algorithm);
- return p;
-}
-
-int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
- struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr)
-{
- __be32 *p;
-
- memset(iter, 0, sizeof(*iter));
-
- p = xdr_inline_decode(xdr, _osd_data_map_xdr_sz() + 4 + 4);
- if (unlikely(!p))
- return -EINVAL;
-
- p = _osd_xdr_decode_data_map(p, &layout->olo_map);
- layout->olo_comps_index = be32_to_cpup(p++);
- layout->olo_num_comps = be32_to_cpup(p++);
- dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__,
- layout->olo_comps_index, layout->olo_num_comps);
-
- iter->total_comps = layout->olo_num_comps;
- return 0;
-}
-
-bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
- struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
- int *err)
-{
- BUG_ON(iter->decoded_comps > iter->total_comps);
- if (iter->decoded_comps == iter->total_comps)
- return false;
-
- *err = _osd_xdr_decode_object_cred(comp, xdr);
- if (unlikely(*err)) {
- dprintk("%s: _osd_xdr_decode_object_cred=>%d decoded_comps=%d "
- "total_comps=%d\n", __func__, *err,
- iter->decoded_comps, iter->total_comps);
- return false; /* stop the loop */
- }
- dprintk("%s: dev(%llx:%llx) par=0x%llx obj=0x%llx "
- "key_len=%u cap_len=%u\n",
- __func__,
- _DEVID_LO(&comp->oc_object_id.oid_device_id),
- _DEVID_HI(&comp->oc_object_id.oid_device_id),
- comp->oc_object_id.oid_partition_id,
- comp->oc_object_id.oid_object_id,
- comp->oc_cap_key.cred_len, comp->oc_cap.cred_len);
-
- iter->decoded_comps++;
- return true;
-}
-
-/*
- * Get Device Information Decoding
- *
- * Note: since Device Information is currently done synchronously, all
- * variable strings fields are left inside the rpc buffer and are only
- * pointed to by the pnfs_osd_deviceaddr members. So the read buffer
- * should not be freed while the returned information is in use.
- */
-/*
- *struct nfs4_string {
- * unsigned int len;
- * char *data;
- *}; // size [variable]
- * NOTE: Returned string points to inside the XDR buffer
- */
-static __be32 *
-__read_u8_opaque(__be32 *p, struct nfs4_string *str)
-{
- str->len = be32_to_cpup(p++);
- str->data = (char *)p;
-
- p += XDR_QUADLEN(str->len);
- return p;
-}
-
-/*
- * struct pnfs_osd_targetid {
- * u32 oti_type;
- * struct nfs4_string oti_scsi_device_id;
- * };// size 4 + [variable]
- */
-static __be32 *
-__read_targetid(__be32 *p, struct pnfs_osd_targetid* targetid)
-{
- u32 oti_type;
-
- oti_type = be32_to_cpup(p++);
- targetid->oti_type = oti_type;
-
- switch (oti_type) {
- case OBJ_TARGET_SCSI_NAME:
- case OBJ_TARGET_SCSI_DEVICE_ID:
- p = __read_u8_opaque(p, &targetid->oti_scsi_device_id);
- }
-
- return p;
-}
-
-/*
- * struct pnfs_osd_net_addr {
- * struct nfs4_string r_netid;
- * struct nfs4_string r_addr;
- * };
- */
-static __be32 *
-__read_net_addr(__be32 *p, struct pnfs_osd_net_addr* netaddr)
-{
- p = __read_u8_opaque(p, &netaddr->r_netid);
- p = __read_u8_opaque(p, &netaddr->r_addr);
-
- return p;
-}
-
-/*
- * struct pnfs_osd_targetaddr {
- * u32 ota_available;
- * struct pnfs_osd_net_addr ota_netaddr;
- * };
- */
-static __be32 *
-__read_targetaddr(__be32 *p, struct pnfs_osd_targetaddr *targetaddr)
-{
- u32 ota_available;
-
- ota_available = be32_to_cpup(p++);
- targetaddr->ota_available = ota_available;
-
- if (ota_available)
- p = __read_net_addr(p, &targetaddr->ota_netaddr);
-
-
- return p;
-}
-
-/*
- * struct pnfs_osd_deviceaddr {
- * struct pnfs_osd_targetid oda_targetid;
- * struct pnfs_osd_targetaddr oda_targetaddr;
- * u8 oda_lun[8];
- * struct nfs4_string oda_systemid;
- * struct pnfs_osd_object_cred oda_root_obj_cred;
- * struct nfs4_string oda_osdname;
- * };
- */
-
-/* We need this version for the pnfs_osd_xdr_decode_deviceaddr which does
- * not have an xdr_stream
- */
-static __be32 *
-__read_opaque_cred(__be32 *p,
- struct pnfs_osd_opaque_cred *opaque_cred)
-{
- opaque_cred->cred_len = be32_to_cpu(*p++);
- opaque_cred->cred = p;
- return p + XDR_QUADLEN(opaque_cred->cred_len);
-}
-
-static __be32 *
-__read_object_cred(__be32 *p, struct pnfs_osd_object_cred *comp)
-{
- p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
- comp->oc_osd_version = be32_to_cpup(p++);
- comp->oc_cap_key_sec = be32_to_cpup(p++);
-
- p = __read_opaque_cred(p, &comp->oc_cap_key);
- p = __read_opaque_cred(p, &comp->oc_cap);
- return p;
-}
-
-void pnfs_osd_xdr_decode_deviceaddr(
- struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p)
-{
- p = __read_targetid(p, &deviceaddr->oda_targetid);
-
- p = __read_targetaddr(p, &deviceaddr->oda_targetaddr);
-
- p = xdr_decode_opaque_fixed(p, deviceaddr->oda_lun,
- sizeof(deviceaddr->oda_lun));
-
- p = __read_u8_opaque(p, &deviceaddr->oda_systemid);
-
- p = __read_object_cred(p, &deviceaddr->oda_root_obj_cred);
-
- p = __read_u8_opaque(p, &deviceaddr->oda_osdname);
-
- /* libosd likes this terminated in dbg. It's last, so no problems */
- deviceaddr->oda_osdname.data[deviceaddr->oda_osdname.len] = 0;
-}
-
-/*
- * struct pnfs_osd_layoutupdate {
- * u32 dsu_valid;
- * s64 dsu_delta;
- * u32 olu_ioerr_flag;
- * }; xdr size 4 + 8 + 4
- */
-int
-pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
- struct pnfs_osd_layoutupdate *lou)
-{
- __be32 *p = xdr_reserve_space(xdr, 4 + 8 + 4);
-
- if (!p)
- return -E2BIG;
-
- *p++ = cpu_to_be32(lou->dsu_valid);
- if (lou->dsu_valid)
- p = xdr_encode_hyper(p, lou->dsu_delta);
- *p++ = cpu_to_be32(lou->olu_ioerr_flag);
- return 0;
-}
-
-/*
- * struct pnfs_osd_objid {
- * struct nfs4_deviceid oid_device_id;
- * u64 oid_partition_id;
- * u64 oid_object_id;
- * }; // xdr size 32 bytes
- */
-static inline __be32 *
-pnfs_osd_xdr_encode_objid(__be32 *p, struct pnfs_osd_objid *object_id)
-{
- p = xdr_encode_opaque_fixed(p, &object_id->oid_device_id.data,
- sizeof(object_id->oid_device_id.data));
- p = xdr_encode_hyper(p, object_id->oid_partition_id);
- p = xdr_encode_hyper(p, object_id->oid_object_id);
-
- return p;
-}
-
-/*
- * struct pnfs_osd_ioerr {
- * struct pnfs_osd_objid oer_component;
- * u64 oer_comp_offset;
- * u64 oer_comp_length;
- * u32 oer_iswrite;
- * u32 oer_errno;
- * }; // xdr size 32 + 24 bytes
- */
-void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr)
-{
- p = pnfs_osd_xdr_encode_objid(p, &ioerr->oer_component);
- p = xdr_encode_hyper(p, ioerr->oer_comp_offset);
- p = xdr_encode_hyper(p, ioerr->oer_comp_length);
- *p++ = cpu_to_be32(ioerr->oer_iswrite);
- *p = cpu_to_be32(ioerr->oer_errno);
-}
-
-__be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr)
-{
- __be32 *p;
-
- p = xdr_reserve_space(xdr, 32 + 24);
- if (unlikely(!p))
- dprintk("%s: out of xdr space\n", __func__);
-
- return p;
-}
static struct kmem_cache *nfs_page_cachep;
static const struct rpc_call_ops nfs_pgio_common_ops;
-static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
-{
- p->npages = pagecount;
- if (pagecount <= ARRAY_SIZE(p->page_array))
- p->pagevec = p->page_array;
- else {
- p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
- if (!p->pagevec)
- p->npages = 0;
- }
- return p->pagevec != NULL;
-}
-
struct nfs_pgio_mirror *
nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc)
{
TASK_KILLABLE);
}
+/**
+ * nfs_async_iocounter_wait - wait on a rpc_waitqueue for I/O
+ * to complete
+ * @task: the rpc_task that should wait
+ * @l_ctx: nfs_lock_context with io_counter to check
+ *
+ * Returns true if there is outstanding I/O to wait on and the
+ * task has been put to sleep.
+ */
+bool
+nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx)
+{
+ struct inode *inode = d_inode(l_ctx->open_context->dentry);
+ bool ret = false;
+
+ if (atomic_read(&l_ctx->io_count) > 0) {
+ rpc_sleep_on(&NFS_SERVER(inode)->uoc_rpcwaitq, task, NULL);
+ ret = true;
+ }
+
+ if (atomic_read(&l_ctx->io_count) == 0) {
+ rpc_wake_up_queued_task(&NFS_SERVER(inode)->uoc_rpcwaitq, task);
+ ret = false;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait);
+
/*
* nfs_page_group_lock - lock the head of the page group
* @req - request in group that is to be locked
req->wb_page = NULL;
}
if (l_ctx != NULL) {
- if (atomic_dec_and_test(&l_ctx->io_count))
+ if (atomic_dec_and_test(&l_ctx->io_count)) {
wake_up_atomic_t(&l_ctx->io_count);
+ if (test_bit(NFS_CONTEXT_UNLOCK, &ctx->flags))
+ rpc_wake_up(&NFS_SERVER(d_inode(ctx->dentry))->uoc_rpcwaitq);
+ }
nfs_put_lock_context(l_ctx);
req->wb_lock_context = NULL;
}
const struct nfs_pgio_completion_ops *compl_ops,
const struct nfs_rw_ops *rw_ops,
size_t bsize,
- int io_flags)
+ int io_flags,
+ gfp_t gfp_flags)
{
struct nfs_pgio_mirror *new;
int i;
/* until we have a request, we don't have an lseg and no
* idea how many mirrors there will be */
new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX,
- sizeof(struct nfs_pgio_mirror), GFP_KERNEL);
+ sizeof(struct nfs_pgio_mirror), gfp_flags);
desc->pg_mirrors_dynamic = new;
desc->pg_mirrors = new;
*last_page;
struct list_head *head = &mirror->pg_list;
struct nfs_commit_info cinfo;
+ struct nfs_page_array *pg_array = &hdr->page_array;
unsigned int pagecount, pageused;
+ gfp_t gfp_flags = GFP_KERNEL;
pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
- if (!nfs_pgarray_set(&hdr->page_array, pagecount)) {
- nfs_pgio_error(hdr);
- desc->pg_error = -ENOMEM;
- return desc->pg_error;
+
+ if (pagecount <= ARRAY_SIZE(pg_array->page_array))
+ pg_array->pagevec = pg_array->page_array;
+ else {
+ if (hdr->rw_mode == FMODE_WRITE)
+ gfp_flags = GFP_NOIO;
+ pg_array->pagevec = kcalloc(pagecount, sizeof(struct page *), gfp_flags);
+ if (!pg_array->pagevec) {
+ pg_array->npages = 0;
+ nfs_pgio_error(hdr);
+ desc->pg_error = -ENOMEM;
+ return desc->pg_error;
+ }
}
nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
mirror = &desc->pg_mirrors[midx];
if (!list_empty(&mirror->pg_list)) {
prev = nfs_list_entry(mirror->pg_list.prev);
- if (index != prev->wb_index + 1)
- nfs_pageio_complete_mirror(desc, midx);
+ if (index != prev->wb_index + 1) {
+ nfs_pageio_complete(desc);
+ break;
+ }
}
}
}
static void
pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
{
+ struct pnfs_layout_segment *lseg;
lo->plh_return_iomode = 0;
lo->plh_return_seq = 0;
clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+ list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
+ if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+ continue;
+ pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0);
+ }
}
static void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
struct pnfs_layout_segment *lseg, *next;
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- pnfs_clear_layoutreturn_info(lo);
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
pnfs_clear_lseg_state(lseg, lseg_list);
+ pnfs_clear_layoutreturn_info(lo);
pnfs_free_returned_lsegs(lo, lseg_list, &range, 0);
if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
!test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags))
}
}
}
-EXPORT_SYMBOL_GPL(pnfs_put_lseg_locked);
/*
* is l2 fully contained in l1?
pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
spin_unlock(&nfsi->vfs_inode.i_lock);
pnfs_free_lseg_list(&tmp_list);
+ nfs_commit_inode(&nfsi->vfs_inode, 0);
pnfs_put_layout_hdr(lo);
} else
spin_unlock(&nfsi->vfs_inode.i_lock);
dprintk("<-- %s status: %d\n", __func__, status);
return status;
}
-EXPORT_SYMBOL_GPL(_pnfs_return_layout);
int
pnfs_commit_and_return_layout(struct inode *inode)
spin_unlock(&ino->i_lock);
lseg->pls_layout = lo;
NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
+ if (!pnfs_layout_is_valid(lo))
+ nfs_commit_inode(ino, 0);
return ERR_PTR(-EAGAIN);
}
bool return_now = false;
spin_lock(&inode->i_lock);
+ if (!pnfs_layout_is_valid(lo)) {
+ spin_unlock(&inode->i_lock);
+ return;
+ }
pnfs_set_plh_return_info(lo, range.iomode, 0);
- /* Block LAYOUTGET */
- set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
/*
* mark all matching lsegs so that we are sure to have no live
* segments at hand when sending layoutreturn. See pnfs_put_lseg()
}
EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
+void
+pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio)
+{
+ if (pgio->pg_lseg == NULL ||
+ test_bit(NFS_LSEG_VALID, &pgio->pg_lseg->pls_flags))
+ return;
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_layout);
+
void
pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
u64 rd_size = req->wb_bytes;
+ pnfs_generic_pg_check_layout(pgio);
if (pgio->pg_lseg == NULL) {
if (pgio->pg_dreq == NULL)
rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req, u64 wb_size)
{
+ pnfs_generic_pg_check_layout(pgio);
if (pgio->pg_lseg == NULL) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
enum pnfs_try_status trypnfs;
trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how);
- if (trypnfs == PNFS_NOT_ATTEMPTED)
+ switch (trypnfs) {
+ case PNFS_NOT_ATTEMPTED:
pnfs_write_through_mds(desc, hdr);
+ case PNFS_ATTEMPTED:
+ break;
+ case PNFS_TRY_AGAIN:
+ /* cleanup hdr and prepare to redo pnfs */
+ if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+ list_splice_init(&hdr->pages, &mirror->pg_list);
+ mirror->pg_recoalesce = 1;
+ }
+ hdr->mds_ops->rpc_release(hdr);
+ }
}
static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
enum pnfs_try_status trypnfs;
trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
- if (trypnfs == PNFS_TRY_AGAIN)
- pnfs_read_resend_pnfs(hdr);
- if (trypnfs == PNFS_NOT_ATTEMPTED || hdr->task.tk_status)
+ switch (trypnfs) {
+ case PNFS_NOT_ATTEMPTED:
pnfs_read_through_mds(desc, hdr);
+ case PNFS_ATTEMPTED:
+ break;
+ case PNFS_TRY_AGAIN:
+ /* cleanup hdr and prepare to redo pnfs */
+ if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+ list_splice_init(&hdr->pages, &mirror->pg_list);
+ mirror->pg_recoalesce = 1;
+ }
+ hdr->mds_ops->rpc_release(hdr);
+ }
}
static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
gfp_t gfp_flags);
int (*prepare_layoutreturn) (struct nfs4_layoutreturn_args *);
- void (*encode_layoutreturn) (struct xdr_stream *xdr,
- const struct nfs4_layoutreturn_args *args);
void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args);
- void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo,
- struct xdr_stream *xdr,
- const struct nfs4_layoutcommit_args *args);
int (*prepare_layoutstats) (struct nfs42_layoutstat_args *args);
};
void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, struct nfs_fsinfo *);
void unset_pnfs_layoutdriver(struct nfs_server *);
+void pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio);
void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
if (list_empty(&bucket->committing))
continue;
- data = nfs_commitdata_alloc();
+ /*
+ * If the layout segment is invalid, then let
+ * pnfs_generic_retry_commit() clean up the bucket.
+ */
+ if (bucket->clseg && !pnfs_is_valid_lseg(bucket->clseg) &&
+ !test_bit(NFS_LSEG_LAYOUTRETURN, &bucket->clseg->pls_flags))
+ break;
+ data = nfs_commitdata_alloc(false);
if (!data)
break;
data->ds_commit_index = i;
unsigned int nreq = 0;
if (!list_empty(mds_pages)) {
- data = nfs_commitdata_alloc();
- if (data != NULL) {
- data->ds_commit_index = -1;
- list_add(&data->pages, &list);
- nreq++;
- } else {
- nfs_retry_commit(mds_pages, NULL, cinfo, 0);
- pnfs_generic_retry_commit(cinfo, 0);
- return -ENOMEM;
- }
+ data = nfs_commitdata_alloc(true);
+ data->ds_commit_index = -1;
+ list_add(&data->pages, &list);
+ nreq++;
}
nreq += pnfs_generic_alloc_ds_commits(cinfo, &list);
get_v3_ds_connect = NULL;
}
}
-EXPORT_SYMBOL_GPL(nfs4_pnfs_v3_ds_connect_unload);
static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
struct nfs4_pnfs_ds *ds,
{
struct inode *inode = file_inode(filp);
- return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
+ return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl, NULL);
}
/* Helper functions for NFS lock bounds checking */
static struct nfs_pgio_header *nfs_readhdr_alloc(void)
{
- return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
+ struct nfs_pgio_header *p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
+
+ if (p)
+ p->rw_mode = FMODE_READ;
+ return p;
}
static void nfs_readhdr_free(struct nfs_pgio_header *rhdr)
pg_ops = server->pnfs_curr_ld->pg_read_ops;
#endif
nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops,
- server->rsize, 0);
+ server->rsize, 0, GFP_KERNEL);
}
EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
}
static const struct nfs_rw_ops nfs_rw_read_ops = {
- .rw_mode = FMODE_READ,
.rw_alloc_header = nfs_readhdr_alloc,
.rw_free_header = nfs_readhdr_free,
.rw_done = nfs_readpage_done,
static struct kmem_cache *nfs_cdata_cachep;
static mempool_t *nfs_commit_mempool;
-struct nfs_commit_data *nfs_commitdata_alloc(void)
+struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail)
{
- struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
+ struct nfs_commit_data *p;
- if (p) {
- memset(p, 0, sizeof(*p));
- INIT_LIST_HEAD(&p->pages);
+ if (never_fail)
+ p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
+ else {
+ /* It is OK to do some reclaim, not no safe to wait
+ * for anything to be returned to the pool.
+ * mempool_alloc() cannot handle that particular combination,
+ * so we need two separate attempts.
+ */
+ p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT);
+ if (!p)
+ p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO |
+ __GFP_NOWARN | __GFP_NORETRY);
+ if (!p)
+ return NULL;
}
+
+ memset(p, 0, sizeof(*p));
+ INIT_LIST_HEAD(&p->pages);
return p;
}
EXPORT_SYMBOL_GPL(nfs_commitdata_alloc);
{
struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
- if (p)
+ if (p) {
memset(p, 0, sizeof(*p));
+ p->rw_mode = FMODE_WRITE;
+ }
return p;
}
{
nfs_unlock_request(req);
nfs_end_page_writeback(req);
- nfs_release_request(req);
generic_error_remove_page(page_file_mapping(req->wb_page),
req->wb_page);
+ nfs_release_request(req);
+}
+
+static bool
+nfs_error_is_fatal_on_server(int err)
+{
+ switch (err) {
+ case 0:
+ case -ERESTARTSYS:
+ case -EINTR:
+ return false;
+ }
+ return nfs_error_is_fatal(err);
}
/*
* May return an error if the user signalled nfs_wait_on_request().
*/
static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
- struct page *page, bool nonblock,
- bool launder)
+ struct page *page, bool nonblock)
{
struct nfs_page *req;
int ret = 0;
WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
ret = 0;
+ /* If there is a fatal error that covers this write, just exit */
+ if (nfs_error_is_fatal_on_server(req->wb_context->error))
+ goto out_launder;
+
if (!nfs_pageio_add_request(pgio, req)) {
ret = pgio->pg_error;
/*
- * Remove the problematic req upon fatal errors
- * in launder case, while other dirty pages can
- * still be around until they get flushed.
+ * Remove the problematic req upon fatal errors on the server
*/
if (nfs_error_is_fatal(ret)) {
nfs_context_set_write_error(req->wb_context, ret);
- if (launder) {
- nfs_write_error_remove_page(req);
- goto out;
- }
+ if (nfs_error_is_fatal_on_server(ret))
+ goto out_launder;
}
nfs_redirty_request(req);
ret = -EAGAIN;
NFSIOS_WRITEPAGES, 1);
out:
return ret;
+out_launder:
+ nfs_write_error_remove_page(req);
+ return ret;
}
static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
- struct nfs_pageio_descriptor *pgio, bool launder)
+ struct nfs_pageio_descriptor *pgio)
{
int ret;
nfs_pageio_cond_complete(pgio, page_index(page));
- ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE,
- launder);
+ ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
if (ret == -EAGAIN) {
redirty_page_for_writepage(wbc, page);
ret = 0;
* Write an mmapped page to the server.
*/
static int nfs_writepage_locked(struct page *page,
- struct writeback_control *wbc,
- bool launder)
+ struct writeback_control *wbc)
{
struct nfs_pageio_descriptor pgio;
struct inode *inode = page_file_mapping(page)->host;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
nfs_pageio_init_write(&pgio, inode, 0,
false, &nfs_async_write_completion_ops);
- err = nfs_do_writepage(page, wbc, &pgio, launder);
+ err = nfs_do_writepage(page, wbc, &pgio);
nfs_pageio_complete(&pgio);
if (err < 0)
return err;
{
int ret;
- ret = nfs_writepage_locked(page, wbc, false);
+ ret = nfs_writepage_locked(page, wbc);
unlock_page(page);
return ret;
}
{
int ret;
- ret = nfs_do_writepage(page, wbc, data, false);
+ ret = nfs_do_writepage(page, wbc, data);
unlock_page(page);
return ret;
}
pg_ops = server->pnfs_curr_ld->pg_write_ops;
#endif
nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops,
- server->wsize, ioflags);
+ server->wsize, ioflags, GFP_NOIO);
}
EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
if (list_empty(head))
return 0;
- data = nfs_commitdata_alloc();
-
- if (!data)
- goto out_bad;
+ data = nfs_commitdata_alloc(true);
/* Set up the argument struct */
nfs_init_commit(data, head, NULL, cinfo);
atomic_inc(&cinfo->mds->rpcs_out);
return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
data->mds_ops, how, 0);
- out_bad:
- nfs_retry_commit(head, NULL, cinfo, 0);
- return -ENOMEM;
-}
-
-int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf)
-{
- struct inode *inode = file_inode(file);
- struct nfs_open_context *open;
- struct nfs_commit_info cinfo;
- struct nfs_page *req;
- int ret;
-
- open = get_nfs_open_context(nfs_file_open_context(file));
- req = nfs_create_request(open, NULL, NULL, 0, i_size_read(inode));
- if (IS_ERR(req)) {
- ret = PTR_ERR(req);
- goto out_put;
- }
-
- nfs_init_cinfo_from_inode(&cinfo, inode);
-
- memcpy(&req->wb_verf, verf, sizeof(struct nfs_write_verifier));
- nfs_request_add_commit_list(req, &cinfo);
- ret = nfs_commit_inode(inode, FLUSH_SYNC);
- if (ret > 0)
- ret = 0;
-
- nfs_free_request(req);
-out_put:
- put_nfs_open_context(open);
- return ret;
}
-EXPORT_SYMBOL_GPL(nfs_commit_file);
/*
* COMMIT call returned
/*
* Write back all requests on one page - we do this before reading it.
*/
-int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder)
+int nfs_wb_page(struct inode *inode, struct page *page)
{
loff_t range_start = page_file_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_SIZE - 1);
for (;;) {
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
- ret = nfs_writepage_locked(page, &wbc, launder);
+ ret = nfs_writepage_locked(page, &wbc);
if (ret < 0)
goto out_error;
continue;
}
static const struct nfs_rw_ops nfs_rw_write_ops = {
- .rw_mode = FMODE_WRITE,
.rw_alloc_header = nfs_writehdr_alloc,
.rw_free_header = nfs_writehdr_free,
.rw_done = nfs_writeback_done,
if (!p)
return 0;
p = xdr_decode_hyper(p, &args->offset);
-
args->count = ntohl(*p++);
+
+ if (!xdr_argsize_check(rqstp, p))
+ return 0;
+
len = min(args->count, max_blocksize);
/* set up the kvec */
v++;
}
args->vlen = v;
- return xdr_argsize_check(rqstp, p);
+ return 1;
}
int
p = decode_fh(p, &args->fh);
if (!p)
return 0;
+ if (!xdr_argsize_check(rqstp, p))
+ return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
- return xdr_argsize_check(rqstp, p);
+ return 1;
}
int
args->verf = p; p += 2;
args->dircount = ~0;
args->count = ntohl(*p++);
+
+ if (!xdr_argsize_check(rqstp, p))
+ return 0;
+
args->count = min_t(u32, args->count, PAGE_SIZE);
args->buffer = page_address(*(rqstp->rq_next_page++));
- return xdr_argsize_check(rqstp, p);
+ return 1;
}
int
args->dircount = ntohl(*p++);
args->count = ntohl(*p++);
+ if (!xdr_argsize_check(rqstp, p))
+ return 0;
+
len = args->count = min(args->count, max_blocksize);
while (len > 0) {
struct page *p = *(rqstp->rq_next_page++);
args->buffer = page_address(p);
len -= PAGE_SIZE;
}
-
- return xdr_argsize_check(rqstp, p);
+ return 1;
}
int
return NULL;
}
- if (!(exp->ex_layout_types & (1 << layout_type))) {
+ if (layout_type >= LAYOUT_TYPE_MAX ||
+ !(exp->ex_layout_types & (1 << layout_type))) {
dprintk("%s: layout type %d not supported\n",
__func__, layout_type);
return NULL;
target->cl_clientid.cl_id = source->cl_clientid.cl_id;
}
-int strdup_if_nonnull(char **target, char *source)
-{
- if (source) {
- *target = kstrdup(source, GFP_KERNEL);
- if (!*target)
- return -ENOMEM;
- } else
- *target = NULL;
- return 0;
-}
-
static int copy_cred(struct svc_cred *target, struct svc_cred *source)
{
- int ret;
+ target->cr_principal = kstrdup(source->cr_principal, GFP_KERNEL);
+ target->cr_raw_principal = kstrdup(source->cr_raw_principal,
+ GFP_KERNEL);
+ if ((source->cr_principal && ! target->cr_principal) ||
+ (source->cr_raw_principal && ! target->cr_raw_principal))
+ return -ENOMEM;
- ret = strdup_if_nonnull(&target->cr_principal, source->cr_principal);
- if (ret)
- return ret;
- ret = strdup_if_nonnull(&target->cr_raw_principal,
- source->cr_raw_principal);
- if (ret)
- return ret;
target->cr_flavor = source->cr_flavor;
target->cr_uid = source->cr_uid;
target->cr_gid = source->cr_gid;
}
#endif /* CONFIG_NFSD_PNFS */
if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
- status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0,
- NFSD_SUPPATTR_EXCLCREAT_WORD1,
- NFSD_SUPPATTR_EXCLCREAT_WORD2);
+ u32 supp[3];
+
+ memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp));
+ supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0;
+ supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1;
+ supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2;
+
+ status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]);
if (status)
goto out;
}
struct nfsd4_getdeviceinfo *gdev)
{
struct xdr_stream *xdr = &resp->xdr;
- const struct nfsd4_layout_ops *ops =
- nfsd4_layout_ops[gdev->gd_layout_type];
+ const struct nfsd4_layout_ops *ops;
u32 starting_len = xdr->buf->len, needed_len;
__be32 *p;
/* If maxcount is 0 then just update notifications */
if (gdev->gd_maxcount != 0) {
+ ops = nfsd4_layout_ops[gdev->gd_layout_type];
nfserr = ops->encode_getdeviceinfo(xdr, gdev);
if (nfserr) {
/*
struct nfsd4_layoutget *lgp)
{
struct xdr_stream *xdr = &resp->xdr;
- const struct nfsd4_layout_ops *ops =
- nfsd4_layout_ops[lgp->lg_layout_type];
+ const struct nfsd4_layout_ops *ops;
__be32 *p;
dprintk("%s: err %d\n", __func__, nfserr);
*p++ = cpu_to_be32(lgp->lg_seg.iomode);
*p++ = cpu_to_be32(lgp->lg_layout_type);
+ ops = nfsd4_layout_ops[lgp->lg_layout_type];
nfserr = ops->encode_layoutget(xdr, lgp);
out:
kfree(lgp->lg_content);
len = args->count = ntohl(*p++);
p++; /* totalcount - unused */
+ if (!xdr_argsize_check(rqstp, p))
+ return 0;
+
len = min_t(unsigned int, len, NFSSVC_MAXBLKSIZE_V2);
/* set up somewhere to store response.
v++;
}
args->vlen = v;
- return xdr_argsize_check(rqstp, p);
+ return 1;
}
int
p = decode_fh(p, &args->fh);
if (!p)
return 0;
+ if (!xdr_argsize_check(rqstp, p))
+ return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
- return xdr_argsize_check(rqstp, p);
+ return 1;
}
int
args->cookie = ntohl(*p++);
args->count = ntohl(*p++);
args->count = min_t(u32, args->count, PAGE_SIZE);
+ if (!xdr_argsize_check(rqstp, p))
+ return 0;
args->buffer = page_address(*(rqstp->rq_next_page++));
- return xdr_argsize_check(rqstp, p);
+ return 1;
}
/*
err = follow_down(&path);
if (err < 0)
goto out;
+ if (path.mnt == exp->ex_path.mnt && path.dentry == dentry &&
+ nfsd_mountpoint(dentry, exp) == 2) {
+ /* This is only a mountpoint in some other namespace */
+ path_put(&path);
+ goto out;
+ }
exp2 = rqst_exp_get_by_name(rqstp, &path);
if (IS_ERR(exp2)) {
/*
* For nfsd purposes, we treat V4ROOT exports as though there was an
* export at *every* directory.
+ * We return:
+ * '1' if this dentry *must* be an export point,
+ * '2' if it might be, if there is really a mount here, and
+ * '0' if there is no chance of an export point here.
*/
int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp)
{
- if (d_mountpoint(dentry))
+ if (!d_inode(dentry))
+ return 0;
+ if (exp->ex_flags & NFSEXP_V4ROOT)
return 1;
if (nfsd4_is_junction(dentry))
return 1;
- if (!(exp->ex_flags & NFSEXP_V4ROOT))
- return 0;
- return d_inode(dentry) != NULL;
+ if (d_mountpoint(dentry))
+ /*
+ * Might only be a mountpoint in a different namespace,
+ * but we need to check.
+ */
+ return 2;
+ return 0;
}
__be32
goto out_putf;
error = -EPERM;
- if (IS_APPEND(inode))
+ /* Check IS_APPEND on real upper inode */
+ if (IS_APPEND(file_inode(f.file)))
goto out_putf;
sb_start_write(inode->i_sb);
#include <linux/namei.h>
#include <linux/fdtable.h>
#include <linux/ratelimit.h>
+#include <linux/exportfs.h>
#include "overlayfs.h"
#include "ovl_entry.h"
return err;
}
+static struct ovl_fh *ovl_encode_fh(struct dentry *lower, uuid_be *uuid)
+{
+ struct ovl_fh *fh;
+ int fh_type, fh_len, dwords;
+ void *buf;
+ int buflen = MAX_HANDLE_SZ;
+
+ buf = kmalloc(buflen, GFP_TEMPORARY);
+ if (!buf)
+ return ERR_PTR(-ENOMEM);
+
+ /*
+ * We encode a non-connectable file handle for non-dir, because we
+ * only need to find the lower inode number and we don't want to pay
+ * the price or reconnecting the dentry.
+ */
+ dwords = buflen >> 2;
+ fh_type = exportfs_encode_fh(lower, buf, &dwords, 0);
+ buflen = (dwords << 2);
+
+ fh = ERR_PTR(-EIO);
+ if (WARN_ON(fh_type < 0) ||
+ WARN_ON(buflen > MAX_HANDLE_SZ) ||
+ WARN_ON(fh_type == FILEID_INVALID))
+ goto out;
+
+ BUILD_BUG_ON(MAX_HANDLE_SZ + offsetof(struct ovl_fh, fid) > 255);
+ fh_len = offsetof(struct ovl_fh, fid) + buflen;
+ fh = kmalloc(fh_len, GFP_KERNEL);
+ if (!fh) {
+ fh = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ fh->version = OVL_FH_VERSION;
+ fh->magic = OVL_FH_MAGIC;
+ fh->type = fh_type;
+ fh->flags = OVL_FH_FLAG_CPU_ENDIAN;
+ fh->len = fh_len;
+ fh->uuid = *uuid;
+ memcpy(fh->fid, buf, buflen);
+
+out:
+ kfree(buf);
+ return fh;
+}
+
+static int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
+ struct dentry *upper)
+{
+ struct super_block *sb = lower->d_sb;
+ uuid_be *uuid = (uuid_be *) &sb->s_uuid;
+ const struct ovl_fh *fh = NULL;
+ int err;
+
+ /*
+ * When lower layer doesn't support export operations store a 'null' fh,
+ * so we can use the overlay.origin xattr to distignuish between a copy
+ * up and a pure upper inode.
+ */
+ if (sb->s_export_op && sb->s_export_op->fh_to_dentry &&
+ uuid_be_cmp(*uuid, NULL_UUID_BE)) {
+ fh = ovl_encode_fh(lower, uuid);
+ if (IS_ERR(fh))
+ return PTR_ERR(fh);
+ }
+
+ err = ovl_do_setxattr(upper, OVL_XATTR_ORIGIN, fh, fh ? fh->len : 0, 0);
+ kfree(fh);
+
+ return err;
+}
+
static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
struct dentry *dentry, struct path *lowerpath,
struct kstat *stat, const char *link,
if (err)
goto out_cleanup;
+ /*
+ * Store identifier of lower inode in upper inode xattr to
+ * allow lookup of the copy up origin inode.
+ */
+ err = ovl_set_origin(dentry, lowerpath->dentry, temp);
+ if (err)
+ goto out_cleanup;
+
if (tmpfile)
err = ovl_do_link(temp, udir, upper, true);
else
return err;
}
-static int ovl_dir_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
-{
- struct dentry *dentry = path->dentry;
- int err;
- enum ovl_path_type type;
- struct path realpath;
- const struct cred *old_cred;
-
- type = ovl_path_real(dentry, &realpath);
- old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_getattr(&realpath, stat, request_mask, flags);
- revert_creds(old_cred);
- if (err)
- return err;
-
- stat->dev = dentry->d_sb->s_dev;
- stat->ino = dentry->d_inode->i_ino;
-
- /*
- * It's probably not worth it to count subdirs to get the
- * correct link count. nlink=1 seems to pacify 'find' and
- * other utilities.
- */
- if (OVL_TYPE_MERGE(type))
- stat->nlink = 1;
-
- return 0;
-}
-
/* Common operations required to be done after creation of file on upper */
static void ovl_instantiate(struct dentry *dentry, struct inode *inode,
struct dentry *newdentry, bool hardlink)
inc_nlink(inode);
}
d_instantiate(dentry, inode);
+ /* Force lookup of new upper hardlink to find its lower */
+ if (hardlink)
+ d_drop(dentry);
}
static bool ovl_type_merge(struct dentry *dentry)
if (err)
goto out_dput;
- if (ovl_type_merge(dentry->d_parent)) {
+ if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry)) {
/* Setting opaque here is just an optimization, allow to fail */
ovl_set_opaque(dentry, newdentry);
}
.create = ovl_create,
.mknod = ovl_mknod,
.permission = ovl_permission,
- .getattr = ovl_dir_getattr,
+ .getattr = ovl_getattr,
.listxattr = ovl_listxattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
return err;
}
-static int ovl_getattr(const struct path *path, struct kstat *stat,
- u32 request_mask, unsigned int flags)
+int ovl_getattr(const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int flags)
{
struct dentry *dentry = path->dentry;
+ enum ovl_path_type type;
struct path realpath;
const struct cred *old_cred;
+ bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
int err;
- ovl_path_real(dentry, &realpath);
+ type = ovl_path_real(dentry, &realpath);
old_cred = ovl_override_creds(dentry->d_sb);
err = vfs_getattr(&realpath, stat, request_mask, flags);
+ if (err)
+ goto out;
+
+ /*
+ * When all layers are on the same fs, all real inode number are
+ * unique, so we use the overlay st_dev, which is friendly to du -x.
+ *
+ * We also use st_ino of the copy up origin, if we know it.
+ * This guaranties constant st_dev/st_ino across copy up.
+ *
+ * If filesystem supports NFS export ops, this also guaranties
+ * persistent st_ino across mount cycle.
+ */
+ if (ovl_same_sb(dentry->d_sb)) {
+ if (OVL_TYPE_ORIGIN(type)) {
+ struct kstat lowerstat;
+ u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);
+
+ ovl_path_lower(dentry, &realpath);
+ err = vfs_getattr(&realpath, &lowerstat,
+ lowermask, flags);
+ if (err)
+ goto out;
+
+ WARN_ON_ONCE(stat->dev != lowerstat.dev);
+ /*
+ * Lower hardlinks are broken on copy up to different
+ * upper files, so we cannot use the lower origin st_ino
+ * for those different files, even for the same fs case.
+ */
+ if (is_dir || lowerstat.nlink == 1)
+ stat->ino = lowerstat.ino;
+ }
+ stat->dev = dentry->d_sb->s_dev;
+ } else if (is_dir) {
+ /*
+ * If not all layers are on the same fs the pair {real st_ino;
+ * overlay st_dev} is not unique, so use the non persistent
+ * overlay st_ino.
+ *
+ * Always use the overlay st_dev for directories, so 'find
+ * -xdev' will scan the entire overlay mount and won't cross the
+ * overlay mount boundaries.
+ */
+ stat->dev = dentry->d_sb->s_dev;
+ stat->ino = dentry->d_inode->i_ino;
+ }
+
+ /*
+ * It's probably not worth it to count subdirs to get the
+ * correct link count. nlink=1 seems to pacify 'find' and
+ * other utilities.
+ */
+ if (is_dir && OVL_TYPE_MERGE(type))
+ stat->nlink = 1;
+
+out:
revert_creds(old_cred);
+
return err;
}
.update_time = ovl_update_time,
};
+/*
+ * It is possible to stack overlayfs instance on top of another
+ * overlayfs instance as lower layer. We need to annonate the
+ * stackable i_mutex locks according to stack level of the super
+ * block instance. An overlayfs instance can never be in stack
+ * depth 0 (there is always a real fs below it). An overlayfs
+ * inode lock will use the lockdep annotaion ovl_i_mutex_key[depth].
+ *
+ * For example, here is a snip from /proc/lockdep_chains after
+ * dir_iterate of nested overlayfs:
+ *
+ * [...] &ovl_i_mutex_dir_key[depth] (stack_depth=2)
+ * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1)
+ * [...] &type->i_mutex_dir_key (stack_depth=0)
+ */
+#define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH
+
+static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
+{
+#ifdef CONFIG_LOCKDEP
+ static struct lock_class_key ovl_i_mutex_key[OVL_MAX_NESTING];
+ static struct lock_class_key ovl_i_mutex_dir_key[OVL_MAX_NESTING];
+
+ int depth = inode->i_sb->s_stack_depth - 1;
+
+ if (WARN_ON_ONCE(depth < 0 || depth >= OVL_MAX_NESTING))
+ depth = 0;
+
+ if (S_ISDIR(inode->i_mode))
+ lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_dir_key[depth]);
+ else
+ lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_key[depth]);
+#endif
+}
+
static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
{
inode->i_ino = get_next_ino();
inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
#endif
+ ovl_lockdep_annotate_inode_mutex_key(inode);
+
switch (mode & S_IFMT) {
case S_IFREG:
inode->i_op = &ovl_file_inode_operations;
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/ratelimit.h>
+#include <linux/mount.h>
+#include <linux/exportfs.h>
#include "overlayfs.h"
#include "ovl_entry.h"
goto err_free;
}
+static int ovl_acceptable(void *ctx, struct dentry *dentry)
+{
+ return 1;
+}
+
+static struct dentry *ovl_get_origin(struct dentry *dentry,
+ struct vfsmount *mnt)
+{
+ int res;
+ struct ovl_fh *fh = NULL;
+ struct dentry *origin = NULL;
+ int bytes;
+
+ res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0);
+ if (res < 0) {
+ if (res == -ENODATA || res == -EOPNOTSUPP)
+ return NULL;
+ goto fail;
+ }
+ /* Zero size value means "copied up but origin unknown" */
+ if (res == 0)
+ return NULL;
+
+ fh = kzalloc(res, GFP_TEMPORARY);
+ if (!fh)
+ return ERR_PTR(-ENOMEM);
+
+ res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, fh, res);
+ if (res < 0)
+ goto fail;
+
+ if (res < sizeof(struct ovl_fh) || res < fh->len)
+ goto invalid;
+
+ if (fh->magic != OVL_FH_MAGIC)
+ goto invalid;
+
+ /* Treat larger version and unknown flags as "origin unknown" */
+ if (fh->version > OVL_FH_VERSION || fh->flags & ~OVL_FH_FLAG_ALL)
+ goto out;
+
+ /* Treat endianness mismatch as "origin unknown" */
+ if (!(fh->flags & OVL_FH_FLAG_ANY_ENDIAN) &&
+ (fh->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN)
+ goto out;
+
+ bytes = (fh->len - offsetof(struct ovl_fh, fid));
+
+ /*
+ * Make sure that the stored uuid matches the uuid of the lower
+ * layer where file handle will be decoded.
+ */
+ if (uuid_be_cmp(fh->uuid, *(uuid_be *) &mnt->mnt_sb->s_uuid))
+ goto out;
+
+ origin = exportfs_decode_fh(mnt, (struct fid *)fh->fid,
+ bytes >> 2, (int)fh->type,
+ ovl_acceptable, NULL);
+ if (IS_ERR(origin)) {
+ /* Treat stale file handle as "origin unknown" */
+ if (origin == ERR_PTR(-ESTALE))
+ origin = NULL;
+ goto out;
+ }
+
+ if (ovl_dentry_weird(origin) ||
+ ((d_inode(origin)->i_mode ^ d_inode(dentry)->i_mode) & S_IFMT)) {
+ dput(origin);
+ origin = NULL;
+ goto invalid;
+ }
+
+out:
+ kfree(fh);
+ return origin;
+
+fail:
+ pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res);
+ goto out;
+invalid:
+ pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh);
+ goto out;
+}
+
static bool ovl_is_opaquedir(struct dentry *dentry)
{
int res;
return 0;
}
+
+static int ovl_check_origin(struct dentry *dentry, struct dentry *upperdentry,
+ struct path **stackp, unsigned int *ctrp)
+{
+ struct super_block *same_sb = ovl_same_sb(dentry->d_sb);
+ struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
+ struct vfsmount *mnt;
+ struct dentry *origin;
+
+ if (!same_sb || !roe->numlower)
+ return 0;
+
+ /*
+ * Since all layers are on the same fs, we use the first layer for
+ * decoding the file handle. We may get a disconnected dentry,
+ * which is fine, because we only need to hold the origin inode in
+ * cache and use its inode number. We may even get a connected dentry,
+ * that is not under the first layer's root. That is also fine for
+ * using it's inode number - it's the same as if we held a reference
+ * to a dentry in first layer that was moved under us.
+ */
+ mnt = roe->lowerstack[0].mnt;
+
+ origin = ovl_get_origin(upperdentry, mnt);
+ if (IS_ERR_OR_NULL(origin))
+ return PTR_ERR(origin);
+
+ BUG_ON(*stackp || *ctrp);
+ *stackp = kmalloc(sizeof(struct path), GFP_TEMPORARY);
+ if (!*stackp) {
+ dput(origin);
+ return -ENOMEM;
+ }
+ **stackp = (struct path) { .dentry = origin, .mnt = mnt };
+ *ctrp = 1;
+
+ return 0;
+}
+
/*
* Returns next layer in stack starting from top.
* Returns -1 if this is the last layer.
const struct cred *old_cred;
struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+ struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
struct path *stack = NULL;
struct dentry *upperdir, *upperdentry = NULL;
unsigned int ctr = 0;
err = -EREMOTE;
goto out;
}
+ if (upperdentry && !d.is_dir) {
+ BUG_ON(!d.stop || d.redirect);
+ err = ovl_check_origin(dentry, upperdentry,
+ &stack, &ctr);
+ if (err)
+ goto out;
+ }
if (d.redirect) {
upperredirect = kstrdup(d.redirect, GFP_KERNEL);
if (!upperredirect)
goto out_put_upper;
if (d.redirect[0] == '/')
- poe = dentry->d_sb->s_root->d_fsdata;
+ poe = roe;
}
upperopaque = d.opaque;
}
if (d.stop)
break;
- if (d.redirect &&
- d.redirect[0] == '/' &&
- poe != dentry->d_sb->s_root->d_fsdata) {
- poe = dentry->d_sb->s_root->d_fsdata;
+ if (d.redirect && d.redirect[0] == '/' && poe != roe) {
+ poe = roe;
/* Find the current layer on the root dentry */
for (i = 0; i < poe->numlower; i++)
*/
#include <linux/kernel.h>
+#include <linux/uuid.h>
enum ovl_path_type {
__OVL_PATH_UPPER = (1 << 0),
__OVL_PATH_MERGE = (1 << 1),
+ __OVL_PATH_ORIGIN = (1 << 2),
};
#define OVL_TYPE_UPPER(type) ((type) & __OVL_PATH_UPPER)
#define OVL_TYPE_MERGE(type) ((type) & __OVL_PATH_MERGE)
+#define OVL_TYPE_ORIGIN(type) ((type) & __OVL_PATH_ORIGIN)
#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay."
#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque"
#define OVL_XATTR_REDIRECT OVL_XATTR_PREFIX "redirect"
+#define OVL_XATTR_ORIGIN OVL_XATTR_PREFIX "origin"
+
+/*
+ * The tuple (fh,uuid) is a universal unique identifier for a copy up origin,
+ * where:
+ * origin.fh - exported file handle of the lower file
+ * origin.uuid - uuid of the lower filesystem
+ */
+#define OVL_FH_VERSION 0
+#define OVL_FH_MAGIC 0xfb
+
+/* CPU byte order required for fid decoding: */
+#define OVL_FH_FLAG_BIG_ENDIAN (1 << 0)
+#define OVL_FH_FLAG_ANY_ENDIAN (1 << 1)
+
+#define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN)
+
+#if defined(__LITTLE_ENDIAN)
+#define OVL_FH_FLAG_CPU_ENDIAN 0
+#elif defined(__BIG_ENDIAN)
+#define OVL_FH_FLAG_CPU_ENDIAN OVL_FH_FLAG_BIG_ENDIAN
+#else
+#error Endianness not defined
+#endif
+
+/* On-disk and in-memeory format for redirect by file handle */
+struct ovl_fh {
+ u8 version; /* 0 */
+ u8 magic; /* 0xfb */
+ u8 len; /* size of this header + size of fid */
+ u8 flags; /* OVL_FH_FLAG_* */
+ u8 type; /* fid_type of fid */
+ uuid_be uuid; /* uuid of filesystem */
+ u8 fid[0]; /* file identifier */
+} __packed;
#define OVL_ISUPPER_MASK 1UL
void ovl_drop_write(struct dentry *dentry);
struct dentry *ovl_workdir(struct dentry *dentry);
const struct cred *ovl_override_creds(struct super_block *sb);
+struct super_block *ovl_same_sb(struct super_block *sb);
struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
bool ovl_dentry_remote(struct dentry *dentry);
bool ovl_dentry_weird(struct dentry *dentry);
/* inode.c */
int ovl_setattr(struct dentry *dentry, struct iattr *attr);
+int ovl_getattr(const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int flags);
int ovl_permission(struct inode *inode, int mask);
int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags);
const struct cred *creator_cred;
bool tmpfile;
wait_queue_head_t copyup_wq;
+ /* sb common to all layers */
+ struct super_block *same_sb;
};
/* private information held for every overlayfs dentry */
}
}
+static int ovl_check_append_only(struct inode *inode, int flag)
+{
+ /*
+ * This test was moot in vfs may_open() because overlay inode does
+ * not have the S_APPEND flag, so re-check on real upper inode
+ */
+ if (IS_APPEND(inode)) {
+ if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
+ return -EPERM;
+ if (flag & O_TRUNC)
+ return -EPERM;
+ }
+
+ return 0;
+}
+
static struct dentry *ovl_d_real(struct dentry *dentry,
const struct inode *inode,
unsigned int open_flags)
{
struct dentry *real;
+ int err;
if (!d_is_reg(dentry)) {
if (!inode || inode == d_inode(dentry))
return dentry;
if (open_flags) {
- int err = ovl_open_maybe_copy_up(dentry, open_flags);
-
+ err = ovl_open_maybe_copy_up(dentry, open_flags);
if (err)
return ERR_PTR(err);
}
real = ovl_dentry_upper(dentry);
- if (real && (!inode || inode == d_inode(real)))
+ if (real && (!inode || inode == d_inode(real))) {
+ if (!inode) {
+ err = ovl_check_append_only(d_inode(real), open_flags);
+ if (err)
+ return ERR_PTR(err);
+ }
return real;
+ }
real = ovl_dentry_lower(dentry);
if (!real)
static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
- struct path upperpath = { NULL, NULL };
- struct path workpath = { NULL, NULL };
+ struct path upperpath = { };
+ struct path workpath = { };
struct dentry *root_dentry;
struct inode *realinode;
struct ovl_entry *oe;
ufs->lower_mnt[ufs->numlower] = mnt;
ufs->numlower++;
+
+ /* Check if all lower layers are on same sb */
+ if (i == 0)
+ ufs->same_sb = mnt->mnt_sb;
+ else if (ufs->same_sb != mnt->mnt_sb)
+ ufs->same_sb = NULL;
}
/* If the upper fs is nonexistent, we mark overlayfs r/o too */
if (!ufs->upper_mnt)
sb->s_flags |= MS_RDONLY;
+ else if (ufs->upper_mnt->mnt_sb != ufs->same_sb)
+ ufs->same_sb = NULL;
if (remote)
sb->s_d_op = &ovl_reval_dentry_operations;
return override_creds(ofs->creator_cred);
}
+struct super_block *ovl_same_sb(struct super_block *sb)
+{
+ struct ovl_fs *ofs = sb->s_fs_info;
+
+ return ofs->same_sb;
+}
+
struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
{
size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
type = __OVL_PATH_UPPER;
/*
- * Non-dir dentry can hold lower dentry from previous
- * location.
+ * Non-dir dentry can hold lower dentry of its copy up origin.
*/
- if (oe->numlower && d_is_dir(dentry))
- type |= __OVL_PATH_MERGE;
+ if (oe->numlower) {
+ type |= __OVL_PATH_ORIGIN;
+ if (d_is_dir(dentry))
+ type |= __OVL_PATH_MERGE;
+ }
} else {
if (oe->numlower > 1)
type |= __OVL_PATH_MERGE;
{
struct ovl_entry *oe = dentry->d_fsdata;
- *path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL };
+ *path = oe->numlower ? oe->lowerstack[0] : (struct path) { };
}
enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
MODULE_PARM_DESC(pmsg_size, "size of user space message log");
static unsigned long long mem_address;
-module_param(mem_address, ullong, 0400);
+module_param_hw(mem_address, ullong, other, 0400);
MODULE_PARM_DESC(mem_address,
"start of reserved RAM used to store oops/panic logs");
/*
* The lockless check can race with remove_wait_queue() in progress,
* but in this case its caller should run under rcu_read_lock() and
- * sighand_cachep is SLAB_DESTROY_BY_RCU, we can safely return.
+ * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return.
*/
if (likely(!waitqueue_active(wqh)))
return;
+++ /dev/null
-# Top-level Makefile calls into asm-$(ARCH)
-# List only non-arch directories below
#define ACPI_MAX_EXTPARSE_CACHE_DEPTH 96 /* Parse tree objects */
#define ACPI_MAX_OBJECT_CACHE_DEPTH 96 /* Interpreter operand objects */
#define ACPI_MAX_NAMESPACE_CACHE_DEPTH 96 /* Namespace objects */
+#define ACPI_MAX_COMMENT_CACHE_DEPTH 96 /* Comments for the -ca option */
/*
* Should the subsystem abort the loading of an ACPI table if the
bool acpi_dma_supported(struct acpi_device *adev);
enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
-void acpi_dma_configure(struct device *dev, enum dev_dma_attr attr);
+int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr);
void acpi_dma_deconfigure(struct device *dev);
struct acpi_device *acpi_find_child_device(struct acpi_device *parent,
int acpi_enable_wakeup_device_power(struct acpi_device *dev, int state);
int acpi_disable_wakeup_device_power(struct acpi_device *dev);
+#ifdef CONFIG_X86
+bool acpi_device_always_present(struct acpi_device *adev);
+#else
+static inline bool acpi_device_always_present(struct acpi_device *adev)
+{
+ return false;
+}
+#endif
+
#ifdef CONFIG_PM
acpi_status acpi_add_pm_notifier(struct acpi_device *adev, struct device *dev,
void (*work_func)(struct work_struct *work));
/* Current ACPICA subsystem version in YYYYMMDD format */
-#define ACPI_CA_VERSION 0x20170119
+#define ACPI_CA_VERSION 0x20170303
#include <acpi/acconfig.h>
#include <acpi/actypes.h>
#define ACPI_SIG_WDAT "WDAT" /* Watchdog Action Table */
#define ACPI_SIG_WDDT "WDDT" /* Watchdog Timer Description Table */
#define ACPI_SIG_WDRT "WDRT" /* Watchdog Resource Table */
+#define ACPI_SIG_XXXX "XXXX" /* Intermediate AML header for ASL/ASL+ converter */
#ifdef ACPI_UNDEFINED_TABLES
/*
#define ACPI_IORT_SMMU_DVM_SUPPORTED (1)
#define ACPI_IORT_SMMU_COHERENT_WALK (1<<1)
+/* Global interrupt format */
+
+struct acpi_iort_smmu_gsi {
+ u32 nsg_irpt;
+ u32 nsg_irpt_flags;
+ u32 nsg_cfg_irpt;
+ u32 nsg_cfg_irpt_flags;
+};
+
struct acpi_iort_smmu_v3 {
u64 base_address; /* SMMUv3 base address */
u32 flags;
+++ /dev/null
-include include/uapi/asm-generic/Kbuild.asm
IRQCHIP_OF_MATCH_TABLE() \
ACPI_PROBE_TABLE(irqchip) \
ACPI_PROBE_TABLE(clksrc) \
- ACPI_PROBE_TABLE(iort) \
EARLYCON_TABLE()
#define INIT_TEXT \
#define HI6220_CS_DAPB 57
#define HI6220_CS_ATB_DIV 58
-#define HI6220_SYS_NR_CLKS 59
+/* gate clock */
+#define HI6220_DAPB_CLK 59
+
+#define HI6220_SYS_NR_CLKS 60
/* clk in Hi6220 media controller */
/* gate clocks */
--- /dev/null
+/*
+ * Copyright (c) 2017 MediaTek Inc.
+ * Author: Kevin Chen <kevin-cw.chen@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DT_BINDINGS_CLK_MT6797_H
+#define _DT_BINDINGS_CLK_MT6797_H
+
+/* TOPCKGEN */
+#define CLK_TOP_MUX_ULPOSC_AXI_CK_MUX_PRE 1
+#define CLK_TOP_MUX_ULPOSC_AXI_CK_MUX 2
+#define CLK_TOP_MUX_AXI 3
+#define CLK_TOP_MUX_MEM 4
+#define CLK_TOP_MUX_DDRPHYCFG 5
+#define CLK_TOP_MUX_MM 6
+#define CLK_TOP_MUX_PWM 7
+#define CLK_TOP_MUX_VDEC 8
+#define CLK_TOP_MUX_VENC 9
+#define CLK_TOP_MUX_MFG 10
+#define CLK_TOP_MUX_CAMTG 11
+#define CLK_TOP_MUX_UART 12
+#define CLK_TOP_MUX_SPI 13
+#define CLK_TOP_MUX_ULPOSC_SPI_CK_MUX 14
+#define CLK_TOP_MUX_USB20 15
+#define CLK_TOP_MUX_MSDC50_0_HCLK 16
+#define CLK_TOP_MUX_MSDC50_0 17
+#define CLK_TOP_MUX_MSDC30_1 18
+#define CLK_TOP_MUX_MSDC30_2 19
+#define CLK_TOP_MUX_AUDIO 20
+#define CLK_TOP_MUX_AUD_INTBUS 21
+#define CLK_TOP_MUX_PMICSPI 22
+#define CLK_TOP_MUX_SCP 23
+#define CLK_TOP_MUX_ATB 24
+#define CLK_TOP_MUX_MJC 25
+#define CLK_TOP_MUX_DPI0 26
+#define CLK_TOP_MUX_AUD_1 27
+#define CLK_TOP_MUX_AUD_2 28
+#define CLK_TOP_MUX_SSUSB_TOP_SYS 29
+#define CLK_TOP_MUX_SPM 30
+#define CLK_TOP_MUX_BSI_SPI 31
+#define CLK_TOP_MUX_AUDIO_H 32
+#define CLK_TOP_MUX_ANC_MD32 33
+#define CLK_TOP_MUX_MFG_52M 34
+#define CLK_TOP_SYSPLL_CK 35
+#define CLK_TOP_SYSPLL_D2 36
+#define CLK_TOP_SYSPLL1_D2 37
+#define CLK_TOP_SYSPLL1_D4 38
+#define CLK_TOP_SYSPLL1_D8 39
+#define CLK_TOP_SYSPLL1_D16 40
+#define CLK_TOP_SYSPLL_D3 41
+#define CLK_TOP_SYSPLL_D3_D3 42
+#define CLK_TOP_SYSPLL2_D2 43
+#define CLK_TOP_SYSPLL2_D4 44
+#define CLK_TOP_SYSPLL2_D8 45
+#define CLK_TOP_SYSPLL_D5 46
+#define CLK_TOP_SYSPLL3_D2 47
+#define CLK_TOP_SYSPLL3_D4 48
+#define CLK_TOP_SYSPLL_D7 49
+#define CLK_TOP_SYSPLL4_D2 50
+#define CLK_TOP_SYSPLL4_D4 51
+#define CLK_TOP_UNIVPLL_CK 52
+#define CLK_TOP_UNIVPLL_D7 53
+#define CLK_TOP_UNIVPLL_D26 54
+#define CLK_TOP_SSUSB_PHY_48M_CK 55
+#define CLK_TOP_USB_PHY48M_CK 56
+#define CLK_TOP_UNIVPLL_D2 57
+#define CLK_TOP_UNIVPLL1_D2 58
+#define CLK_TOP_UNIVPLL1_D4 59
+#define CLK_TOP_UNIVPLL1_D8 60
+#define CLK_TOP_UNIVPLL_D3 61
+#define CLK_TOP_UNIVPLL2_D2 62
+#define CLK_TOP_UNIVPLL2_D4 63
+#define CLK_TOP_UNIVPLL2_D8 64
+#define CLK_TOP_UNIVPLL_D5 65
+#define CLK_TOP_UNIVPLL3_D2 66
+#define CLK_TOP_UNIVPLL3_D4 67
+#define CLK_TOP_UNIVPLL3_D8 68
+#define CLK_TOP_ULPOSC_CK_ORG 69
+#define CLK_TOP_ULPOSC_CK 70
+#define CLK_TOP_ULPOSC_D2 71
+#define CLK_TOP_ULPOSC_D3 72
+#define CLK_TOP_ULPOSC_D4 73
+#define CLK_TOP_ULPOSC_D8 74
+#define CLK_TOP_ULPOSC_D10 75
+#define CLK_TOP_APLL1_CK 76
+#define CLK_TOP_APLL2_CK 77
+#define CLK_TOP_MFGPLL_CK 78
+#define CLK_TOP_MFGPLL_D2 79
+#define CLK_TOP_IMGPLL_CK 80
+#define CLK_TOP_IMGPLL_D2 81
+#define CLK_TOP_IMGPLL_D4 82
+#define CLK_TOP_CODECPLL_CK 83
+#define CLK_TOP_CODECPLL_D2 84
+#define CLK_TOP_VDECPLL_CK 85
+#define CLK_TOP_TVDPLL_CK 86
+#define CLK_TOP_TVDPLL_D2 87
+#define CLK_TOP_TVDPLL_D4 88
+#define CLK_TOP_TVDPLL_D8 89
+#define CLK_TOP_TVDPLL_D16 90
+#define CLK_TOP_MSDCPLL_CK 91
+#define CLK_TOP_MSDCPLL_D2 92
+#define CLK_TOP_MSDCPLL_D4 93
+#define CLK_TOP_MSDCPLL_D8 94
+#define CLK_TOP_NR 95
+
+/* APMIXED_SYS */
+#define CLK_APMIXED_MAINPLL 1
+#define CLK_APMIXED_UNIVPLL 2
+#define CLK_APMIXED_MFGPLL 3
+#define CLK_APMIXED_MSDCPLL 4
+#define CLK_APMIXED_IMGPLL 5
+#define CLK_APMIXED_TVDPLL 6
+#define CLK_APMIXED_CODECPLL 7
+#define CLK_APMIXED_VDECPLL 8
+#define CLK_APMIXED_APLL1 9
+#define CLK_APMIXED_APLL2 10
+#define CLK_APMIXED_NR 11
+
+/* INFRA_SYS */
+#define CLK_INFRA_PMIC_TMR 1
+#define CLK_INFRA_PMIC_AP 2
+#define CLK_INFRA_PMIC_MD 3
+#define CLK_INFRA_PMIC_CONN 4
+#define CLK_INFRA_SCP 5
+#define CLK_INFRA_SEJ 6
+#define CLK_INFRA_APXGPT 7
+#define CLK_INFRA_SEJ_13M 8
+#define CLK_INFRA_ICUSB 9
+#define CLK_INFRA_GCE 10
+#define CLK_INFRA_THERM 11
+#define CLK_INFRA_I2C0 12
+#define CLK_INFRA_I2C1 13
+#define CLK_INFRA_I2C2 14
+#define CLK_INFRA_I2C3 15
+#define CLK_INFRA_PWM_HCLK 16
+#define CLK_INFRA_PWM1 17
+#define CLK_INFRA_PWM2 18
+#define CLK_INFRA_PWM3 19
+#define CLK_INFRA_PWM4 20
+#define CLK_INFRA_PWM 21
+#define CLK_INFRA_UART0 22
+#define CLK_INFRA_UART1 23
+#define CLK_INFRA_UART2 24
+#define CLK_INFRA_UART3 25
+#define CLK_INFRA_MD2MD_CCIF_0 26
+#define CLK_INFRA_MD2MD_CCIF_1 27
+#define CLK_INFRA_MD2MD_CCIF_2 28
+#define CLK_INFRA_FHCTL 29
+#define CLK_INFRA_BTIF 30
+#define CLK_INFRA_MD2MD_CCIF_3 31
+#define CLK_INFRA_SPI 32
+#define CLK_INFRA_MSDC0 33
+#define CLK_INFRA_MD2MD_CCIF_4 34
+#define CLK_INFRA_MSDC1 35
+#define CLK_INFRA_MSDC2 36
+#define CLK_INFRA_MD2MD_CCIF_5 37
+#define CLK_INFRA_GCPU 38
+#define CLK_INFRA_TRNG 39
+#define CLK_INFRA_AUXADC 40
+#define CLK_INFRA_CPUM 41
+#define CLK_INFRA_AP_C2K_CCIF_0 42
+#define CLK_INFRA_AP_C2K_CCIF_1 43
+#define CLK_INFRA_CLDMA 44
+#define CLK_INFRA_DISP_PWM 45
+#define CLK_INFRA_AP_DMA 46
+#define CLK_INFRA_DEVICE_APC 47
+#define CLK_INFRA_L2C_SRAM 48
+#define CLK_INFRA_CCIF_AP 49
+#define CLK_INFRA_AUDIO 50
+#define CLK_INFRA_CCIF_MD 51
+#define CLK_INFRA_DRAMC_F26M 52
+#define CLK_INFRA_I2C4 53
+#define CLK_INFRA_I2C_APPM 54
+#define CLK_INFRA_I2C_GPUPM 55
+#define CLK_INFRA_I2C2_IMM 56
+#define CLK_INFRA_I2C2_ARB 57
+#define CLK_INFRA_I2C3_IMM 58
+#define CLK_INFRA_I2C3_ARB 59
+#define CLK_INFRA_I2C5 60
+#define CLK_INFRA_SYS_CIRQ 61
+#define CLK_INFRA_SPI1 62
+#define CLK_INFRA_DRAMC_B_F26M 63
+#define CLK_INFRA_ANC_MD32 64
+#define CLK_INFRA_ANC_MD32_32K 65
+#define CLK_INFRA_DVFS_SPM1 66
+#define CLK_INFRA_AES_TOP0 67
+#define CLK_INFRA_AES_TOP1 68
+#define CLK_INFRA_SSUSB_BUS 69
+#define CLK_INFRA_SPI2 70
+#define CLK_INFRA_SPI3 71
+#define CLK_INFRA_SPI4 72
+#define CLK_INFRA_SPI5 73
+#define CLK_INFRA_IRTX 74
+#define CLK_INFRA_SSUSB_SYS 75
+#define CLK_INFRA_SSUSB_REF 76
+#define CLK_INFRA_AUDIO_26M 77
+#define CLK_INFRA_AUDIO_26M_PAD_TOP 78
+#define CLK_INFRA_MODEM_TEMP_SHARE 79
+#define CLK_INFRA_VAD_WRAP_SOC 80
+#define CLK_INFRA_DRAMC_CONF 81
+#define CLK_INFRA_DRAMC_B_CONF 82
+#define CLK_INFRA_MFG_VCG 83
+#define CLK_INFRA_13M 84
+#define CLK_INFRA_NR 85
+
+/* IMG_SYS */
+#define CLK_IMG_FDVT 1
+#define CLK_IMG_DPE 2
+#define CLK_IMG_DIP 3
+#define CLK_IMG_LARB6 4
+#define CLK_IMG_NR 5
+
+/* MM_SYS */
+#define CLK_MM_SMI_COMMON 1
+#define CLK_MM_SMI_LARB0 2
+#define CLK_MM_SMI_LARB5 3
+#define CLK_MM_CAM_MDP 4
+#define CLK_MM_MDP_RDMA0 5
+#define CLK_MM_MDP_RDMA1 6
+#define CLK_MM_MDP_RSZ0 7
+#define CLK_MM_MDP_RSZ1 8
+#define CLK_MM_MDP_RSZ2 9
+#define CLK_MM_MDP_TDSHP 10
+#define CLK_MM_MDP_COLOR 11
+#define CLK_MM_MDP_WDMA 12
+#define CLK_MM_MDP_WROT0 13
+#define CLK_MM_MDP_WROT1 14
+#define CLK_MM_FAKE_ENG 15
+#define CLK_MM_DISP_OVL0 16
+#define CLK_MM_DISP_OVL1 17
+#define CLK_MM_DISP_OVL0_2L 18
+#define CLK_MM_DISP_OVL1_2L 19
+#define CLK_MM_DISP_RDMA0 20
+#define CLK_MM_DISP_RDMA1 21
+#define CLK_MM_DISP_WDMA0 22
+#define CLK_MM_DISP_WDMA1 23
+#define CLK_MM_DISP_COLOR 24
+#define CLK_MM_DISP_CCORR 25
+#define CLK_MM_DISP_AAL 26
+#define CLK_MM_DISP_GAMMA 27
+#define CLK_MM_DISP_OD 28
+#define CLK_MM_DISP_DITHER 29
+#define CLK_MM_DISP_UFOE 30
+#define CLK_MM_DISP_DSC 31
+#define CLK_MM_DISP_SPLIT 32
+#define CLK_MM_DSI0_MM_CLOCK 33
+#define CLK_MM_DSI1_MM_CLOCK 34
+#define CLK_MM_DPI_MM_CLOCK 35
+#define CLK_MM_DPI_INTERFACE_CLOCK 36
+#define CLK_MM_LARB4_AXI_ASIF_MM_CLOCK 37
+#define CLK_MM_LARB4_AXI_ASIF_MJC_CLOCK 38
+#define CLK_MM_DISP_OVL0_MOUT_CLOCK 39
+#define CLK_MM_FAKE_ENG2 40
+#define CLK_MM_DSI0_INTERFACE_CLOCK 41
+#define CLK_MM_DSI1_INTERFACE_CLOCK 42
+#define CLK_MM_NR 43
+
+/* VDEC_SYS */
+#define CLK_VDEC_CKEN_ENG 1
+#define CLK_VDEC_ACTIVE 2
+#define CLK_VDEC_CKEN 3
+#define CLK_VDEC_LARB1_CKEN 4
+#define CLK_VDEC_NR 5
+
+/* VENC_SYS */
+#define CLK_VENC_0 1
+#define CLK_VENC_1 2
+#define CLK_VENC_2 3
+#define CLK_VENC_3 4
+#define CLK_VENC_NR 5
+
+#endif /* _DT_BINDINGS_CLK_MT6797_H */
#define R8A7795_CLK_R 45
#define R8A7795_CLK_OSC 46
+/* r8a7795 ES2.0 CPG Core Clocks */
+#define R8A7795_CLK_S0D2 47
+#define R8A7795_CLK_S0D3 48
+#define R8A7795_CLK_S0D6 49
+#define R8A7795_CLK_S0D8 50
+#define R8A7795_CLK_S0D12 51
+
#endif /* __DT_BINDINGS_CLOCK_R8A7795_CPG_MSSR_H__ */
#define SCLK_MAC2IO_SRC 99
#define SCLK_MAC2IO 100
#define SCLK_MAC2PHY 101
+#define SCLK_MAC2IO_EXT 102
/* dclk gates */
#define DCLK_LCDC 120
#define SCLK_I2S_8CH 82
#define SCLK_SPDIF_8CH 83
#define SCLK_I2S_2CH 84
-#define SCLK_TIMER0 85
-#define SCLK_TIMER1 86
-#define SCLK_TIMER2 87
-#define SCLK_TIMER3 88
-#define SCLK_TIMER4 89
-#define SCLK_TIMER5 90
-#define SCLK_TIMER6 91
+#define SCLK_TIMER00 85
+#define SCLK_TIMER01 86
+#define SCLK_TIMER02 87
+#define SCLK_TIMER03 88
+#define SCLK_TIMER04 89
+#define SCLK_TIMER05 90
#define SCLK_OTGPHY0 93
#define SCLK_OTG_ADP 96
#define SCLK_HSICPHY480M 97
#define SCLK_SFC 126
#define SCLK_MAC 127
#define SCLK_MACREF_OUT 128
+#define SCLK_TIMER10 133
+#define SCLK_TIMER11 134
+#define SCLK_TIMER12 135
+#define SCLK_TIMER13 136
+#define SCLK_TIMER14 137
+#define SCLK_TIMER15 138
#define DCLK_VOP 190
#define MCLK_CRYPTO 191
* GNU General Public License for more details.
*/
-#ifndef _DT_BINDINGS_CLK_ROCKCHIP_RK1108_H
-#define _DT_BINDINGS_CLK_ROCKCHIP_RK1108_H
+#ifndef _DT_BINDINGS_CLK_ROCKCHIP_RV1108_H
+#define _DT_BINDINGS_CLK_ROCKCHIP_RV1108_H
/* pll id */
#define PLL_APLL 0
#define ARST_DSP_EDP_PERF 184
#define ARST_DSP_EPP_PERF 185
-#endif /* _DT_BINDINGS_CLK_ROCKCHIP_RK1108_H */
+#endif /* _DT_BINDINGS_CLK_ROCKCHIP_RV1108_H */
#define CLK_BUS_UART1 63
#define CLK_BUS_UART2 64
#define CLK_BUS_UART3 65
-#define CLK_BUS_SCR 66
+#define CLK_BUS_SCR0 66
#define CLK_BUS_EPHY 67
#define CLK_BUS_DBG 68
#define CLK_GPU 114
+/* New clocks imported in H5 */
+#define CLK_BUS_SCR1 115
+
#endif /* _DT_BINDINGS_CLK_SUN8I_H3_H_ */
--- /dev/null
+/*
+ * Copyright (c) 2016 Icenowy Zheng <icenowy@aosc.xyz>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ * a) This file is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ * b) Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following
+ * conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DT_BINDINGS_CLK_SUN8I_R_CCU_H_
+#define _DT_BINDINGS_CLK_SUN8I_R_CCU_H_
+
+#define CLK_AR100 0
+
+#define CLK_APB0_PIO 3
+#define CLK_APB0_IR 4
+#define CLK_APB0_TIMER 5
+#define CLK_APB0_RSB 6
+#define CLK_APB0_UART 7
+/* 8 is reserved for CLK_APB0_W1 on A31 */
+#define CLK_APB0_I2C 9
+#define CLK_APB0_TWD 10
+
+#define CLK_IR 11
+
+#endif /* _DT_BINDINGS_CLK_SUN8I_R_CCU_H_ */
/* 133 */
/* 134 */
/* 135 */
-/* 136 */
+#define TEGRA114_CLK_CEC 136
/* 137 */
/* 138 */
/* 139 */
/* 133 */
/* 134 */
/* 135 */
-/* 136 */
+#define TEGRA124_CLK_CEC 136
/* 137 */
/* 138 */
/* 139 */
/* 20 (register bit affects vi and vi_sensor) */
/* 21 */
#define TEGRA210_CLK_USBD 22
-#define TEGRA210_CLK_ISP 23
+#define TEGRA210_CLK_ISPA 23
/* 24 */
/* 25 */
#define TEGRA210_CLK_DISP2 26
/* 133 */
/* 134 */
/* 135 */
-/* 136 */
+#define TEGRA210_CLK_CEC 136
/* 137 */
/* 138 */
/* 139 */
#define TEGRA210_CLK_ENTROPY 149
/* 150 */
/* 151 */
-/* 152 */
+#define TEGRA210_CLK_DP2 152
/* 153 */
/* 154 */
/* 155 (bit affects dfll_ref and dfll_soc) */
#define TEGRA210_CLK_DBGAPB 185
/* 186 */
#define TEGRA210_CLK_PLL_P_OUT_ADSP 187
-/* 188 */
+/* 188 ((bit affects pll_a_out_adsp and pll_a_out0_out_adsp)*/
#define TEGRA210_CLK_PLL_G_REF 189
/* 190 */
/* 191 */
/* 196 */
#define TEGRA210_CLK_DMIC3 197
#define TEGRA210_CLK_APE 198
-/* 199 */
+#define TEGRA210_CLK_ADSP 199
/* 200 */
/* 201 */
#define TEGRA210_CLK_MAUD 202
/* 215 */
/* 216 */
/* 217 */
-/* 218 */
+#define TEGRA210_CLK_ADSP_NEON 218
#define TEGRA210_CLK_NVENC 219
-/* 220 */
-/* 221 */
+#define TEGRA210_CLK_IQC2 220
+#define TEGRA210_CLK_IQC1 221
#define TEGRA210_CLK_SOR_SAFE 222
#define TEGRA210_CLK_PLL_P_OUT_CPU 223
#define TEGRA210_CLK_PLL_RE_OUT1 319
/* 320 */
/* 321 */
-/* 322 */
-/* 323 */
-/* 324 */
+#define TEGRA210_CLK_ISP 322
+#define TEGRA210_CLK_PLL_A_OUT_ADSP 323
+#define TEGRA210_CLK_PLL_A_OUT0_OUT_ADSP 324
/* 325 */
/* 326 */
/* 327 */
#define TEGRA210_CLK_PLL_C_UD 364
#define TEGRA210_CLK_SCLK_MUX 365
-#define TEGRA210_CLK_CLK_MAX 366
+#define TEGRA210_CLK_ACLK 370
+
+#define TEGRA210_CLK_DMIC1_SYNC_CLK 388
+#define TEGRA210_CLK_DMIC1_SYNC_CLK_MUX 389
+#define TEGRA210_CLK_DMIC2_SYNC_CLK 390
+#define TEGRA210_CLK_DMIC2_SYNC_CLK_MUX 391
+#define TEGRA210_CLK_DMIC3_SYNC_CLK 392
+#define TEGRA210_CLK_DMIC3_SYNC_CLK_MUX 393
+
+#define TEGRA210_CLK_CLK_MAX 394
#endif /* _DT_BINDINGS_CLOCK_TEGRA210_CAR_H */
/* 133 */
/* 134 */
/* 135 */
-/* 136 */
+#define TEGRA30_CLK_CEC 136
/* 137 */
/* 138 */
/* 139 */
#define MT2701_HIFSYS_PCIE1_RST 25
#define MT2701_HIFSYS_PCIE2_RST 26
+/* ETHSYS resets */
+#define MT2701_ETHSYS_SYS_RST 0
+#define MT2701_ETHSYS_MCM_RST 2
+#define MT2701_ETHSYS_FE_RST 6
+#define MT2701_ETHSYS_GMAC_RST 23
+#define MT2701_ETHSYS_PPE_RST 31
+
#endif /* _DT_BINDINGS_RESET_CONTROLLER_MT2701 */
#define RST_BUS_UART1 50
#define RST_BUS_UART2 51
#define RST_BUS_UART3 52
-#define RST_BUS_SCR 53
+#define RST_BUS_SCR0 53
+
+/* New resets imported in H5 */
+#define RST_BUS_SCR1 54
#endif /* _DT_BINDINGS_RST_SUN8I_H3_H_ */
--- /dev/null
+/*
+ * Copyright (C) 2016 Icenowy Zheng <icenowy@aosc.xyz>
+ *
+ * This file is dual-licensed: you can use it either under the terms
+ * of the GPL or the X11 license, at your option. Note that this dual
+ * licensing only applies to this file, and not this project as a
+ * whole.
+ *
+ * a) This file is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Or, alternatively,
+ *
+ * b) Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+ * files (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use,
+ * copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following
+ * conditions:
+ *
+ * The above copyright notice and this permission notice shall be
+ * included in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
+ * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
+ * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
+ * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef _DT_BINDINGS_RST_SUN8I_R_CCU_H_
+#define _DT_BINDINGS_RST_SUN8I_R_CCU_H_
+
+#define RST_APB0_IR 0
+#define RST_APB0_TIMER 1
+#define RST_APB0_RSB 2
+#define RST_APB0_UART 3
+/* 4 is reserved for RST_APB0_W1 on A31 */
+#define RST_APB0_I2C 5
+
+#endif /* _DT_BINDINGS_RST_SUN8I_R_CCU_H_ */
--- /dev/null
+/*
+ * This header provides Tegra210-specific constants for binding
+ * nvidia,tegra210-car.
+ */
+
+#ifndef _DT_BINDINGS_RESET_TEGRA210_CAR_H
+#define _DT_BINDINGS_RESET_TEGRA210_CAR_H
+
+#define TEGRA210_RESET(x) (7 * 32 + (x))
+#define TEGRA210_RST_DFLL_DVCO TEGRA210_RESET(0)
+#define TEGRA210_RST_ADSP TEGRA210_RESET(1)
+
+#endif /* _DT_BINDINGS_RESET_TEGRA210_CAR_H */
gpa_t vgic_its_base;
bool enabled;
- bool initialized;
struct vgic_io_device iodev;
struct kvm_device *dev;
u32 creadr;
u32 cwriter;
+ /* migration ABI revision in use */
+ u32 abi_rev;
+
/* Protects the device and collection lists */
struct mutex its_lock;
struct list_head device_list;
int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
void kvm_vgic_early_init(struct kvm *kvm);
+int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
int kvm_vgic_create(struct kvm *kvm, u32 type);
void kvm_vgic_destroy(struct kvm *kvm);
void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
return DEV_DMA_NOT_SUPPORTED;
}
-static inline void acpi_dma_configure(struct device *dev,
- enum dev_dma_attr attr) { }
+static inline int acpi_dma_configure(struct device *dev,
+ enum dev_dma_attr attr)
+{
+ return 0;
+}
static inline void acpi_dma_deconfigure(struct device *dev) { }
{ return NULL; }
#endif
-#define IORT_ACPI_DECLARE(name, table_id, fn) \
- ACPI_DECLARE_PROBE_ENTRY(iort, name, table_id, 0, NULL, 0, fn)
-
#endif /* __ACPI_IORT_H__ */
#define PL080_SOFT_LSREQ (0x2C)
#define PL080_CONFIG (0x30)
-#define PL080_CONFIG_M2_BE (1 << 2)
-#define PL080_CONFIG_M1_BE (1 << 1)
-#define PL080_CONFIG_ENABLE (1 << 0)
+#define PL080_CONFIG_M2_BE BIT(2)
+#define PL080_CONFIG_M1_BE BIT(1)
+#define PL080_CONFIG_ENABLE BIT(0)
#define PL080_SYNC (0x34)
/* Per channel configuration registers */
-#define PL080_Cx_STRIDE (0x20)
+/* Per channel configuration registers */
#define PL080_Cx_BASE(x) ((0x100 + (x * 0x20)))
-#define PL080_Cx_SRC_ADDR(x) ((0x100 + (x * 0x20)))
-#define PL080_Cx_DST_ADDR(x) ((0x104 + (x * 0x20)))
-#define PL080_Cx_LLI(x) ((0x108 + (x * 0x20)))
-#define PL080_Cx_CONTROL(x) ((0x10C + (x * 0x20)))
-#define PL080_Cx_CONFIG(x) ((0x110 + (x * 0x20)))
-#define PL080S_Cx_CONTROL2(x) ((0x110 + (x * 0x20)))
-#define PL080S_Cx_CONFIG(x) ((0x114 + (x * 0x20)))
-
#define PL080_CH_SRC_ADDR (0x00)
#define PL080_CH_DST_ADDR (0x04)
#define PL080_CH_LLI (0x08)
#define PL080_LLI_ADDR_MASK (0x3fffffff << 2)
#define PL080_LLI_ADDR_SHIFT (2)
-#define PL080_LLI_LM_AHB2 (1 << 0)
+#define PL080_LLI_LM_AHB2 BIT(0)
-#define PL080_CONTROL_TC_IRQ_EN (1 << 31)
+#define PL080_CONTROL_TC_IRQ_EN BIT(31)
#define PL080_CONTROL_PROT_MASK (0x7 << 28)
#define PL080_CONTROL_PROT_SHIFT (28)
-#define PL080_CONTROL_PROT_CACHE (1 << 30)
-#define PL080_CONTROL_PROT_BUFF (1 << 29)
-#define PL080_CONTROL_PROT_SYS (1 << 28)
-#define PL080_CONTROL_DST_INCR (1 << 27)
-#define PL080_CONTROL_SRC_INCR (1 << 26)
-#define PL080_CONTROL_DST_AHB2 (1 << 25)
-#define PL080_CONTROL_SRC_AHB2 (1 << 24)
+#define PL080_CONTROL_PROT_CACHE BIT(30)
+#define PL080_CONTROL_PROT_BUFF BIT(29)
+#define PL080_CONTROL_PROT_SYS BIT(28)
+#define PL080_CONTROL_DST_INCR BIT(27)
+#define PL080_CONTROL_SRC_INCR BIT(26)
+#define PL080_CONTROL_DST_AHB2 BIT(25)
+#define PL080_CONTROL_SRC_AHB2 BIT(24)
#define PL080_CONTROL_DWIDTH_MASK (0x7 << 21)
#define PL080_CONTROL_DWIDTH_SHIFT (21)
#define PL080_CONTROL_SWIDTH_MASK (0x7 << 18)
#define PL080_WIDTH_16BIT (0x1)
#define PL080_WIDTH_32BIT (0x2)
-#define PL080N_CONFIG_ITPROT (1 << 20)
-#define PL080N_CONFIG_SECPROT (1 << 19)
-#define PL080_CONFIG_HALT (1 << 18)
-#define PL080_CONFIG_ACTIVE (1 << 17) /* RO */
-#define PL080_CONFIG_LOCK (1 << 16)
-#define PL080_CONFIG_TC_IRQ_MASK (1 << 15)
-#define PL080_CONFIG_ERR_IRQ_MASK (1 << 14)
+#define PL080N_CONFIG_ITPROT BIT(20)
+#define PL080N_CONFIG_SECPROT BIT(19)
+#define PL080_CONFIG_HALT BIT(18)
+#define PL080_CONFIG_ACTIVE BIT(17) /* RO */
+#define PL080_CONFIG_LOCK BIT(16)
+#define PL080_CONFIG_TC_IRQ_MASK BIT(15)
+#define PL080_CONFIG_ERR_IRQ_MASK BIT(14)
#define PL080_CONFIG_FLOW_CONTROL_MASK (0x7 << 11)
#define PL080_CONFIG_FLOW_CONTROL_SHIFT (11)
#define PL080_CONFIG_DST_SEL_MASK (0xf << 6)
#define PL080_CONFIG_DST_SEL_SHIFT (6)
#define PL080_CONFIG_SRC_SEL_MASK (0xf << 1)
#define PL080_CONFIG_SRC_SEL_SHIFT (1)
-#define PL080_CONFIG_ENABLE (1 << 0)
+#define PL080_CONFIG_ENABLE BIT(0)
#define PL080_FLOW_MEM2MEM (0x0)
#define PL080_FLOW_MEM2PER (0x1)
+++ /dev/null
-/* linux/include/linux/amba/pl330.h
- *
- * Copyright (C) 2010 Samsung Electronics Co. Ltd.
- * Jaswinder Singh <jassi.brar@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef __AMBA_PL330_H_
-#define __AMBA_PL330_H_
-
-#include <linux/dmaengine.h>
-
-struct dma_pl330_platdata {
- /*
- * Number of valid peripherals connected to DMAC.
- * This may be different from the value read from
- * CR0, as the PL330 implementation might have 'holes'
- * in the peri list or the peri could also be reached
- * from another DMAC which the platform prefers.
- */
- u8 nr_valid_peri;
- /* Array of valid peripherals */
- u8 *peri_id;
- /* Operational capabilities */
- dma_cap_mask_t cap_mask;
- /* Bytes to allocate for MC buffer */
- unsigned mcbuf_sz;
-};
-
-extern bool pl330_filter(struct dma_chan *chan, void *param);
-#endif /* __AMBA_PL330_H_ */
*/
#define CEPH_FEATURES_SUPPORTED_DEFAULT \
(CEPH_FEATURE_NOSRCADDR | \
+ CEPH_FEATURE_FLOCK | \
CEPH_FEATURE_SUBSCRIBE2 | \
CEPH_FEATURE_RECONNECT_SEQ | \
+ CEPH_FEATURE_DIRLAYOUTHASH | \
CEPH_FEATURE_PGID64 | \
CEPH_FEATURE_PGPOOL3 | \
CEPH_FEATURE_OSDENC | \
CEPH_FEATURE_MSG_AUTH | \
CEPH_FEATURE_CRUSH_TUNABLES2 | \
CEPH_FEATURE_REPLY_CREATE_INODE | \
+ CEPH_FEATURE_MDSENC | \
CEPH_FEATURE_OSDHASHPSPOOL | \
CEPH_FEATURE_OSD_CACHEPOOL | \
CEPH_FEATURE_CRUSH_V2 | \
CEPH_FEATURE_EXPORT_PEER | \
CEPH_FEATURE_OSDMAP_ENC | \
+ CEPH_FEATURE_MDS_INLINE_DATA | \
CEPH_FEATURE_CRUSH_TUNABLES3 | \
CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \
CEPH_FEATURE_MSGR_KEEPALIVE2 | \
#define CEPH_READDIR_FRAG_END (1<<0)
#define CEPH_READDIR_FRAG_COMPLETE (1<<8)
#define CEPH_READDIR_HASH_ORDER (1<<9)
+#define CEPH_READDIR_OFFSET_HASH (1<<10)
+
+/*
+ * open request flags
+ */
+#define CEPH_O_RDONLY 00000000
+#define CEPH_O_WRONLY 00000001
+#define CEPH_O_RDWR 00000002
+#define CEPH_O_CREAT 00000100
+#define CEPH_O_EXCL 00000200
+#define CEPH_O_TRUNC 00001000
+#define CEPH_O_DIRECTORY 00200000
+#define CEPH_O_NOFOLLOW 00400000
union ceph_mds_request_args {
struct {
__le32 max_entries; /* how many dentries to grab */
__le32 max_bytes;
__le16 flags;
+ __le32 offset_hash;
} __attribute__ ((packed)) readdir;
struct {
__le32 mode;
struct ceph_object_locator *oloc,
char *lock_name, char *cookie,
struct ceph_entity_name *locker);
+int ceph_cls_set_cookie(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ char *lock_name, u8 type, char *old_cookie,
+ char *tag, char *new_cookie);
void ceph_free_lockers(struct ceph_locker *lockers, u32 num_lockers);
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>
+#include <linux/refcount.h>
#include <linux/ceph/types.h>
#include <linux/ceph/messenger.h>
* dirtied.
*/
struct ceph_snap_context {
- atomic_t nref;
+ refcount_t nref;
u64 seq;
u32 num_snaps;
u64 snaps[];
extern void ceph_destroy_options(struct ceph_options *opt);
extern int ceph_compare_options(struct ceph_options *new_opt,
struct ceph_client *client);
-extern struct ceph_client *ceph_create_client(struct ceph_options *opt,
- void *private,
- u64 supported_features,
- u64 required_features);
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private);
struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client);
u64 ceph_client_gid(struct ceph_client *client);
extern void ceph_destroy_client(struct ceph_client *client);
u32 m_session_autoclose; /* seconds */
u64 m_max_file_size;
u32 m_max_mds; /* size of m_addr, m_state arrays */
+ int m_num_mds;
struct ceph_mds_info *m_info;
/* which object pools file data can be stored in */
static inline struct ceph_entity_addr *
ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
{
- if (w >= m->m_max_mds)
+ if (w >= m->m_num_mds)
return NULL;
return &m->m_info[w].addr;
}
static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
{
BUG_ON(w < 0);
- if (w >= m->m_max_mds)
+ if (w >= m->m_num_mds)
return CEPH_MDS_STATE_DNE;
return m->m_info[w].state;
}
static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
{
- if (w >= 0 && w < m->m_max_mds)
+ if (w >= 0 && w < m->m_num_mds)
return m->m_info[w].laggy;
return false;
}
#include <linux/kref.h>
#include <linux/mempool.h>
#include <linux/rbtree.h>
+#include <linux/refcount.h>
#include <linux/ceph/types.h>
#include <linux/ceph/osdmap.h>
/* a given osd we're communicating with */
struct ceph_osd {
- atomic_t o_ref;
+ refcount_t o_ref;
struct ceph_osd_client *o_osdc;
int o_osd;
int o_incarnation;
struct timespec r_mtime; /* ditto */
u64 r_data_offset; /* ditto */
bool r_linger; /* don't resend on failure */
+ bool r_abort_on_full; /* return ENOSPC when full */
/* internal */
unsigned long r_stamp; /* jiffies, send or check time */
unsigned long r_start_stamp; /* jiffies */
int r_attempts;
- struct ceph_eversion r_replay_version; /* aka reassert_version */
u32 r_last_force_resend;
u32 r_map_dne_bound;
struct rb_root osds; /* osds */
struct list_head osd_lru; /* idle osds */
spinlock_t osd_lru_lock;
+ u32 epoch_barrier;
struct ceph_osd homeless_osd;
atomic64_t last_tid; /* tid of last request */
u64 last_linger_id;
struct ceph_msg *msg);
extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
struct ceph_msg *msg);
+void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
extern void osd_req_op_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode, u32 flags);
#define __FS_CEPH_PAGELIST_H
#include <asm/byteorder.h>
-#include <linux/atomic.h>
+#include <linux/refcount.h>
#include <linux/list.h>
#include <linux/types.h>
size_t room;
struct list_head free_list;
size_t num_pages_free;
- atomic_t refcnt;
+ refcount_t refcnt;
};
struct ceph_pagelist_cursor {
pl->room = 0;
INIT_LIST_HEAD(&pl->free_list);
pl->num_pages_free = 0;
- atomic_set(&pl->refcnt, 1);
+ refcount_set(&pl->refcnt, 1);
}
extern void ceph_pagelist_release(struct ceph_pagelist *pl);
extern void tegra210_xusb_pll_hw_sequence_start(void);
extern void tegra210_sata_pll_hw_control_enable(void);
extern void tegra210_sata_pll_hw_sequence_start(void);
+extern void tegra210_set_sata_pll_seq_sw(bool state);
+extern void tegra210_put_utmipll_in_iddq(void);
+extern void tegra210_put_utmipll_out_iddq(void);
#endif /* __LINUX_CLK_TEGRA_H_ */
#include <linux/clk-provider.h>
#include <linux/clkdev.h>
+/**
+ * struct clk_omap_reg - OMAP register declaration
+ * @offset: offset from the master IP module base address
+ * @index: index of the master IP module
+ */
+struct clk_omap_reg {
+ void __iomem *ptr;
+ u16 offset;
+ u8 index;
+ u8 flags;
+};
+
/**
* struct dpll_data - DPLL registers and integration data
* @mult_div1_reg: register containing the DPLL M and N bitfields
* can be placed into read-only space.
*/
struct dpll_data {
- void __iomem *mult_div1_reg;
+ struct clk_omap_reg mult_div1_reg;
u32 mult_mask;
u32 div1_mask;
struct clk_hw *clk_bypass;
struct clk_hw *clk_ref;
- void __iomem *control_reg;
+ struct clk_omap_reg control_reg;
u32 enable_mask;
unsigned long last_rounded_rate;
u16 last_rounded_m;
u16 max_divider;
unsigned long max_rate;
u8 modes;
- void __iomem *autoidle_reg;
- void __iomem *idlest_reg;
+ struct clk_omap_reg autoidle_reg;
+ struct clk_omap_reg idlest_reg;
u32 autoidle_mask;
u32 freqsel_mask;
u32 idlest_mask;
*/
struct clk_hw_omap_ops {
void (*find_idlest)(struct clk_hw_omap *oclk,
- void __iomem **idlest_reg,
+ struct clk_omap_reg *idlest_reg,
u8 *idlest_bit, u8 *idlest_val);
void (*find_companion)(struct clk_hw_omap *oclk,
- void __iomem **other_reg,
+ struct clk_omap_reg *other_reg,
u8 *other_bit);
void (*allow_idle)(struct clk_hw_omap *oclk);
void (*deny_idle)(struct clk_hw_omap *oclk);
* @enable_bit: bitshift to write to enable/disable the clock (see @enable_reg)
* @flags: see "struct clk.flags possibilities" above
* @clksel_reg: for clksel clks, register va containing src/divisor select
- * @clksel_mask: bitmask in @clksel_reg for the src/divisor selector
- * @clksel: for clksel clks, pointer to struct clksel for this clock
* @dpll_data: for DPLLs, pointer to struct dpll_data for this clock
* @clkdm_name: clockdomain name that this clock is contained in
* @clkdm: pointer to struct clockdomain, resolved from @clkdm_name at runtime
struct list_head node;
unsigned long fixed_rate;
u8 fixed_div;
- void __iomem *enable_reg;
+ struct clk_omap_reg enable_reg;
u8 enable_bit;
u8 flags;
- void __iomem *clksel_reg;
- u32 clksel_mask;
- const struct clksel *clksel;
+ struct clk_omap_reg clksel_reg;
struct dpll_data *dpll_data;
const char *clkdm_name;
struct clockdomain *clkdm;
* should be used. This is a temporary solution - a better approach
* would be to associate clock type-specific data with the clock,
* similar to the struct dpll_data approach.
- * MEMMAP_ADDRESSING: Use memmap addressing to access clock registers.
*/
#define ENABLE_REG_32BIT (1 << 0) /* Use 32-bit access */
#define CLOCK_IDLE_CONTROL (1 << 1)
#define ENABLE_ON_INIT (1 << 3) /* Enable upon framework init */
#define INVERT_ENABLE (1 << 4) /* 0 enables, 1 disables */
#define CLOCK_CLKOUTX2 (1 << 5)
-#define MEMMAP_ADDRESSING (1 << 6)
/* CM_CLKEN_PLL*.EN* bit values - not all are available for every DPLL */
#define DPLL_LOW_POWER_STOP 0x1
CLK_MAX_MEMMAPS
};
-/**
- * struct clk_omap_reg - OMAP register declaration
- * @offset: offset from the master IP module base address
- * @index: index of the master IP module
- */
-struct clk_omap_reg {
- u16 offset;
- u16 index;
-};
-
/**
* struct ti_clk_ll_ops - low-level ops for clocks
* @clk_readl: pointer to register read function
* @clk_writel: pointer to register write function
* @clkdm_clk_enable: pointer to clockdomain enable function
* @clkdm_clk_disable: pointer to clockdomain disable function
+ * @clkdm_lookup: pointer to clockdomain lookup function
* @cm_wait_module_ready: pointer to CM module wait ready function
* @cm_split_idlest_reg: pointer to CM module function to split idlest reg
*
* operations not provided directly by clock drivers.
*/
struct ti_clk_ll_ops {
- u32 (*clk_readl)(void __iomem *reg);
- void (*clk_writel)(u32 val, void __iomem *reg);
+ u32 (*clk_readl)(const struct clk_omap_reg *reg);
+ void (*clk_writel)(u32 val, const struct clk_omap_reg *reg);
int (*clkdm_clk_enable)(struct clockdomain *clkdm, struct clk *clk);
int (*clkdm_clk_disable)(struct clockdomain *clkdm,
struct clk *clk);
+ struct clockdomain * (*clkdm_lookup)(const char *name);
int (*cm_wait_module_ready)(u8 part, s16 prcm_mod, u16 idlest_reg,
u8 idlest_shift);
- int (*cm_split_idlest_reg)(void __iomem *idlest_reg, s16 *prcm_inst,
- u8 *idlest_reg_id);
+ int (*cm_split_idlest_reg)(struct clk_omap_reg *idlest_reg,
+ s16 *prcm_inst, u8 *idlest_reg_id);
};
#define to_clk_hw_omap(_hw) container_of(_hw, struct clk_hw_omap, hw)
-void omap2_init_clk_clkdm(struct clk_hw *clk);
int omap2_clk_disable_autoidle_all(void);
int omap2_clk_enable_autoidle_all(void);
int omap2_clk_allow_idle(struct clk *clk);
*
* Function returns NULL if no refcount could be obtained, or the fence.
* This function handles acquiring a reference to a fence that may be
- * reallocated within the RCU grace period (such as with SLAB_DESTROY_BY_RCU),
+ * reallocated within the RCU grace period (such as with SLAB_TYPESAFE_BY_RCU),
* so long as the caller is using RCU on the pointer to the fence.
*
* An alternative mechanism is to employ a seqlock to protect a bunch of
* have successfully acquire a reference to it. If it no
* longer matches, we are holding a reference to some other
* reallocated pointer. This is possible if the allocator
- * is using a freelist like SLAB_DESTROY_BY_RCU where the
+ * is using a freelist like SLAB_TYPESAFE_BY_RCU where the
* fence remains valid for the RCU grace period, but it
* may be reallocated. When using such allocators, we are
* responsible for ensuring the reference we get is to
#include <asm/errno.h>
#ifdef CONFIG_IOMMU_DMA
+#include <linux/dma-mapping.h>
#include <linux/iommu.h>
#include <linux/msi.h>
/* The DMA API isn't _quite_ the whole story, though... */
void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg);
+void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
#else
{
}
+static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list)
+{
+}
+
#endif /* CONFIG_IOMMU_DMA */
#endif /* __KERNEL__ */
#endif /* __DMA_IOMMU_H */
}
#endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
+#ifdef CONFIG_HAS_DMA
+int dma_configure(struct device *dev);
+void dma_deconfigure(struct device *dev);
+#else
+static inline int dma_configure(struct device *dev)
+{
+ return 0;
+}
+
+static inline void dma_deconfigure(struct device *dev) {}
+#endif
+
/*
* Managed DMA API
*/
extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu);
extern int dmar_disabled;
extern int intel_iommu_enabled;
+extern int intel_iommu_tboot_noforce;
#else
static inline int iommu_calculate_agaw(struct intel_iommu *iommu)
{
#define FL_OFDLCK 1024 /* lock is "owned" by struct file */
#define FL_LAYOUT 2048 /* outstanding pNFS layout */
+#define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)
+
/*
* Special return value from posix_lock_file() and vfs_lock_file() for
* asynchronous locking.
#include <linux/mmu_notifier.h>
#include <linux/list.h>
#include <linux/iommu.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+
#include <asm/cacheflush.h>
#include <asm/iommu.h>
#define OFFSET_STRIDE (9)
-#ifdef CONFIG_64BIT
#define dmar_readq(a) readq(a)
#define dmar_writeq(a,v) writeq(v,a)
-#else
-static inline u64 dmar_readq(void __iomem *addr)
-{
- u32 lo, hi;
- lo = readl(addr);
- hi = readl(addr + 4);
- return (((u64) hi) << 32) + lo;
-}
-
-static inline void dmar_writeq(void __iomem *addr, u64 val)
-{
- writel((u32)val, addr);
- writel((u32)(val >> 32), addr + 4);
-}
-#endif
#define DMAR_VER_MAJOR(v) (((v) & 0xf0) >> 4)
#define DMAR_VER_MINOR(v) ((v) & 0x0f)
#ifndef __LINUX_IOMMU_H
#define __LINUX_IOMMU_H
+#include <linux/scatterlist.h>
+#include <linux/device.h>
+#include <linux/types.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/of.h>
-#include <linux/types.h>
-#include <linux/scatterlist.h>
-#include <trace/events/iommu.h>
#define IOMMU_READ (1 << 0)
#define IOMMU_WRITE (1 << 1)
#define IOMMU_NOEXEC (1 << 3)
#define IOMMU_MMIO (1 << 4) /* e.g. things like MSI doorbells */
/*
- * This is to make the IOMMU API setup privileged
- * mapppings accessible by the master only at higher
- * privileged execution level and inaccessible at
- * less privileged levels.
+ * Where the bus hardware includes a privilege level as part of its access type
+ * markings, and certain devices are capable of issuing transactions marked as
+ * either 'supervisor' or 'user', the IOMMU_PRIV flag requests that the other
+ * given permission flags only apply to accesses at the higher privilege level,
+ * and that unprivileged transactions should have as little access as possible.
+ * This would usually imply the same permissions as kernel mappings on the CPU,
+ * if the IOMMU page table format is equivalent.
*/
#define IOMMU_PRIV (1 << 5)
phys_addr_t offset, u64 size,
int prot);
extern void iommu_domain_window_disable(struct iommu_domain *domain, u32 wnd_nr);
-/**
- * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework
- * @domain: the iommu domain where the fault has happened
- * @dev: the device where the fault has happened
- * @iova: the faulting address
- * @flags: mmu fault flags (e.g. IOMMU_FAULT_READ/IOMMU_FAULT_WRITE/...)
- *
- * This function should be called by the low-level IOMMU implementations
- * whenever IOMMU faults happen, to allow high-level users, that are
- * interested in such events, to know about them.
- *
- * This event may be useful for several possible use cases:
- * - mere logging of the event
- * - dynamic TLB/PTE loading
- * - if restarting of the faulting device is required
- *
- * Returns 0 on success and an appropriate error code otherwise (if dynamic
- * PTE/TLB loading will one day be supported, implementations will be able
- * to tell whether it succeeded or not according to this return value).
- *
- * Specifically, -ENOSYS is returned if a fault handler isn't installed
- * (though fault handlers can also return -ENOSYS, in case they want to
- * elicit the default behavior of the IOMMU drivers).
- */
-static inline int report_iommu_fault(struct iommu_domain *domain,
- struct device *dev, unsigned long iova, int flags)
-{
- int ret = -ENOSYS;
-
- /*
- * if upper layers showed interest and installed a fault handler,
- * invoke it.
- */
- if (domain->handler)
- ret = domain->handler(domain, dev, iova, flags,
- domain->handler_token);
- trace_io_page_fault(dev, iova, flags);
- return ret;
-}
+extern int report_iommu_fault(struct iommu_domain *domain, struct device *dev,
+ unsigned long iova, int flags);
static inline size_t iommu_map_sg(struct iommu_domain *domain,
unsigned long iova, struct scatterlist *sg,
#define GIC_BASER_SHAREABILITY(reg, type) \
(GIC_BASER_##type << reg##_SHAREABILITY_SHIFT)
+/* encode a size field of width @w containing @n - 1 units */
+#define GIC_ENCODE_SZ(n, w) (((unsigned long)(n) - 1) & GENMASK_ULL(((w) - 1), 0))
+
#define GICR_PROPBASER_SHAREABILITY_SHIFT (10)
#define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT (7)
#define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT (56)
#define GICR_PROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb)
#define GICR_PROPBASER_IDBITS_MASK (0x1f)
+#define GICR_PROPBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 12))
+#define GICR_PENDBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 16))
#define GICR_PENDBASER_SHAREABILITY_SHIFT (10)
#define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT (7)
#define GITS_CTLR_QUIESCENT (1U << 31)
#define GITS_TYPER_PLPIS (1UL << 0)
+#define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4
#define GITS_TYPER_IDBITS_SHIFT 8
#define GITS_TYPER_DEVBITS_SHIFT 13
#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
#define GITS_TYPER_PTA (1UL << 19)
#define GITS_TYPER_HWCOLLCNT_SHIFT 24
+#define GITS_IIDR_REV_SHIFT 12
+#define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT)
+#define GITS_IIDR_REV(r) (((r) >> GITS_IIDR_REV_SHIFT) & 0xf)
+#define GITS_IIDR_PRODUCTID_SHIFT 24
+
#define GITS_CBASER_VALID (1ULL << 63)
#define GITS_CBASER_SHAREABILITY_SHIFT (10)
#define GITS_CBASER_INNER_CACHEABILITY_SHIFT (59)
#define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7)
#define GITS_BASER_ENTRY_SIZE_SHIFT (48)
#define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
+#define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48)
#define GITS_BASER_SHAREABILITY_SHIFT (10)
#define GITS_BASER_InnerShareable \
GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307
#define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507
#define E_ITS_MAPD_DEVICE_OOR 0x010801
+#define E_ITS_MAPD_ITTSIZE_OOR 0x010802
#define E_ITS_MAPC_PROCNUM_OOR 0x010902
#define E_ITS_MAPC_COLLECTION_OOR 0x010903
#define E_ITS_MAPTI_UNMAPPED_DEVICE 0x010a04
+#define E_ITS_MAPTI_ID_OOR 0x010a05
#define E_ITS_MAPTI_PHYSICALID_OOR 0x010a06
#define E_ITS_INV_UNMAPPED_INTERRUPT 0x010c07
#define E_ITS_INVALL_UNMAPPED_COLLECTION 0x010d09
#define __LINUX_KBUILD_H
#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
+ asm volatile("\n.ascii \"->" #sym " %0 " #val "\"" : : "i" (val))
-#define BLANK() asm volatile("\n->" : : )
+#define BLANK() asm volatile("\n.ascii \"->\"" : : )
#define OFFSET(sym, str, mem) \
DEFINE(sym, offsetof(struct str, mem))
#define COMMENT(x) \
- asm volatile("\n->#" x)
+ asm volatile("\n.ascii \"->#" x "\"")
#endif
struct mutex slots_lock;
struct mm_struct *mm; /* userspace tied to this vm */
struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM];
- struct srcu_struct srcu;
- struct srcu_struct irq_srcu;
struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
/*
struct list_head devices;
struct dentry *debugfs_dentry;
struct kvm_stat_data **debugfs_stat_data;
+ struct srcu_struct srcu;
+ struct srcu_struct irq_srcu;
};
#define kvm_err(fmt, ...) \
return NULL;
}
+static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu *tmp;
+ int idx;
+
+ kvm_for_each_vcpu(idx, tmp, vcpu->kvm)
+ if (tmp == vcpu)
+ return idx;
+ BUG();
+}
+
#define kvm_for_each_memslot(memslot, slots) \
for (memslot = &slots->memslots[0]; \
memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
void kvm_unregister_device_ops(u32 type);
extern struct kvm_device_ops kvm_mpic_ops;
-extern struct kvm_device_ops kvm_xics_ops;
extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
extern struct kvm_device_ops kvm_arm_vgic_v3_ops;
/* Dummy declarations */
struct svc_rqst;
+struct rpc_task;
/*
* This is the set of functions for lockd->nfsd communication
u32 nfs_version;
int noresvport;
struct net *net;
+ const struct nlmclnt_operations *nlmclnt_ops;
};
/*
extern struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init);
extern void nlmclnt_done(struct nlm_host *host);
-extern int nlmclnt_proc(struct nlm_host *host, int cmd,
- struct file_lock *fl);
+/*
+ * NLM client operations provide a means to modify RPC processing of NLM
+ * requests. Callbacks receive a pointer to data passed into the call to
+ * nlmclnt_proc().
+ */
+struct nlmclnt_operations {
+ /* Called on successful allocation of nlm_rqst, use for allocation or
+ * reference counting. */
+ void (*nlmclnt_alloc_call)(void *);
+
+ /* Called in rpc_task_prepare for unlock. A return value of true
+ * indicates the callback has put the task to sleep on a waitqueue
+ * and NLM should not call rpc_call_start(). */
+ bool (*nlmclnt_unlock_prepare)(struct rpc_task*, void *);
+
+ /* Called when the nlm_rqst is freed, callbacks should clean up here */
+ void (*nlmclnt_release_call)(void *);
+};
+
+extern int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl, void *data);
extern int lockd_up(struct net *net);
extern void lockd_down(struct net *net);
char *h_addrbuf; /* address eyecatcher */
struct net *net; /* host net */
char nodename[UNX_MAXNODENAME + 1];
+ const struct nlmclnt_operations *h_nlmclnt_ops; /* Callback ops for NLM users */
};
/*
struct nlm_block * a_block;
unsigned int a_retries; /* Retry count */
u8 a_owner[NLMCLNT_OHSIZE];
+ void * a_callback_data; /* sent to nlmclnt_operations callbacks */
};
/*
* Flags available for kernel_param
*
* UNSAFE - the parameter is dangerous and setting it will taint the kernel
+ * HWPARAM - Hardware param not permitted in lockdown mode
*/
enum {
- KERNEL_PARAM_FL_UNSAFE = (1 << 0)
+ KERNEL_PARAM_FL_UNSAFE = (1 << 0),
+ KERNEL_PARAM_FL_HWPARAM = (1 << 1),
};
struct kernel_param {
perm, -1, 0); \
__MODULE_PARM_TYPE(name, "array of " #type)
+enum hwparam_type {
+ hwparam_ioport, /* Module parameter configures an I/O port */
+ hwparam_iomem, /* Module parameter configures an I/O mem address */
+ hwparam_ioport_or_iomem, /* Module parameter could be either, depending on other option */
+ hwparam_irq, /* Module parameter configures an I/O port */
+ hwparam_dma, /* Module parameter configures a DMA channel */
+ hwparam_dma_addr, /* Module parameter configures a DMA buffer address */
+ hwparam_other, /* Module parameter configures some other value */
+};
+
+/**
+ * module_param_hw_named - A parameter representing a hw parameters
+ * @name: a valid C identifier which is the parameter name.
+ * @value: the actual lvalue to alter.
+ * @type: the type of the parameter
+ * @hwtype: what the value represents (enum hwparam_type)
+ * @perm: visibility in sysfs.
+ *
+ * Usually it's a good idea to have variable names and user-exposed names the
+ * same, but that's harder if the variable must be non-static or is inside a
+ * structure. This allows exposure under a different name.
+ */
+#define module_param_hw_named(name, value, type, hwtype, perm) \
+ param_check_##type(name, &(value)); \
+ __module_param_call(MODULE_PARAM_PREFIX, name, \
+ ¶m_ops_##type, &value, \
+ perm, -1, \
+ KERNEL_PARAM_FL_HWPARAM | (hwparam_##hwtype & 0)); \
+ __MODULE_PARM_TYPE(name, #type)
+
+#define module_param_hw(name, type, hwtype, perm) \
+ module_param_hw_named(name, name, type, hwtype, perm)
+
+/**
+ * module_param_hw_array - A parameter representing an array of hw parameters
+ * @name: the name of the array variable
+ * @type: the type, as per module_param()
+ * @hwtype: what the value represents (enum hwparam_type)
+ * @nump: optional pointer filled in with the number written
+ * @perm: visibility in sysfs
+ *
+ * Input and output are as comma-separated values. Commas inside values
+ * don't work properly (eg. an array of charp).
+ *
+ * ARRAY_SIZE(@name) is used to determine the number of elements in the
+ * array, so the definition must be visible.
+ */
+#define module_param_hw_array(name, type, hwtype, nump, perm) \
+ param_check_##type(name, &(name)[0]); \
+ static const struct kparam_array __param_arr_##name \
+ = { .max = ARRAY_SIZE(name), .num = nump, \
+ .ops = ¶m_ops_##type, \
+ .elemsize = sizeof(name[0]), .elem = name }; \
+ __module_param_call(MODULE_PARAM_PREFIX, name, \
+ ¶m_array_ops, \
+ .arr = &__param_arr_##name, \
+ perm, -1, \
+ KERNEL_PARAM_FL_HWPARAM | (hwparam_##hwtype & 0)); \
+ __MODULE_PARM_TYPE(name, "array of " #type)
+
+
extern const struct kernel_param_ops param_array_ops;
extern const struct kernel_param_ops param_ops_string;
static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd)
{
- return mtd->dev.of_node;
+ return dev_of_node(&mtd->dev);
}
static inline int mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops)
*/
} __packed;
-struct nand_onfi_vendor_micron {
- u8 two_plane_read;
- u8 read_cache;
- u8 read_unique_id;
- u8 dq_imped;
- u8 dq_imped_num_settings;
- u8 dq_imped_feat_addr;
- u8 rb_pulldown_strength;
- u8 rb_pulldown_strength_feat_addr;
- u8 rb_pulldown_strength_num_settings;
- u8 otp_mode;
- u8 otp_page_start;
- u8 otp_data_prot_addr;
- u8 otp_num_pages;
- u8 otp_feat_addr;
- u8 read_retry_options;
- u8 reserved[72];
- u8 param_revision;
-} __packed;
-
struct jedec_ecc_info {
u8 ecc_bits;
u8 codeword_size;
__le16 crc;
} __packed;
+/**
+ * struct nand_id - NAND id structure
+ * @data: buffer containing the id bytes. Currently 8 bytes large, but can
+ * be extended if required.
+ * @len: ID length.
+ */
+struct nand_id {
+ u8 data[8];
+ int len;
+};
+
/**
* struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices
* @lock: protection lock
* out-of-band data).
* @read_page: function to read a page according to the ECC generator
* requirements; returns maximum number of bitflips corrected in
- * any single ECC step, 0 if bitflips uncorrectable, -EIO hw error
+ * any single ECC step, -EIO hw error
* @read_subpage: function to read parts of the page covered by ECC;
* returns same as read_page()
* @write_subpage: function to write parts of the page covered by ECC.
return &conf->timings.sdr;
}
+/**
+ * struct nand_manufacturer_ops - NAND Manufacturer operations
+ * @detect: detect the NAND memory organization and capabilities
+ * @init: initialize all vendor specific fields (like the ->read_retry()
+ * implementation) if any.
+ * @cleanup: the ->init() function may have allocated resources, ->cleanup()
+ * is here to let vendor specific code release those resources.
+ */
+struct nand_manufacturer_ops {
+ void (*detect)(struct nand_chip *chip);
+ int (*init)(struct nand_chip *chip);
+ void (*cleanup)(struct nand_chip *chip);
+};
+
/**
* struct nand_chip - NAND Private Flash Chip Data
* @mtd: MTD device registered to the MTD framework
* setting the read-retry mode. Mostly needed for MLC NAND.
* @ecc: [BOARDSPECIFIC] ECC control structure
* @buffers: buffer structure for read/write
+ * @buf_align: minimum buffer alignment required by a platform
* @hwcontrol: platform-specific hardware control structure
* @erase: [REPLACEABLE] erase function
* @scan_bbt: [REPLACEABLE] function to scan bad block table
* @pagebuf_bitflips: [INTERN] holds the bitflip count for the page which is
* currently in data_buf.
* @subpagesize: [INTERN] holds the subpagesize
+ * @id: [INTERN] holds NAND ID
* @onfi_version: [INTERN] holds the chip ONFI version (BCD encoded),
* non 0 if ONFI supported.
* @jedec_version: [INTERN] holds the chip JEDEC version (BCD encoded),
* @errstat: [OPTIONAL] hardware specific function to perform
* additional error status checks (determine if errors are
* correctable).
- * @write_page: [REPLACEABLE] High-level page write function
+ * @manufacturer: [INTERN] Contains manufacturer information
*/
struct nand_chip {
int (*scan_bbt)(struct mtd_info *mtd);
int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state,
int status, int page);
- int (*write_page)(struct mtd_info *mtd, struct nand_chip *chip,
- uint32_t offset, int data_len, const uint8_t *buf,
- int oob_required, int page, int cached, int raw);
int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip,
int feature_addr, uint8_t *subfeature_para);
int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip,
int badblockpos;
int badblockbits;
+ struct nand_id id;
int onfi_version;
int jedec_version;
union {
struct nand_ecc_ctrl ecc;
struct nand_buffers *buffers;
+ unsigned long buf_align;
struct nand_hw_control hwcontrol;
uint8_t *bbt;
struct nand_bbt_descr *badblock_pattern;
void *priv;
+
+ struct {
+ const struct nand_manufacturer *desc;
+ void *priv;
+ } manufacturer;
};
extern const struct mtd_ooblayout_ops nand_ooblayout_sp_ops;
chip->priv = priv;
}
+static inline void nand_set_manufacturer_data(struct nand_chip *chip,
+ void *priv)
+{
+ chip->manufacturer.priv = priv;
+}
+
+static inline void *nand_get_manufacturer_data(struct nand_chip *chip)
+{
+ return chip->manufacturer.priv;
+}
+
/*
* NAND Flash Manufacturer ID Codes
*/
};
/**
- * struct nand_manufacturers - NAND Flash Manufacturer ID Structure
+ * struct nand_manufacturer - NAND Flash Manufacturer structure
* @name: Manufacturer name
* @id: manufacturer ID code of device.
+ * @ops: manufacturer operations
*/
-struct nand_manufacturers {
+struct nand_manufacturer {
int id;
char *name;
+ const struct nand_manufacturer_ops *ops;
};
+const struct nand_manufacturer *nand_get_manufacturer(u8 id);
+
+static inline const char *
+nand_manufacturer_name(const struct nand_manufacturer *manufacturer)
+{
+ return manufacturer ? manufacturer->name : "Unknown";
+}
+
extern struct nand_flash_dev nand_flash_ids[];
-extern struct nand_manufacturers nand_manuf_ids[];
+
+extern const struct nand_manufacturer_ops toshiba_nand_manuf_ops;
+extern const struct nand_manufacturer_ops samsung_nand_manuf_ops;
+extern const struct nand_manufacturer_ops hynix_nand_manuf_ops;
+extern const struct nand_manufacturer_ops micron_nand_manuf_ops;
+extern const struct nand_manufacturer_ops amd_nand_manuf_ops;
+extern const struct nand_manufacturer_ops macronix_nand_manuf_ops;
int nand_default_bbt(struct mtd_info *mtd);
int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs);
/* Free resources held by the NAND device */
void nand_cleanup(struct nand_chip *chip);
+/* Default extended ID decoding function */
+void nand_decode_ext_id(struct nand_chip *chip);
#endif /* __LINUX_MTD_NAND_H */
#define NFS_CONTEXT_ERROR_WRITE (0)
#define NFS_CONTEXT_RESEND_WRITES (1)
#define NFS_CONTEXT_BAD (2)
+#define NFS_CONTEXT_UNLOCK (3)
int error;
struct list_head list;
*/
extern int nfs_sync_inode(struct inode *inode);
extern int nfs_wb_all(struct inode *inode);
-extern int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder);
+extern int nfs_wb_page(struct inode *inode, struct page *page);
extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
extern int nfs_commit_inode(struct inode *, int);
-extern struct nfs_commit_data *nfs_commitdata_alloc(void);
+extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail);
extern void nfs_commit_free(struct nfs_commit_data *data);
-static inline int
-nfs_wb_launder_page(struct inode *inode, struct page *page)
-{
- return nfs_wb_single_page(inode, page, true);
-}
-
-static inline int
-nfs_wb_page(struct inode *inode, struct page *page)
-{
- return nfs_wb_single_page(inode, page, false);
-}
-
static inline int
nfs_have_writebacks(struct inode *inode)
{
u32 mountd_version;
unsigned short mountd_port;
unsigned short mountd_protocol;
+ struct rpc_wait_queue uoc_rpcwaitq;
};
/* Server capabilities */
};
struct nfs_rw_ops {
- const fmode_t rw_mode;
struct nfs_pgio_header *(*rw_alloc_header)(void);
void (*rw_free_header)(struct nfs_pgio_header *);
int (*rw_done)(struct rpc_task *, struct nfs_pgio_header *,
const struct nfs_pgio_completion_ops *compl_ops,
const struct nfs_rw_ops *rw_ops,
size_t bsize,
- int how);
+ int how,
+ gfp_t gfp_flags);
extern int nfs_pageio_add_request(struct nfs_pageio_descriptor *,
struct nfs_page *);
extern int nfs_pageio_resend(struct nfs_pageio_descriptor *,
extern void nfs_page_group_lock_wait(struct nfs_page *);
extern void nfs_page_group_unlock(struct nfs_page *);
extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
+extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);
/*
* Lock the page of an asynchronous request
struct nfs42_write_res write_res;
bool consecutive;
bool synchronous;
+ struct nfs_commitres commit_res;
};
struct nfs42_seek_args {
struct list_head pages;
struct nfs_page *req;
struct nfs_writeverf verf; /* Used for writes */
+ fmode_t rw_mode;
struct pnfs_layout_segment *lseg;
loff_t io_start;
const struct rpc_call_ops *mds_ops;
const struct inode_operations *dir_inode_ops;
const struct inode_operations *file_inode_ops;
const struct file_operations *file_ops;
+ const struct nlmclnt_operations *nlmclnt_ops;
int (*getroot) (struct nfs_server *, struct nfs_fh *,
struct nfs_fsinfo *);
return of_node_get(cpu_dev->of_node);
}
-void of_dma_configure(struct device *dev, struct device_node *np);
+int of_dma_configure(struct device *dev, struct device_node *np);
+void of_dma_deconfigure(struct device *dev);
#else /* CONFIG_OF */
static inline int of_driver_match_device(struct device *dev,
{
return NULL;
}
-static inline void of_dma_configure(struct device *dev, struct device_node *np)
+
+static inline int of_dma_configure(struct device *dev, struct device_node *np)
+{
+ return 0;
+}
+static inline void of_dma_deconfigure(struct device *dev)
{}
#endif /* CONFIG_OF */
#include <linux/platform_device.h>
-#define MMU_REG_SIZE 256
-
-/**
- * struct iommu_arch_data - omap iommu private data
- * @name: name of the iommu device
- * @iommu_dev: handle of the iommu device
- *
- * This is an omap iommu private data object, which binds an iommu user
- * to its iommu device. This object should be placed at the iommu user's
- * dev_archdata so generic IOMMU API can be used without having to
- * utilize omap-specific plumbing anymore.
- */
-struct omap_iommu_arch_data {
- const char *name;
- struct omap_iommu *iommu_dev;
-};
-
struct iommu_platform_data {
- const char *name;
const char *reset_name;
- int nr_tlb_entries;
-
int (*assert_reset)(struct platform_device *pdev, const char *name);
int (*deassert_reset)(struct platform_device *pdev, const char *name);
};
struct imx_fb_videomode {
struct fb_videomode mode;
u32 pcr;
+ bool aus_mode;
unsigned char bpp;
};
extern void pm_stay_awake(struct device *dev);
extern void __pm_relax(struct wakeup_source *ws);
extern void pm_relax(struct device *dev);
-extern void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec);
-extern void pm_wakeup_event(struct device *dev, unsigned int msec);
+extern void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard);
+extern void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard);
#else /* !CONFIG_PM_SLEEP */
static inline void pm_relax(struct device *dev) {}
-static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec) {}
+static inline void pm_wakeup_ws_event(struct wakeup_source *ws,
+ unsigned int msec, bool hard) {}
-static inline void pm_wakeup_event(struct device *dev, unsigned int msec) {}
+static inline void pm_wakeup_dev_event(struct device *dev, unsigned int msec,
+ bool hard) {}
#endif /* !CONFIG_PM_SLEEP */
wakeup_source_drop(ws);
}
+static inline void __pm_wakeup_event(struct wakeup_source *ws, unsigned int msec)
+{
+ return pm_wakeup_ws_event(ws, msec, false);
+}
+
+static inline void pm_wakeup_event(struct device *dev, unsigned int msec)
+{
+ return pm_wakeup_dev_event(dev, msec, false);
+}
+
+static inline void pm_wakeup_hard_event(struct device *dev)
+{
+ return pm_wakeup_dev_event(dev, 0, true);
+}
+
#endif /* _LINUX_PM_WAKEUP_H */
struct ptr_ring {
int producer ____cacheline_aligned_in_smp;
spinlock_t producer_lock;
- int consumer ____cacheline_aligned_in_smp;
+ int consumer_head ____cacheline_aligned_in_smp; /* next valid entry */
+ int consumer_tail; /* next entry to invalidate */
spinlock_t consumer_lock;
/* Shared consumer/producer data */
/* Read-only by both the producer and the consumer */
int size ____cacheline_aligned_in_smp; /* max entries in queue */
+ int batch; /* number of entries to consume in a batch */
void **queue;
};
static inline void *__ptr_ring_peek(struct ptr_ring *r)
{
if (likely(r->size))
- return r->queue[r->consumer];
+ return r->queue[r->consumer_head];
return NULL;
}
/* Must only be called after __ptr_ring_peek returned !NULL */
static inline void __ptr_ring_discard_one(struct ptr_ring *r)
{
- r->queue[r->consumer++] = NULL;
- if (unlikely(r->consumer >= r->size))
- r->consumer = 0;
+ /* Fundamentally, what we want to do is update consumer
+ * index and zero out the entry so producer can reuse it.
+ * Doing it naively at each consume would be as simple as:
+ * r->queue[r->consumer++] = NULL;
+ * if (unlikely(r->consumer >= r->size))
+ * r->consumer = 0;
+ * but that is suboptimal when the ring is full as producer is writing
+ * out new entries in the same cache line. Defer these updates until a
+ * batch of entries has been consumed.
+ */
+ int head = r->consumer_head++;
+
+ /* Once we have processed enough entries invalidate them in
+ * the ring all at once so producer can reuse their space in the ring.
+ * We also do this when we reach end of the ring - not mandatory
+ * but helps keep the implementation simple.
+ */
+ if (unlikely(r->consumer_head - r->consumer_tail >= r->batch ||
+ r->consumer_head >= r->size)) {
+ /* Zero out entries in the reverse order: this way we touch the
+ * cache line that producer might currently be reading the last;
+ * producer won't make progress and touch other cache lines
+ * besides the first one until we write out all entries.
+ */
+ while (likely(head >= r->consumer_tail))
+ r->queue[head--] = NULL;
+ r->consumer_tail = r->consumer_head;
+ }
+ if (unlikely(r->consumer_head >= r->size)) {
+ r->consumer_head = 0;
+ r->consumer_tail = 0;
+ }
}
static inline void *__ptr_ring_consume(struct ptr_ring *r)
return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
}
+static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
+{
+ r->size = size;
+ r->batch = SMP_CACHE_BYTES * 2 / sizeof(*(r->queue));
+ /* We need to set batch at least to 1 to make logic
+ * in __ptr_ring_discard_one work correctly.
+ * Batching too much (because ring is small) would cause a lot of
+ * burstiness. Needs tuning, for now disable batching.
+ */
+ if (r->batch > r->size / 2 || !r->batch)
+ r->batch = 1;
+}
+
static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
{
r->queue = __ptr_ring_init_queue_alloc(size, gfp);
if (!r->queue)
return -ENOMEM;
- r->size = size;
- r->producer = r->consumer = 0;
+ __ptr_ring_set_size(r, size);
+ r->producer = r->consumer_head = r->consumer_tail = 0;
spin_lock_init(&r->producer_lock);
spin_lock_init(&r->consumer_lock);
else if (destroy)
destroy(ptr);
- r->size = size;
+ __ptr_ring_set_size(r, size);
r->producer = producer;
- r->consumer = 0;
+ r->consumer_head = 0;
+ r->consumer_tail = 0;
old = r->queue;
r->queue = queue;
--- /dev/null
+/*
+ * RCU node combining tree definitions. These are used to compute
+ * global attributes while avoiding common-case global contention. A key
+ * property that these computations rely on is a tournament-style approach
+ * where only one of the tasks contending a lower level in the tree need
+ * advance to the next higher level. If properly configured, this allows
+ * unlimited scalability while maintaining a constant level of contention
+ * on the root node.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2017
+ *
+ * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifndef __LINUX_RCU_NODE_TREE_H
+#define __LINUX_RCU_NODE_TREE_H
+
+/*
+ * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
+ * CONFIG_RCU_FANOUT_LEAF.
+ * In theory, it should be possible to add more levels straightforwardly.
+ * In practice, this did work well going from three levels to four.
+ * Of course, your mileage may vary.
+ */
+
+#ifdef CONFIG_RCU_FANOUT
+#define RCU_FANOUT CONFIG_RCU_FANOUT
+#else /* #ifdef CONFIG_RCU_FANOUT */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT 64
+# else
+# define RCU_FANOUT 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT */
+
+#ifdef CONFIG_RCU_FANOUT_LEAF
+#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
+#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
+#define RCU_FANOUT_LEAF 16
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
+
+#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
+#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
+#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
+
+#if NR_CPUS <= RCU_FANOUT_1
+# define RCU_NUM_LVLS 1
+# define NUM_RCU_LVL_0 1
+# define NUM_RCU_NODES NUM_RCU_LVL_0
+# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
+# define RCU_NODE_NAME_INIT { "rcu_node_0" }
+# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
+#elif NR_CPUS <= RCU_FANOUT_2
+# define RCU_NUM_LVLS 2
+# define NUM_RCU_LVL_0 1
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
+# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
+# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
+# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
+#elif NR_CPUS <= RCU_FANOUT_3
+# define RCU_NUM_LVLS 3
+# define NUM_RCU_LVL_0 1
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
+# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
+# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
+# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
+#elif NR_CPUS <= RCU_FANOUT_4
+# define RCU_NUM_LVLS 4
+# define NUM_RCU_LVL_0 1
+# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
+# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
+# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
+# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
+# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
+# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
+#else
+# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
+#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
+
+#endif /* __LINUX_RCU_NODE_TREE_H */
--- /dev/null
+/*
+ * RCU segmented callback lists
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2017
+ *
+ * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#ifndef __INCLUDE_LINUX_RCU_SEGCBLIST_H
+#define __INCLUDE_LINUX_RCU_SEGCBLIST_H
+
+/* Simple unsegmented callback lists. */
+struct rcu_cblist {
+ struct rcu_head *head;
+ struct rcu_head **tail;
+ long len;
+ long len_lazy;
+};
+
+#define RCU_CBLIST_INITIALIZER(n) { .head = NULL, .tail = &n.head }
+
+/* Complicated segmented callback lists. ;-) */
+
+/*
+ * Index values for segments in rcu_segcblist structure.
+ *
+ * The segments are as follows:
+ *
+ * [head, *tails[RCU_DONE_TAIL]):
+ * Callbacks whose grace period has elapsed, and thus can be invoked.
+ * [*tails[RCU_DONE_TAIL], *tails[RCU_WAIT_TAIL]):
+ * Callbacks waiting for the current GP from the current CPU's viewpoint.
+ * [*tails[RCU_WAIT_TAIL], *tails[RCU_NEXT_READY_TAIL]):
+ * Callbacks that arrived before the next GP started, again from
+ * the current CPU's viewpoint. These can be handled by the next GP.
+ * [*tails[RCU_NEXT_READY_TAIL], *tails[RCU_NEXT_TAIL]):
+ * Callbacks that might have arrived after the next GP started.
+ * There is some uncertainty as to when a given GP starts and
+ * ends, but a CPU knows the exact times if it is the one starting
+ * or ending the GP. Other CPUs know that the previous GP ends
+ * before the next one starts.
+ *
+ * Note that RCU_WAIT_TAIL cannot be empty unless RCU_NEXT_READY_TAIL is also
+ * empty.
+ *
+ * The ->gp_seq[] array contains the grace-period number at which the
+ * corresponding segment of callbacks will be ready to invoke. A given
+ * element of this array is meaningful only when the corresponding segment
+ * is non-empty, and it is never valid for RCU_DONE_TAIL (whose callbacks
+ * are already ready to invoke) or for RCU_NEXT_TAIL (whose callbacks have
+ * not yet been assigned a grace-period number).
+ */
+#define RCU_DONE_TAIL 0 /* Also RCU_WAIT head. */
+#define RCU_WAIT_TAIL 1 /* Also RCU_NEXT_READY head. */
+#define RCU_NEXT_READY_TAIL 2 /* Also RCU_NEXT head. */
+#define RCU_NEXT_TAIL 3
+#define RCU_CBLIST_NSEGS 4
+
+struct rcu_segcblist {
+ struct rcu_head *head;
+ struct rcu_head **tails[RCU_CBLIST_NSEGS];
+ unsigned long gp_seq[RCU_CBLIST_NSEGS];
+ long len;
+ long len_lazy;
+};
+
+#define RCU_SEGCBLIST_INITIALIZER(n) \
+{ \
+ .head = NULL, \
+ .tails[RCU_DONE_TAIL] = &n.head, \
+ .tails[RCU_WAIT_TAIL] = &n.head, \
+ .tails[RCU_NEXT_READY_TAIL] = &n.head, \
+ .tails[RCU_NEXT_TAIL] = &n.head, \
+}
+
+#endif /* __INCLUDE_LINUX_RCU_SEGCBLIST_H */
{
struct hlist_node *i, *last = NULL;
- for (i = hlist_first_rcu(h); i; i = hlist_next_rcu(i))
+ /* Note: write side code, so rcu accessors are not needed. */
+ for (i = h->first; i; i = i->next)
last = i;
if (last) {
#ifdef CONFIG_TASKS_RCU
#define TASKS_RCU(x) x
extern struct srcu_struct tasks_rcu_exit_srcu;
-#define rcu_note_voluntary_context_switch(t) \
+#define rcu_note_voluntary_context_switch_lite(t) \
do { \
- rcu_all_qs(); \
if (READ_ONCE((t)->rcu_tasks_holdout)) \
WRITE_ONCE((t)->rcu_tasks_holdout, false); \
} while (0)
+#define rcu_note_voluntary_context_switch(t) \
+ do { \
+ rcu_all_qs(); \
+ rcu_note_voluntary_context_switch_lite(t); \
+ } while (0)
#else /* #ifdef CONFIG_TASKS_RCU */
#define TASKS_RCU(x) do { } while (0)
-#define rcu_note_voluntary_context_switch(t) rcu_all_qs()
+#define rcu_note_voluntary_context_switch_lite(t) do { } while (0)
+#define rcu_note_voluntary_context_switch(t) rcu_all_qs()
#endif /* #else #ifdef CONFIG_TASKS_RCU */
/**
* if the UNLOCK and LOCK are executed by the same CPU or if the
* UNLOCK and LOCK operate on the same lock variable.
*/
-#ifdef CONFIG_PPC
+#ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE
#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */
-#else /* #ifdef CONFIG_PPC */
+#else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
#define smp_mb__after_unlock_lock() do { } while (0)
-#endif /* #else #ifdef CONFIG_PPC */
+#endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */
#endif /* __LINUX_RCUPDATE_H */
return 0;
}
+static inline bool rcu_eqs_special_set(int cpu)
+{
+ return false; /* Never flag non-existent other CPUs! */
+}
+
static inline unsigned long get_state_synchronize_rcu(void)
{
return 0;
call_rcu(head, func);
}
-static inline void rcu_note_context_switch(void)
-{
- rcu_sched_qs();
-}
+#define rcu_note_context_switch(preempt) \
+ do { \
+ rcu_sched_qs(); \
+ rcu_note_voluntary_context_switch_lite(current); \
+ } while (0)
/*
* Take advantage of the fact that there is only one CPU, which
{
}
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
extern int rcu_scheduler_active __read_mostly;
void rcu_scheduler_starting(void);
-#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#else /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
static inline void rcu_scheduler_starting(void)
{
}
-#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* #else #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
#endif /* #else defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
+static inline void rcu_request_urgent_qs_task(struct task_struct *t)
+{
+}
+
static inline void rcu_all_qs(void)
{
barrier(); /* Avoid RCU read-side critical sections leaking across. */
#ifndef __LINUX_RCUTREE_H
#define __LINUX_RCUTREE_H
-void rcu_note_context_switch(void);
+void rcu_note_context_switch(bool preempt);
int rcu_needs_cpu(u64 basem, u64 *nextevt);
void rcu_cpu_stall_reset(void);
*/
static inline void rcu_virt_note_context_switch(int cpu)
{
- rcu_note_context_switch();
+ rcu_note_context_switch(false);
}
void synchronize_rcu_bh(void);
extern int rcu_scheduler_active __read_mostly;
bool rcu_is_watching(void);
+void rcu_request_urgent_qs_task(struct task_struct *t);
void rcu_all_qs(void);
#define SLAB_STORE_USER 0x00010000UL /* DEBUG: Store the last owner for bug hunting */
#define SLAB_PANIC 0x00040000UL /* Panic if kmem_cache_create() fails */
/*
- * SLAB_DESTROY_BY_RCU - **WARNING** READ THIS!
+ * SLAB_TYPESAFE_BY_RCU - **WARNING** READ THIS!
*
* This delays freeing the SLAB page by a grace period, it does _NOT_
* delay object freeing. This means that if you do kmem_cache_free()
*
* rcu_read_lock before reading the address, then rcu_read_unlock after
* taking the spinlock within the structure expected at that address.
+ *
+ * Note that SLAB_TYPESAFE_BY_RCU was originally named SLAB_DESTROY_BY_RCU.
*/
-#define SLAB_DESTROY_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */
+#define SLAB_TYPESAFE_BY_RCU 0x00080000UL /* Defer freeing slabs to RCU */
#define SLAB_MEM_SPREAD 0x00100000UL /* Spread some memory over cpuset */
#define SLAB_TRACE 0x00200000UL /* Trace allocations and frees */
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
- * Documentation/RCU/ *.txt
+ * Documentation/RCU/ *.txt
*
*/
#include <linux/mutex.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
+#include <linux/rcu_segcblist.h>
-struct srcu_array {
- unsigned long lock_count[2];
- unsigned long unlock_count[2];
-};
-
-struct rcu_batch {
- struct rcu_head *head, **tail;
-};
-
-#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
-
-struct srcu_struct {
- unsigned long completed;
- struct srcu_array __percpu *per_cpu_ref;
- spinlock_t queue_lock; /* protect ->batch_queue, ->running */
- bool running;
- /* callbacks just queued */
- struct rcu_batch batch_queue;
- /* callbacks try to do the first check_zero */
- struct rcu_batch batch_check0;
- /* callbacks done with the first check_zero and the flip */
- struct rcu_batch batch_check1;
- struct rcu_batch batch_done;
- struct delayed_work work;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
- struct lockdep_map dep_map;
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-};
+struct srcu_struct;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
#define __SRCU_DEP_MAP_INIT(srcu_name)
#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
-void process_srcu(struct work_struct *work);
-
-#define __SRCU_STRUCT_INIT(name) \
- { \
- .completed = -300, \
- .per_cpu_ref = &name##_srcu_array, \
- .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \
- .running = false, \
- .batch_queue = RCU_BATCH_INIT(name.batch_queue), \
- .batch_check0 = RCU_BATCH_INIT(name.batch_check0), \
- .batch_check1 = RCU_BATCH_INIT(name.batch_check1), \
- .batch_done = RCU_BATCH_INIT(name.batch_done), \
- .work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
- __SRCU_DEP_MAP_INIT(name) \
- }
-
-/*
- * Define and initialize a srcu struct at build time.
- * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
- *
- * Note that although DEFINE_STATIC_SRCU() hides the name from other
- * files, the per-CPU variable rules nevertheless require that the
- * chosen name be globally unique. These rules also prohibit use of
- * DEFINE_STATIC_SRCU() within a function. If these rules are too
- * restrictive, declare the srcu_struct manually. For example, in
- * each file:
- *
- * static struct srcu_struct my_srcu;
- *
- * Then, before the first use of each my_srcu, manually initialize it:
- *
- * init_srcu_struct(&my_srcu);
- *
- * See include/linux/percpu-defs.h for the rules on per-CPU variables.
- */
-#define __DEFINE_SRCU(name, is_static) \
- static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
- is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
-#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
-#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
+#ifdef CONFIG_TINY_SRCU
+#include <linux/srcutiny.h>
+#elif defined(CONFIG_TREE_SRCU)
+#include <linux/srcutree.h>
+#elif defined(CONFIG_CLASSIC_SRCU)
+#include <linux/srcuclassic.h>
+#else
+#error "Unknown SRCU implementation specified to kernel configuration"
+#endif
/**
* call_srcu() - Queue a callback for invocation after an SRCU grace period
int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp);
void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp);
void synchronize_srcu(struct srcu_struct *sp);
-void synchronize_srcu_expedited(struct srcu_struct *sp);
-unsigned long srcu_batches_completed(struct srcu_struct *sp);
-void srcu_barrier(struct srcu_struct *sp);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
--- /dev/null
+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ * classic v4.11 variant.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#ifndef _LINUX_SRCU_CLASSIC_H
+#define _LINUX_SRCU_CLASSIC_H
+
+struct srcu_array {
+ unsigned long lock_count[2];
+ unsigned long unlock_count[2];
+};
+
+struct rcu_batch {
+ struct rcu_head *head, **tail;
+};
+
+#define RCU_BATCH_INIT(name) { NULL, &(name.head) }
+
+struct srcu_struct {
+ unsigned long completed;
+ struct srcu_array __percpu *per_cpu_ref;
+ spinlock_t queue_lock; /* protect ->batch_queue, ->running */
+ bool running;
+ /* callbacks just queued */
+ struct rcu_batch batch_queue;
+ /* callbacks try to do the first check_zero */
+ struct rcu_batch batch_check0;
+ /* callbacks done with the first check_zero and the flip */
+ struct rcu_batch batch_check1;
+ struct rcu_batch batch_done;
+ struct delayed_work work;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+};
+
+void process_srcu(struct work_struct *work);
+
+#define __SRCU_STRUCT_INIT(name) \
+ { \
+ .completed = -300, \
+ .per_cpu_ref = &name##_srcu_array, \
+ .queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock), \
+ .running = false, \
+ .batch_queue = RCU_BATCH_INIT(name.batch_queue), \
+ .batch_check0 = RCU_BATCH_INIT(name.batch_check0), \
+ .batch_check1 = RCU_BATCH_INIT(name.batch_check1), \
+ .batch_done = RCU_BATCH_INIT(name.batch_done), \
+ .work = __DELAYED_WORK_INITIALIZER(name.work, process_srcu, 0),\
+ __SRCU_DEP_MAP_INIT(name) \
+ }
+
+/*
+ * Define and initialize a srcu struct at build time.
+ * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ *
+ * Note that although DEFINE_STATIC_SRCU() hides the name from other
+ * files, the per-CPU variable rules nevertheless require that the
+ * chosen name be globally unique. These rules also prohibit use of
+ * DEFINE_STATIC_SRCU() within a function. If these rules are too
+ * restrictive, declare the srcu_struct manually. For example, in
+ * each file:
+ *
+ * static struct srcu_struct my_srcu;
+ *
+ * Then, before the first use of each my_srcu, manually initialize it:
+ *
+ * init_srcu_struct(&my_srcu);
+ *
+ * See include/linux/percpu-defs.h for the rules on per-CPU variables.
+ */
+#define __DEFINE_SRCU(name, is_static) \
+ static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
+ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
+#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
+
+void synchronize_srcu_expedited(struct srcu_struct *sp);
+void srcu_barrier(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
+
+static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
+ struct srcu_struct *sp, int *flags,
+ unsigned long *gpnum,
+ unsigned long *completed)
+{
+ if (test_type != SRCU_FLAVOR)
+ return;
+ *flags = 0;
+ *completed = sp->completed;
+ *gpnum = *completed;
+ if (sp->batch_queue.head || sp->batch_check0.head || sp->batch_check0.head)
+ (*gpnum)++;
+}
+
+#endif
--- /dev/null
+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ * tiny variant.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#ifndef _LINUX_SRCU_TINY_H
+#define _LINUX_SRCU_TINY_H
+
+#include <linux/swait.h>
+
+struct srcu_struct {
+ int srcu_lock_nesting[2]; /* srcu_read_lock() nesting depth. */
+ struct swait_queue_head srcu_wq;
+ /* Last srcu_read_unlock() wakes GP. */
+ unsigned long srcu_gp_seq; /* GP seq # for callback tagging. */
+ struct rcu_segcblist srcu_cblist;
+ /* Pending SRCU callbacks. */
+ int srcu_idx; /* Current reader array element. */
+ bool srcu_gp_running; /* GP workqueue running? */
+ bool srcu_gp_waiting; /* GP waiting for readers? */
+ struct work_struct srcu_work; /* For driving grace periods. */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+};
+
+void srcu_drive_gp(struct work_struct *wp);
+
+#define __SRCU_STRUCT_INIT(name) \
+{ \
+ .srcu_wq = __SWAIT_QUEUE_HEAD_INITIALIZER(name.srcu_wq), \
+ .srcu_cblist = RCU_SEGCBLIST_INITIALIZER(name.srcu_cblist), \
+ .srcu_work = __WORK_INITIALIZER(name.srcu_work, srcu_drive_gp), \
+ __SRCU_DEP_MAP_INIT(name) \
+}
+
+/*
+ * This odd _STATIC_ arrangement is needed for API compatibility with
+ * Tree SRCU, which needs some per-CPU data.
+ */
+#define DEFINE_SRCU(name) \
+ struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+#define DEFINE_STATIC_SRCU(name) \
+ static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+
+void synchronize_srcu(struct srcu_struct *sp);
+
+static inline void synchronize_srcu_expedited(struct srcu_struct *sp)
+{
+ synchronize_srcu(sp);
+}
+
+static inline void srcu_barrier(struct srcu_struct *sp)
+{
+ synchronize_srcu(sp);
+}
+
+static inline unsigned long srcu_batches_completed(struct srcu_struct *sp)
+{
+ return 0;
+}
+
+static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
+ struct srcu_struct *sp, int *flags,
+ unsigned long *gpnum,
+ unsigned long *completed)
+{
+ if (test_type != SRCU_FLAVOR)
+ return;
+ *flags = 0;
+ *completed = sp->srcu_gp_seq;
+ *gpnum = *completed;
+}
+
+#endif
--- /dev/null
+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ * tree variant.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#ifndef _LINUX_SRCU_TREE_H
+#define _LINUX_SRCU_TREE_H
+
+#include <linux/rcu_node_tree.h>
+#include <linux/completion.h>
+
+struct srcu_node;
+struct srcu_struct;
+
+/*
+ * Per-CPU structure feeding into leaf srcu_node, similar in function
+ * to rcu_node.
+ */
+struct srcu_data {
+ /* Read-side state. */
+ unsigned long srcu_lock_count[2]; /* Locks per CPU. */
+ unsigned long srcu_unlock_count[2]; /* Unlocks per CPU. */
+
+ /* Update-side state. */
+ spinlock_t lock ____cacheline_internodealigned_in_smp;
+ struct rcu_segcblist srcu_cblist; /* List of callbacks.*/
+ unsigned long srcu_gp_seq_needed; /* Furthest future GP needed. */
+ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */
+ bool srcu_cblist_invoking; /* Invoking these CBs? */
+ struct delayed_work work; /* Context for CB invoking. */
+ struct rcu_head srcu_barrier_head; /* For srcu_barrier() use. */
+ struct srcu_node *mynode; /* Leaf srcu_node. */
+ unsigned long grpmask; /* Mask for leaf srcu_node */
+ /* ->srcu_data_have_cbs[]. */
+ int cpu;
+ struct srcu_struct *sp;
+};
+
+/*
+ * Node in SRCU combining tree, similar in function to rcu_data.
+ */
+struct srcu_node {
+ spinlock_t lock;
+ unsigned long srcu_have_cbs[4]; /* GP seq for children */
+ /* having CBs, but only */
+ /* is > ->srcu_gq_seq. */
+ unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */
+ /* have CBs for given GP? */
+ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */
+ struct srcu_node *srcu_parent; /* Next up in tree. */
+ int grplo; /* Least CPU for node. */
+ int grphi; /* Biggest CPU for node. */
+};
+
+/*
+ * Per-SRCU-domain structure, similar in function to rcu_state.
+ */
+struct srcu_struct {
+ struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */
+ struct srcu_node *level[RCU_NUM_LVLS + 1];
+ /* First node at each level. */
+ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */
+ spinlock_t gp_lock; /* protect ->srcu_cblist */
+ struct mutex srcu_gp_mutex; /* Serialize GP work. */
+ unsigned int srcu_idx; /* Current rdr array element. */
+ unsigned long srcu_gp_seq; /* Grace-period seq #. */
+ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */
+ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */
+ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */
+ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */
+ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */
+ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */
+ struct completion srcu_barrier_completion;
+ /* Awaken barrier rq at end. */
+ atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */
+ /* callback for the barrier */
+ /* operation. */
+ struct delayed_work work;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+};
+
+/* Values for state variable (bottom bits of ->srcu_gp_seq). */
+#define SRCU_STATE_IDLE 0
+#define SRCU_STATE_SCAN1 1
+#define SRCU_STATE_SCAN2 2
+
+void process_srcu(struct work_struct *work);
+
+#define __SRCU_STRUCT_INIT(name) \
+ { \
+ .sda = &name##_srcu_data, \
+ .gp_lock = __SPIN_LOCK_UNLOCKED(name.gp_lock), \
+ .srcu_gp_seq_needed = 0 - 1, \
+ __SRCU_DEP_MAP_INIT(name) \
+ }
+
+/*
+ * Define and initialize a srcu struct at build time.
+ * Do -not- call init_srcu_struct() nor cleanup_srcu_struct() on it.
+ *
+ * Note that although DEFINE_STATIC_SRCU() hides the name from other
+ * files, the per-CPU variable rules nevertheless require that the
+ * chosen name be globally unique. These rules also prohibit use of
+ * DEFINE_STATIC_SRCU() within a function. If these rules are too
+ * restrictive, declare the srcu_struct manually. For example, in
+ * each file:
+ *
+ * static struct srcu_struct my_srcu;
+ *
+ * Then, before the first use of each my_srcu, manually initialize it:
+ *
+ * init_srcu_struct(&my_srcu);
+ *
+ * See include/linux/percpu-defs.h for the rules on per-CPU variables.
+ */
+#define __DEFINE_SRCU(name, is_static) \
+ static DEFINE_PER_CPU(struct srcu_data, name##_srcu_data);\
+ is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+#define DEFINE_SRCU(name) __DEFINE_SRCU(name, /* not static */)
+#define DEFINE_STATIC_SRCU(name) __DEFINE_SRCU(name, static)
+
+void synchronize_srcu_expedited(struct srcu_struct *sp);
+void srcu_barrier(struct srcu_struct *sp);
+unsigned long srcu_batches_completed(struct srcu_struct *sp);
+
+void srcutorture_get_gp_data(enum rcutorture_type test_type,
+ struct srcu_struct *sp, int *flags,
+ unsigned long *gpnum, unsigned long *completed);
+
+#endif
#define rdma_done cpu_to_be32(RDMA_DONE)
#define rdma_error cpu_to_be32(RDMA_ERROR)
+#define err_vers cpu_to_be32(ERR_VERS)
+#define err_chunk cpu_to_be32(ERR_CHUNK)
+
/*
* Private extension to RPC-over-RDMA Version One.
* Message passed during RDMA-CM connection set-up.
{
char *cp = (char *)p;
struct kvec *vec = &rqstp->rq_arg.head[0];
- return cp >= (char*)vec->iov_base
- && cp <= (char*)vec->iov_base + vec->iov_len;
+ return cp == (char *)vec->iov_base + vec->iov_len;
}
static inline int
struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int,
struct svc_serv_ops *);
int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
+int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int);
int svc_pool_stats_open(struct svc_serv *serv, struct file *file);
void svc_destroy(struct svc_serv *);
void svc_shutdown_net(struct svc_serv *, struct net *);
#include <rdma/rdma_cm.h>
#define SVCRDMA_DEBUG
+/* Default and maximum inline threshold sizes */
+enum {
+ RPCRDMA_DEF_INLINE_THRESH = 4096,
+ RPCRDMA_MAX_INLINE_THRESH = 65536
+};
+
/* RPC/RDMA parameters and stats */
extern unsigned int svcrdma_ord;
extern unsigned int svcrdma_max_requests;
enum dma_data_direction direction;
int count;
unsigned int mapped_sges;
- struct ib_sge sge[RPCSVC_MAXPAGES];
+ struct ib_send_wr send_wr;
+ struct ib_sge sge[1 + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE];
struct page *pages[RPCSVC_MAXPAGES];
};
-/*
- * NFS_ requests are mapped on the client side by the chunk lists in
- * the RPCRDMA header. During the fetching of the RPC from the client
- * and the writing of the reply to the client, the memory in the
- * client and the memory in the server must be mapped as contiguous
- * vaddr/len for access by the hardware. These data strucures keep
- * these mappings.
- *
- * For an RDMA_WRITE, the 'sge' maps the RPC REPLY. For RDMA_READ, the
- * 'sge' in the svc_rdma_req_map maps the server side RPC reply and the
- * 'ch' field maps the read-list of the RPCRDMA header to the 'sge'
- * mapping of the reply.
- */
-struct svc_rdma_chunk_sge {
- int start; /* sge no for this chunk */
- int count; /* sge count for this chunk */
-};
struct svc_rdma_fastreg_mr {
struct ib_mr *mr;
struct scatterlist *sg;
enum dma_data_direction direction;
struct list_head frmr_list;
};
-struct svc_rdma_req_map {
- struct list_head free;
- unsigned long count;
- union {
- struct kvec sge[RPCSVC_MAXPAGES];
- struct svc_rdma_chunk_sge ch[RPCSVC_MAXPAGES];
- unsigned long lkey[RPCSVC_MAXPAGES];
- };
-};
+
#define RDMACTXT_F_LAST_CTXT 2
#define SVCRDMA_DEVCAP_FAST_REG 1 /* fast mr registration */
u32 sc_max_requests; /* Max requests */
u32 sc_max_bc_requests;/* Backward credits */
int sc_max_req_size; /* Size of each RQ WR buf */
+ u8 sc_port_num;
struct ib_pd *sc_pd;
spinlock_t sc_ctxt_lock;
struct list_head sc_ctxts;
int sc_ctxt_used;
- spinlock_t sc_map_lock;
- struct list_head sc_maps;
+ spinlock_t sc_rw_ctxt_lock;
+ struct list_head sc_rw_ctxts;
struct list_head sc_rq_dto_q;
spinlock_t sc_rq_dto_lock;
/* The default ORD value is based on two outstanding full-size writes with a
* page size of 4k, or 32k * 2 ops / 4k = 16 outstanding RDMA_READ. */
#define RPCRDMA_ORD (64/4)
-#define RPCRDMA_SQ_DEPTH_MULT 8
#define RPCRDMA_MAX_REQUESTS 32
-#define RPCRDMA_MAX_REQ_SIZE 4096
/* Typical ULP usage of BC requests is NFSv4.1 backchannel. Our
* current NFSv4.1 implementation supports one backchannel slot.
/* svc_rdma_backchannel.c */
extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
- struct rpcrdma_msg *rmsgp,
+ __be32 *rdma_resp,
struct xdr_buf *rcvbuf);
/* svc_rdma_marshal.c */
extern int svc_rdma_xdr_decode_req(struct xdr_buf *);
-extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
- struct rpcrdma_msg *,
- enum rpcrdma_errcode, __be32 *);
-extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int);
-extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int);
-extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int,
- __be32, __be64, u32);
-extern unsigned int svc_rdma_xdr_get_reply_hdr_len(__be32 *rdma_resp);
/* svc_rdma_recvfrom.c */
extern int svc_rdma_recvfrom(struct svc_rqst *);
struct svc_rdma_op_ctxt *, int *, u32 *,
u32, u32, u64, bool);
+/* svc_rdma_rw.c */
+extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
+extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
+ __be32 *wr_ch, struct xdr_buf *xdr);
+extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
+ __be32 *rp_ch, bool writelist,
+ struct xdr_buf *xdr);
+
/* svc_rdma_sendto.c */
-extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *,
- struct svc_rdma_req_map *, bool);
+extern int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma,
+ struct svc_rdma_op_ctxt *ctxt,
+ __be32 *rdma_resp, unsigned int len);
+extern int svc_rdma_post_send_wr(struct svcxprt_rdma *rdma,
+ struct svc_rdma_op_ctxt *ctxt,
+ int num_sge, u32 inv_rkey);
extern int svc_rdma_sendto(struct svc_rqst *);
-extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *,
- int);
/* svc_rdma_transport.c */
extern void svc_rdma_wc_send(struct ib_cq *, struct ib_wc *);
-extern void svc_rdma_wc_write(struct ib_cq *, struct ib_wc *);
extern void svc_rdma_wc_reg(struct ib_cq *, struct ib_wc *);
extern void svc_rdma_wc_read(struct ib_cq *, struct ib_wc *);
extern void svc_rdma_wc_inv(struct ib_cq *, struct ib_wc *);
extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt);
-extern struct svc_rdma_req_map *svc_rdma_get_req_map(struct svcxprt_rdma *);
-extern void svc_rdma_put_req_map(struct svcxprt_rdma *,
- struct svc_rdma_req_map *);
extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *);
extern void svc_rdma_put_frmr(struct svcxprt_rdma *,
struct svc_rdma_fastreg_mr *);
struct platform_freeze_ops {
int (*begin)(void);
int (*prepare)(void);
+ void (*wake)(void);
+ void (*sync)(void);
void (*restore)(void);
void (*end)(void);
};
extern bool pm_wakeup_pending(void);
extern void pm_system_wakeup(void);
-extern void pm_wakeup_clear(void);
+extern void pm_system_cancel_wakeup(void);
+extern void pm_wakeup_clear(bool reset);
extern void pm_system_irq_wakeup(unsigned int irq_number);
extern bool pm_get_wakeup_count(unsigned int *count, bool block);
extern bool pm_save_wakeup_count(unsigned int count);
static inline bool pm_wakeup_pending(void) { return false; }
static inline void pm_system_wakeup(void) {}
-static inline void pm_wakeup_clear(void) {}
+static inline void pm_wakeup_clear(bool reset) {}
static inline void pm_system_irq_wakeup(unsigned int irq_number) {}
static inline void lock_system_sleep(void) {}
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __TEE_DRV_H
+#define __TEE_DRV_H
+
+#include <linux/types.h>
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <linux/tee.h>
+
+/*
+ * The file describes the API provided by the generic TEE driver to the
+ * specific TEE driver.
+ */
+
+#define TEE_SHM_MAPPED 0x1 /* Memory mapped by the kernel */
+#define TEE_SHM_DMA_BUF 0x2 /* Memory with dma-buf handle */
+
+struct tee_device;
+struct tee_shm;
+struct tee_shm_pool;
+
+/**
+ * struct tee_context - driver specific context on file pointer data
+ * @teedev: pointer to this drivers struct tee_device
+ * @list_shm: List of shared memory object owned by this context
+ * @data: driver specific context data, managed by the driver
+ */
+struct tee_context {
+ struct tee_device *teedev;
+ struct list_head list_shm;
+ void *data;
+};
+
+struct tee_param_memref {
+ size_t shm_offs;
+ size_t size;
+ struct tee_shm *shm;
+};
+
+struct tee_param_value {
+ u64 a;
+ u64 b;
+ u64 c;
+};
+
+struct tee_param {
+ u64 attr;
+ union {
+ struct tee_param_memref memref;
+ struct tee_param_value value;
+ } u;
+};
+
+/**
+ * struct tee_driver_ops - driver operations vtable
+ * @get_version: returns version of driver
+ * @open: called when the device file is opened
+ * @release: release this open file
+ * @open_session: open a new session
+ * @close_session: close a session
+ * @invoke_func: invoke a trusted function
+ * @cancel_req: request cancel of an ongoing invoke or open
+ * @supp_revc: called for supplicant to get a command
+ * @supp_send: called for supplicant to send a response
+ */
+struct tee_driver_ops {
+ void (*get_version)(struct tee_device *teedev,
+ struct tee_ioctl_version_data *vers);
+ int (*open)(struct tee_context *ctx);
+ void (*release)(struct tee_context *ctx);
+ int (*open_session)(struct tee_context *ctx,
+ struct tee_ioctl_open_session_arg *arg,
+ struct tee_param *param);
+ int (*close_session)(struct tee_context *ctx, u32 session);
+ int (*invoke_func)(struct tee_context *ctx,
+ struct tee_ioctl_invoke_arg *arg,
+ struct tee_param *param);
+ int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session);
+ int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params,
+ struct tee_param *param);
+ int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params,
+ struct tee_param *param);
+};
+
+/**
+ * struct tee_desc - Describes the TEE driver to the subsystem
+ * @name: name of driver
+ * @ops: driver operations vtable
+ * @owner: module providing the driver
+ * @flags: Extra properties of driver, defined by TEE_DESC_* below
+ */
+#define TEE_DESC_PRIVILEGED 0x1
+struct tee_desc {
+ const char *name;
+ const struct tee_driver_ops *ops;
+ struct module *owner;
+ u32 flags;
+};
+
+/**
+ * tee_device_alloc() - Allocate a new struct tee_device instance
+ * @teedesc: Descriptor for this driver
+ * @dev: Parent device for this device
+ * @pool: Shared memory pool, NULL if not used
+ * @driver_data: Private driver data for this device
+ *
+ * Allocates a new struct tee_device instance. The device is
+ * removed by tee_device_unregister().
+ *
+ * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure
+ */
+struct tee_device *tee_device_alloc(const struct tee_desc *teedesc,
+ struct device *dev,
+ struct tee_shm_pool *pool,
+ void *driver_data);
+
+/**
+ * tee_device_register() - Registers a TEE device
+ * @teedev: Device to register
+ *
+ * tee_device_unregister() need to be called to remove the @teedev if
+ * this function fails.
+ *
+ * @returns < 0 on failure
+ */
+int tee_device_register(struct tee_device *teedev);
+
+/**
+ * tee_device_unregister() - Removes a TEE device
+ * @teedev: Device to unregister
+ *
+ * This function should be called to remove the @teedev even if
+ * tee_device_register() hasn't been called yet. Does nothing if
+ * @teedev is NULL.
+ */
+void tee_device_unregister(struct tee_device *teedev);
+
+/**
+ * struct tee_shm_pool_mem_info - holds information needed to create a shared
+ * memory pool
+ * @vaddr: Virtual address of start of pool
+ * @paddr: Physical address of start of pool
+ * @size: Size in bytes of the pool
+ */
+struct tee_shm_pool_mem_info {
+ unsigned long vaddr;
+ phys_addr_t paddr;
+ size_t size;
+};
+
+/**
+ * tee_shm_pool_alloc_res_mem() - Create a shared memory pool from reserved
+ * memory range
+ * @priv_info: Information for driver private shared memory pool
+ * @dmabuf_info: Information for dma-buf shared memory pool
+ *
+ * Start and end of pools will must be page aligned.
+ *
+ * Allocation with the flag TEE_SHM_DMA_BUF set will use the range supplied
+ * in @dmabuf, others will use the range provided by @priv.
+ *
+ * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure.
+ */
+struct tee_shm_pool *
+tee_shm_pool_alloc_res_mem(struct tee_shm_pool_mem_info *priv_info,
+ struct tee_shm_pool_mem_info *dmabuf_info);
+
+/**
+ * tee_shm_pool_free() - Free a shared memory pool
+ * @pool: The shared memory pool to free
+ *
+ * The must be no remaining shared memory allocated from this pool when
+ * this function is called.
+ */
+void tee_shm_pool_free(struct tee_shm_pool *pool);
+
+/**
+ * tee_get_drvdata() - Return driver_data pointer
+ * @returns the driver_data pointer supplied to tee_register().
+ */
+void *tee_get_drvdata(struct tee_device *teedev);
+
+/**
+ * tee_shm_alloc() - Allocate shared memory
+ * @ctx: Context that allocates the shared memory
+ * @size: Requested size of shared memory
+ * @flags: Flags setting properties for the requested shared memory.
+ *
+ * Memory allocated as global shared memory is automatically freed when the
+ * TEE file pointer is closed. The @flags field uses the bits defined by
+ * TEE_SHM_* above. TEE_SHM_MAPPED must currently always be set. If
+ * TEE_SHM_DMA_BUF global shared memory will be allocated and associated
+ * with a dma-buf handle, else driver private memory.
+ *
+ * @returns a pointer to 'struct tee_shm'
+ */
+struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags);
+
+/**
+ * tee_shm_free() - Free shared memory
+ * @shm: Handle to shared memory to free
+ */
+void tee_shm_free(struct tee_shm *shm);
+
+/**
+ * tee_shm_put() - Decrease reference count on a shared memory handle
+ * @shm: Shared memory handle
+ */
+void tee_shm_put(struct tee_shm *shm);
+
+/**
+ * tee_shm_va2pa() - Get physical address of a virtual address
+ * @shm: Shared memory handle
+ * @va: Virtual address to tranlsate
+ * @pa: Returned physical address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_va2pa(struct tee_shm *shm, void *va, phys_addr_t *pa);
+
+/**
+ * tee_shm_pa2va() - Get virtual address of a physical address
+ * @shm: Shared memory handle
+ * @pa: Physical address to tranlsate
+ * @va: Returned virtual address
+ * @returns 0 on success and < 0 on failure
+ */
+int tee_shm_pa2va(struct tee_shm *shm, phys_addr_t pa, void **va);
+
+/**
+ * tee_shm_get_va() - Get virtual address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @returns virtual address of the shared memory + offs if offs is within
+ * the bounds of this shared memory, else an ERR_PTR
+ */
+void *tee_shm_get_va(struct tee_shm *shm, size_t offs);
+
+/**
+ * tee_shm_get_pa() - Get physical address of a shared memory plus an offset
+ * @shm: Shared memory handle
+ * @offs: Offset from start of this shared memory
+ * @pa: Physical address to return
+ * @returns 0 if offs is within the bounds of this shared memory, else an
+ * error code.
+ */
+int tee_shm_get_pa(struct tee_shm *shm, size_t offs, phys_addr_t *pa);
+
+/**
+ * tee_shm_get_id() - Get id of a shared memory object
+ * @shm: Shared memory handle
+ * @returns id
+ */
+int tee_shm_get_id(struct tee_shm *shm);
+
+/**
+ * tee_shm_get_from_id() - Find shared memory object and increase reference
+ * count
+ * @ctx: Context owning the shared memory
+ * @id: Id of shared memory object
+ * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure
+ */
+struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id);
+
+#endif /*__TEE_DRV_H*/
* naturally due ABI requirements, but some architectures (like CRIS) have
* weird ABI and we need to ask it explicitly.
*
- * The alignment is required to guarantee that bits 0 and 1 of @next will be
+ * The alignment is required to guarantee that bit 0 of @next will be
* clear under normal conditions -- as long as we use call_rcu(),
* call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback.
*
void *data,
gfp_t gfp);
+int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
+ struct scatterlist sg[], unsigned int num,
+ void *data,
+ void *ctx,
+ gfp_t gfp);
+
int virtqueue_add_sgs(struct virtqueue *vq,
struct scatterlist *sgs[],
unsigned int out_sgs,
void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
+void *virtqueue_get_buf_ctx(struct virtqueue *vq, unsigned int *len,
+ void **ctx);
+
void virtqueue_disable_cb(struct virtqueue *vq);
bool virtqueue_enable_cb(struct virtqueue *vq);
* @feature_table_legacy: same as feature_table but when working in legacy mode.
* @feature_table_size_legacy: number of entries in feature table legacy array.
* @probe: the function to call when a device is found. Returns 0 or -errno.
+ * @scan: optional function to call after successful probe; intended
+ * for virtio-scsi to invoke a scan.
* @remove: the function to call when a device is removed.
* @config_changed: optional function to call when the device configuration
* changes; may be called in interrupt context.
+ * @freeze: optional function to call during suspend/hibernation.
+ * @restore: optional function to call on resume.
*/
struct virtio_driver {
struct device_driver driver;
void (*reset)(struct virtio_device *vdev);
int (*find_vqs)(struct virtio_device *, unsigned nvqs,
struct virtqueue *vqs[], vq_callback_t *callbacks[],
- const char * const names[], struct irq_affinity *desc);
+ const char * const names[], const bool *ctx,
+ struct irq_affinity *desc);
void (*del_vqs)(struct virtio_device *);
u64 (*get_features)(struct virtio_device *vdev);
int (*finalize_features)(struct virtio_device *vdev);
vq_callback_t *callbacks[] = { c };
const char *names[] = { n };
struct virtqueue *vq;
- int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL);
+ int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL,
+ NULL);
if (err < 0)
return ERR_PTR(err);
return vq;
}
+static inline
+int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[], vq_callback_t *callbacks[],
+ const char * const names[],
+ struct irq_affinity *desc)
+{
+ return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc);
+}
+
+static inline
+int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[], vq_callback_t *callbacks[],
+ const char * const names[], const bool *ctx,
+ struct irq_affinity *desc)
+{
+ return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx,
+ desc);
+}
+
/**
* virtio_device_ready - enable vq use in probe function
* @vdev: the device
struct virtio_device *vdev,
bool weak_barriers,
bool may_reduce_num,
+ bool ctx,
bool (*notify)(struct virtqueue *vq),
void (*callback)(struct virtqueue *vq),
const char *name);
struct vring vring,
struct virtio_device *vdev,
bool weak_barriers,
+ bool ctx,
bool (*notify)(struct virtqueue *),
void (*callback)(struct virtqueue *),
const char *name);
unsigned int vring_align,
struct virtio_device *vdev,
bool weak_barriers,
+ bool ctx,
void *pages,
bool (*notify)(struct virtqueue *vq),
void (*callback)(struct virtqueue *vq),
#define ADDRCONF_TIMER_FUZZ (HZ / 4)
#define ADDRCONF_TIMER_FUZZ_MAX (HZ)
+#define ADDRCONF_NOTIFY_PRIORITY 0
+
#include <linux/in.h>
#include <linux/in6.h>
* (others are filtered out).
* If ommited, all results are passed.
* @n_match_sets: number of match sets
- * @results_wk: worker for processing results notification.
+ * @report_results: indicates that results were reported for this request
* @wiphy: the wiphy this was for
* @dev: the interface
* @scan_start: start time of the scheduled scan
* enum mac80211_rx_encoding_flags - MCS & bandwidth flags
*
* @RX_ENC_FLAG_SHORTPRE: Short preamble was used for this frame
- * @RX_ENC_FLAG_40MHZ: HT40 (40 MHz) was used
* @RX_ENC_FLAG_SHORT_GI: Short guard interval was used
* @RX_ENC_FLAG_HT_GF: This frame was received in a HT-greenfield transmission,
* if the driver fills this value it should add
*/
enum mac80211_rx_encoding_flags {
RX_ENC_FLAG_SHORTPRE = BIT(0),
- RX_ENC_FLAG_40MHZ = BIT(1),
RX_ENC_FLAG_SHORT_GI = BIT(2),
RX_ENC_FLAG_HT_GF = BIT(3),
RX_ENC_FLAG_STBC_MASK = BIT(4) | BIT(5),
u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport);
u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport);
-u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
- __be16 sport, __be16 dport, u32 *tsoff);
-u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
- __be16 sport, __be16 dport, u32 *tsoff);
+u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport);
+u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr);
+u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
+ __be16 sport, __be16 dport);
+u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr);
u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
__be16 sport, __be16 dport);
u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
struct module;
/*
- * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes
+ * caches using SLAB_TYPESAFE_BY_RCU should let .next pointer from nulls nodes
* un-modified. Special care is taken when initializing object to zero.
*/
static inline void sk_prot_clear_nulls(struct sock *sk, int size)
/* From syncookies.c */
struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
- struct dst_entry *dst);
+ struct dst_entry *dst, u32 tsoff);
int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th,
u32 cookie);
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
static inline void tcp_slow_start_after_idle_check(struct sock *sk)
{
+ const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
struct tcp_sock *tp = tcp_sk(sk);
s32 delta;
- if (!sysctl_tcp_slow_start_after_idle || tp->packets_out)
+ if (!sysctl_tcp_slow_start_after_idle || tp->packets_out ||
+ ca_ops->cong_control)
return;
delta = tcp_time_stamp - tp->lsndtime;
if (delta > inet_csk(sk)->icsk_rto)
#endif
struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl,
const struct request_sock *req);
- __u32 (*init_seq_tsoff)(const struct sk_buff *skb, u32 *tsoff);
+ u32 (*init_seq)(const struct sk_buff *skb);
+ u32 (*init_ts_off)(const struct sk_buff *skb);
int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl, struct request_sock *req,
struct tcp_fastopen_cookie *foc,
#include <linux/mmu_notifier.h>
#include <linux/uaccess.h>
#include <linux/cgroup_rdma.h>
+#include <uapi/rdma/ib_user_verbs.h>
extern struct workqueue_struct *ib_wq;
extern struct workqueue_struct *ib_comp_wq;
IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */
};
-#define IB_DEVICE_NAME_MAX 64
-
struct ib_port_cache {
struct ib_pkey_cache *pkey;
struct ib_gid_table *gid;
struct btrfs_fs_info;
struct btrfs_inode;
struct extent_map;
+struct btrfs_file_extent_item;
struct btrfs_ordered_extent;
struct btrfs_delayed_ref_node;
struct btrfs_delayed_tree_ref;
struct btrfs_work;
struct __btrfs_workqueue;
struct btrfs_qgroup_extent_record;
+struct btrfs_qgroup;
#define show_ref_type(type) \
__print_symbolic(type, \
(obj >= BTRFS_ROOT_TREE_OBJECTID && \
obj <= BTRFS_QUOTA_TREE_OBJECTID)) ? __show_root_type(obj) : "-"
+#define show_fi_type(type) \
+ __print_symbolic(type, \
+ { BTRFS_FILE_EXTENT_INLINE, "INLINE" }, \
+ { BTRFS_FILE_EXTENT_REG, "REG" }, \
+ { BTRFS_FILE_EXTENT_PREALLOC, "PREALLOC"})
+
#define BTRFS_GROUP_FLAGS \
{ BTRFS_BLOCK_GROUP_DATA, "DATA"}, \
{ BTRFS_BLOCK_GROUP_SYSTEM, "SYSTEM"}, \
__entry->block_start = map->block_start;
__entry->block_len = map->block_len;
__entry->flags = map->flags;
- __entry->refs = atomic_read(&map->refs);
+ __entry->refs = refcount_read(&map->refs);
__entry->compress_type = map->compress_type;
),
__entry->refs, __entry->compress_type)
);
+/* file extent item */
+DECLARE_EVENT_CLASS(btrfs__file_extent_item_regular,
+
+ TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
+ struct btrfs_file_extent_item *fi, u64 start),
+
+ TP_ARGS(bi, l, fi, start),
+
+ TP_STRUCT__entry_btrfs(
+ __field( u64, root_obj )
+ __field( u64, ino )
+ __field( loff_t, isize )
+ __field( u64, disk_isize )
+ __field( u64, num_bytes )
+ __field( u64, ram_bytes )
+ __field( u64, disk_bytenr )
+ __field( u64, disk_num_bytes )
+ __field( u64, extent_offset )
+ __field( u8, extent_type )
+ __field( u8, compression )
+ __field( u64, extent_start )
+ __field( u64, extent_end )
+ ),
+
+ TP_fast_assign_btrfs(bi->root->fs_info,
+ __entry->root_obj = bi->root->objectid;
+ __entry->ino = btrfs_ino(bi);
+ __entry->isize = bi->vfs_inode.i_size;
+ __entry->disk_isize = bi->disk_i_size;
+ __entry->num_bytes = btrfs_file_extent_num_bytes(l, fi);
+ __entry->ram_bytes = btrfs_file_extent_ram_bytes(l, fi);
+ __entry->disk_bytenr = btrfs_file_extent_disk_bytenr(l, fi);
+ __entry->disk_num_bytes = btrfs_file_extent_disk_num_bytes(l, fi);
+ __entry->extent_offset = btrfs_file_extent_offset(l, fi);
+ __entry->extent_type = btrfs_file_extent_type(l, fi);
+ __entry->compression = btrfs_file_extent_compression(l, fi);
+ __entry->extent_start = start;
+ __entry->extent_end = (start + __entry->num_bytes);
+ ),
+
+ TP_printk_btrfs(
+ "root=%llu(%s) inode=%llu size=%llu disk_isize=%llu "
+ "file extent range=[%llu %llu] "
+ "(num_bytes=%llu ram_bytes=%llu disk_bytenr=%llu "
+ "disk_num_bytes=%llu extent_offset=%llu type=%s "
+ "compression=%u",
+ show_root_type(__entry->root_obj), __entry->ino,
+ __entry->isize,
+ __entry->disk_isize, __entry->extent_start,
+ __entry->extent_end, __entry->num_bytes, __entry->ram_bytes,
+ __entry->disk_bytenr, __entry->disk_num_bytes,
+ __entry->extent_offset, show_fi_type(__entry->extent_type),
+ __entry->compression)
+);
+
+DECLARE_EVENT_CLASS(
+ btrfs__file_extent_item_inline,
+
+ TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
+ struct btrfs_file_extent_item *fi, int slot, u64 start),
+
+ TP_ARGS(bi, l, fi, slot, start),
+
+ TP_STRUCT__entry_btrfs(
+ __field( u64, root_obj )
+ __field( u64, ino )
+ __field( loff_t, isize )
+ __field( u64, disk_isize )
+ __field( u8, extent_type )
+ __field( u8, compression )
+ __field( u64, extent_start )
+ __field( u64, extent_end )
+ ),
+
+ TP_fast_assign_btrfs(
+ bi->root->fs_info,
+ __entry->root_obj = bi->root->objectid;
+ __entry->ino = btrfs_ino(bi);
+ __entry->isize = bi->vfs_inode.i_size;
+ __entry->disk_isize = bi->disk_i_size;
+ __entry->extent_type = btrfs_file_extent_type(l, fi);
+ __entry->compression = btrfs_file_extent_compression(l, fi);
+ __entry->extent_start = start;
+ __entry->extent_end = (start + btrfs_file_extent_inline_len(l, slot, fi));
+ ),
+
+ TP_printk_btrfs(
+ "root=%llu(%s) inode=%llu size=%llu disk_isize=%llu "
+ "file extent range=[%llu %llu] "
+ "extent_type=%s compression=%u",
+ show_root_type(__entry->root_obj), __entry->ino, __entry->isize,
+ __entry->disk_isize, __entry->extent_start,
+ __entry->extent_end, show_fi_type(__entry->extent_type),
+ __entry->compression)
+);
+
+DEFINE_EVENT(
+ btrfs__file_extent_item_regular, btrfs_get_extent_show_fi_regular,
+
+ TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
+ struct btrfs_file_extent_item *fi, u64 start),
+
+ TP_ARGS(bi, l, fi, start)
+);
+
+DEFINE_EVENT(
+ btrfs__file_extent_item_regular, btrfs_truncate_show_fi_regular,
+
+ TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
+ struct btrfs_file_extent_item *fi, u64 start),
+
+ TP_ARGS(bi, l, fi, start)
+);
+
+DEFINE_EVENT(
+ btrfs__file_extent_item_inline, btrfs_get_extent_show_fi_inline,
+
+ TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
+ struct btrfs_file_extent_item *fi, int slot, u64 start),
+
+ TP_ARGS(bi, l, fi, slot, start)
+);
+
+DEFINE_EVENT(
+ btrfs__file_extent_item_inline, btrfs_truncate_show_fi_inline,
+
+ TP_PROTO(struct btrfs_inode *bi, struct extent_buffer *l,
+ struct btrfs_file_extent_item *fi, int slot, u64 start),
+
+ TP_ARGS(bi, l, fi, slot, start)
+);
+
#define show_ordered_flags(flags) \
__print_flags(flags, "|", \
{ (1 << BTRFS_ORDERED_IO_DONE), "IO_DONE" }, \
__entry->bytes_left = ordered->bytes_left;
__entry->flags = ordered->flags;
__entry->compress_type = ordered->compress_type;
- __entry->refs = atomic_read(&ordered->refs);
+ __entry->refs = refcount_read(&ordered->refs);
__entry->root_objectid =
BTRFS_I(inode)->root->root_key.objectid;
__entry->truncated_len = ordered->truncated_len;
__entry->cur_new_count)
);
+TRACE_EVENT(qgroup_update_reserve,
+
+ TP_PROTO(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup,
+ s64 diff),
+
+ TP_ARGS(fs_info, qgroup, diff),
+
+ TP_STRUCT__entry_btrfs(
+ __field( u64, qgid )
+ __field( u64, cur_reserved )
+ __field( s64, diff )
+ ),
+
+ TP_fast_assign_btrfs(fs_info,
+ __entry->qgid = qgroup->qgroupid;
+ __entry->cur_reserved = qgroup->reserved;
+ __entry->diff = diff;
+ ),
+
+ TP_printk_btrfs("qgid=%llu cur_reserved=%llu diff=%lld",
+ __entry->qgid, __entry->cur_reserved, __entry->diff)
+);
+
+TRACE_EVENT(qgroup_meta_reserve,
+
+ TP_PROTO(struct btrfs_root *root, s64 diff),
+
+ TP_ARGS(root, diff),
+
+ TP_STRUCT__entry_btrfs(
+ __field( u64, refroot )
+ __field( s64, diff )
+ ),
+
+ TP_fast_assign_btrfs(root->fs_info,
+ __entry->refroot = root->objectid;
+ __entry->diff = diff;
+ ),
+
+ TP_printk_btrfs("refroot=%llu(%s) diff=%lld",
+ show_root_type(__entry->refroot), __entry->diff)
+);
+
#endif /* _TRACE_BTRFS_H */
/* This part must be outside protection */
#define _TRACE_IOMMU_H
#include <linux/tracepoint.h>
-#include <linux/pci.h>
struct device;
+++ /dev/null
-# UAPI Header export list
-# Top-level Makefile calls into asm-$(ARCH)
-# List only non-arch directories below
-
-
-header-y += asm-generic/
-header-y += linux/
-header-y += sound/
-header-y += mtd/
-header-y += rdma/
-header-y += video/
-header-y += drm/
-header-y += xen/
-header-y += scsi/
-header-y += misc/
+++ /dev/null
-# UAPI Header export list
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += errno-base.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += int-l64.h
-header-y += int-ll64.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += kvm_para.h
-header-y += mman-common.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += shmparam.h
-header-y += siginfo.h
-header-y += signal-defs.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += ucontext.h
-header-y += unistd.h
-#
-# Headers that are optional in usr/include/asm/
-#
-opt-header += kvm.h
-opt-header += kvm_para.h
-opt-header += a.out.h
-
#
# Headers that are mandatory in usr/include/asm/
#
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += byteorder.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += param.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += unistd.h
-
-header-y += $(foreach hdr,$(opt-header), \
- $(if \
- $(wildcard \
- $(srctree)/arch/$(SRCARCH)/include/uapi/asm/$(hdr) \
- $(srctree)/arch/$(SRCARCH)/include/asm/$(hdr) \
- ), \
- $(hdr) \
- ))
+mandatory-y += auxvec.h
+mandatory-y += bitsperlong.h
+mandatory-y += byteorder.h
+mandatory-y += errno.h
+mandatory-y += fcntl.h
+mandatory-y += ioctl.h
+mandatory-y += ioctls.h
+mandatory-y += ipcbuf.h
+mandatory-y += mman.h
+mandatory-y += msgbuf.h
+mandatory-y += param.h
+mandatory-y += poll.h
+mandatory-y += posix_types.h
+mandatory-y += ptrace.h
+mandatory-y += resource.h
+mandatory-y += sembuf.h
+mandatory-y += setup.h
+mandatory-y += shmbuf.h
+mandatory-y += sigcontext.h
+mandatory-y += siginfo.h
+mandatory-y += signal.h
+mandatory-y += socket.h
+mandatory-y += sockios.h
+mandatory-y += stat.h
+mandatory-y += statfs.h
+mandatory-y += swab.h
+mandatory-y += termbits.h
+mandatory-y += termios.h
+mandatory-y += types.h
+mandatory-y += unistd.h
+++ /dev/null
-# UAPI Header export list
-header-y += drm.h
-header-y += drm_fourcc.h
-header-y += drm_mode.h
-header-y += drm_sarea.h
-header-y += amdgpu_drm.h
-header-y += exynos_drm.h
-header-y += i810_drm.h
-header-y += i915_drm.h
-header-y += mga_drm.h
-header-y += nouveau_drm.h
-header-y += omap_drm.h
-header-y += qxl_drm.h
-header-y += r128_drm.h
-header-y += radeon_drm.h
-header-y += savage_drm.h
-header-y += sis_drm.h
-header-y += tegra_drm.h
-header-y += via_drm.h
-header-y += vmwgfx_drm.h
-header-y += msm_drm.h
-header-y += vc4_drm.h
-header-y += virtgpu_drm.h
# UAPI Header export list
-header-y += android/
-header-y += byteorder/
-header-y += can/
-header-y += caif/
-header-y += dvb/
-header-y += hdlc/
-header-y += hsi/
-header-y += iio/
-header-y += isdn/
-header-y += mmc/
-header-y += nfsd/
-header-y += raid/
-header-y += spi/
-header-y += sunrpc/
-header-y += tc_act/
-header-y += tc_ematch/
-header-y += netfilter/
-header-y += netfilter_arp/
-header-y += netfilter_bridge/
-header-y += netfilter_ipv4/
-header-y += netfilter_ipv6/
-header-y += usb/
-header-y += wimax/
-genhdr-y += version.h
-
-ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/a.out.h \
- $(srctree)/arch/$(SRCARCH)/include/asm/a.out.h),)
-header-y += a.out.h
+ifeq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/a.out.h),)
+no-export-headers += a.out.h
endif
-header-y += acct.h
-header-y += adb.h
-header-y += adfs_fs.h
-header-y += affs_hardblocks.h
-header-y += agpgart.h
-header-y += aio_abi.h
-header-y += am437x-vpfe.h
-header-y += apm_bios.h
-header-y += arcfb.h
-header-y += atalk.h
-header-y += atmapi.h
-header-y += atmarp.h
-header-y += atmbr2684.h
-header-y += atmclip.h
-header-y += atmdev.h
-header-y += atm_eni.h
-header-y += atm.h
-header-y += atm_he.h
-header-y += atm_idt77105.h
-header-y += atmioc.h
-header-y += atmlec.h
-header-y += atmmpc.h
-header-y += atm_nicstar.h
-header-y += atmppp.h
-header-y += atmsap.h
-header-y += atmsvc.h
-header-y += atm_tcp.h
-header-y += atm_zatm.h
-header-y += audit.h
-header-y += auto_fs4.h
-header-y += auto_fs.h
-header-y += auxvec.h
-header-y += ax25.h
-header-y += b1lli.h
-header-y += batman_adv.h
-header-y += baycom.h
-header-y += bcm933xx_hcs.h
-header-y += bfs_fs.h
-header-y += binfmts.h
-header-y += blkpg.h
-header-y += blktrace_api.h
-header-y += blkzoned.h
-header-y += bpf_common.h
-header-y += bpf_perf_event.h
-header-y += bpf.h
-header-y += bpqether.h
-header-y += bsg.h
-header-y += bt-bmc.h
-header-y += btrfs.h
-header-y += can.h
-header-y += capability.h
-header-y += capi.h
-header-y += cciss_defs.h
-header-y += cciss_ioctl.h
-header-y += cdrom.h
-header-y += cec.h
-header-y += cec-funcs.h
-header-y += cgroupstats.h
-header-y += chio.h
-header-y += cm4000_cs.h
-header-y += cn_proc.h
-header-y += coda.h
-header-y += coda_psdev.h
-header-y += coff.h
-header-y += connector.h
-header-y += const.h
-header-y += cramfs_fs.h
-header-y += cuda.h
-header-y += cyclades.h
-header-y += cycx_cfm.h
-header-y += dcbnl.h
-header-y += dccp.h
-header-y += devlink.h
-header-y += dlmconstants.h
-header-y += dlm_device.h
-header-y += dlm.h
-header-y += dlm_netlink.h
-header-y += dlm_plock.h
-header-y += dm-ioctl.h
-header-y += dm-log-userspace.h
-header-y += dma-buf.h
-header-y += dn.h
-header-y += dqblk_xfs.h
-header-y += edd.h
-header-y += efs_fs_sb.h
-header-y += elfcore.h
-header-y += elf-em.h
-header-y += elf-fdpic.h
-header-y += elf.h
-header-y += errno.h
-header-y += errqueue.h
-header-y += ethtool.h
-header-y += eventpoll.h
-header-y += fadvise.h
-header-y += falloc.h
-header-y += fanotify.h
-header-y += fb.h
-header-y += fcntl.h
-header-y += fd.h
-header-y += fdreg.h
-header-y += fib_rules.h
-header-y += fiemap.h
-header-y += filter.h
-header-y += firewire-cdev.h
-header-y += firewire-constants.h
-header-y += flat.h
-header-y += fou.h
-header-y += fs.h
-header-y += fsl_hypervisor.h
-header-y += fuse.h
-header-y += futex.h
-header-y += gameport.h
-header-y += genetlink.h
-header-y += gen_stats.h
-header-y += gfs2_ondisk.h
-header-y += gigaset_dev.h
-header-y += gpio.h
-header-y += gsmmux.h
-header-y += gtp.h
-header-y += hdlcdrv.h
-header-y += hdlc.h
-header-y += hdreg.h
-header-y += hiddev.h
-header-y += hid.h
-header-y += hidraw.h
-header-y += hpet.h
-header-y += hsr_netlink.h
-header-y += hyperv.h
-header-y += hysdn_if.h
-header-y += i2c-dev.h
-header-y += i2c.h
-header-y += i2o-dev.h
-header-y += i8k.h
-header-y += icmp.h
-header-y += icmpv6.h
-header-y += if_addr.h
-header-y += if_addrlabel.h
-header-y += if_alg.h
-header-y += if_arcnet.h
-header-y += if_arp.h
-header-y += if_bonding.h
-header-y += if_bridge.h
-header-y += if_cablemodem.h
-header-y += if_eql.h
-header-y += if_ether.h
-header-y += if_fc.h
-header-y += if_fddi.h
-header-y += if_frad.h
-header-y += if.h
-header-y += if_hippi.h
-header-y += if_infiniband.h
-header-y += if_link.h
-header-y += if_ltalk.h
-header-y += if_macsec.h
-header-y += if_packet.h
-header-y += if_phonet.h
-header-y += if_plip.h
-header-y += if_ppp.h
-header-y += if_pppol2tp.h
-header-y += if_pppox.h
-header-y += if_slip.h
-header-y += if_team.h
-header-y += if_tun.h
-header-y += if_tunnel.h
-header-y += if_vlan.h
-header-y += if_x25.h
-header-y += ife.h
-header-y += igmp.h
-header-y += ila.h
-header-y += in6.h
-header-y += inet_diag.h
-header-y += in.h
-header-y += inotify.h
-header-y += input.h
-header-y += input-event-codes.h
-header-y += in_route.h
-header-y += ioctl.h
-header-y += ip6_tunnel.h
-header-y += ipc.h
-header-y += ip.h
-header-y += ipmi.h
-header-y += ipmi_msgdefs.h
-header-y += ipsec.h
-header-y += ipv6.h
-header-y += ipv6_route.h
-header-y += ip_vs.h
-header-y += ipx.h
-header-y += irda.h
-header-y += irqnr.h
-header-y += isdn_divertif.h
-header-y += isdn.h
-header-y += isdnif.h
-header-y += isdn_ppp.h
-header-y += iso_fs.h
-header-y += ivtvfb.h
-header-y += ivtv.h
-header-y += ixjuser.h
-header-y += jffs2.h
-header-y += joystick.h
-header-y += kcmp.h
-header-y += kdev_t.h
-header-y += kd.h
-header-y += kernelcapi.h
-header-y += kernel.h
-header-y += kernel-page-flags.h
-header-y += kexec.h
-header-y += keyboard.h
-header-y += keyctl.h
-
-ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm.h \
- $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h),)
-header-y += kvm.h
+ifeq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm.h),)
+no-export-headers += kvm.h
endif
-
-ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm_para.h \
- $(srctree)/arch/$(SRCARCH)/include/asm/kvm_para.h),)
-header-y += kvm_para.h
+ifeq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm_para.h),)
+no-export-headers += kvm_para.h
endif
-
-header-y += hw_breakpoint.h
-header-y += l2tp.h
-header-y += libc-compat.h
-header-y += lirc.h
-header-y += limits.h
-header-y += llc.h
-header-y += loop.h
-header-y += lp.h
-header-y += lwtunnel.h
-header-y += magic.h
-header-y += major.h
-header-y += map_to_7segment.h
-header-y += matroxfb.h
-header-y += mdio.h
-header-y += media.h
-header-y += media-bus-format.h
-header-y += mei.h
-header-y += membarrier.h
-header-y += memfd.h
-header-y += mempolicy.h
-header-y += meye.h
-header-y += mic_common.h
-header-y += mic_ioctl.h
-header-y += mii.h
-header-y += minix_fs.h
-header-y += mman.h
-header-y += mmtimer.h
-header-y += mpls.h
-header-y += mpls_iptunnel.h
-header-y += mqueue.h
-header-y += mroute6.h
-header-y += mroute.h
-header-y += msdos_fs.h
-header-y += msg.h
-header-y += mtio.h
-header-y += nbd.h
-header-y += ncp_fs.h
-header-y += ncp.h
-header-y += ncp_mount.h
-header-y += ncp_no.h
-header-y += ndctl.h
-header-y += neighbour.h
-header-y += netconf.h
-header-y += netdevice.h
-header-y += net_dropmon.h
-header-y += netfilter_arp.h
-header-y += netfilter_bridge.h
-header-y += netfilter_decnet.h
-header-y += netfilter.h
-header-y += netfilter_ipv4.h
-header-y += netfilter_ipv6.h
-header-y += net.h
-header-y += netlink_diag.h
-header-y += netlink.h
-header-y += netrom.h
-header-y += net_namespace.h
-header-y += net_tstamp.h
-header-y += nfc.h
-header-y += psample.h
-header-y += nfs2.h
-header-y += nfs3.h
-header-y += nfs4.h
-header-y += nfs4_mount.h
-header-y += nfsacl.h
-header-y += nfs_fs.h
-header-y += nfs.h
-header-y += nfs_idmap.h
-header-y += nfs_mount.h
-header-y += nl80211.h
-header-y += n_r3964.h
-header-y += nubus.h
-header-y += nvme_ioctl.h
-header-y += nvram.h
-header-y += omap3isp.h
-header-y += omapfb.h
-header-y += oom.h
-header-y += openvswitch.h
-header-y += packet_diag.h
-header-y += param.h
-header-y += parport.h
-header-y += patchkey.h
-header-y += pci.h
-header-y += pci_regs.h
-header-y += pcitest.h
-header-y += perf_event.h
-header-y += personality.h
-header-y += pfkeyv2.h
-header-y += pg.h
-header-y += phantom.h
-header-y += phonet.h
-header-y += pktcdvd.h
-header-y += pkt_cls.h
-header-y += pkt_sched.h
-header-y += pmu.h
-header-y += poll.h
-header-y += posix_acl.h
-header-y += posix_acl_xattr.h
-header-y += posix_types.h
-header-y += ppdev.h
-header-y += ppp-comp.h
-header-y += ppp_defs.h
-header-y += ppp-ioctl.h
-header-y += pps.h
-header-y += prctl.h
-header-y += psci.h
-header-y += ptp_clock.h
-header-y += ptrace.h
-header-y += qnx4_fs.h
-header-y += qnxtypes.h
-header-y += quota.h
-header-y += radeonfb.h
-header-y += random.h
-header-y += raw.h
-header-y += rds.h
-header-y += reboot.h
-header-y += reiserfs_fs.h
-header-y += reiserfs_xattr.h
-header-y += resource.h
-header-y += rfkill.h
-header-y += rio_cm_cdev.h
-header-y += rio_mport_cdev.h
-header-y += romfs_fs.h
-header-y += rose.h
-header-y += route.h
-header-y += rtc.h
-header-y += rtnetlink.h
-header-y += scc.h
-header-y += sched.h
-header-y += scif_ioctl.h
-header-y += screen_info.h
-header-y += sctp.h
-header-y += sdla.h
-header-y += seccomp.h
-header-y += securebits.h
-header-y += seg6_genl.h
-header-y += seg6.h
-header-y += seg6_hmac.h
-header-y += seg6_iptunnel.h
-header-y += selinux_netlink.h
-header-y += sem.h
-header-y += serial_core.h
-header-y += serial.h
-header-y += serial_reg.h
-header-y += serio.h
-header-y += shm.h
-header-y += signalfd.h
-header-y += signal.h
-header-y += smiapp.h
-header-y += snmp.h
-header-y += sock_diag.h
-header-y += socket.h
-header-y += sockios.h
-header-y += sonet.h
-header-y += sonypi.h
-header-y += soundcard.h
-header-y += sound.h
-header-y += stat.h
-header-y += stddef.h
-header-y += string.h
-header-y += suspend_ioctls.h
-header-y += swab.h
-header-y += synclink.h
-header-y += sync_file.h
-header-y += sysctl.h
-header-y += sysinfo.h
-header-y += target_core_user.h
-header-y += taskstats.h
-header-y += tcp.h
-header-y += tcp_metrics.h
-header-y += telephony.h
-header-y += termios.h
-header-y += thermal.h
-header-y += time.h
-header-y += timerfd.h
-header-y += times.h
-header-y += timex.h
-header-y += tiocl.h
-header-y += tipc_config.h
-header-y += tipc_netlink.h
-header-y += tipc.h
-header-y += toshiba.h
-header-y += tty_flags.h
-header-y += tty.h
-header-y += types.h
-header-y += udf_fs_i.h
-header-y += udp.h
-header-y += uhid.h
-header-y += uinput.h
-header-y += uio.h
-header-y += uleds.h
-header-y += ultrasound.h
-header-y += un.h
-header-y += unistd.h
-header-y += unix_diag.h
-header-y += usbdevice_fs.h
-header-y += usbip.h
-header-y += userio.h
-header-y += utime.h
-header-y += utsname.h
-header-y += uuid.h
-header-y += uvcvideo.h
-header-y += v4l2-common.h
-header-y += v4l2-controls.h
-header-y += v4l2-dv-timings.h
-header-y += v4l2-mediabus.h
-header-y += v4l2-subdev.h
-header-y += veth.h
-header-y += vfio.h
-header-y += vhost.h
-header-y += videodev2.h
-header-y += virtio_9p.h
-header-y += virtio_balloon.h
-header-y += virtio_blk.h
-header-y += virtio_config.h
-header-y += virtio_console.h
-header-y += virtio_gpu.h
-header-y += virtio_ids.h
-header-y += virtio_input.h
-header-y += virtio_mmio.h
-header-y += virtio_net.h
-header-y += virtio_pci.h
-header-y += virtio_ring.h
-header-y += virtio_rng.h
-header-y += virtio_scsi.h
-header-y += virtio_types.h
-header-y += virtio_vsock.h
-header-y += virtio_crypto.h
-header-y += vm_sockets.h
-header-y += vsockmon.h
-header-y += vt.h
-header-y += vtpm_proxy.h
-header-y += wait.h
-header-y += wanrouter.h
-header-y += watchdog.h
-header-y += wimax.h
-header-y += wireless.h
-header-y += x25.h
-header-y += xattr.h
-header-y += xfrm.h
-header-y += xilinx-v4l2-controls.h
-header-y += zorro.h
-header-y += zorro_ids.h
-header-y += userfaultfd.h
+++ /dev/null
-# UAPI Header export list
-header-y += binder.h
* Bcache on disk data structures
*/
-#include <asm/types.h>
+#include <linux/types.h>
#define BITMASK(name, type, field, offset, size) \
static inline __u64 name(const type *k) \
struct btrfs_balance_args {
__u64 profiles;
union {
- __le64 usage;
+ __u64 usage;
struct {
- __le32 usage_min;
- __le32 usage_max;
+ __u32 usage_min;
+ __u32 usage_max;
};
};
__u64 devid;
* Process chunks that cross stripes_min..stripes_max devices,
* BTRFS_BALANCE_ARGS_STRIPES_RANGE
*/
- __le32 stripes_min;
- __le32 stripes_max;
+ __u32 stripes_min;
+ __u32 stripes_max;
__u64 unused[6];
} __attribute__ ((__packed__));
#ifndef _BTRFS_CTREE_H_
#define _BTRFS_CTREE_H_
+#include <linux/btrfs.h>
+#include <linux/types.h>
+
/*
* This header contains the structure definitions and constants used
* by file system objects that can be retrieved using
+++ /dev/null
-# UAPI Header export list
-header-y += big_endian.h
-header-y += little_endian.h
+++ /dev/null
-# UAPI Header export list
-header-y += caif_socket.h
-header-y += if_caif.h
+++ /dev/null
-# UAPI Header export list
-header-y += bcm.h
-header-y += error.h
-header-y += gw.h
-header-y += netlink.h
-header-y += raw.h
* 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
*/
+#include <linux/types.h>
+
/* Netlink configuration messages. */
enum {
CRYPTO_MSG_BASE = 0x10,
+++ /dev/null
-# UAPI Header export list
-header-y += audio.h
-header-y += ca.h
-header-y += dmx.h
-header-y += frontend.h
-header-y += net.h
-header-y += osd.h
-header-y += version.h
-header-y += video.h
+++ /dev/null
-# UAPI Header export list
-header-y += ioctl.h
+++ /dev/null
-# UAPI Header export list
-header-y += hsi_char.h cs-protocol.h
+++ /dev/null
-# UAPI Header export list
-header-y += events.h
-header-y += types.h
+++ /dev/null
-# UAPI Header export list
-header-y += capicmd.h
+++ /dev/null
-# UAPI Header export list
-header-y += ioctl.h
+++ /dev/null
-# UAPI Header export list
-header-y += ipset/
-header-y += nf_conntrack_common.h
-header-y += nf_conntrack_ftp.h
-header-y += nf_conntrack_sctp.h
-header-y += nf_conntrack_tcp.h
-header-y += nf_conntrack_tuple_common.h
-header-y += nf_log.h
-header-y += nf_tables.h
-header-y += nf_tables_compat.h
-header-y += nf_nat.h
-header-y += nfnetlink.h
-header-y += nfnetlink_acct.h
-header-y += nfnetlink_compat.h
-header-y += nfnetlink_conntrack.h
-header-y += nfnetlink_cthelper.h
-header-y += nfnetlink_cttimeout.h
-header-y += nfnetlink_log.h
-header-y += nfnetlink_queue.h
-header-y += x_tables.h
-header-y += xt_AUDIT.h
-header-y += xt_CHECKSUM.h
-header-y += xt_CLASSIFY.h
-header-y += xt_CONNMARK.h
-header-y += xt_CONNSECMARK.h
-header-y += xt_CT.h
-header-y += xt_DSCP.h
-header-y += xt_HMARK.h
-header-y += xt_IDLETIMER.h
-header-y += xt_LED.h
-header-y += xt_LOG.h
-header-y += xt_MARK.h
-header-y += xt_NFLOG.h
-header-y += xt_NFQUEUE.h
-header-y += xt_RATEEST.h
-header-y += xt_SECMARK.h
-header-y += xt_SYNPROXY.h
-header-y += xt_TCPMSS.h
-header-y += xt_TCPOPTSTRIP.h
-header-y += xt_TEE.h
-header-y += xt_TPROXY.h
-header-y += xt_addrtype.h
-header-y += xt_bpf.h
-header-y += xt_cgroup.h
-header-y += xt_cluster.h
-header-y += xt_comment.h
-header-y += xt_connbytes.h
-header-y += xt_connlabel.h
-header-y += xt_connlimit.h
-header-y += xt_connmark.h
-header-y += xt_conntrack.h
-header-y += xt_cpu.h
-header-y += xt_dccp.h
-header-y += xt_devgroup.h
-header-y += xt_dscp.h
-header-y += xt_ecn.h
-header-y += xt_esp.h
-header-y += xt_hashlimit.h
-header-y += xt_helper.h
-header-y += xt_ipcomp.h
-header-y += xt_iprange.h
-header-y += xt_ipvs.h
-header-y += xt_l2tp.h
-header-y += xt_length.h
-header-y += xt_limit.h
-header-y += xt_mac.h
-header-y += xt_mark.h
-header-y += xt_multiport.h
-header-y += xt_nfacct.h
-header-y += xt_osf.h
-header-y += xt_owner.h
-header-y += xt_physdev.h
-header-y += xt_pkttype.h
-header-y += xt_policy.h
-header-y += xt_quota.h
-header-y += xt_rateest.h
-header-y += xt_realm.h
-header-y += xt_recent.h
-header-y += xt_rpfilter.h
-header-y += xt_sctp.h
-header-y += xt_set.h
-header-y += xt_socket.h
-header-y += xt_state.h
-header-y += xt_statistic.h
-header-y += xt_string.h
-header-y += xt_tcpmss.h
-header-y += xt_tcpudp.h
-header-y += xt_time.h
-header-y += xt_u32.h
+++ /dev/null
-# UAPI Header export list
-header-y += ip_set.h
-header-y += ip_set_bitmap.h
-header-y += ip_set_hash.h
-header-y += ip_set_list.h
+++ /dev/null
-# UAPI Header export list
-header-y += arp_tables.h
-header-y += arpt_mangle.h
+++ /dev/null
-# UAPI Header export list
-header-y += ebt_802_3.h
-header-y += ebt_among.h
-header-y += ebt_arp.h
-header-y += ebt_arpreply.h
-header-y += ebt_ip.h
-header-y += ebt_ip6.h
-header-y += ebt_limit.h
-header-y += ebt_log.h
-header-y += ebt_mark_m.h
-header-y += ebt_mark_t.h
-header-y += ebt_nat.h
-header-y += ebt_nflog.h
-header-y += ebt_pkttype.h
-header-y += ebt_redirect.h
-header-y += ebt_stp.h
-header-y += ebt_vlan.h
-header-y += ebtables.h
+++ /dev/null
-# UAPI Header export list
-header-y += ip_tables.h
-header-y += ipt_CLUSTERIP.h
-header-y += ipt_ECN.h
-header-y += ipt_LOG.h
-header-y += ipt_REJECT.h
-header-y += ipt_TTL.h
-header-y += ipt_ah.h
-header-y += ipt_ecn.h
-header-y += ipt_ttl.h
+++ /dev/null
-# UAPI Header export list
-header-y += ip6_tables.h
-header-y += ip6t_HL.h
-header-y += ip6t_LOG.h
-header-y += ip6t_NPT.h
-header-y += ip6t_REJECT.h
-header-y += ip6t_ah.h
-header-y += ip6t_frag.h
-header-y += ip6t_hl.h
-header-y += ip6t_ipv6header.h
-header-y += ip6t_mh.h
-header-y += ip6t_opts.h
-header-y += ip6t_rt.h
+++ /dev/null
-# UAPI Header export list
-header-y += cld.h
-header-y += debug.h
-header-y += export.h
-header-y += nfsfh.h
-header-y += stats.h
#ifndef _NFSD_CLD_H
#define _NFSD_CLD_H
+#include <linux/types.h>
+
/* latest upcall version available */
#define CLD_UPCALL_VERSION 1
/* representation of long-form NFSv4 client ID */
struct cld_name {
- uint16_t cn_len; /* length of cm_id */
+ __u16 cn_len; /* length of cm_id */
unsigned char cn_id[NFS4_OPAQUE_LIMIT]; /* client-provided */
} __attribute__((packed));
/* message struct for communication with userspace */
struct cld_msg {
- uint8_t cm_vers; /* upcall version */
- uint8_t cm_cmd; /* upcall command */
- int16_t cm_status; /* return code */
- uint32_t cm_xid; /* transaction id */
+ __u8 cm_vers; /* upcall version */
+ __u8 cm_cmd; /* upcall command */
+ __s16 cm_status; /* return code */
+ __u32 cm_xid; /* transaction id */
union {
- int64_t cm_gracetime; /* grace period start time */
+ __s64 cm_gracetime; /* grace period start time */
struct cld_name cm_name;
} __attribute__((packed)) cm_u;
} __attribute__((packed));
#ifndef _UAPI_PR_H
#define _UAPI_PR_H
+#include <linux/types.h>
+
enum pr_type {
PR_WRITE_EXCLUSIVE = 1,
PR_EXCLUSIVE_ACCESS = 2,
#define _LINUX_QRTR_H
#include <linux/socket.h>
+#include <linux/types.h>
struct sockaddr_qrtr {
__kernel_sa_family_t sq_family;
+++ /dev/null
-# UAPI Header export list
-header-y += md_p.h
-header-y += md_u.h
#include <linux/types.h>
#include <linux/inet_diag.h>
-#include <rdma/ib_verbs.h>
+#include <rdma/ib_user_verbs.h>
/* Request structure */
struct smc_diag_req {
+++ /dev/null
-# UAPI Header export list
-header-y += spidev.h
+++ /dev/null
-# UAPI Header export list
-header-y += debug.h
+++ /dev/null
-# UAPI Header export list
-header-y += tc_csum.h
-header-y += tc_defact.h
-header-y += tc_gact.h
-header-y += tc_ipt.h
-header-y += tc_mirred.h
-header-y += tc_sample.h
-header-y += tc_nat.h
-header-y += tc_pedit.h
-header-y += tc_skbedit.h
-header-y += tc_vlan.h
-header-y += tc_bpf.h
-header-y += tc_connmark.h
-header-y += tc_ife.h
-header-y += tc_tunnel_key.h
-header-y += tc_skbmod.h
+++ /dev/null
-# UAPI Header export list
-header-y += tc_em_cmp.h
-header-y += tc_em_meta.h
-header-y += tc_em_nbyte.h
-header-y += tc_em_text.h
--- /dev/null
+/*
+ * Copyright (c) 2015-2016, Linaro Limited
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ *
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __TEE_H
+#define __TEE_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/*
+ * This file describes the API provided by a TEE driver to user space.
+ *
+ * Each TEE driver defines a TEE specific protocol which is used for the
+ * data passed back and forth using TEE_IOC_CMD.
+ */
+
+/* Helpers to make the ioctl defines */
+#define TEE_IOC_MAGIC 0xa4
+#define TEE_IOC_BASE 0
+
+/* Flags relating to shared memory */
+#define TEE_IOCTL_SHM_MAPPED 0x1 /* memory mapped in normal world */
+#define TEE_IOCTL_SHM_DMA_BUF 0x2 /* dma-buf handle on shared memory */
+
+#define TEE_MAX_ARG_SIZE 1024
+
+#define TEE_GEN_CAP_GP (1 << 0)/* GlobalPlatform compliant TEE */
+
+/*
+ * TEE Implementation ID
+ */
+#define TEE_IMPL_ID_OPTEE 1
+
+/*
+ * OP-TEE specific capabilities
+ */
+#define TEE_OPTEE_CAP_TZ (1 << 0)
+
+/**
+ * struct tee_ioctl_version_data - TEE version
+ * @impl_id: [out] TEE implementation id
+ * @impl_caps: [out] Implementation specific capabilities
+ * @gen_caps: [out] Generic capabilities, defined by TEE_GEN_CAPS_* above
+ *
+ * Identifies the TEE implementation, @impl_id is one of TEE_IMPL_ID_* above.
+ * @impl_caps is implementation specific, for example TEE_OPTEE_CAP_*
+ * is valid when @impl_id == TEE_IMPL_ID_OPTEE.
+ */
+struct tee_ioctl_version_data {
+ __u32 impl_id;
+ __u32 impl_caps;
+ __u32 gen_caps;
+};
+
+/**
+ * TEE_IOC_VERSION - query version of TEE
+ *
+ * Takes a tee_ioctl_version_data struct and returns with the TEE version
+ * data filled in.
+ */
+#define TEE_IOC_VERSION _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 0, \
+ struct tee_ioctl_version_data)
+
+/**
+ * struct tee_ioctl_shm_alloc_data - Shared memory allocate argument
+ * @size: [in/out] Size of shared memory to allocate
+ * @flags: [in/out] Flags to/from allocation.
+ * @id: [out] Identifier of the shared memory
+ *
+ * The flags field should currently be zero as input. Updated by the call
+ * with actual flags as defined by TEE_IOCTL_SHM_* above.
+ * This structure is used as argument for TEE_IOC_SHM_ALLOC below.
+ */
+struct tee_ioctl_shm_alloc_data {
+ __u64 size;
+ __u32 flags;
+ __s32 id;
+};
+
+/**
+ * TEE_IOC_SHM_ALLOC - allocate shared memory
+ *
+ * Allocates shared memory between the user space process and secure OS.
+ *
+ * Returns a file descriptor on success or < 0 on failure
+ *
+ * The returned file descriptor is used to map the shared memory into user
+ * space. The shared memory is freed when the descriptor is closed and the
+ * memory is unmapped.
+ */
+#define TEE_IOC_SHM_ALLOC _IOWR(TEE_IOC_MAGIC, TEE_IOC_BASE + 1, \
+ struct tee_ioctl_shm_alloc_data)
+
+/**
+ * struct tee_ioctl_buf_data - Variable sized buffer
+ * @buf_ptr: [in] A __user pointer to a buffer
+ * @buf_len: [in] Length of the buffer above
+ *
+ * Used as argument for TEE_IOC_OPEN_SESSION, TEE_IOC_INVOKE,
+ * TEE_IOC_SUPPL_RECV, and TEE_IOC_SUPPL_SEND below.
+ */
+struct tee_ioctl_buf_data {
+ __u64 buf_ptr;
+ __u64 buf_len;
+};
+
+/*
+ * Attributes for struct tee_ioctl_param, selects field in the union
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_NONE 0 /* parameter not used */
+
+/*
+ * These defines value parameters (struct tee_ioctl_param_value)
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INPUT 1
+#define TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_OUTPUT 2
+#define TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT 3 /* input and output */
+
+/*
+ * These defines shared memory reference parameters (struct
+ * tee_ioctl_param_memref)
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT 5
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT 6
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT 7 /* input and output */
+
+/*
+ * Mask for the type part of the attribute, leaves room for more types
+ */
+#define TEE_IOCTL_PARAM_ATTR_TYPE_MASK 0xff
+
+/*
+ * Matches TEEC_LOGIN_* in GP TEE Client API
+ * Are only defined for GP compliant TEEs
+ */
+#define TEE_IOCTL_LOGIN_PUBLIC 0
+#define TEE_IOCTL_LOGIN_USER 1
+#define TEE_IOCTL_LOGIN_GROUP 2
+#define TEE_IOCTL_LOGIN_APPLICATION 4
+#define TEE_IOCTL_LOGIN_USER_APPLICATION 5
+#define TEE_IOCTL_LOGIN_GROUP_APPLICATION 6
+
+/**
+ * struct tee_ioctl_param - parameter
+ * @attr: attributes
+ * @a: if a memref, offset into the shared memory object, else a value parameter
+ * @b: if a memref, size of the buffer, else a value parameter
+ * @c: if a memref, shared memory identifier, else a value parameter
+ *
+ * @attr & TEE_PARAM_ATTR_TYPE_MASK indicates if memref or value is used in
+ * the union. TEE_PARAM_ATTR_TYPE_VALUE_* indicates value and
+ * TEE_PARAM_ATTR_TYPE_MEMREF_* indicates memref. TEE_PARAM_ATTR_TYPE_NONE
+ * indicates that none of the members are used.
+ *
+ * Shared memory is allocated with TEE_IOC_SHM_ALLOC which returns an
+ * identifier representing the shared memory object. A memref can reference
+ * a part of a shared memory by specifying an offset (@a) and size (@b) of
+ * the object. To supply the entire shared memory object set the offset
+ * (@a) to 0 and size (@b) to the previously returned size of the object.
+ */
+struct tee_ioctl_param {
+ __u64 attr;
+ __u64 a;
+ __u64 b;
+ __u64 c;
+};
+
+#define TEE_IOCTL_UUID_LEN 16
+
+/**
+ * struct tee_ioctl_open_session_arg - Open session argument
+ * @uuid: [in] UUID of the Trusted Application
+ * @clnt_uuid: [in] UUID of client
+ * @clnt_login: [in] Login class of client, TEE_IOCTL_LOGIN_* above
+ * @cancel_id: [in] Cancellation id, a unique value to identify this request
+ * @session: [out] Session id
+ * @ret: [out] return value
+ * @ret_origin [out] origin of the return value
+ * @num_params [in] number of parameters following this struct
+ */
+struct tee_ioctl_open_session_arg {
+ __u8 uuid[TEE_IOCTL_UUID_LEN];
+ __u8 clnt_uuid[TEE_IOCTL_UUID_LEN];
+ __u32 clnt_login;
+ __u32 cancel_id;
+ __u32 session;
+ __u32 ret;
+ __u32 ret_origin;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_OPEN_SESSION - opens a session to a Trusted Application
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_ioctl_open_session_arg followed by any array of struct
+ * tee_ioctl_param
+ */
+#define TEE_IOC_OPEN_SESSION _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 2, \
+ struct tee_ioctl_buf_data)
+
+/**
+ * struct tee_ioctl_invoke_func_arg - Invokes a function in a Trusted
+ * Application
+ * @func: [in] Trusted Application function, specific to the TA
+ * @session: [in] Session id
+ * @cancel_id: [in] Cancellation id, a unique value to identify this request
+ * @ret: [out] return value
+ * @ret_origin [out] origin of the return value
+ * @num_params [in] number of parameters following this struct
+ */
+struct tee_ioctl_invoke_arg {
+ __u32 func;
+ __u32 session;
+ __u32 cancel_id;
+ __u32 ret;
+ __u32 ret_origin;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_INVOKE - Invokes a function in a Trusted Application
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_invoke_func_arg followed by any array of struct tee_param
+ */
+#define TEE_IOC_INVOKE _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 3, \
+ struct tee_ioctl_buf_data)
+
+/**
+ * struct tee_ioctl_cancel_arg - Cancels an open session or invoke ioctl
+ * @cancel_id: [in] Cancellation id, a unique value to identify this request
+ * @session: [in] Session id, if the session is opened, else set to 0
+ */
+struct tee_ioctl_cancel_arg {
+ __u32 cancel_id;
+ __u32 session;
+};
+
+/**
+ * TEE_IOC_CANCEL - Cancels an open session or invoke
+ */
+#define TEE_IOC_CANCEL _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 4, \
+ struct tee_ioctl_cancel_arg)
+
+/**
+ * struct tee_ioctl_close_session_arg - Closes an open session
+ * @session: [in] Session id
+ */
+struct tee_ioctl_close_session_arg {
+ __u32 session;
+};
+
+/**
+ * TEE_IOC_CLOSE_SESSION - Closes a session
+ */
+#define TEE_IOC_CLOSE_SESSION _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 5, \
+ struct tee_ioctl_close_session_arg)
+
+/**
+ * struct tee_iocl_supp_recv_arg - Receive a request for a supplicant function
+ * @func: [in] supplicant function
+ * @num_params [in/out] number of parameters following this struct
+ *
+ * @num_params is the number of params that tee-supplicant has room to
+ * receive when input, @num_params is the number of actual params
+ * tee-supplicant receives when output.
+ */
+struct tee_iocl_supp_recv_arg {
+ __u32 func;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_SUPPL_RECV - Receive a request for a supplicant function
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_iocl_supp_recv_arg followed by any array of struct tee_param
+ */
+#define TEE_IOC_SUPPL_RECV _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 6, \
+ struct tee_ioctl_buf_data)
+
+/**
+ * struct tee_iocl_supp_send_arg - Send a response to a received request
+ * @ret: [out] return value
+ * @num_params [in] number of parameters following this struct
+ */
+struct tee_iocl_supp_send_arg {
+ __u32 ret;
+ __u32 num_params;
+ /* num_params tells the actual number of element in params */
+ struct tee_ioctl_param params[];
+};
+
+/**
+ * TEE_IOC_SUPPL_SEND - Receive a request for a supplicant function
+ *
+ * Takes a struct tee_ioctl_buf_data which contains a struct
+ * tee_iocl_supp_send_arg followed by any array of struct tee_param
+ */
+#define TEE_IOC_SUPPL_SEND _IOR(TEE_IOC_MAGIC, TEE_IOC_BASE + 7, \
+ struct tee_ioctl_buf_data)
+
+/*
+ * Five syscalls are used when communicating with the TEE driver.
+ * open(): opens the device associated with the driver
+ * ioctl(): as described above operating on the file descriptor from open()
+ * close(): two cases
+ * - closes the device file descriptor
+ * - closes a file descriptor connected to allocated shared memory
+ * mmap(): maps shared memory into user space using information from struct
+ * tee_ioctl_shm_alloc_data
+ * munmap(): unmaps previously shared memory
+ */
+
+#endif /*__TEE_H*/
+++ /dev/null
-# UAPI Header export list
-header-y += audio.h
-header-y += cdc.h
-header-y += cdc-wdm.h
-header-y += ch11.h
-header-y += ch9.h
-header-y += functionfs.h
-header-y += g_printer.h
-header-y += gadgetfs.h
-header-y += midi.h
-header-y += tmc.h
-header-y += video.h
+++ /dev/null
-# UAPI Header export list
-header-y += i2400m.h
+++ /dev/null
-# misc Header export list
-header-y += cxl.h
+++ /dev/null
-# UAPI Header export list
-header-y += inftl-user.h
-header-y += mtd-abi.h
-header-y += mtd-user.h
-header-y += nftl-user.h
-header-y += ubi-user.h
+++ /dev/null
-# UAPI Header export list
-header-y += ib_user_cm.h
-header-y += rdma_user_ioctl.h
-header-y += ib_user_mad.h
-header-y += ib_user_sa.h
-header-y += ib_user_verbs.h
-header-y += rdma_netlink.h
-header-y += rdma_user_cm.h
-header-y += hfi/
-header-y += rdma_user_rxe.h
-header-y += cxgb3-abi.h
-header-y += cxgb4-abi.h
-header-y += mlx4-abi.h
-header-y += mlx5-abi.h
-header-y += mthca-abi.h
-header-y += nes-abi.h
-header-y += ocrdma-abi.h
-header-y += hns-abi.h
-header-y += vmw_pvrdma-abi.h
-header-y += qedr-abi.h
#ifndef __BNXT_RE_UVERBS_ABI_H__
#define __BNXT_RE_UVERBS_ABI_H__
+#include <linux/types.h>
+
#define BNXT_RE_ABI_VERSION 1
struct bnxt_re_uctx_resp {
+++ /dev/null
-# UAPI Header export list
-header-y += hfi1_user.h
-header-y += hfi1_ioctl.h
__u32 ind_tbl_handle;
};
+#define IB_DEVICE_NAME_MAX 64
+
#endif /* IB_USER_VERBS_H */
+++ /dev/null
-# UAPI Header export list
-header-y += fc/
-header-y += scsi_bsg_fc.h
-header-y += scsi_netlink.h
-header-y += scsi_netlink_fc.h
-header-y += cxlflash_ioctl.h
+++ /dev/null
-# UAPI Header export list
-header-y += fc_els.h
-header-y += fc_fs.h
-header-y += fc_gs.h
-header-y += fc_ns.h
+++ /dev/null
-# UAPI Header export list
-header-y += asequencer.h
-header-y += asoc.h
-header-y += asound.h
-header-y += asound_fm.h
-header-y += compress_offload.h
-header-y += compress_params.h
-header-y += emu10k1.h
-header-y += firewire.h
-header-y += hdsp.h
-header-y += hdspm.h
-header-y += sb16_csp.h
-header-y += sfnt_info.h
-header-y += tlv.h
-header-y += usb_stream.h
-header-y += snd_sst_tokens.h
+++ /dev/null
-# UAPI Header export list
-header-y += edid.h
-header-y += sisfb.h
-header-y += uvesafb.h
+++ /dev/null
-# UAPI Header export list
-header-y += evtchn.h
-header-y += gntalloc.h
-header-y += gntdev.h
-header-y += privcmd.h
config SRCU
bool
+ default y
help
This option selects the sleepable version of RCU. This version
permits arbitrary sleeping or blocking within RCU read-side critical
sections.
+config CLASSIC_SRCU
+ bool "Use v4.11 classic SRCU implementation"
+ default n
+ depends on RCU_EXPERT && SRCU
+ help
+ This option selects the traditional well-tested classic SRCU
+ implementation from v4.11, as might be desired for enterprise
+ Linux distributions. Without this option, the shiny new
+ Tiny SRCU and Tree SRCU implementations are used instead.
+ At some point, it is hoped that Tiny SRCU and Tree SRCU
+ will accumulate enough test time and confidence to allow
+ Classic SRCU to be dropped entirely.
+
+ Say Y if you need a rock-solid SRCU.
+
+ Say N if you would like help test Tree SRCU.
+
+config TINY_SRCU
+ bool
+ default y if SRCU && TINY_RCU && !CLASSIC_SRCU
+ help
+ This option selects the single-CPU non-preemptible version of SRCU.
+
+config TREE_SRCU
+ bool
+ default y if SRCU && !TINY_RCU && !CLASSIC_SRCU
+ help
+ This option selects the full-fledged version of SRCU.
+
config TASKS_RCU
bool
default n
the tiny variants to disable RCU CPU stall warnings, while
making these warnings mandatory for the tree variants.
+config RCU_NEED_SEGCBLIST
+ def_bool ( TREE_RCU || PREEMPT_RCU || TINY_SRCU || TREE_SRCU )
+
config CONTEXT_TRACKING
bool
initialization. These systems tend to run CPU-bound, and thus
are not helped by synchronized interrupts, and thus tend to
skew them, which reduces lock contention enough that large
- leaf-level fanouts work well.
+ leaf-level fanouts work well. That said, setting leaf-level
+ fanout to a large number will likely cause problematic
+ lock contention on the leaf-level rcu_node structures unless
+ you boot with the skew_tick kernel parameter.
Select a specific number if testing RCU itself.
- Select the maximum permissible value for large systems.
+ Select the maximum permissible value for large systems, but
+ please understand that you may also need to set the skew_tick
+ kernel boot parameter to avoid contention on the rcu_node
+ structure's locks.
Take the default if unsure.
[BPF_EXIT >> 4] = "exit",
};
-static void print_bpf_insn(struct bpf_insn *insn)
+static void print_bpf_insn(const struct bpf_verifier_env *env,
+ const struct bpf_insn *insn)
{
u8 class = BPF_CLASS(insn->code);
insn->code,
bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
insn->src_reg, insn->imm);
- } else if (BPF_MODE(insn->code) == BPF_IMM) {
- verbose("(%02x) r%d = 0x%x\n",
- insn->code, insn->dst_reg, insn->imm);
+ } else if (BPF_MODE(insn->code) == BPF_IMM &&
+ BPF_SIZE(insn->code) == BPF_DW) {
+ /* At this point, we already made sure that the second
+ * part of the ldimm64 insn is accessible.
+ */
+ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
+ bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+
+ if (map_ptr && !env->allow_ptr_leaks)
+ imm = 0;
+
+ verbose("(%02x) r%d = 0x%llx\n", insn->code,
+ insn->dst_reg, (unsigned long long)imm);
} else {
verbose("BUG_ld_%02x\n", insn->code);
return;
if (log_level) {
verbose("%d: ", insn_idx);
- print_bpf_insn(insn);
+ print_bpf_insn(env, insn);
}
err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
if (atomic_dec_and_test(&sighand->count)) {
signalfd_cleanup(sighand);
/*
- * sighand_cachep is SLAB_DESTROY_BY_RCU so we can free it
+ * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
* without an RCU grace period, see __lock_task_sighand().
*/
kmem_cache_free(sighand_cachep, sighand);
{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,
return 0;
printk("\n");
- printk("======================================================\n");
- printk("[ INFO: possible circular locking dependency detected ]\n");
+ pr_warn("======================================================\n");
+ pr_warn("WARNING: possible circular locking dependency detected\n");
print_kernel_ident();
- printk("-------------------------------------------------------\n");
+ pr_warn("------------------------------------------------------\n");
printk("%s/%d is trying to acquire lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(check_src);
return 0;
printk("\n");
- printk("======================================================\n");
- printk("[ INFO: %s-safe -> %s-unsafe lock order detected ]\n",
+ pr_warn("=====================================================\n");
+ pr_warn("WARNING: %s-safe -> %s-unsafe lock order detected\n",
irqclass, irqclass);
print_kernel_ident();
- printk("------------------------------------------------------\n");
+ pr_warn("-----------------------------------------------------\n");
printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n",
curr->comm, task_pid_nr(curr),
curr->hardirq_context, hardirq_count() >> HARDIRQ_SHIFT,
return 0;
printk("\n");
- printk("=============================================\n");
- printk("[ INFO: possible recursive locking detected ]\n");
+ pr_warn("============================================\n");
+ pr_warn("WARNING: possible recursive locking detected\n");
print_kernel_ident();
- printk("---------------------------------------------\n");
+ pr_warn("--------------------------------------------\n");
printk("%s/%d is trying to acquire lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(next);
struct lock_chain *chain)
{
printk("\n");
- printk("======================\n");
- printk("[chain_key collision ]\n");
+ pr_warn("============================\n");
+ pr_warn("WARNING: chain_key collision\n");
print_kernel_ident();
- printk("----------------------\n");
+ pr_warn("----------------------------\n");
printk("%s/%d: ", current->comm, task_pid_nr(current));
printk("Hash chain already cached but the contents don't match!\n");
return 0;
printk("\n");
- printk("=================================\n");
- printk("[ INFO: inconsistent lock state ]\n");
+ pr_warn("================================\n");
+ pr_warn("WARNING: inconsistent lock state\n");
print_kernel_ident();
- printk("---------------------------------\n");
+ pr_warn("--------------------------------\n");
printk("inconsistent {%s} -> {%s} usage.\n",
usage_str[prev_bit], usage_str[new_bit]);
return 0;
printk("\n");
- printk("=========================================================\n");
- printk("[ INFO: possible irq lock inversion dependency detected ]\n");
+ pr_warn("========================================================\n");
+ pr_warn("WARNING: possible irq lock inversion dependency detected\n");
print_kernel_ident();
- printk("---------------------------------------------------------\n");
+ pr_warn("--------------------------------------------------------\n");
printk("%s/%d just changed the state of lock:\n",
curr->comm, task_pid_nr(curr));
print_lock(this);
return 0;
printk("\n");
- printk("==================================\n");
- printk("[ BUG: Nested lock was not taken ]\n");
+ pr_warn("==================================\n");
+ pr_warn("WARNING: Nested lock was not taken\n");
print_kernel_ident();
- printk("----------------------------------\n");
+ pr_warn("----------------------------------\n");
printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr));
print_lock(hlock);
return 0;
printk("\n");
- printk("=====================================\n");
- printk("[ BUG: bad unlock balance detected! ]\n");
+ pr_warn("=====================================\n");
+ pr_warn("WARNING: bad unlock balance detected!\n");
print_kernel_ident();
- printk("-------------------------------------\n");
+ pr_warn("-------------------------------------\n");
printk("%s/%d is trying to release lock (",
curr->comm, task_pid_nr(curr));
print_lockdep_cache(lock);
return 0;
printk("\n");
- printk("=================================\n");
- printk("[ BUG: bad contention detected! ]\n");
+ pr_warn("=================================\n");
+ pr_warn("WARNING: bad contention detected!\n");
print_kernel_ident();
- printk("---------------------------------\n");
+ pr_warn("---------------------------------\n");
printk("%s/%d is trying to contend lock (",
curr->comm, task_pid_nr(curr));
print_lockdep_cache(lock);
return;
printk("\n");
- printk("=========================\n");
- printk("[ BUG: held lock freed! ]\n");
+ pr_warn("=========================\n");
+ pr_warn("WARNING: held lock freed!\n");
print_kernel_ident();
- printk("-------------------------\n");
+ pr_warn("-------------------------\n");
printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n",
curr->comm, task_pid_nr(curr), mem_from, mem_to-1);
print_lock(hlock);
return;
printk("\n");
- printk("=====================================\n");
- printk("[ BUG: %s/%d still has locks held! ]\n",
+ pr_warn("====================================\n");
+ pr_warn("WARNING: %s/%d still has locks held!\n",
current->comm, task_pid_nr(current));
print_kernel_ident();
- printk("-------------------------------------\n");
+ pr_warn("------------------------------------\n");
lockdep_print_held_locks(current);
printk("\nstack backtrace:\n");
dump_stack();
} while_each_thread(g, p);
printk("\n");
- printk("=============================================\n\n");
+ pr_warn("=============================================\n\n");
if (unlock)
read_unlock(&tasklist_lock);
if (!debug_locks_off())
return;
printk("\n");
- printk("================================================\n");
- printk("[ BUG: lock held when returning to user space! ]\n");
+ pr_warn("================================================\n");
+ pr_warn("WARNING: lock held when returning to user space!\n");
print_kernel_ident();
- printk("------------------------------------------------\n");
+ pr_warn("------------------------------------------------\n");
printk("%s/%d is leaving the kernel with locks still held!\n",
curr->comm, curr->pid);
lockdep_print_held_locks(curr);
#endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
/* Note: the following can be executed concurrently, so be careful. */
printk("\n");
- pr_err("===============================\n");
- pr_err("[ ERR: suspicious RCU usage. ]\n");
+ pr_warn("=============================\n");
+ pr_warn("WARNING: suspicious RCU usage\n");
print_kernel_ident();
- pr_err("-------------------------------\n");
- pr_err("%s:%d %s!\n", file, line, s);
- pr_err("\nother info that might help us debug this:\n\n");
- pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
+ pr_warn("-----------------------------\n");
+ printk("%s:%d %s!\n", file, line, s);
+ printk("\nother info that might help us debug this:\n\n");
+ printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
!rcu_lockdep_current_cpu_online()
? "RCU used illegally from offline CPU!\n"
: !rcu_is_watching()
return;
}
- printk("\n============================================\n");
- printk( "[ BUG: circular locking deadlock detected! ]\n");
- printk("%s\n", print_tainted());
- printk( "--------------------------------------------\n");
+ pr_warn("\n");
+ pr_warn("============================================\n");
+ pr_warn("WARNING: circular locking deadlock detected!\n");
+ pr_warn("%s\n", print_tainted());
+ pr_warn("--------------------------------------------\n");
printk("%s/%d is deadlocking current task %s/%d\n\n",
task->comm, task_pid_nr(task),
current->comm, task_pid_nr(current));
if (!pm_freezing)
atomic_inc(&system_freezing_cnt);
- pm_wakeup_clear();
+ pm_wakeup_clear(true);
pr_info("Freezing user space processes ... ");
pm_freezing = true;
error = try_to_freeze_tasks(true);
static void freeze_enter(void)
{
+ trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, true);
+
spin_lock_irq(&suspend_freeze_lock);
if (pm_wakeup_pending())
goto out;
out:
suspend_freeze_state = FREEZE_STATE_NONE;
spin_unlock_irq(&suspend_freeze_lock);
+
+ trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, false);
+}
+
+static void s2idle_loop(void)
+{
+ do {
+ freeze_enter();
+
+ if (freeze_ops && freeze_ops->wake)
+ freeze_ops->wake();
+
+ dpm_resume_noirq(PMSG_RESUME);
+ if (freeze_ops && freeze_ops->sync)
+ freeze_ops->sync();
+
+ if (pm_wakeup_pending())
+ break;
+
+ pm_wakeup_clear(false);
+ } while (!dpm_suspend_noirq(PMSG_SUSPEND));
}
void freeze_wake(void)
* all the devices are suspended.
*/
if (state == PM_SUSPEND_FREEZE) {
- trace_suspend_resume(TPS("machine_suspend"), state, true);
- freeze_enter();
- trace_suspend_resume(TPS("machine_suspend"), state, false);
- goto Platform_wake;
+ s2idle_loop();
+ goto Platform_early_resume;
}
error = disable_nonboot_cpus();
KCOV_INSTRUMENT := n
obj-y += update.o sync.o
-obj-$(CONFIG_SRCU) += srcu.o
+obj-$(CONFIG_CLASSIC_SRCU) += srcu.o
+obj-$(CONFIG_TREE_SRCU) += srcutree.o
+obj-$(CONFIG_TINY_SRCU) += srcutiny.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o
obj-$(CONFIG_TREE_RCU) += tree.o
obj-$(CONFIG_PREEMPT_RCU) += tree.o
obj-$(CONFIG_TREE_RCU_TRACE) += tree_trace.o
obj-$(CONFIG_TINY_RCU) += tiny.o
+obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o
#define DYNTICK_TASK_EXIT_IDLE (DYNTICK_TASK_NEST_VALUE + \
DYNTICK_TASK_FLAG)
+
+/*
+ * Grace-period counter management.
+ */
+
+#define RCU_SEQ_CTR_SHIFT 2
+#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1)
+
+/*
+ * Return the counter portion of a sequence number previously returned
+ * by rcu_seq_snap() or rcu_seq_current().
+ */
+static inline unsigned long rcu_seq_ctr(unsigned long s)
+{
+ return s >> RCU_SEQ_CTR_SHIFT;
+}
+
+/*
+ * Return the state portion of a sequence number previously returned
+ * by rcu_seq_snap() or rcu_seq_current().
+ */
+static inline int rcu_seq_state(unsigned long s)
+{
+ return s & RCU_SEQ_STATE_MASK;
+}
+
+/*
+ * Set the state portion of the pointed-to sequence number.
+ * The caller is responsible for preventing conflicting updates.
+ */
+static inline void rcu_seq_set_state(unsigned long *sp, int newstate)
+{
+ WARN_ON_ONCE(newstate & ~RCU_SEQ_STATE_MASK);
+ WRITE_ONCE(*sp, (*sp & ~RCU_SEQ_STATE_MASK) + newstate);
+}
+
+/* Adjust sequence number for start of update-side operation. */
+static inline void rcu_seq_start(unsigned long *sp)
+{
+ WRITE_ONCE(*sp, *sp + 1);
+ smp_mb(); /* Ensure update-side operation after counter increment. */
+ WARN_ON_ONCE(rcu_seq_state(*sp) != 1);
+}
+
+/* Adjust sequence number for end of update-side operation. */
+static inline void rcu_seq_end(unsigned long *sp)
+{
+ smp_mb(); /* Ensure update-side operation before counter increment. */
+ WARN_ON_ONCE(!rcu_seq_state(*sp));
+ WRITE_ONCE(*sp, (*sp | RCU_SEQ_STATE_MASK) + 1);
+}
+
+/* Take a snapshot of the update side's sequence number. */
+static inline unsigned long rcu_seq_snap(unsigned long *sp)
+{
+ unsigned long s;
+
+ s = (READ_ONCE(*sp) + 2 * RCU_SEQ_STATE_MASK + 1) & ~RCU_SEQ_STATE_MASK;
+ smp_mb(); /* Above access must not bleed into critical section. */
+ return s;
+}
+
+/* Return the current value the update side's sequence number, no ordering. */
+static inline unsigned long rcu_seq_current(unsigned long *sp)
+{
+ return READ_ONCE(*sp);
+}
+
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not a
+ * full update-side operation has occurred.
+ */
+static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
+{
+ return ULONG_CMP_GE(READ_ONCE(*sp), s);
+}
+
/*
* debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
* by call_rcu() and rcu callback execution, and are therefore not part of the
rcu_lock_acquire(&rcu_callback_map);
if (__is_kfree_rcu_offset(offset)) {
- RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset));
+ RCU_TRACE(trace_rcu_invoke_kfree_callback(rn, head, offset);)
kfree((void *)head - offset);
rcu_lock_release(&rcu_callback_map);
return true;
} else {
- RCU_TRACE(trace_rcu_invoke_callback(rn, head));
+ RCU_TRACE(trace_rcu_invoke_callback(rn, head);)
head->func(head);
rcu_lock_release(&rcu_callback_map);
return false;
*/
extern void resched_cpu(int cpu);
+#if defined(SRCU) || !defined(TINY_RCU)
+
+#include <linux/rcu_node_tree.h>
+
+extern int rcu_num_lvls;
+extern int num_rcu_lvl[];
+extern int rcu_num_nodes;
+static bool rcu_fanout_exact;
+static int rcu_fanout_leaf;
+
+/*
+ * Compute the per-level fanout, either using the exact fanout specified
+ * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
+ */
+static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
+{
+ int i;
+
+ if (rcu_fanout_exact) {
+ levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+ for (i = rcu_num_lvls - 2; i >= 0; i--)
+ levelspread[i] = RCU_FANOUT;
+ } else {
+ int ccur;
+ int cprv;
+
+ cprv = nr_cpu_ids;
+ for (i = rcu_num_lvls - 1; i >= 0; i--) {
+ ccur = levelcnt[i];
+ levelspread[i] = (cprv + ccur - 1) / ccur;
+ cprv = ccur;
+ }
+ }
+}
+
+/*
+ * Do a full breadth-first scan of the rcu_node structures for the
+ * specified rcu_state structure.
+ */
+#define rcu_for_each_node_breadth_first(rsp, rnp) \
+ for ((rnp) = &(rsp)->node[0]; \
+ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+
+/*
+ * Do a breadth-first scan of the non-leaf rcu_node structures for the
+ * specified rcu_state structure. Note that if there is a singleton
+ * rcu_node tree with but one rcu_node structure, this loop is a no-op.
+ */
+#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
+ for ((rnp) = &(rsp)->node[0]; \
+ (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
+
+/*
+ * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
+ * structure. Note that if there is a singleton rcu_node tree with but
+ * one rcu_node structure, this loop -will- visit the rcu_node structure.
+ * It is still a leaf node, even if it is also the root node.
+ */
+#define rcu_for_each_leaf_node(rsp, rnp) \
+ for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
+ (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
+
+/*
+ * Iterate over all possible CPUs in a leaf RCU node.
+ */
+#define for_each_leaf_node_possible_cpu(rnp, cpu) \
+ for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
+ cpu <= rnp->grphi; \
+ cpu = cpumask_next((cpu), cpu_possible_mask))
+
+#endif /* #if defined(SRCU) || !defined(TINY_RCU) */
+
#endif /* __LINUX_RCU_H */
--- /dev/null
+/*
+ * RCU segmented callback lists, function definitions
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2017
+ *
+ * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+
+#include "rcu_segcblist.h"
+
+/* Initialize simple callback list. */
+void rcu_cblist_init(struct rcu_cblist *rclp)
+{
+ rclp->head = NULL;
+ rclp->tail = &rclp->head;
+ rclp->len = 0;
+ rclp->len_lazy = 0;
+}
+
+/*
+ * Debug function to actually count the number of callbacks.
+ * If the number exceeds the limit specified, return -1.
+ */
+long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim)
+{
+ int cnt = 0;
+ struct rcu_head **rhpp = &rclp->head;
+
+ for (;;) {
+ if (!*rhpp)
+ return cnt;
+ if (++cnt > lim)
+ return -1;
+ rhpp = &(*rhpp)->next;
+ }
+}
+
+/*
+ * Dequeue the oldest rcu_head structure from the specified callback
+ * list. This function assumes that the callback is non-lazy, but
+ * the caller can later invoke rcu_cblist_dequeued_lazy() if it
+ * finds otherwise (and if it cares about laziness). This allows
+ * different users to have different ways of determining laziness.
+ */
+struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp)
+{
+ struct rcu_head *rhp;
+
+ rhp = rclp->head;
+ if (!rhp)
+ return NULL;
+ rclp->len--;
+ rclp->head = rhp->next;
+ if (!rclp->head)
+ rclp->tail = &rclp->head;
+ return rhp;
+}
+
+/*
+ * Initialize an rcu_segcblist structure.
+ */
+void rcu_segcblist_init(struct rcu_segcblist *rsclp)
+{
+ int i;
+
+ BUILD_BUG_ON(RCU_NEXT_TAIL + 1 != ARRAY_SIZE(rsclp->gp_seq));
+ BUILD_BUG_ON(ARRAY_SIZE(rsclp->tails) != ARRAY_SIZE(rsclp->gp_seq));
+ rsclp->head = NULL;
+ for (i = 0; i < RCU_CBLIST_NSEGS; i++)
+ rsclp->tails[i] = &rsclp->head;
+ rsclp->len = 0;
+ rsclp->len_lazy = 0;
+}
+
+/*
+ * Disable the specified rcu_segcblist structure, so that callbacks can
+ * no longer be posted to it. This structure must be empty.
+ */
+void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
+{
+ WARN_ON_ONCE(!rcu_segcblist_empty(rsclp));
+ WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp));
+ WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp));
+ rsclp->tails[RCU_NEXT_TAIL] = NULL;
+}
+
+/*
+ * Is the specified segment of the specified rcu_segcblist structure
+ * empty of callbacks?
+ */
+bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg)
+{
+ if (seg == RCU_DONE_TAIL)
+ return &rsclp->head == rsclp->tails[RCU_DONE_TAIL];
+ return rsclp->tails[seg - 1] == rsclp->tails[seg];
+}
+
+/*
+ * Does the specified rcu_segcblist structure contain callbacks that
+ * are ready to be invoked?
+ */
+bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp)
+{
+ return rcu_segcblist_is_enabled(rsclp) &&
+ &rsclp->head != rsclp->tails[RCU_DONE_TAIL];
+}
+
+/*
+ * Does the specified rcu_segcblist structure contain callbacks that
+ * are still pending, that is, not yet ready to be invoked?
+ */
+bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp)
+{
+ return rcu_segcblist_is_enabled(rsclp) &&
+ !rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL);
+}
+
+/*
+ * Dequeue and return the first ready-to-invoke callback. If there
+ * are no ready-to-invoke callbacks, return NULL. Disables interrupts
+ * to avoid interference. Does not protect from interference from other
+ * CPUs or tasks.
+ */
+struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp)
+{
+ unsigned long flags;
+ int i;
+ struct rcu_head *rhp;
+
+ local_irq_save(flags);
+ if (!rcu_segcblist_ready_cbs(rsclp)) {
+ local_irq_restore(flags);
+ return NULL;
+ }
+ rhp = rsclp->head;
+ BUG_ON(!rhp);
+ rsclp->head = rhp->next;
+ for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) {
+ if (rsclp->tails[i] != &rhp->next)
+ break;
+ rsclp->tails[i] = &rsclp->head;
+ }
+ smp_mb(); /* Dequeue before decrement for rcu_barrier(). */
+ WRITE_ONCE(rsclp->len, rsclp->len - 1);
+ local_irq_restore(flags);
+ return rhp;
+}
+
+/*
+ * Account for the fact that a previously dequeued callback turned out
+ * to be marked as lazy.
+ */
+void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ rsclp->len_lazy--;
+ local_irq_restore(flags);
+}
+
+/*
+ * Return a pointer to the first callback in the specified rcu_segcblist
+ * structure. This is useful for diagnostics.
+ */
+struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp)
+{
+ if (rcu_segcblist_is_enabled(rsclp))
+ return rsclp->head;
+ return NULL;
+}
+
+/*
+ * Return a pointer to the first pending callback in the specified
+ * rcu_segcblist structure. This is useful just after posting a given
+ * callback -- if that callback is the first pending callback, then
+ * you cannot rely on someone else having already started up the required
+ * grace period.
+ */
+struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp)
+{
+ if (rcu_segcblist_is_enabled(rsclp))
+ return *rsclp->tails[RCU_DONE_TAIL];
+ return NULL;
+}
+
+/*
+ * Does the specified rcu_segcblist structure contain callbacks that
+ * have not yet been processed beyond having been posted, that is,
+ * does it contain callbacks in its last segment?
+ */
+bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp)
+{
+ return rcu_segcblist_is_enabled(rsclp) &&
+ !rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL);
+}
+
+/*
+ * Enqueue the specified callback onto the specified rcu_segcblist
+ * structure, updating accounting as needed. Note that the ->len
+ * field may be accessed locklessly, hence the WRITE_ONCE().
+ * The ->len field is used by rcu_barrier() and friends to determine
+ * if it must post a callback on this structure, and it is OK
+ * for rcu_barrier() to sometimes post callbacks needlessly, but
+ * absolutely not OK for it to ever miss posting a callback.
+ */
+void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy)
+{
+ WRITE_ONCE(rsclp->len, rsclp->len + 1); /* ->len sampled locklessly. */
+ if (lazy)
+ rsclp->len_lazy++;
+ smp_mb(); /* Ensure counts are updated before callback is enqueued. */
+ rhp->next = NULL;
+ *rsclp->tails[RCU_NEXT_TAIL] = rhp;
+ rsclp->tails[RCU_NEXT_TAIL] = &rhp->next;
+}
+
+/*
+ * Entrain the specified callback onto the specified rcu_segcblist at
+ * the end of the last non-empty segment. If the entire rcu_segcblist
+ * is empty, make no change, but return false.
+ *
+ * This is intended for use by rcu_barrier()-like primitives, -not-
+ * for normal grace-period use. IMPORTANT: The callback you enqueue
+ * will wait for all prior callbacks, NOT necessarily for a grace
+ * period. You have been warned.
+ */
+bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy)
+{
+ int i;
+
+ if (rcu_segcblist_n_cbs(rsclp) == 0)
+ return false;
+ WRITE_ONCE(rsclp->len, rsclp->len + 1);
+ if (lazy)
+ rsclp->len_lazy++;
+ smp_mb(); /* Ensure counts are updated before callback is entrained. */
+ rhp->next = NULL;
+ for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--)
+ if (rsclp->tails[i] != rsclp->tails[i - 1])
+ break;
+ *rsclp->tails[i] = rhp;
+ for (; i <= RCU_NEXT_TAIL; i++)
+ rsclp->tails[i] = &rhp->next;
+ return true;
+}
+
+/*
+ * Extract only the counts from the specified rcu_segcblist structure,
+ * and place them in the specified rcu_cblist structure. This function
+ * supports both callback orphaning and invocation, hence the separation
+ * of counts and callbacks. (Callbacks ready for invocation must be
+ * orphaned and adopted separately from pending callbacks, but counts
+ * apply to all callbacks. Locking must be used to make sure that
+ * both orphaned-callbacks lists are consistent.)
+ */
+void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ rclp->len_lazy += rsclp->len_lazy;
+ rclp->len += rsclp->len;
+ rsclp->len_lazy = 0;
+ WRITE_ONCE(rsclp->len, 0); /* ->len sampled locklessly. */
+}
+
+/*
+ * Extract only those callbacks ready to be invoked from the specified
+ * rcu_segcblist structure and place them in the specified rcu_cblist
+ * structure.
+ */
+void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ int i;
+
+ if (!rcu_segcblist_ready_cbs(rsclp))
+ return; /* Nothing to do. */
+ *rclp->tail = rsclp->head;
+ rsclp->head = *rsclp->tails[RCU_DONE_TAIL];
+ *rsclp->tails[RCU_DONE_TAIL] = NULL;
+ rclp->tail = rsclp->tails[RCU_DONE_TAIL];
+ for (i = RCU_CBLIST_NSEGS - 1; i >= RCU_DONE_TAIL; i--)
+ if (rsclp->tails[i] == rsclp->tails[RCU_DONE_TAIL])
+ rsclp->tails[i] = &rsclp->head;
+}
+
+/*
+ * Extract only those callbacks still pending (not yet ready to be
+ * invoked) from the specified rcu_segcblist structure and place them in
+ * the specified rcu_cblist structure. Note that this loses information
+ * about any callbacks that might have been partway done waiting for
+ * their grace period. Too bad! They will have to start over.
+ */
+void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ int i;
+
+ if (!rcu_segcblist_pend_cbs(rsclp))
+ return; /* Nothing to do. */
+ *rclp->tail = *rsclp->tails[RCU_DONE_TAIL];
+ rclp->tail = rsclp->tails[RCU_NEXT_TAIL];
+ *rsclp->tails[RCU_DONE_TAIL] = NULL;
+ for (i = RCU_DONE_TAIL + 1; i < RCU_CBLIST_NSEGS; i++)
+ rsclp->tails[i] = rsclp->tails[RCU_DONE_TAIL];
+}
+
+/*
+ * Insert counts from the specified rcu_cblist structure in the
+ * specified rcu_segcblist structure.
+ */
+void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ rsclp->len_lazy += rclp->len_lazy;
+ /* ->len sampled locklessly. */
+ WRITE_ONCE(rsclp->len, rsclp->len + rclp->len);
+ rclp->len_lazy = 0;
+ rclp->len = 0;
+}
+
+/*
+ * Move callbacks from the specified rcu_cblist to the beginning of the
+ * done-callbacks segment of the specified rcu_segcblist.
+ */
+void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ int i;
+
+ if (!rclp->head)
+ return; /* No callbacks to move. */
+ *rclp->tail = rsclp->head;
+ rsclp->head = rclp->head;
+ for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++)
+ if (&rsclp->head == rsclp->tails[i])
+ rsclp->tails[i] = rclp->tail;
+ else
+ break;
+ rclp->head = NULL;
+ rclp->tail = &rclp->head;
+}
+
+/*
+ * Move callbacks from the specified rcu_cblist to the end of the
+ * new-callbacks segment of the specified rcu_segcblist.
+ */
+void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp)
+{
+ if (!rclp->head)
+ return; /* Nothing to do. */
+ *rsclp->tails[RCU_NEXT_TAIL] = rclp->head;
+ rsclp->tails[RCU_NEXT_TAIL] = rclp->tail;
+ rclp->head = NULL;
+ rclp->tail = &rclp->head;
+}
+
+/*
+ * Advance the callbacks in the specified rcu_segcblist structure based
+ * on the current value passed in for the grace-period counter.
+ */
+void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq)
+{
+ int i, j;
+
+ WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
+ if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
+ return;
+
+ /*
+ * Find all callbacks whose ->gp_seq numbers indicate that they
+ * are ready to invoke, and put them into the RCU_DONE_TAIL segment.
+ */
+ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
+ if (ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
+ break;
+ rsclp->tails[RCU_DONE_TAIL] = rsclp->tails[i];
+ }
+
+ /* If no callbacks moved, nothing more need be done. */
+ if (i == RCU_WAIT_TAIL)
+ return;
+
+ /* Clean up tail pointers that might have been misordered above. */
+ for (j = RCU_WAIT_TAIL; j < i; j++)
+ rsclp->tails[j] = rsclp->tails[RCU_DONE_TAIL];
+
+ /*
+ * Callbacks moved, so clean up the misordered ->tails[] pointers
+ * that now point into the middle of the list of ready-to-invoke
+ * callbacks. The overall effect is to copy down the later pointers
+ * into the gap that was created by the now-ready segments.
+ */
+ for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
+ if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL])
+ break; /* No more callbacks. */
+ rsclp->tails[j] = rsclp->tails[i];
+ rsclp->gp_seq[j] = rsclp->gp_seq[i];
+ }
+}
+
+/*
+ * "Accelerate" callbacks based on more-accurate grace-period information.
+ * The reason for this is that RCU does not synchronize the beginnings and
+ * ends of grace periods, and that callbacks are posted locally. This in
+ * turn means that the callbacks must be labelled conservatively early
+ * on, as getting exact information would degrade both performance and
+ * scalability. When more accurate grace-period information becomes
+ * available, previously posted callbacks can be "accelerated", marking
+ * them to complete at the end of the earlier grace period.
+ *
+ * This function operates on an rcu_segcblist structure, and also the
+ * grace-period sequence number seq at which new callbacks would become
+ * ready to invoke. Returns true if there are callbacks that won't be
+ * ready to invoke until seq, false otherwise.
+ */
+bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq)
+{
+ int i;
+
+ WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp));
+ if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL))
+ return false;
+
+ /*
+ * Find the segment preceding the oldest segment of callbacks
+ * whose ->gp_seq[] completion is at or after that passed in via
+ * "seq", skipping any empty segments. This oldest segment, along
+ * with any later segments, can be merged in with any newly arrived
+ * callbacks in the RCU_NEXT_TAIL segment, and assigned "seq"
+ * as their ->gp_seq[] grace-period completion sequence number.
+ */
+ for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--)
+ if (rsclp->tails[i] != rsclp->tails[i - 1] &&
+ ULONG_CMP_LT(rsclp->gp_seq[i], seq))
+ break;
+
+ /*
+ * If all the segments contain callbacks that correspond to
+ * earlier grace-period sequence numbers than "seq", leave.
+ * Assuming that the rcu_segcblist structure has enough
+ * segments in its arrays, this can only happen if some of
+ * the non-done segments contain callbacks that really are
+ * ready to invoke. This situation will get straightened
+ * out by the next call to rcu_segcblist_advance().
+ *
+ * Also advance to the oldest segment of callbacks whose
+ * ->gp_seq[] completion is at or after that passed in via "seq",
+ * skipping any empty segments.
+ */
+ if (++i >= RCU_NEXT_TAIL)
+ return false;
+
+ /*
+ * Merge all later callbacks, including newly arrived callbacks,
+ * into the segment located by the for-loop above. Assign "seq"
+ * as the ->gp_seq[] value in order to correctly handle the case
+ * where there were no pending callbacks in the rcu_segcblist
+ * structure other than in the RCU_NEXT_TAIL segment.
+ */
+ for (; i < RCU_NEXT_TAIL; i++) {
+ rsclp->tails[i] = rsclp->tails[RCU_NEXT_TAIL];
+ rsclp->gp_seq[i] = seq;
+ }
+ return true;
+}
+
+/*
+ * Scan the specified rcu_segcblist structure for callbacks that need
+ * a grace period later than the one specified by "seq". We don't look
+ * at the RCU_DONE_TAIL or RCU_NEXT_TAIL segments because they don't
+ * have a grace-period sequence number.
+ */
+bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
+ unsigned long seq)
+{
+ int i;
+
+ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
+ if (rsclp->tails[i - 1] != rsclp->tails[i] &&
+ ULONG_CMP_LT(seq, rsclp->gp_seq[i]))
+ return true;
+ return false;
+}
--- /dev/null
+/*
+ * RCU segmented callback lists, internal-to-rcu header file
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright IBM Corporation, 2017
+ *
+ * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+ */
+
+#include <linux/rcu_segcblist.h>
+
+/*
+ * Account for the fact that a previously dequeued callback turned out
+ * to be marked as lazy.
+ */
+static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp)
+{
+ rclp->len_lazy--;
+}
+
+/*
+ * Interim function to return rcu_cblist head pointer. Longer term, the
+ * rcu_cblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head *rcu_cblist_head(struct rcu_cblist *rclp)
+{
+ return rclp->head;
+}
+
+/*
+ * Interim function to return rcu_cblist head pointer. Longer term, the
+ * rcu_cblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head **rcu_cblist_tail(struct rcu_cblist *rclp)
+{
+ WARN_ON_ONCE(!rclp->head);
+ return rclp->tail;
+}
+
+void rcu_cblist_init(struct rcu_cblist *rclp);
+long rcu_cblist_count_cbs(struct rcu_cblist *rclp, long lim);
+struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp);
+
+/*
+ * Is the specified rcu_segcblist structure empty?
+ *
+ * But careful! The fact that the ->head field is NULL does not
+ * necessarily imply that there are no callbacks associated with
+ * this structure. When callbacks are being invoked, they are
+ * removed as a group. If callback invocation must be preempted,
+ * the remaining callbacks will be added back to the list. Either
+ * way, the counts are updated later.
+ *
+ * So it is often the case that rcu_segcblist_n_cbs() should be used
+ * instead.
+ */
+static inline bool rcu_segcblist_empty(struct rcu_segcblist *rsclp)
+{
+ return !rsclp->head;
+}
+
+/* Return number of callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp)
+{
+ return READ_ONCE(rsclp->len);
+}
+
+/* Return number of lazy callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp)
+{
+ return rsclp->len_lazy;
+}
+
+/* Return number of lazy callbacks in segmented callback list. */
+static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp)
+{
+ return rsclp->len - rsclp->len_lazy;
+}
+
+/*
+ * Is the specified rcu_segcblist enabled, for example, not corresponding
+ * to an offline or callback-offloaded CPU?
+ */
+static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
+{
+ return !!rsclp->tails[RCU_NEXT_TAIL];
+}
+
+/*
+ * Are all segments following the specified segment of the specified
+ * rcu_segcblist structure empty of callbacks? (The specified
+ * segment might well contain callbacks.)
+ */
+static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg)
+{
+ return !*rsclp->tails[seg];
+}
+
+/*
+ * Interim function to return rcu_segcblist head pointer. Longer term, the
+ * rcu_segcblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head *rcu_segcblist_head(struct rcu_segcblist *rsclp)
+{
+ return rsclp->head;
+}
+
+/*
+ * Interim function to return rcu_segcblist head pointer. Longer term, the
+ * rcu_segcblist will be used more pervasively, removing the need for this
+ * function.
+ */
+static inline struct rcu_head **rcu_segcblist_tail(struct rcu_segcblist *rsclp)
+{
+ WARN_ON_ONCE(rcu_segcblist_empty(rsclp));
+ return rsclp->tails[RCU_NEXT_TAIL];
+}
+
+void rcu_segcblist_init(struct rcu_segcblist *rsclp);
+void rcu_segcblist_disable(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg);
+bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_dequeue(struct rcu_segcblist *rsclp);
+void rcu_segcblist_dequeued_lazy(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp);
+struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp);
+bool rcu_segcblist_new_cbs(struct rcu_segcblist *rsclp);
+void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy);
+bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp,
+ struct rcu_head *rhp, bool lazy);
+void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp,
+ struct rcu_cblist *rclp);
+void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq);
+bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq);
+bool rcu_segcblist_future_gp_needed(struct rcu_segcblist *rsclp,
+ unsigned long seq);
static void srcu_torture_stats(void)
{
- int cpu;
- int idx = srcu_ctlp->completed & 0x1;
+ int __maybe_unused cpu;
+ int idx;
- pr_alert("%s%s per-CPU(idx=%d):",
+#if defined(CONFIG_TREE_SRCU) || defined(CONFIG_CLASSIC_SRCU)
+#ifdef CONFIG_TREE_SRCU
+ idx = srcu_ctlp->srcu_idx & 0x1;
+#else /* #ifdef CONFIG_TREE_SRCU */
+ idx = srcu_ctlp->completed & 0x1;
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
+ pr_alert("%s%s Tree SRCU per-CPU(idx=%d):",
torture_type, TORTURE_FLAG, idx);
for_each_possible_cpu(cpu) {
unsigned long l0, l1;
unsigned long u0, u1;
long c0, c1;
- struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
+#ifdef CONFIG_TREE_SRCU
+ struct srcu_data *counts;
+ counts = per_cpu_ptr(srcu_ctlp->sda, cpu);
+ u0 = counts->srcu_unlock_count[!idx];
+ u1 = counts->srcu_unlock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
+ struct srcu_array *counts;
+
+ counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
u0 = counts->unlock_count[!idx];
u1 = counts->unlock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
/*
* Make sure that a lock is always counted if the corresponding
*/
smp_rmb();
+#ifdef CONFIG_TREE_SRCU
+ l0 = counts->srcu_lock_count[!idx];
+ l1 = counts->srcu_lock_count[idx];
+#else /* #ifdef CONFIG_TREE_SRCU */
l0 = counts->lock_count[!idx];
l1 = counts->lock_count[idx];
+#endif /* #else #ifdef CONFIG_TREE_SRCU */
c0 = l0 - u0;
c1 = l1 - u1;
pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
}
pr_cont("\n");
+#elif defined(CONFIG_TINY_SRCU)
+ idx = READ_ONCE(srcu_ctlp->srcu_idx) & 0x1;
+ pr_alert("%s%s Tiny SRCU per-CPU(idx=%d): (%d,%d)\n",
+ torture_type, TORTURE_FLAG, idx,
+ READ_ONCE(srcu_ctlp->srcu_lock_nesting[!idx]),
+ READ_ONCE(srcu_ctlp->srcu_lock_nesting[idx]));
+#endif
}
static void srcu_torture_synchronize_expedited(void)
cur_ops->stats();
if (rtcv_snap == rcu_torture_current_version &&
rcu_torture_current != NULL) {
- int __maybe_unused flags;
- unsigned long __maybe_unused gpnum;
- unsigned long __maybe_unused completed;
+ int __maybe_unused flags = 0;
+ unsigned long __maybe_unused gpnum = 0;
+ unsigned long __maybe_unused completed = 0;
rcutorture_get_gp_data(cur_ops->ttype,
&flags, &gpnum, &completed);
+ srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
+ &flags, &gpnum, &completed);
wtp = READ_ONCE(writer_task);
pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx\n",
rcu_torture_writer_state_getname(),
* Lai Jiangshan <laijs@cn.fujitsu.com>
*
* For detailed explanation of Read-Copy Update mechanism see -
- * Documentation/RCU/ *.txt
+ * Documentation/RCU/ *.txt
*
*/
* cleanup_srcu_struct - deconstruct a sleep-RCU structure
* @sp: structure to clean up.
*
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
+ * Must invoke this only after you are finished using a given srcu_struct
+ * that was initialized via init_srcu_struct(). This code does some
+ * probabalistic checking, spotting late uses of srcu_read_lock(),
+ * synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu().
+ * If any such late uses are detected, the per-CPU memory associated with
+ * the srcu_struct is simply leaked and WARN_ON() is invoked. If the
+ * caller frees the srcu_struct itself, a use-after-free crash will likely
+ * ensue, but at least there will be a warning printed.
*/
void cleanup_srcu_struct(struct srcu_struct *sp)
{
--- /dev/null
+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion,
+ * tiny version for non-preemptible single-CPU use.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2017
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ */
+
+#include <linux/export.h>
+#include <linux/mutex.h>
+#include <linux/preempt.h>
+#include <linux/rcupdate_wait.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/srcu.h>
+
+#include <linux/rcu_node_tree.h>
+#include "rcu_segcblist.h"
+#include "rcu.h"
+
+static int init_srcu_struct_fields(struct srcu_struct *sp)
+{
+ sp->srcu_lock_nesting[0] = 0;
+ sp->srcu_lock_nesting[1] = 0;
+ init_swait_queue_head(&sp->srcu_wq);
+ sp->srcu_gp_seq = 0;
+ rcu_segcblist_init(&sp->srcu_cblist);
+ sp->srcu_gp_running = false;
+ sp->srcu_gp_waiting = false;
+ sp->srcu_idx = 0;
+ INIT_WORK(&sp->srcu_work, srcu_drive_gp);
+ return 0;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+ struct lock_class_key *key)
+{
+ /* Don't re-initialize a lock while it is held. */
+ debug_check_no_locks_freed((void *)sp, sizeof(*sp));
+ lockdep_init_map(&sp->dep_map, name, key, 0);
+ return init_srcu_struct_fields(sp);
+}
+EXPORT_SYMBOL_GPL(__init_srcu_struct);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * init_srcu_struct - initialize a sleep-RCU structure
+ * @sp: structure to initialize.
+ *
+ * Must invoke this on a given srcu_struct before passing that srcu_struct
+ * to any other function. Each srcu_struct represents a separate domain
+ * of SRCU protection.
+ */
+int init_srcu_struct(struct srcu_struct *sp)
+{
+ return init_srcu_struct_fields(sp);
+}
+EXPORT_SYMBOL_GPL(init_srcu_struct);
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+ WARN_ON(sp->srcu_lock_nesting[0] || sp->srcu_lock_nesting[1]);
+ flush_work(&sp->srcu_work);
+ WARN_ON(rcu_seq_state(sp->srcu_gp_seq));
+ WARN_ON(sp->srcu_gp_running);
+ WARN_ON(sp->srcu_gp_waiting);
+ WARN_ON(!rcu_segcblist_empty(&sp->srcu_cblist));
+}
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct. Must be called from process context.
+ * Returns an index that must be passed to the matching srcu_read_unlock().
+ */
+int __srcu_read_lock(struct srcu_struct *sp)
+{
+ int idx;
+
+ idx = READ_ONCE(sp->srcu_idx);
+ WRITE_ONCE(sp->srcu_lock_nesting[idx], sp->srcu_lock_nesting[idx] + 1);
+ return idx;
+}
+EXPORT_SYMBOL_GPL(__srcu_read_lock);
+
+/*
+ * Removes the count for the old reader from the appropriate element of
+ * the srcu_struct. Must be called from process context.
+ */
+void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+{
+ int newval = sp->srcu_lock_nesting[idx] - 1;
+
+ WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
+ if (!newval && READ_ONCE(sp->srcu_gp_waiting))
+ swake_up(&sp->srcu_wq);
+}
+EXPORT_SYMBOL_GPL(__srcu_read_unlock);
+
+/*
+ * Workqueue handler to drive one grace period and invoke any callbacks
+ * that become ready as a result. Single-CPU and !PREEMPT operation
+ * means that we get away with murder on synchronization. ;-)
+ */
+void srcu_drive_gp(struct work_struct *wp)
+{
+ int idx;
+ struct rcu_cblist ready_cbs;
+ struct srcu_struct *sp;
+ struct rcu_head *rhp;
+
+ sp = container_of(wp, struct srcu_struct, srcu_work);
+ if (sp->srcu_gp_running || rcu_segcblist_empty(&sp->srcu_cblist))
+ return; /* Already running or nothing to do. */
+
+ /* Tag recently arrived callbacks and wait for readers. */
+ WRITE_ONCE(sp->srcu_gp_running, true);
+ rcu_segcblist_accelerate(&sp->srcu_cblist,
+ rcu_seq_snap(&sp->srcu_gp_seq));
+ rcu_seq_start(&sp->srcu_gp_seq);
+ idx = sp->srcu_idx;
+ WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
+ WRITE_ONCE(sp->srcu_gp_waiting, true); /* srcu_read_unlock() wakes! */
+ swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+ WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
+ rcu_seq_end(&sp->srcu_gp_seq);
+
+ /* Update callback list based on GP, and invoke ready callbacks. */
+ rcu_segcblist_advance(&sp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ if (rcu_segcblist_ready_cbs(&sp->srcu_cblist)) {
+ rcu_cblist_init(&ready_cbs);
+ local_irq_disable();
+ rcu_segcblist_extract_done_cbs(&sp->srcu_cblist, &ready_cbs);
+ local_irq_enable();
+ rhp = rcu_cblist_dequeue(&ready_cbs);
+ for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
+ local_bh_disable();
+ rhp->func(rhp);
+ local_bh_enable();
+ }
+ local_irq_disable();
+ rcu_segcblist_insert_count(&sp->srcu_cblist, &ready_cbs);
+ local_irq_enable();
+ }
+ WRITE_ONCE(sp->srcu_gp_running, false);
+
+ /*
+ * If more callbacks, reschedule ourselves. This can race with
+ * a call_srcu() at interrupt level, but the ->srcu_gp_running
+ * checks will straighten that out.
+ */
+ if (!rcu_segcblist_empty(&sp->srcu_cblist))
+ schedule_work(&sp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(srcu_drive_gp);
+
+/*
+ * Enqueue an SRCU callback on the specified srcu_struct structure,
+ * initiating grace-period processing if it is not already running.
+ */
+void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
+ rcu_callback_t func)
+{
+ unsigned long flags;
+
+ head->func = func;
+ local_irq_save(flags);
+ rcu_segcblist_enqueue(&sp->srcu_cblist, head, false);
+ local_irq_restore(flags);
+ if (!READ_ONCE(sp->srcu_gp_running))
+ schedule_work(&sp->srcu_work);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
+
+/*
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+ struct rcu_synchronize rs;
+
+ init_rcu_head_on_stack(&rs.head);
+ init_completion(&rs.completion);
+ call_srcu(sp, &rs.head, wakeme_after_rcu);
+ wait_for_completion(&rs.completion);
+ destroy_rcu_head_on_stack(&rs.head);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);
--- /dev/null
+/*
+ * Sleepable Read-Copy Update mechanism for mutual exclusion.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ *
+ * Copyright (C) IBM Corporation, 2006
+ * Copyright (C) Fujitsu, 2012
+ *
+ * Author: Paul McKenney <paulmck@us.ibm.com>
+ * Lai Jiangshan <laijs@cn.fujitsu.com>
+ *
+ * For detailed explanation of Read-Copy Update mechanism see -
+ * Documentation/RCU/ *.txt
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/rcupdate_wait.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/srcu.h>
+
+#include "rcu.h"
+#include "rcu_segcblist.h"
+
+ulong exp_holdoff = 25 * 1000; /* Holdoff (ns) for auto-expediting. */
+module_param(exp_holdoff, ulong, 0444);
+
+static void srcu_invoke_callbacks(struct work_struct *work);
+static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay);
+
+/*
+ * Initialize SRCU combining tree. Note that statically allocated
+ * srcu_struct structures might already have srcu_read_lock() and
+ * srcu_read_unlock() running against them. So if the is_static parameter
+ * is set, don't initialize ->srcu_lock_count[] and ->srcu_unlock_count[].
+ */
+static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static)
+{
+ int cpu;
+ int i;
+ int level = 0;
+ int levelspread[RCU_NUM_LVLS];
+ struct srcu_data *sdp;
+ struct srcu_node *snp;
+ struct srcu_node *snp_first;
+
+ /* Work out the overall tree geometry. */
+ sp->level[0] = &sp->node[0];
+ for (i = 1; i < rcu_num_lvls; i++)
+ sp->level[i] = sp->level[i - 1] + num_rcu_lvl[i - 1];
+ rcu_init_levelspread(levelspread, num_rcu_lvl);
+
+ /* Each pass through this loop initializes one srcu_node structure. */
+ rcu_for_each_node_breadth_first(sp, snp) {
+ spin_lock_init(&snp->lock);
+ WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) !=
+ ARRAY_SIZE(snp->srcu_data_have_cbs));
+ for (i = 0; i < ARRAY_SIZE(snp->srcu_have_cbs); i++) {
+ snp->srcu_have_cbs[i] = 0;
+ snp->srcu_data_have_cbs[i] = 0;
+ }
+ snp->srcu_gp_seq_needed_exp = 0;
+ snp->grplo = -1;
+ snp->grphi = -1;
+ if (snp == &sp->node[0]) {
+ /* Root node, special case. */
+ snp->srcu_parent = NULL;
+ continue;
+ }
+
+ /* Non-root node. */
+ if (snp == sp->level[level + 1])
+ level++;
+ snp->srcu_parent = sp->level[level - 1] +
+ (snp - sp->level[level]) /
+ levelspread[level - 1];
+ }
+
+ /*
+ * Initialize the per-CPU srcu_data array, which feeds into the
+ * leaves of the srcu_node tree.
+ */
+ WARN_ON_ONCE(ARRAY_SIZE(sdp->srcu_lock_count) !=
+ ARRAY_SIZE(sdp->srcu_unlock_count));
+ level = rcu_num_lvls - 1;
+ snp_first = sp->level[level];
+ for_each_possible_cpu(cpu) {
+ sdp = per_cpu_ptr(sp->sda, cpu);
+ spin_lock_init(&sdp->lock);
+ rcu_segcblist_init(&sdp->srcu_cblist);
+ sdp->srcu_cblist_invoking = false;
+ sdp->srcu_gp_seq_needed = sp->srcu_gp_seq;
+ sdp->srcu_gp_seq_needed_exp = sp->srcu_gp_seq;
+ sdp->mynode = &snp_first[cpu / levelspread[level]];
+ for (snp = sdp->mynode; snp != NULL; snp = snp->srcu_parent) {
+ if (snp->grplo < 0)
+ snp->grplo = cpu;
+ snp->grphi = cpu;
+ }
+ sdp->cpu = cpu;
+ INIT_DELAYED_WORK(&sdp->work, srcu_invoke_callbacks);
+ sdp->sp = sp;
+ sdp->grpmask = 1 << (cpu - sdp->mynode->grplo);
+ if (is_static)
+ continue;
+
+ /* Dynamically allocated, better be no srcu_read_locks()! */
+ for (i = 0; i < ARRAY_SIZE(sdp->srcu_lock_count); i++) {
+ sdp->srcu_lock_count[i] = 0;
+ sdp->srcu_unlock_count[i] = 0;
+ }
+ }
+}
+
+/*
+ * Initialize non-compile-time initialized fields, including the
+ * associated srcu_node and srcu_data structures. The is_static
+ * parameter is passed through to init_srcu_struct_nodes(), and
+ * also tells us that ->sda has already been wired up to srcu_data.
+ */
+static int init_srcu_struct_fields(struct srcu_struct *sp, bool is_static)
+{
+ mutex_init(&sp->srcu_cb_mutex);
+ mutex_init(&sp->srcu_gp_mutex);
+ sp->srcu_idx = 0;
+ sp->srcu_gp_seq = 0;
+ sp->srcu_barrier_seq = 0;
+ mutex_init(&sp->srcu_barrier_mutex);
+ atomic_set(&sp->srcu_barrier_cpu_cnt, 0);
+ INIT_DELAYED_WORK(&sp->work, process_srcu);
+ if (!is_static)
+ sp->sda = alloc_percpu(struct srcu_data);
+ init_srcu_struct_nodes(sp, is_static);
+ sp->srcu_gp_seq_needed_exp = 0;
+ sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ smp_store_release(&sp->srcu_gp_seq_needed, 0); /* Init done. */
+ return sp->sda ? 0 : -ENOMEM;
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+
+int __init_srcu_struct(struct srcu_struct *sp, const char *name,
+ struct lock_class_key *key)
+{
+ /* Don't re-initialize a lock while it is held. */
+ debug_check_no_locks_freed((void *)sp, sizeof(*sp));
+ lockdep_init_map(&sp->dep_map, name, key, 0);
+ spin_lock_init(&sp->gp_lock);
+ return init_srcu_struct_fields(sp, false);
+}
+EXPORT_SYMBOL_GPL(__init_srcu_struct);
+
+#else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/**
+ * init_srcu_struct - initialize a sleep-RCU structure
+ * @sp: structure to initialize.
+ *
+ * Must invoke this on a given srcu_struct before passing that srcu_struct
+ * to any other function. Each srcu_struct represents a separate domain
+ * of SRCU protection.
+ */
+int init_srcu_struct(struct srcu_struct *sp)
+{
+ spin_lock_init(&sp->gp_lock);
+ return init_srcu_struct_fields(sp, false);
+}
+EXPORT_SYMBOL_GPL(init_srcu_struct);
+
+#endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+/*
+ * First-use initialization of statically allocated srcu_struct
+ * structure. Wiring up the combining tree is more than can be
+ * done with compile-time initialization, so this check is added
+ * to each update-side SRCU primitive. Use ->gp_lock, which -is-
+ * compile-time initialized, to resolve races involving multiple
+ * CPUs trying to garner first-use privileges.
+ */
+static void check_init_srcu_struct(struct srcu_struct *sp)
+{
+ unsigned long flags;
+
+ WARN_ON_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INIT);
+ /* The smp_load_acquire() pairs with the smp_store_release(). */
+ if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/
+ return; /* Already initialized. */
+ spin_lock_irqsave(&sp->gp_lock, flags);
+ if (!rcu_seq_state(sp->srcu_gp_seq_needed)) {
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+ return;
+ }
+ init_srcu_struct_fields(sp, true);
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+}
+
+/*
+ * Returns approximate total of the readers' ->srcu_lock_count[] values
+ * for the rank of per-CPU counters specified by idx.
+ */
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
+{
+ int cpu;
+ unsigned long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+
+ sum += READ_ONCE(cpuc->srcu_lock_count[idx]);
+ }
+ return sum;
+}
+
+/*
+ * Returns approximate total of the readers' ->srcu_unlock_count[] values
+ * for the rank of per-CPU counters specified by idx.
+ */
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
+{
+ int cpu;
+ unsigned long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+
+ sum += READ_ONCE(cpuc->srcu_unlock_count[idx]);
+ }
+ return sum;
+}
+
+/*
+ * Return true if the number of pre-existing readers is determined to
+ * be zero.
+ */
+static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
+{
+ unsigned long unlocks;
+
+ unlocks = srcu_readers_unlock_idx(sp, idx);
+
+ /*
+ * Make sure that a lock is always counted if the corresponding
+ * unlock is counted. Needs to be a smp_mb() as the read side may
+ * contain a read from a variable that is written to before the
+ * synchronize_srcu() in the write side. In this case smp_mb()s
+ * A and B act like the store buffering pattern.
+ *
+ * This smp_mb() also pairs with smp_mb() C to prevent accesses
+ * after the synchronize_srcu() from being executed before the
+ * grace period ends.
+ */
+ smp_mb(); /* A */
+
+ /*
+ * If the locks are the same as the unlocks, then there must have
+ * been no readers on this index at some time in between. This does
+ * not mean that there are no more readers, as one could have read
+ * the current index but not have incremented the lock counter yet.
+ *
+ * Possible bug: There is no guarantee that there haven't been
+ * ULONG_MAX increments of ->srcu_lock_count[] since the unlocks were
+ * counted, meaning that this could return true even if there are
+ * still active readers. Since there are no memory barriers around
+ * srcu_flip(), the CPU is not required to increment ->srcu_idx
+ * before running srcu_readers_unlock_idx(), which means that there
+ * could be an arbitrarily large number of critical sections that
+ * execute after srcu_readers_unlock_idx() but use the old value
+ * of ->srcu_idx.
+ */
+ return srcu_readers_lock_idx(sp, idx) == unlocks;
+}
+
+/**
+ * srcu_readers_active - returns true if there are readers. and false
+ * otherwise
+ * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
+ *
+ * Note that this is not an atomic primitive, and can therefore suffer
+ * severe errors when invoked on an active srcu_struct. That said, it
+ * can be useful as an error check at cleanup time.
+ */
+static bool srcu_readers_active(struct srcu_struct *sp)
+{
+ int cpu;
+ unsigned long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ struct srcu_data *cpuc = per_cpu_ptr(sp->sda, cpu);
+
+ sum += READ_ONCE(cpuc->srcu_lock_count[0]);
+ sum += READ_ONCE(cpuc->srcu_lock_count[1]);
+ sum -= READ_ONCE(cpuc->srcu_unlock_count[0]);
+ sum -= READ_ONCE(cpuc->srcu_unlock_count[1]);
+ }
+ return sum;
+}
+
+#define SRCU_INTERVAL 1
+
+/*
+ * Return grace-period delay, zero if there are expedited grace
+ * periods pending, SRCU_INTERVAL otherwise.
+ */
+static unsigned long srcu_get_delay(struct srcu_struct *sp)
+{
+ if (ULONG_CMP_LT(READ_ONCE(sp->srcu_gp_seq),
+ READ_ONCE(sp->srcu_gp_seq_needed_exp)))
+ return 0;
+ return SRCU_INTERVAL;
+}
+
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @sp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *sp)
+{
+ int cpu;
+
+ if (WARN_ON(!srcu_get_delay(sp)))
+ return; /* Leakage unless caller handles error. */
+ if (WARN_ON(srcu_readers_active(sp)))
+ return; /* Leakage unless caller handles error. */
+ flush_delayed_work(&sp->work);
+ for_each_possible_cpu(cpu)
+ flush_delayed_work(&per_cpu_ptr(sp->sda, cpu)->work);
+ if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
+ WARN_ON(srcu_readers_active(sp))) {
+ pr_info("cleanup_srcu_struct: Active srcu_struct %p state: %d\n", sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+ return; /* Caller forgot to stop doing call_srcu()? */
+ }
+ free_percpu(sp->sda);
+ sp->sda = NULL;
+}
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
+
+/*
+ * Counts the new reader in the appropriate per-CPU element of the
+ * srcu_struct. Must be called from process context.
+ * Returns an index that must be passed to the matching srcu_read_unlock().
+ */
+int __srcu_read_lock(struct srcu_struct *sp)
+{
+ int idx;
+
+ idx = READ_ONCE(sp->srcu_idx) & 0x1;
+ __this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+ smp_mb(); /* B */ /* Avoid leaking the critical section. */
+ return idx;
+}
+EXPORT_SYMBOL_GPL(__srcu_read_lock);
+
+/*
+ * Removes the count for the old reader from the appropriate per-CPU
+ * element of the srcu_struct. Note that this may well be a different
+ * CPU than that which was incremented by the corresponding srcu_read_lock().
+ * Must be called from process context.
+ */
+void __srcu_read_unlock(struct srcu_struct *sp, int idx)
+{
+ smp_mb(); /* C */ /* Avoid leaking the critical section. */
+ this_cpu_inc(sp->sda->srcu_unlock_count[idx]);
+}
+EXPORT_SYMBOL_GPL(__srcu_read_unlock);
+
+/*
+ * We use an adaptive strategy for synchronize_srcu() and especially for
+ * synchronize_srcu_expedited(). We spin for a fixed time period
+ * (defined below) to allow SRCU readers to exit their read-side critical
+ * sections. If there are still some readers after a few microseconds,
+ * we repeatedly block for 1-millisecond time periods.
+ */
+#define SRCU_RETRY_CHECK_DELAY 5
+
+/*
+ * Start an SRCU grace period.
+ */
+static void srcu_gp_start(struct srcu_struct *sp)
+{
+ struct srcu_data *sdp = this_cpu_ptr(sp->sda);
+ int state;
+
+ RCU_LOCKDEP_WARN(!lockdep_is_held(&sp->gp_lock),
+ "Invoked srcu_gp_start() without ->gp_lock!");
+ WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
+ rcu_seq_snap(&sp->srcu_gp_seq));
+ smp_mb(); /* Order prior store to ->srcu_gp_seq_needed vs. GP start. */
+ rcu_seq_start(&sp->srcu_gp_seq);
+ state = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+ WARN_ON_ONCE(state != SRCU_STATE_SCAN1);
+}
+
+/*
+ * Track online CPUs to guide callback workqueue placement.
+ */
+DEFINE_PER_CPU(bool, srcu_online);
+
+void srcu_online_cpu(unsigned int cpu)
+{
+ WRITE_ONCE(per_cpu(srcu_online, cpu), true);
+}
+
+void srcu_offline_cpu(unsigned int cpu)
+{
+ WRITE_ONCE(per_cpu(srcu_online, cpu), false);
+}
+
+/*
+ * Place the workqueue handler on the specified CPU if online, otherwise
+ * just run it whereever. This is useful for placing workqueue handlers
+ * that are to invoke the specified CPU's callbacks.
+ */
+static bool srcu_queue_delayed_work_on(int cpu, struct workqueue_struct *wq,
+ struct delayed_work *dwork,
+ unsigned long delay)
+{
+ bool ret;
+
+ preempt_disable();
+ if (READ_ONCE(per_cpu(srcu_online, cpu)))
+ ret = queue_delayed_work_on(cpu, wq, dwork, delay);
+ else
+ ret = queue_delayed_work(wq, dwork, delay);
+ preempt_enable();
+ return ret;
+}
+
+/*
+ * Schedule callback invocation for the specified srcu_data structure,
+ * if possible, on the corresponding CPU.
+ */
+static void srcu_schedule_cbs_sdp(struct srcu_data *sdp, unsigned long delay)
+{
+ srcu_queue_delayed_work_on(sdp->cpu, system_power_efficient_wq,
+ &sdp->work, delay);
+}
+
+/*
+ * Schedule callback invocation for all srcu_data structures associated
+ * with the specified srcu_node structure that have callbacks for the
+ * just-completed grace period, the one corresponding to idx. If possible,
+ * schedule this invocation on the corresponding CPUs.
+ */
+static void srcu_schedule_cbs_snp(struct srcu_struct *sp, struct srcu_node *snp,
+ unsigned long mask, unsigned long delay)
+{
+ int cpu;
+
+ for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) {
+ if (!(mask & (1 << (cpu - snp->grplo))))
+ continue;
+ srcu_schedule_cbs_sdp(per_cpu_ptr(sp->sda, cpu), delay);
+ }
+}
+
+/*
+ * Note the end of an SRCU grace period. Initiates callback invocation
+ * and starts a new grace period if needed.
+ *
+ * The ->srcu_cb_mutex acquisition does not protect any data, but
+ * instead prevents more than one grace period from starting while we
+ * are initiating callback invocation. This allows the ->srcu_have_cbs[]
+ * array to have a finite number of elements.
+ */
+static void srcu_gp_end(struct srcu_struct *sp)
+{
+ unsigned long cbdelay;
+ bool cbs;
+ unsigned long gpseq;
+ int idx;
+ int idxnext;
+ unsigned long mask;
+ struct srcu_node *snp;
+
+ /* Prevent more than one additional grace period. */
+ mutex_lock(&sp->srcu_cb_mutex);
+
+ /* End the current grace period. */
+ spin_lock_irq(&sp->gp_lock);
+ idx = rcu_seq_state(sp->srcu_gp_seq);
+ WARN_ON_ONCE(idx != SRCU_STATE_SCAN2);
+ cbdelay = srcu_get_delay(sp);
+ sp->srcu_last_gp_end = ktime_get_mono_fast_ns();
+ rcu_seq_end(&sp->srcu_gp_seq);
+ gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+ if (ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, gpseq))
+ sp->srcu_gp_seq_needed_exp = gpseq;
+ spin_unlock_irq(&sp->gp_lock);
+ mutex_unlock(&sp->srcu_gp_mutex);
+ /* A new grace period can start at this point. But only one. */
+
+ /* Initiate callback invocation as needed. */
+ idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs);
+ idxnext = (idx + 1) % ARRAY_SIZE(snp->srcu_have_cbs);
+ rcu_for_each_node_breadth_first(sp, snp) {
+ spin_lock_irq(&snp->lock);
+ cbs = false;
+ if (snp >= sp->level[rcu_num_lvls - 1])
+ cbs = snp->srcu_have_cbs[idx] == gpseq;
+ snp->srcu_have_cbs[idx] = gpseq;
+ rcu_seq_set_state(&snp->srcu_have_cbs[idx], 1);
+ if (ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, gpseq))
+ snp->srcu_gp_seq_needed_exp = gpseq;
+ mask = snp->srcu_data_have_cbs[idx];
+ snp->srcu_data_have_cbs[idx] = 0;
+ spin_unlock_irq(&snp->lock);
+ if (cbs) {
+ smp_mb(); /* GP end before CB invocation. */
+ srcu_schedule_cbs_snp(sp, snp, mask, cbdelay);
+ }
+ }
+
+ /* Callback initiation done, allow grace periods after next. */
+ mutex_unlock(&sp->srcu_cb_mutex);
+
+ /* Start a new grace period if needed. */
+ spin_lock_irq(&sp->gp_lock);
+ gpseq = rcu_seq_current(&sp->srcu_gp_seq);
+ if (!rcu_seq_state(gpseq) &&
+ ULONG_CMP_LT(gpseq, sp->srcu_gp_seq_needed)) {
+ srcu_gp_start(sp);
+ spin_unlock_irq(&sp->gp_lock);
+ /* Throttle expedited grace periods: Should be rare! */
+ srcu_reschedule(sp, rcu_seq_ctr(gpseq) & 0x3ff
+ ? 0 : SRCU_INTERVAL);
+ } else {
+ spin_unlock_irq(&sp->gp_lock);
+ }
+}
+
+/*
+ * Funnel-locking scheme to scalably mediate many concurrent expedited
+ * grace-period requests. This function is invoked for the first known
+ * expedited request for a grace period that has already been requested,
+ * but without expediting. To start a completely new grace period,
+ * whether expedited or not, use srcu_funnel_gp_start() instead.
+ */
+static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
+ unsigned long s)
+{
+ unsigned long flags;
+
+ for (; snp != NULL; snp = snp->srcu_parent) {
+ if (rcu_seq_done(&sp->srcu_gp_seq, s) ||
+ ULONG_CMP_GE(READ_ONCE(snp->srcu_gp_seq_needed_exp), s))
+ return;
+ spin_lock_irqsave(&snp->lock, flags);
+ if (ULONG_CMP_GE(snp->srcu_gp_seq_needed_exp, s)) {
+ spin_unlock_irqrestore(&snp->lock, flags);
+ return;
+ }
+ WRITE_ONCE(snp->srcu_gp_seq_needed_exp, s);
+ spin_unlock_irqrestore(&snp->lock, flags);
+ }
+ spin_lock_irqsave(&sp->gp_lock, flags);
+ if (!ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
+ sp->srcu_gp_seq_needed_exp = s;
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+}
+
+/*
+ * Funnel-locking scheme to scalably mediate many concurrent grace-period
+ * requests. The winner has to do the work of actually starting grace
+ * period s. Losers must either ensure that their desired grace-period
+ * number is recorded on at least their leaf srcu_node structure, or they
+ * must take steps to invoke their own callbacks.
+ */
+static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
+ unsigned long s, bool do_norm)
+{
+ unsigned long flags;
+ int idx = rcu_seq_ctr(s) % ARRAY_SIZE(sdp->mynode->srcu_have_cbs);
+ struct srcu_node *snp = sdp->mynode;
+ unsigned long snp_seq;
+
+ /* Each pass through the loop does one level of the srcu_node tree. */
+ for (; snp != NULL; snp = snp->srcu_parent) {
+ if (rcu_seq_done(&sp->srcu_gp_seq, s) && snp != sdp->mynode)
+ return; /* GP already done and CBs recorded. */
+ spin_lock_irqsave(&snp->lock, flags);
+ if (ULONG_CMP_GE(snp->srcu_have_cbs[idx], s)) {
+ snp_seq = snp->srcu_have_cbs[idx];
+ if (snp == sdp->mynode && snp_seq == s)
+ snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
+ spin_unlock_irqrestore(&snp->lock, flags);
+ if (snp == sdp->mynode && snp_seq != s) {
+ smp_mb(); /* CBs after GP! */
+ srcu_schedule_cbs_sdp(sdp, do_norm
+ ? SRCU_INTERVAL
+ : 0);
+ return;
+ }
+ if (!do_norm)
+ srcu_funnel_exp_start(sp, snp, s);
+ return;
+ }
+ snp->srcu_have_cbs[idx] = s;
+ if (snp == sdp->mynode)
+ snp->srcu_data_have_cbs[idx] |= sdp->grpmask;
+ if (!do_norm && ULONG_CMP_LT(snp->srcu_gp_seq_needed_exp, s))
+ snp->srcu_gp_seq_needed_exp = s;
+ spin_unlock_irqrestore(&snp->lock, flags);
+ }
+
+ /* Top of tree, must ensure the grace period will be started. */
+ spin_lock_irqsave(&sp->gp_lock, flags);
+ if (ULONG_CMP_LT(sp->srcu_gp_seq_needed, s)) {
+ /*
+ * Record need for grace period s. Pair with load
+ * acquire setting up for initialization.
+ */
+ smp_store_release(&sp->srcu_gp_seq_needed, s); /*^^^*/
+ }
+ if (!do_norm && ULONG_CMP_LT(sp->srcu_gp_seq_needed_exp, s))
+ sp->srcu_gp_seq_needed_exp = s;
+
+ /* If grace period not already done and none in progress, start it. */
+ if (!rcu_seq_done(&sp->srcu_gp_seq, s) &&
+ rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) {
+ WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed));
+ srcu_gp_start(sp);
+ queue_delayed_work(system_power_efficient_wq, &sp->work,
+ srcu_get_delay(sp));
+ }
+ spin_unlock_irqrestore(&sp->gp_lock, flags);
+}
+
+/*
+ * Wait until all readers counted by array index idx complete, but
+ * loop an additional time if there is an expedited grace period pending.
+ * The caller must ensure that ->srcu_idx is not changed while checking.
+ */
+static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
+{
+ for (;;) {
+ if (srcu_readers_active_idx_check(sp, idx))
+ return true;
+ if (--trycount + !srcu_get_delay(sp) <= 0)
+ return false;
+ udelay(SRCU_RETRY_CHECK_DELAY);
+ }
+}
+
+/*
+ * Increment the ->srcu_idx counter so that future SRCU readers will
+ * use the other rank of the ->srcu_(un)lock_count[] arrays. This allows
+ * us to wait for pre-existing readers in a starvation-free manner.
+ */
+static void srcu_flip(struct srcu_struct *sp)
+{
+ WRITE_ONCE(sp->srcu_idx, sp->srcu_idx + 1);
+
+ /*
+ * Ensure that if the updater misses an __srcu_read_unlock()
+ * increment, that task's next __srcu_read_lock() will see the
+ * above counter update. Note that both this memory barrier
+ * and the one in srcu_readers_active_idx_check() provide the
+ * guarantee for __srcu_read_lock().
+ */
+ smp_mb(); /* D */ /* Pairs with C. */
+}
+
+/*
+ * If SRCU is likely idle, return true, otherwise return false.
+ *
+ * Note that it is OK for several current from-idle requests for a new
+ * grace period from idle to specify expediting because they will all end
+ * up requesting the same grace period anyhow. So no loss.
+ *
+ * Note also that if any CPU (including the current one) is still invoking
+ * callbacks, this function will nevertheless say "idle". This is not
+ * ideal, but the overhead of checking all CPUs' callback lists is even
+ * less ideal, especially on large systems. Furthermore, the wakeup
+ * can happen before the callback is fully removed, so we have no choice
+ * but to accept this type of error.
+ *
+ * This function is also subject to counter-wrap errors, but let's face
+ * it, if this function was preempted for enough time for the counters
+ * to wrap, it really doesn't matter whether or not we expedite the grace
+ * period. The extra overhead of a needlessly expedited grace period is
+ * negligible when amoritized over that time period, and the extra latency
+ * of a needlessly non-expedited grace period is similarly negligible.
+ */
+static bool srcu_might_be_idle(struct srcu_struct *sp)
+{
+ unsigned long curseq;
+ unsigned long flags;
+ struct srcu_data *sdp;
+ unsigned long t;
+
+ /* If the local srcu_data structure has callbacks, not idle. */
+ local_irq_save(flags);
+ sdp = this_cpu_ptr(sp->sda);
+ if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) {
+ local_irq_restore(flags);
+ return false; /* Callbacks already present, so not idle. */
+ }
+ local_irq_restore(flags);
+
+ /*
+ * No local callbacks, so probabalistically probe global state.
+ * Exact information would require acquiring locks, which would
+ * kill scalability, hence the probabalistic nature of the probe.
+ */
+
+ /* First, see if enough time has passed since the last GP. */
+ t = ktime_get_mono_fast_ns();
+ if (exp_holdoff == 0 ||
+ time_in_range_open(t, sp->srcu_last_gp_end,
+ sp->srcu_last_gp_end + exp_holdoff))
+ return false; /* Too soon after last GP. */
+
+ /* Next, check for probable idleness. */
+ curseq = rcu_seq_current(&sp->srcu_gp_seq);
+ smp_mb(); /* Order ->srcu_gp_seq with ->srcu_gp_seq_needed. */
+ if (ULONG_CMP_LT(curseq, READ_ONCE(sp->srcu_gp_seq_needed)))
+ return false; /* Grace period in progress, so not idle. */
+ smp_mb(); /* Order ->srcu_gp_seq with prior access. */
+ if (curseq != rcu_seq_current(&sp->srcu_gp_seq))
+ return false; /* GP # changed, so not idle. */
+ return true; /* With reasonable probability, idle! */
+}
+
+/*
+ * Enqueue an SRCU callback on the srcu_data structure associated with
+ * the current CPU and the specified srcu_struct structure, initiating
+ * grace-period processing if it is not already running.
+ *
+ * Note that all CPUs must agree that the grace period extended beyond
+ * all pre-existing SRCU read-side critical section. On systems with
+ * more than one CPU, this means that when "func()" is invoked, each CPU
+ * is guaranteed to have executed a full memory barrier since the end of
+ * its last corresponding SRCU read-side critical section whose beginning
+ * preceded the call to call_rcu(). It also means that each CPU executing
+ * an SRCU read-side critical section that continues beyond the start of
+ * "func()" must have executed a memory barrier after the call_rcu()
+ * but before the beginning of that SRCU read-side critical section.
+ * Note that these guarantees include CPUs that are offline, idle, or
+ * executing in user mode, as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * resulting SRCU callback function "func()", then both CPU A and CPU
+ * B are guaranteed to execute a full memory barrier during the time
+ * interval between the call to call_rcu() and the invocation of "func()".
+ * This guarantee applies even if CPU A and CPU B are the same CPU (but
+ * again only if the system has more than one CPU).
+ *
+ * Of course, these guarantees apply only for invocations of call_srcu(),
+ * srcu_read_lock(), and srcu_read_unlock() that are all passed the same
+ * srcu_struct structure.
+ */
+void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+ rcu_callback_t func, bool do_norm)
+{
+ unsigned long flags;
+ bool needexp = false;
+ bool needgp = false;
+ unsigned long s;
+ struct srcu_data *sdp;
+
+ check_init_srcu_struct(sp);
+ rhp->func = func;
+ local_irq_save(flags);
+ sdp = this_cpu_ptr(sp->sda);
+ spin_lock(&sdp->lock);
+ rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false);
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ s = rcu_seq_snap(&sp->srcu_gp_seq);
+ (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s);
+ if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) {
+ sdp->srcu_gp_seq_needed = s;
+ needgp = true;
+ }
+ if (!do_norm && ULONG_CMP_LT(sdp->srcu_gp_seq_needed_exp, s)) {
+ sdp->srcu_gp_seq_needed_exp = s;
+ needexp = true;
+ }
+ spin_unlock_irqrestore(&sdp->lock, flags);
+ if (needgp)
+ srcu_funnel_gp_start(sp, sdp, s, do_norm);
+ else if (needexp)
+ srcu_funnel_exp_start(sp, sdp->mynode, s);
+}
+
+void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
+ rcu_callback_t func)
+{
+ __call_srcu(sp, rhp, func, true);
+}
+EXPORT_SYMBOL_GPL(call_srcu);
+
+/*
+ * Helper function for synchronize_srcu() and synchronize_srcu_expedited().
+ */
+static void __synchronize_srcu(struct srcu_struct *sp, bool do_norm)
+{
+ struct rcu_synchronize rcu;
+
+ RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
+ lock_is_held(&rcu_bh_lock_map) ||
+ lock_is_held(&rcu_lock_map) ||
+ lock_is_held(&rcu_sched_lock_map),
+ "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section");
+
+ if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
+ return;
+ might_sleep();
+ check_init_srcu_struct(sp);
+ init_completion(&rcu.completion);
+ init_rcu_head_on_stack(&rcu.head);
+ __call_srcu(sp, &rcu.head, wakeme_after_rcu, do_norm);
+ wait_for_completion(&rcu.completion);
+ destroy_rcu_head_on_stack(&rcu.head);
+}
+
+/**
+ * synchronize_srcu_expedited - Brute-force SRCU grace period
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Wait for an SRCU grace period to elapse, but be more aggressive about
+ * spinning rather than blocking when waiting.
+ *
+ * Note that synchronize_srcu_expedited() has the same deadlock and
+ * memory-ordering properties as does synchronize_srcu().
+ */
+void synchronize_srcu_expedited(struct srcu_struct *sp)
+{
+ __synchronize_srcu(sp, rcu_gp_is_normal());
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu_expedited);
+
+/**
+ * synchronize_srcu - wait for prior SRCU read-side critical-section completion
+ * @sp: srcu_struct with which to synchronize.
+ *
+ * Wait for the count to drain to zero of both indexes. To avoid the
+ * possible starvation of synchronize_srcu(), it waits for the count of
+ * the index=((->srcu_idx & 1) ^ 1) to drain to zero at first,
+ * and then flip the srcu_idx and wait for the count of the other index.
+ *
+ * Can block; must be called from process context.
+ *
+ * Note that it is illegal to call synchronize_srcu() from the corresponding
+ * SRCU read-side critical section; doing so will result in deadlock.
+ * However, it is perfectly legal to call synchronize_srcu() on one
+ * srcu_struct from some other srcu_struct's read-side critical section,
+ * as long as the resulting graph of srcu_structs is acyclic.
+ *
+ * There are memory-ordering constraints implied by synchronize_srcu().
+ * On systems with more than one CPU, when synchronize_srcu() returns,
+ * each CPU is guaranteed to have executed a full memory barrier since
+ * the end of its last corresponding SRCU-sched read-side critical section
+ * whose beginning preceded the call to synchronize_srcu(). In addition,
+ * each CPU having an SRCU read-side critical section that extends beyond
+ * the return from synchronize_srcu() is guaranteed to have executed a
+ * full memory barrier after the beginning of synchronize_srcu() and before
+ * the beginning of that SRCU read-side critical section. Note that these
+ * guarantees include CPUs that are offline, idle, or executing in user mode,
+ * as well as CPUs that are executing in the kernel.
+ *
+ * Furthermore, if CPU A invoked synchronize_srcu(), which returned
+ * to its caller on CPU B, then both CPU A and CPU B are guaranteed
+ * to have executed a full memory barrier during the execution of
+ * synchronize_srcu(). This guarantee applies even if CPU A and CPU B
+ * are the same CPU, but again only if the system has more than one CPU.
+ *
+ * Of course, these memory-ordering guarantees apply only when
+ * synchronize_srcu(), srcu_read_lock(), and srcu_read_unlock() are
+ * passed the same srcu_struct structure.
+ *
+ * If SRCU is likely idle, expedite the first request. This semantic
+ * was provided by Classic SRCU, and is relied upon by its users, so TREE
+ * SRCU must also provide it. Note that detecting idleness is heuristic
+ * and subject to both false positives and negatives.
+ */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+ if (srcu_might_be_idle(sp) || rcu_gp_is_expedited())
+ synchronize_srcu_expedited(sp);
+ else
+ __synchronize_srcu(sp, true);
+}
+EXPORT_SYMBOL_GPL(synchronize_srcu);
+
+/*
+ * Callback function for srcu_barrier() use.
+ */
+static void srcu_barrier_cb(struct rcu_head *rhp)
+{
+ struct srcu_data *sdp;
+ struct srcu_struct *sp;
+
+ sdp = container_of(rhp, struct srcu_data, srcu_barrier_head);
+ sp = sdp->sp;
+ if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
+ complete(&sp->srcu_barrier_completion);
+}
+
+/**
+ * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete.
+ * @sp: srcu_struct on which to wait for in-flight callbacks.
+ */
+void srcu_barrier(struct srcu_struct *sp)
+{
+ int cpu;
+ struct srcu_data *sdp;
+ unsigned long s = rcu_seq_snap(&sp->srcu_barrier_seq);
+
+ check_init_srcu_struct(sp);
+ mutex_lock(&sp->srcu_barrier_mutex);
+ if (rcu_seq_done(&sp->srcu_barrier_seq, s)) {
+ smp_mb(); /* Force ordering following return. */
+ mutex_unlock(&sp->srcu_barrier_mutex);
+ return; /* Someone else did our work for us. */
+ }
+ rcu_seq_start(&sp->srcu_barrier_seq);
+ init_completion(&sp->srcu_barrier_completion);
+
+ /* Initial count prevents reaching zero until all CBs are posted. */
+ atomic_set(&sp->srcu_barrier_cpu_cnt, 1);
+
+ /*
+ * Each pass through this loop enqueues a callback, but only
+ * on CPUs already having callbacks enqueued. Note that if
+ * a CPU already has callbacks enqueue, it must have already
+ * registered the need for a future grace period, so all we
+ * need do is enqueue a callback that will use the same
+ * grace period as the last callback already in the queue.
+ */
+ for_each_possible_cpu(cpu) {
+ sdp = per_cpu_ptr(sp->sda, cpu);
+ spin_lock_irq(&sdp->lock);
+ atomic_inc(&sp->srcu_barrier_cpu_cnt);
+ sdp->srcu_barrier_head.func = srcu_barrier_cb;
+ if (!rcu_segcblist_entrain(&sdp->srcu_cblist,
+ &sdp->srcu_barrier_head, 0))
+ atomic_dec(&sp->srcu_barrier_cpu_cnt);
+ spin_unlock_irq(&sdp->lock);
+ }
+
+ /* Remove the initial count, at which point reaching zero can happen. */
+ if (atomic_dec_and_test(&sp->srcu_barrier_cpu_cnt))
+ complete(&sp->srcu_barrier_completion);
+ wait_for_completion(&sp->srcu_barrier_completion);
+
+ rcu_seq_end(&sp->srcu_barrier_seq);
+ mutex_unlock(&sp->srcu_barrier_mutex);
+}
+EXPORT_SYMBOL_GPL(srcu_barrier);
+
+/**
+ * srcu_batches_completed - return batches completed.
+ * @sp: srcu_struct on which to report batch completion.
+ *
+ * Report the number of batches, correlated with, but not necessarily
+ * precisely the same as, the number of grace periods that have elapsed.
+ */
+unsigned long srcu_batches_completed(struct srcu_struct *sp)
+{
+ return sp->srcu_idx;
+}
+EXPORT_SYMBOL_GPL(srcu_batches_completed);
+
+/*
+ * Core SRCU state machine. Push state bits of ->srcu_gp_seq
+ * to SRCU_STATE_SCAN2, and invoke srcu_gp_end() when scan has
+ * completed in that state.
+ */
+static void srcu_advance_state(struct srcu_struct *sp)
+{
+ int idx;
+
+ mutex_lock(&sp->srcu_gp_mutex);
+
+ /*
+ * Because readers might be delayed for an extended period after
+ * fetching ->srcu_idx for their index, at any point in time there
+ * might well be readers using both idx=0 and idx=1. We therefore
+ * need to wait for readers to clear from both index values before
+ * invoking a callback.
+ *
+ * The load-acquire ensures that we see the accesses performed
+ * by the prior grace period.
+ */
+ idx = rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq)); /* ^^^ */
+ if (idx == SRCU_STATE_IDLE) {
+ spin_lock_irq(&sp->gp_lock);
+ if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
+ WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq));
+ spin_unlock_irq(&sp->gp_lock);
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return;
+ }
+ idx = rcu_seq_state(READ_ONCE(sp->srcu_gp_seq));
+ if (idx == SRCU_STATE_IDLE)
+ srcu_gp_start(sp);
+ spin_unlock_irq(&sp->gp_lock);
+ if (idx != SRCU_STATE_IDLE) {
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return; /* Someone else started the grace period. */
+ }
+ }
+
+ if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN1) {
+ idx = 1 ^ (sp->srcu_idx & 1);
+ if (!try_check_zero(sp, idx, 1)) {
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return; /* readers present, retry later. */
+ }
+ srcu_flip(sp);
+ rcu_seq_set_state(&sp->srcu_gp_seq, SRCU_STATE_SCAN2);
+ }
+
+ if (rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) == SRCU_STATE_SCAN2) {
+
+ /*
+ * SRCU read-side critical sections are normally short,
+ * so check at least twice in quick succession after a flip.
+ */
+ idx = 1 ^ (sp->srcu_idx & 1);
+ if (!try_check_zero(sp, idx, 2)) {
+ mutex_unlock(&sp->srcu_gp_mutex);
+ return; /* readers present, retry later. */
+ }
+ srcu_gp_end(sp); /* Releases ->srcu_gp_mutex. */
+ }
+}
+
+/*
+ * Invoke a limited number of SRCU callbacks that have passed through
+ * their grace period. If there are more to do, SRCU will reschedule
+ * the workqueue. Note that needed memory barriers have been executed
+ * in this task's context by srcu_readers_active_idx_check().
+ */
+static void srcu_invoke_callbacks(struct work_struct *work)
+{
+ bool more;
+ struct rcu_cblist ready_cbs;
+ struct rcu_head *rhp;
+ struct srcu_data *sdp;
+ struct srcu_struct *sp;
+
+ sdp = container_of(work, struct srcu_data, work.work);
+ sp = sdp->sp;
+ rcu_cblist_init(&ready_cbs);
+ spin_lock_irq(&sdp->lock);
+ smp_mb(); /* Old grace periods before callback invocation! */
+ rcu_segcblist_advance(&sdp->srcu_cblist,
+ rcu_seq_current(&sp->srcu_gp_seq));
+ if (sdp->srcu_cblist_invoking ||
+ !rcu_segcblist_ready_cbs(&sdp->srcu_cblist)) {
+ spin_unlock_irq(&sdp->lock);
+ return; /* Someone else on the job or nothing to do. */
+ }
+
+ /* We are on the job! Extract and invoke ready callbacks. */
+ sdp->srcu_cblist_invoking = true;
+ rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs);
+ spin_unlock_irq(&sdp->lock);
+ rhp = rcu_cblist_dequeue(&ready_cbs);
+ for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) {
+ local_bh_disable();
+ rhp->func(rhp);
+ local_bh_enable();
+ }
+
+ /*
+ * Update counts, accelerate new callbacks, and if needed,
+ * schedule another round of callback invocation.
+ */
+ spin_lock_irq(&sdp->lock);
+ rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs);
+ (void)rcu_segcblist_accelerate(&sdp->srcu_cblist,
+ rcu_seq_snap(&sp->srcu_gp_seq));
+ sdp->srcu_cblist_invoking = false;
+ more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist);
+ spin_unlock_irq(&sdp->lock);
+ if (more)
+ srcu_schedule_cbs_sdp(sdp, 0);
+}
+
+/*
+ * Finished one round of SRCU grace period. Start another if there are
+ * more SRCU callbacks queued, otherwise put SRCU into not-running state.
+ */
+static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay)
+{
+ bool pushgp = true;
+
+ spin_lock_irq(&sp->gp_lock);
+ if (ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)) {
+ if (!WARN_ON_ONCE(rcu_seq_state(sp->srcu_gp_seq))) {
+ /* All requests fulfilled, time to go idle. */
+ pushgp = false;
+ }
+ } else if (!rcu_seq_state(sp->srcu_gp_seq)) {
+ /* Outstanding request and no GP. Start one. */
+ srcu_gp_start(sp);
+ }
+ spin_unlock_irq(&sp->gp_lock);
+
+ if (pushgp)
+ queue_delayed_work(system_power_efficient_wq, &sp->work, delay);
+}
+
+/*
+ * This is the work-queue function that handles SRCU grace periods.
+ */
+void process_srcu(struct work_struct *work)
+{
+ struct srcu_struct *sp;
+
+ sp = container_of(work, struct srcu_struct, work.work);
+
+ srcu_advance_state(sp);
+ srcu_reschedule(sp, srcu_get_delay(sp));
+}
+EXPORT_SYMBOL_GPL(process_srcu);
+
+void srcutorture_get_gp_data(enum rcutorture_type test_type,
+ struct srcu_struct *sp, int *flags,
+ unsigned long *gpnum, unsigned long *completed)
+{
+ if (test_type != SRCU_FLAVOR)
+ return;
+ *flags = 0;
+ *completed = rcu_seq_ctr(sp->srcu_gp_seq);
+ *gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
+}
+EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
*/
static int rcu_qsctr_help(struct rcu_ctrlblk *rcp)
{
- RCU_TRACE(reset_cpu_stall_ticks(rcp));
+ RCU_TRACE(reset_cpu_stall_ticks(rcp);)
if (rcp->donetail != rcp->curtail) {
rcp->donetail = rcp->curtail;
return 1;
*/
void rcu_check_callbacks(int user)
{
- RCU_TRACE(check_cpu_stalls());
+ RCU_TRACE(check_cpu_stalls();)
if (user)
rcu_sched_qs();
else if (!in_softirq())
const char *rn = NULL;
struct rcu_head *next, *list;
unsigned long flags;
- RCU_TRACE(int cb_count = 0);
+ RCU_TRACE(int cb_count = 0;)
/* Move the ready-to-invoke callbacks to a local list. */
local_irq_save(flags);
local_irq_restore(flags);
return;
}
- RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
+ RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1);)
list = rcp->rcucblist;
rcp->rcucblist = *rcp->donetail;
*rcp->donetail = NULL;
local_irq_restore(flags);
/* Invoke the callbacks on the local list. */
- RCU_TRACE(rn = rcp->name);
+ RCU_TRACE(rn = rcp->name;)
while (list) {
next = list->next;
prefetch(next);
__rcu_reclaim(rn, list);
local_bh_enable();
list = next;
- RCU_TRACE(cb_count++);
+ RCU_TRACE(cb_count++;)
}
- RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
+ RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count);)
RCU_TRACE(trace_rcu_batch_end(rcp->name,
cb_count, 0, need_resched(),
is_idle_task(current),
local_irq_save(flags);
*rcp->curtail = head;
rcp->curtail = &head->next;
- RCU_TRACE(rcp->qlen++);
+ RCU_TRACE(rcp->qlen++;)
local_irq_restore(flags);
if (unlikely(is_idle_task(current))) {
void __init rcu_init(void)
{
open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
- RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk));
- RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk));
+ RCU_TRACE(reset_cpu_stall_ticks(&rcu_sched_ctrlblk);)
+ RCU_TRACE(reset_cpu_stall_ticks(&rcu_bh_ctrlblk);)
rcu_early_boot_tests();
}
RCU_TRACE(.name = "rcu_bh")
};
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU)
#include <linux/kernel_stat.h>
int rcu_scheduler_active __read_mostly;
* to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage.
* The reason for this is that Tiny RCU does not need kthreads, so does
* not have to care about the fact that the scheduler is half-initialized
- * at a certain phase of the boot process.
+ * at a certain phase of the boot process. Unless SRCU is in the mix.
*/
void __init rcu_scheduler_starting(void)
{
WARN_ON(nr_context_switches() > 0);
- rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+ rcu_scheduler_active = IS_ENABLED(CONFIG_SRCU)
+ ? RCU_SCHEDULER_INIT : RCU_SCHEDULER_RUNNING;
}
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SRCU) */
#ifdef CONFIG_RCU_TRACE
static void check_cpu_stalls(void)
{
- RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk));
- RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk));
+ RCU_TRACE(check_cpu_stall(&rcu_bh_ctrlblk);)
+ RCU_TRACE(check_cpu_stall(&rcu_sched_ctrlblk);)
}
#endif /* #ifdef CONFIG_RCU_TRACE */
.gpnum = 0UL - 300UL, \
.completed = 0UL - 300UL, \
.orphan_lock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.orphan_lock), \
- .orphan_nxttail = &sname##_state.orphan_nxtlist, \
- .orphan_donetail = &sname##_state.orphan_donelist, \
+ .orphan_pend = RCU_CBLIST_INITIALIZER(sname##_state.orphan_pend), \
+ .orphan_done = RCU_CBLIST_INITIALIZER(sname##_state.orphan_done), \
.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
.name = RCU_STATE_NAME(sname), \
.abbr = sabbr, \
module_param(rcu_fanout_leaf, int, 0444);
int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
/* Number of rcu_nodes at specified level. */
-static int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
+int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
/* panic() on RCU Stall sysctl. */
int sysctl_panic_on_rcu_stall __read_mostly;
/*
* Number of grace periods between delays, normalized by the duration of
- * the delay. The longer the the delay, the more the grace periods between
+ * the delay. The longer the delay, the more the grace periods between
* each delay. The reason for this normalization is that it means that,
* for non-zero delays, the overall slowdown of grace periods is constant
* regardless of the duration of the delay. This arrangement balances
}
}
-static DEFINE_PER_CPU(int, rcu_sched_qs_mask);
+/*
+ * Steal a bit from the bottom of ->dynticks for idle entry/exit
+ * control. Initially this is for TLB flushing.
+ */
+#define RCU_DYNTICK_CTRL_MASK 0x1
+#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1)
+#ifndef rcu_eqs_special_exit
+#define rcu_eqs_special_exit() do { } while (0)
+#endif
static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
- .dynticks = ATOMIC_INIT(1),
+ .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR),
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
.dynticks_idle = ATOMIC_INIT(1),
static void rcu_dynticks_eqs_enter(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special;
+ int seq;
/*
- * CPUs seeing atomic_inc_return() must see prior RCU read-side
+ * CPUs seeing atomic_add_return() must see prior RCU read-side
* critical sections, and we also must force ordering with the
* next idle sojourn.
*/
- special = atomic_inc_return(&rdtp->dynticks);
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && special & 0x1);
+ seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ /* Better be in an extended quiescent state! */
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ (seq & RCU_DYNTICK_CTRL_CTR));
+ /* Better not have special action (TLB flush) pending! */
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ (seq & RCU_DYNTICK_CTRL_MASK));
}
/*
static void rcu_dynticks_eqs_exit(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special;
+ int seq;
/*
- * CPUs seeing atomic_inc_return() must see prior idle sojourns,
+ * CPUs seeing atomic_add_return() must see prior idle sojourns,
* and we also must force ordering with the next RCU read-side
* critical section.
*/
- special = atomic_inc_return(&rdtp->dynticks);
- WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(special & 0x1));
+ seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+ !(seq & RCU_DYNTICK_CTRL_CTR));
+ if (seq & RCU_DYNTICK_CTRL_MASK) {
+ atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdtp->dynticks);
+ smp_mb__after_atomic(); /* _exit after clearing mask. */
+ /* Prefer duplicate flushes to losing a flush. */
+ rcu_eqs_special_exit();
+ }
}
/*
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- if (atomic_read(&rdtp->dynticks) & 0x1)
+ if (atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR)
return;
- atomic_add(0x1, &rdtp->dynticks);
+ atomic_add(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
}
/*
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- return !(atomic_read(&rdtp->dynticks) & 0x1);
+ return !(atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR);
}
/*
{
int snap = atomic_add_return(0, &rdtp->dynticks);
- return snap;
+ return snap & ~RCU_DYNTICK_CTRL_MASK;
}
/*
*/
static bool rcu_dynticks_in_eqs(int snap)
{
- return !(snap & 0x1);
+ return !(snap & RCU_DYNTICK_CTRL_CTR);
}
/*
static void rcu_dynticks_momentary_idle(void)
{
struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
- int special = atomic_add_return(2, &rdtp->dynticks);
+ int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
+ &rdtp->dynticks);
/* It is illegal to call this from idle state. */
- WARN_ON_ONCE(!(special & 0x1));
+ WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
}
-DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
-EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
+/*
+ * Set the special (bottom) bit of the specified CPU so that it
+ * will take special action (such as flushing its TLB) on the
+ * next exit from an extended quiescent state. Returns true if
+ * the bit was successfully set, or false if the CPU was not in
+ * an extended quiescent state.
+ */
+bool rcu_eqs_special_set(int cpu)
+{
+ int old;
+ int new;
+ struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+ do {
+ old = atomic_read(&rdtp->dynticks);
+ if (old & RCU_DYNTICK_CTRL_CTR)
+ return false;
+ new = old | RCU_DYNTICK_CTRL_MASK;
+ } while (atomic_cmpxchg(&rdtp->dynticks, old, new) != old);
+ return true;
+}
/*
* Let the RCU core know that this CPU has gone through the scheduler,
* memory barriers to let the RCU core know about it, regardless of what
* this CPU might (or might not) do in the near future.
*
- * We inform the RCU core by emulating a zero-duration dyntick-idle
- * period, which we in turn do by incrementing the ->dynticks counter
- * by two.
+ * We inform the RCU core by emulating a zero-duration dyntick-idle period.
*
* The caller must have disabled interrupts.
*/
static void rcu_momentary_dyntick_idle(void)
{
- struct rcu_data *rdp;
- int resched_mask;
- struct rcu_state *rsp;
-
- /*
- * Yes, we can lose flag-setting operations. This is OK, because
- * the flag will be set again after some delay.
- */
- resched_mask = raw_cpu_read(rcu_sched_qs_mask);
- raw_cpu_write(rcu_sched_qs_mask, 0);
-
- /* Find the flavor that needs a quiescent state. */
- for_each_rcu_flavor(rsp) {
- rdp = raw_cpu_ptr(rsp->rda);
- if (!(resched_mask & rsp->flavor_mask))
- continue;
- smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
- if (READ_ONCE(rdp->mynode->completed) !=
- READ_ONCE(rdp->cond_resched_completed))
- continue;
-
- /*
- * Pretend to be momentarily idle for the quiescent state.
- * This allows the grace-period kthread to record the
- * quiescent state, with no need for this CPU to do anything
- * further.
- */
- rcu_dynticks_momentary_idle();
- break;
- }
+ raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
+ rcu_dynticks_momentary_idle();
}
/*
* and requires special handling for preemptible RCU.
* The caller must have disabled interrupts.
*/
-void rcu_note_context_switch(void)
+void rcu_note_context_switch(bool preempt)
{
barrier(); /* Avoid RCU read-side critical sections leaking down. */
trace_rcu_utilization(TPS("Start context switch"));
rcu_sched_qs();
rcu_preempt_note_context_switch();
- if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+ /* Load rcu_urgent_qs before other flags. */
+ if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs)))
+ goto out;
+ this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
+ if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs)))
rcu_momentary_dyntick_idle();
+ this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
+ if (!preempt)
+ rcu_note_voluntary_context_switch_lite(current);
+out:
trace_rcu_utilization(TPS("End context switch"));
barrier(); /* Avoid RCU read-side critical sections leaking up. */
}
{
unsigned long flags;
+ if (!raw_cpu_read(rcu_dynticks.rcu_urgent_qs))
+ return;
+ preempt_disable();
+ /* Load rcu_urgent_qs before other flags. */
+ if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) {
+ preempt_enable();
+ return;
+ }
+ this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
barrier(); /* Avoid RCU read-side critical sections leaking down. */
- if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) {
+ if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs))) {
local_irq_save(flags);
rcu_momentary_dyntick_idle();
local_irq_restore(flags);
}
- if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))) {
- /*
- * Yes, we just checked a per-CPU variable with preemption
- * enabled, so we might be migrated to some other CPU at
- * this point. That is OK because in that case, the
- * migration will supply the needed quiescent state.
- * We might end up needlessly disabling preemption and
- * invoking rcu_sched_qs() on the destination CPU, but
- * the probability and cost are both quite low, so this
- * should not be a problem in practice.
- */
- preempt_disable();
+ if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)))
rcu_sched_qs();
- preempt_enable();
- }
- this_cpu_inc(rcu_qs_ctr);
+ this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
barrier(); /* Avoid RCU read-side critical sections leaking up. */
+ preempt_enable();
}
EXPORT_SYMBOL_GPL(rcu_all_qs);
default:
break;
}
- if (rsp != NULL) {
- *flags = READ_ONCE(rsp->gp_flags);
- *gpnum = READ_ONCE(rsp->gpnum);
- *completed = READ_ONCE(rsp->completed);
+ if (rsp == NULL)
return;
- }
- *flags = 0;
- *gpnum = 0;
- *completed = 0;
+ *flags = READ_ONCE(rsp->gp_flags);
+ *gpnum = READ_ONCE(rsp->gpnum);
+ *completed = READ_ONCE(rsp->completed);
}
EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
}
EXPORT_SYMBOL_GPL(rcutorture_record_progress);
-/*
- * Does the CPU have callbacks ready to be invoked?
- */
-static int
-cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
-{
- return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
- rdp->nxttail[RCU_NEXT_TAIL] != NULL;
-}
-
/*
* Return the root node of the specified rcu_state structure.
*/
static bool
cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
{
- int i;
-
if (rcu_gp_in_progress(rsp))
return false; /* No, a grace period is already in progress. */
if (rcu_future_needs_gp(rsp))
return true; /* Yes, a no-CBs CPU needs one. */
- if (!rdp->nxttail[RCU_NEXT_TAIL])
+ if (!rcu_segcblist_is_enabled(&rdp->cblist))
return false; /* No, this is a no-CBs (or offline) CPU. */
- if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
+ if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
return true; /* Yes, CPU has newly registered callbacks. */
- for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
- if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
- ULONG_CMP_LT(READ_ONCE(rsp->completed),
- rdp->nxtcompleted[i]))
- return true; /* Yes, CBs for future grace period. */
+ if (rcu_segcblist_future_gp_needed(&rdp->cblist,
+ READ_ONCE(rsp->completed)))
+ return true; /* Yes, CBs for future grace period. */
return false; /* No grace period needed. */
}
}
EXPORT_SYMBOL_GPL(rcu_is_watching);
+/*
+ * If a holdout task is actually running, request an urgent quiescent
+ * state from its CPU. This is unsynchronized, so migrations can cause
+ * the request to go to the wrong CPU. Which is OK, all that will happen
+ * is that the CPU's next context switch will be a bit slower and next
+ * time around this task will generate another request.
+ */
+void rcu_request_urgent_qs_task(struct task_struct *t)
+{
+ int cpu;
+
+ barrier();
+ cpu = task_cpu(t);
+ if (!task_curr(t))
+ return; /* This task is not running on that CPU. */
+ smp_store_release(per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, cpu), true);
+}
+
#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
/*
bool *isidle, unsigned long *maxj)
{
unsigned long jtsq;
- int *rcrmp;
+ bool *rnhqp;
+ bool *ruqp;
unsigned long rjtsc;
struct rcu_node *rnp;
* might not be the case for nohz_full CPUs looping in the kernel.
*/
rnp = rdp->mynode;
+ ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
- READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_qs_ctr, rdp->cpu) &&
+ READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
return 1;
+ } else {
+ /* Load rcu_qs_ctr before store to rcu_urgent_qs. */
+ smp_store_release(ruqp, true);
}
/* Check for the CPU being offline. */
* in-kernel CPU-bound tasks cannot advance grace periods.
* So if the grace period is old enough, make the CPU pay attention.
* Note that the unsynchronized assignments to the per-CPU
- * rcu_sched_qs_mask variable are safe. Yes, setting of
+ * rcu_need_heavy_qs variable are safe. Yes, setting of
* bits can be lost, but they will be set again on the next
* force-quiescent-state pass. So lost bit sets do not result
* in incorrect behavior, merely in a grace period lasting
* is set too high, we override with half of the RCU CPU stall
* warning delay.
*/
- rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
- if (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
- time_after(jiffies, rdp->rsp->jiffies_resched)) {
- if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
- WRITE_ONCE(rdp->cond_resched_completed,
- READ_ONCE(rdp->mynode->completed));
- smp_mb(); /* ->cond_resched_completed before *rcrmp. */
- WRITE_ONCE(*rcrmp,
- READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
- }
+ rnhqp = &per_cpu(rcu_dynticks.rcu_need_heavy_qs, rdp->cpu);
+ if (!READ_ONCE(*rnhqp) &&
+ (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
+ time_after(jiffies, rdp->rsp->jiffies_resched))) {
+ WRITE_ONCE(*rnhqp, true);
+ /* Store rcu_need_heavy_qs before rcu_urgent_qs. */
+ smp_store_release(ruqp, true);
rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
}
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
+ totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
+ cpu)->cblist);
pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
smp_processor_id(), (long)(jiffies - rsp->gp_start),
(long)rsp->gpnum, (long)rsp->completed, totqlen);
print_cpu_stall_info(rsp, smp_processor_id());
print_cpu_stall_info_end();
for_each_possible_cpu(cpu)
- totqlen += per_cpu_ptr(rsp->rda, cpu)->qlen;
+ totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
+ cpu)->cblist);
pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
jiffies - rsp->gp_start,
(long)rsp->gpnum, (long)rsp->completed, totqlen);
WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
}
-/*
- * Initialize the specified rcu_data structure's default callback list
- * to empty. The default callback list is the one that is not used by
- * no-callbacks CPUs.
- */
-static void init_default_callback_list(struct rcu_data *rdp)
-{
- int i;
-
- rdp->nxtlist = NULL;
- for (i = 0; i < RCU_NEXT_SIZE; i++)
- rdp->nxttail[i] = &rdp->nxtlist;
-}
-
-/*
- * Initialize the specified rcu_data structure's callback list to empty.
- */
-static void init_callback_list(struct rcu_data *rdp)
-{
- if (init_nocb_callback_list(rdp))
- return;
- init_default_callback_list(rdp);
-}
-
/*
* Determine the value that ->completed will have at the end of the
* next subsequent grace period. This is used to tag callbacks so that
unsigned long *c_out)
{
unsigned long c;
- int i;
bool ret = false;
struct rcu_node *rnp_root = rcu_get_root(rdp->rsp);
/*
* Get a new grace-period number. If there really is no grace
* period in progress, it will be smaller than the one we obtained
- * earlier. Adjust callbacks as needed. Note that even no-CBs
- * CPUs have a ->nxtcompleted[] array, so no no-CBs checks needed.
+ * earlier. Adjust callbacks as needed.
*/
c = rcu_cbs_completed(rdp->rsp, rnp_root);
- for (i = RCU_DONE_TAIL; i < RCU_NEXT_TAIL; i++)
- if (ULONG_CMP_LT(c, rdp->nxtcompleted[i]))
- rdp->nxtcompleted[i] = c;
+ if (!rcu_is_nocb_cpu(rdp->cpu))
+ (void)rcu_segcblist_accelerate(&rdp->cblist, c);
/*
* If the needed for the required grace period is already
/*
* Clean up any old requests for the just-ended grace period. Also return
- * whether any additional grace periods have been requested. Also invoke
- * rcu_nocb_gp_cleanup() in order to wake up any no-callbacks kthreads
- * waiting for this grace period to complete.
+ * whether any additional grace periods have been requested.
*/
static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
{
static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
- unsigned long c;
- int i;
- bool ret;
-
- /* If the CPU has no callbacks, nothing to do. */
- if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
- return false;
-
- /*
- * Starting from the sublist containing the callbacks most
- * recently assigned a ->completed number and working down, find the
- * first sublist that is not assignable to an upcoming grace period.
- * Such a sublist has something in it (first two tests) and has
- * a ->completed number assigned that will complete sooner than
- * the ->completed number for newly arrived callbacks (last test).
- *
- * The key point is that any later sublist can be assigned the
- * same ->completed number as the newly arrived callbacks, which
- * means that the callbacks in any of these later sublist can be
- * grouped into a single sublist, whether or not they have already
- * been assigned a ->completed number.
- */
- c = rcu_cbs_completed(rsp, rnp);
- for (i = RCU_NEXT_TAIL - 1; i > RCU_DONE_TAIL; i--)
- if (rdp->nxttail[i] != rdp->nxttail[i - 1] &&
- !ULONG_CMP_GE(rdp->nxtcompleted[i], c))
- break;
+ bool ret = false;
- /*
- * If there are no sublist for unassigned callbacks, leave.
- * At the same time, advance "i" one sublist, so that "i" will
- * index into the sublist where all the remaining callbacks should
- * be grouped into.
- */
- if (++i >= RCU_NEXT_TAIL)
+ /* If no pending (not yet ready to invoke) callbacks, nothing to do. */
+ if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
/*
- * Assign all subsequent callbacks' ->completed number to the next
- * full grace period and group them all in the sublist initially
- * indexed by "i".
+ * Callbacks are often registered with incomplete grace-period
+ * information. Something about the fact that getting exact
+ * information requires acquiring a global lock... RCU therefore
+ * makes a conservative estimate of the grace period number at which
+ * a given callback will become ready to invoke. The following
+ * code checks this estimate and improves it when possible, thus
+ * accelerating callback invocation to an earlier grace-period
+ * number.
*/
- for (; i <= RCU_NEXT_TAIL; i++) {
- rdp->nxttail[i] = rdp->nxttail[RCU_NEXT_TAIL];
- rdp->nxtcompleted[i] = c;
- }
- /* Record any needed additional grace periods. */
- ret = rcu_start_future_gp(rnp, rdp, NULL);
+ if (rcu_segcblist_accelerate(&rdp->cblist, rcu_cbs_completed(rsp, rnp)))
+ ret = rcu_start_future_gp(rnp, rdp, NULL);
/* Trace depending on how much we were able to accelerate. */
- if (!*rdp->nxttail[RCU_WAIT_TAIL])
+ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
else
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
struct rcu_data *rdp)
{
- int i, j;
-
- /* If the CPU has no callbacks, nothing to do. */
- if (!rdp->nxttail[RCU_NEXT_TAIL] || !*rdp->nxttail[RCU_DONE_TAIL])
+ /* If no pending (not yet ready to invoke) callbacks, nothing to do. */
+ if (!rcu_segcblist_pend_cbs(&rdp->cblist))
return false;
/*
* Find all callbacks whose ->completed numbers indicate that they
* are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
*/
- for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) {
- if (ULONG_CMP_LT(rnp->completed, rdp->nxtcompleted[i]))
- break;
- rdp->nxttail[RCU_DONE_TAIL] = rdp->nxttail[i];
- }
- /* Clean up any sublist tail pointers that were misordered above. */
- for (j = RCU_WAIT_TAIL; j < i; j++)
- rdp->nxttail[j] = rdp->nxttail[RCU_DONE_TAIL];
-
- /* Copy down callbacks to fill in empty sublists. */
- for (j = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++, j++) {
- if (rdp->nxttail[j] == rdp->nxttail[RCU_NEXT_TAIL])
- break;
- rdp->nxttail[j] = rdp->nxttail[i];
- rdp->nxtcompleted[j] = rdp->nxtcompleted[i];
- }
+ rcu_segcblist_advance(&rdp->cblist, rnp->completed);
/* Classify any remaining callbacks. */
return rcu_accelerate_cbs(rsp, rnp, rdp);
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
need_gp = !!(rnp->qsmask & rdp->grpmask);
rdp->cpu_no_qs.b.norm = need_gp;
- rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
rdp->core_needs_qs = need_gp;
zero_cpu_stall_ticks(rdp);
WRITE_ONCE(rdp->gpwrap, false);
* within the current grace period.
*/
rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */
- rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+ rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
return;
}
* because _rcu_barrier() excludes CPU-hotplug operations, so it
* cannot be running now. Thus no memory barrier is required.
*/
- if (rdp->nxtlist != NULL) {
- rsp->qlen_lazy += rdp->qlen_lazy;
- rsp->qlen += rdp->qlen;
- rdp->n_cbs_orphaned += rdp->qlen;
- rdp->qlen_lazy = 0;
- WRITE_ONCE(rdp->qlen, 0);
- }
+ rdp->n_cbs_orphaned += rcu_segcblist_n_cbs(&rdp->cblist);
+ rcu_segcblist_extract_count(&rdp->cblist, &rsp->orphan_done);
/*
* Next, move those callbacks still needing a grace period to
* Some of the callbacks might have gone partway through a grace
* period, but that is too bad. They get to start over because we
* cannot assume that grace periods are synchronized across CPUs.
- * We don't bother updating the ->nxttail[] array yet, instead
- * we just reset the whole thing later on.
*/
- if (*rdp->nxttail[RCU_DONE_TAIL] != NULL) {
- *rsp->orphan_nxttail = *rdp->nxttail[RCU_DONE_TAIL];
- rsp->orphan_nxttail = rdp->nxttail[RCU_NEXT_TAIL];
- *rdp->nxttail[RCU_DONE_TAIL] = NULL;
- }
+ rcu_segcblist_extract_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
/*
* Then move the ready-to-invoke callbacks to the orphanage,
* where some other CPU will pick them up. These will not be
* required to pass though another grace period: They are done.
*/
- if (rdp->nxtlist != NULL) {
- *rsp->orphan_donetail = rdp->nxtlist;
- rsp->orphan_donetail = rdp->nxttail[RCU_DONE_TAIL];
- }
+ rcu_segcblist_extract_done_cbs(&rdp->cblist, &rsp->orphan_done);
- /*
- * Finally, initialize the rcu_data structure's list to empty and
- * disallow further callbacks on this CPU.
- */
- init_callback_list(rdp);
- rdp->nxttail[RCU_NEXT_TAIL] = NULL;
+ /* Finally, disallow further callbacks on this CPU. */
+ rcu_segcblist_disable(&rdp->cblist);
}
/*
*/
static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
{
- int i;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
/* No-CBs CPUs are handled specially. */
return;
/* Do the accounting first. */
- rdp->qlen_lazy += rsp->qlen_lazy;
- rdp->qlen += rsp->qlen;
- rdp->n_cbs_adopted += rsp->qlen;
- if (rsp->qlen_lazy != rsp->qlen)
+ rdp->n_cbs_adopted += rsp->orphan_done.len;
+ if (rsp->orphan_done.len_lazy != rsp->orphan_done.len)
rcu_idle_count_callbacks_posted();
- rsp->qlen_lazy = 0;
- rsp->qlen = 0;
+ rcu_segcblist_insert_count(&rdp->cblist, &rsp->orphan_done);
/*
* We do not need a memory barrier here because the only way we
* we are the task doing the rcu_barrier().
*/
- /* First adopt the ready-to-invoke callbacks. */
- if (rsp->orphan_donelist != NULL) {
- *rsp->orphan_donetail = *rdp->nxttail[RCU_DONE_TAIL];
- *rdp->nxttail[RCU_DONE_TAIL] = rsp->orphan_donelist;
- for (i = RCU_NEXT_SIZE - 1; i >= RCU_DONE_TAIL; i--)
- if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
- rdp->nxttail[i] = rsp->orphan_donetail;
- rsp->orphan_donelist = NULL;
- rsp->orphan_donetail = &rsp->orphan_donelist;
- }
-
- /* And then adopt the callbacks that still need a grace period. */
- if (rsp->orphan_nxtlist != NULL) {
- *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxtlist;
- rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_nxttail;
- rsp->orphan_nxtlist = NULL;
- rsp->orphan_nxttail = &rsp->orphan_nxtlist;
- }
+ /* First adopt the ready-to-invoke callbacks, then the done ones. */
+ rcu_segcblist_insert_done_cbs(&rdp->cblist, &rsp->orphan_done);
+ WARN_ON_ONCE(rsp->orphan_done.head);
+ rcu_segcblist_insert_pend_cbs(&rdp->cblist, &rsp->orphan_pend);
+ WARN_ON_ONCE(rsp->orphan_pend.head);
+ WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) !=
+ !rcu_segcblist_n_cbs(&rdp->cblist));
}
/*
*/
static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
{
- RCU_TRACE(unsigned long mask);
- RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
- RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
+ RCU_TRACE(unsigned long mask;)
+ RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
+ RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
return;
- RCU_TRACE(mask = rdp->grpmask);
+ RCU_TRACE(mask = rdp->grpmask;)
trace_rcu_grace_period(rsp->name,
rnp->gpnum + 1 - !!(rnp->qsmask & mask),
TPS("cpuofl"));
rcu_adopt_orphan_cbs(rsp, flags);
raw_spin_unlock_irqrestore(&rsp->orphan_lock, flags);
- WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL,
- "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n",
- cpu, rdp->qlen, rdp->nxtlist);
+ WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 ||
+ !rcu_segcblist_empty(&rdp->cblist),
+ "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n",
+ cpu, rcu_segcblist_n_cbs(&rdp->cblist),
+ rcu_segcblist_first_cb(&rdp->cblist));
}
/*
static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
{
unsigned long flags;
- struct rcu_head *next, *list, **tail;
- long bl, count, count_lazy;
- int i;
+ struct rcu_head *rhp;
+ struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
+ long bl, count;
/* If no callbacks are ready, just return. */
- if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
- trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
- trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist),
+ if (!rcu_segcblist_ready_cbs(&rdp->cblist)) {
+ trace_rcu_batch_start(rsp->name,
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist), 0);
+ trace_rcu_batch_end(rsp->name, 0,
+ !rcu_segcblist_empty(&rdp->cblist),
need_resched(), is_idle_task(current),
rcu_is_callbacks_kthread());
return;
/*
* Extract the list of ready callbacks, disabling to prevent
- * races with call_rcu() from interrupt handlers.
+ * races with call_rcu() from interrupt handlers. Leave the
+ * callback counts, as rcu_barrier() needs to be conservative.
*/
local_irq_save(flags);
WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
bl = rdp->blimit;
- trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, bl);
- list = rdp->nxtlist;
- rdp->nxtlist = *rdp->nxttail[RCU_DONE_TAIL];
- *rdp->nxttail[RCU_DONE_TAIL] = NULL;
- tail = rdp->nxttail[RCU_DONE_TAIL];
- for (i = RCU_NEXT_SIZE - 1; i >= 0; i--)
- if (rdp->nxttail[i] == rdp->nxttail[RCU_DONE_TAIL])
- rdp->nxttail[i] = &rdp->nxtlist;
+ trace_rcu_batch_start(rsp->name, rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist), bl);
+ rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
local_irq_restore(flags);
/* Invoke callbacks. */
- count = count_lazy = 0;
- while (list) {
- next = list->next;
- prefetch(next);
- debug_rcu_head_unqueue(list);
- if (__rcu_reclaim(rsp->name, list))
- count_lazy++;
- list = next;
- /* Stop only if limit reached and CPU has something to do. */
- if (++count >= bl &&
+ rhp = rcu_cblist_dequeue(&rcl);
+ for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+ debug_rcu_head_unqueue(rhp);
+ if (__rcu_reclaim(rsp->name, rhp))
+ rcu_cblist_dequeued_lazy(&rcl);
+ /*
+ * Stop only if limit reached and CPU has something to do.
+ * Note: The rcl structure counts down from zero.
+ */
+ if (-rcl.len >= bl &&
(need_resched() ||
(!is_idle_task(current) && !rcu_is_callbacks_kthread())))
break;
}
local_irq_save(flags);
- trace_rcu_batch_end(rsp->name, count, !!list, need_resched(),
- is_idle_task(current),
- rcu_is_callbacks_kthread());
-
- /* Update count, and requeue any remaining callbacks. */
- if (list != NULL) {
- *tail = rdp->nxtlist;
- rdp->nxtlist = list;
- for (i = 0; i < RCU_NEXT_SIZE; i++)
- if (&rdp->nxtlist == rdp->nxttail[i])
- rdp->nxttail[i] = tail;
- else
- break;
- }
+ count = -rcl.len;
+ trace_rcu_batch_end(rsp->name, count, !!rcl.head, need_resched(),
+ is_idle_task(current), rcu_is_callbacks_kthread());
+
+ /* Update counts and requeue any remaining callbacks. */
+ rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl);
smp_mb(); /* List handling before counting for rcu_barrier(). */
- rdp->qlen_lazy -= count_lazy;
- WRITE_ONCE(rdp->qlen, rdp->qlen - count);
rdp->n_cbs_invoked += count;
+ rcu_segcblist_insert_count(&rdp->cblist, &rcl);
/* Reinstate batch limit if we have worked down the excess. */
- if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
+ count = rcu_segcblist_n_cbs(&rdp->cblist);
+ if (rdp->blimit == LONG_MAX && count <= qlowmark)
rdp->blimit = blimit;
/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
- if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
+ if (count == 0 && rdp->qlen_last_fqs_check != 0) {
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
- } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
- rdp->qlen_last_fqs_check = rdp->qlen;
- WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0));
+ } else if (count < rdp->qlen_last_fqs_check - qhimark)
+ rdp->qlen_last_fqs_check = count;
+ WARN_ON_ONCE(rcu_segcblist_empty(&rdp->cblist) != (count == 0));
local_irq_restore(flags);
/* Re-invoke RCU core processing if there are callbacks remaining. */
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_core();
}
bool needwake;
struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
- WARN_ON_ONCE(rdp->beenonline == 0);
+ WARN_ON_ONCE(!rdp->beenonline);
/* Update RCU state based on any recent quiescent states. */
rcu_check_quiescent_state(rsp, rdp);
}
/* If there are callbacks ready, invoke them. */
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (rcu_segcblist_ready_cbs(&rdp->cblist))
invoke_rcu_callbacks(rsp, rdp);
/* Do any needed deferred wakeups of rcuo kthreads. */
* invoking force_quiescent_state() if the newly enqueued callback
* is the only one waiting for a grace period to complete.
*/
- if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
+ if (unlikely(rcu_segcblist_n_cbs(&rdp->cblist) >
+ rdp->qlen_last_fqs_check + qhimark)) {
/* Are we ignoring a completed grace period? */
note_gp_changes(rsp, rdp);
/* Give the grace period a kick. */
rdp->blimit = LONG_MAX;
if (rsp->n_force_qs == rdp->n_force_qs_snap &&
- *rdp->nxttail[RCU_DONE_TAIL] != head)
+ rcu_segcblist_first_pend_cb(&rdp->cblist) != head)
force_quiescent_state(rsp);
rdp->n_force_qs_snap = rsp->n_force_qs;
- rdp->qlen_last_fqs_check = rdp->qlen;
+ rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
}
}
}
rdp = this_cpu_ptr(rsp->rda);
/* Add the callback to our list. */
- if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL) || cpu != -1) {
+ if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist)) || cpu != -1) {
int offline;
if (cpu != -1)
*/
BUG_ON(cpu != -1);
WARN_ON_ONCE(!rcu_is_watching());
- if (!likely(rdp->nxtlist))
- init_default_callback_list(rdp);
+ if (rcu_segcblist_empty(&rdp->cblist))
+ rcu_segcblist_init(&rdp->cblist);
}
- WRITE_ONCE(rdp->qlen, rdp->qlen + 1);
- if (lazy)
- rdp->qlen_lazy++;
- else
+ rcu_segcblist_enqueue(&rdp->cblist, head, lazy);
+ if (!lazy)
rcu_idle_count_callbacks_posted();
- smp_mb(); /* Count before adding callback for rcu_barrier(). */
- *rdp->nxttail[RCU_NEXT_TAIL] = head;
- rdp->nxttail[RCU_NEXT_TAIL] = &head->next;
if (__is_kfree_rcu_offset((unsigned long)func))
trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func,
- rdp->qlen_lazy, rdp->qlen);
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist));
else
- trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen);
+ trace_rcu_callback(rsp->name, head,
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist),
+ rcu_segcblist_n_cbs(&rdp->cblist));
/* Go handle any RCU core processing required. */
__call_rcu_core(rsp, rdp, head, flags);
}
EXPORT_SYMBOL_GPL(cond_synchronize_sched);
-/* Adjust sequence number for start of update-side operation. */
-static void rcu_seq_start(unsigned long *sp)
-{
- WRITE_ONCE(*sp, *sp + 1);
- smp_mb(); /* Ensure update-side operation after counter increment. */
- WARN_ON_ONCE(!(*sp & 0x1));
-}
-
-/* Adjust sequence number for end of update-side operation. */
-static void rcu_seq_end(unsigned long *sp)
-{
- smp_mb(); /* Ensure update-side operation before counter increment. */
- WRITE_ONCE(*sp, *sp + 1);
- WARN_ON_ONCE(*sp & 0x1);
-}
-
-/* Take a snapshot of the update side's sequence number. */
-static unsigned long rcu_seq_snap(unsigned long *sp)
-{
- unsigned long s;
-
- s = (READ_ONCE(*sp) + 3) & ~0x1;
- smp_mb(); /* Above access must not bleed into critical section. */
- return s;
-}
-
-/*
- * Given a snapshot from rcu_seq_snap(), determine whether or not a
- * full update-side operation has occurred.
- */
-static bool rcu_seq_done(unsigned long *sp, unsigned long s)
-{
- return ULONG_CMP_GE(READ_ONCE(*sp), s);
-}
-
/*
* Check to see if there is any immediate RCU-related work to be done
* by the current CPU, for the specified type of RCU, returning 1 if so.
/* Is the RCU core waiting for a quiescent state from this CPU? */
if (rcu_scheduler_fully_active &&
rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
- rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
+ rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_dynticks.rcu_qs_ctr)) {
rdp->n_rp_core_needs_qs++;
} else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) {
rdp->n_rp_report_qs++;
}
/* Does this CPU have callbacks ready to invoke? */
- if (cpu_has_callbacks_ready_to_invoke(rdp)) {
+ if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
rdp->n_rp_cb_ready++;
return 1;
}
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
- if (!rdp->nxtlist)
+ if (rcu_segcblist_empty(&rdp->cblist))
continue;
hc = true;
- if (rdp->qlen != rdp->qlen_lazy || !all_lazy) {
+ if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist) || !all_lazy) {
al = false;
break;
}
__call_rcu(&rdp->barrier_head,
rcu_barrier_callback, rsp, cpu, 0);
}
- } else if (READ_ONCE(rdp->qlen)) {
+ } else if (rcu_segcblist_n_cbs(&rdp->cblist)) {
_rcu_barrier_trace(rsp, "OnlineQ", cpu,
rsp->barrier_sequence);
smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
rdp->qlen_last_fqs_check = 0;
rdp->n_force_qs_snap = rsp->n_force_qs;
rdp->blimit = blimit;
- if (!rdp->nxtlist)
- init_callback_list(rdp); /* Re-enable callbacks on this CPU. */
+ if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */
+ !init_nocb_callback_list(rdp))
+ rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */
rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
rcu_sysidle_init_percpu_data(rdp->dynticks);
rcu_dynticks_eqs_online();
rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
rdp->completed = rnp->completed;
rdp->cpu_no_qs.b.norm = true;
- rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
+ rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
rdp->core_needs_qs = false;
trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
+/*
+ * Invoked early in the CPU-online process, when pretty much all
+ * services are available. The incoming CPU is not present.
+ */
int rcutree_prepare_cpu(unsigned int cpu)
{
struct rcu_state *rsp;
return 0;
}
+/*
+ * Update RCU priority boot kthread affinity for CPU-hotplug changes.
+ */
static void rcutree_affinity_setting(unsigned int cpu, int outgoing)
{
struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu);
rcu_boost_kthread_setaffinity(rdp->mynode, outgoing);
}
+/*
+ * Near the end of the CPU-online process. Pretty much all services
+ * enabled, and the CPU is now very much alive.
+ */
int rcutree_online_cpu(unsigned int cpu)
{
sync_sched_exp_online_cleanup(cpu);
rcutree_affinity_setting(cpu, -1);
+ if (IS_ENABLED(CONFIG_TREE_SRCU))
+ srcu_online_cpu(cpu);
return 0;
}
+/*
+ * Near the beginning of the process. The CPU is still very much alive
+ * with pretty much all services enabled.
+ */
int rcutree_offline_cpu(unsigned int cpu)
{
rcutree_affinity_setting(cpu, cpu);
+ if (IS_ENABLED(CONFIG_TREE_SRCU))
+ srcu_offline_cpu(cpu);
return 0;
}
-
+/*
+ * Near the end of the offline process. We do only tracing here.
+ */
int rcutree_dying_cpu(unsigned int cpu)
{
struct rcu_state *rsp;
return 0;
}
+/*
+ * The outgoing CPU is gone and we are running elsewhere.
+ */
int rcutree_dead_cpu(unsigned int cpu)
{
struct rcu_state *rsp;
* incoming CPUs are not allowed to use RCU read-side critical sections
* until this function is called. Failing to observe this restriction
* will result in lockdep splats.
+ *
+ * Note that this function is special in that it is invoked directly
+ * from the incoming CPU rather than from the cpuhp_step mechanism.
+ * This is because this function must be invoked at a precise location.
*/
void rcu_cpu_starting(unsigned int cpu)
{
#ifdef CONFIG_HOTPLUG_CPU
/*
- * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function. We now remove it from the rcu_node tree's ->qsmaskinit
- * bit masks.
* The CPU is exiting the idle loop into the arch_cpu_idle_dead()
* function. We now remove it from the rcu_node tree's ->qsmaskinit
* bit masks.
raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
+/*
+ * The outgoing function has no further need of RCU, so remove it from
+ * the list of CPUs that RCU must track.
+ *
+ * Note that this function is special in that it is invoked directly
+ * from the outgoing CPU rather than from the cpuhp_step mechanism.
+ * This is because this function must be invoked at a precise location.
+ */
void rcu_report_dead(unsigned int cpu)
{
struct rcu_state *rsp;
}
#endif
+/*
+ * On non-huge systems, use expedited RCU grace periods to make suspend
+ * and hibernation run faster.
+ */
static int rcu_pm_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
* task is booting the system, and such primitives are no-ops). After this
* function is called, any synchronous grace-period primitives are run as
* expedited, with the requesting task driving the grace period forward.
- * A later core_initcall() rcu_exp_runtime_mode() will switch to full
+ * A later core_initcall() rcu_set_runtime_mode() will switch to full
* runtime RCU functionality.
*/
void rcu_scheduler_starting(void)
rcu_test_sync_prims();
}
-/*
- * Compute the per-level fanout, either using the exact fanout specified
- * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
- */
-static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt)
-{
- int i;
-
- if (rcu_fanout_exact) {
- levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
- for (i = rcu_num_lvls - 2; i >= 0; i--)
- levelspread[i] = RCU_FANOUT;
- } else {
- int ccur;
- int cprv;
-
- cprv = nr_cpu_ids;
- for (i = rcu_num_lvls - 1; i >= 0; i--) {
- ccur = levelcnt[i];
- levelspread[i] = (cprv + ccur - 1) / ccur;
- cprv = ccur;
- }
- }
-}
-
/*
* Helper function for rcu_init() that initializes one rcu_state structure.
*/
static const char * const fqs[] = RCU_FQS_NAME_INIT;
static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
- static u8 fl_mask = 0x1;
- int levelcnt[RCU_NUM_LVLS]; /* # nodes in each level. */
int levelspread[RCU_NUM_LVLS]; /* kids/node in each level. */
int cpustride = 1;
int i;
/* Initialize the level-tracking arrays. */
- for (i = 0; i < rcu_num_lvls; i++)
- levelcnt[i] = num_rcu_lvl[i];
for (i = 1; i < rcu_num_lvls; i++)
- rsp->level[i] = rsp->level[i - 1] + levelcnt[i - 1];
- rcu_init_levelspread(levelspread, levelcnt);
- rsp->flavor_mask = fl_mask;
- fl_mask <<= 1;
+ rsp->level[i] = rsp->level[i - 1] + num_rcu_lvl[i - 1];
+ rcu_init_levelspread(levelspread, num_rcu_lvl);
/* Initialize the elements themselves, starting from the leaves. */
for (i = rcu_num_lvls - 1; i >= 0; i--) {
cpustride *= levelspread[i];
rnp = rsp->level[i];
- for (j = 0; j < levelcnt[i]; j++, rnp++) {
+ for (j = 0; j < num_rcu_lvl[i]; j++, rnp++) {
raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock));
lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock),
&rcu_node_class[i], buf[i]);
for_each_online_cpu(cpu) {
rcutree_prepare_cpu(cpu);
rcu_cpu_starting(cpu);
+ if (IS_ENABLED(CONFIG_TREE_SRCU))
+ srcu_online_cpu(cpu);
}
}
#include <linux/seqlock.h>
#include <linux/swait.h>
#include <linux/stop_machine.h>
+#include <linux/rcu_node_tree.h>
-/*
- * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
- * CONFIG_RCU_FANOUT_LEAF.
- * In theory, it should be possible to add more levels straightforwardly.
- * In practice, this did work well going from three levels to four.
- * Of course, your mileage may vary.
- */
-
-#ifdef CONFIG_RCU_FANOUT
-#define RCU_FANOUT CONFIG_RCU_FANOUT
-#else /* #ifdef CONFIG_RCU_FANOUT */
-# ifdef CONFIG_64BIT
-# define RCU_FANOUT 64
-# else
-# define RCU_FANOUT 32
-# endif
-#endif /* #else #ifdef CONFIG_RCU_FANOUT */
-
-#ifdef CONFIG_RCU_FANOUT_LEAF
-#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
-#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
-# ifdef CONFIG_64BIT
-# define RCU_FANOUT_LEAF 64
-# else
-# define RCU_FANOUT_LEAF 32
-# endif
-#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
-
-#define RCU_FANOUT_1 (RCU_FANOUT_LEAF)
-#define RCU_FANOUT_2 (RCU_FANOUT_1 * RCU_FANOUT)
-#define RCU_FANOUT_3 (RCU_FANOUT_2 * RCU_FANOUT)
-#define RCU_FANOUT_4 (RCU_FANOUT_3 * RCU_FANOUT)
-
-#if NR_CPUS <= RCU_FANOUT_1
-# define RCU_NUM_LVLS 1
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_NODES NUM_RCU_LVL_0
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0" }
-#elif NR_CPUS <= RCU_FANOUT_2
-# define RCU_NUM_LVLS 2
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1" }
-#elif NR_CPUS <= RCU_FANOUT_3
-# define RCU_NUM_LVLS 3
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
-#elif NR_CPUS <= RCU_FANOUT_4
-# define RCU_NUM_LVLS 4
-# define NUM_RCU_LVL_0 1
-# define NUM_RCU_LVL_1 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
-# define NUM_RCU_LVL_2 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
-# define NUM_RCU_LVL_3 DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-# define NUM_RCU_NODES (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
-# define NUM_RCU_LVL_INIT { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
-# define RCU_NODE_NAME_INIT { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
-# define RCU_FQS_NAME_INIT { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
-#else
-# error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
-#endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
-
-extern int rcu_num_lvls;
-extern int rcu_num_nodes;
+#include "rcu_segcblist.h"
/*
* Dynticks per-CPU state.
/* Process level is worth LLONG_MAX/2. */
int dynticks_nmi_nesting; /* Track NMI nesting level. */
atomic_t dynticks; /* Even value for idle, else odd. */
+ bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */
+ unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */
+ bool rcu_urgent_qs; /* GP old need light quiescent state. */
#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
long long dynticks_idle_nesting;
/* irq/process nesting level from idle. */
*/
#define leaf_node_cpu_bit(rnp, cpu) (1UL << ((cpu) - (rnp)->grplo))
-/*
- * Do a full breadth-first scan of the rcu_node structures for the
- * specified rcu_state structure.
- */
-#define rcu_for_each_node_breadth_first(rsp, rnp) \
- for ((rnp) = &(rsp)->node[0]; \
- (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
-
-/*
- * Do a breadth-first scan of the non-leaf rcu_node structures for the
- * specified rcu_state structure. Note that if there is a singleton
- * rcu_node tree with but one rcu_node structure, this loop is a no-op.
- */
-#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \
- for ((rnp) = &(rsp)->node[0]; \
- (rnp) < (rsp)->level[rcu_num_lvls - 1]; (rnp)++)
-
-/*
- * Scan the leaves of the rcu_node hierarchy for the specified rcu_state
- * structure. Note that if there is a singleton rcu_node tree with but
- * one rcu_node structure, this loop -will- visit the rcu_node structure.
- * It is still a leaf node, even if it is also the root node.
- */
-#define rcu_for_each_leaf_node(rsp, rnp) \
- for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
- (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
-
-/*
- * Iterate over all possible CPUs in a leaf RCU node.
- */
-#define for_each_leaf_node_possible_cpu(rnp, cpu) \
- for ((cpu) = cpumask_next(rnp->grplo - 1, cpu_possible_mask); \
- cpu <= rnp->grphi; \
- cpu = cpumask_next((cpu), cpu_possible_mask))
-
/*
* Union to allow "aggregate OR" operation on the need for a quiescent
* state by the normal and expedited grace periods.
/* period it is aware of. */
/* 2) batch handling */
- /*
- * If nxtlist is not NULL, it is partitioned as follows.
- * Any of the partitions might be empty, in which case the
- * pointer to that partition will be equal to the pointer for
- * the following partition. When the list is empty, all of
- * the nxttail elements point to the ->nxtlist pointer itself,
- * which in that case is NULL.
- *
- * [nxtlist, *nxttail[RCU_DONE_TAIL]):
- * Entries that batch # <= ->completed
- * The grace period for these entries has completed, and
- * the other grace-period-completed entries may be moved
- * here temporarily in rcu_process_callbacks().
- * [*nxttail[RCU_DONE_TAIL], *nxttail[RCU_WAIT_TAIL]):
- * Entries that batch # <= ->completed - 1: waiting for current GP
- * [*nxttail[RCU_WAIT_TAIL], *nxttail[RCU_NEXT_READY_TAIL]):
- * Entries known to have arrived before current GP ended
- * [*nxttail[RCU_NEXT_READY_TAIL], *nxttail[RCU_NEXT_TAIL]):
- * Entries that might have arrived after current GP ended
- * Note that the value of *nxttail[RCU_NEXT_TAIL] will
- * always be NULL, as this is the end of the list.
- */
- struct rcu_head *nxtlist;
- struct rcu_head **nxttail[RCU_NEXT_SIZE];
- unsigned long nxtcompleted[RCU_NEXT_SIZE];
- /* grace periods for sublists. */
- long qlen_lazy; /* # of lazy queued callbacks */
- long qlen; /* # of queued callbacks, incl lazy */
+ struct rcu_segcblist cblist; /* Segmented callback list, with */
+ /* different callbacks waiting for */
+ /* different grace periods. */
long qlen_last_fqs_check;
/* qlen at last check for QS forcing */
unsigned long n_cbs_invoked; /* count of RCU cbs invoked. */
struct rcu_node *level[RCU_NUM_LVLS + 1];
/* Hierarchy levels (+1 to */
/* shut bogus gcc warning) */
- u8 flavor_mask; /* bit in flavor mask. */
struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */
call_rcu_func_t call; /* call_rcu() flavor. */
int ncpus; /* # CPUs seen so far. */
raw_spinlock_t orphan_lock ____cacheline_internodealigned_in_smp;
/* Protect following fields. */
- struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */
+ struct rcu_cblist orphan_pend; /* Orphaned callbacks that */
/* need a grace period. */
- struct rcu_head **orphan_nxttail; /* Tail of above. */
- struct rcu_head *orphan_donelist; /* Orphaned callbacks that */
+ struct rcu_cblist orphan_done; /* Orphaned callbacks that */
/* are ready to invoke. */
- struct rcu_head **orphan_donetail; /* Tail of above. */
- long qlen_lazy; /* Number of lazy callbacks. */
- long qlen; /* Total number of callbacks. */
+ /* (Contains counts.) */
/* End of fields guarded by orphan_lock. */
struct mutex barrier_mutex; /* Guards barrier fields. */
#endif /* #ifdef CONFIG_PREEMPT_RCU */
int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
+bool rcu_eqs_special_set(int cpu);
#ifdef CONFIG_RCU_BOOST
DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
static void rcu_dynticks_task_enter(void);
static void rcu_dynticks_task_exit(void);
+#ifdef CONFIG_SRCU
+void srcu_online_cpu(unsigned int cpu);
+void srcu_offline_cpu(unsigned int cpu);
+#else /* #ifdef CONFIG_SRCU */
+void srcu_online_cpu(unsigned int cpu) { }
+void srcu_offline_cpu(unsigned int cpu) { }
+#endif /* #else #ifdef CONFIG_SRCU */
+
#endif /* #ifndef RCU_TREE_NONCORE */
#ifdef CONFIG_RCU_TRACE
trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
rnp->grplo, rnp->grphi,
TPS("wait"));
- wait_event(rnp->exp_wq[(s >> 1) & 0x3],
+ wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
sync_exp_work_done(rsp,
&rdp->exp_workdone2, s));
return true;
return;
}
__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
+ /* Store .exp before .rcu_urgent_qs. */
+ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
resched_cpu(smp_processor_id());
}
rnp->exp_seq_rq = s;
spin_unlock(&rnp->exp_lock);
}
- wake_up_all(&rnp->exp_wq[(rsp->expedited_sequence >> 1) & 0x3]);
+ smp_mb(); /* All above changes before wakeup. */
+ wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rsp->expedited_sequence) & 0x3]);
}
trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
mutex_unlock(&rsp->exp_wake_mutex);
/* Wait for expedited grace period to complete. */
rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
rnp = rcu_get_root(rsp);
- wait_event(rnp->exp_wq[(s >> 1) & 0x3],
- sync_exp_work_done(rsp,
- &rdp->exp_workdone0, s));
+ wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
+ sync_exp_work_done(rsp, &rdp->exp_workdone0, s));
+ smp_mb(); /* Workqueue actions happen before return. */
/* Let the next expedited grace period start. */
mutex_unlock(&rsp->exp_mutex);
EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
-
-/*
- * Switch to run-time mode once Tree RCU has fully initialized.
- */
-static int __init rcu_exp_runtime_mode(void)
-{
- rcu_test_sync_prims();
- rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
- rcu_test_sync_prims();
- return 0;
-}
-core_initcall(rcu_exp_runtime_mode);
*/
if ((rdp->completed != rnp->completed ||
unlikely(READ_ONCE(rdp->gpwrap))) &&
- rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
+ rcu_segcblist_pend_cbs(&rdp->cblist))
note_gp_changes(rsp, rdp);
- if (cpu_has_callbacks_ready_to_invoke(rdp))
+ if (rcu_segcblist_ready_cbs(&rdp->cblist))
cbs_ready = true;
}
return cbs_ready;
rdtp->last_accelerate = jiffies;
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
- if (!*rdp->nxttail[RCU_DONE_TAIL])
+ if (rcu_segcblist_pend_cbs(&rdp->cblist))
continue;
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
for_each_rcu_flavor(rsp) {
rdp = raw_cpu_ptr(rsp->rda);
- if (rdp->qlen_lazy != 0) {
+ if (rcu_segcblist_n_lazy_cbs(&rdp->cblist)) {
atomic_inc(&oom_callback_count);
rsp->call(&rdp->oom_head, rcu_oom_callback);
}
static int __init parse_rcu_nocb_poll(char *arg)
{
- rcu_nocb_poll = 1;
+ rcu_nocb_poll = true;
return 0;
}
early_param("rcu_nocb_poll", parse_rcu_nocb_poll);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmpty"));
} else {
- rdp->nocb_defer_wakeup = RCU_NOGP_WAKE;
+ WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE);
+ /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
+ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeEmptyIsDeferred"));
}
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvf"));
} else {
- rdp->nocb_defer_wakeup = RCU_NOGP_WAKE_FORCE;
+ WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_FORCE);
+ /* Store ->nocb_defer_wakeup before ->rcu_urgent_qs. */
+ smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true);
trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
TPS("WakeOvfIsDeferred"));
}
struct rcu_data *rdp,
unsigned long flags)
{
- long ql = rsp->qlen;
- long qll = rsp->qlen_lazy;
+ long ql = rsp->orphan_done.len;
+ long qll = rsp->orphan_done.len_lazy;
/* If this is not a no-CBs CPU, tell the caller to do it the old way. */
if (!rcu_is_nocb_cpu(smp_processor_id()))
return false;
- rsp->qlen = 0;
- rsp->qlen_lazy = 0;
/* First, enqueue the donelist, if any. This preserves CB ordering. */
- if (rsp->orphan_donelist != NULL) {
- __call_rcu_nocb_enqueue(rdp, rsp->orphan_donelist,
- rsp->orphan_donetail, ql, qll, flags);
- ql = qll = 0;
- rsp->orphan_donelist = NULL;
- rsp->orphan_donetail = &rsp->orphan_donelist;
+ if (rsp->orphan_done.head) {
+ __call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_done),
+ rcu_cblist_tail(&rsp->orphan_done),
+ ql, qll, flags);
}
- if (rsp->orphan_nxtlist != NULL) {
- __call_rcu_nocb_enqueue(rdp, rsp->orphan_nxtlist,
- rsp->orphan_nxttail, ql, qll, flags);
- ql = qll = 0;
- rsp->orphan_nxtlist = NULL;
- rsp->orphan_nxttail = &rsp->orphan_nxtlist;
+ if (rsp->orphan_pend.head) {
+ __call_rcu_nocb_enqueue(rdp, rcu_cblist_head(&rsp->orphan_pend),
+ rcu_cblist_tail(&rsp->orphan_pend),
+ ql, qll, flags);
}
+ rcu_cblist_init(&rsp->orphan_done);
+ rcu_cblist_init(&rsp->orphan_pend);
return true;
}
return false;
/* If there are early-boot callbacks, move them to nocb lists. */
- if (rdp->nxtlist) {
- rdp->nocb_head = rdp->nxtlist;
- rdp->nocb_tail = rdp->nxttail[RCU_NEXT_TAIL];
- atomic_long_set(&rdp->nocb_q_count, rdp->qlen);
- atomic_long_set(&rdp->nocb_q_count_lazy, rdp->qlen_lazy);
- rdp->nxtlist = NULL;
- rdp->qlen = 0;
- rdp->qlen_lazy = 0;
+ if (!rcu_segcblist_empty(&rdp->cblist)) {
+ rdp->nocb_head = rcu_segcblist_head(&rdp->cblist);
+ rdp->nocb_tail = rcu_segcblist_tail(&rdp->cblist);
+ atomic_long_set(&rdp->nocb_q_count,
+ rcu_segcblist_n_cbs(&rdp->cblist));
+ atomic_long_set(&rdp->nocb_q_count_lazy,
+ rcu_segcblist_n_lazy_cbs(&rdp->cblist));
+ rcu_segcblist_init(&rdp->cblist);
}
- rdp->nxttail[RCU_NEXT_TAIL] = NULL;
+ rcu_segcblist_disable(&rdp->cblist);
return true;
}
#include <linux/mutex.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/prefetch.h>
#define RCU_TREE_NONCORE
#include "tree.h"
-
-DECLARE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
+#include "rcu.h"
static int r_open(struct inode *inode, struct file *file,
const struct seq_operations *op)
cpu_is_offline(rdp->cpu) ? '!' : ' ',
ulong2long(rdp->completed), ulong2long(rdp->gpnum),
rdp->cpu_no_qs.b.norm,
- rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
+ rdp->rcu_qs_ctr_snap == per_cpu(rdp->dynticks->rcu_qs_ctr, rdp->cpu),
rdp->core_needs_qs);
seq_printf(m, " dt=%d/%llx/%d df=%lu",
rcu_dynticks_snap(rdp->dynticks),
rdp->dynticks_fqs);
seq_printf(m, " of=%lu", rdp->offline_fqs);
rcu_nocb_q_lengths(rdp, &ql, &qll);
- qll += rdp->qlen_lazy;
- ql += rdp->qlen;
+ qll += rcu_segcblist_n_lazy_cbs(&rdp->cblist);
+ ql += rcu_segcblist_n_cbs(&rdp->cblist);
seq_printf(m, " ql=%ld/%ld qs=%c%c%c%c",
qll, ql,
- ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] !=
- rdp->nxttail[RCU_NEXT_TAIL]],
- ".R"[rdp->nxttail[RCU_WAIT_TAIL] !=
- rdp->nxttail[RCU_NEXT_READY_TAIL]],
- ".W"[rdp->nxttail[RCU_DONE_TAIL] !=
- rdp->nxttail[RCU_WAIT_TAIL]],
- ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]);
+ ".N"[!rcu_segcblist_segempty(&rdp->cblist, RCU_NEXT_TAIL)],
+ ".R"[!rcu_segcblist_segempty(&rdp->cblist,
+ RCU_NEXT_READY_TAIL)],
+ ".W"[!rcu_segcblist_segempty(&rdp->cblist, RCU_WAIT_TAIL)],
+ ".D"[!rcu_segcblist_segempty(&rdp->cblist, RCU_DONE_TAIL)]);
#ifdef CONFIG_RCU_BOOST
seq_printf(m, " kt=%d/%c ktl=%x",
per_cpu(rcu_cpu_has_work, rdp->cpu),
seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
rsp->n_force_qs, rsp->n_force_qs_ngp,
rsp->n_force_qs - rsp->n_force_qs_ngp,
- READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
+ READ_ONCE(rsp->n_force_qs_lh),
+ rsp->orphan_done.len_lazy,
+ rsp->orphan_done.len);
for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
if (rnp->level != level) {
seq_puts(m, "\n");
* non-expedited counterparts? Intended for use within RCU. Note
* that if the user specifies both rcu_expedited and rcu_normal, then
* rcu_normal wins. (Except during the time period during boot from
- * when the first task is spawned until the rcu_exp_runtime_mode()
+ * when the first task is spawned until the rcu_set_runtime_mode()
* core_initcall() is invoked, at which point everything is expedited.)
*/
bool rcu_gp_is_normal(void)
#endif /* #ifndef CONFIG_TINY_RCU */
+/*
+ * Test each non-SRCU synchronous grace-period wait API. This is
+ * useful just after a change in mode for these primitives, and
+ * during early boot.
+ */
+void rcu_test_sync_prims(void)
+{
+ if (!IS_ENABLED(CONFIG_PROVE_RCU))
+ return;
+ synchronize_rcu();
+ synchronize_rcu_bh();
+ synchronize_sched();
+ synchronize_rcu_expedited();
+ synchronize_rcu_bh_expedited();
+ synchronize_sched_expedited();
+}
+
+#if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU)
+
+/*
+ * Switch to run-time mode once RCU has fully initialized.
+ */
+static int __init rcu_set_runtime_mode(void)
+{
+ rcu_test_sync_prims();
+ rcu_scheduler_active = RCU_SCHEDULER_RUNNING;
+ rcu_test_sync_prims();
+ return 0;
+}
+core_initcall(rcu_set_runtime_mode);
+
+#endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */
+
#ifdef CONFIG_PREEMPT_RCU
/*
put_task_struct(t);
return;
}
+ rcu_request_urgent_qs_task(t);
if (!needreport)
return;
if (*firstreport) {
#endif /* #ifdef CONFIG_TASKS_RCU */
-/*
- * Test each non-SRCU synchronous grace-period wait API. This is
- * useful just after a change in mode for these primitives, and
- * during early boot.
- */
-void rcu_test_sync_prims(void)
-{
- if (!IS_ENABLED(CONFIG_PROVE_RCU))
- return;
- synchronize_rcu();
- synchronize_rcu_bh();
- synchronize_sched();
- synchronize_rcu_expedited();
- synchronize_rcu_bh_expedited();
- synchronize_sched_expedited();
-}
-
#ifdef CONFIG_PROVE_RCU
/*
hrtick_clear(rq);
local_irq_disable();
- rcu_note_context_switch();
+ rcu_note_context_switch(preempt);
/*
* Make sure that signal_pending_state()->signal_pending() below
}
/*
* This sighand can be already freed and even reused, but
- * we rely on SLAB_DESTROY_BY_RCU and sighand_ctor() which
+ * we rely on SLAB_TYPESAFE_BY_RCU and sighand_ctor() which
* initializes ->siglock: this slab can't go away, it has
* the same object type, ->siglock can't be reinitialized.
*
if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
return;
- if (iter->started && cpumask_test_cpu(iter->cpu, iter->started))
+ if (cpumask_available(iter->started) &&
+ cpumask_test_cpu(iter->cpu, iter->started))
return;
if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries)
return;
- if (iter->started)
+ if (cpumask_available(iter->started))
cpumask_set_cpu(iter->cpu, iter->started);
/* Don't print started cpu buffer for the first entry of the trace */
entry->type = dma_debug_coherent;
entry->dev = dev;
entry->pfn = page_to_pfn(virt_to_page(virt));
- entry->offset = (size_t) virt & ~PAGE_MASK;
+ entry->offset = offset_in_page(virt);
entry->size = size;
entry->dev_addr = dma_addr;
entry->direction = DMA_BIDIRECTIONAL;
.type = dma_debug_coherent,
.dev = dev,
.pfn = page_to_pfn(virt_to_page(virt)),
- .offset = (size_t) virt & ~PAGE_MASK,
+ .offset = offset_in_page(virt),
.dev_addr = addr,
.size = size,
.direction = DMA_BIDIRECTIONAL,
*size += sizeof(struct kasan_alloc_meta);
/* Add free meta. */
- if (cache->flags & SLAB_DESTROY_BY_RCU || cache->ctor ||
+ if (cache->flags & SLAB_TYPESAFE_BY_RCU || cache->ctor ||
cache->object_size < sizeof(struct kasan_free_meta)) {
cache->kasan_info.free_meta_offset = *size;
*size += sizeof(struct kasan_free_meta);
unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE);
/* RCU slabs could be legally used after free within the RCU period */
- if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
+ if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
return;
kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE);
s8 shadow_byte;
/* RCU slabs could be legally used after free within the RCU period */
- if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
+ if (unlikely(cache->flags & SLAB_TYPESAFE_BY_RCU))
return false;
shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));
void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size)
{
/* TODO: RCU freeing is unsupported for now; hide false positives. */
- if (!s->ctor && !(s->flags & SLAB_DESTROY_BY_RCU))
+ if (!s->ctor && !(s->flags & SLAB_TYPESAFE_BY_RCU))
kmemcheck_mark_freed(object, size);
}
#include <linux/slab.h>
/* global SRCU for all MMs */
-static struct srcu_struct srcu;
+DEFINE_STATIC_SRCU(srcu);
/*
* This function allows mmu_notifier::release callback to delay a call to
BUG_ON(atomic_read(&mm->mm_users) <= 0);
- /*
- * Verify that mmu_notifier_init() already run and the global srcu is
- * initialized.
- */
- BUG_ON(!srcu.per_cpu_ref);
-
ret = -ENOMEM;
mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
if (unlikely(!mmu_notifier_mm))
mmdrop(mm);
}
EXPORT_SYMBOL_GPL(mmu_notifier_unregister_no_release);
-
-static int __init mmu_notifier_init(void)
-{
- return init_srcu_struct(&srcu);
-}
-subsys_initcall(mmu_notifier_init);
void __init anon_vma_init(void)
{
anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma),
- 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
+ 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT,
anon_vma_ctor);
anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain,
SLAB_PANIC|SLAB_ACCOUNT);
* If this page is still mapped, then its anon_vma cannot have been
* freed. But if it has been unmapped, we have no security against the
* anon_vma structure being freed and reused (for another anon_vma:
- * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero()
+ * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero()
* above cannot corrupt).
*/
if (!page_mapped(page)) {
freelist = page->freelist;
slab_destroy_debugcheck(cachep, page);
- if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
+ if (unlikely(cachep->flags & SLAB_TYPESAFE_BY_RCU))
call_rcu(&page->rcu_head, kmem_rcu_free);
else
kmem_freepages(cachep, page);
cachep->num = 0;
- if (cachep->ctor || flags & SLAB_DESTROY_BY_RCU)
+ if (cachep->ctor || flags & SLAB_TYPESAFE_BY_RCU)
return false;
left = calculate_slab_order(cachep, size,
if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
2 * sizeof(unsigned long long)))
flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
- if (!(flags & SLAB_DESTROY_BY_RCU))
+ if (!(flags & SLAB_TYPESAFE_BY_RCU))
flags |= SLAB_POISON;
#endif
#endif
/* Legal flag mask for kmem_cache_create(), for various configurations */
#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
- SLAB_DESTROY_BY_RCU | SLAB_DEBUG_OBJECTS )
+ SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
#if defined(CONFIG_DEBUG_SLAB)
#define SLAB_DEBUG_FLAGS (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER)
* back there or track user information then we can
* only use the space before that information.
*/
- if (s->flags & (SLAB_DESTROY_BY_RCU | SLAB_STORE_USER))
+ if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER))
return s->inuse;
/*
* Else we can use all the padding etc for the allocation
* Set of flags that will prevent slab merging
*/
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
- SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
+ SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \
SLAB_FAILSLAB | SLAB_KASAN)
#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
struct kmem_cache *s, *s2;
/*
- * On destruction, SLAB_DESTROY_BY_RCU kmem_caches are put on the
+ * On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the
* @slab_caches_to_rcu_destroy list. The slab pages are freed
* through RCU and and the associated kmem_cache are dereferenced
* while freeing the pages, so the kmem_caches should be freed only
memcg_unlink_cache(s);
list_del(&s->list);
- if (s->flags & SLAB_DESTROY_BY_RCU) {
+ if (s->flags & SLAB_TYPESAFE_BY_RCU) {
list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
schedule_work(&slab_caches_to_rcu_destroy_work);
} else {
/*
* struct slob_rcu is inserted at the tail of allocated slob blocks, which
- * were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
+ * were created with a SLAB_TYPESAFE_BY_RCU slab. slob_rcu is used to free
* the block using call_rcu.
*/
struct slob_rcu {
int __kmem_cache_create(struct kmem_cache *c, unsigned long flags)
{
- if (flags & SLAB_DESTROY_BY_RCU) {
+ if (flags & SLAB_TYPESAFE_BY_RCU) {
/* leave room for rcu footer at the end of object */
c->size += sizeof(struct slob_rcu);
}
void kmem_cache_free(struct kmem_cache *c, void *b)
{
kmemleak_free_recursive(b, c->flags);
- if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
+ if (unlikely(c->flags & SLAB_TYPESAFE_BY_RCU)) {
struct slob_rcu *slob_rcu;
slob_rcu = b + (c->size - sizeof(struct slob_rcu));
slob_rcu->size = c->size;
static void free_slab(struct kmem_cache *s, struct page *page)
{
- if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
+ if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
struct rcu_head *head;
if (need_reserve_slab_rcu) {
* slab_free_freelist_hook() could have put the items into quarantine.
* If so, no need to free them.
*/
- if (s->flags & SLAB_KASAN && !(s->flags & SLAB_DESTROY_BY_RCU))
+ if (s->flags & SLAB_KASAN && !(s->flags & SLAB_TYPESAFE_BY_RCU))
return;
do_slab_free(s, page, head, tail, cnt, addr);
}
* the slab may touch the object after free or before allocation
* then we should never poison the object itself.
*/
- if ((flags & SLAB_POISON) && !(flags & SLAB_DESTROY_BY_RCU) &&
+ if ((flags & SLAB_POISON) && !(flags & SLAB_TYPESAFE_BY_RCU) &&
!s->ctor)
s->flags |= __OBJECT_POISON;
else
*/
s->inuse = size;
- if (((flags & (SLAB_DESTROY_BY_RCU | SLAB_POISON)) ||
+ if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) ||
s->ctor)) {
/*
* Relocate free pointer after the object if it is not
s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor);
s->reserved = 0;
- if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
+ if (need_reserve_slab_rcu && (s->flags & SLAB_TYPESAFE_BY_RCU))
s->reserved = sizeof(struct rcu_head);
if (!calculate_sizes(s, -1))
static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", !!(s->flags & SLAB_DESTROY_BY_RCU));
+ return sprintf(buf, "%d\n", !!(s->flags & SLAB_TYPESAFE_BY_RCU));
}
SLAB_ATTR_RO(destroy_by_rcu);
}
}
- if (printk_ratelimit())
+ if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n",
size);
kfree(va);
{
struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
netdev_features_t old_features = features;
+ netdev_features_t lower_features;
- features = netdev_intersect_features(features, real_dev->vlan_features);
- features |= NETIF_F_RXCSUM;
- features = netdev_intersect_features(features, real_dev->features);
+ lower_features = netdev_intersect_features((real_dev->vlan_features |
+ NETIF_F_RXCSUM),
+ real_dev->features);
+ /* Add HW_CSUM setting to preserve user ability to control
+ * checksum offload on the vlan device.
+ */
+ if (lower_features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
+ lower_features |= NETIF_F_HW_CSUM;
+ features = netdev_intersect_features(features, lower_features);
features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE);
features |= NETIF_F_LLTX;
+ nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */
+ nla_total_size(1) /* IFLA_BRPORT_LEARNING */
+ nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */
+ + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */
+ + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP */
+ nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */
+ nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */
[IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 },
[IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 },
[IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 },
+ [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 },
+ [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 },
};
/* Change the state of the port and notify spanning tree */
}
EXPORT_SYMBOL(libceph_compatible);
+static int param_get_supported_features(char *buffer,
+ const struct kernel_param *kp)
+{
+ return sprintf(buffer, "0x%llx", CEPH_FEATURES_SUPPORTED_DEFAULT);
+}
+static const struct kernel_param_ops param_ops_supported_features = {
+ .get = param_get_supported_features,
+};
+module_param_cb(supported_features, ¶m_ops_supported_features, NULL,
+ S_IRUGO);
+
/*
* find filename portion of a path (/foo/bar/baz -> baz)
*/
/*
* create a fresh client instance
*/
-struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private,
- u64 supported_features,
- u64 required_features)
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
{
struct ceph_client *client;
struct ceph_entity_addr *myaddr = NULL;
init_waitqueue_head(&client->auth_wq);
client->auth_err = 0;
- if (!ceph_test_opt(client, NOMSGAUTH))
- required_features |= CEPH_FEATURE_MSG_AUTH;
-
client->extra_mon_dispatch = NULL;
- client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT |
- supported_features;
- client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT |
- required_features;
+ client->supported_features = CEPH_FEATURES_SUPPORTED_DEFAULT;
+ client->required_features = CEPH_FEATURES_REQUIRED_DEFAULT;
+
+ if (!ceph_test_opt(client, NOMSGAUTH))
+ client->required_features |= CEPH_FEATURE_MSG_AUTH;
/* msgr */
if (ceph_test_opt(client, MYIP))
}
EXPORT_SYMBOL(ceph_cls_break_lock);
+int ceph_cls_set_cookie(struct ceph_osd_client *osdc,
+ struct ceph_object_id *oid,
+ struct ceph_object_locator *oloc,
+ char *lock_name, u8 type, char *old_cookie,
+ char *tag, char *new_cookie)
+{
+ int cookie_op_buf_size;
+ int name_len = strlen(lock_name);
+ int old_cookie_len = strlen(old_cookie);
+ int tag_len = strlen(tag);
+ int new_cookie_len = strlen(new_cookie);
+ void *p, *end;
+ struct page *cookie_op_page;
+ int ret;
+
+ cookie_op_buf_size = name_len + sizeof(__le32) +
+ old_cookie_len + sizeof(__le32) +
+ tag_len + sizeof(__le32) +
+ new_cookie_len + sizeof(__le32) +
+ sizeof(u8) + CEPH_ENCODING_START_BLK_LEN;
+ if (cookie_op_buf_size > PAGE_SIZE)
+ return -E2BIG;
+
+ cookie_op_page = alloc_page(GFP_NOIO);
+ if (!cookie_op_page)
+ return -ENOMEM;
+
+ p = page_address(cookie_op_page);
+ end = p + cookie_op_buf_size;
+
+ /* encode cls_lock_set_cookie_op struct */
+ ceph_start_encoding(&p, 1, 1,
+ cookie_op_buf_size - CEPH_ENCODING_START_BLK_LEN);
+ ceph_encode_string(&p, end, lock_name, name_len);
+ ceph_encode_8(&p, type);
+ ceph_encode_string(&p, end, old_cookie, old_cookie_len);
+ ceph_encode_string(&p, end, tag, tag_len);
+ ceph_encode_string(&p, end, new_cookie, new_cookie_len);
+
+ dout("%s lock_name %s type %d old_cookie %s tag %s new_cookie %s\n",
+ __func__, lock_name, type, old_cookie, tag, new_cookie);
+ ret = ceph_osdc_call(osdc, oid, oloc, "lock", "set_cookie",
+ CEPH_OSD_FLAG_WRITE, cookie_op_page,
+ cookie_op_buf_size, NULL, NULL);
+
+ dout("%s: status %d\n", __func__, ret);
+ __free_page(cookie_op_page);
+ return ret;
+}
+EXPORT_SYMBOL(ceph_cls_set_cookie);
+
void ceph_free_lockers(struct ceph_locker *lockers, u32 num_lockers)
{
int i;
return 0;
down_read(&osdc->lock);
- seq_printf(s, "epoch %d flags 0x%x\n", map->epoch, map->flags);
+ seq_printf(s, "epoch %u barrier %u flags 0x%x\n", map->epoch,
+ osdc->epoch_barrier, map->flags);
for (n = rb_first(&map->pg_pools); n; n = rb_next(n)) {
struct ceph_pg_pool_info *pi =
seq_printf(s, "%llu\t", req->r_tid);
dump_target(s, &req->r_t);
- seq_printf(s, "\t%d\t%u'%llu", req->r_attempts,
- le32_to_cpu(req->r_replay_version.epoch),
- le64_to_cpu(req->r_replay_version.version));
+ seq_printf(s, "\t%d", req->r_attempts);
for (i = 0; i < req->r_num_ops; i++) {
struct ceph_osd_req_op *op = &req->r_ops[i];
truncate_size, truncate_seq);
}
+ req->r_abort_on_full = true;
req->r_flags = flags;
req->r_base_oloc.pool = layout->pool_id;
req->r_base_oloc.pool_ns = ceph_try_get_string(layout->pool_ns);
*/
static void osd_init(struct ceph_osd *osd)
{
- atomic_set(&osd->o_ref, 1);
+ refcount_set(&osd->o_ref, 1);
RB_CLEAR_NODE(&osd->o_node);
osd->o_requests = RB_ROOT;
osd->o_linger_requests = RB_ROOT;
static struct ceph_osd *get_osd(struct ceph_osd *osd)
{
- if (atomic_inc_not_zero(&osd->o_ref)) {
- dout("get_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref)-1,
- atomic_read(&osd->o_ref));
+ if (refcount_inc_not_zero(&osd->o_ref)) {
+ dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1,
+ refcount_read(&osd->o_ref));
return osd;
} else {
dout("get_osd %p FAIL\n", osd);
static void put_osd(struct ceph_osd *osd)
{
- dout("put_osd %p %d -> %d\n", osd, atomic_read(&osd->o_ref),
- atomic_read(&osd->o_ref) - 1);
- if (atomic_dec_and_test(&osd->o_ref)) {
+ dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref),
+ refcount_read(&osd->o_ref) - 1);
+ if (refcount_dec_and_test(&osd->o_ref)) {
osd_cleanup(osd);
kfree(osd);
}
__pool_full(pi);
WARN_ON(pi->id != t->base_oloc.pool);
- return (t->flags & CEPH_OSD_FLAG_READ && pauserd) ||
- (t->flags & CEPH_OSD_FLAG_WRITE && pausewr);
+ return ((t->flags & CEPH_OSD_FLAG_READ) && pauserd) ||
+ ((t->flags & CEPH_OSD_FLAG_WRITE) && pausewr) ||
+ (osdc->osdmap->epoch < osdc->epoch_barrier);
}
enum calc_target_result {
ceph_encode_32(&p, req->r_flags);
ceph_encode_timespec(p, &req->r_mtime);
p += sizeof(struct ceph_timespec);
- /* aka reassert_version */
- memcpy(p, &req->r_replay_version, sizeof(req->r_replay_version));
- p += sizeof(req->r_replay_version);
+
+ /* reassert_version */
+ memset(p, 0, sizeof(struct ceph_eversion));
+ p += sizeof(struct ceph_eversion);
/* oloc */
ceph_start_encoding(&p, 5, 4,
ceph_monc_renew_subs(&osdc->client->monc);
}
+static void complete_request(struct ceph_osd_request *req, int err);
static void send_map_check(struct ceph_osd_request *req);
static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
enum calc_target_result ct_res;
bool need_send = false;
bool promoted = false;
+ bool need_abort = false;
WARN_ON(req->r_tid);
dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
goto promote;
}
- if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
- ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
+ if (osdc->osdmap->epoch < osdc->epoch_barrier) {
+ dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch,
+ osdc->epoch_barrier);
+ req->r_t.paused = true;
+ maybe_request_map(osdc);
+ } else if ((req->r_flags & CEPH_OSD_FLAG_WRITE) &&
+ ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR)) {
dout("req %p pausewr\n", req);
req->r_t.paused = true;
maybe_request_map(osdc);
pr_warn_ratelimited("FULL or reached pool quota\n");
req->r_t.paused = true;
maybe_request_map(osdc);
+ if (req->r_abort_on_full)
+ need_abort = true;
} else if (!osd_homeless(osd)) {
need_send = true;
} else {
link_request(osd, req);
if (need_send)
send_request(req);
+ else if (need_abort)
+ complete_request(req, -ENOSPC);
mutex_unlock(&osd->lock);
if (ct_res == CALC_TARGET_POOL_DNE)
complete_request(req, err);
}
+static void update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
+{
+ if (likely(eb > osdc->epoch_barrier)) {
+ dout("updating epoch_barrier from %u to %u\n",
+ osdc->epoch_barrier, eb);
+ osdc->epoch_barrier = eb;
+ /* Request map if we're not to the barrier yet */
+ if (eb > osdc->osdmap->epoch)
+ maybe_request_map(osdc);
+ }
+}
+
+void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
+{
+ down_read(&osdc->lock);
+ if (unlikely(eb > osdc->epoch_barrier)) {
+ up_read(&osdc->lock);
+ down_write(&osdc->lock);
+ update_epoch_barrier(osdc, eb);
+ up_write(&osdc->lock);
+ } else {
+ up_read(&osdc->lock);
+ }
+}
+EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier);
+
+/*
+ * Drop all pending requests that are stalled waiting on a full condition to
+ * clear, and complete them with ENOSPC as the return code. Set the
+ * osdc->epoch_barrier to the latest map epoch that we've seen if any were
+ * cancelled.
+ */
+static void ceph_osdc_abort_on_full(struct ceph_osd_client *osdc)
+{
+ struct rb_node *n;
+ bool victims = false;
+
+ dout("enter abort_on_full\n");
+
+ if (!ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) && !have_pool_full(osdc))
+ goto out;
+
+ /* Scan list and see if there is anything to abort */
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+ struct rb_node *m;
+
+ m = rb_first(&osd->o_requests);
+ while (m) {
+ struct ceph_osd_request *req = rb_entry(m,
+ struct ceph_osd_request, r_node);
+ m = rb_next(m);
+
+ if (req->r_abort_on_full) {
+ victims = true;
+ break;
+ }
+ }
+ if (victims)
+ break;
+ }
+
+ if (!victims)
+ goto out;
+
+ /*
+ * Update the barrier to current epoch if it's behind that point,
+ * since we know we have some calls to be aborted in the tree.
+ */
+ update_epoch_barrier(osdc, osdc->osdmap->epoch);
+
+ for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
+ struct ceph_osd *osd = rb_entry(n, struct ceph_osd, o_node);
+ struct rb_node *m;
+
+ m = rb_first(&osd->o_requests);
+ while (m) {
+ struct ceph_osd_request *req = rb_entry(m,
+ struct ceph_osd_request, r_node);
+ m = rb_next(m);
+
+ if (req->r_abort_on_full &&
+ (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
+ pool_full(osdc, req->r_t.target_oloc.pool)))
+ abort_request(req, -ENOSPC);
+ }
+ }
+out:
+ dout("return abort_on_full barrier=%u\n", osdc->epoch_barrier);
+}
+
static void check_pool_dne(struct ceph_osd_request *req)
{
struct ceph_osd_client *osdc = req->r_osdc;
pausewr = ceph_osdmap_flag(osdc, CEPH_OSDMAP_PAUSEWR) ||
ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL) ||
have_pool_full(osdc);
- if (was_pauserd || was_pausewr || pauserd || pausewr)
+ if (was_pauserd || was_pausewr || pauserd || pausewr ||
+ osdc->osdmap->epoch < osdc->epoch_barrier)
maybe_request_map(osdc);
kick_requests(osdc, &need_resend, &need_resend_linger);
+ ceph_osdc_abort_on_full(osdc);
ceph_monc_got_map(&osdc->client->monc, CEPH_SUB_OSDMAP,
osdc->osdmap->epoch);
up_write(&osdc->lock);
close_osd(osd);
}
up_write(&osdc->lock);
- WARN_ON(atomic_read(&osdc->homeless_osd.o_ref) != 1);
+ WARN_ON(refcount_read(&osdc->homeless_osd.o_ref) != 1);
osd_cleanup(&osdc->homeless_osd);
WARN_ON(!list_empty(&osdc->osd_lru));
void ceph_pagelist_release(struct ceph_pagelist *pl)
{
- if (!atomic_dec_and_test(&pl->refcnt))
+ if (!refcount_dec_and_test(&pl->refcnt))
return;
ceph_pagelist_unmap_tail(pl);
while (!list_empty(&pl->head)) {
if (!snapc)
return NULL;
- atomic_set(&snapc->nref, 1);
+ refcount_set(&snapc->nref, 1);
snapc->num_snaps = snap_count;
return snapc;
struct ceph_snap_context *ceph_get_snap_context(struct ceph_snap_context *sc)
{
if (sc)
- atomic_inc(&sc->nref);
+ refcount_inc(&sc->nref);
return sc;
}
EXPORT_SYMBOL(ceph_get_snap_context);
{
if (!sc)
return;
- if (atomic_dec_and_test(&sc->nref)) {
+ if (refcount_dec_and_test(&sc->nref)) {
/*printk(" deleting snap_context %p\n", sc);*/
kfree(sc);
}
static __always_inline void net_secret_init(void)
{
- net_get_random_once(&ts_secret, sizeof(ts_secret));
net_get_random_once(&net_secret, sizeof(net_secret));
}
+
+static __always_inline void ts_secret_init(void)
+{
+ net_get_random_once(&ts_secret, sizeof(ts_secret));
+}
#endif
#ifdef CONFIG_INET
#endif
#if IS_ENABLED(CONFIG_IPV6)
-static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
+u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
{
const struct {
struct in6_addr saddr;
if (sysctl_tcp_timestamps != 1)
return 0;
+ ts_secret_init();
return siphash(&combined, offsetofend(typeof(combined), daddr),
&ts_secret);
}
+EXPORT_SYMBOL(secure_tcpv6_ts_off);
-u32 secure_tcpv6_seq_and_tsoff(const __be32 *saddr, const __be32 *daddr,
- __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
+ __be16 sport, __be16 dport)
{
const struct {
struct in6_addr saddr;
.sport = sport,
.dport = dport
};
- u64 hash;
+ u32 hash;
+
net_secret_init();
hash = siphash(&combined, offsetofend(typeof(combined), dport),
&net_secret);
- *tsoff = secure_tcpv6_ts_off(saddr, daddr);
return seq_scale(hash);
}
-EXPORT_SYMBOL(secure_tcpv6_seq_and_tsoff);
+EXPORT_SYMBOL(secure_tcpv6_seq);
u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
__be16 dport)
#endif
#ifdef CONFIG_INET
-static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
+u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
{
if (sysctl_tcp_timestamps != 1)
return 0;
+ ts_secret_init();
return siphash_2u32((__force u32)saddr, (__force u32)daddr,
&ts_secret);
}
* it would be easy enough to have the former function use siphash_4u32, passing
* the arguments as separate u32.
*/
-u32 secure_tcp_seq_and_tsoff(__be32 saddr, __be32 daddr,
- __be16 sport, __be16 dport, u32 *tsoff)
+u32 secure_tcp_seq(__be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport)
{
- u64 hash;
+ u32 hash;
+
net_secret_init();
hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
(__force u32)sport << 16 | (__force u32)dport,
&net_secret);
- *tsoff = secure_tcp_ts_off(saddr, daddr);
return seq_scale(hash);
}
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
.rsk_prot = &dccp_request_sock_ops,
.twsk_prot = &dccp_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
.rsk_prot = &dccp6_request_sock_ops,
.twsk_prot = &dccp6_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,
static int dn_neigh_construct(struct neighbour *neigh)
{
struct net_device *dev = neigh->dev;
- struct dn_neigh *dn = (struct dn_neigh *)neigh;
+ struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n);
struct dn_dev *dn_db;
struct neigh_parms *parms;
struct dst_entry *dst = skb_dst(skb);
struct dn_route *rt = (struct dn_route *) dst;
struct neighbour *neigh = rt->n;
- struct dn_neigh *dn = (struct dn_neigh *)neigh;
+ struct dn_neigh *dn = container_of(neigh, struct dn_neigh, n);
struct dn_dev *dn_db;
bool use_long;
neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1);
- dn = (struct dn_neigh *)neigh;
+ dn = container_of(neigh, struct dn_neigh, n);
if (neigh) {
write_lock(&neigh->lock);
neigh = __neigh_lookup(&dn_neigh_table, &src, skb->dev, 1);
- dn = (struct dn_neigh *)neigh;
+ dn = container_of(neigh, struct dn_neigh, n);
if (neigh) {
write_lock(&neigh->lock);
if (neigh->dev != s->dev)
return;
- dn = (struct dn_neigh *) neigh;
+ dn = container_of(neigh, struct dn_neigh, n);
if (!(dn->flags & (DN_NDFLAG_R1|DN_NDFLAG_R2)))
return;
static inline void dn_neigh_format_entry(struct seq_file *seq,
struct neighbour *n)
{
- struct dn_neigh *dn = (struct dn_neigh *) n;
+ struct dn_neigh *dn = container_of(n, struct dn_neigh, n);
char buf[DN_ASCBUF_LEN];
read_lock(&n->lock);
/* listeners have SOCK_RCU_FREE, not the children */
sock_reset_flag(newsk, SOCK_RCU_FREE);
+ inet_sk(newsk)->mc_list = NULL;
+
newsk->sk_mark = inet_rsk(req)->ir_mark;
atomic64_set(&newsk->sk_cookie,
atomic64_read(&inet_rsk(req)->ir_cookie));
struct ip_tunnel *t = netdev_priv(dev);
struct ip_tunnel_parm *p = &t->parms;
- nla_put_u32(skb, IFLA_VTI_LINK, p->link);
- nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key);
- nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key);
- nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr);
- nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr);
- nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark);
+ if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) ||
+ nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) ||
+ nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) ||
+ nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) ||
+ nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) ||
+ nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark))
+ return -EMSGSIZE;
return 0;
}
#include <linux/siphash.h>
#include <linux/kernel.h>
#include <linux/export.h>
+#include <net/secure_seq.h>
#include <net/tcp.h>
#include <net/route.h>
struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
- struct dst_entry *dst)
+ struct dst_entry *dst, u32 tsoff)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct sock *child;
NULL, &own_req);
if (child) {
atomic_set(&req->rsk_refcnt, 1);
+ tcp_sk(child)->tsoffset = tsoff;
sock_rps_save_rxhash(child, skb);
inet_csk_reqsk_queue_add(sk, req, child);
} else {
struct rtable *rt;
__u8 rcv_wscale;
struct flowi4 fl4;
+ u32 tsoff = 0;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
memset(&tcp_opt, 0, sizeof(tcp_opt));
tcp_parse_options(skb, &tcp_opt, 0, NULL);
+ if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
+ tsoff = secure_tcp_ts_off(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr);
+ tcp_opt.rcv_tsecr -= tsoff;
+ }
+
if (!cookie_timestamp_decode(&tcp_opt))
goto out;
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), &rt->dst);
- ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
+ ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst, tsoff);
/* ip_queue_xmit() depends on our flow being setup
* Normal sockets get it right from inet_csk_route_child_sock()
*/
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 1;
EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
-EXPORT_SYMBOL(sysctl_tcp_timestamps);
/* rfc5961 challenge ack rate limiting */
int sysctl_tcp_challenge_ack_limit = 1000;
if (security_inet_conn_request(sk, skb, req))
goto drop_and_free;
- if (isn && tmp_opt.tstamp_ok)
- af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
+ if (tmp_opt.tstamp_ok)
+ tcp_rsk(req)->ts_off = af_ops->init_ts_off(skb);
if (!want_cookie && !isn) {
/* Kill the following clause, if you dislike this way. */
goto drop_and_release;
}
- isn = af_ops->init_seq_tsoff(skb, &tcp_rsk(req)->ts_off);
+ isn = af_ops->init_seq(skb);
}
if (!dst) {
dst = af_ops->route_req(sk, &fl, req);
if (want_cookie) {
isn = cookie_init_sequence(af_ops, sk, skb, &req->mss);
- tcp_rsk(req)->ts_off = 0;
req->cookie_ts = tmp_opt.tstamp_ok;
if (!tmp_opt.tstamp_ok)
inet_rsk(req)->ecn_ok = 0;
struct inet_hashinfo tcp_hashinfo;
EXPORT_SYMBOL(tcp_hashinfo);
-static u32 tcp_v4_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v4_init_seq(const struct sk_buff *skb)
{
- return secure_tcp_seq_and_tsoff(ip_hdr(skb)->daddr,
- ip_hdr(skb)->saddr,
- tcp_hdr(skb)->dest,
- tcp_hdr(skb)->source, tsoff);
+ return secure_tcp_seq(ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr,
+ tcp_hdr(skb)->dest,
+ tcp_hdr(skb)->source);
+}
+
+static u32 tcp_v4_init_ts_off(const struct sk_buff *skb)
+{
+ return secure_tcp_ts_off(ip_hdr(skb)->daddr,
+ ip_hdr(skb)->saddr);
}
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
struct flowi4 *fl4;
struct rtable *rt;
int err;
- u32 seq;
struct ip_options_rcu *inet_opt;
struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
rt = NULL;
if (likely(!tp->repair)) {
- seq = secure_tcp_seq_and_tsoff(inet->inet_saddr,
- inet->inet_daddr,
- inet->inet_sport,
- usin->sin_port,
- &tp->tsoffset);
if (!tp->write_seq)
- tp->write_seq = seq;
+ tp->write_seq = secure_tcp_seq(inet->inet_saddr,
+ inet->inet_daddr,
+ inet->inet_sport,
+ usin->sin_port);
+ tp->tsoffset = secure_tcp_ts_off(inet->inet_saddr,
+ inet->inet_daddr);
}
inet->inet_id = tp->write_seq ^ jiffies;
.cookie_init_seq = cookie_v4_init_sequence,
#endif
.route_req = tcp_v4_route_req,
- .init_seq_tsoff = tcp_v4_init_seq_and_tsoff,
+ .init_seq = tcp_v4_init_seq,
+ .init_ts_off = tcp_v4_init_ts_off,
.send_synack = tcp_v4_send_synack,
};
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
{
+ const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
struct tcp_sock *tp = tcp_sk(sk);
/* Track the maximum number of outstanding packets in each
tp->snd_cwnd_used = tp->packets_out;
if (sysctl_tcp_slow_start_after_idle &&
- (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto)
+ (s32)(tcp_time_stamp - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
+ !ca_ops->cong_control)
tcp_cwnd_application_limited(sk);
/* The following conditions together indicate the starvation
*/
static struct notifier_block ipv6_dev_notf = {
.notifier_call = addrconf_notify,
+ .priority = ADDRCONF_NOTIFY_PRIORITY,
};
static void addrconf_type_change(struct net_device *dev, unsigned long event)
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
- if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
+ if (!(dev->flags & IFF_LOOPBACK))
+ return NOTIFY_OK;
+
+ if (event == NETDEV_REGISTER) {
net->ipv6.ip6_null_entry->dst.dev = dev;
net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev);
net->ipv6.ip6_blk_hole_entry->dst.dev = dev;
net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
+#endif
+ } else if (event == NETDEV_UNREGISTER) {
+ in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev);
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+ in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev);
+ in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev);
#endif
}
static struct notifier_block ip6_route_dev_notifier = {
.notifier_call = ip6_route_dev_notify,
- .priority = 0,
+ .priority = ADDRCONF_NOTIFY_PRIORITY - 10,
};
void __init ip6_route_init_special_entries(void)
#include <linux/random.h>
#include <linux/siphash.h>
#include <linux/kernel.h>
+#include <net/secure_seq.h>
#include <net/ipv6.h>
#include <net/tcp.h>
int mss;
struct dst_entry *dst;
__u8 rcv_wscale;
+ u32 tsoff = 0;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
memset(&tcp_opt, 0, sizeof(tcp_opt));
tcp_parse_options(skb, &tcp_opt, 0, NULL);
+ if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) {
+ tsoff = secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32,
+ ipv6_hdr(skb)->saddr.s6_addr32);
+ tcp_opt.rcv_tsecr -= tsoff;
+ }
+
if (!cookie_timestamp_decode(&tcp_opt))
goto out;
ireq->rcv_wscale = rcv_wscale;
ireq->ecn_ok = cookie_ecn_ok(&tcp_opt, sock_net(sk), dst);
- ret = tcp_get_cookie_sock(sk, skb, req, dst);
+ ret = tcp_get_cookie_sock(sk, skb, req, dst, tsoff);
out:
return ret;
out_free:
}
}
-static u32 tcp_v6_init_seq_and_tsoff(const struct sk_buff *skb, u32 *tsoff)
+static u32 tcp_v6_init_seq(const struct sk_buff *skb)
{
- return secure_tcpv6_seq_and_tsoff(ipv6_hdr(skb)->daddr.s6_addr32,
- ipv6_hdr(skb)->saddr.s6_addr32,
- tcp_hdr(skb)->dest,
- tcp_hdr(skb)->source, tsoff);
+ return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32,
+ ipv6_hdr(skb)->saddr.s6_addr32,
+ tcp_hdr(skb)->dest,
+ tcp_hdr(skb)->source);
+}
+
+static u32 tcp_v6_init_ts_off(const struct sk_buff *skb)
+{
+ return secure_tcpv6_ts_off(ipv6_hdr(skb)->daddr.s6_addr32,
+ ipv6_hdr(skb)->saddr.s6_addr32);
}
static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
struct flowi6 fl6;
struct dst_entry *dst;
int addr_type;
- u32 seq;
int err;
struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
sk_set_txhash(sk);
if (likely(!tp->repair)) {
- seq = secure_tcpv6_seq_and_tsoff(np->saddr.s6_addr32,
- sk->sk_v6_daddr.s6_addr32,
- inet->inet_sport,
- inet->inet_dport,
- &tp->tsoffset);
if (!tp->write_seq)
- tp->write_seq = seq;
+ tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32,
+ sk->sk_v6_daddr.s6_addr32,
+ inet->inet_sport,
+ inet->inet_dport);
+ tp->tsoffset = secure_tcpv6_ts_off(np->saddr.s6_addr32,
+ sk->sk_v6_daddr.s6_addr32);
}
if (tcp_fastopen_defer_connect(sk, &err))
.cookie_init_seq = cookie_v6_init_sequence,
#endif
.route_req = tcp_v6_route_req,
- .init_seq_tsoff = tcp_v6_init_seq_and_tsoff,
+ .init_seq = tcp_v6_init_seq,
+ .init_ts_off = tcp_v6_init_ts_off,
.send_synack = tcp_v6_send_synack,
};
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
.obj_size = sizeof(struct tcp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
.twsk_prot = &tcp6_timewait_sock_ops,
.rsk_prot = &tcp6_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
.name = "LLC",
.owner = THIS_MODULE,
.obj_size = sizeof(struct llc_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
};
/**
again:
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_estab_match(sap, daddr, laddr, rc)) {
- /* Extra checks required by SLAB_DESTROY_BY_RCU */
+ /* Extra checks required by SLAB_TYPESAFE_BY_RCU */
if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
again:
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_listener_match(sap, laddr, rc)) {
- /* Extra checks required by SLAB_DESTROY_BY_RCU */
+ /* Extra checks required by SLAB_TYPESAFE_BY_RCU */
if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
again:
sk_nulls_for_each_rcu(rc, node, laddr_hb) {
if (llc_dgram_match(sap, laddr, rc)) {
- /* Extra checks required by SLAB_DESTROY_BY_RCU */
+ /* Extra checks required by SLAB_TYPESAFE_BY_RCU */
if (unlikely(!atomic_inc_not_zero(&rc->sk_refcnt)))
goto again;
if (unlikely(llc_sk(rc)->sap != sap ||
2 + (IEEE80211_MAX_SUPP_RATES - 8) +
2 + sizeof(struct ieee80211_ht_cap) +
2 + sizeof(struct ieee80211_ht_operation) +
+ 2 + sizeof(struct ieee80211_vht_cap) +
+ 2 + sizeof(struct ieee80211_vht_operation) +
ifibss->ie_len;
presp = kzalloc(sizeof(*presp) + frame_len, GFP_KERNEL);
if (!presp)
if (WARN_ON(!ifmgd->auth_data && !ifmgd->assoc_data))
return -EINVAL;
+ /* If a reconfig is happening, bail out */
+ if (local->in_reconfig)
+ return -EBUSY;
+
if (assoc) {
rcu_read_lock();
have_sta = sta_info_get(sdata, cbss->bssid);
continue;
/* kill only if still in same netns -- might have moved due to
- * SLAB_DESTROY_BY_RCU rules.
+ * SLAB_TYPESAFE_BY_RCU rules.
*
* We steal the timer reference. If that fails timer has
* already fired or someone else deleted it. Just drop ref
/*
* Do not use kmem_cache_zalloc(), as this cache uses
- * SLAB_DESTROY_BY_RCU.
+ * SLAB_TYPESAFE_BY_RCU.
*/
ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
if (ct == NULL)
struct net *net = nf_ct_net(ct);
/* A freed object has refcnt == 0, that's
- * the golden rule for SLAB_DESTROY_BY_RCU
+ * the golden rule for SLAB_TYPESAFE_BY_RCU
*/
NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
sizeof(struct nf_conn),
NFCT_INFOMASK + 1,
- SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
+ SLAB_TYPESAFE_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
if (!nf_conntrack_cachep)
goto err_cachep;
.unhash = smc_unhash_sk,
.obj_size = sizeof(struct smc_sock),
.h.smc_hash = &smc_v4_hashinfo,
- .slab_flags = SLAB_DESTROY_BY_RCU,
+ .slab_flags = SLAB_TYPESAFE_BY_RCU,
};
EXPORT_SYMBOL_GPL(smc_proto);
tristate "RPC-over-RDMA transport"
depends on SUNRPC && INFINIBAND && INFINIBAND_ADDR_TRANS
default SUNRPC && INFINIBAND
+ select SG_POOL
help
This option allows the NFS client and server to use RDMA
transports (InfiniBand, iWARP, or RoCE).
struct rpc_task *task;
task = rpc_new_task(task_setup_data);
- if (IS_ERR(task))
- goto out;
rpc_task_set_client(task, task_setup_data->rpc_client);
rpc_task_set_rpc_message(task, task_setup_data->rpc_message);
atomic_inc(&task->tk_count);
rpc_execute(task);
-out:
return task;
}
EXPORT_SYMBOL_GPL(rpc_run_task);
* Create an rpc_task to send the data
*/
task = rpc_new_task(&task_setup_data);
- if (IS_ERR(task)) {
- xprt_free_bc_request(req);
- goto out;
- }
task->tk_rqstp = req;
/*
WARN_ON_ONCE(atomic_read(&task->tk_count) != 2);
rpc_execute(task);
-out:
dprintk("RPC: rpc_run_bc_task: task= %p\n", task);
return task;
}
if (task == NULL) {
task = rpc_alloc_task();
- if (task == NULL) {
- rpc_release_calldata(setup_data->callback_ops,
- setup_data->callback_data);
- return ERR_PTR(-ENOMEM);
- }
flags = RPC_TASK_DYNAMIC;
}
return task;
}
-/*
- * Create or destroy enough new threads to make the number
- * of threads the given number. If `pool' is non-NULL, applies
- * only to threads in that pool, otherwise round-robins between
- * all pools. Caller must ensure that mutual exclusion between this and
- * server startup or shutdown.
- *
- * Destroying threads relies on the service threads filling in
- * rqstp->rq_task, which only the nfs ones do. Assumes the serv
- * has been created using svc_create_pooled().
- *
- * Based on code that used to be in nfsd_svc() but tweaked
- * to be pool-aware.
- */
-int
-svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+/* create new threads */
+static int
+svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
{
struct svc_rqst *rqstp;
struct task_struct *task;
struct svc_pool *chosen_pool;
- int error = 0;
unsigned int state = serv->sv_nrthreads-1;
int node;
- if (pool == NULL) {
- /* The -1 assumes caller has done a svc_get() */
- nrservs -= (serv->sv_nrthreads-1);
- } else {
- spin_lock_bh(&pool->sp_lock);
- nrservs -= pool->sp_nrthreads;
- spin_unlock_bh(&pool->sp_lock);
- }
-
- /* create new threads */
- while (nrservs > 0) {
+ do {
nrservs--;
chosen_pool = choose_pool(serv, pool, &state);
node = svc_pool_map_get_node(chosen_pool->sp_id);
rqstp = svc_prepare_thread(serv, chosen_pool, node);
- if (IS_ERR(rqstp)) {
- error = PTR_ERR(rqstp);
- break;
- }
+ if (IS_ERR(rqstp))
+ return PTR_ERR(rqstp);
__module_get(serv->sv_ops->svo_module);
task = kthread_create_on_node(serv->sv_ops->svo_function, rqstp,
node, "%s", serv->sv_name);
if (IS_ERR(task)) {
- error = PTR_ERR(task);
module_put(serv->sv_ops->svo_module);
svc_exit_thread(rqstp);
- break;
+ return PTR_ERR(task);
}
rqstp->rq_task = task;
svc_sock_update_bufs(serv);
wake_up_process(task);
- }
+ } while (nrservs > 0);
+
+ return 0;
+}
+
+
+/* destroy old threads */
+static int
+svc_signal_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+ struct task_struct *task;
+ unsigned int state = serv->sv_nrthreads-1;
+
/* destroy old threads */
- while (nrservs < 0 &&
- (task = choose_victim(serv, pool, &state)) != NULL) {
+ do {
+ task = choose_victim(serv, pool, &state);
+ if (task == NULL)
+ break;
send_sig(SIGINT, task, 1);
nrservs++;
+ } while (nrservs < 0);
+
+ return 0;
+}
+
+/*
+ * Create or destroy enough new threads to make the number
+ * of threads the given number. If `pool' is non-NULL, applies
+ * only to threads in that pool, otherwise round-robins between
+ * all pools. Caller must ensure that mutual exclusion between this and
+ * server startup or shutdown.
+ *
+ * Destroying threads relies on the service threads filling in
+ * rqstp->rq_task, which only the nfs ones do. Assumes the serv
+ * has been created using svc_create_pooled().
+ *
+ * Based on code that used to be in nfsd_svc() but tweaked
+ * to be pool-aware.
+ */
+int
+svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+ if (pool == NULL) {
+ /* The -1 assumes caller has done a svc_get() */
+ nrservs -= (serv->sv_nrthreads-1);
+ } else {
+ spin_lock_bh(&pool->sp_lock);
+ nrservs -= pool->sp_nrthreads;
+ spin_unlock_bh(&pool->sp_lock);
}
- return error;
+ if (nrservs > 0)
+ return svc_start_kthreads(serv, pool, nrservs);
+ if (nrservs < 0)
+ return svc_signal_kthreads(serv, pool, nrservs);
+ return 0;
}
EXPORT_SYMBOL_GPL(svc_set_num_threads);
+/* destroy old threads */
+static int
+svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+ struct task_struct *task;
+ unsigned int state = serv->sv_nrthreads-1;
+
+ /* destroy old threads */
+ do {
+ task = choose_victim(serv, pool, &state);
+ if (task == NULL)
+ break;
+ kthread_stop(task);
+ nrservs++;
+ } while (nrservs < 0);
+ return 0;
+}
+
+int
+svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
+{
+ if (pool == NULL) {
+ /* The -1 assumes caller has done a svc_get() */
+ nrservs -= (serv->sv_nrthreads-1);
+ } else {
+ spin_lock_bh(&pool->sp_lock);
+ nrservs -= pool->sp_nrthreads;
+ spin_unlock_bh(&pool->sp_lock);
+ }
+
+ if (nrservs > 0)
+ return svc_start_kthreads(serv, pool, nrservs);
+ if (nrservs < 0)
+ return svc_stop_kthreads(serv, pool, nrservs);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(svc_set_num_threads_sync);
+
/*
* Called from a server thread as it's exiting. Caller must hold the "service
* mutex" for the service.
EXPORT_SYMBOL_GPL(xdr_init_decode);
/**
- * xdr_init_decode - Initialize an xdr_stream for decoding data.
+ * xdr_init_decode_pages - Initialize an xdr_stream for decoding into pages
* @xdr: pointer to xdr_stream struct
* @buf: pointer to XDR buffer from which to decode data
* @pages: list of pages to decode into
xprt_wake_pending_tasks(xprt, -EAGAIN);
spin_unlock_bh(&xprt->transport_lock);
}
+EXPORT_SYMBOL_GPL(xprt_force_disconnect);
/**
* xprt_conditional_disconnect - force a transport to disconnect
fmr_ops.o frwr_ops.o \
svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \
- module.o
+ svc_rdma_rw.o module.o
rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o
}
sge->length = len;
- ib_dma_sync_single_for_device(ia->ri_device, sge->addr,
+ ib_dma_sync_single_for_device(rdmab_device(rb), sge->addr,
sge->length, DMA_TO_DEVICE);
req->rl_send_wr.num_sge++;
return true;
sge[sge_no].addr = rdmab_addr(rb);
sge[sge_no].length = xdr->head[0].iov_len;
sge[sge_no].lkey = rdmab_lkey(rb);
- ib_dma_sync_single_for_device(device, sge[sge_no].addr,
+ ib_dma_sync_single_for_device(rdmab_device(rb), sge[sge_no].addr,
sge[sge_no].length, DMA_TO_DEVICE);
/* If there is a Read chunk, the page list is being handled
return 0;
out_err:
- pr_err("rpcrdma: rpcrdma_marshal_req failed, status %ld\n",
- PTR_ERR(iptr));
- r_xprt->rx_stats.failed_marshal_count++;
+ if (PTR_ERR(iptr) != -ENOBUFS) {
+ pr_err("rpcrdma: rpcrdma_marshal_req failed, status %ld\n",
+ PTR_ERR(iptr));
+ r_xprt->rx_stats.failed_marshal_count++;
+ }
return PTR_ERR(iptr);
}
unsigned int svcrdma_max_bc_requests = RPCRDMA_MAX_BC_REQUESTS;
static unsigned int min_max_requests = 4;
static unsigned int max_max_requests = 16384;
-unsigned int svcrdma_max_req_size = RPCRDMA_MAX_REQ_SIZE;
-static unsigned int min_max_inline = 4096;
-static unsigned int max_max_inline = 65536;
+unsigned int svcrdma_max_req_size = RPCRDMA_DEF_INLINE_THRESH;
+static unsigned int min_max_inline = RPCRDMA_DEF_INLINE_THRESH;
+static unsigned int max_max_inline = RPCRDMA_MAX_INLINE_THRESH;
atomic_t rdma_stat_recv;
atomic_t rdma_stat_read;
dprintk("SVCRDMA Module Init, register RPC RDMA transport\n");
dprintk("\tsvcrdma_ord : %d\n", svcrdma_ord);
dprintk("\tmax_requests : %u\n", svcrdma_max_requests);
- dprintk("\tsq_depth : %u\n",
- svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT);
dprintk("\tmax_bc_requests : %u\n", svcrdma_max_bc_requests);
dprintk("\tmax_inline : %d\n", svcrdma_max_req_size);
#undef SVCRDMA_BACKCHANNEL_DEBUG
-int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, struct rpcrdma_msg *rmsgp,
+/**
+ * svc_rdma_handle_bc_reply - Process incoming backchannel reply
+ * @xprt: controlling backchannel transport
+ * @rdma_resp: pointer to incoming transport header
+ * @rcvbuf: XDR buffer into which to decode the reply
+ *
+ * Returns:
+ * %0 if @rcvbuf is filled in, xprt_complete_rqst called,
+ * %-EAGAIN if server should call ->recvfrom again.
+ */
+int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
struct xdr_buf *rcvbuf)
{
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
p = (__be32 *)src->iov_base;
len = src->iov_len;
- xid = rmsgp->rm_xid;
+ xid = *rdma_resp;
#ifdef SVCRDMA_BACKCHANNEL_DEBUG
pr_info("%s: xid=%08x, length=%zu\n",
__func__, be32_to_cpu(xid), len);
pr_info("%s: RPC/RDMA: %*ph\n",
- __func__, (int)RPCRDMA_HDRLEN_MIN, rmsgp);
+ __func__, (int)RPCRDMA_HDRLEN_MIN, rdma_resp);
pr_info("%s: RPC: %*ph\n",
__func__, (int)len, p);
#endif
goto out_unlock;
memcpy(dst->iov_base, p, len);
- credits = be32_to_cpu(rmsgp->rm_credit);
+ credits = be32_to_cpup(rdma_resp + 2);
if (credits == 0)
credits = 1; /* don't deadlock */
else if (credits > r_xprt->rx_buf.rb_bc_max_requests)
* Caller holds the connection's mutex and has already marshaled
* the RPC/RDMA request.
*
- * This is similar to svc_rdma_reply, but takes an rpc_rqst
- * instead, does not support chunks, and avoids blocking memory
- * allocation.
+ * This is similar to svc_rdma_send_reply_msg, but takes a struct
+ * rpc_rqst instead, does not support chunks, and avoids blocking
+ * memory allocation.
*
* XXX: There is still an opportunity to block in svc_rdma_send()
* if there are no SQ entries to post the Send. This may occur if
static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
struct rpc_rqst *rqst)
{
- struct xdr_buf *sndbuf = &rqst->rq_snd_buf;
struct svc_rdma_op_ctxt *ctxt;
- struct svc_rdma_req_map *vec;
- struct ib_send_wr send_wr;
int ret;
- vec = svc_rdma_get_req_map(rdma);
- ret = svc_rdma_map_xdr(rdma, sndbuf, vec, false);
- if (ret)
+ ctxt = svc_rdma_get_context(rdma);
+
+ /* rpcrdma_bc_send_request builds the transport header and
+ * the backchannel RPC message in the same buffer. Thus only
+ * one SGE is needed to send both.
+ */
+ ret = svc_rdma_map_reply_hdr(rdma, ctxt, rqst->rq_buffer,
+ rqst->rq_snd_buf.len);
+ if (ret < 0)
goto out_err;
ret = svc_rdma_repost_recv(rdma, GFP_NOIO);
if (ret)
goto out_err;
- ctxt = svc_rdma_get_context(rdma);
- ctxt->pages[0] = virt_to_page(rqst->rq_buffer);
- ctxt->count = 1;
-
- ctxt->direction = DMA_TO_DEVICE;
- ctxt->sge[0].lkey = rdma->sc_pd->local_dma_lkey;
- ctxt->sge[0].length = sndbuf->len;
- ctxt->sge[0].addr =
- ib_dma_map_page(rdma->sc_cm_id->device, ctxt->pages[0], 0,
- sndbuf->len, DMA_TO_DEVICE);
- if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr)) {
- ret = -EIO;
- goto out_unmap;
- }
- svc_rdma_count_mappings(rdma, ctxt);
-
- memset(&send_wr, 0, sizeof(send_wr));
- ctxt->cqe.done = svc_rdma_wc_send;
- send_wr.wr_cqe = &ctxt->cqe;
- send_wr.sg_list = ctxt->sge;
- send_wr.num_sge = 1;
- send_wr.opcode = IB_WR_SEND;
- send_wr.send_flags = IB_SEND_SIGNALED;
-
- ret = svc_rdma_send(rdma, &send_wr);
- if (ret) {
- ret = -EIO;
+ ret = svc_rdma_post_send_wr(rdma, ctxt, 1, 0);
+ if (ret)
goto out_unmap;
- }
out_err:
- svc_rdma_put_req_map(rdma, vec);
dprintk("svcrdma: %s returns %d\n", __func__, ret);
return ret;
out_unmap:
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 1);
+ ret = -EIO;
goto out_err;
}
dprintk("svcrdma: failed to parse transport header\n");
return -EINVAL;
}
-
-int svc_rdma_xdr_encode_error(struct svcxprt_rdma *xprt,
- struct rpcrdma_msg *rmsgp,
- enum rpcrdma_errcode err, __be32 *va)
-{
- __be32 *startp = va;
-
- *va++ = rmsgp->rm_xid;
- *va++ = rmsgp->rm_vers;
- *va++ = xprt->sc_fc_credits;
- *va++ = rdma_error;
- *va++ = cpu_to_be32(err);
- if (err == ERR_VERS) {
- *va++ = rpcrdma_version;
- *va++ = rpcrdma_version;
- }
-
- return (int)((unsigned long)va - (unsigned long)startp);
-}
-
-/**
- * svc_rdma_xdr_get_reply_hdr_length - Get length of Reply transport header
- * @rdma_resp: buffer containing Reply transport header
- *
- * Returns length of transport header, in bytes.
- */
-unsigned int svc_rdma_xdr_get_reply_hdr_len(__be32 *rdma_resp)
-{
- unsigned int nsegs;
- __be32 *p;
-
- p = rdma_resp;
-
- /* RPC-over-RDMA V1 replies never have a Read list. */
- p += rpcrdma_fixed_maxsz + 1;
-
- /* Skip Write list. */
- while (*p++ != xdr_zero) {
- nsegs = be32_to_cpup(p++);
- p += nsegs * rpcrdma_segment_maxsz;
- }
-
- /* Skip Reply chunk. */
- if (*p++ != xdr_zero) {
- nsegs = be32_to_cpup(p++);
- p += nsegs * rpcrdma_segment_maxsz;
- }
-
- return (unsigned long)p - (unsigned long)rdma_resp;
-}
-
-void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *rmsgp, int chunks)
-{
- struct rpcrdma_write_array *ary;
-
- /* no read-list */
- rmsgp->rm_body.rm_chunks[0] = xdr_zero;
-
- /* write-array discrim */
- ary = (struct rpcrdma_write_array *)
- &rmsgp->rm_body.rm_chunks[1];
- ary->wc_discrim = xdr_one;
- ary->wc_nchunks = cpu_to_be32(chunks);
-
- /* write-list terminator */
- ary->wc_array[chunks].wc_target.rs_handle = xdr_zero;
-
- /* reply-array discriminator */
- ary->wc_array[chunks].wc_target.rs_length = xdr_zero;
-}
-
-void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *ary,
- int chunks)
-{
- ary->wc_discrim = xdr_one;
- ary->wc_nchunks = cpu_to_be32(chunks);
-}
-
-void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary,
- int chunk_no,
- __be32 rs_handle,
- __be64 rs_offset,
- u32 write_len)
-{
- struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target;
- seg->rs_handle = rs_handle;
- seg->rs_offset = rs_offset;
- seg->rs_length = cpu_to_be32(write_len);
-}
rqstp->rq_arg.buflen = head->arg.buflen;
}
+static void svc_rdma_send_error(struct svcxprt_rdma *xprt,
+ __be32 *rdma_argp, int status)
+{
+ struct svc_rdma_op_ctxt *ctxt;
+ __be32 *p, *err_msgp;
+ unsigned int length;
+ struct page *page;
+ int ret;
+
+ ret = svc_rdma_repost_recv(xprt, GFP_KERNEL);
+ if (ret)
+ return;
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return;
+ err_msgp = page_address(page);
+
+ p = err_msgp;
+ *p++ = *rdma_argp;
+ *p++ = *(rdma_argp + 1);
+ *p++ = xprt->sc_fc_credits;
+ *p++ = rdma_error;
+ if (status == -EPROTONOSUPPORT) {
+ *p++ = err_vers;
+ *p++ = rpcrdma_version;
+ *p++ = rpcrdma_version;
+ } else {
+ *p++ = err_chunk;
+ }
+ length = (unsigned long)p - (unsigned long)err_msgp;
+
+ /* Map transport header; no RPC message payload */
+ ctxt = svc_rdma_get_context(xprt);
+ ret = svc_rdma_map_reply_hdr(xprt, ctxt, err_msgp, length);
+ if (ret) {
+ dprintk("svcrdma: Error %d mapping send for protocol error\n",
+ ret);
+ return;
+ }
+
+ ret = svc_rdma_post_send_wr(xprt, ctxt, 1, 0);
+ if (ret) {
+ dprintk("svcrdma: Error %d posting send for protocol error\n",
+ ret);
+ svc_rdma_unmap_dma(ctxt);
+ svc_rdma_put_context(ctxt, 1);
+ }
+}
+
/* By convention, backchannel calls arrive via rdma_msg type
* messages, and never populate the chunk lists. This makes
* the RPC/RDMA header small and fixed in size, so it is
* straightforward to check the RPC header's direction field.
*/
-static bool
-svc_rdma_is_backchannel_reply(struct svc_xprt *xprt, struct rpcrdma_msg *rmsgp)
+static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt,
+ __be32 *rdma_resp)
{
- __be32 *p = (__be32 *)rmsgp;
+ __be32 *p;
if (!xprt->xpt_bc_xprt)
return false;
- if (rmsgp->rm_type != rdma_msg)
+ p = rdma_resp + 3;
+ if (*p++ != rdma_msg)
return false;
- if (rmsgp->rm_body.rm_chunks[0] != xdr_zero)
+
+ if (*p++ != xdr_zero)
return false;
- if (rmsgp->rm_body.rm_chunks[1] != xdr_zero)
+ if (*p++ != xdr_zero)
return false;
- if (rmsgp->rm_body.rm_chunks[2] != xdr_zero)
+ if (*p++ != xdr_zero)
return false;
- /* sanity */
- if (p[7] != rmsgp->rm_xid)
+ /* XID sanity */
+ if (*p++ != *rdma_resp)
return false;
/* call direction */
- if (p[8] == cpu_to_be32(RPC_CALL))
+ if (*p == cpu_to_be32(RPC_CALL))
return false;
return true;
goto out_drop;
rqstp->rq_xprt_hlen = ret;
- if (svc_rdma_is_backchannel_reply(xprt, rmsgp)) {
- ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, rmsgp,
+ if (svc_rdma_is_backchannel_reply(xprt, &rmsgp->rm_xid)) {
+ ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt,
+ &rmsgp->rm_xid,
&rqstp->rq_arg);
svc_rdma_put_context(ctxt, 0);
if (ret)
return ret;
out_err:
- svc_rdma_send_error(rdma_xprt, rmsgp, ret);
+ svc_rdma_send_error(rdma_xprt, &rmsgp->rm_xid, ret);
svc_rdma_put_context(ctxt, 0);
return 0;
--- /dev/null
+/*
+ * Copyright (c) 2016 Oracle. All rights reserved.
+ *
+ * Use the core R/W API to move RPC-over-RDMA Read and Write chunks.
+ */
+
+#include <linux/sunrpc/rpc_rdma.h>
+#include <linux/sunrpc/svc_rdma.h>
+#include <linux/sunrpc/debug.h>
+
+#include <rdma/rw.h>
+
+#define RPCDBG_FACILITY RPCDBG_SVCXPRT
+
+/* Each R/W context contains state for one chain of RDMA Read or
+ * Write Work Requests.
+ *
+ * Each WR chain handles a single contiguous server-side buffer,
+ * because scatterlist entries after the first have to start on
+ * page alignment. xdr_buf iovecs cannot guarantee alignment.
+ *
+ * Each WR chain handles only one R_key. Each RPC-over-RDMA segment
+ * from a client may contain a unique R_key, so each WR chain moves
+ * up to one segment at a time.
+ *
+ * The scatterlist makes this data structure over 4KB in size. To
+ * make it less likely to fail, and to handle the allocation for
+ * smaller I/O requests without disabling bottom-halves, these
+ * contexts are created on demand, but cached and reused until the
+ * controlling svcxprt_rdma is destroyed.
+ */
+struct svc_rdma_rw_ctxt {
+ struct list_head rw_list;
+ struct rdma_rw_ctx rw_ctx;
+ int rw_nents;
+ struct sg_table rw_sg_table;
+ struct scatterlist rw_first_sgl[0];
+};
+
+static inline struct svc_rdma_rw_ctxt *
+svc_rdma_next_ctxt(struct list_head *list)
+{
+ return list_first_entry_or_null(list, struct svc_rdma_rw_ctxt,
+ rw_list);
+}
+
+static struct svc_rdma_rw_ctxt *
+svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges)
+{
+ struct svc_rdma_rw_ctxt *ctxt;
+
+ spin_lock(&rdma->sc_rw_ctxt_lock);
+
+ ctxt = svc_rdma_next_ctxt(&rdma->sc_rw_ctxts);
+ if (ctxt) {
+ list_del(&ctxt->rw_list);
+ spin_unlock(&rdma->sc_rw_ctxt_lock);
+ } else {
+ spin_unlock(&rdma->sc_rw_ctxt_lock);
+ ctxt = kmalloc(sizeof(*ctxt) +
+ SG_CHUNK_SIZE * sizeof(struct scatterlist),
+ GFP_KERNEL);
+ if (!ctxt)
+ goto out;
+ INIT_LIST_HEAD(&ctxt->rw_list);
+ }
+
+ ctxt->rw_sg_table.sgl = ctxt->rw_first_sgl;
+ if (sg_alloc_table_chained(&ctxt->rw_sg_table, sges,
+ ctxt->rw_sg_table.sgl)) {
+ kfree(ctxt);
+ ctxt = NULL;
+ }
+out:
+ return ctxt;
+}
+
+static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma,
+ struct svc_rdma_rw_ctxt *ctxt)
+{
+ sg_free_table_chained(&ctxt->rw_sg_table, true);
+
+ spin_lock(&rdma->sc_rw_ctxt_lock);
+ list_add(&ctxt->rw_list, &rdma->sc_rw_ctxts);
+ spin_unlock(&rdma->sc_rw_ctxt_lock);
+}
+
+/**
+ * svc_rdma_destroy_rw_ctxts - Free accumulated R/W contexts
+ * @rdma: transport about to be destroyed
+ *
+ */
+void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma)
+{
+ struct svc_rdma_rw_ctxt *ctxt;
+
+ while ((ctxt = svc_rdma_next_ctxt(&rdma->sc_rw_ctxts)) != NULL) {
+ list_del(&ctxt->rw_list);
+ kfree(ctxt);
+ }
+}
+
+/* A chunk context tracks all I/O for moving one Read or Write
+ * chunk. This is a a set of rdma_rw's that handle data movement
+ * for all segments of one chunk.
+ *
+ * These are small, acquired with a single allocator call, and
+ * no more than one is needed per chunk. They are allocated on
+ * demand, and not cached.
+ */
+struct svc_rdma_chunk_ctxt {
+ struct ib_cqe cc_cqe;
+ struct svcxprt_rdma *cc_rdma;
+ struct list_head cc_rwctxts;
+ int cc_sqecount;
+ enum dma_data_direction cc_dir;
+};
+
+static void svc_rdma_cc_init(struct svcxprt_rdma *rdma,
+ struct svc_rdma_chunk_ctxt *cc,
+ enum dma_data_direction dir)
+{
+ cc->cc_rdma = rdma;
+ svc_xprt_get(&rdma->sc_xprt);
+
+ INIT_LIST_HEAD(&cc->cc_rwctxts);
+ cc->cc_sqecount = 0;
+ cc->cc_dir = dir;
+}
+
+static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc)
+{
+ struct svcxprt_rdma *rdma = cc->cc_rdma;
+ struct svc_rdma_rw_ctxt *ctxt;
+
+ while ((ctxt = svc_rdma_next_ctxt(&cc->cc_rwctxts)) != NULL) {
+ list_del(&ctxt->rw_list);
+
+ rdma_rw_ctx_destroy(&ctxt->rw_ctx, rdma->sc_qp,
+ rdma->sc_port_num, ctxt->rw_sg_table.sgl,
+ ctxt->rw_nents, cc->cc_dir);
+ svc_rdma_put_rw_ctxt(rdma, ctxt);
+ }
+ svc_xprt_put(&rdma->sc_xprt);
+}
+
+/* State for sending a Write or Reply chunk.
+ * - Tracks progress of writing one chunk over all its segments
+ * - Stores arguments for the SGL constructor functions
+ */
+struct svc_rdma_write_info {
+ /* write state of this chunk */
+ unsigned int wi_seg_off;
+ unsigned int wi_seg_no;
+ unsigned int wi_nsegs;
+ __be32 *wi_segs;
+
+ /* SGL constructor arguments */
+ struct xdr_buf *wi_xdr;
+ unsigned char *wi_base;
+ unsigned int wi_next_off;
+
+ struct svc_rdma_chunk_ctxt wi_cc;
+};
+
+static struct svc_rdma_write_info *
+svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
+{
+ struct svc_rdma_write_info *info;
+
+ info = kmalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return info;
+
+ info->wi_seg_off = 0;
+ info->wi_seg_no = 0;
+ info->wi_nsegs = be32_to_cpup(++chunk);
+ info->wi_segs = ++chunk;
+ svc_rdma_cc_init(rdma, &info->wi_cc, DMA_TO_DEVICE);
+ return info;
+}
+
+static void svc_rdma_write_info_free(struct svc_rdma_write_info *info)
+{
+ svc_rdma_cc_release(&info->wi_cc);
+ kfree(info);
+}
+
+/**
+ * svc_rdma_write_done - Write chunk completion
+ * @cq: controlling Completion Queue
+ * @wc: Work Completion
+ *
+ * Pages under I/O are freed by a subsequent Send completion.
+ */
+static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
+{
+ struct ib_cqe *cqe = wc->wr_cqe;
+ struct svc_rdma_chunk_ctxt *cc =
+ container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe);
+ struct svcxprt_rdma *rdma = cc->cc_rdma;
+ struct svc_rdma_write_info *info =
+ container_of(cc, struct svc_rdma_write_info, wi_cc);
+
+ atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
+ wake_up(&rdma->sc_send_wait);
+
+ if (unlikely(wc->status != IB_WC_SUCCESS)) {
+ set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+ if (wc->status != IB_WC_WR_FLUSH_ERR)
+ pr_err("svcrdma: write ctx: %s (%u/0x%x)\n",
+ ib_wc_status_msg(wc->status),
+ wc->status, wc->vendor_err);
+ }
+
+ svc_rdma_write_info_free(info);
+}
+
+/* This function sleeps when the transport's Send Queue is congested.
+ *
+ * Assumptions:
+ * - If ib_post_send() succeeds, only one completion is expected,
+ * even if one or more WRs are flushed. This is true when posting
+ * an rdma_rw_ctx or when posting a single signaled WR.
+ */
+static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
+{
+ struct svcxprt_rdma *rdma = cc->cc_rdma;
+ struct svc_xprt *xprt = &rdma->sc_xprt;
+ struct ib_send_wr *first_wr, *bad_wr;
+ struct list_head *tmp;
+ struct ib_cqe *cqe;
+ int ret;
+
+ first_wr = NULL;
+ cqe = &cc->cc_cqe;
+ list_for_each(tmp, &cc->cc_rwctxts) {
+ struct svc_rdma_rw_ctxt *ctxt;
+
+ ctxt = list_entry(tmp, struct svc_rdma_rw_ctxt, rw_list);
+ first_wr = rdma_rw_ctx_wrs(&ctxt->rw_ctx, rdma->sc_qp,
+ rdma->sc_port_num, cqe, first_wr);
+ cqe = NULL;
+ }
+
+ do {
+ if (atomic_sub_return(cc->cc_sqecount,
+ &rdma->sc_sq_avail) > 0) {
+ ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr);
+ if (ret)
+ break;
+ return 0;
+ }
+
+ atomic_inc(&rdma_stat_sq_starve);
+ atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
+ wait_event(rdma->sc_send_wait,
+ atomic_read(&rdma->sc_sq_avail) > cc->cc_sqecount);
+ } while (1);
+
+ pr_err("svcrdma: ib_post_send failed (%d)\n", ret);
+ set_bit(XPT_CLOSE, &xprt->xpt_flags);
+
+ /* If even one was posted, there will be a completion. */
+ if (bad_wr != first_wr)
+ return 0;
+
+ atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail);
+ wake_up(&rdma->sc_send_wait);
+ return -ENOTCONN;
+}
+
+/* Build and DMA-map an SGL that covers one kvec in an xdr_buf
+ */
+static void svc_rdma_vec_to_sg(struct svc_rdma_write_info *info,
+ unsigned int len,
+ struct svc_rdma_rw_ctxt *ctxt)
+{
+ struct scatterlist *sg = ctxt->rw_sg_table.sgl;
+
+ sg_set_buf(&sg[0], info->wi_base, len);
+ info->wi_base += len;
+
+ ctxt->rw_nents = 1;
+}
+
+/* Build and DMA-map an SGL that covers part of an xdr_buf's pagelist.
+ */
+static void svc_rdma_pagelist_to_sg(struct svc_rdma_write_info *info,
+ unsigned int remaining,
+ struct svc_rdma_rw_ctxt *ctxt)
+{
+ unsigned int sge_no, sge_bytes, page_off, page_no;
+ struct xdr_buf *xdr = info->wi_xdr;
+ struct scatterlist *sg;
+ struct page **page;
+
+ page_off = (info->wi_next_off + xdr->page_base) & ~PAGE_MASK;
+ page_no = (info->wi_next_off + xdr->page_base) >> PAGE_SHIFT;
+ page = xdr->pages + page_no;
+ info->wi_next_off += remaining;
+ sg = ctxt->rw_sg_table.sgl;
+ sge_no = 0;
+ do {
+ sge_bytes = min_t(unsigned int, remaining,
+ PAGE_SIZE - page_off);
+ sg_set_page(sg, *page, sge_bytes, page_off);
+
+ remaining -= sge_bytes;
+ sg = sg_next(sg);
+ page_off = 0;
+ sge_no++;
+ page++;
+ } while (remaining);
+
+ ctxt->rw_nents = sge_no;
+}
+
+/* Construct RDMA Write WRs to send a portion of an xdr_buf containing
+ * an RPC Reply.
+ */
+static int
+svc_rdma_build_writes(struct svc_rdma_write_info *info,
+ void (*constructor)(struct svc_rdma_write_info *info,
+ unsigned int len,
+ struct svc_rdma_rw_ctxt *ctxt),
+ unsigned int remaining)
+{
+ struct svc_rdma_chunk_ctxt *cc = &info->wi_cc;
+ struct svcxprt_rdma *rdma = cc->cc_rdma;
+ struct svc_rdma_rw_ctxt *ctxt;
+ __be32 *seg;
+ int ret;
+
+ cc->cc_cqe.done = svc_rdma_write_done;
+ seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz;
+ do {
+ unsigned int write_len;
+ u32 seg_length, seg_handle;
+ u64 seg_offset;
+
+ if (info->wi_seg_no >= info->wi_nsegs)
+ goto out_overflow;
+
+ seg_handle = be32_to_cpup(seg);
+ seg_length = be32_to_cpup(seg + 1);
+ xdr_decode_hyper(seg + 2, &seg_offset);
+ seg_offset += info->wi_seg_off;
+
+ write_len = min(remaining, seg_length - info->wi_seg_off);
+ ctxt = svc_rdma_get_rw_ctxt(rdma,
+ (write_len >> PAGE_SHIFT) + 2);
+ if (!ctxt)
+ goto out_noctx;
+
+ constructor(info, write_len, ctxt);
+ ret = rdma_rw_ctx_init(&ctxt->rw_ctx, rdma->sc_qp,
+ rdma->sc_port_num, ctxt->rw_sg_table.sgl,
+ ctxt->rw_nents, 0, seg_offset,
+ seg_handle, DMA_TO_DEVICE);
+ if (ret < 0)
+ goto out_initerr;
+
+ list_add(&ctxt->rw_list, &cc->cc_rwctxts);
+ cc->cc_sqecount += ret;
+ if (write_len == seg_length - info->wi_seg_off) {
+ seg += 4;
+ info->wi_seg_no++;
+ info->wi_seg_off = 0;
+ } else {
+ info->wi_seg_off += write_len;
+ }
+ remaining -= write_len;
+ } while (remaining);
+
+ return 0;
+
+out_overflow:
+ dprintk("svcrdma: inadequate space in Write chunk (%u)\n",
+ info->wi_nsegs);
+ return -E2BIG;
+
+out_noctx:
+ dprintk("svcrdma: no R/W ctxs available\n");
+ return -ENOMEM;
+
+out_initerr:
+ svc_rdma_put_rw_ctxt(rdma, ctxt);
+ pr_err("svcrdma: failed to map pagelist (%d)\n", ret);
+ return -EIO;
+}
+
+/* Send one of an xdr_buf's kvecs by itself. To send a Reply
+ * chunk, the whole RPC Reply is written back to the client.
+ * This function writes either the head or tail of the xdr_buf
+ * containing the Reply.
+ */
+static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info,
+ struct kvec *vec)
+{
+ info->wi_base = vec->iov_base;
+ return svc_rdma_build_writes(info, svc_rdma_vec_to_sg,
+ vec->iov_len);
+}
+
+/* Send an xdr_buf's page list by itself. A Write chunk is
+ * just the page list. a Reply chunk is the head, page list,
+ * and tail. This function is shared between the two types
+ * of chunk.
+ */
+static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
+ struct xdr_buf *xdr)
+{
+ info->wi_xdr = xdr;
+ info->wi_next_off = 0;
+ return svc_rdma_build_writes(info, svc_rdma_pagelist_to_sg,
+ xdr->page_len);
+}
+
+/**
+ * svc_rdma_send_write_chunk - Write all segments in a Write chunk
+ * @rdma: controlling RDMA transport
+ * @wr_ch: Write chunk provided by client
+ * @xdr: xdr_buf containing the data payload
+ *
+ * Returns a non-negative number of bytes the chunk consumed, or
+ * %-E2BIG if the payload was larger than the Write chunk,
+ * %-ENOMEM if rdma_rw context pool was exhausted,
+ * %-ENOTCONN if posting failed (connection is lost),
+ * %-EIO if rdma_rw initialization failed (DMA mapping, etc).
+ */
+int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
+ struct xdr_buf *xdr)
+{
+ struct svc_rdma_write_info *info;
+ int ret;
+
+ if (!xdr->page_len)
+ return 0;
+
+ info = svc_rdma_write_info_alloc(rdma, wr_ch);
+ if (!info)
+ return -ENOMEM;
+
+ ret = svc_rdma_send_xdr_pagelist(info, xdr);
+ if (ret < 0)
+ goto out_err;
+
+ ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
+ if (ret < 0)
+ goto out_err;
+ return xdr->page_len;
+
+out_err:
+ svc_rdma_write_info_free(info);
+ return ret;
+}
+
+/**
+ * svc_rdma_send_reply_chunk - Write all segments in the Reply chunk
+ * @rdma: controlling RDMA transport
+ * @rp_ch: Reply chunk provided by client
+ * @writelist: true if client provided a Write list
+ * @xdr: xdr_buf containing an RPC Reply
+ *
+ * Returns a non-negative number of bytes the chunk consumed, or
+ * %-E2BIG if the payload was larger than the Reply chunk,
+ * %-ENOMEM if rdma_rw context pool was exhausted,
+ * %-ENOTCONN if posting failed (connection is lost),
+ * %-EIO if rdma_rw initialization failed (DMA mapping, etc).
+ */
+int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch,
+ bool writelist, struct xdr_buf *xdr)
+{
+ struct svc_rdma_write_info *info;
+ int consumed, ret;
+
+ info = svc_rdma_write_info_alloc(rdma, rp_ch);
+ if (!info)
+ return -ENOMEM;
+
+ ret = svc_rdma_send_xdr_kvec(info, &xdr->head[0]);
+ if (ret < 0)
+ goto out_err;
+ consumed = xdr->head[0].iov_len;
+
+ /* Send the page list in the Reply chunk only if the
+ * client did not provide Write chunks.
+ */
+ if (!writelist && xdr->page_len) {
+ ret = svc_rdma_send_xdr_pagelist(info, xdr);
+ if (ret < 0)
+ goto out_err;
+ consumed += xdr->page_len;
+ }
+
+ if (xdr->tail[0].iov_len) {
+ ret = svc_rdma_send_xdr_kvec(info, &xdr->tail[0]);
+ if (ret < 0)
+ goto out_err;
+ consumed += xdr->tail[0].iov_len;
+ }
+
+ ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
+ if (ret < 0)
+ goto out_err;
+ return consumed;
+
+out_err:
+ svc_rdma_write_info_free(info);
+ return ret;
+}
/*
+ * Copyright (c) 2016 Oracle. All rights reserved.
* Copyright (c) 2014 Open Grid Computing, Inc. All rights reserved.
* Copyright (c) 2005-2006 Network Appliance, Inc. All rights reserved.
*
* Author: Tom Tucker <tom@opengridcomputing.com>
*/
+/* Operation
+ *
+ * The main entry point is svc_rdma_sendto. This is called by the
+ * RPC server when an RPC Reply is ready to be transmitted to a client.
+ *
+ * The passed-in svc_rqst contains a struct xdr_buf which holds an
+ * XDR-encoded RPC Reply message. sendto must construct the RPC-over-RDMA
+ * transport header, post all Write WRs needed for this Reply, then post
+ * a Send WR conveying the transport header and the RPC message itself to
+ * the client.
+ *
+ * svc_rdma_sendto must fully transmit the Reply before returning, as
+ * the svc_rqst will be recycled as soon as sendto returns. Remaining
+ * resources referred to by the svc_rqst are also recycled at that time.
+ * Therefore any resources that must remain longer must be detached
+ * from the svc_rqst and released later.
+ *
+ * Page Management
+ *
+ * The I/O that performs Reply transmission is asynchronous, and may
+ * complete well after sendto returns. Thus pages under I/O must be
+ * removed from the svc_rqst before sendto returns.
+ *
+ * The logic here depends on Send Queue and completion ordering. Since
+ * the Send WR is always posted last, it will always complete last. Thus
+ * when it completes, it is guaranteed that all previous Write WRs have
+ * also completed.
+ *
+ * Write WRs are constructed and posted. Each Write segment gets its own
+ * svc_rdma_rw_ctxt, allowing the Write completion handler to find and
+ * DMA-unmap the pages under I/O for that Write segment. The Write
+ * completion handler does not release any pages.
+ *
+ * When the Send WR is constructed, it also gets its own svc_rdma_op_ctxt.
+ * The ownership of all of the Reply's pages are transferred into that
+ * ctxt, the Send WR is posted, and sendto returns.
+ *
+ * The svc_rdma_op_ctxt is presented when the Send WR completes. The
+ * Send completion handler finally releases the Reply's pages.
+ *
+ * This mechanism also assumes that completions on the transport's Send
+ * Completion Queue do not run in parallel. Otherwise a Write completion
+ * and Send completion running at the same time could release pages that
+ * are still DMA-mapped.
+ *
+ * Error Handling
+ *
+ * - If the Send WR is posted successfully, it will either complete
+ * successfully, or get flushed. Either way, the Send completion
+ * handler releases the Reply's pages.
+ * - If the Send WR cannot be not posted, the forward path releases
+ * the Reply's pages.
+ *
+ * This handles the case, without the use of page reference counting,
+ * where two different Write segments send portions of the same page.
+ */
+
#include <linux/sunrpc/debug.h>
#include <linux/sunrpc/rpc_rdma.h>
#include <linux/spinlock.h>
return (len & 3) ? (4 - (len & 3)) : 0;
}
-int svc_rdma_map_xdr(struct svcxprt_rdma *xprt,
- struct xdr_buf *xdr,
- struct svc_rdma_req_map *vec,
- bool write_chunk_present)
+/* Returns length of transport header, in bytes.
+ */
+static unsigned int svc_rdma_reply_hdr_len(__be32 *rdma_resp)
{
- int sge_no;
- u32 sge_bytes;
- u32 page_bytes;
- u32 page_off;
- int page_no;
-
- if (xdr->len !=
- (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)) {
- pr_err("svcrdma: %s: XDR buffer length error\n", __func__);
- return -EIO;
- }
+ unsigned int nsegs;
+ __be32 *p;
- /* Skip the first sge, this is for the RPCRDMA header */
- sge_no = 1;
+ p = rdma_resp;
+
+ /* RPC-over-RDMA V1 replies never have a Read list. */
+ p += rpcrdma_fixed_maxsz + 1;
- /* Head SGE */
- vec->sge[sge_no].iov_base = xdr->head[0].iov_base;
- vec->sge[sge_no].iov_len = xdr->head[0].iov_len;
- sge_no++;
-
- /* pages SGE */
- page_no = 0;
- page_bytes = xdr->page_len;
- page_off = xdr->page_base;
- while (page_bytes) {
- vec->sge[sge_no].iov_base =
- page_address(xdr->pages[page_no]) + page_off;
- sge_bytes = min_t(u32, page_bytes, (PAGE_SIZE - page_off));
- page_bytes -= sge_bytes;
- vec->sge[sge_no].iov_len = sge_bytes;
-
- sge_no++;
- page_no++;
- page_off = 0; /* reset for next time through loop */
+ /* Skip Write list. */
+ while (*p++ != xdr_zero) {
+ nsegs = be32_to_cpup(p++);
+ p += nsegs * rpcrdma_segment_maxsz;
}
- /* Tail SGE */
- if (xdr->tail[0].iov_len) {
- unsigned char *base = xdr->tail[0].iov_base;
- size_t len = xdr->tail[0].iov_len;
- u32 xdr_pad = xdr_padsize(xdr->page_len);
+ /* Skip Reply chunk. */
+ if (*p++ != xdr_zero) {
+ nsegs = be32_to_cpup(p++);
+ p += nsegs * rpcrdma_segment_maxsz;
+ }
- if (write_chunk_present && xdr_pad) {
- base += xdr_pad;
- len -= xdr_pad;
- }
+ return (unsigned long)p - (unsigned long)rdma_resp;
+}
- if (len) {
- vec->sge[sge_no].iov_base = base;
- vec->sge[sge_no].iov_len = len;
- sge_no++;
+/* One Write chunk is copied from Call transport header to Reply
+ * transport header. Each segment's length field is updated to
+ * reflect number of bytes consumed in the segment.
+ *
+ * Returns number of segments in this chunk.
+ */
+static unsigned int xdr_encode_write_chunk(__be32 *dst, __be32 *src,
+ unsigned int remaining)
+{
+ unsigned int i, nsegs;
+ u32 seg_len;
+
+ /* Write list discriminator */
+ *dst++ = *src++;
+
+ /* number of segments in this chunk */
+ nsegs = be32_to_cpup(src);
+ *dst++ = *src++;
+
+ for (i = nsegs; i; i--) {
+ /* segment's RDMA handle */
+ *dst++ = *src++;
+
+ /* bytes returned in this segment */
+ seg_len = be32_to_cpu(*src);
+ if (remaining >= seg_len) {
+ /* entire segment was consumed */
+ *dst = *src;
+ remaining -= seg_len;
+ } else {
+ /* segment only partly filled */
+ *dst = cpu_to_be32(remaining);
+ remaining = 0;
}
- }
+ dst++; src++;
- dprintk("svcrdma: %s: sge_no %d page_no %d "
- "page_base %u page_len %u head_len %zu tail_len %zu\n",
- __func__, sge_no, page_no, xdr->page_base, xdr->page_len,
- xdr->head[0].iov_len, xdr->tail[0].iov_len);
+ /* segment's RDMA offset */
+ *dst++ = *src++;
+ *dst++ = *src++;
+ }
- vec->count = sge_no;
- return 0;
+ return nsegs;
}
-static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
- struct xdr_buf *xdr,
- u32 xdr_off, size_t len, int dir)
+/* The client provided a Write list in the Call message. Fill in
+ * the segments in the first Write chunk in the Reply's transport
+ * header with the number of bytes consumed in each segment.
+ * Remaining chunks are returned unused.
+ *
+ * Assumptions:
+ * - Client has provided only one Write chunk
+ */
+static void svc_rdma_xdr_encode_write_list(__be32 *rdma_resp, __be32 *wr_ch,
+ unsigned int consumed)
{
- struct page *page;
- dma_addr_t dma_addr;
- if (xdr_off < xdr->head[0].iov_len) {
- /* This offset is in the head */
- xdr_off += (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
- page = virt_to_page(xdr->head[0].iov_base);
- } else {
- xdr_off -= xdr->head[0].iov_len;
- if (xdr_off < xdr->page_len) {
- /* This offset is in the page list */
- xdr_off += xdr->page_base;
- page = xdr->pages[xdr_off >> PAGE_SHIFT];
- xdr_off &= ~PAGE_MASK;
- } else {
- /* This offset is in the tail */
- xdr_off -= xdr->page_len;
- xdr_off += (unsigned long)
- xdr->tail[0].iov_base & ~PAGE_MASK;
- page = virt_to_page(xdr->tail[0].iov_base);
- }
+ unsigned int nsegs;
+ __be32 *p, *q;
+
+ /* RPC-over-RDMA V1 replies never have a Read list. */
+ p = rdma_resp + rpcrdma_fixed_maxsz + 1;
+
+ q = wr_ch;
+ while (*q != xdr_zero) {
+ nsegs = xdr_encode_write_chunk(p, q, consumed);
+ q += 2 + nsegs * rpcrdma_segment_maxsz;
+ p += 2 + nsegs * rpcrdma_segment_maxsz;
+ consumed = 0;
}
- dma_addr = ib_dma_map_page(xprt->sc_cm_id->device, page, xdr_off,
- min_t(size_t, PAGE_SIZE, len), dir);
- return dma_addr;
+
+ /* Terminate Write list */
+ *p++ = xdr_zero;
+
+ /* Reply chunk discriminator; may be replaced later */
+ *p = xdr_zero;
+}
+
+/* The client provided a Reply chunk in the Call message. Fill in
+ * the segments in the Reply chunk in the Reply message with the
+ * number of bytes consumed in each segment.
+ *
+ * Assumptions:
+ * - Reply can always fit in the provided Reply chunk
+ */
+static void svc_rdma_xdr_encode_reply_chunk(__be32 *rdma_resp, __be32 *rp_ch,
+ unsigned int consumed)
+{
+ __be32 *p;
+
+ /* Find the Reply chunk in the Reply's xprt header.
+ * RPC-over-RDMA V1 replies never have a Read list.
+ */
+ p = rdma_resp + rpcrdma_fixed_maxsz + 1;
+
+ /* Skip past Write list */
+ while (*p++ != xdr_zero)
+ p += 1 + be32_to_cpup(p) * rpcrdma_segment_maxsz;
+
+ xdr_encode_write_chunk(p, rp_ch, consumed);
}
/* Parse the RPC Call's transport header.
*/
-static void svc_rdma_get_write_arrays(struct rpcrdma_msg *rmsgp,
- struct rpcrdma_write_array **write,
- struct rpcrdma_write_array **reply)
+static void svc_rdma_get_write_arrays(__be32 *rdma_argp,
+ __be32 **write, __be32 **reply)
{
__be32 *p;
- p = (__be32 *)&rmsgp->rm_body.rm_chunks[0];
+ p = rdma_argp + rpcrdma_fixed_maxsz;
/* Read list */
while (*p++ != xdr_zero)
/* Write list */
if (*p != xdr_zero) {
- *write = (struct rpcrdma_write_array *)p;
+ *write = p;
while (*p++ != xdr_zero)
p += 1 + be32_to_cpu(*p) * 4;
} else {
/* Reply chunk */
if (*p != xdr_zero)
- *reply = (struct rpcrdma_write_array *)p;
+ *reply = p;
else
*reply = NULL;
}
* Invalidate, and responder chooses one rkey to invalidate.
*
* Find a candidate rkey to invalidate when sending a reply. Picks the
- * first rkey it finds in the chunks lists.
+ * first R_key it finds in the chunk lists.
*
* Returns zero if RPC's chunk lists are empty.
*/
-static u32 svc_rdma_get_inv_rkey(struct rpcrdma_msg *rdma_argp,
- struct rpcrdma_write_array *wr_ary,
- struct rpcrdma_write_array *rp_ary)
+static u32 svc_rdma_get_inv_rkey(__be32 *rdma_argp,
+ __be32 *wr_lst, __be32 *rp_ch)
{
- struct rpcrdma_read_chunk *rd_ary;
- struct rpcrdma_segment *arg_ch;
+ __be32 *p;
- rd_ary = (struct rpcrdma_read_chunk *)&rdma_argp->rm_body.rm_chunks[0];
- if (rd_ary->rc_discrim != xdr_zero)
- return be32_to_cpu(rd_ary->rc_target.rs_handle);
+ p = rdma_argp + rpcrdma_fixed_maxsz;
+ if (*p != xdr_zero)
+ p += 2;
+ else if (wr_lst && be32_to_cpup(wr_lst + 1))
+ p = wr_lst + 2;
+ else if (rp_ch && be32_to_cpup(rp_ch + 1))
+ p = rp_ch + 2;
+ else
+ return 0;
+ return be32_to_cpup(p);
+}
- if (wr_ary && be32_to_cpu(wr_ary->wc_nchunks)) {
- arg_ch = &wr_ary->wc_array[0].wc_target;
- return be32_to_cpu(arg_ch->rs_handle);
- }
+/* ib_dma_map_page() is used here because svc_rdma_dma_unmap()
+ * is used during completion to DMA-unmap this memory, and
+ * it uses ib_dma_unmap_page() exclusively.
+ */
+static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
+ struct svc_rdma_op_ctxt *ctxt,
+ unsigned int sge_no,
+ unsigned char *base,
+ unsigned int len)
+{
+ unsigned long offset = (unsigned long)base & ~PAGE_MASK;
+ struct ib_device *dev = rdma->sc_cm_id->device;
+ dma_addr_t dma_addr;
- if (rp_ary && be32_to_cpu(rp_ary->wc_nchunks)) {
- arg_ch = &rp_ary->wc_array[0].wc_target;
- return be32_to_cpu(arg_ch->rs_handle);
- }
+ dma_addr = ib_dma_map_page(dev, virt_to_page(base),
+ offset, len, DMA_TO_DEVICE);
+ if (ib_dma_mapping_error(dev, dma_addr))
+ return -EIO;
+ ctxt->sge[sge_no].addr = dma_addr;
+ ctxt->sge[sge_no].length = len;
+ ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey;
+ svc_rdma_count_mappings(rdma, ctxt);
return 0;
}
-/* Assumptions:
- * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE
- */
-static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
- u32 rmr, u64 to,
- u32 xdr_off, int write_len,
- struct svc_rdma_req_map *vec)
+static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma,
+ struct svc_rdma_op_ctxt *ctxt,
+ unsigned int sge_no,
+ struct page *page,
+ unsigned int offset,
+ unsigned int len)
{
- struct ib_rdma_wr write_wr;
- struct ib_sge *sge;
- int xdr_sge_no;
- int sge_no;
- int sge_bytes;
- int sge_off;
- int bc;
- struct svc_rdma_op_ctxt *ctxt;
+ struct ib_device *dev = rdma->sc_cm_id->device;
+ dma_addr_t dma_addr;
- if (vec->count > RPCSVC_MAXPAGES) {
- pr_err("svcrdma: Too many pages (%lu)\n", vec->count);
+ dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE);
+ if (ib_dma_mapping_error(dev, dma_addr))
return -EIO;
- }
- dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, "
- "write_len=%d, vec->sge=%p, vec->count=%lu\n",
- rmr, (unsigned long long)to, xdr_off,
- write_len, vec->sge, vec->count);
+ ctxt->sge[sge_no].addr = dma_addr;
+ ctxt->sge[sge_no].length = len;
+ ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey;
+ svc_rdma_count_mappings(rdma, ctxt);
+ return 0;
+}
- ctxt = svc_rdma_get_context(xprt);
+/**
+ * svc_rdma_map_reply_hdr - DMA map the transport header buffer
+ * @rdma: controlling transport
+ * @ctxt: op_ctxt for the Send WR
+ * @rdma_resp: buffer containing transport header
+ * @len: length of transport header
+ *
+ * Returns:
+ * %0 if the header is DMA mapped,
+ * %-EIO if DMA mapping failed.
+ */
+int svc_rdma_map_reply_hdr(struct svcxprt_rdma *rdma,
+ struct svc_rdma_op_ctxt *ctxt,
+ __be32 *rdma_resp,
+ unsigned int len)
+{
ctxt->direction = DMA_TO_DEVICE;
- sge = ctxt->sge;
-
- /* Find the SGE associated with xdr_off */
- for (bc = xdr_off, xdr_sge_no = 1; bc && xdr_sge_no < vec->count;
- xdr_sge_no++) {
- if (vec->sge[xdr_sge_no].iov_len > bc)
- break;
- bc -= vec->sge[xdr_sge_no].iov_len;
- }
-
- sge_off = bc;
- bc = write_len;
- sge_no = 0;
-
- /* Copy the remaining SGE */
- while (bc != 0) {
- sge_bytes = min_t(size_t,
- bc, vec->sge[xdr_sge_no].iov_len-sge_off);
- sge[sge_no].length = sge_bytes;
- sge[sge_no].addr =
- dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
- sge_bytes, DMA_TO_DEVICE);
- xdr_off += sge_bytes;
- if (ib_dma_mapping_error(xprt->sc_cm_id->device,
- sge[sge_no].addr))
- goto err;
- svc_rdma_count_mappings(xprt, ctxt);
- sge[sge_no].lkey = xprt->sc_pd->local_dma_lkey;
- ctxt->count++;
- sge_off = 0;
- sge_no++;
- xdr_sge_no++;
- if (xdr_sge_no > vec->count) {
- pr_err("svcrdma: Too many sges (%d)\n", xdr_sge_no);
- goto err;
- }
- bc -= sge_bytes;
- if (sge_no == xprt->sc_max_sge)
- break;
- }
-
- /* Prepare WRITE WR */
- memset(&write_wr, 0, sizeof write_wr);
- ctxt->cqe.done = svc_rdma_wc_write;
- write_wr.wr.wr_cqe = &ctxt->cqe;
- write_wr.wr.sg_list = &sge[0];
- write_wr.wr.num_sge = sge_no;
- write_wr.wr.opcode = IB_WR_RDMA_WRITE;
- write_wr.wr.send_flags = IB_SEND_SIGNALED;
- write_wr.rkey = rmr;
- write_wr.remote_addr = to;
-
- /* Post It */
- atomic_inc(&rdma_stat_write);
- if (svc_rdma_send(xprt, &write_wr.wr))
- goto err;
- return write_len - bc;
- err:
- svc_rdma_unmap_dma(ctxt);
- svc_rdma_put_context(ctxt, 0);
- return -EIO;
+ ctxt->pages[0] = virt_to_page(rdma_resp);
+ ctxt->count = 1;
+ return svc_rdma_dma_map_page(rdma, ctxt, 0, ctxt->pages[0], 0, len);
}
-noinline
-static int send_write_chunks(struct svcxprt_rdma *xprt,
- struct rpcrdma_write_array *wr_ary,
- struct rpcrdma_msg *rdma_resp,
- struct svc_rqst *rqstp,
- struct svc_rdma_req_map *vec)
+/* Load the xdr_buf into the ctxt's sge array, and DMA map each
+ * element as it is added.
+ *
+ * Returns the number of sge elements loaded on success, or
+ * a negative errno on failure.
+ */
+static int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
+ struct svc_rdma_op_ctxt *ctxt,
+ struct xdr_buf *xdr, __be32 *wr_lst)
{
- u32 xfer_len = rqstp->rq_res.page_len;
- int write_len;
- u32 xdr_off;
- int chunk_off;
- int chunk_no;
- int nchunks;
- struct rpcrdma_write_array *res_ary;
+ unsigned int len, sge_no, remaining, page_off;
+ struct page **ppages;
+ unsigned char *base;
+ u32 xdr_pad;
int ret;
- res_ary = (struct rpcrdma_write_array *)
- &rdma_resp->rm_body.rm_chunks[1];
-
- /* Write chunks start at the pagelist */
- nchunks = be32_to_cpu(wr_ary->wc_nchunks);
- for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0;
- xfer_len && chunk_no < nchunks;
- chunk_no++) {
- struct rpcrdma_segment *arg_ch;
- u64 rs_offset;
-
- arg_ch = &wr_ary->wc_array[chunk_no].wc_target;
- write_len = min(xfer_len, be32_to_cpu(arg_ch->rs_length));
-
- /* Prepare the response chunk given the length actually
- * written */
- xdr_decode_hyper((__be32 *)&arg_ch->rs_offset, &rs_offset);
- svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
- arg_ch->rs_handle,
- arg_ch->rs_offset,
- write_len);
- chunk_off = 0;
- while (write_len) {
- ret = send_write(xprt, rqstp,
- be32_to_cpu(arg_ch->rs_handle),
- rs_offset + chunk_off,
- xdr_off,
- write_len,
- vec);
- if (ret <= 0)
- goto out_err;
- chunk_off += ret;
- xdr_off += ret;
- xfer_len -= ret;
- write_len -= ret;
+ sge_no = 1;
+
+ ret = svc_rdma_dma_map_buf(rdma, ctxt, sge_no++,
+ xdr->head[0].iov_base,
+ xdr->head[0].iov_len);
+ if (ret < 0)
+ return ret;
+
+ /* If a Write chunk is present, the xdr_buf's page list
+ * is not included inline. However the Upper Layer may
+ * have added XDR padding in the tail buffer, and that
+ * should not be included inline.
+ */
+ if (wr_lst) {
+ base = xdr->tail[0].iov_base;
+ len = xdr->tail[0].iov_len;
+ xdr_pad = xdr_padsize(xdr->page_len);
+
+ if (len && xdr_pad) {
+ base += xdr_pad;
+ len -= xdr_pad;
}
+
+ goto tail;
+ }
+
+ ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+ page_off = xdr->page_base & ~PAGE_MASK;
+ remaining = xdr->page_len;
+ while (remaining) {
+ len = min_t(u32, PAGE_SIZE - page_off, remaining);
+
+ ret = svc_rdma_dma_map_page(rdma, ctxt, sge_no++,
+ *ppages++, page_off, len);
+ if (ret < 0)
+ return ret;
+
+ remaining -= len;
+ page_off = 0;
}
- /* Update the req with the number of chunks actually used */
- svc_rdma_xdr_encode_write_list(rdma_resp, chunk_no);
- return rqstp->rq_res.page_len;
+ base = xdr->tail[0].iov_base;
+ len = xdr->tail[0].iov_len;
+tail:
+ if (len) {
+ ret = svc_rdma_dma_map_buf(rdma, ctxt, sge_no++, base, len);
+ if (ret < 0)
+ return ret;
+ }
-out_err:
- pr_err("svcrdma: failed to send write chunks, rc=%d\n", ret);
- return -EIO;
+ return sge_no - 1;
}
-noinline
-static int send_reply_chunks(struct svcxprt_rdma *xprt,
- struct rpcrdma_write_array *rp_ary,
- struct rpcrdma_msg *rdma_resp,
- struct svc_rqst *rqstp,
- struct svc_rdma_req_map *vec)
+/* The svc_rqst and all resources it owns are released as soon as
+ * svc_rdma_sendto returns. Transfer pages under I/O to the ctxt
+ * so they are released by the Send completion handler.
+ */
+static void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
+ struct svc_rdma_op_ctxt *ctxt)
{
- u32 xfer_len = rqstp->rq_res.len;
- int write_len;
- u32 xdr_off;
- int chunk_no;
- int chunk_off;
- int nchunks;
- struct rpcrdma_segment *ch;
- struct rpcrdma_write_array *res_ary;
- int ret;
+ int i, pages = rqstp->rq_next_page - rqstp->rq_respages;
- /* XXX: need to fix when reply lists occur with read-list and or
- * write-list */
- res_ary = (struct rpcrdma_write_array *)
- &rdma_resp->rm_body.rm_chunks[2];
-
- /* xdr offset starts at RPC message */
- nchunks = be32_to_cpu(rp_ary->wc_nchunks);
- for (xdr_off = 0, chunk_no = 0;
- xfer_len && chunk_no < nchunks;
- chunk_no++) {
- u64 rs_offset;
- ch = &rp_ary->wc_array[chunk_no].wc_target;
- write_len = min(xfer_len, be32_to_cpu(ch->rs_length));
-
- /* Prepare the reply chunk given the length actually
- * written */
- xdr_decode_hyper((__be32 *)&ch->rs_offset, &rs_offset);
- svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
- ch->rs_handle, ch->rs_offset,
- write_len);
- chunk_off = 0;
- while (write_len) {
- ret = send_write(xprt, rqstp,
- be32_to_cpu(ch->rs_handle),
- rs_offset + chunk_off,
- xdr_off,
- write_len,
- vec);
- if (ret <= 0)
- goto out_err;
- chunk_off += ret;
- xdr_off += ret;
- xfer_len -= ret;
- write_len -= ret;
- }
+ ctxt->count += pages;
+ for (i = 0; i < pages; i++) {
+ ctxt->pages[i + 1] = rqstp->rq_respages[i];
+ rqstp->rq_respages[i] = NULL;
}
- /* Update the req with the number of chunks actually used */
- svc_rdma_xdr_encode_reply_array(res_ary, chunk_no);
+ rqstp->rq_next_page = rqstp->rq_respages + 1;
+}
- return rqstp->rq_res.len;
+/**
+ * svc_rdma_post_send_wr - Set up and post one Send Work Request
+ * @rdma: controlling transport
+ * @ctxt: op_ctxt for transmitting the Send WR
+ * @num_sge: number of SGEs to send
+ * @inv_rkey: R_key argument to Send With Invalidate, or zero
+ *
+ * Returns:
+ * %0 if the Send* was posted successfully,
+ * %-ENOTCONN if the connection was lost or dropped,
+ * %-EINVAL if there was a problem with the Send we built,
+ * %-ENOMEM if ib_post_send failed.
+ */
+int svc_rdma_post_send_wr(struct svcxprt_rdma *rdma,
+ struct svc_rdma_op_ctxt *ctxt, int num_sge,
+ u32 inv_rkey)
+{
+ struct ib_send_wr *send_wr = &ctxt->send_wr;
-out_err:
- pr_err("svcrdma: failed to send reply chunks, rc=%d\n", ret);
- return -EIO;
+ dprintk("svcrdma: posting Send WR with %u sge(s)\n", num_sge);
+
+ send_wr->next = NULL;
+ ctxt->cqe.done = svc_rdma_wc_send;
+ send_wr->wr_cqe = &ctxt->cqe;
+ send_wr->sg_list = ctxt->sge;
+ send_wr->num_sge = num_sge;
+ send_wr->send_flags = IB_SEND_SIGNALED;
+ if (inv_rkey) {
+ send_wr->opcode = IB_WR_SEND_WITH_INV;
+ send_wr->ex.invalidate_rkey = inv_rkey;
+ } else {
+ send_wr->opcode = IB_WR_SEND;
+ }
+
+ return svc_rdma_send(rdma, send_wr);
}
-/* This function prepares the portion of the RPCRDMA message to be
- * sent in the RDMA_SEND. This function is called after data sent via
- * RDMA has already been transmitted. There are three cases:
- * - The RPCRDMA header, RPC header, and payload are all sent in a
- * single RDMA_SEND. This is the "inline" case.
- * - The RPCRDMA header and some portion of the RPC header and data
- * are sent via this RDMA_SEND and another portion of the data is
- * sent via RDMA.
- * - The RPCRDMA header [NOMSG] is sent in this RDMA_SEND and the RPC
- * header and data are all transmitted via RDMA.
- * In all three cases, this function prepares the RPCRDMA header in
- * sge[0], the 'type' parameter indicates the type to place in the
- * RPCRDMA header, and the 'byte_count' field indicates how much of
- * the XDR to include in this RDMA_SEND. NB: The offset of the payload
- * to send is zero in the XDR.
+/* Prepare the portion of the RPC Reply that will be transmitted
+ * via RDMA Send. The RPC-over-RDMA transport header is prepared
+ * in sge[0], and the RPC xdr_buf is prepared in following sges.
+ *
+ * Depending on whether a Write list or Reply chunk is present,
+ * the server may send all, a portion of, or none of the xdr_buf.
+ * In the latter case, only the transport header (sge[0]) is
+ * transmitted.
+ *
+ * RDMA Send is the last step of transmitting an RPC reply. Pages
+ * involved in the earlier RDMA Writes are here transferred out
+ * of the rqstp and into the ctxt's page array. These pages are
+ * DMA unmapped by each Write completion, but the subsequent Send
+ * completion finally releases these pages.
+ *
+ * Assumptions:
+ * - The Reply's transport header will never be larger than a page.
*/
-static int send_reply(struct svcxprt_rdma *rdma,
- struct svc_rqst *rqstp,
- struct page *page,
- struct rpcrdma_msg *rdma_resp,
- struct svc_rdma_req_map *vec,
- int byte_count,
- u32 inv_rkey)
+static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma,
+ __be32 *rdma_argp, __be32 *rdma_resp,
+ struct svc_rqst *rqstp,
+ __be32 *wr_lst, __be32 *rp_ch)
{
struct svc_rdma_op_ctxt *ctxt;
- struct ib_send_wr send_wr;
- u32 xdr_off;
- int sge_no;
- int sge_bytes;
- int page_no;
- int pages;
- int ret = -EIO;
-
- /* Prepare the context */
+ u32 inv_rkey;
+ int ret;
+
+ dprintk("svcrdma: sending %s reply: head=%zu, pagelen=%u, tail=%zu\n",
+ (rp_ch ? "RDMA_NOMSG" : "RDMA_MSG"),
+ rqstp->rq_res.head[0].iov_len,
+ rqstp->rq_res.page_len,
+ rqstp->rq_res.tail[0].iov_len);
+
ctxt = svc_rdma_get_context(rdma);
- ctxt->direction = DMA_TO_DEVICE;
- ctxt->pages[0] = page;
- ctxt->count = 1;
- /* Prepare the SGE for the RPCRDMA Header */
- ctxt->sge[0].lkey = rdma->sc_pd->local_dma_lkey;
- ctxt->sge[0].length =
- svc_rdma_xdr_get_reply_hdr_len((__be32 *)rdma_resp);
- ctxt->sge[0].addr =
- ib_dma_map_page(rdma->sc_cm_id->device, page, 0,
- ctxt->sge[0].length, DMA_TO_DEVICE);
- if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr))
+ ret = svc_rdma_map_reply_hdr(rdma, ctxt, rdma_resp,
+ svc_rdma_reply_hdr_len(rdma_resp));
+ if (ret < 0)
goto err;
- svc_rdma_count_mappings(rdma, ctxt);
-
- ctxt->direction = DMA_TO_DEVICE;
- /* Map the payload indicated by 'byte_count' */
- xdr_off = 0;
- for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
- sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
- byte_count -= sge_bytes;
- ctxt->sge[sge_no].addr =
- dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
- sge_bytes, DMA_TO_DEVICE);
- xdr_off += sge_bytes;
- if (ib_dma_mapping_error(rdma->sc_cm_id->device,
- ctxt->sge[sge_no].addr))
+ if (!rp_ch) {
+ ret = svc_rdma_map_reply_msg(rdma, ctxt,
+ &rqstp->rq_res, wr_lst);
+ if (ret < 0)
goto err;
- svc_rdma_count_mappings(rdma, ctxt);
- ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey;
- ctxt->sge[sge_no].length = sge_bytes;
}
- if (byte_count != 0) {
- pr_err("svcrdma: Could not map %d bytes\n", byte_count);
+
+ svc_rdma_save_io_pages(rqstp, ctxt);
+
+ inv_rkey = 0;
+ if (rdma->sc_snd_w_inv)
+ inv_rkey = svc_rdma_get_inv_rkey(rdma_argp, wr_lst, rp_ch);
+ ret = svc_rdma_post_send_wr(rdma, ctxt, 1 + ret, inv_rkey);
+ if (ret)
goto err;
- }
- /* Save all respages in the ctxt and remove them from the
- * respages array. They are our pages until the I/O
- * completes.
+ return 0;
+
+err:
+ pr_err("svcrdma: failed to post Send WR (%d)\n", ret);
+ svc_rdma_unmap_dma(ctxt);
+ svc_rdma_put_context(ctxt, 1);
+ return ret;
+}
+
+/* Given the client-provided Write and Reply chunks, the server was not
+ * able to form a complete reply. Return an RDMA_ERROR message so the
+ * client can retire this RPC transaction. As above, the Send completion
+ * routine releases payload pages that were part of a previous RDMA Write.
+ *
+ * Remote Invalidation is skipped for simplicity.
+ */
+static int svc_rdma_send_error_msg(struct svcxprt_rdma *rdma,
+ __be32 *rdma_resp, struct svc_rqst *rqstp)
+{
+ struct svc_rdma_op_ctxt *ctxt;
+ __be32 *p;
+ int ret;
+
+ ctxt = svc_rdma_get_context(rdma);
+
+ /* Replace the original transport header with an
+ * RDMA_ERROR response. XID etc are preserved.
*/
- pages = rqstp->rq_next_page - rqstp->rq_respages;
- for (page_no = 0; page_no < pages; page_no++) {
- ctxt->pages[page_no+1] = rqstp->rq_respages[page_no];
- ctxt->count++;
- rqstp->rq_respages[page_no] = NULL;
- }
- rqstp->rq_next_page = rqstp->rq_respages + 1;
+ p = rdma_resp + 3;
+ *p++ = rdma_error;
+ *p = err_chunk;
- if (sge_no > rdma->sc_max_sge) {
- pr_err("svcrdma: Too many sges (%d)\n", sge_no);
+ ret = svc_rdma_map_reply_hdr(rdma, ctxt, rdma_resp, 20);
+ if (ret < 0)
goto err;
- }
- memset(&send_wr, 0, sizeof send_wr);
- ctxt->cqe.done = svc_rdma_wc_send;
- send_wr.wr_cqe = &ctxt->cqe;
- send_wr.sg_list = ctxt->sge;
- send_wr.num_sge = sge_no;
- if (inv_rkey) {
- send_wr.opcode = IB_WR_SEND_WITH_INV;
- send_wr.ex.invalidate_rkey = inv_rkey;
- } else
- send_wr.opcode = IB_WR_SEND;
- send_wr.send_flags = IB_SEND_SIGNALED;
- ret = svc_rdma_send(rdma, &send_wr);
+ svc_rdma_save_io_pages(rqstp, ctxt);
+
+ ret = svc_rdma_post_send_wr(rdma, ctxt, 1 + ret, 0);
if (ret)
goto err;
return 0;
- err:
+err:
+ pr_err("svcrdma: failed to post Send WR (%d)\n", ret);
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 1);
return ret;
{
}
+/**
+ * svc_rdma_sendto - Transmit an RPC reply
+ * @rqstp: processed RPC request, reply XDR already in ::rq_res
+ *
+ * Any resources still associated with @rqstp are released upon return.
+ * If no reply message was possible, the connection is closed.
+ *
+ * Returns:
+ * %0 if an RPC reply has been successfully posted,
+ * %-ENOMEM if a resource shortage occurred (connection is lost),
+ * %-ENOTCONN if posting failed (connection is lost).
+ */
int svc_rdma_sendto(struct svc_rqst *rqstp)
{
struct svc_xprt *xprt = rqstp->rq_xprt;
struct svcxprt_rdma *rdma =
container_of(xprt, struct svcxprt_rdma, sc_xprt);
- struct rpcrdma_msg *rdma_argp;
- struct rpcrdma_msg *rdma_resp;
- struct rpcrdma_write_array *wr_ary, *rp_ary;
- int ret;
- int inline_bytes;
+ __be32 *p, *rdma_argp, *rdma_resp, *wr_lst, *rp_ch;
+ struct xdr_buf *xdr = &rqstp->rq_res;
struct page *res_page;
- struct svc_rdma_req_map *vec;
- u32 inv_rkey;
- __be32 *p;
-
- dprintk("svcrdma: sending response for rqstp=%p\n", rqstp);
+ int ret;
- /* Get the RDMA request header. The receive logic always
- * places this at the start of page 0.
+ /* Find the call's chunk lists to decide how to send the reply.
+ * Receive places the Call's xprt header at the start of page 0.
*/
rdma_argp = page_address(rqstp->rq_pages[0]);
- svc_rdma_get_write_arrays(rdma_argp, &wr_ary, &rp_ary);
-
- inv_rkey = 0;
- if (rdma->sc_snd_w_inv)
- inv_rkey = svc_rdma_get_inv_rkey(rdma_argp, wr_ary, rp_ary);
+ svc_rdma_get_write_arrays(rdma_argp, &wr_lst, &rp_ch);
- /* Build an req vec for the XDR */
- vec = svc_rdma_get_req_map(rdma);
- ret = svc_rdma_map_xdr(rdma, &rqstp->rq_res, vec, wr_ary != NULL);
- if (ret)
- goto err0;
- inline_bytes = rqstp->rq_res.len;
+ dprintk("svcrdma: preparing response for XID 0x%08x\n",
+ be32_to_cpup(rdma_argp));
/* Create the RDMA response header. xprt->xpt_mutex,
* acquired in svc_send(), serializes RPC replies. The
goto err0;
rdma_resp = page_address(res_page);
- p = &rdma_resp->rm_xid;
- *p++ = rdma_argp->rm_xid;
- *p++ = rdma_argp->rm_vers;
+ p = rdma_resp;
+ *p++ = *rdma_argp;
+ *p++ = *(rdma_argp + 1);
*p++ = rdma->sc_fc_credits;
- *p++ = rp_ary ? rdma_nomsg : rdma_msg;
+ *p++ = rp_ch ? rdma_nomsg : rdma_msg;
/* Start with empty chunks */
*p++ = xdr_zero;
*p++ = xdr_zero;
*p = xdr_zero;
- /* Send any write-chunk data and build resp write-list */
- if (wr_ary) {
- ret = send_write_chunks(rdma, wr_ary, rdma_resp, rqstp, vec);
+ if (wr_lst) {
+ /* XXX: Presume the client sent only one Write chunk */
+ ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr);
if (ret < 0)
- goto err1;
- inline_bytes -= ret + xdr_padsize(ret);
+ goto err2;
+ svc_rdma_xdr_encode_write_list(rdma_resp, wr_lst, ret);
}
-
- /* Send any reply-list data and update resp reply-list */
- if (rp_ary) {
- ret = send_reply_chunks(rdma, rp_ary, rdma_resp, rqstp, vec);
+ if (rp_ch) {
+ ret = svc_rdma_send_reply_chunk(rdma, rp_ch, wr_lst, xdr);
if (ret < 0)
- goto err1;
- inline_bytes -= ret;
+ goto err2;
+ svc_rdma_xdr_encode_reply_chunk(rdma_resp, rp_ch, ret);
}
- /* Post a fresh Receive buffer _before_ sending the reply */
ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
if (ret)
goto err1;
-
- ret = send_reply(rdma, rqstp, res_page, rdma_resp, vec,
- inline_bytes, inv_rkey);
+ ret = svc_rdma_send_reply_msg(rdma, rdma_argp, rdma_resp, rqstp,
+ wr_lst, rp_ch);
if (ret < 0)
goto err0;
+ return 0;
- svc_rdma_put_req_map(rdma, vec);
- dprintk("svcrdma: send_reply returns %d\n", ret);
- return ret;
+ err2:
+ if (ret != -E2BIG)
+ goto err1;
+
+ ret = svc_rdma_post_recv(rdma, GFP_KERNEL);
+ if (ret)
+ goto err1;
+ ret = svc_rdma_send_error_msg(rdma, rdma_resp, rqstp);
+ if (ret < 0)
+ goto err0;
+ return 0;
err1:
put_page(res_page);
err0:
- svc_rdma_put_req_map(rdma, vec);
pr_err("svcrdma: Could not send reply, err=%d. Closing transport.\n",
ret);
- set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
+ set_bit(XPT_CLOSE, &xprt->xpt_flags);
return -ENOTCONN;
}
-
-void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp,
- int status)
-{
- struct ib_send_wr err_wr;
- struct page *p;
- struct svc_rdma_op_ctxt *ctxt;
- enum rpcrdma_errcode err;
- __be32 *va;
- int length;
- int ret;
-
- ret = svc_rdma_repost_recv(xprt, GFP_KERNEL);
- if (ret)
- return;
-
- p = alloc_page(GFP_KERNEL);
- if (!p)
- return;
- va = page_address(p);
-
- /* XDR encode an error reply */
- err = ERR_CHUNK;
- if (status == -EPROTONOSUPPORT)
- err = ERR_VERS;
- length = svc_rdma_xdr_encode_error(xprt, rmsgp, err, va);
-
- ctxt = svc_rdma_get_context(xprt);
- ctxt->direction = DMA_TO_DEVICE;
- ctxt->count = 1;
- ctxt->pages[0] = p;
-
- /* Prepare SGE for local address */
- ctxt->sge[0].lkey = xprt->sc_pd->local_dma_lkey;
- ctxt->sge[0].length = length;
- ctxt->sge[0].addr = ib_dma_map_page(xprt->sc_cm_id->device,
- p, 0, length, DMA_TO_DEVICE);
- if (ib_dma_mapping_error(xprt->sc_cm_id->device, ctxt->sge[0].addr)) {
- dprintk("svcrdma: Error mapping buffer for protocol error\n");
- svc_rdma_put_context(ctxt, 1);
- return;
- }
- svc_rdma_count_mappings(xprt, ctxt);
-
- /* Prepare SEND WR */
- memset(&err_wr, 0, sizeof(err_wr));
- ctxt->cqe.done = svc_rdma_wc_send;
- err_wr.wr_cqe = &ctxt->cqe;
- err_wr.sg_list = ctxt->sge;
- err_wr.num_sge = 1;
- err_wr.opcode = IB_WR_SEND;
- err_wr.send_flags = IB_SEND_SIGNALED;
-
- /* Post It */
- ret = svc_rdma_send(xprt, &err_wr);
- if (ret) {
- dprintk("svcrdma: Error %d posting send for protocol error\n",
- ret);
- svc_rdma_unmap_dma(ctxt);
- svc_rdma_put_context(ctxt, 1);
- }
-}
}
}
-static struct svc_rdma_req_map *alloc_req_map(gfp_t flags)
-{
- struct svc_rdma_req_map *map;
-
- map = kmalloc(sizeof(*map), flags);
- if (map)
- INIT_LIST_HEAD(&map->free);
- return map;
-}
-
-static bool svc_rdma_prealloc_maps(struct svcxprt_rdma *xprt)
-{
- unsigned int i;
-
- /* One for each receive buffer on this connection. */
- i = xprt->sc_max_requests;
-
- while (i--) {
- struct svc_rdma_req_map *map;
-
- map = alloc_req_map(GFP_KERNEL);
- if (!map) {
- dprintk("svcrdma: No memory for request map\n");
- return false;
- }
- list_add(&map->free, &xprt->sc_maps);
- }
- return true;
-}
-
-struct svc_rdma_req_map *svc_rdma_get_req_map(struct svcxprt_rdma *xprt)
-{
- struct svc_rdma_req_map *map = NULL;
-
- spin_lock(&xprt->sc_map_lock);
- if (list_empty(&xprt->sc_maps))
- goto out_empty;
-
- map = list_first_entry(&xprt->sc_maps,
- struct svc_rdma_req_map, free);
- list_del_init(&map->free);
- spin_unlock(&xprt->sc_map_lock);
-
-out:
- map->count = 0;
- return map;
-
-out_empty:
- spin_unlock(&xprt->sc_map_lock);
-
- /* Pre-allocation amount was incorrect */
- map = alloc_req_map(GFP_NOIO);
- if (map)
- goto out;
-
- WARN_ONCE(1, "svcrdma: empty request map list?\n");
- return NULL;
-}
-
-void svc_rdma_put_req_map(struct svcxprt_rdma *xprt,
- struct svc_rdma_req_map *map)
-{
- spin_lock(&xprt->sc_map_lock);
- list_add(&map->free, &xprt->sc_maps);
- spin_unlock(&xprt->sc_map_lock);
-}
-
-static void svc_rdma_destroy_maps(struct svcxprt_rdma *xprt)
-{
- while (!list_empty(&xprt->sc_maps)) {
- struct svc_rdma_req_map *map;
-
- map = list_first_entry(&xprt->sc_maps,
- struct svc_rdma_req_map, free);
- list_del(&map->free);
- kfree(map);
- }
-}
-
/* QP event handler */
static void qp_event_handler(struct ib_event *event, void *context)
{
svc_rdma_put_context(ctxt, 1);
}
-/**
- * svc_rdma_wc_write - Invoked by RDMA provider for each polled Write WC
- * @cq: completion queue
- * @wc: completed WR
- *
- */
-void svc_rdma_wc_write(struct ib_cq *cq, struct ib_wc *wc)
-{
- struct ib_cqe *cqe = wc->wr_cqe;
- struct svc_rdma_op_ctxt *ctxt;
-
- svc_rdma_send_wc_common_put(cq, wc, "write");
-
- ctxt = container_of(cqe, struct svc_rdma_op_ctxt, cqe);
- svc_rdma_unmap_dma(ctxt);
- svc_rdma_put_context(ctxt, 0);
-}
-
/**
* svc_rdma_wc_reg - Invoked by RDMA provider for each polled FASTREG WC
* @cq: completion queue
INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q);
INIT_LIST_HEAD(&cma_xprt->sc_frmr_q);
INIT_LIST_HEAD(&cma_xprt->sc_ctxts);
- INIT_LIST_HEAD(&cma_xprt->sc_maps);
+ INIT_LIST_HEAD(&cma_xprt->sc_rw_ctxts);
init_waitqueue_head(&cma_xprt->sc_send_wait);
spin_lock_init(&cma_xprt->sc_lock);
spin_lock_init(&cma_xprt->sc_rq_dto_lock);
spin_lock_init(&cma_xprt->sc_frmr_q_lock);
spin_lock_init(&cma_xprt->sc_ctxt_lock);
- spin_lock_init(&cma_xprt->sc_map_lock);
+ spin_lock_init(&cma_xprt->sc_rw_ctxt_lock);
/*
* Note that this implies that the underlying transport support
newxprt, newxprt->sc_cm_id);
dev = newxprt->sc_cm_id->device;
+ newxprt->sc_port_num = newxprt->sc_cm_id->port_num;
/* Qualify the transport resource defaults with the
* capabilities of this particular device */
svcrdma_max_bc_requests);
newxprt->sc_rq_depth = newxprt->sc_max_requests +
newxprt->sc_max_bc_requests;
- newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_rq_depth;
+ newxprt->sc_sq_depth = newxprt->sc_rq_depth;
atomic_set(&newxprt->sc_sq_avail, newxprt->sc_sq_depth);
if (!svc_rdma_prealloc_ctxts(newxprt))
goto errout;
- if (!svc_rdma_prealloc_maps(newxprt))
- goto errout;
/*
* Limit ORD based on client limit, local device limit, and
memset(&qp_attr, 0, sizeof qp_attr);
qp_attr.event_handler = qp_event_handler;
qp_attr.qp_context = &newxprt->sc_xprt;
+ qp_attr.port_num = newxprt->sc_cm_id->port_num;
+ qp_attr.cap.max_rdma_ctxs = newxprt->sc_max_requests;
qp_attr.cap.max_send_wr = newxprt->sc_sq_depth;
qp_attr.cap.max_recv_wr = newxprt->sc_rq_depth;
qp_attr.cap.max_send_sge = newxprt->sc_max_sge;
}
rdma_dealloc_frmr_q(rdma);
+ svc_rdma_destroy_rw_ctxts(rdma);
svc_rdma_destroy_ctxts(rdma);
- svc_rdma_destroy_maps(rdma);
/* Destroy the QP if present (not a listener) */
if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
unsigned int xprt_rdma_max_inline_read = RPCRDMA_DEF_INLINE;
static unsigned int xprt_rdma_max_inline_write = RPCRDMA_DEF_INLINE;
static unsigned int xprt_rdma_inline_write_padding;
-static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR;
- int xprt_rdma_pad_optimize = 0;
+unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR;
+int xprt_rdma_pad_optimize;
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
new_xprt = rpcx_to_rdmax(xprt);
- rc = rpcrdma_ia_open(new_xprt, sap, xprt_rdma_memreg_strategy);
+ rc = rpcrdma_ia_open(new_xprt, sap);
if (rc)
goto out1;
return ERR_PTR(rc);
}
-/*
- * Close a connection, during shutdown or timeout/reconnect
+/**
+ * xprt_rdma_close - Close down RDMA connection
+ * @xprt: generic transport to be closed
+ *
+ * Called during transport shutdown reconnect, or device
+ * removal. Caller holds the transport's write lock.
*/
static void
xprt_rdma_close(struct rpc_xprt *xprt)
{
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+ struct rpcrdma_ep *ep = &r_xprt->rx_ep;
+ struct rpcrdma_ia *ia = &r_xprt->rx_ia;
+
+ dprintk("RPC: %s: closing xprt %p\n", __func__, xprt);
- dprintk("RPC: %s: closing\n", __func__);
- if (r_xprt->rx_ep.rep_connected > 0)
+ if (test_and_clear_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags)) {
+ xprt_clear_connected(xprt);
+ rpcrdma_ia_remove(ia);
+ return;
+ }
+ if (ep->rep_connected == -ENODEV)
+ return;
+ if (ep->rep_connected > 0)
xprt->reestablish_timeout = 0;
xprt_disconnect_done(xprt);
- rpcrdma_ep_disconnect(&r_xprt->rx_ep, &r_xprt->rx_ia);
+ rpcrdma_ep_disconnect(ep, ia);
}
static void
dprintk("RPC: %s: %u\n", __func__, port);
}
+/**
+ * xprt_rdma_timer - invoked when an RPC times out
+ * @xprt: controlling RPC transport
+ * @task: RPC task that timed out
+ *
+ * Invoked when the transport is still connected, but an RPC
+ * retransmit timeout occurs.
+ *
+ * Since RDMA connections don't have a keep-alive, forcibly
+ * disconnect and retry to connect. This drives full
+ * detection of the network path, and retransmissions of
+ * all pending RPCs.
+ */
+static void
+xprt_rdma_timer(struct rpc_xprt *xprt, struct rpc_task *task)
+{
+ dprintk("RPC: %5u %s: xprt = %p\n", task->tk_pid, __func__, xprt);
+
+ xprt_force_disconnect(xprt);
+}
+
static void
xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
{
* xprt_rdma_send_request - marshal and send an RPC request
* @task: RPC task with an RPC message in rq_snd_buf
*
+ * Caller holds the transport's write lock.
+ *
* Return values:
* 0: The request has been sent
* ENOTCONN: Caller needs to invoke connect logic then call again
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
int rc = 0;
+ if (!xprt_connected(xprt))
+ goto drop_connection;
+
/* On retransmit, remove any previously registered chunks */
if (unlikely(!list_empty(&req->rl_registered)))
r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false);
.alloc_slot = xprt_alloc_slot,
.release_request = xprt_release_rqst_cong, /* ditto */
.set_retrans_timeout = xprt_set_retrans_timeout_def, /* ditto */
+ .timer = xprt_rdma_timer,
.rpcbind = rpcb_getport_async, /* sunrpc/rpcb_clnt.c */
.set_port = xprt_rdma_set_port,
.connect = xprt_rdma_connect,
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/svc_rdma.h>
#include <asm/bitops.h>
-#include <linux/module.h> /* try_module_get()/module_put() */
+
#include <rdma/ib_cm.h>
#include "xprt_rdma.h"
/*
* internal functions
*/
+static void rpcrdma_create_mrs(struct rpcrdma_xprt *r_xprt);
+static void rpcrdma_destroy_mrs(struct rpcrdma_buffer *buf);
+static void rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb);
-static struct workqueue_struct *rpcrdma_receive_wq;
+static struct workqueue_struct *rpcrdma_receive_wq __read_mostly;
int
rpcrdma_alloc_wq(void)
rep->rr_wc_flags = wc->wc_flags;
rep->rr_inv_rkey = wc->ex.invalidate_rkey;
- ib_dma_sync_single_for_cpu(rep->rr_device,
+ ib_dma_sync_single_for_cpu(rdmab_device(rep->rr_rdmabuf),
rdmab_addr(rep->rr_rdmabuf),
rep->rr_len, DMA_FROM_DEVICE);
__func__, ep);
complete(&ia->ri_done);
break;
+ case RDMA_CM_EVENT_DEVICE_REMOVAL:
+#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
+ pr_info("rpcrdma: removing device for %pIS:%u\n",
+ sap, rpc_get_port(sap));
+#endif
+ set_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags);
+ ep->rep_connected = -ENODEV;
+ xprt_force_disconnect(&xprt->rx_xprt);
+ wait_for_completion(&ia->ri_remove_done);
+
+ ia->ri_id = NULL;
+ ia->ri_pd = NULL;
+ ia->ri_device = NULL;
+ /* Return 1 to ensure the core destroys the id. */
+ return 1;
case RDMA_CM_EVENT_ESTABLISHED:
connstate = 1;
ib_query_qp(ia->ri_id->qp, attr,
goto connected;
case RDMA_CM_EVENT_DISCONNECTED:
connstate = -ECONNABORTED;
- goto connected;
- case RDMA_CM_EVENT_DEVICE_REMOVAL:
- connstate = -ENODEV;
connected:
dprintk("RPC: %s: %sconnected\n",
__func__, connstate > 0 ? "" : "dis");
return 0;
}
-static void rpcrdma_destroy_id(struct rdma_cm_id *id)
-{
- if (id) {
- module_put(id->device->owner);
- rdma_destroy_id(id);
- }
-}
-
static struct rdma_cm_id *
rpcrdma_create_id(struct rpcrdma_xprt *xprt,
struct rpcrdma_ia *ia, struct sockaddr *addr)
int rc;
init_completion(&ia->ri_done);
+ init_completion(&ia->ri_remove_done);
id = rdma_create_id(&init_net, rpcrdma_conn_upcall, xprt, RDMA_PS_TCP,
IB_QPT_RC);
goto out;
}
- /* FIXME:
- * Until xprtrdma supports DEVICE_REMOVAL, the provider must
- * be pinned while there are active NFS/RDMA mounts to prevent
- * hangs and crashes at umount time.
- */
- if (!ia->ri_async_rc && !try_module_get(id->device->owner)) {
- dprintk("RPC: %s: Failed to get device module\n",
- __func__);
- ia->ri_async_rc = -ENODEV;
- }
rc = ia->ri_async_rc;
if (rc)
goto out;
if (rc) {
dprintk("RPC: %s: rdma_resolve_route() failed %i\n",
__func__, rc);
- goto put;
+ goto out;
}
rc = wait_for_completion_interruptible_timeout(&ia->ri_done, wtimeout);
if (rc < 0) {
dprintk("RPC: %s: wait() exited: %i\n",
__func__, rc);
- goto put;
+ goto out;
}
rc = ia->ri_async_rc;
if (rc)
- goto put;
+ goto out;
return id;
-put:
- module_put(id->device->owner);
+
out:
rdma_destroy_id(id);
return ERR_PTR(rc);
* Exported functions.
*/
-/*
- * Open and initialize an Interface Adapter.
- * o initializes fields of struct rpcrdma_ia, including
- * interface and provider attributes and protection zone.
+/**
+ * rpcrdma_ia_open - Open and initialize an Interface Adapter.
+ * @xprt: controlling transport
+ * @addr: IP address of remote peer
+ *
+ * Returns 0 on success, negative errno if an appropriate
+ * Interface Adapter could not be found and opened.
*/
int
-rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
+rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr)
{
struct rpcrdma_ia *ia = &xprt->rx_ia;
int rc;
ia->ri_id = rpcrdma_create_id(xprt, ia, addr);
if (IS_ERR(ia->ri_id)) {
rc = PTR_ERR(ia->ri_id);
- goto out1;
+ goto out_err;
}
ia->ri_device = ia->ri_id->device;
if (IS_ERR(ia->ri_pd)) {
rc = PTR_ERR(ia->ri_pd);
pr_err("rpcrdma: ib_alloc_pd() returned %d\n", rc);
- goto out2;
+ goto out_err;
}
- switch (memreg) {
+ switch (xprt_rdma_memreg_strategy) {
case RPCRDMA_FRMR:
if (frwr_is_supported(ia)) {
ia->ri_ops = &rpcrdma_frwr_memreg_ops;
}
/*FALLTHROUGH*/
default:
- pr_err("rpcrdma: Unsupported memory registration mode: %d\n",
- memreg);
+ pr_err("rpcrdma: Device %s does not support memreg mode %d\n",
+ ia->ri_device->name, xprt_rdma_memreg_strategy);
rc = -EINVAL;
- goto out3;
+ goto out_err;
}
return 0;
-out3:
- ib_dealloc_pd(ia->ri_pd);
- ia->ri_pd = NULL;
-out2:
- rpcrdma_destroy_id(ia->ri_id);
- ia->ri_id = NULL;
-out1:
+out_err:
+ rpcrdma_ia_close(ia);
return rc;
}
-/*
- * Clean up/close an IA.
- * o if event handles and PD have been initialized, free them.
- * o close the IA
+/**
+ * rpcrdma_ia_remove - Handle device driver unload
+ * @ia: interface adapter being removed
+ *
+ * Divest transport H/W resources associated with this adapter,
+ * but allow it to be restored later.
+ */
+void
+rpcrdma_ia_remove(struct rpcrdma_ia *ia)
+{
+ struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt,
+ rx_ia);
+ struct rpcrdma_ep *ep = &r_xprt->rx_ep;
+ struct rpcrdma_buffer *buf = &r_xprt->rx_buf;
+ struct rpcrdma_req *req;
+ struct rpcrdma_rep *rep;
+
+ cancel_delayed_work_sync(&buf->rb_refresh_worker);
+
+ /* This is similar to rpcrdma_ep_destroy, but:
+ * - Don't cancel the connect worker.
+ * - Don't call rpcrdma_ep_disconnect, which waits
+ * for another conn upcall, which will deadlock.
+ * - rdma_disconnect is unneeded, the underlying
+ * connection is already gone.
+ */
+ if (ia->ri_id->qp) {
+ ib_drain_qp(ia->ri_id->qp);
+ rdma_destroy_qp(ia->ri_id);
+ ia->ri_id->qp = NULL;
+ }
+ ib_free_cq(ep->rep_attr.recv_cq);
+ ib_free_cq(ep->rep_attr.send_cq);
+
+ /* The ULP is responsible for ensuring all DMA
+ * mappings and MRs are gone.
+ */
+ list_for_each_entry(rep, &buf->rb_recv_bufs, rr_list)
+ rpcrdma_dma_unmap_regbuf(rep->rr_rdmabuf);
+ list_for_each_entry(req, &buf->rb_allreqs, rl_all) {
+ rpcrdma_dma_unmap_regbuf(req->rl_rdmabuf);
+ rpcrdma_dma_unmap_regbuf(req->rl_sendbuf);
+ rpcrdma_dma_unmap_regbuf(req->rl_recvbuf);
+ }
+ rpcrdma_destroy_mrs(buf);
+
+ /* Allow waiters to continue */
+ complete(&ia->ri_remove_done);
+}
+
+/**
+ * rpcrdma_ia_close - Clean up/close an IA.
+ * @ia: interface adapter to close
+ *
*/
void
rpcrdma_ia_close(struct rpcrdma_ia *ia)
if (ia->ri_id != NULL && !IS_ERR(ia->ri_id)) {
if (ia->ri_id->qp)
rdma_destroy_qp(ia->ri_id);
- rpcrdma_destroy_id(ia->ri_id);
- ia->ri_id = NULL;
+ rdma_destroy_id(ia->ri_id);
}
+ ia->ri_id = NULL;
+ ia->ri_device = NULL;
/* If the pd is still busy, xprtrdma missed freeing a resource */
if (ia->ri_pd && !IS_ERR(ia->ri_pd))
ib_dealloc_pd(ia->ri_pd);
+ ia->ri_pd = NULL;
}
/*
ib_free_cq(ep->rep_attr.send_cq);
}
+/* Re-establish a connection after a device removal event.
+ * Unlike a normal reconnection, a fresh PD and a new set
+ * of MRs and buffers is needed.
+ */
+static int
+rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt,
+ struct rpcrdma_ep *ep, struct rpcrdma_ia *ia)
+{
+ struct sockaddr *sap = (struct sockaddr *)&r_xprt->rx_data.addr;
+ int rc, err;
+
+ pr_info("%s: r_xprt = %p\n", __func__, r_xprt);
+
+ rc = -EHOSTUNREACH;
+ if (rpcrdma_ia_open(r_xprt, sap))
+ goto out1;
+
+ rc = -ENOMEM;
+ err = rpcrdma_ep_create(ep, ia, &r_xprt->rx_data);
+ if (err) {
+ pr_err("rpcrdma: rpcrdma_ep_create returned %d\n", err);
+ goto out2;
+ }
+
+ rc = -ENETUNREACH;
+ err = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr);
+ if (err) {
+ pr_err("rpcrdma: rdma_create_qp returned %d\n", err);
+ goto out3;
+ }
+
+ rpcrdma_create_mrs(r_xprt);
+ return 0;
+
+out3:
+ rpcrdma_ep_destroy(ep, ia);
+out2:
+ rpcrdma_ia_close(ia);
+out1:
+ return rc;
+}
+
+static int
+rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rpcrdma_ep *ep,
+ struct rpcrdma_ia *ia)
+{
+ struct sockaddr *sap = (struct sockaddr *)&r_xprt->rx_data.addr;
+ struct rdma_cm_id *id, *old;
+ int err, rc;
+
+ dprintk("RPC: %s: reconnecting...\n", __func__);
+
+ rpcrdma_ep_disconnect(ep, ia);
+
+ rc = -EHOSTUNREACH;
+ id = rpcrdma_create_id(r_xprt, ia, sap);
+ if (IS_ERR(id))
+ goto out;
+
+ /* As long as the new ID points to the same device as the
+ * old ID, we can reuse the transport's existing PD and all
+ * previously allocated MRs. Also, the same device means
+ * the transport's previous DMA mappings are still valid.
+ *
+ * This is a sanity check only. There should be no way these
+ * point to two different devices here.
+ */
+ old = id;
+ rc = -ENETUNREACH;
+ if (ia->ri_device != id->device) {
+ pr_err("rpcrdma: can't reconnect on different device!\n");
+ goto out_destroy;
+ }
+
+ err = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr);
+ if (err) {
+ dprintk("RPC: %s: rdma_create_qp returned %d\n",
+ __func__, err);
+ goto out_destroy;
+ }
+
+ /* Atomically replace the transport's ID and QP. */
+ rc = 0;
+ old = ia->ri_id;
+ ia->ri_id = id;
+ rdma_destroy_qp(old);
+
+out_destroy:
+ rdma_destroy_id(old);
+out:
+ return rc;
+}
+
/*
* Connect unconnected endpoint.
*/
{
struct rpcrdma_xprt *r_xprt = container_of(ia, struct rpcrdma_xprt,
rx_ia);
- struct rdma_cm_id *id, *old;
- struct sockaddr *sap;
unsigned int extras;
- int rc = 0;
+ int rc;
- if (ep->rep_connected != 0) {
retry:
- dprintk("RPC: %s: reconnecting...\n", __func__);
-
- rpcrdma_ep_disconnect(ep, ia);
-
- sap = (struct sockaddr *)&r_xprt->rx_data.addr;
- id = rpcrdma_create_id(r_xprt, ia, sap);
- if (IS_ERR(id)) {
- rc = -EHOSTUNREACH;
- goto out;
- }
- /* TEMP TEMP TEMP - fail if new device:
- * Deregister/remarshal *all* requests!
- * Close and recreate adapter, pd, etc!
- * Re-determine all attributes still sane!
- * More stuff I haven't thought of!
- * Rrrgh!
- */
- if (ia->ri_device != id->device) {
- printk("RPC: %s: can't reconnect on "
- "different device!\n", __func__);
- rpcrdma_destroy_id(id);
- rc = -ENETUNREACH;
- goto out;
- }
- /* END TEMP */
- rc = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr);
- if (rc) {
- dprintk("RPC: %s: rdma_create_qp failed %i\n",
- __func__, rc);
- rpcrdma_destroy_id(id);
- rc = -ENETUNREACH;
- goto out;
- }
-
- old = ia->ri_id;
- ia->ri_id = id;
-
- rdma_destroy_qp(old);
- rpcrdma_destroy_id(old);
- } else {
+ switch (ep->rep_connected) {
+ case 0:
dprintk("RPC: %s: connecting...\n", __func__);
rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr);
if (rc) {
dprintk("RPC: %s: rdma_create_qp failed %i\n",
__func__, rc);
- /* do not update ep->rep_connected */
- return -ENETUNREACH;
+ rc = -ENETUNREACH;
+ goto out_noupdate;
}
+ break;
+ case -ENODEV:
+ rc = rpcrdma_ep_recreate_xprt(r_xprt, ep, ia);
+ if (rc)
+ goto out_noupdate;
+ break;
+ default:
+ rc = rpcrdma_ep_reconnect(r_xprt, ep, ia);
+ if (rc)
+ goto out;
}
ep->rep_connected = 0;
out:
if (rc)
ep->rep_connected = rc;
+
+out_noupdate:
return rc;
}
rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt)
{
struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
- struct rpcrdma_ia *ia = &r_xprt->rx_ia;
struct rpcrdma_rep *rep;
int rc;
goto out_free;
}
- rep->rr_device = ia->ri_device;
rep->rr_cqe.done = rpcrdma_wc_receive;
rep->rr_rxprt = r_xprt;
INIT_WORK(&rep->rr_work, rpcrdma_reply_handler);
rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
{
cancel_delayed_work_sync(&buf->rb_recovery_worker);
+ cancel_delayed_work_sync(&buf->rb_refresh_worker);
while (!list_empty(&buf->rb_recv_bufs)) {
struct rpcrdma_rep *rep;
out_nomws:
dprintk("RPC: %s: no MWs available\n", __func__);
- schedule_delayed_work(&buf->rb_refresh_worker, 0);
+ if (r_xprt->rx_ep.rep_connected != -ENODEV)
+ schedule_delayed_work(&buf->rb_refresh_worker, 0);
/* Allow the reply handler and refresh worker to run */
cond_resched();
bool
__rpcrdma_dma_map_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb)
{
+ struct ib_device *device = ia->ri_device;
+
if (rb->rg_direction == DMA_NONE)
return false;
- rb->rg_iov.addr = ib_dma_map_single(ia->ri_device,
+ rb->rg_iov.addr = ib_dma_map_single(device,
(void *)rb->rg_base,
rdmab_length(rb),
rb->rg_direction);
- if (ib_dma_mapping_error(ia->ri_device, rdmab_addr(rb)))
+ if (ib_dma_mapping_error(device, rdmab_addr(rb)))
return false;
- rb->rg_device = ia->ri_device;
+ rb->rg_device = device;
rb->rg_iov.lkey = ia->ri_pd->local_dma_lkey;
return true;
}
struct rdma_cm_id *ri_id;
struct ib_pd *ri_pd;
struct completion ri_done;
+ struct completion ri_remove_done;
int ri_async_rc;
unsigned int ri_max_segs;
unsigned int ri_max_frmr_depth;
bool ri_reminv_expected;
bool ri_implicit_roundup;
enum ib_mr_type ri_mrtype;
+ unsigned long ri_flags;
struct ib_qp_attr ri_qp_attr;
struct ib_qp_init_attr ri_qp_init_attr;
};
+enum {
+ RPCRDMA_IAF_REMOVING = 0,
+};
+
/*
* RDMA Endpoint -- one per transport instance
*/
return (struct rpcrdma_msg *)rb->rg_base;
}
+static inline struct ib_device *
+rdmab_device(struct rpcrdma_regbuf *rb)
+{
+ return rb->rg_device;
+}
+
#define RPCRDMA_DEF_GFP (GFP_NOIO | __GFP_NOWARN)
/* To ensure a transport can always make forward progress,
unsigned int rr_len;
int rr_wc_flags;
u32 rr_inv_rkey;
- struct ib_device *rr_device;
struct rpcrdma_xprt *rr_rxprt;
struct work_struct rr_work;
struct list_head rr_list;
spinlock_t rb_mwlock; /* protect rb_mws list */
struct list_head rb_mws;
struct list_head rb_all;
- char *rb_pool;
spinlock_t rb_lock; /* protect buf lists */
int rb_send_count, rb_recv_count;
* Default is 0, see sysctl entry and rpc_rdma.c rpcrdma_convert_iovs() */
extern int xprt_rdma_pad_optimize;
+/* This setting controls the hunt for a supported memory
+ * registration strategy.
+ */
+extern unsigned int xprt_rdma_memreg_strategy;
+
/*
* Interface Adapter calls - xprtrdma/verbs.c
*/
-int rpcrdma_ia_open(struct rpcrdma_xprt *, struct sockaddr *, int);
+int rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr);
+void rpcrdma_ia_remove(struct rpcrdma_ia *ia);
void rpcrdma_ia_close(struct rpcrdma_ia *);
bool frwr_is_supported(struct rpcrdma_ia *);
bool fmr_is_supported(struct rpcrdma_ia *);
vsock->vdev = vdev;
- ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX,
- vsock->vqs, callbacks, names,
- NULL);
+ ret = virtio_find_vqs(vsock->vdev, VSOCK_VQ_MAX,
+ vsock->vqs, callbacks, names,
+ NULL);
if (ret < 0)
goto out;
nla_data(info->attrs[NL80211_ATTR_MU_MIMO_GROUP_DATA]);
/* bits 0 and 63 are reserved and must be zero */
- if ((mumimo_groups[0] & BIT(7)) ||
- (mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN - 1] & BIT(0)))
+ if ((mumimo_groups[0] & BIT(0)) ||
+ (mumimo_groups[VHT_MUMIMO_GROUPS_DATA_LEN - 1] & BIT(7)))
return -EINVAL;
params->vht_mumimo_groups = mumimo_groups;
# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
cc-option = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
# cc-option-yn
# Usage: flag := $(call cc-option-yn,-march=winchip-c6)
cc-option-yn = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
+ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
# cc-option-align
# Prefix align with either -falign or -malign
# cc-disable-warning
# Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable)
cc-disable-warning = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
# cc-name
# Expands to either gcc or clang
$(obj)/%.symtypes : $(src)/%.c FORCE
$(call cmd,cc_symtypes_c)
+# LLVM assembly
+# Generate .ll files from .c
+quiet_cmd_cc_ll_c = CC $(quiet_modtag) $@
+ cmd_cc_ll_c = $(CC) $(c_flags) -emit-llvm -S -o $@ $<
+
+$(obj)/%.ll: $(src)/%.c FORCE
+ $(call if_changed_dep,cc_ll_c)
+
# C (.c) files
# The C file is compiled and updated dependency information is generated.
# (See cmd_cc_o_c + relevant part of rule_cc_o_c)
$(call echo-cmd,checksrc) $(cmd_checksrc) \
$(call cmd_and_fixdep,cc_o_c) \
$(cmd_modversions_c) \
- $(cmd_objtool) \
+ $(call echo-cmd,objtool) $(cmd_objtool) \
$(call echo-cmd,record_mcount) $(cmd_record_mcount)
endef
define rule_as_o_S
$(call cmd_and_fixdep,as_o_S) \
$(cmd_modversions_S) \
- $(cmd_objtool)
+ $(call echo-cmd,objtool) $(cmd_objtool)
endef
# List module undefined symbols (or empty line if not enabled)
include scripts/Kbuild.include
include $(src)/Makefile
-PHONY += __dtbs_install_prep
-__dtbs_install_prep:
-ifeq ("$(dtbinst-root)", "$(obj)")
- $(Q)mkdir -p $(INSTALL_DTBS_PATH)
-endif
-
dtbinst-files := $(dtb-y)
dtbinst-dirs := $(dts-dirs)
install-dir = $(patsubst $(dtbinst-root)%,$(INSTALL_DTBS_PATH)%,$(obj))
-$(dtbinst-files) $(dtbinst-dirs): | __dtbs_install_prep
-
$(dtbinst-files): %.dtb: $(obj)/%.dtb
$(call cmd,dtb_install,$(install-dir))
KBUILD_CFLAGS += $(call cc-disable-warning, initializer-overrides)
KBUILD_CFLAGS += $(call cc-disable-warning, unused-value)
KBUILD_CFLAGS += $(call cc-disable-warning, format)
-KBUILD_CFLAGS += $(call cc-disable-warning, unknown-warning-option)
KBUILD_CFLAGS += $(call cc-disable-warning, sign-compare)
KBUILD_CFLAGS += $(call cc-disable-warning, format-zero-length)
KBUILD_CFLAGS += $(call cc-disable-warning, uninitialized)
# ==========================================================================
# Installing headers
#
-# header-y - list files to be installed. They are preprocessed
-# to remove __KERNEL__ section of the file
-# genhdr-y - Same as header-y but in a generated/ directory
+# All headers under include/uapi, include/generated/uapi,
+# arch/<arch>/include/uapi and arch/<arch>/include/generated/uapi are
+# exported.
+# They are preprocessed to remove __KERNEL__ section of the file.
#
# ==========================================================================
# generated header directory
gen := $(if $(gen),$(gen),$(subst include/,include/generated/,$(obj)))
+# Kbuild file is optional
kbuild-file := $(srctree)/$(obj)/Kbuild
-include $(kbuild-file)
+-include $(kbuild-file)
# called may set destination dir (when installing to asm/)
-_dst := $(if $(destination-y),$(destination-y),$(if $(dst),$(dst),$(obj)))
+_dst := $(if $(dst),$(dst),$(obj))
old-kbuild-file := $(srctree)/$(subst uapi/,,$(obj))/Kbuild
ifneq ($(wildcard $(old-kbuild-file)),)
installdir := $(INSTALL_HDR_PATH)/$(subst uapi/,,$(_dst))
-header-y := $(sort $(header-y))
-subdirs := $(patsubst %/,%,$(filter %/, $(header-y)))
-header-y := $(filter-out %/, $(header-y))
+srcdir := $(srctree)/$(obj)
+gendir := $(objtree)/$(gen)
+subdirs := $(patsubst $(srcdir)/%/.,%,$(wildcard $(srcdir)/*/.))
+header-files := $(notdir $(wildcard $(srcdir)/*.h))
+header-files += $(notdir $(wildcard $(srcdir)/*.agh))
+header-files := $(filter-out $(no-export-headers), $(header-files))
+genhdr-files := $(notdir $(wildcard $(gendir)/*.h))
+genhdr-files := $(filter-out $(header-files), $(genhdr-files))
# files used to track state of install/check
install-file := $(installdir)/.install
# generic-y list all files an architecture uses from asm-generic
# Use this to build a list of headers which require a wrapper
-wrapper-files := $(filter $(header-y), $(generic-y))
-
-srcdir := $(srctree)/$(obj)
-gendir := $(objtree)/$(gen)
-
-oldsrcdir := $(srctree)/$(subst /uapi,,$(obj))
+generic-files := $(notdir $(wildcard $(srctree)/include/uapi/asm-generic/*.h))
+wrapper-files := $(filter $(generic-files), $(generic-y))
+wrapper-files := $(filter-out $(header-files), $(wrapper-files))
# all headers files for this dir
-header-y := $(filter-out $(generic-y), $(header-y))
-all-files := $(header-y) $(genhdr-y) $(wrapper-files)
+all-files := $(header-files) $(genhdr-files) $(wrapper-files)
output-files := $(addprefix $(installdir)/, $(all-files))
-input-files1 := $(foreach hdr, $(header-y), \
- $(if $(wildcard $(srcdir)/$(hdr)), \
- $(wildcard $(srcdir)/$(hdr))) \
- )
-input-files1-name := $(notdir $(input-files1))
-input-files2 := $(foreach hdr, $(header-y), \
- $(if $(wildcard $(srcdir)/$(hdr)),, \
- $(if $(wildcard $(oldsrcdir)/$(hdr)), \
- $(wildcard $(oldsrcdir)/$(hdr)), \
- $(error Missing UAPI file $(srcdir)/$(hdr))) \
- ))
-input-files2-name := $(notdir $(input-files2))
-input-files3 := $(foreach hdr, $(genhdr-y), \
- $(if $(wildcard $(gendir)/$(hdr)), \
- $(wildcard $(gendir)/$(hdr)), \
- $(error Missing generated UAPI file $(gendir)/$(hdr)) \
- ))
-input-files3-name := $(notdir $(input-files3))
+ifneq ($(mandatory-y),)
+missing := $(filter-out $(all-files),$(mandatory-y))
+ifneq ($(missing),)
+$(error Some mandatory headers ($(missing)) are missing in $(obj))
+endif
+endif
# Work out what needs to be removed
oldheaders := $(patsubst $(installdir)/%,%,$(wildcard $(installdir)/*.h))
quiet_cmd_install = INSTALL $(printdir) ($(words $(all-files))\
file$(if $(word 2, $(all-files)),s))
cmd_install = \
- $(CONFIG_SHELL) $< $(installdir) $(srcdir) $(input-files1-name); \
- $(CONFIG_SHELL) $< $(installdir) $(oldsrcdir) $(input-files2-name); \
- $(CONFIG_SHELL) $< $(installdir) $(gendir) $(input-files3-name); \
+ $(CONFIG_SHELL) $< $(installdir) $(srcdir) $(header-files); \
+ $(CONFIG_SHELL) $< $(installdir) $(gendir) $(genhdr-files); \
for F in $(wrapper-files); do \
echo "\#include <asm-generic/$$F>" > $(installdir)/$$F; \
done; \
@:
targets += $(install-file)
-$(install-file): scripts/headers_install.sh $(input-files1) $(input-files2) $(input-files3) FORCE
+$(install-file): scripts/headers_install.sh \
+ $(addprefix $(srcdir)/,$(header-files)) \
+ $(addprefix $(gendir)/,$(genhdr-files)) FORCE
$(if $(unwanted),$(call cmd,remove),)
$(if $(wildcard $(dir $@)),,$(shell mkdir -p $(dir $@)))
$(call if_changed,install)
cmd_xzmisc = (cat $(filter-out FORCE,$^) | \
xz --check=crc32 --lzma2=dict=1MiB) > $@ || \
(rm -f $@ ; false)
+
+# ASM offsets
+# ---------------------------------------------------------------------------
+
+# Default sed regexp - multiline due to syntax constraints
+#
+# Use [:space:] because LLVM's integrated assembler inserts <tab> around
+# the .ascii directive whereas GCC keeps the <space> as-is.
+define sed-offsets
+ 's:^[[:space:]]*\.ascii[[:space:]]*"\(.*\)".*:\1:; \
+ /^->/{s:->#\(.*\):/* \1 */:; \
+ s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
+ s:->::; p;}'
+endef
+
+# Use filechk to avoid rebuilds when a header changes, but the resulting file
+# does not
+define filechk_offsets
+ (set -e; \
+ echo "#ifndef $2"; \
+ echo "#define $2"; \
+ echo "/*"; \
+ echo " * DO NOT MODIFY."; \
+ echo " *"; \
+ echo " * This file was generated by Kbuild"; \
+ echo " */"; \
+ echo ""; \
+ sed -ne $(sed-offsets); \
+ echo ""; \
+ echo "#endif" )
+endef
/* YYFINAL -- State number of the termination state. */
#define YYFINAL 4
/* YYLAST -- Last index in YYTABLE. */
-#define YYLAST 524
+#define YYLAST 522
/* YYNTOKENS -- Number of terminals. */
#define YYNTOKENS 55
/* YYNNTS -- Number of nonterminals. */
#define YYNNTS 49
/* YYNRULES -- Number of rules. */
-#define YYNRULES 134
+#define YYNRULES 133
/* YYNRULES -- Number of states. */
-#define YYNSTATES 189
+#define YYNSTATES 187
/* YYTRANSLATE(YYLEX) -- Bison symbol number corresponding to YYLEX. */
#define YYUNDEFTOK 2
97, 101, 105, 109, 112, 115, 118, 120, 122, 124,
126, 128, 130, 132, 134, 136, 138, 140, 142, 145,
146, 148, 150, 153, 155, 157, 159, 161, 164, 166,
- 168, 170, 175, 180, 183, 187, 191, 194, 196, 198,
- 200, 205, 210, 213, 217, 221, 224, 226, 230, 231,
- 233, 235, 239, 242, 245, 247, 248, 250, 252, 257,
- 262, 265, 269, 273, 277, 278, 280, 283, 287, 291,
- 292, 294, 296, 299, 303, 306, 307, 309, 311, 315,
- 318, 321, 323, 326, 327, 330, 334, 339, 341, 345,
- 347, 351, 354, 355, 357
+ 168, 170, 175, 180, 183, 187, 190, 192, 194, 196,
+ 201, 206, 209, 213, 217, 220, 222, 226, 227, 229,
+ 231, 235, 238, 241, 243, 244, 246, 248, 253, 258,
+ 261, 265, 269, 273, 274, 276, 279, 283, 287, 288,
+ 290, 292, 295, 299, 302, 303, 305, 307, 311, 314,
+ 317, 319, 322, 323, 326, 330, 335, 337, 341, 343,
+ 347, 350, 351, 353
};
/* YYRHS -- A `-1'-separated list of the rules' RHS. */
74, 75, -1, 8, -1, 27, -1, 32, -1, 18,
-1, 72, 76, -1, 77, -1, 39, -1, 43, -1,
77, 49, 80, 50, -1, 77, 49, 1, 50, -1,
- 77, 35, -1, 49, 76, 50, -1, 49, 1, 50,
- -1, 72, 78, -1, 79, -1, 39, -1, 43, -1,
- 79, 49, 80, 50, -1, 79, 49, 1, 50, -1,
- 79, 35, -1, 49, 78, 50, -1, 49, 1, 50,
- -1, 81, 38, -1, 81, -1, 82, 48, 38, -1,
- -1, 82, -1, 83, -1, 82, 48, 83, -1, 67,
- 84, -1, 72, 84, -1, 85, -1, -1, 39, -1,
- 43, -1, 85, 49, 80, 50, -1, 85, 49, 1,
- 50, -1, 85, 35, -1, 49, 84, 50, -1, 49,
- 1, 50, -1, 66, 76, 34, -1, -1, 88, -1,
- 52, 36, -1, 53, 90, 47, -1, 53, 1, 47,
- -1, -1, 91, -1, 92, -1, 91, 92, -1, 66,
- 93, 46, -1, 1, 46, -1, -1, 94, -1, 95,
- -1, 94, 48, 95, -1, 78, 97, -1, 39, 96,
- -1, 96, -1, 54, 36, -1, -1, 97, 32, -1,
- 53, 99, 47, -1, 53, 99, 48, 47, -1, 100,
- -1, 99, 48, 100, -1, 39, -1, 39, 52, 36,
- -1, 31, 46, -1, -1, 31, -1, 30, 49, 39,
- 50, 46, -1
+ 77, 35, -1, 49, 76, 50, -1, 72, 78, -1,
+ 79, -1, 39, -1, 43, -1, 79, 49, 80, 50,
+ -1, 79, 49, 1, 50, -1, 79, 35, -1, 49,
+ 78, 50, -1, 49, 1, 50, -1, 81, 38, -1,
+ 81, -1, 82, 48, 38, -1, -1, 82, -1, 83,
+ -1, 82, 48, 83, -1, 67, 84, -1, 72, 84,
+ -1, 85, -1, -1, 39, -1, 43, -1, 85, 49,
+ 80, 50, -1, 85, 49, 1, 50, -1, 85, 35,
+ -1, 49, 84, 50, -1, 49, 1, 50, -1, 66,
+ 76, 34, -1, -1, 88, -1, 52, 36, -1, 53,
+ 90, 47, -1, 53, 1, 47, -1, -1, 91, -1,
+ 92, -1, 91, 92, -1, 66, 93, 46, -1, 1,
+ 46, -1, -1, 94, -1, 95, -1, 94, 48, 95,
+ -1, 78, 97, -1, 39, 96, -1, 96, -1, 54,
+ 36, -1, -1, 97, 32, -1, 53, 99, 47, -1,
+ 53, 99, 48, 47, -1, 100, -1, 99, 48, 100,
+ -1, 39, -1, 39, 52, 36, -1, 31, 46, -1,
+ -1, 31, -1, 30, 49, 39, 50, 46, -1
};
/* YYRLINE[YYN] -- source line where rule number YYN was defined. */
238, 240, 242, 247, 250, 251, 255, 256, 257, 258,
259, 260, 261, 262, 263, 264, 265, 266, 270, 275,
276, 280, 281, 285, 285, 285, 286, 294, 295, 299,
- 308, 317, 319, 321, 323, 325, 332, 333, 337, 338,
- 339, 341, 343, 345, 347, 352, 353, 354, 358, 359,
- 363, 364, 369, 374, 376, 380, 381, 389, 393, 395,
- 397, 399, 401, 406, 415, 416, 421, 426, 427, 431,
- 432, 436, 437, 441, 443, 448, 449, 453, 454, 458,
- 459, 460, 464, 468, 469, 473, 474, 478, 479, 482,
- 487, 495, 499, 500, 504
+ 308, 317, 319, 321, 323, 330, 331, 335, 336, 337,
+ 339, 341, 343, 345, 350, 351, 352, 356, 357, 361,
+ 362, 367, 372, 374, 378, 379, 387, 391, 393, 395,
+ 397, 399, 404, 413, 414, 419, 424, 425, 429, 430,
+ 434, 435, 439, 441, 446, 447, 451, 452, 456, 457,
+ 458, 462, 466, 467, 471, 472, 476, 477, 480, 485,
+ 493, 497, 498, 502
};
#endif
70, 70, 70, 70, 70, 70, 71, 71, 71, 71,
71, 71, 71, 71, 71, 71, 71, 71, 72, 73,
73, 74, 74, 75, 75, 75, 75, 76, 76, 77,
- 77, 77, 77, 77, 77, 77, 78, 78, 79, 79,
- 79, 79, 79, 79, 79, 80, 80, 80, 81, 81,
- 82, 82, 83, 84, 84, 85, 85, 85, 85, 85,
- 85, 85, 85, 86, 87, 87, 88, 89, 89, 90,
- 90, 91, 91, 92, 92, 93, 93, 94, 94, 95,
- 95, 95, 96, 97, 97, 98, 98, 99, 99, 100,
- 100, 101, 102, 102, 103
+ 77, 77, 77, 77, 77, 78, 78, 79, 79, 79,
+ 79, 79, 79, 79, 80, 80, 80, 81, 81, 82,
+ 82, 83, 84, 84, 85, 85, 85, 85, 85, 85,
+ 85, 85, 86, 87, 87, 88, 89, 89, 90, 90,
+ 91, 91, 92, 92, 93, 93, 94, 94, 95, 95,
+ 95, 96, 97, 97, 98, 98, 99, 99, 100, 100,
+ 101, 102, 102, 103
};
/* YYR2[YYN] -- Number of symbols composing right hand side of rule YYN. */
3, 3, 3, 2, 2, 2, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 2, 0,
1, 1, 2, 1, 1, 1, 1, 2, 1, 1,
- 1, 4, 4, 2, 3, 3, 2, 1, 1, 1,
- 4, 4, 2, 3, 3, 2, 1, 3, 0, 1,
- 1, 3, 2, 2, 1, 0, 1, 1, 4, 4,
- 2, 3, 3, 3, 0, 1, 2, 3, 3, 0,
- 1, 1, 2, 3, 2, 0, 1, 1, 3, 2,
- 2, 1, 2, 0, 2, 3, 4, 1, 3, 1,
- 3, 2, 0, 1, 5
+ 1, 4, 4, 2, 3, 2, 1, 1, 1, 4,
+ 4, 2, 3, 3, 2, 1, 3, 0, 1, 1,
+ 3, 2, 2, 1, 0, 1, 1, 4, 4, 2,
+ 3, 3, 3, 0, 1, 2, 3, 3, 0, 1,
+ 1, 2, 3, 2, 0, 1, 1, 3, 2, 2,
+ 1, 2, 0, 2, 3, 4, 1, 3, 1, 3,
+ 2, 0, 1, 5
};
/* YYDEFACT[STATE-NAME] -- Default reduction number in state STATE-NUM.
0, 56, 0, 0, 65, 36, 57, 5, 10, 17,
23, 24, 26, 27, 33, 34, 11, 12, 13, 14,
15, 39, 0, 43, 6, 37, 0, 44, 22, 38,
- 45, 0, 0, 131, 69, 70, 0, 59, 0, 18,
- 19, 0, 132, 68, 25, 42, 129, 0, 127, 22,
- 40, 0, 115, 0, 0, 111, 9, 17, 41, 95,
- 0, 0, 0, 0, 58, 60, 61, 16, 0, 67,
- 133, 103, 123, 73, 0, 0, 125, 0, 7, 114,
- 108, 78, 79, 0, 0, 0, 123, 77, 0, 116,
- 117, 121, 107, 0, 112, 132, 96, 57, 0, 95,
- 92, 94, 35, 0, 75, 74, 62, 20, 104, 0,
- 0, 86, 89, 90, 130, 126, 128, 120, 0, 78,
- 0, 122, 76, 119, 82, 0, 113, 0, 0, 97,
- 0, 93, 100, 0, 134, 124, 0, 21, 105, 72,
- 71, 85, 0, 84, 83, 0, 0, 118, 102, 101,
- 0, 0, 106, 87, 91, 81, 80, 99, 98
+ 45, 0, 0, 130, 69, 70, 0, 59, 0, 18,
+ 19, 0, 131, 68, 25, 42, 128, 0, 126, 22,
+ 40, 0, 114, 0, 0, 110, 9, 17, 41, 94,
+ 0, 0, 0, 58, 60, 61, 16, 0, 67, 132,
+ 102, 122, 73, 0, 0, 124, 0, 7, 113, 107,
+ 77, 78, 0, 0, 0, 122, 76, 0, 115, 116,
+ 120, 106, 0, 111, 131, 95, 57, 0, 94, 91,
+ 93, 35, 0, 74, 62, 20, 103, 0, 0, 85,
+ 88, 89, 129, 125, 127, 119, 0, 77, 0, 121,
+ 75, 118, 81, 0, 112, 0, 0, 96, 0, 92,
+ 99, 0, 133, 123, 0, 21, 104, 72, 71, 84,
+ 0, 83, 82, 0, 0, 117, 101, 100, 0, 0,
+ 105, 86, 90, 80, 79, 98, 97
};
/* YYDEFGOTO[NTERM-NUM]. */
static const yytype_int16 yydefgoto[] =
{
-1, 1, 2, 3, 37, 79, 58, 38, 68, 69,
- 70, 82, 40, 41, 42, 43, 44, 71, 94, 95,
- 45, 125, 73, 116, 117, 140, 141, 142, 143, 130,
- 131, 46, 167, 168, 57, 83, 84, 85, 118, 119,
- 120, 121, 138, 53, 77, 78, 47, 102, 48
+ 70, 82, 40, 41, 42, 43, 44, 71, 93, 94,
+ 45, 124, 73, 115, 116, 138, 139, 140, 141, 129,
+ 130, 46, 165, 166, 57, 83, 84, 85, 117, 118,
+ 119, 120, 136, 53, 77, 78, 47, 101, 48
};
/* YYPACT[STATE-NUM] -- Index in YYTABLE of the portion describing
STATE-NUM. */
-#define YYPACT_NINF -111
+#define YYPACT_NINF -94
static const yytype_int16 yypact[] =
{
- -111, 13, -111, 210, -111, -111, 28, -111, -111, -111,
- -111, -111, -27, -111, 44, -111, -111, -111, -111, -111,
- -111, -111, -111, -111, -24, -111, -20, -111, -111, -111,
- 31, -111, 32, 42, -111, -111, -111, -111, -111, 34,
- 481, -111, -111, -111, -111, -111, -111, -111, -111, -111,
- -111, 51, 56, -111, -111, 52, 108, -111, 481, 52,
- -111, 481, 58, -111, -111, -111, 19, 0, 54, 55,
- -111, 34, 30, -18, -111, -111, 68, -25, -111, 481,
- -111, 45, 33, 59, 159, -111, -111, 34, -111, 395,
- 57, 60, 81, 88, -111, 0, -111, -111, 34, -111,
- -111, -111, -111, -111, 257, 72, -111, -23, -111, -111,
- -111, 85, -111, 20, 106, 47, -111, -10, 97, 96,
- -111, -111, -111, 99, -111, 115, -111, -111, 5, 50,
- -111, 11, -111, 102, -111, -111, -111, -111, -22, 100,
- 103, 111, 104, -111, -111, -111, -111, -111, 113, -111,
- 121, -111, -111, 124, -111, 303, -111, 33, 132, -111,
- 139, -111, -111, 349, -111, -111, 122, -111, -111, -111,
- -111, -111, 442, -111, -111, 140, 143, -111, -111, -111,
- 144, 145, -111, -111, -111, -111, -111, -111, -111
+ -94, 15, -94, 208, -94, -94, 34, -94, -94, -94,
+ -94, -94, -27, -94, -5, -94, -94, -94, -94, -94,
+ -94, -94, -94, -94, -25, -94, -16, -94, -94, -94,
+ -4, -94, 19, -24, -94, -94, -94, -94, -94, 24,
+ 479, -94, -94, -94, -94, -94, -94, -94, -94, -94,
+ -94, 29, 48, -94, -94, 37, 106, -94, 479, 37,
+ -94, 479, 54, -94, -94, -94, 24, -2, 49, 53,
+ -94, 24, -14, -11, -94, -94, 47, 38, -94, 479,
+ -94, 51, 23, 55, 157, -94, -94, 24, -94, 393,
+ 56, 58, 68, -94, -2, -94, -94, 24, -94, -94,
+ -94, -94, -94, 255, 67, -94, 5, -94, -94, -94,
+ 50, -94, 7, 69, 40, -94, -8, 83, 88, -94,
+ -94, -94, 91, -94, 109, -94, -94, 4, 45, -94,
+ 16, -94, 95, -94, -94, -94, -23, 92, 93, 108,
+ 96, -94, -94, -94, -94, -94, 97, -94, 98, -94,
+ -94, 118, -94, 301, -94, 23, 101, -94, 104, -94,
+ -94, 347, -94, -94, 120, -94, -94, -94, -94, -94,
+ 440, -94, -94, 111, 119, -94, -94, -94, 130, 137,
+ -94, -94, -94, -94, -94, -94, -94
};
/* YYPGOTO[NTERM-NUM]. */
static const yytype_int16 yypgoto[] =
{
- -111, -111, 160, -111, -111, -111, -111, -51, -111, -111,
- 98, -1, -61, -37, -111, -111, -111, -78, -111, -111,
- -53, -30, -111, -66, -111, -110, -111, -111, -60, -63,
- -111, -111, -111, -111, -21, -111, -111, 116, -111, -111,
- 40, 90, 83, 152, -111, 105, -111, -111, -111
+ -94, -94, 158, -94, -94, -94, -94, -45, -94, -94,
+ 94, -1, -61, -29, -94, -94, -94, -79, -94, -94,
+ -63, -7, -94, -93, -94, -92, -94, -94, -60, -57,
+ -94, -94, -94, -94, -19, -94, -94, 110, -94, -94,
+ 33, 82, 78, 144, -94, 99, -94, -94, -94
};
/* YYTABLE[YYPACT[STATE-NUM]]. What to do in state STATE-NUM. If
positive, shift that token. If negative, reduce the rule which
number is the opposite. If YYTABLE_NINF, syntax error. */
-#define YYTABLE_NINF -111
+#define YYTABLE_NINF -110
static const yytype_int16 yytable[] =
{
- 89, 90, 39, 74, 115, 60, 158, 86, 10, 72,
- 165, 129, 51, 4, 96, 55, 76, 103, 20, 59,
- 92, 148, 106, 107, 145, 154, 52, 29, 108, 56,
- 166, 104, 34, 56, 80, 115, 93, 115, 88, 155,
- -95, 99, 136, 89, 126, 176, 162, 150, 159, 152,
- 129, 129, 74, 181, 128, -95, 67, 87, 64, 149,
- 163, 100, 65, 112, 101, 160, 161, 54, 66, 113,
- 67, 67, 111, 64, 49, 50, 112, 65, 87, 115,
- 61, 62, 113, 66, 67, 67, 149, 114, 63, 126,
- 112, 109, 110, 159, 89, 76, 113, 91, 67, 128,
- 97, 67, 89, 98, 52, 56, 122, 132, 144, 81,
- 133, 89, 184, 7, 8, 9, 10, 11, 12, 13,
- 105, 15, 16, 17, 18, 19, 20, 21, 22, 23,
- 24, 134, 26, 27, 28, 29, 30, 31, 135, 114,
- 34, 35, 151, 156, 157, 109, 100, -22, 164, 171,
- 169, 36, 172, 170, -22, -109, 165, -22, 182, -22,
- 123, 5, -22, 173, 7, 8, 9, 10, 11, 12,
- 13, 174, 15, 16, 17, 18, 19, 20, 21, 22,
- 23, 24, 178, 26, 27, 28, 29, 30, 31, 179,
- 185, 34, 35, 186, 187, 188, 137, 177, -22, 153,
- 124, 147, 36, 75, 0, -22, -110, 0, -22, 0,
- -22, 6, 146, -22, 0, 7, 8, 9, 10, 11,
- 12, 13, 14, 15, 16, 17, 18, 19, 20, 21,
- 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
- 32, 33, 34, 35, 0, 0, 0, 0, 0, -22,
- 0, 0, 0, 36, 0, 0, -22, 0, 139, -22,
- 0, -22, 7, 8, 9, 10, 11, 12, 13, 0,
+ 89, 90, 39, 114, 95, 156, 10, 60, 146, 163,
+ 128, 74, 51, 86, 55, 4, 20, 99, 54, 148,
+ 100, 150, 63, 59, 102, 29, 52, 152, 56, 164,
+ 34, 134, 72, 114, 107, 114, 80, 56, 103, -94,
+ 88, 153, 89, 125, 76, 61, 147, 157, 128, 128,
+ 111, 160, 143, 127, -94, 67, 112, 87, 67, 92,
+ 74, 174, 110, 64, 98, 161, 111, 65, 62, 179,
+ 158, 159, 112, 66, 67, 67, 114, 113, 87, 147,
+ 49, 50, 52, 111, 125, 105, 106, 76, 157, 112,
+ 56, 67, 89, 91, 127, 96, 67, 108, 109, 104,
+ 89, 97, 121, 142, 113, 149, 131, 81, 132, 89,
+ 182, 7, 8, 9, 10, 11, 12, 13, 133, 15,
+ 16, 17, 18, 19, 20, 21, 22, 23, 24, 154,
+ 26, 27, 28, 29, 30, 31, 155, 108, 34, 35,
+ 99, 162, 167, 168, 170, -22, 169, 171, 172, 36,
+ 163, 176, -22, -108, 177, -22, 180, -22, 122, 5,
+ -22, 183, 7, 8, 9, 10, 11, 12, 13, 184,
+ 15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
+ 185, 26, 27, 28, 29, 30, 31, 186, 175, 34,
+ 35, 135, 145, 151, 123, 75, -22, 0, 0, 0,
+ 36, 0, 0, -22, -109, 144, -22, 0, -22, 6,
+ 0, -22, 0, 7, 8, 9, 10, 11, 12, 13,
+ 14, 15, 16, 17, 18, 19, 20, 21, 22, 23,
+ 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,
+ 34, 35, 0, 0, 0, 0, 0, -22, 0, 0,
+ 0, 36, 0, 0, -22, 0, 137, -22, 0, -22,
+ 7, 8, 9, 10, 11, 12, 13, 0, 15, 16,
+ 17, 18, 19, 20, 21, 22, 23, 24, 0, 26,
+ 27, 28, 29, 30, 31, 0, 0, 34, 35, 0,
+ 0, 0, 0, -87, 0, 0, 0, 0, 36, 0,
+ 0, 0, 173, 0, 0, -87, 7, 8, 9, 10,
+ 11, 12, 13, 0, 15, 16, 17, 18, 19, 20,
+ 21, 22, 23, 24, 0, 26, 27, 28, 29, 30,
+ 31, 0, 0, 34, 35, 0, 0, 0, 0, -87,
+ 0, 0, 0, 0, 36, 0, 0, 0, 178, 0,
+ 0, -87, 7, 8, 9, 10, 11, 12, 13, 0,
15, 16, 17, 18, 19, 20, 21, 22, 23, 24,
0, 26, 27, 28, 29, 30, 31, 0, 0, 34,
- 35, 0, 0, 0, 0, -88, 0, 0, 0, 0,
- 36, 0, 0, 0, 175, 0, 0, -88, 7, 8,
+ 35, 0, 0, 0, 0, -87, 0, 0, 0, 0,
+ 36, 0, 0, 0, 0, 0, 0, -87, 7, 8,
9, 10, 11, 12, 13, 0, 15, 16, 17, 18,
19, 20, 21, 22, 23, 24, 0, 26, 27, 28,
29, 30, 31, 0, 0, 34, 35, 0, 0, 0,
- 0, -88, 0, 0, 0, 0, 36, 0, 0, 0,
- 180, 0, 0, -88, 7, 8, 9, 10, 11, 12,
+ 0, 0, 125, 0, 0, 0, 126, 0, 0, 0,
+ 0, 0, 127, 0, 67, 7, 8, 9, 10, 11,
+ 12, 13, 0, 15, 16, 17, 18, 19, 20, 21,
+ 22, 23, 24, 0, 26, 27, 28, 29, 30, 31,
+ 0, 0, 34, 35, 0, 0, 0, 0, 181, 0,
+ 0, 0, 0, 36, 7, 8, 9, 10, 11, 12,
13, 0, 15, 16, 17, 18, 19, 20, 21, 22,
23, 24, 0, 26, 27, 28, 29, 30, 31, 0,
- 0, 34, 35, 0, 0, 0, 0, -88, 0, 0,
- 0, 0, 36, 0, 0, 0, 0, 0, 0, -88,
- 7, 8, 9, 10, 11, 12, 13, 0, 15, 16,
- 17, 18, 19, 20, 21, 22, 23, 24, 0, 26,
- 27, 28, 29, 30, 31, 0, 0, 34, 35, 0,
- 0, 0, 0, 0, 126, 0, 0, 0, 127, 0,
- 0, 0, 0, 0, 128, 0, 67, 7, 8, 9,
- 10, 11, 12, 13, 0, 15, 16, 17, 18, 19,
- 20, 21, 22, 23, 24, 0, 26, 27, 28, 29,
- 30, 31, 0, 0, 34, 35, 0, 0, 0, 0,
- 183, 0, 0, 0, 0, 36, 7, 8, 9, 10,
- 11, 12, 13, 0, 15, 16, 17, 18, 19, 20,
- 21, 22, 23, 24, 0, 26, 27, 28, 29, 30,
- 31, 0, 0, 34, 35, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 36
+ 0, 34, 35, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 36
};
#define yypact_value_is_default(Yystate) \
- (!!((Yystate) == (-111)))
+ (!!((Yystate) == (-94)))
#define yytable_value_is_error(Yytable_value) \
YYID (0)
static const yytype_int16 yycheck[] =
{
- 61, 61, 3, 40, 82, 26, 1, 58, 8, 39,
- 32, 89, 39, 0, 67, 39, 39, 35, 18, 39,
- 1, 1, 47, 48, 47, 35, 53, 27, 79, 53,
- 52, 49, 32, 53, 55, 113, 66, 115, 59, 49,
- 35, 71, 95, 104, 39, 155, 35, 113, 43, 115,
- 128, 129, 89, 163, 49, 50, 51, 58, 39, 39,
- 49, 31, 43, 43, 34, 128, 129, 23, 49, 49,
- 51, 51, 39, 39, 46, 47, 43, 43, 79, 157,
- 49, 49, 49, 49, 51, 51, 39, 54, 46, 39,
- 43, 46, 47, 43, 155, 39, 49, 39, 51, 49,
- 46, 51, 163, 48, 53, 53, 47, 50, 36, 1,
- 50, 172, 172, 5, 6, 7, 8, 9, 10, 11,
- 52, 13, 14, 15, 16, 17, 18, 19, 20, 21,
- 22, 50, 24, 25, 26, 27, 28, 29, 50, 54,
- 32, 33, 36, 46, 48, 46, 31, 39, 46, 38,
- 50, 43, 48, 50, 46, 47, 32, 49, 36, 51,
- 1, 1, 54, 50, 5, 6, 7, 8, 9, 10,
- 11, 50, 13, 14, 15, 16, 17, 18, 19, 20,
- 21, 22, 50, 24, 25, 26, 27, 28, 29, 50,
- 50, 32, 33, 50, 50, 50, 98, 157, 39, 116,
- 84, 111, 43, 51, -1, 46, 47, -1, 49, -1,
- 51, 1, 107, 54, -1, 5, 6, 7, 8, 9,
- 10, 11, 12, 13, 14, 15, 16, 17, 18, 19,
- 20, 21, 22, 23, 24, 25, 26, 27, 28, 29,
- 30, 31, 32, 33, -1, -1, -1, -1, -1, 39,
- -1, -1, -1, 43, -1, -1, 46, -1, 1, 49,
- -1, 51, 5, 6, 7, 8, 9, 10, 11, -1,
+ 61, 61, 3, 82, 67, 1, 8, 26, 1, 32,
+ 89, 40, 39, 58, 39, 0, 18, 31, 23, 112,
+ 34, 114, 46, 39, 35, 27, 53, 35, 53, 52,
+ 32, 94, 39, 112, 79, 114, 55, 53, 49, 35,
+ 59, 49, 103, 39, 39, 49, 39, 43, 127, 128,
+ 43, 35, 47, 49, 50, 51, 49, 58, 51, 66,
+ 89, 153, 39, 39, 71, 49, 43, 43, 49, 161,
+ 127, 128, 49, 49, 51, 51, 155, 54, 79, 39,
+ 46, 47, 53, 43, 39, 47, 48, 39, 43, 49,
+ 53, 51, 153, 39, 49, 46, 51, 46, 47, 52,
+ 161, 48, 47, 36, 54, 36, 50, 1, 50, 170,
+ 170, 5, 6, 7, 8, 9, 10, 11, 50, 13,
+ 14, 15, 16, 17, 18, 19, 20, 21, 22, 46,
+ 24, 25, 26, 27, 28, 29, 48, 46, 32, 33,
+ 31, 46, 50, 50, 48, 39, 38, 50, 50, 43,
+ 32, 50, 46, 47, 50, 49, 36, 51, 1, 1,
+ 54, 50, 5, 6, 7, 8, 9, 10, 11, 50,
+ 13, 14, 15, 16, 17, 18, 19, 20, 21, 22,
+ 50, 24, 25, 26, 27, 28, 29, 50, 155, 32,
+ 33, 97, 110, 115, 84, 51, 39, -1, -1, -1,
+ 43, -1, -1, 46, 47, 106, 49, -1, 51, 1,
+ -1, 54, -1, 5, 6, 7, 8, 9, 10, 11,
+ 12, 13, 14, 15, 16, 17, 18, 19, 20, 21,
+ 22, 23, 24, 25, 26, 27, 28, 29, 30, 31,
+ 32, 33, -1, -1, -1, -1, -1, 39, -1, -1,
+ -1, 43, -1, -1, 46, -1, 1, 49, -1, 51,
+ 5, 6, 7, 8, 9, 10, 11, -1, 13, 14,
+ 15, 16, 17, 18, 19, 20, 21, 22, -1, 24,
+ 25, 26, 27, 28, 29, -1, -1, 32, 33, -1,
+ -1, -1, -1, 38, -1, -1, -1, -1, 43, -1,
+ -1, -1, 1, -1, -1, 50, 5, 6, 7, 8,
+ 9, 10, 11, -1, 13, 14, 15, 16, 17, 18,
+ 19, 20, 21, 22, -1, 24, 25, 26, 27, 28,
+ 29, -1, -1, 32, 33, -1, -1, -1, -1, 38,
+ -1, -1, -1, -1, 43, -1, -1, -1, 1, -1,
+ -1, 50, 5, 6, 7, 8, 9, 10, 11, -1,
13, 14, 15, 16, 17, 18, 19, 20, 21, 22,
-1, 24, 25, 26, 27, 28, 29, -1, -1, 32,
33, -1, -1, -1, -1, 38, -1, -1, -1, -1,
- 43, -1, -1, -1, 1, -1, -1, 50, 5, 6,
+ 43, -1, -1, -1, -1, -1, -1, 50, 5, 6,
7, 8, 9, 10, 11, -1, 13, 14, 15, 16,
17, 18, 19, 20, 21, 22, -1, 24, 25, 26,
27, 28, 29, -1, -1, 32, 33, -1, -1, -1,
- -1, 38, -1, -1, -1, -1, 43, -1, -1, -1,
- 1, -1, -1, 50, 5, 6, 7, 8, 9, 10,
+ -1, -1, 39, -1, -1, -1, 43, -1, -1, -1,
+ -1, -1, 49, -1, 51, 5, 6, 7, 8, 9,
+ 10, 11, -1, 13, 14, 15, 16, 17, 18, 19,
+ 20, 21, 22, -1, 24, 25, 26, 27, 28, 29,
+ -1, -1, 32, 33, -1, -1, -1, -1, 38, -1,
+ -1, -1, -1, 43, 5, 6, 7, 8, 9, 10,
11, -1, 13, 14, 15, 16, 17, 18, 19, 20,
21, 22, -1, 24, 25, 26, 27, 28, 29, -1,
- -1, 32, 33, -1, -1, -1, -1, 38, -1, -1,
- -1, -1, 43, -1, -1, -1, -1, -1, -1, 50,
- 5, 6, 7, 8, 9, 10, 11, -1, 13, 14,
- 15, 16, 17, 18, 19, 20, 21, 22, -1, 24,
- 25, 26, 27, 28, 29, -1, -1, 32, 33, -1,
- -1, -1, -1, -1, 39, -1, -1, -1, 43, -1,
- -1, -1, -1, -1, 49, -1, 51, 5, 6, 7,
- 8, 9, 10, 11, -1, 13, 14, 15, 16, 17,
- 18, 19, 20, 21, 22, -1, 24, 25, 26, 27,
- 28, 29, -1, -1, 32, 33, -1, -1, -1, -1,
- 38, -1, -1, -1, -1, 43, 5, 6, 7, 8,
- 9, 10, 11, -1, 13, 14, 15, 16, 17, 18,
- 19, 20, 21, 22, -1, 24, 25, 26, 27, 28,
- 29, -1, -1, 32, 33, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, 43
+ -1, 32, 33, -1, -1, -1, -1, -1, -1, -1,
+ -1, -1, 43
};
/* YYSTOS[STATE-NUM] -- The (internal number of the) accessing
89, 49, 49, 46, 39, 43, 49, 51, 63, 64,
65, 72, 76, 77, 68, 98, 39, 99, 100, 60,
89, 1, 66, 90, 91, 92, 62, 66, 89, 67,
- 83, 39, 1, 76, 73, 74, 75, 46, 48, 76,
- 31, 34, 102, 35, 49, 52, 47, 48, 62, 46,
- 47, 39, 43, 49, 54, 72, 78, 79, 93, 94,
- 95, 96, 47, 1, 92, 76, 39, 43, 49, 72,
- 84, 85, 50, 50, 50, 50, 75, 65, 97, 1,
- 80, 81, 82, 83, 36, 47, 100, 96, 1, 39,
- 78, 36, 78, 97, 35, 49, 46, 48, 1, 43,
- 84, 84, 35, 49, 46, 32, 52, 87, 88, 50,
- 50, 38, 48, 50, 50, 1, 80, 95, 50, 50,
- 1, 80, 36, 38, 83, 50, 50, 50, 50
+ 83, 39, 76, 73, 74, 75, 46, 48, 76, 31,
+ 34, 102, 35, 49, 52, 47, 48, 62, 46, 47,
+ 39, 43, 49, 54, 72, 78, 79, 93, 94, 95,
+ 96, 47, 1, 92, 76, 39, 43, 49, 72, 84,
+ 85, 50, 50, 50, 75, 65, 97, 1, 80, 81,
+ 82, 83, 36, 47, 100, 96, 1, 39, 78, 36,
+ 78, 97, 35, 49, 46, 48, 1, 43, 84, 84,
+ 35, 49, 46, 32, 52, 87, 88, 50, 50, 38,
+ 48, 50, 50, 1, 80, 95, 50, 50, 1, 80,
+ 36, 38, 83, 50, 50, 50, 50
};
#define yyerrok (yyerrstatus = 0)
case 75:
- { (yyval) = (yyvsp[(3) - (3)]); }
+ { (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 76:
+ case 79:
- { (yyval) = (yyvsp[(2) - (2)]); }
+ { (yyval) = (yyvsp[(4) - (4)]); }
break;
case 80:
case 81:
- { (yyval) = (yyvsp[(4) - (4)]); }
+ { (yyval) = (yyvsp[(2) - (2)]); }
break;
case 82:
- { (yyval) = (yyvsp[(2) - (2)]); }
+ { (yyval) = (yyvsp[(3) - (3)]); }
break;
case 83:
case 84:
- { (yyval) = (yyvsp[(3) - (3)]); }
- break;
-
- case 85:
-
{ (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 87:
+ case 86:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 88:
+ case 87:
{ (yyval) = NULL; }
break;
- case 91:
+ case 90:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 92:
+ case 91:
{ (yyval) = (yyvsp[(2) - (2)]) ? (yyvsp[(2) - (2)]) : (yyvsp[(1) - (2)]); }
break;
- case 93:
+ case 92:
{ (yyval) = (yyvsp[(2) - (2)]) ? (yyvsp[(2) - (2)]) : (yyvsp[(1) - (2)]); }
break;
- case 95:
+ case 94:
{ (yyval) = NULL; }
break;
- case 96:
+ case 95:
{ /* For version 2 checksums, we don't want to remember
private parameter names. */
}
break;
- case 97:
+ case 96:
{ remove_node((yyvsp[(1) - (1)]));
(yyval) = (yyvsp[(1) - (1)]);
}
break;
- case 98:
+ case 97:
{ (yyval) = (yyvsp[(4) - (4)]); }
break;
- case 99:
+ case 98:
{ (yyval) = (yyvsp[(4) - (4)]); }
break;
- case 100:
+ case 99:
{ (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 101:
+ case 100:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 102:
+ case 101:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 103:
+ case 102:
{ struct string_list *decl = *(yyvsp[(2) - (3)]);
*(yyvsp[(2) - (3)]) = NULL;
}
break;
- case 104:
+ case 103:
{ (yyval) = NULL; }
break;
- case 106:
+ case 105:
{ remove_list((yyvsp[(2) - (2)]), &(*(yyvsp[(1) - (2)]))->next); (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 107:
+ case 106:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 108:
+ case 107:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 109:
+ case 108:
{ (yyval) = NULL; }
break;
- case 112:
+ case 111:
{ (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 113:
+ case 112:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 114:
+ case 113:
{ (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 115:
+ case 114:
{ (yyval) = NULL; }
break;
- case 118:
+ case 117:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 119:
+ case 118:
{ (yyval) = (yyvsp[(2) - (2)]) ? (yyvsp[(2) - (2)]) : (yyvsp[(1) - (2)]); }
break;
- case 120:
+ case 119:
{ (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 122:
+ case 121:
{ (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 123:
+ case 122:
{ (yyval) = NULL; }
break;
- case 125:
+ case 124:
{ (yyval) = (yyvsp[(3) - (3)]); }
break;
- case 126:
+ case 125:
{ (yyval) = (yyvsp[(4) - (4)]); }
break;
- case 129:
+ case 128:
{
const char *name = strdup((*(yyvsp[(1) - (1)]))->string);
}
break;
- case 130:
+ case 129:
{
const char *name = strdup((*(yyvsp[(1) - (3)]))->string);
}
break;
- case 131:
+ case 130:
{ (yyval) = (yyvsp[(2) - (2)]); }
break;
- case 132:
+ case 131:
{ (yyval) = NULL; }
break;
- case 134:
+ case 133:
{ export_symbol((*(yyvsp[(3) - (5)]))->string); (yyval) = (yyvsp[(5) - (5)]); }
break;
{ $$ = $2; }
| '(' declarator ')'
{ $$ = $3; }
- | '(' error ')'
- { $$ = $3; }
;
/* Nested declarators differ from regular declarators in that they do
devicetable-offsets-file := devicetable-offsets.h
-define sed-y
- "/^->/{s:->#\(.*\):/* \1 */:; \
- s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
- s:->::; p;}"
-endef
-
-quiet_cmd_offsets = GEN $@
-define cmd_offsets
- (set -e; \
- echo "#ifndef __DEVICETABLE_OFFSETS_H__"; \
- echo "#define __DEVICETABLE_OFFSETS_H__"; \
- echo "/*"; \
- echo " * DO NOT MODIFY."; \
- echo " *"; \
- echo " * This file was generated by Kbuild"; \
- echo " *"; \
- echo " */"; \
- echo ""; \
- sed -ne $(sed-y) $<; \
- echo ""; \
- echo "#endif" ) > $@
-endef
-
-$(obj)/$(devicetable-offsets-file): $(obj)/devicetable-offsets.s
- $(call if_changed,offsets)
+$(obj)/$(devicetable-offsets-file): $(obj)/devicetable-offsets.s FORCE
+ $(call filechk,offsets,__DEVICETABLE_OFFSETS_H__)
targets += $(devicetable-offsets-file) devicetable-offsets.s
do_objdump() {
dir=$(get_output_dir $1)
base=${1##*/}
+ stripped=$dir/${base%.o}.stripped
dis=$dir/${base%.o}.dis
[ ! -d "$dir" ] && mkdir -p $dir
# remove addresses for a cleaner diff
# http://dummdida.tumblr.com/post/60924060451/binary-diff-between-libc-from-scientificlinux-and
- $OBJDUMP -D $1 | sed "s/^[[:space:]]\+[0-9a-f]\+//" > $dis
+ $STRIP -g $1 -R __bug_table -R .note -R .comment -o $stripped
+ $OBJDUMP -D $stripped | sed -e "s/^[[:space:]]\+[0-9a-f]\+//" -e "s:^$stripped:$1:" > $dis
}
dorecord() {
CMT="`git rev-parse --short HEAD`"
+ STRIP="${CROSS_COMPILE}strip"
OBJDUMP="${CROSS_COMPILE}objdump"
for d in $FILES; do
echo "" >&2
echo "** ** ** WARNING ** ** **" >&2
echo "" >&2
- echo "Your architecture doesn't have it's equivalent" >&2
+ echo "Your architecture doesn't have its equivalent" >&2
echo "Debian userspace architecture defined!" >&2
echo "Falling back to using your current userspace instead!" >&2
echo "Please add support for $UTS_MACHINE to ${0} ..." >&2
cp System.map "$tmpdir/boot/System.map-$version"
cp $KCONFIG_CONFIG "$tmpdir/boot/config-$version"
fi
-# Not all arches include the boot path in KBUILD_IMAGE
-if [ -e $KBUILD_IMAGE ]; then
- cp $KBUILD_IMAGE "$tmpdir/$installed_image_path"
-else
- cp arch/$ARCH/boot/$KBUILD_IMAGE "$tmpdir/$installed_image_path"
-fi
+cp "$($MAKE -s image_name)" "$tmpdir/$installed_image_path"
if grep -q "^CONFIG_OF=y" $KCONFIG_CONFIG ; then
# Only some architectures with OF support have this target
The sources may be found at most Linux archive sites, including:
https://www.kernel.org/pub/linux/kernel
-Copyright: 1991 - 2015 Linus Torvalds and others.
+Copyright: 1991 - 2017 Linus Torvalds and others.
The git repository for mainline kernel development is at:
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Priority: optional
Maintainer: $maintainer
Build-Depends: $build_depends
-Standards-Version: 3.8.4
Homepage: http://www.kernel.org/
EOF
cat <<EOF >> debian/control
Package: $packagename
-Provides: linux-image, linux-image-2.6, linux-modules-$version
Architecture: any
Description: User Mode Linux kernel, version $version
User-mode Linux is a port of the Linux kernel to its own system call
cat <<EOF >> debian/control
Package: $packagename
-Provides: linux-image, linux-image-2.6, linux-modules-$version
Suggests: $fwpackagename
Architecture: any
Description: Linux kernel, version $version
cat <<EOF >> debian/control
Package: $kernel_headers_packagename
-Provides: linux-headers, linux-headers-2.6
Architecture: any
Description: Linux kernel headers for $KERNELRELEASE on \${kernel:debarch}
This package provides kernel header files for $KERNELRELEASE on \${kernel:debarch}
Package: $dbg_packagename
Section: debug
-Provides: linux-debug, linux-debug-$version
Architecture: any
Description: Linux kernel debugging symbols for $version
This package will come in handy if you need to debug the kernel. It provides
module_param_array(pnp, bool, NULL, 0444);
MODULE_PARM_DESC(pnp, "PnP detection for MPU-401 device.");
#endif
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for MPU-401 device.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for MPU-401 device.");
module_param_array(uart_enter, bool, NULL, 0444);
MODULE_PARM_DESC(uart_enter, "Issue UART_ENTER command at open.");
MODULE_PARM_DESC(index, "Index value for MotuMTPAV MIDI.");
module_param(id, charp, 0444);
MODULE_PARM_DESC(id, "ID string for MotuMTPAV MIDI.");
-module_param(port, long, 0444);
+module_param_hw(port, long, ioport, 0444);
MODULE_PARM_DESC(port, "Parallel port # for MotuMTPAV MIDI.");
-module_param(irq, int, 0444);
+module_param_hw(irq, int, irq, 0444);
MODULE_PARM_DESC(irq, "Parallel IRQ # for MotuMTPAV MIDI.");
module_param(hwports, int, 0444);
MODULE_PARM_DESC(hwports, "Hardware ports # for MotuMTPAV MIDI.");
MODULE_PARM_DESC(id, "ID string for Serial MIDI.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable UART16550A chip.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for UART16550A chip.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for UART16550A chip.");
module_param_array(speed, int, NULL, 0444);
MODULE_PARM_DESC(speed, "Speed in bauds.");
MODULE_PARM_DESC(id, "ID string for " CRD_NAME " soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable " CRD_NAME " soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " CRD_NAME " driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for " CRD_NAME " driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for " CRD_NAME " driver.");
module_param_array(thinkpad, bool, NULL, 0444);
MODULE_PARM_DESC(thinkpad, "Enable only for the onboard CS4248 of IBM Thinkpad 360/750/755 series.");
MODULE_PARM_DESC(id, "ID string for " CRD_NAME " soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable " CRD_NAME " soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " CRD_NAME " driver.");
static int snd_adlib_match(struct device *dev, unsigned int n)
module_param_array(id, charp, NULL, 0444);
MODULE_PARM_DESC(id, "ID string for CMI8328 soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for CMI8328 driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for CMI8328 driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 for CMI8328 driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 for CMI8328 driver.");
-module_param_array(mpuport, long, NULL, 0444);
+module_param_hw_array(mpuport, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpuport, "MPU-401 port # for CMI8328 driver.");
-module_param_array(mpuirq, int, NULL, 0444);
+module_param_hw_array(mpuirq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpuirq, "IRQ # for CMI8328 MPU-401 port.");
#ifdef SUPPORT_JOYSTICK
module_param_array(gameport, bool, NULL, 0444);
MODULE_PARM_DESC(isapnp, "PnP detection for specified soundcard.");
#endif
-module_param_array(sbport, long, NULL, 0444);
+module_param_hw_array(sbport, long, ioport, NULL, 0444);
MODULE_PARM_DESC(sbport, "Port # for CMI8330/CMI8329 SB driver.");
-module_param_array(sbirq, int, NULL, 0444);
+module_param_hw_array(sbirq, int, irq, NULL, 0444);
MODULE_PARM_DESC(sbirq, "IRQ # for CMI8330/CMI8329 SB driver.");
-module_param_array(sbdma8, int, NULL, 0444);
+module_param_hw_array(sbdma8, int, dma, NULL, 0444);
MODULE_PARM_DESC(sbdma8, "DMA8 for CMI8330/CMI8329 SB driver.");
-module_param_array(sbdma16, int, NULL, 0444);
+module_param_hw_array(sbdma16, int, dma, NULL, 0444);
MODULE_PARM_DESC(sbdma16, "DMA16 for CMI8330/CMI8329 SB driver.");
-module_param_array(wssport, long, NULL, 0444);
+module_param_hw_array(wssport, long, ioport, NULL, 0444);
MODULE_PARM_DESC(wssport, "Port # for CMI8330/CMI8329 WSS driver.");
-module_param_array(wssirq, int, NULL, 0444);
+module_param_hw_array(wssirq, int, irq, NULL, 0444);
MODULE_PARM_DESC(wssirq, "IRQ # for CMI8330/CMI8329 WSS driver.");
-module_param_array(wssdma, int, NULL, 0444);
+module_param_hw_array(wssdma, int, dma, NULL, 0444);
MODULE_PARM_DESC(wssdma, "DMA for CMI8330/CMI8329 WSS driver.");
-module_param_array(fmport, long, NULL, 0444);
+module_param_hw_array(fmport, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fmport, "FM port # for CMI8330/CMI8329 driver.");
-module_param_array(mpuport, long, NULL, 0444);
+module_param_hw_array(mpuport, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpuport, "MPU-401 port # for CMI8330/CMI8329 driver.");
-module_param_array(mpuirq, int, NULL, 0444);
+module_param_hw_array(mpuirq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpuirq, "IRQ # for CMI8330/CMI8329 MPU-401 port.");
#ifdef CONFIG_PNP
static int isa_registered;
MODULE_PARM_DESC(id, "ID string for " CRD_NAME " soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable " CRD_NAME " soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " CRD_NAME " driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for " CRD_NAME " driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for " CRD_NAME " driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ # for " CRD_NAME " driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for " CRD_NAME " driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for " CRD_NAME " driver.");
static int snd_cs4231_match(struct device *dev, unsigned int n)
module_param_array(isapnp, bool, NULL, 0444);
MODULE_PARM_DESC(isapnp, "ISA PnP detection for specified soundcard.");
#endif
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " IDENT " driver.");
-module_param_array(cport, long, NULL, 0444);
+module_param_hw_array(cport, long, ioport, NULL, 0444);
MODULE_PARM_DESC(cport, "Control port # for " IDENT " driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for " IDENT " driver.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port # for " IDENT " driver.");
-module_param_array(sb_port, long, NULL, 0444);
+module_param_hw_array(sb_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(sb_port, "SB port # for " IDENT " driver (optional).");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for " IDENT " driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ # for " IDENT " driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for " IDENT " driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for " IDENT " driver.");
#ifdef CONFIG_PNP
MODULE_PARM_DESC(isapnp, "PnP detection for specified soundcard.");
#endif
MODULE_PARM_DESC(enable, "Enable " CRD_NAME " soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " CRD_NAME " driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for " CRD_NAME " driver.");
-module_param_array(irq, int, NULL, 0444);
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port # for ES1688 driver.");
MODULE_PARM_DESC(irq, "IRQ # for " CRD_NAME " driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ # for " CRD_NAME " driver.");
-module_param_array(dma8, int, NULL, 0444);
+module_param_hw_array(dma8, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma8, "8-bit DMA # for " CRD_NAME " driver.");
#ifdef CONFIG_PNP
module_param_array(isapnp, bool, NULL, 0444);
MODULE_PARM_DESC(isapnp, "PnP detection for specified soundcard.");
#endif
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for ES18xx driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for ES18xx driver.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port # for ES18xx driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for ES18xx driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA 1 # for ES18xx driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA 2 # for ES18xx driver.");
#ifdef CONFIG_PNP
static int dma1[SNDRV_CARDS] = SNDRV_DEFAULT_DMA;
static int dma2[SNDRV_CARDS] = SNDRV_DEFAULT_DMA;
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " CRD_NAME " driver.");
-module_param_array(wss_port, long, NULL, 0444);
+module_param_hw_array(wss_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(wss_port, "WSS port # for " CRD_NAME " driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for " CRD_NAME " driver.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port # for " CRD_NAME " driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for " CRD_NAME " driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ # for " CRD_NAME " driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "Playback DMA # for " CRD_NAME " driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "Capture DMA # for " CRD_NAME " driver.");
/*
MODULE_PARM_DESC(id, "ID string for " CRD_NAME " soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable " CRD_NAME " soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " CRD_NAME " driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for " CRD_NAME " driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for " CRD_NAME " driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for " CRD_NAME " driver.");
module_param_array(joystick_dac, int, NULL, 0444);
MODULE_PARM_DESC(joystick_dac, "Joystick DAC level 0.59V-4.52V or 0.389V-2.98V for " CRD_NAME " driver.");
MODULE_PARM_DESC(id, "ID string for " CRD_NAME " soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable " CRD_NAME " soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for " CRD_NAME " driver.");
-module_param_array(gf1_port, long, NULL, 0444);
+module_param_hw_array(gf1_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(gf1_port, "GF1 port # for " CRD_NAME " driver (optional).");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for " CRD_NAME " driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for " CRD_NAME " driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ # for " CRD_NAME " driver.");
-module_param_array(gf1_irq, int, NULL, 0444);
+module_param_hw_array(gf1_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(gf1_irq, "GF1 IRQ # for " CRD_NAME " driver.");
-module_param_array(dma8, int, NULL, 0444);
+module_param_hw_array(dma8, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma8, "8-bit DMA # for " CRD_NAME " driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "GF1 DMA # for " CRD_NAME " driver.");
module_param_array(joystick_dac, int, NULL, 0444);
MODULE_PARM_DESC(joystick_dac, "Joystick DAC level 0.59V-4.52V or 0.389V-2.98V for " CRD_NAME " driver.");
MODULE_PARM_DESC(id, "ID string for GUS MAX soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable GUS MAX soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for GUS MAX driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for GUS MAX driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for GUS MAX driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for GUS MAX driver.");
module_param_array(joystick_dac, int, NULL, 0444);
MODULE_PARM_DESC(joystick_dac, "Joystick DAC level 0.59V-4.52V or 0.389V-2.98V for GUS MAX driver.");
module_param_array(isapnp, bool, NULL, 0444);
MODULE_PARM_DESC(isapnp, "ISA PnP detection for specified soundcard.");
#endif
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for InterWave driver.");
#ifdef SNDRV_STB
-module_param_array(port_tc, long, NULL, 0444);
+module_param_hw_array(port_tc, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port_tc, "Tone control (TEA6330T - i2c bus) port # for InterWave driver.");
#endif
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for InterWave driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for InterWave driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for InterWave driver.");
module_param_array(joystick_dac, int, NULL, 0444);
MODULE_PARM_DESC(joystick_dac, "Joystick DAC level 0.59V-4.52V or 0.389V-2.98V for InterWave driver.");
MODULE_FIRMWARE(INITCODEFILE);
MODULE_FIRMWARE(PERMCODEFILE);
-module_param_array(io, long, NULL, S_IRUGO);
+module_param_hw_array(io, long, ioport, NULL, S_IRUGO);
MODULE_PARM_DESC(io, "IO port #");
-module_param_array(irq, int, NULL, S_IRUGO);
-module_param_array(mem, long, NULL, S_IRUGO);
+module_param_hw_array(irq, int, irq, NULL, S_IRUGO);
+module_param_hw_array(mem, long, iomem, NULL, S_IRUGO);
module_param_array(write_ndelay, int, NULL, S_IRUGO);
module_param(calibrate_signal, int, S_IRUGO);
#ifndef MSND_CLASSIC
module_param_array(digital, int, NULL, S_IRUGO);
-module_param_array(cfg, long, NULL, S_IRUGO);
+module_param_hw_array(cfg, long, ioport, NULL, S_IRUGO);
module_param_array(reset, int, 0, S_IRUGO);
-module_param_array(mpu_io, long, NULL, S_IRUGO);
-module_param_array(mpu_irq, int, NULL, S_IRUGO);
-module_param_array(ide_io0, long, NULL, S_IRUGO);
-module_param_array(ide_io1, long, NULL, S_IRUGO);
-module_param_array(ide_irq, int, NULL, S_IRUGO);
-module_param_array(joystick_io, long, NULL, S_IRUGO);
+module_param_hw_array(mpu_io, long, ioport, NULL, S_IRUGO);
+module_param_hw_array(mpu_irq, int, irq, NULL, S_IRUGO);
+module_param_hw_array(ide_io0, long, ioport, NULL, S_IRUGO);
+module_param_hw_array(ide_io1, long, ioport, NULL, S_IRUGO);
+module_param_hw_array(ide_irq, int, irq, NULL, S_IRUGO);
+module_param_hw_array(joystick_io, long, ioport, NULL, S_IRUGO);
#endif
module_param_array(isapnp, bool, NULL, 0444);
MODULE_PARM_DESC(isapnp, "PnP detection for specified soundcard.");
#endif
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for OPL3-SA driver.");
-module_param_array(sb_port, long, NULL, 0444);
+module_param_hw_array(sb_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(sb_port, "SB port # for OPL3-SA driver.");
-module_param_array(wss_port, long, NULL, 0444);
+module_param_hw_array(wss_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(wss_port, "WSS port # for OPL3-SA driver.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port # for OPL3-SA driver.");
-module_param_array(midi_port, long, NULL, 0444);
+module_param_hw_array(midi_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(midi_port, "MIDI port # for OPL3-SA driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for OPL3-SA driver.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for OPL3-SA driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for OPL3-SA driver.");
module_param_array(opl3sa3_ymode, int, NULL, 0444);
MODULE_PARM_DESC(opl3sa3_ymode, "Speaker size selection for 3D Enhancement mode: Desktop/Large Notebook/Small Notebook/HiFi.");
MODULE_PARM_DESC(index, "Index value for miro soundcard.");
module_param(id, charp, 0444);
MODULE_PARM_DESC(id, "ID string for miro soundcard.");
-module_param(port, long, 0444);
+module_param_hw(port, long, ioport, 0444);
MODULE_PARM_DESC(port, "WSS port # for miro driver.");
-module_param(mpu_port, long, 0444);
+module_param_hw(mpu_port, long, ioport, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for miro driver.");
-module_param(fm_port, long, 0444);
+module_param_hw(fm_port, long, ioport, 0444);
MODULE_PARM_DESC(fm_port, "FM Port # for miro driver.");
-module_param(irq, int, 0444);
+module_param_hw(irq, int, irq, 0444);
MODULE_PARM_DESC(irq, "WSS irq # for miro driver.");
-module_param(mpu_irq, int, 0444);
+module_param_hw(mpu_irq, int, irq, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 irq # for miro driver.");
-module_param(dma1, int, 0444);
+module_param_hw(dma1, int, dma, 0444);
MODULE_PARM_DESC(dma1, "1st dma # for miro driver.");
-module_param(dma2, int, 0444);
+module_param_hw(dma2, int, dma, 0444);
MODULE_PARM_DESC(dma2, "2nd dma # for miro driver.");
module_param(wss, int, 0444);
MODULE_PARM_DESC(wss, "wss mode");
module_param(isapnp, bool, 0444);
MODULE_PARM_DESC(isapnp, "Enable ISA PnP detection for specified soundcard.");
#endif
-module_param(port, long, 0444);
+module_param_hw(port, long, ioport, 0444);
MODULE_PARM_DESC(port, "WSS port # for opti9xx driver.");
-module_param(mpu_port, long, 0444);
+module_param_hw(mpu_port, long, ioport, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for opti9xx driver.");
-module_param(fm_port, long, 0444);
+module_param_hw(fm_port, long, ioport, 0444);
MODULE_PARM_DESC(fm_port, "FM port # for opti9xx driver.");
-module_param(irq, int, 0444);
+module_param_hw(irq, int, irq, 0444);
MODULE_PARM_DESC(irq, "WSS irq # for opti9xx driver.");
-module_param(mpu_irq, int, 0444);
+module_param_hw(mpu_irq, int, irq, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 irq # for opti9xx driver.");
-module_param(dma1, int, 0444);
+module_param_hw(dma1, int, dma, 0444);
MODULE_PARM_DESC(dma1, "1st dma # for opti9xx driver.");
#if defined(CS4231) || defined(OPTi93X)
-module_param(dma2, int, 0444);
+module_param_hw(dma2, int, dma, 0444);
MODULE_PARM_DESC(dma2, "2nd dma # for opti9xx driver.");
#endif /* CS4231 || OPTi93X */
MODULE_PARM_DESC(id, "ID string for Media Vision Jazz16 based soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable Media Vision Jazz16 based soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for jazz16 driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for jazz16 driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for jazz16 driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ # for jazz16 driver.");
-module_param_array(dma8, int, NULL, 0444);
+module_param_hw_array(dma8, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma8, "DMA8 # for jazz16 driver.");
-module_param_array(dma16, int, NULL, 0444);
+module_param_hw_array(dma16, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma16, "DMA16 # for jazz16 driver.");
#define SB_JAZZ16_WAKEUP 0xaf
module_param_array(isapnp, bool, NULL, 0444);
MODULE_PARM_DESC(isapnp, "PnP detection for specified soundcard.");
#endif
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for SB16 driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for SB16 driver.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port # for SB16 PnP driver.");
#ifdef SNDRV_SBAWE_EMU8000
-module_param_array(awe_port, long, NULL, 0444);
+module_param_hw_array(awe_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(awe_port, "AWE port # for SB16 PnP driver.");
#endif
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for SB16 driver.");
-module_param_array(dma8, int, NULL, 0444);
+module_param_hw_array(dma8, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma8, "8-bit DMA # for SB16 driver.");
-module_param_array(dma16, int, NULL, 0444);
+module_param_hw_array(dma16, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma16, "16-bit DMA # for SB16 driver.");
module_param_array(mic_agc, int, NULL, 0444);
MODULE_PARM_DESC(mic_agc, "Mic Auto-Gain-Control switch.");
MODULE_PARM_DESC(id, "ID string for Sound Blaster soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable Sound Blaster soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for SB8 driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for SB8 driver.");
-module_param_array(dma8, int, NULL, 0444);
+module_param_hw_array(dma8, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma8, "8-bit DMA # for SB8 driver.");
struct snd_sb8 {
MODULE_PARM_DESC(id, "ID string for sc-6000 based soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable sc-6000 based soundcard.");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for sc-6000 driver.");
-module_param_array(mss_port, long, NULL, 0444);
+module_param_hw_array(mss_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mss_port, "MSS Port # for sc-6000 driver.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port # for sc-6000 driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for sc-6000 driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ # for sc-6000 driver.");
-module_param_array(dma, int, NULL, 0444);
+module_param_hw_array(dma, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma, "DMA # for sc-6000 driver.");
module_param_array(joystick, bool, NULL, 0444);
MODULE_PARM_DESC(joystick, "Enable gameport.");
module_param_array(id, charp, NULL, 0444);
MODULE_PARM_DESC(id, "Description for SoundScape card");
-module_param_array(port, long, NULL, 0444);
+module_param_hw_array(port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(port, "Port # for SoundScape driver.");
-module_param_array(wss_port, long, NULL, 0444);
+module_param_hw_array(wss_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(wss_port, "WSS Port # for SoundScape driver.");
-module_param_array(irq, int, NULL, 0444);
+module_param_hw_array(irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(irq, "IRQ # for SoundScape driver.");
-module_param_array(mpu_irq, int, NULL, 0444);
+module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(mpu_irq, "MPU401 IRQ # for SoundScape driver.");
-module_param_array(dma, int, NULL, 0444);
+module_param_hw_array(dma, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma, "DMA # for SoundScape driver.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for SoundScape driver.");
module_param_array(joystick, bool, NULL, 0444);
module_param_array(isapnp, bool, NULL, 0444);
MODULE_PARM_DESC(isapnp, "ISA PnP detection for WaveFront soundcards.");
#endif
-module_param_array(cs4232_pcm_port, long, NULL, 0444);
+module_param_hw_array(cs4232_pcm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(cs4232_pcm_port, "Port # for CS4232 PCM interface.");
-module_param_array(cs4232_pcm_irq, int, NULL, 0444);
+module_param_hw_array(cs4232_pcm_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(cs4232_pcm_irq, "IRQ # for CS4232 PCM interface.");
-module_param_array(dma1, int, NULL, 0444);
+module_param_hw_array(dma1, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma1, "DMA1 # for CS4232 PCM interface.");
-module_param_array(dma2, int, NULL, 0444);
+module_param_hw_array(dma2, int, dma, NULL, 0444);
MODULE_PARM_DESC(dma2, "DMA2 # for CS4232 PCM interface.");
-module_param_array(cs4232_mpu_port, long, NULL, 0444);
+module_param_hw_array(cs4232_mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(cs4232_mpu_port, "port # for CS4232 MPU-401 interface.");
-module_param_array(cs4232_mpu_irq, int, NULL, 0444);
+module_param_hw_array(cs4232_mpu_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(cs4232_mpu_irq, "IRQ # for CS4232 MPU-401 interface.");
-module_param_array(ics2115_irq, int, NULL, 0444);
+module_param_hw_array(ics2115_irq, int, irq, NULL, 0444);
MODULE_PARM_DESC(ics2115_irq, "IRQ # for ICS2115.");
-module_param_array(ics2115_port, long, NULL, 0444);
+module_param_hw_array(ics2115_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(ics2115_port, "Port # for ICS2115.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port #.");
module_param_array(use_cs4232_midi, bool, NULL, 0444);
MODULE_PARM_DESC(use_cs4232_midi, "Use CS4232 MPU-401 interface (inaccessibly located inside your computer)");
static int __initdata dma2 = -1;
static int __initdata type = 0;
-module_param(io, int, 0); /* I/O for a raw AD1848 card */
-module_param(irq, int, 0); /* IRQ to use */
-module_param(dma, int, 0); /* First DMA channel */
-module_param(dma2, int, 0); /* Second DMA channel */
+module_param_hw(io, int, ioport, 0); /* I/O for a raw AD1848 card */
+module_param_hw(irq, int, irq, 0); /* IRQ to use */
+module_param_hw(dma, int, dma, 0); /* First DMA channel */
+module_param_hw(dma2, int, dma, 0); /* Second DMA channel */
module_param(type, int, 0); /* Card type */
module_param(deskpro_xl, bool, 0); /* Special magic for Deskpro XL boxen */
module_param(deskpro_m, bool, 0); /* Special magic for Deskpro M box */
static int __initdata mss_base = -1;
static int __initdata mpu_base = -1;
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
MODULE_PARM_DESC(io, "I/O base address (0x220 0x240)");
-module_param(irq, int, 0);
+module_param_hw(irq, int, irq, 0);
MODULE_PARM_DESC(irq, "IRQ line (5 7 9 10 11)");
-module_param(dma, int, 0);
+module_param_hw(dma, int, dma, 0);
MODULE_PARM_DESC(dma, "dma line (0 1 3)");
-module_param(mpu_irq, int, 0);
+module_param_hw(mpu_irq, int, irq, 0);
MODULE_PARM_DESC(mpu_irq, "MPU-401 IRQ line (5 7 9 10 0)");
-module_param(mss_base, int, 0);
+module_param_hw(mss_base, int, ioport, 0);
MODULE_PARM_DESC(mss_base, "MSS emulation I/O base address (0x530 0xE80)");
-module_param(mpu_base, int, 0);
+module_param_hw(mpu_base, int, ioport, 0);
MODULE_PARM_DESC(mpu_base,"MPU-401 I/O base address (0x300 0x310 0x320 0x330)");
MODULE_AUTHOR("Riccardo Facchetti <fizban@tin.it>");
MODULE_DESCRIPTION("Audio Excel DSP 16 Driver Version " VERSION);
static int io = -1;
static int irq = -1;
-module_param(irq, int, 0);
-module_param(io, int, 0);
+module_param_hw(irq, int, irq, 0);
+module_param_hw(io, int, ioport, 0);
static int __init init_mpu401(void)
{
calibrate_signal __initdata = CONFIG_MSND_CALSIGNAL;
#endif /* MODULE */
-module_param (io, int, 0);
-module_param (irq, int, 0);
-module_param (mem, int, 0);
+module_param_hw (io, int, ioport, 0);
+module_param_hw (irq, int, irq, 0);
+module_param_hw (mem, int, iomem, 0);
module_param (write_ndelay, int, 0);
module_param (fifosize, int, 0);
module_param (calibrate_signal, int, 0);
#ifndef MSND_CLASSIC
module_param (digital, bool, 0);
-module_param (cfg, int, 0);
+module_param_hw (cfg, int, ioport, 0);
module_param (reset, int, 0);
-module_param (mpu_io, int, 0);
-module_param (mpu_irq, int, 0);
-module_param (ide_io0, int, 0);
-module_param (ide_io1, int, 0);
-module_param (ide_irq, int, 0);
-module_param (joystick_io, int, 0);
+module_param_hw (mpu_io, int, ioport, 0);
+module_param_hw (mpu_irq, int, irq, 0);
+module_param_hw (ide_io0, int, ioport, 0);
+module_param_hw (ide_io1, int, ioport, 0);
+module_param_hw (ide_irq, int, irq, 0);
+module_param_hw (joystick_io, int, ioport, 0);
#endif
static int __init msnd_init(void)
static int io = -1;
-module_param(io, int, 0);
+module_param_hw(io, int, ioport, 0);
static int __init init_opl3 (void)
{
static int __initdata sb_dma = -1;
static int __initdata sb_dma16 = -1;
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(dma, int, 0);
-module_param(dma16, int, 0);
-
-module_param(sb_io, int, 0);
-module_param(sb_irq, int, 0);
-module_param(sb_dma, int, 0);
-module_param(sb_dma16, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
+module_param_hw(dma, int, dma, 0);
+module_param_hw(dma16, int, dma, 0);
+
+module_param_hw(sb_io, int, ioport, 0);
+module_param_hw(sb_irq, int, irq, 0);
+module_param_hw(sb_dma, int, dma, 0);
+module_param_hw(sb_dma16, int, dma, 0);
module_param(joystick, bool, 0);
module_param(symphony, bool, 0);
static bool pss_keep_settings = 1; /* Keep hardware settings at module exit */
static char *pss_firmware = "/etc/sound/pss_synth";
-module_param(pss_io, int, 0);
+module_param_hw(pss_io, int, ioport, 0);
MODULE_PARM_DESC(pss_io, "Set i/o base of PSS card (probably 0x220 or 0x240)");
-module_param(mss_io, int, 0);
+module_param_hw(mss_io, int, ioport, 0);
MODULE_PARM_DESC(mss_io, "Set WSS (audio) i/o base (0x530, 0x604, 0xE80, 0xF40, or other. Address must end in 0 or 4 and must be from 0x100 to 0xFF4)");
-module_param(mss_irq, int, 0);
+module_param_hw(mss_irq, int, irq, 0);
MODULE_PARM_DESC(mss_irq, "Set WSS (audio) IRQ (3, 5, 7, 9, 10, 11, 12)");
-module_param(mss_dma, int, 0);
+module_param_hw(mss_dma, int, dma, 0);
MODULE_PARM_DESC(mss_dma, "Set WSS (audio) DMA (0, 1, 3)");
-module_param(mpu_io, int, 0);
+module_param_hw(mpu_io, int, ioport, 0);
MODULE_PARM_DESC(mpu_io, "Set MIDI i/o base (0x330 or other. Address must be on 4 location boundaries and must be from 0x100 to 0xFFC)");
-module_param(mpu_irq, int, 0);
+module_param_hw(mpu_irq, int, irq, 0);
MODULE_PARM_DESC(mpu_irq, "Set MIDI IRQ (3, 5, 7, 9, 10, 11, 12)");
-module_param(pss_cdrom_port, int, 0);
+module_param_hw(pss_cdrom_port, int, ioport, 0);
MODULE_PARM_DESC(pss_cdrom_port, "Set the PSS CDROM port i/o base (0x340 or other)");
module_param(pss_enable_joystick, bool, 0);
MODULE_PARM_DESC(pss_enable_joystick, "Enables the PSS joystick port (1 to enable, 0 to disable)");
static int __initdata pnp = 0;
#endif
-module_param(io, int, 000);
+module_param_hw(io, int, ioport, 000);
MODULE_PARM_DESC(io, "Soundblaster i/o base address (0x220,0x240,0x260,0x280)");
-module_param(irq, int, 000);
+module_param_hw(irq, int, irq, 000);
MODULE_PARM_DESC(irq, "IRQ (5,7,9,10)");
-module_param(dma, int, 000);
+module_param_hw(dma, int, dma, 000);
MODULE_PARM_DESC(dma, "8-bit DMA channel (0,1,3)");
-module_param(dma16, int, 000);
+module_param_hw(dma16, int, dma, 000);
MODULE_PARM_DESC(dma16, "16-bit DMA channel (5,6,7)");
-module_param(mpu_io, int, 000);
+module_param_hw(mpu_io, int, ioport, 000);
MODULE_PARM_DESC(mpu_io, "MPU base address");
module_param(type, int, 000);
MODULE_PARM_DESC(type, "You can set this to specific card type (doesn't " \
static int __initdata mpu_io = -1;
static int __initdata mpu_irq = -1;
-module_param(io, int, 0);
-module_param(irq, int, 0);
-module_param(dma, int, 0);
-module_param(dma2, int, 0);
-module_param(sb_io, int, 0);
-module_param(sb_dma, int, 0);
-module_param(sb_irq, int, 0);
-module_param(mpu_io, int, 0);
-module_param(mpu_irq, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
+module_param_hw(dma, int, dma, 0);
+module_param_hw(dma2, int, dma, 0);
+module_param_hw(sb_io, int, ioport, 0);
+module_param_hw(sb_dma, int, dma, 0);
+module_param_hw(sb_irq, int, irq, 0);
+module_param_hw(mpu_io, int, ioport, 0);
+module_param_hw(mpu_irq, int, irq, 0);
module_param(joystick, bool, 0);
static int __init init_trix(void)
static int io = -1;
static int irq = -1;
-module_param(io, int, 0444);
-module_param(irq, int, 0444);
+module_param_hw(io, int, ioport, 0444);
+module_param_hw(irq, int, irq, 0444);
static int __init init_uart401(void)
static int __initdata io = -1;
static int __initdata irq = -1;
-module_param(io, int, 0);
-module_param(irq, int, 0);
+module_param_hw(io, int, ioport, 0);
+module_param_hw(irq, int, irq, 0);
static int __init init_uart6850(void)
{
#endif
MODULE_DESCRIPTION("Rockwell WaveArtist RWA-010 sound driver");
-module_param(io, int, 0); /* IO base */
-module_param(irq, int, 0); /* IRQ */
-module_param(dma, int, 0); /* DMA */
-module_param(dma2, int, 0); /* DMA2 */
+module_param_hw(io, int, ioport, 0); /* IO base */
+module_param_hw(irq, int, irq, 0); /* IRQ */
+module_param_hw(dma, int, dma, 0); /* DMA */
+module_param_hw(dma2, int, dma, 0); /* DMA2 */
MODULE_LICENSE("GPL");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable ALS4000 soundcard.");
#ifdef SUPPORT_JOYSTICK
-module_param_array(joystick_port, int, NULL, 0444);
+module_param_hw_array(joystick_port, int, ioport, NULL, 0444);
MODULE_PARM_DESC(joystick_port, "Joystick port address for ALS4000 soundcard. (0 = disabled)");
#endif
MODULE_PARM_DESC(id, "ID string for C-Media PCI soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable C-Media PCI soundcard.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM port.");
module_param_array(soft_ac3, bool, NULL, 0444);
MODULE_PARM_DESC(soft_ac3, "Software-conversion of raw SPDIF packets (model 033 only).");
#ifdef SUPPORT_JOYSTICK
-module_param_array(joystick_port, int, NULL, 0444);
+module_param_hw_array(joystick_port, int, ioport, NULL, 0444);
MODULE_PARM_DESC(joystick_port, "Joystick port address.");
#endif
MODULE_PARM_DESC(enable, "Enable Ensoniq AudioPCI soundcard.");
#ifdef SUPPORT_JOYSTICK
#ifdef CHIP1371
-module_param_array(joystick_port, int, NULL, 0444);
+module_param_hw_array(joystick_port, int, ioport, NULL, 0444);
MODULE_PARM_DESC(joystick_port, "Joystick port address.");
#else
module_param_array(joystick, bool, NULL, 0444);
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable Riptide soundcard.");
#ifdef SUPPORT_JOYSTICK
-module_param_array(joystick_port, int, NULL, 0444);
+module_param_hw_array(joystick_port, int, ioport, NULL, 0444);
MODULE_PARM_DESC(joystick_port, "Joystick port # for Riptide soundcard.");
#endif
-module_param_array(mpu_port, int, NULL, 0444);
+module_param_hw_array(mpu_port, int, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU401 port # for Riptide driver.");
-module_param_array(opl3_port, int, NULL, 0444);
+module_param_hw_array(opl3_port, int, ioport, NULL, 0444);
MODULE_PARM_DESC(opl3_port, "OPL3 port # for Riptide driver.");
/*
MODULE_PARM_DESC(reverb, "Enable reverb (SRAM is present) for S3 SonicVibes soundcard.");
module_param_array(mge, bool, NULL, 0444);
MODULE_PARM_DESC(mge, "MIC Gain Enable for S3 SonicVibes soundcard.");
-module_param(dmaio, uint, 0444);
+module_param_hw(dmaio, uint, ioport, 0444);
MODULE_PARM_DESC(dmaio, "DDMA i/o base address for S3 SonicVibes soundcard.");
/*
MODULE_PARM_DESC(index, "Index value for VIA 82xx bridge.");
module_param(id, charp, 0444);
MODULE_PARM_DESC(id, "ID string for VIA 82xx bridge.");
-module_param(mpu_port, long, 0444);
+module_param_hw(mpu_port, long, ioport, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 port. (VT82C686x only)");
#ifdef SUPPORT_JOYSTICK
module_param(joystick, bool, 0444);
MODULE_PARM_DESC(id, "ID string for the Yamaha DS-1 PCI soundcard.");
module_param_array(enable, bool, NULL, 0444);
MODULE_PARM_DESC(enable, "Enable Yamaha DS-1 soundcard.");
-module_param_array(mpu_port, long, NULL, 0444);
+module_param_hw_array(mpu_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(mpu_port, "MPU-401 Port.");
-module_param_array(fm_port, long, NULL, 0444);
+module_param_hw_array(fm_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(fm_port, "FM OPL-3 Port.");
#ifdef SUPPORT_JOYSTICK
-module_param_array(joystick_port, long, NULL, 0444);
+module_param_hw_array(joystick_port, long, ioport, NULL, 0444);
MODULE_PARM_DESC(joystick_port, "Joystick port address");
#endif
module_param_array(rear_switch, bool, NULL, 0444);
# Pull in Kconfig-fragment boot parameters
boot_args="`configfrag_boot_params "$boot_args" "$config_template"`"
# Generate kernel-version-specific boot parameters
-boot_args="`per_version_boot_params "$boot_args" $builddir/.config $seconds`"
+boot_args="`per_version_boot_params "$boot_args" $resdir/.config $seconds`"
if test -n "$TORTURE_BUILDONLY"
then
unsigned int vring_align,
struct virtio_device *vdev,
bool weak_barriers,
+ bool ctx,
void *pages,
bool (*notify)(struct virtqueue *vq),
void (*callback)(struct virtqueue *vq),
int runcycles = 10000000;
int max_outstanding = INT_MAX;
int batch = 1;
+int param = 0;
bool do_sleep = false;
bool do_relax = false;
cpu = strtol(arg, &endptr, 0);
assert(!*endptr);
- assert(cpu >= 0 || cpu < CPU_SETSIZE);
+ assert(cpu >= 0 && cpu < CPU_SETSIZE);
self = pthread_self();
CPU_ZERO(&cpuset);
.has_arg = required_argument,
.val = 'b',
},
+ {
+ .name = "param",
+ .has_arg = required_argument,
+ .val = 'p',
+ },
{
.name = "sleep",
.has_arg = no_argument,
" [--run-cycles C (default: %d)]"
" [--batch b]"
" [--outstanding o]"
+ " [--param p]"
" [--sleep]"
" [--relax]"
" [--exit]"
assert(c > 0 && c < INT_MAX);
max_outstanding = c;
break;
+ case 'p':
+ c = strtol(optarg, &endptr, 0);
+ assert(!*endptr);
+ assert(c > 0 && c < INT_MAX);
+ param = c;
+ break;
case 'b':
c = strtol(optarg, &endptr, 0);
assert(!*endptr);
#include <stdbool.h>
+extern int param;
+
extern bool do_exit;
#if defined(__x86_64__) || defined(__i386__)
{
int ret = ptr_ring_init(&array, ring_size, 0);
assert(!ret);
+ /* Hacky way to poke at ring internals. Useful for testing though. */
+ if (param)
+ array.batch = param;
}
/* guest side */
vring_init(&info->vring, num, info->ring, 4096);
info->vq = vring_new_virtqueue(info->idx,
info->vring.num, 4096, &dev->vdev,
- true, info->ring,
+ true, false, info->ring,
vq_notify, vq_callback, "test");
assert(info->vq);
info->vq->priv = info;
test = 0;
r = ioctl(dev->control, VHOST_TEST_RUN, &test);
assert(r >= 0);
- fprintf(stderr, "spurious wakeus: 0x%llx\n", spurious);
+ fprintf(stderr, "spurious wakeups: 0x%llx\n", spurious);
}
const char optstring[] = "h";
err(1, "Could not set affinity to cpu %u", first_cpu);
vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &gvdev.vdev, true,
- guest_map, fast_vringh ? no_notify_host
+ false, guest_map,
+ fast_vringh ? no_notify_host
: parallel_notify_host,
never_callback_guest, "guest vq");
memset(__user_addr_min, 0, vring_size(RINGSIZE, ALIGN));
/* Set up guest side. */
- vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
+ vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true, false,
__user_addr_min,
never_notify_host, never_callback_guest,
"guest vq");
/* Force creation of direct, which we modify. */
__virtio_clear_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC);
vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
- __user_addr_min,
+ false, __user_addr_min,
never_notify_host,
never_callback_guest,
"guest vq");
kvm_arm_reset_debug_ptr(vcpu);
- return 0;
+ return kvm_vgic_vcpu_init(vcpu);
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
#define TRACE_SYSTEM kvm
/*
- * Tracepoints for vgic
+ * Tracepoints for entry/exit to guest
*/
-TRACE_EVENT(vgic_update_irq_pending,
- TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level),
- TP_ARGS(vcpu_id, irq, level),
+TRACE_EVENT(kvm_entry,
+ TP_PROTO(unsigned long vcpu_pc),
+ TP_ARGS(vcpu_pc),
TP_STRUCT__entry(
- __field( unsigned long, vcpu_id )
- __field( __u32, irq )
- __field( bool, level )
+ __field( unsigned long, vcpu_pc )
),
TP_fast_assign(
- __entry->vcpu_id = vcpu_id;
- __entry->irq = irq;
+ __entry->vcpu_pc = vcpu_pc;
+ ),
+
+ TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_exit,
+ TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
+ TP_ARGS(idx, exit_reason, vcpu_pc),
+
+ TP_STRUCT__entry(
+ __field( int, idx )
+ __field( unsigned int, exit_reason )
+ __field( unsigned long, vcpu_pc )
+ ),
+
+ TP_fast_assign(
+ __entry->idx = idx;
+ __entry->exit_reason = exit_reason;
+ __entry->vcpu_pc = vcpu_pc;
+ ),
+
+ TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+ __print_symbolic(__entry->idx, kvm_arm_exception_type),
+ __entry->exit_reason,
+ __print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
+ __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_guest_fault,
+ TP_PROTO(unsigned long vcpu_pc, unsigned long hsr,
+ unsigned long hxfar,
+ unsigned long long ipa),
+ TP_ARGS(vcpu_pc, hsr, hxfar, ipa),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( unsigned long, hsr )
+ __field( unsigned long, hxfar )
+ __field( unsigned long long, ipa )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->hsr = hsr;
+ __entry->hxfar = hxfar;
+ __entry->ipa = ipa;
+ ),
+
+ TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+ __entry->ipa, __entry->hsr,
+ __entry->hxfar, __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_access_fault,
+ TP_PROTO(unsigned long ipa),
+ TP_ARGS(ipa),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, ipa )
+ ),
+
+ TP_fast_assign(
+ __entry->ipa = ipa;
+ ),
+
+ TP_printk("IPA: %lx", __entry->ipa)
+);
+
+TRACE_EVENT(kvm_irq_line,
+ TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level),
+ TP_ARGS(type, vcpu_idx, irq_num, level),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, type )
+ __field( int, vcpu_idx )
+ __field( int, irq_num )
+ __field( int, level )
+ ),
+
+ TP_fast_assign(
+ __entry->type = type;
+ __entry->vcpu_idx = vcpu_idx;
+ __entry->irq_num = irq_num;
__entry->level = level;
),
- TP_printk("VCPU: %ld, IRQ %d, level: %d",
- __entry->vcpu_id, __entry->irq, __entry->level)
+ TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d",
+ (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" :
+ (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" :
+ (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN",
+ __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level)
+);
+
+TRACE_EVENT(kvm_mmio_emulate,
+ TP_PROTO(unsigned long vcpu_pc, unsigned long instr,
+ unsigned long cpsr),
+ TP_ARGS(vcpu_pc, instr, cpsr),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( unsigned long, instr )
+ __field( unsigned long, cpsr )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->instr = instr;
+ __entry->cpsr = cpsr;
+ ),
+
+ TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+ __entry->vcpu_pc, __entry->instr, __entry->cpsr)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+ TP_PROTO(unsigned long hva),
+ TP_ARGS(hva),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, hva )
+ ),
+
+ TP_fast_assign(
+ __entry->hva = hva;
+ ),
+
+ TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_unmap_hva_range,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, start )
+ __field( unsigned long, end )
+ ),
+
+ TP_fast_assign(
+ __entry->start = start;
+ __entry->end = end;
+ ),
+
+ TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+ __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_set_spte_hva,
+ TP_PROTO(unsigned long hva),
+ TP_ARGS(hva),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, hva )
+ ),
+
+ TP_fast_assign(
+ __entry->hva = hva;
+ ),
+
+ TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_age_hva,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, start )
+ __field( unsigned long, end )
+ ),
+
+ TP_fast_assign(
+ __entry->start = start;
+ __entry->end = end;
+ ),
+
+ TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+ __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_test_age_hva,
+ TP_PROTO(unsigned long hva),
+ TP_ARGS(hva),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, hva )
+ ),
+
+ TP_fast_assign(
+ __entry->hva = hva;
+ ),
+
+ TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_set_way_flush,
+ TP_PROTO(unsigned long vcpu_pc, bool cache),
+ TP_ARGS(vcpu_pc, cache),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( bool, cache )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->cache = cache;
+ ),
+
+ TP_printk("S/W flush at 0x%016lx (cache %s)",
+ __entry->vcpu_pc, __entry->cache ? "on" : "off")
+);
+
+TRACE_EVENT(kvm_toggle_cache,
+ TP_PROTO(unsigned long vcpu_pc, bool was, bool now),
+ TP_ARGS(vcpu_pc, was, now),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( bool, was )
+ __field( bool, now )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->was = was;
+ __entry->now = now;
+ ),
+
+ TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
+ __entry->vcpu_pc, __entry->was ? "on" : "off",
+ __entry->now ? "on" : "off")
);
/*
--- /dev/null
+#if !defined(_TRACE_VGIC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_VGIC_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+TRACE_EVENT(vgic_update_irq_pending,
+ TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level),
+ TP_ARGS(vcpu_id, irq, level),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_id )
+ __field( __u32, irq )
+ __field( bool, level )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu_id;
+ __entry->irq = irq;
+ __entry->level = level;
+ ),
+
+ TP_printk("VCPU: %ld, IRQ %d, level: %d",
+ __entry->vcpu_id, __entry->irq, __entry->level)
+);
+
+#endif /* _TRACE_VGIC_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm/vgic
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
}
/**
- * kvm_vgic_vcpu_init() - Enable the VCPU interface
- * @vcpu: the VCPU which's VGIC should be enabled
+ * kvm_vgic_vcpu_init() - Register VCPU-specific KVM iodevs
+ * @vcpu: pointer to the VCPU being created and initialized
*/
-static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ int ret = 0;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return 0;
+
+ /*
+ * If we are creating a VCPU with a GICv3 we must also register the
+ * KVM io device for the redistributor that belongs to this VCPU.
+ */
+ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ ret = vgic_register_redist_iodev(vcpu);
+ return ret;
+}
+
+static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_enable(vcpu);
dist->msis_require_devid = true;
kvm_for_each_vcpu(i, vcpu, kvm)
- kvm_vgic_vcpu_init(vcpu);
+ kvm_vgic_vcpu_enable(vcpu);
ret = kvm_vgic_setup_default_irq_routing(kvm);
if (ret)
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/uaccess.h>
+#include <linux/list_sort.h>
#include <linux/irqchip/arm-gic-v3.h>
#include "vgic.h"
#include "vgic-mmio.h"
+static int vgic_its_save_tables_v0(struct vgic_its *its);
+static int vgic_its_restore_tables_v0(struct vgic_its *its);
+static int vgic_its_commit_v0(struct vgic_its *its);
+static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
+ struct kvm_vcpu *filter_vcpu);
+
/*
* Creates a new (reference to a) struct vgic_irq for a given LPI.
* If this LPI is already mapped on another ITS, we increase its refcount
* If this is a "new" LPI, we allocate and initialize a new struct vgic_irq.
* This function returns a pointer to the _unlocked_ structure.
*/
-static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
+static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
+ struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+ int ret;
/* In this case there is no put, since we keep the reference. */
if (irq)
irq->config = VGIC_CONFIG_EDGE;
kref_init(&irq->refcount);
irq->intid = intid;
+ irq->target_vcpu = vcpu;
spin_lock(&dist->lpi_list_lock);
out_unlock:
spin_unlock(&dist->lpi_list_lock);
+ /*
+ * We "cache" the configuration table entries in our struct vgic_irq's.
+ * However we only have those structs for mapped IRQs, so we read in
+ * the respective config data from memory here upon mapping the LPI.
+ */
+ ret = update_lpi_config(kvm, irq, NULL);
+ if (ret)
+ return ERR_PTR(ret);
+
+ ret = vgic_v3_lpi_sync_pending_status(kvm, irq);
+ if (ret)
+ return ERR_PTR(ret);
+
return irq;
}
/* the head for the list of ITTEs */
struct list_head itt_head;
+ u32 num_eventid_bits;
+ gpa_t itt_addr;
u32 device_id;
};
#define its_is_collection_mapped(coll) ((coll) && \
((coll)->target_addr != COLLECTION_NOT_MAPPED))
-struct its_itte {
- struct list_head itte_list;
+struct its_ite {
+ struct list_head ite_list;
struct vgic_irq *irq;
struct its_collection *collection;
u32 event_id;
};
+/**
+ * struct vgic_its_abi - ITS abi ops and settings
+ * @cte_esz: collection table entry size
+ * @dte_esz: device table entry size
+ * @ite_esz: interrupt translation table entry size
+ * @save tables: save the ITS tables into guest RAM
+ * @restore_tables: restore the ITS internal structs from tables
+ * stored in guest RAM
+ * @commit: initialize the registers which expose the ABI settings,
+ * especially the entry sizes
+ */
+struct vgic_its_abi {
+ int cte_esz;
+ int dte_esz;
+ int ite_esz;
+ int (*save_tables)(struct vgic_its *its);
+ int (*restore_tables)(struct vgic_its *its);
+ int (*commit)(struct vgic_its *its);
+};
+
+static const struct vgic_its_abi its_table_abi_versions[] = {
+ [0] = {.cte_esz = 8, .dte_esz = 8, .ite_esz = 8,
+ .save_tables = vgic_its_save_tables_v0,
+ .restore_tables = vgic_its_restore_tables_v0,
+ .commit = vgic_its_commit_v0,
+ },
+};
+
+#define NR_ITS_ABIS ARRAY_SIZE(its_table_abi_versions)
+
+inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its)
+{
+ return &its_table_abi_versions[its->abi_rev];
+}
+
+int vgic_its_set_abi(struct vgic_its *its, int rev)
+{
+ const struct vgic_its_abi *abi;
+
+ its->abi_rev = rev;
+ abi = vgic_its_get_abi(its);
+ return abi->commit(its);
+}
+
/*
* Find and returns a device in the device table for an ITS.
* Must be called with the its_lock mutex held.
* Device ID/Event ID pair on an ITS.
* Must be called with the its_lock mutex held.
*/
-static struct its_itte *find_itte(struct vgic_its *its, u32 device_id,
+static struct its_ite *find_ite(struct vgic_its *its, u32 device_id,
u32 event_id)
{
struct its_device *device;
- struct its_itte *itte;
+ struct its_ite *ite;
device = find_its_device(its, device_id);
if (device == NULL)
return NULL;
- list_for_each_entry(itte, &device->itt_head, itte_list)
- if (itte->event_id == event_id)
- return itte;
+ list_for_each_entry(ite, &device->itt_head, ite_list)
+ if (ite->event_id == event_id)
+ return ite;
return NULL;
}
/* To be used as an iterator this macro misses the enclosing parentheses */
-#define for_each_lpi_its(dev, itte, its) \
+#define for_each_lpi_its(dev, ite, its) \
list_for_each_entry(dev, &(its)->device_list, dev_list) \
- list_for_each_entry(itte, &(dev)->itt_head, itte_list)
+ list_for_each_entry(ite, &(dev)->itt_head, ite_list)
/*
* We only implement 48 bits of PA at the moment, although the ITS
*/
#define BASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 16))
#define CBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 12))
-#define PENDBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 16))
-#define PROPBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 12))
#define GIC_LPI_OFFSET 8192
+#define VITS_TYPER_IDBITS 16
+#define VITS_TYPER_DEVBITS 16
+#define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1)
+#define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1)
+
/*
* Finds and returns a collection in the ITS collection table.
* Must be called with the its_lock mutex held.
static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
struct kvm_vcpu *filter_vcpu)
{
- u64 propbase = PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
+ u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
u8 prop;
int ret;
}
/*
- * Create a snapshot of the current LPI list, so that we can enumerate all
- * LPIs without holding any lock.
- * Returns the array length and puts the kmalloc'ed array into intid_ptr.
+ * Create a snapshot of the current LPIs targeting @vcpu, so that we can
+ * enumerate those LPIs without holding any lock.
+ * Returns their number and puts the kmalloc'ed array into intid_ptr.
*/
-static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
+static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
{
- struct vgic_dist *dist = &kvm->arch.vgic;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_irq *irq;
u32 *intids;
int irq_count = dist->lpi_list_count, i = 0;
spin_lock(&dist->lpi_list_lock);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
/* We don't need to "get" the IRQ, as we hold the list lock. */
- intids[i] = irq->intid;
- if (++i == irq_count)
- break;
+ if (irq->target_vcpu != vcpu)
+ continue;
+ intids[i++] = irq->intid;
}
spin_unlock(&dist->lpi_list_lock);
*intid_ptr = intids;
- return irq_count;
+ return i;
}
/*
* Needs to be called whenever either the collection for a LPIs has
* changed or the collection itself got retargeted.
*/
-static void update_affinity_itte(struct kvm *kvm, struct its_itte *itte)
+static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite)
{
struct kvm_vcpu *vcpu;
- if (!its_is_collection_mapped(itte->collection))
+ if (!its_is_collection_mapped(ite->collection))
return;
- vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+ vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);
- spin_lock(&itte->irq->irq_lock);
- itte->irq->target_vcpu = vcpu;
- spin_unlock(&itte->irq->irq_lock);
+ spin_lock(&ite->irq->irq_lock);
+ ite->irq->target_vcpu = vcpu;
+ spin_unlock(&ite->irq->irq_lock);
}
/*
struct its_collection *coll)
{
struct its_device *device;
- struct its_itte *itte;
+ struct its_ite *ite;
- for_each_lpi_its(device, itte, its) {
- if (!itte->collection || coll != itte->collection)
+ for_each_lpi_its(device, ite, its) {
+ if (!ite->collection || coll != ite->collection)
continue;
- update_affinity_itte(kvm, itte);
+ update_affinity_ite(kvm, ite);
}
}
}
/*
- * Scan the whole LPI pending table and sync the pending bit in there
+ * Sync the pending table pending bit of LPIs targeting @vcpu
* with our own data structures. This relies on the LPI being
* mapped before.
*/
static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
{
- gpa_t pendbase = PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+ gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
struct vgic_irq *irq;
int last_byte_offset = -1;
int ret = 0;
u32 *intids;
int nr_irqs, i;
- nr_irqs = vgic_copy_lpi_list(vcpu->kvm, &intids);
+ nr_irqs = vgic_copy_lpi_list(vcpu, &intids);
if (nr_irqs < 0)
return nr_irqs;
struct vgic_its *its,
gpa_t addr, unsigned int len)
{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
u64 reg = GITS_TYPER_PLPIS;
/*
* To avoid memory waste in the guest, we keep the number of IDBits and
* DevBits low - as least for the time being.
*/
- reg |= 0x0f << GITS_TYPER_DEVBITS_SHIFT;
- reg |= 0x0f << GITS_TYPER_IDBITS_SHIFT;
+ reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT;
+ reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT;
+ reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT;
return extract_bytes(reg, addr & 7, len);
}
struct vgic_its *its,
gpa_t addr, unsigned int len)
{
- return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+ u32 val;
+
+ val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK;
+ val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM;
+ return val;
+}
+
+static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm,
+ struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 rev = GITS_IIDR_REV(val);
+
+ if (rev >= NR_ITS_ABIS)
+ return -EINVAL;
+ return vgic_its_set_abi(its, rev);
}
static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm,
u32 devid, u32 eventid)
{
struct kvm_vcpu *vcpu;
- struct its_itte *itte;
+ struct its_ite *ite;
if (!its->enabled)
return -EBUSY;
- itte = find_itte(its, devid, eventid);
- if (!itte || !its_is_collection_mapped(itte->collection))
+ ite = find_ite(its, devid, eventid);
+ if (!ite || !its_is_collection_mapped(ite->collection))
return E_ITS_INT_UNMAPPED_INTERRUPT;
- vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+ vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);
if (!vcpu)
return E_ITS_INT_UNMAPPED_INTERRUPT;
if (!vcpu->arch.vgic_cpu.lpis_enabled)
return -EBUSY;
- spin_lock(&itte->irq->irq_lock);
- itte->irq->pending_latch = true;
- vgic_queue_irq_unlock(kvm, itte->irq);
+ spin_lock(&ite->irq->irq_lock);
+ ite->irq->pending_latch = true;
+ vgic_queue_irq_unlock(kvm, ite->irq);
return 0;
}
}
/* Requires the its_lock to be held. */
-static void its_free_itte(struct kvm *kvm, struct its_itte *itte)
+static void its_free_ite(struct kvm *kvm, struct its_ite *ite)
{
- list_del(&itte->itte_list);
+ list_del(&ite->ite_list);
/* This put matches the get in vgic_add_lpi. */
- if (itte->irq)
- vgic_put_irq(kvm, itte->irq);
+ if (ite->irq)
+ vgic_put_irq(kvm, ite->irq);
- kfree(itte);
+ kfree(ite);
}
static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size)
#define its_cmd_get_command(cmd) its_cmd_mask_field(cmd, 0, 0, 8)
#define its_cmd_get_deviceid(cmd) its_cmd_mask_field(cmd, 0, 32, 32)
+#define its_cmd_get_size(cmd) (its_cmd_mask_field(cmd, 1, 0, 5) + 1)
#define its_cmd_get_id(cmd) its_cmd_mask_field(cmd, 1, 0, 32)
#define its_cmd_get_physical_id(cmd) its_cmd_mask_field(cmd, 1, 32, 32)
#define its_cmd_get_collection(cmd) its_cmd_mask_field(cmd, 2, 0, 16)
+#define its_cmd_get_ittaddr(cmd) (its_cmd_mask_field(cmd, 2, 8, 44) << 8)
#define its_cmd_get_target_addr(cmd) its_cmd_mask_field(cmd, 2, 16, 32)
#define its_cmd_get_validbit(cmd) its_cmd_mask_field(cmd, 2, 63, 1)
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
- itte = find_itte(its, device_id, event_id);
- if (itte && itte->collection) {
+ ite = find_ite(its, device_id, event_id);
+ if (ite && ite->collection) {
/*
* Though the spec talks about removing the pending state, we
* don't bother here since we clear the ITTE anyway and the
* pending state is a property of the ITTE struct.
*/
- its_free_itte(kvm, itte);
+ its_free_ite(kvm, ite);
return 0;
}
u32 event_id = its_cmd_get_id(its_cmd);
u32 coll_id = its_cmd_get_collection(its_cmd);
struct kvm_vcpu *vcpu;
- struct its_itte *itte;
+ struct its_ite *ite;
struct its_collection *collection;
- itte = find_itte(its, device_id, event_id);
- if (!itte)
+ ite = find_ite(its, device_id, event_id);
+ if (!ite)
return E_ITS_MOVI_UNMAPPED_INTERRUPT;
- if (!its_is_collection_mapped(itte->collection))
+ if (!its_is_collection_mapped(ite->collection))
return E_ITS_MOVI_UNMAPPED_COLLECTION;
collection = find_collection(its, coll_id);
if (!its_is_collection_mapped(collection))
return E_ITS_MOVI_UNMAPPED_COLLECTION;
- itte->collection = collection;
+ ite->collection = collection;
vcpu = kvm_get_vcpu(kvm, collection->target_addr);
- spin_lock(&itte->irq->irq_lock);
- itte->irq->target_vcpu = vcpu;
- spin_unlock(&itte->irq->irq_lock);
+ spin_lock(&ite->irq->irq_lock);
+ ite->irq->target_vcpu = vcpu;
+ spin_unlock(&ite->irq->irq_lock);
return 0;
}
* Check whether an ID can be stored into the corresponding guest table.
* For a direct table this is pretty easy, but gets a bit nasty for
* indirect tables. We check whether the resulting guest physical address
- * is actually valid (covered by a memslot and guest accessbible).
+ * is actually valid (covered by a memslot and guest accessible).
* For this we have to read the respective first level entry.
*/
-static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
+static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
+ gpa_t *eaddr)
{
int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
+ u64 indirect_ptr, type = GITS_BASER_TYPE(baser);
+ int esz = GITS_BASER_ENTRY_SIZE(baser);
int index;
- u64 indirect_ptr;
gfn_t gfn;
- int esz = GITS_BASER_ENTRY_SIZE(baser);
+
+ switch (type) {
+ case GITS_BASER_TYPE_DEVICE:
+ if (id >= BIT_ULL(VITS_TYPER_DEVBITS))
+ return false;
+ break;
+ case GITS_BASER_TYPE_COLLECTION:
+ /* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */
+ if (id >= BIT_ULL(16))
+ return false;
+ break;
+ default:
+ return false;
+ }
if (!(baser & GITS_BASER_INDIRECT)) {
phys_addr_t addr;
addr = BASER_ADDRESS(baser) + id * esz;
gfn = addr >> PAGE_SHIFT;
+ if (eaddr)
+ *eaddr = addr;
return kvm_is_visible_gfn(its->dev->kvm, gfn);
}
indirect_ptr += index * esz;
gfn = indirect_ptr >> PAGE_SHIFT;
+ if (eaddr)
+ *eaddr = indirect_ptr;
return kvm_is_visible_gfn(its->dev->kvm, gfn);
}
{
struct its_collection *collection;
- if (!vgic_its_check_id(its, its->baser_coll_table, coll_id))
+ if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL))
return E_ITS_MAPC_COLLECTION_OOR;
collection = kzalloc(sizeof(*collection), GFP_KERNEL);
{
struct its_collection *collection;
struct its_device *device;
- struct its_itte *itte;
+ struct its_ite *ite;
/*
* Clearing the mapping for that collection ID removes the
if (!collection)
return;
- for_each_lpi_its(device, itte, its)
- if (itte->collection &&
- itte->collection->collection_id == coll_id)
- itte->collection = NULL;
+ for_each_lpi_its(device, ite, its)
+ if (ite->collection &&
+ ite->collection->collection_id == coll_id)
+ ite->collection = NULL;
list_del(&collection->coll_list);
kfree(collection);
}
+/* Must be called with its_lock mutex held */
+static struct its_ite *vgic_its_alloc_ite(struct its_device *device,
+ struct its_collection *collection,
+ u32 lpi_id, u32 event_id)
+{
+ struct its_ite *ite;
+
+ ite = kzalloc(sizeof(*ite), GFP_KERNEL);
+ if (!ite)
+ return ERR_PTR(-ENOMEM);
+
+ ite->event_id = event_id;
+ ite->collection = collection;
+ ite->lpi = lpi_id;
+
+ list_add_tail(&ite->ite_list, &device->itt_head);
+ return ite;
+}
+
/*
* The MAPTI and MAPI commands map LPIs to ITTEs.
* Must be called with its_lock mutex held.
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
u32 coll_id = its_cmd_get_collection(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
+ struct kvm_vcpu *vcpu = NULL;
struct its_device *device;
struct its_collection *collection, *new_coll = NULL;
- int lpi_nr;
struct vgic_irq *irq;
+ int lpi_nr;
device = find_its_device(its, device_id);
if (!device)
return E_ITS_MAPTI_UNMAPPED_DEVICE;
+ if (event_id >= BIT_ULL(device->num_eventid_bits))
+ return E_ITS_MAPTI_ID_OOR;
+
if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI)
lpi_nr = its_cmd_get_physical_id(its_cmd);
else
return E_ITS_MAPTI_PHYSICALID_OOR;
/* If there is an existing mapping, behavior is UNPREDICTABLE. */
- if (find_itte(its, device_id, event_id))
+ if (find_ite(its, device_id, event_id))
return 0;
collection = find_collection(its, coll_id);
new_coll = collection;
}
- itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
- if (!itte) {
+ ite = vgic_its_alloc_ite(device, collection, lpi_nr, event_id);
+ if (IS_ERR(ite)) {
if (new_coll)
vgic_its_free_collection(its, coll_id);
- return -ENOMEM;
+ return PTR_ERR(ite);
}
- itte->event_id = event_id;
- list_add_tail(&itte->itte_list, &device->itt_head);
-
- itte->collection = collection;
- itte->lpi = lpi_nr;
+ if (its_is_collection_mapped(collection))
+ vcpu = kvm_get_vcpu(kvm, collection->target_addr);
- irq = vgic_add_lpi(kvm, lpi_nr);
+ irq = vgic_add_lpi(kvm, lpi_nr, vcpu);
if (IS_ERR(irq)) {
if (new_coll)
vgic_its_free_collection(its, coll_id);
- its_free_itte(kvm, itte);
+ its_free_ite(kvm, ite);
return PTR_ERR(irq);
}
- itte->irq = irq;
-
- update_affinity_itte(kvm, itte);
-
- /*
- * We "cache" the configuration table entries in out struct vgic_irq's.
- * However we only have those structs for mapped IRQs, so we read in
- * the respective config data from memory here upon mapping the LPI.
- */
- update_lpi_config(kvm, itte->irq, NULL);
+ ite->irq = irq;
return 0;
}
/* Requires the its_lock to be held. */
static void vgic_its_unmap_device(struct kvm *kvm, struct its_device *device)
{
- struct its_itte *itte, *temp;
+ struct its_ite *ite, *temp;
/*
* The spec says that unmapping a device with still valid
* ITTEs associated is UNPREDICTABLE. We remove all ITTEs,
* since we cannot leave the memory unreferenced.
*/
- list_for_each_entry_safe(itte, temp, &device->itt_head, itte_list)
- its_free_itte(kvm, itte);
+ list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list)
+ its_free_ite(kvm, ite);
list_del(&device->dev_list);
kfree(device);
}
+/* Must be called with its_lock mutex held */
+static struct its_device *vgic_its_alloc_device(struct vgic_its *its,
+ u32 device_id, gpa_t itt_addr,
+ u8 num_eventid_bits)
+{
+ struct its_device *device;
+
+ device = kzalloc(sizeof(*device), GFP_KERNEL);
+ if (!device)
+ return ERR_PTR(-ENOMEM);
+
+ device->device_id = device_id;
+ device->itt_addr = itt_addr;
+ device->num_eventid_bits = num_eventid_bits;
+ INIT_LIST_HEAD(&device->itt_head);
+
+ list_add_tail(&device->dev_list, &its->device_list);
+ return device;
+}
+
/*
* MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs).
* Must be called with the its_lock mutex held.
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
bool valid = its_cmd_get_validbit(its_cmd);
+ u8 num_eventid_bits = its_cmd_get_size(its_cmd);
+ gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd);
struct its_device *device;
- if (!vgic_its_check_id(its, its->baser_device_table, device_id))
+ if (!vgic_its_check_id(its, its->baser_device_table, device_id, NULL))
return E_ITS_MAPD_DEVICE_OOR;
+ if (valid && num_eventid_bits > VITS_TYPER_IDBITS)
+ return E_ITS_MAPD_ITTSIZE_OOR;
+
device = find_its_device(its, device_id);
/*
if (!valid)
return 0;
- device = kzalloc(sizeof(struct its_device), GFP_KERNEL);
- if (!device)
- return -ENOMEM;
-
- device->device_id = device_id;
- INIT_LIST_HEAD(&device->itt_head);
-
- list_add_tail(&device->dev_list, &its->device_list);
+ device = vgic_its_alloc_device(its, device_id, itt_addr,
+ num_eventid_bits);
+ if (IS_ERR(device))
+ return PTR_ERR(device);
return 0;
}
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
- itte = find_itte(its, device_id, event_id);
- if (!itte)
+ ite = find_ite(its, device_id, event_id);
+ if (!ite)
return E_ITS_CLEAR_UNMAPPED_INTERRUPT;
- itte->irq->pending_latch = false;
+ ite->irq->pending_latch = false;
return 0;
}
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
- itte = find_itte(its, device_id, event_id);
- if (!itte)
+ ite = find_ite(its, device_id, event_id);
+ if (!ite)
return E_ITS_INV_UNMAPPED_INTERRUPT;
- return update_lpi_config(kvm, itte->irq, NULL);
+ return update_lpi_config(kvm, ite->irq, NULL);
}
/*
vcpu = kvm_get_vcpu(kvm, collection->target_addr);
- irq_count = vgic_copy_lpi_list(kvm, &intids);
+ irq_count = vgic_copy_lpi_list(vcpu, &intids);
if (irq_count < 0)
return irq_count;
return extract_bytes(its->creadr, addr & 0x7, len);
}
+static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm,
+ struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 cmd_offset;
+ int ret = 0;
+
+ mutex_lock(&its->cmd_lock);
+
+ if (its->enabled) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ cmd_offset = ITS_CMD_OFFSET(val);
+ if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ its->creadr = cmd_offset;
+out:
+ mutex_unlock(&its->cmd_lock);
+ return ret;
+}
+
#define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7)
static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm,
struct vgic_its *its,
gpa_t addr, unsigned int len,
unsigned long val)
{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
u64 entry_size, device_type;
u64 reg, *regptr, clearbits = 0;
switch (BASER_INDEX(addr)) {
case 0:
regptr = &its->baser_device_table;
- entry_size = 8;
+ entry_size = abi->dte_esz;
device_type = GITS_BASER_TYPE_DEVICE;
break;
case 1:
regptr = &its->baser_coll_table;
- entry_size = 8;
+ entry_size = abi->cte_esz;
device_type = GITS_BASER_TYPE_COLLECTION;
clearbits = GITS_BASER_INDIRECT;
break;
.its_write = wr, \
}
+#define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\
+{ \
+ .reg_offset = off, \
+ .len = length, \
+ .access_flags = acc, \
+ .its_read = rd, \
+ .its_write = wr, \
+ .uaccess_its_write = uwr, \
+}
+
static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its,
gpa_t addr, unsigned int len, unsigned long val)
{
REGISTER_ITS_DESC(GITS_CTLR,
vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4,
VGIC_ACCESS_32bit),
- REGISTER_ITS_DESC(GITS_IIDR,
- vgic_mmio_read_its_iidr, its_mmio_write_wi, 4,
+ REGISTER_ITS_DESC_UACCESS(GITS_IIDR,
+ vgic_mmio_read_its_iidr, its_mmio_write_wi,
+ vgic_mmio_uaccess_write_its_iidr, 4,
VGIC_ACCESS_32bit),
REGISTER_ITS_DESC(GITS_TYPER,
vgic_mmio_read_its_typer, its_mmio_write_wi, 8,
REGISTER_ITS_DESC(GITS_CWRITER,
vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8,
VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
- REGISTER_ITS_DESC(GITS_CREADR,
- vgic_mmio_read_its_creadr, its_mmio_write_wi, 8,
+ REGISTER_ITS_DESC_UACCESS(GITS_CREADR,
+ vgic_mmio_read_its_creadr, its_mmio_write_wi,
+ vgic_mmio_uaccess_write_its_creadr, 8,
VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
REGISTER_ITS_DESC(GITS_BASER,
vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40,
its_sync_lpi_pending_table(vcpu);
}
-static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
+static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its,
+ u64 addr)
{
struct vgic_io_device *iodev = &its->iodev;
int ret;
- if (!its->initialized)
- return -EBUSY;
-
- if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
- return -ENXIO;
+ mutex_lock(&kvm->slots_lock);
+ if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ its->vgic_its_base = addr;
iodev->regions = its_registers;
iodev->nr_regions = ARRAY_SIZE(its_registers);
kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops);
iodev->base_addr = its->vgic_its_base;
iodev->iodev_type = IODEV_ITS;
iodev->its = its;
- mutex_lock(&kvm->slots_lock);
ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr,
KVM_VGIC_V3_ITS_SIZE, &iodev->dev);
+out:
mutex_unlock(&kvm->slots_lock);
return ret;
(GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \
GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \
GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) | \
- ((8ULL - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) | \
GITS_BASER_PAGE_SIZE_64K)
#define INITIAL_PROPBASER_VALUE \
INIT_LIST_HEAD(&its->collection_list);
dev->kvm->arch.vgic.has_its = true;
- its->initialized = false;
its->enabled = false;
its->dev = dev;
dev->private = its;
- return 0;
+ return vgic_its_set_abi(its, NR_ITS_ABIS - 1);
+}
+
+static void vgic_its_free_device(struct kvm *kvm, struct its_device *dev)
+{
+ struct its_ite *ite, *tmp;
+
+ list_for_each_entry_safe(ite, tmp, &dev->itt_head, ite_list)
+ its_free_ite(kvm, ite);
+ list_del(&dev->dev_list);
+ kfree(dev);
}
static void vgic_its_destroy(struct kvm_device *kvm_dev)
{
struct kvm *kvm = kvm_dev->kvm;
struct vgic_its *its = kvm_dev->private;
- struct its_device *dev;
- struct its_itte *itte;
- struct list_head *dev_cur, *dev_temp;
struct list_head *cur, *temp;
/*
return;
mutex_lock(&its->its_lock);
- list_for_each_safe(dev_cur, dev_temp, &its->device_list) {
- dev = container_of(dev_cur, struct its_device, dev_list);
- list_for_each_safe(cur, temp, &dev->itt_head) {
- itte = (container_of(cur, struct its_itte, itte_list));
- its_free_itte(kvm, itte);
- }
- list_del(dev_cur);
- kfree(dev);
+ list_for_each_safe(cur, temp, &its->device_list) {
+ struct its_device *dev;
+
+ dev = list_entry(cur, struct its_device, dev_list);
+ vgic_its_free_device(kvm, dev);
}
list_for_each_safe(cur, temp, &its->collection_list) {
+ struct its_collection *coll;
+
+ coll = list_entry(cur, struct its_collection, coll_list);
list_del(cur);
- kfree(container_of(cur, struct its_collection, coll_list));
+ kfree(coll);
}
mutex_unlock(&its->its_lock);
kfree(its);
}
+int vgic_its_has_attr_regs(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ const struct vgic_register_region *region;
+ gpa_t offset = attr->attr;
+ int align;
+
+ align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7;
+
+ if (offset & align)
+ return -EINVAL;
+
+ region = vgic_find_mmio_region(its_registers,
+ ARRAY_SIZE(its_registers),
+ offset);
+ if (!region)
+ return -ENXIO;
+
+ return 0;
+}
+
+int vgic_its_attr_regs_access(struct kvm_device *dev,
+ struct kvm_device_attr *attr,
+ u64 *reg, bool is_write)
+{
+ const struct vgic_register_region *region;
+ struct vgic_its *its;
+ gpa_t addr, offset;
+ unsigned int len;
+ int align, ret = 0;
+
+ its = dev->private;
+ offset = attr->attr;
+
+ /*
+ * Although the spec supports upper/lower 32-bit accesses to
+ * 64-bit ITS registers, the userspace ABI requires 64-bit
+ * accesses to all 64-bit wide registers. We therefore only
+ * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID
+ * registers
+ */
+ if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4))
+ align = 0x3;
+ else
+ align = 0x7;
+
+ if (offset & align)
+ return -EINVAL;
+
+ mutex_lock(&dev->kvm->lock);
+
+ if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+ region = vgic_find_mmio_region(its_registers,
+ ARRAY_SIZE(its_registers),
+ offset);
+ if (!region) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!lock_all_vcpus(dev->kvm)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ addr = its->vgic_its_base + offset;
+
+ len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4;
+
+ if (is_write) {
+ if (region->uaccess_its_write)
+ ret = region->uaccess_its_write(dev->kvm, its, addr,
+ len, *reg);
+ else
+ region->its_write(dev->kvm, its, addr, len, *reg);
+ } else {
+ *reg = region->its_read(dev->kvm, its, addr, len);
+ }
+ unlock_all_vcpus(dev->kvm);
+out:
+ mutex_unlock(&dev->kvm->lock);
+ return ret;
+}
+
+static u32 compute_next_devid_offset(struct list_head *h,
+ struct its_device *dev)
+{
+ struct its_device *next;
+ u32 next_offset;
+
+ if (list_is_last(&dev->dev_list, h))
+ return 0;
+ next = list_next_entry(dev, dev_list);
+ next_offset = next->device_id - dev->device_id;
+
+ return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET);
+}
+
+static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite)
+{
+ struct its_ite *next;
+ u32 next_offset;
+
+ if (list_is_last(&ite->ite_list, h))
+ return 0;
+ next = list_next_entry(ite, ite_list);
+ next_offset = next->event_id - ite->event_id;
+
+ return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET);
+}
+
+/**
+ * entry_fn_t - Callback called on a table entry restore path
+ * @its: its handle
+ * @id: id of the entry
+ * @entry: pointer to the entry
+ * @opaque: pointer to an opaque data
+ *
+ * Return: < 0 on error, 0 if last element was identified, id offset to next
+ * element otherwise
+ */
+typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry,
+ void *opaque);
+
+/**
+ * scan_its_table - Scan a contiguous table in guest RAM and applies a function
+ * to each entry
+ *
+ * @its: its handle
+ * @base: base gpa of the table
+ * @size: size of the table in bytes
+ * @esz: entry size in bytes
+ * @start_id: the ID of the first entry in the table
+ * (non zero for 2d level tables)
+ * @fn: function to apply on each entry
+ *
+ * Return: < 0 on error, 0 if last element was identified, 1 otherwise
+ * (the last element may not be found on second level tables)
+ */
+static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
+ int start_id, entry_fn_t fn, void *opaque)
+{
+ void *entry = kzalloc(esz, GFP_KERNEL);
+ struct kvm *kvm = its->dev->kvm;
+ unsigned long len = size;
+ int id = start_id;
+ gpa_t gpa = base;
+ int ret;
+
+ while (len > 0) {
+ int next_offset;
+ size_t byte_offset;
+
+ ret = kvm_read_guest(kvm, gpa, entry, esz);
+ if (ret)
+ goto out;
+
+ next_offset = fn(its, id, entry, opaque);
+ if (next_offset <= 0) {
+ ret = next_offset;
+ goto out;
+ }
+
+ byte_offset = next_offset * esz;
+ id += next_offset;
+ gpa += byte_offset;
+ len -= byte_offset;
+ }
+ ret = 1;
+
+out:
+ kfree(entry);
+ return ret;
+}
+
+/**
+ * vgic_its_save_ite - Save an interrupt translation entry at @gpa
+ */
+static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
+ struct its_ite *ite, gpa_t gpa, int ite_esz)
+{
+ struct kvm *kvm = its->dev->kvm;
+ u32 next_offset;
+ u64 val;
+
+ next_offset = compute_next_eventid_offset(&dev->itt_head, ite);
+ val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) |
+ ((u64)ite->lpi << KVM_ITS_ITE_PINTID_SHIFT) |
+ ite->collection->collection_id;
+ val = cpu_to_le64(val);
+ return kvm_write_guest(kvm, gpa, &val, ite_esz);
+}
+
+/**
+ * vgic_its_restore_ite - restore an interrupt translation entry
+ * @event_id: id used for indexing
+ * @ptr: pointer to the ITE entry
+ * @opaque: pointer to the its_device
+ */
+static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id,
+ void *ptr, void *opaque)
+{
+ struct its_device *dev = (struct its_device *)opaque;
+ struct its_collection *collection;
+ struct kvm *kvm = its->dev->kvm;
+ struct kvm_vcpu *vcpu = NULL;
+ u64 val;
+ u64 *p = (u64 *)ptr;
+ struct vgic_irq *irq;
+ u32 coll_id, lpi_id;
+ struct its_ite *ite;
+ u32 offset;
+
+ val = *p;
+
+ val = le64_to_cpu(val);
+
+ coll_id = val & KVM_ITS_ITE_ICID_MASK;
+ lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT;
+
+ if (!lpi_id)
+ return 1; /* invalid entry, no choice but to scan next entry */
+
+ if (lpi_id < VGIC_MIN_LPI)
+ return -EINVAL;
+
+ offset = val >> KVM_ITS_ITE_NEXT_SHIFT;
+ if (event_id + offset >= BIT_ULL(dev->num_eventid_bits))
+ return -EINVAL;
+
+ collection = find_collection(its, coll_id);
+ if (!collection)
+ return -EINVAL;
+
+ ite = vgic_its_alloc_ite(dev, collection, lpi_id, event_id);
+ if (IS_ERR(ite))
+ return PTR_ERR(ite);
+
+ if (its_is_collection_mapped(collection))
+ vcpu = kvm_get_vcpu(kvm, collection->target_addr);
+
+ irq = vgic_add_lpi(kvm, lpi_id, vcpu);
+ if (IS_ERR(irq))
+ return PTR_ERR(irq);
+ ite->irq = irq;
+
+ return offset;
+}
+
+static int vgic_its_ite_cmp(void *priv, struct list_head *a,
+ struct list_head *b)
+{
+ struct its_ite *itea = container_of(a, struct its_ite, ite_list);
+ struct its_ite *iteb = container_of(b, struct its_ite, ite_list);
+
+ if (itea->event_id < iteb->event_id)
+ return -1;
+ else
+ return 1;
+}
+
+static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ gpa_t base = device->itt_addr;
+ struct its_ite *ite;
+ int ret;
+ int ite_esz = abi->ite_esz;
+
+ list_sort(NULL, &device->itt_head, vgic_its_ite_cmp);
+
+ list_for_each_entry(ite, &device->itt_head, ite_list) {
+ gpa_t gpa = base + ite->event_id * ite_esz;
+
+ ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ gpa_t base = dev->itt_addr;
+ int ret;
+ int ite_esz = abi->ite_esz;
+ size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz;
+
+ ret = scan_its_table(its, base, max_size, ite_esz, 0,
+ vgic_its_restore_ite, dev);
+
+ return ret;
+}
+
+/**
+ * vgic_its_save_dte - Save a device table entry at a given GPA
+ *
+ * @its: ITS handle
+ * @dev: ITS device
+ * @ptr: GPA
+ */
+static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev,
+ gpa_t ptr, int dte_esz)
+{
+ struct kvm *kvm = its->dev->kvm;
+ u64 val, itt_addr_field;
+ u32 next_offset;
+
+ itt_addr_field = dev->itt_addr >> 8;
+ next_offset = compute_next_devid_offset(&its->device_list, dev);
+ val = (1ULL << KVM_ITS_DTE_VALID_SHIFT |
+ ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) |
+ (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) |
+ (dev->num_eventid_bits - 1));
+ val = cpu_to_le64(val);
+ return kvm_write_guest(kvm, ptr, &val, dte_esz);
+}
+
+/**
+ * vgic_its_restore_dte - restore a device table entry
+ *
+ * @its: its handle
+ * @id: device id the DTE corresponds to
+ * @ptr: kernel VA where the 8 byte DTE is located
+ * @opaque: unused
+ *
+ * Return: < 0 on error, 0 if the dte is the last one, id offset to the
+ * next dte otherwise
+ */
+static int vgic_its_restore_dte(struct vgic_its *its, u32 id,
+ void *ptr, void *opaque)
+{
+ struct its_device *dev;
+ gpa_t itt_addr;
+ u8 num_eventid_bits;
+ u64 entry = *(u64 *)ptr;
+ bool valid;
+ u32 offset;
+ int ret;
+
+ entry = le64_to_cpu(entry);
+
+ valid = entry >> KVM_ITS_DTE_VALID_SHIFT;
+ num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1;
+ itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK)
+ >> KVM_ITS_DTE_ITTADDR_SHIFT) << 8;
+
+ if (!valid)
+ return 1;
+
+ /* dte entry is valid */
+ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT;
+
+ dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits);
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
+
+ ret = vgic_its_restore_itt(its, dev);
+ if (ret) {
+ vgic_its_free_device(its->dev->kvm, dev);
+ return ret;
+ }
+
+ return offset;
+}
+
+static int vgic_its_device_cmp(void *priv, struct list_head *a,
+ struct list_head *b)
+{
+ struct its_device *deva = container_of(a, struct its_device, dev_list);
+ struct its_device *devb = container_of(b, struct its_device, dev_list);
+
+ if (deva->device_id < devb->device_id)
+ return -1;
+ else
+ return 1;
+}
+
+/**
+ * vgic_its_save_device_tables - Save the device table and all ITT
+ * into guest RAM
+ *
+ * L1/L2 handling is hidden by vgic_its_check_id() helper which directly
+ * returns the GPA of the device entry
+ */
+static int vgic_its_save_device_tables(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ struct its_device *dev;
+ int dte_esz = abi->dte_esz;
+ u64 baser;
+
+ baser = its->baser_device_table;
+
+ list_sort(NULL, &its->device_list, vgic_its_device_cmp);
+
+ list_for_each_entry(dev, &its->device_list, dev_list) {
+ int ret;
+ gpa_t eaddr;
+
+ if (!vgic_its_check_id(its, baser,
+ dev->device_id, &eaddr))
+ return -EINVAL;
+
+ ret = vgic_its_save_itt(its, dev);
+ if (ret)
+ return ret;
+
+ ret = vgic_its_save_dte(its, dev, eaddr, dte_esz);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+/**
+ * handle_l1_dte - callback used for L1 device table entries (2 stage case)
+ *
+ * @its: its handle
+ * @id: index of the entry in the L1 table
+ * @addr: kernel VA
+ * @opaque: unused
+ *
+ * L1 table entries are scanned by steps of 1 entry
+ * Return < 0 if error, 0 if last dte was found when scanning the L2
+ * table, +1 otherwise (meaning next L1 entry must be scanned)
+ */
+static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr,
+ void *opaque)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ int l2_start_id = id * (SZ_64K / abi->dte_esz);
+ u64 entry = *(u64 *)addr;
+ int dte_esz = abi->dte_esz;
+ gpa_t gpa;
+ int ret;
+
+ entry = le64_to_cpu(entry);
+
+ if (!(entry & KVM_ITS_L1E_VALID_MASK))
+ return 1;
+
+ gpa = entry & KVM_ITS_L1E_ADDR_MASK;
+
+ ret = scan_its_table(its, gpa, SZ_64K, dte_esz,
+ l2_start_id, vgic_its_restore_dte, NULL);
+
+ if (ret <= 0)
+ return ret;
+
+ return 1;
+}
+
+/**
+ * vgic_its_restore_device_tables - Restore the device table and all ITT
+ * from guest RAM to internal data structs
+ */
+static int vgic_its_restore_device_tables(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ u64 baser = its->baser_device_table;
+ int l1_esz, ret;
+ int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
+ gpa_t l1_gpa;
+
+ if (!(baser & GITS_BASER_VALID))
+ return 0;
+
+ l1_gpa = BASER_ADDRESS(baser);
+
+ if (baser & GITS_BASER_INDIRECT) {
+ l1_esz = GITS_LVL1_ENTRY_SIZE;
+ ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0,
+ handle_l1_dte, NULL);
+ } else {
+ l1_esz = abi->dte_esz;
+ ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0,
+ vgic_its_restore_dte, NULL);
+ }
+
+ if (ret > 0)
+ ret = -EINVAL;
+
+ return ret;
+}
+
+static int vgic_its_save_cte(struct vgic_its *its,
+ struct its_collection *collection,
+ gpa_t gpa, int esz)
+{
+ u64 val;
+
+ val = (1ULL << KVM_ITS_CTE_VALID_SHIFT |
+ ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) |
+ collection->collection_id);
+ val = cpu_to_le64(val);
+ return kvm_write_guest(its->dev->kvm, gpa, &val, esz);
+}
+
+static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
+{
+ struct its_collection *collection;
+ struct kvm *kvm = its->dev->kvm;
+ u32 target_addr, coll_id;
+ u64 val;
+ int ret;
+
+ BUG_ON(esz > sizeof(val));
+ ret = kvm_read_guest(kvm, gpa, &val, esz);
+ if (ret)
+ return ret;
+ val = le64_to_cpu(val);
+ if (!(val & KVM_ITS_CTE_VALID_MASK))
+ return 0;
+
+ target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT);
+ coll_id = val & KVM_ITS_CTE_ICID_MASK;
+
+ if (target_addr >= atomic_read(&kvm->online_vcpus))
+ return -EINVAL;
+
+ collection = find_collection(its, coll_id);
+ if (collection)
+ return -EEXIST;
+ ret = vgic_its_alloc_collection(its, &collection, coll_id);
+ if (ret)
+ return ret;
+ collection->target_addr = target_addr;
+ return 1;
+}
+
+/**
+ * vgic_its_save_collection_table - Save the collection table into
+ * guest RAM
+ */
+static int vgic_its_save_collection_table(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ struct its_collection *collection;
+ u64 val;
+ gpa_t gpa;
+ size_t max_size, filled = 0;
+ int ret, cte_esz = abi->cte_esz;
+
+ gpa = BASER_ADDRESS(its->baser_coll_table);
+ if (!gpa)
+ return 0;
+
+ max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+
+ list_for_each_entry(collection, &its->collection_list, coll_list) {
+ ret = vgic_its_save_cte(its, collection, gpa, cte_esz);
+ if (ret)
+ return ret;
+ gpa += cte_esz;
+ filled += cte_esz;
+ }
+
+ if (filled == max_size)
+ return 0;
+
+ /*
+ * table is not fully filled, add a last dummy element
+ * with valid bit unset
+ */
+ val = 0;
+ BUG_ON(cte_esz > sizeof(val));
+ ret = kvm_write_guest(its->dev->kvm, gpa, &val, cte_esz);
+ return ret;
+}
+
+/**
+ * vgic_its_restore_collection_table - reads the collection table
+ * in guest memory and restores the ITS internal state. Requires the
+ * BASER registers to be restored before.
+ */
+static int vgic_its_restore_collection_table(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ int cte_esz = abi->cte_esz;
+ size_t max_size, read = 0;
+ gpa_t gpa;
+ int ret;
+
+ if (!(its->baser_coll_table & GITS_BASER_VALID))
+ return 0;
+
+ gpa = BASER_ADDRESS(its->baser_coll_table);
+
+ max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+
+ while (read < max_size) {
+ ret = vgic_its_restore_cte(its, gpa, cte_esz);
+ if (ret <= 0)
+ break;
+ gpa += cte_esz;
+ read += cte_esz;
+ }
+ return ret;
+}
+
+/**
+ * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM
+ * according to v0 ABI
+ */
+static int vgic_its_save_tables_v0(struct vgic_its *its)
+{
+ struct kvm *kvm = its->dev->kvm;
+ int ret;
+
+ mutex_lock(&kvm->lock);
+ mutex_lock(&its->its_lock);
+
+ if (!lock_all_vcpus(kvm)) {
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
+ }
+
+ ret = vgic_its_save_device_tables(its);
+ if (ret)
+ goto out;
+
+ ret = vgic_its_save_collection_table(its);
+
+out:
+ unlock_all_vcpus(kvm);
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
+/**
+ * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM
+ * to internal data structs according to V0 ABI
+ *
+ */
+static int vgic_its_restore_tables_v0(struct vgic_its *its)
+{
+ struct kvm *kvm = its->dev->kvm;
+ int ret;
+
+ mutex_lock(&kvm->lock);
+ mutex_lock(&its->its_lock);
+
+ if (!lock_all_vcpus(kvm)) {
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
+ }
+
+ ret = vgic_its_restore_collection_table(its);
+ if (ret)
+ goto out;
+
+ ret = vgic_its_restore_device_tables(its);
+out:
+ unlock_all_vcpus(kvm);
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+
+ return ret;
+}
+
+static int vgic_its_commit_v0(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi;
+
+ abi = vgic_its_get_abi(its);
+ its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK;
+ its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK;
+
+ its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5)
+ << GITS_BASER_ENTRY_SIZE_SHIFT);
+
+ its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5)
+ << GITS_BASER_ENTRY_SIZE_SHIFT);
+ return 0;
+}
+
static int vgic_its_has_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
return 0;
+ case KVM_DEV_ARM_ITS_SAVE_TABLES:
+ return 0;
+ case KVM_DEV_ARM_ITS_RESTORE_TABLES:
+ return 0;
}
break;
+ case KVM_DEV_ARM_VGIC_GRP_ITS_REGS:
+ return vgic_its_has_attr_regs(dev, attr);
}
return -ENXIO;
}
if (ret)
return ret;
- its->vgic_its_base = addr;
-
- return 0;
+ return vgic_register_its_iodev(dev->kvm, its, addr);
}
- case KVM_DEV_ARM_VGIC_GRP_CTRL:
+ case KVM_DEV_ARM_VGIC_GRP_CTRL: {
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
- its->initialized = true;
-
+ /* Nothing to do */
return 0;
+ case KVM_DEV_ARM_ITS_SAVE_TABLES:
+ return abi->save_tables(its);
+ case KVM_DEV_ARM_ITS_RESTORE_TABLES:
+ return abi->restore_tables(its);
}
- break;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 reg;
+
+ if (get_user(reg, uaddr))
+ return -EFAULT;
+
+ return vgic_its_attr_regs_access(dev, attr, ®, true);
+ }
}
return -ENXIO;
}
if (copy_to_user(uaddr, &addr, sizeof(addr)))
return -EFAULT;
break;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 reg;
+ int ret;
+
+ ret = vgic_its_attr_regs_access(dev, attr, ®, false);
+ if (ret)
+ return ret;
+ return put_user(reg, uaddr);
+ }
default:
return -ENXIO;
}
- }
return 0;
}
return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
KVM_DEV_TYPE_ARM_VGIC_ITS);
}
-
-/*
- * Registers all ITSes with the kvm_io_bus framework.
- * To follow the existing VGIC initialization sequence, this has to be
- * done as late as possible, just before the first VCPU runs.
- */
-int vgic_register_its_iodevs(struct kvm *kvm)
-{
- struct kvm_device *dev;
- int ret = 0;
-
- list_for_each_entry(dev, &kvm->devices, vm_node) {
- if (dev->ops != &kvm_arm_vgic_its_ops)
- continue;
-
- ret = vgic_register_its_iodev(kvm, dev->private);
- if (ret)
- return ret;
- /*
- * We don't need to care about tearing down previously
- * registered ITSes, as the kvm_io_bus framework removes
- * them for us if the VM gets destroyed.
- */
- }
-
- return ret;
-}
return 0;
}
+static int vgic_check_type(struct kvm *kvm, int type_needed)
+{
+ if (kvm->arch.vgic.vgic_model != type_needed)
+ return -ENODEV;
+ else
+ return 0;
+}
+
/**
* kvm_vgic_addr - set or get vgic VM base addresses
* @kvm: pointer to the vm struct
{
int r = 0;
struct vgic_dist *vgic = &kvm->arch.vgic;
- int type_needed;
phys_addr_t *addr_ptr, alignment;
mutex_lock(&kvm->lock);
switch (type) {
case KVM_VGIC_V2_ADDR_TYPE_DIST:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
addr_ptr = &vgic->vgic_dist_base;
alignment = SZ_4K;
break;
case KVM_VGIC_V2_ADDR_TYPE_CPU:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
addr_ptr = &vgic->vgic_cpu_base;
alignment = SZ_4K;
break;
case KVM_VGIC_V3_ADDR_TYPE_DIST:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
addr_ptr = &vgic->vgic_dist_base;
alignment = SZ_64K;
break;
case KVM_VGIC_V3_ADDR_TYPE_REDIST:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
+ if (r)
+ break;
+ if (write) {
+ r = vgic_v3_set_redist_base(kvm, *addr);
+ goto out;
+ }
addr_ptr = &vgic->vgic_redist_base;
- alignment = SZ_64K;
break;
default:
r = -ENODEV;
- goto out;
}
- if (vgic->vgic_model != type_needed) {
- r = -ENODEV;
+ if (r)
goto out;
- }
if (write) {
r = vgic_check_ioaddr(kvm, addr_ptr, *addr, alignment);
}
}
-static void unlock_all_vcpus(struct kvm *kvm)
+void unlock_all_vcpus(struct kvm *kvm)
{
unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
}
/* Returns true if all vcpus were locked, false otherwise */
-static bool lock_all_vcpus(struct kvm *kvm)
+bool lock_all_vcpus(struct kvm *kvm)
{
struct kvm_vcpu *tmp_vcpu;
int c;
reg = tmp32;
return vgic_v3_attr_regs_access(dev, attr, ®, true);
}
+ case KVM_DEV_ARM_VGIC_GRP_CTRL: {
+ int ret;
+
+ switch (attr->attr) {
+ case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES:
+ mutex_lock(&dev->kvm->lock);
+
+ if (!lock_all_vcpus(dev->kvm)) {
+ mutex_unlock(&dev->kvm->lock);
+ return -EBUSY;
+ }
+ ret = vgic_v3_save_pending_tables(dev->kvm);
+ unlock_all_vcpus(dev->kvm);
+ mutex_unlock(&dev->kvm->lock);
+ return ret;
+ }
+ break;
+ }
}
return -ENXIO;
}
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
return 0;
+ case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES:
+ return 0;
}
}
return -ENXIO;
return SZ_64K;
}
-int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
+/**
+ * vgic_register_redist_iodev - register a single redist iodev
+ * @vcpu: The VCPU to which the redistributor belongs
+ *
+ * Register a KVM iodev for this VCPU's redistributor using the address
+ * provided.
+ *
+ * Return 0 on success, -ERRNO otherwise.
+ */
+int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct vgic_dist *vgic = &kvm->arch.vgic;
+ struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
+ struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+ gpa_t rd_base, sgi_base;
+ int ret;
+
+ /*
+ * We may be creating VCPUs before having set the base address for the
+ * redistributor region, in which case we will come back to this
+ * function for all VCPUs when the base address is set. Just return
+ * without doing any work for now.
+ */
+ if (IS_VGIC_ADDR_UNDEF(vgic->vgic_redist_base))
+ return 0;
+
+ if (!vgic_v3_check_base(kvm))
+ return -EINVAL;
+
+ rd_base = vgic->vgic_redist_base + kvm_vcpu_get_idx(vcpu) * SZ_64K * 2;
+ sgi_base = rd_base + SZ_64K;
+
+ kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
+ rd_dev->base_addr = rd_base;
+ rd_dev->iodev_type = IODEV_REDIST;
+ rd_dev->regions = vgic_v3_rdbase_registers;
+ rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
+ rd_dev->redist_vcpu = vcpu;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
+ SZ_64K, &rd_dev->dev);
+ mutex_unlock(&kvm->slots_lock);
+
+ if (ret)
+ return ret;
+
+ kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
+ sgi_dev->base_addr = sgi_base;
+ sgi_dev->iodev_type = IODEV_REDIST;
+ sgi_dev->regions = vgic_v3_sgibase_registers;
+ sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
+ sgi_dev->redist_vcpu = vcpu;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
+ SZ_64K, &sgi_dev->dev);
+ mutex_unlock(&kvm->slots_lock);
+ if (ret)
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+ &rd_dev->dev);
+
+ return ret;
+}
+
+static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
+{
+ struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
+ struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+
+ kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev);
+ kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &sgi_dev->dev);
+}
+
+static int vgic_register_all_redist_iodevs(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
int c, ret = 0;
kvm_for_each_vcpu(c, vcpu, kvm) {
- gpa_t rd_base = redist_base_address + c * SZ_64K * 2;
- gpa_t sgi_base = rd_base + SZ_64K;
- struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
- struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
-
- kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
- rd_dev->base_addr = rd_base;
- rd_dev->iodev_type = IODEV_REDIST;
- rd_dev->regions = vgic_v3_rdbase_registers;
- rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
- rd_dev->redist_vcpu = vcpu;
-
- mutex_lock(&kvm->slots_lock);
- ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
- SZ_64K, &rd_dev->dev);
- mutex_unlock(&kvm->slots_lock);
-
+ ret = vgic_register_redist_iodev(vcpu);
if (ret)
break;
-
- kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
- sgi_dev->base_addr = sgi_base;
- sgi_dev->iodev_type = IODEV_REDIST;
- sgi_dev->regions = vgic_v3_sgibase_registers;
- sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
- sgi_dev->redist_vcpu = vcpu;
-
- mutex_lock(&kvm->slots_lock);
- ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
- SZ_64K, &sgi_dev->dev);
- mutex_unlock(&kvm->slots_lock);
- if (ret) {
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
- &rd_dev->dev);
- break;
- }
}
if (ret) {
/* The current c failed, so we start with the previous one. */
for (c--; c >= 0; c--) {
- struct vgic_cpu *vgic_cpu;
-
vcpu = kvm_get_vcpu(kvm, c);
- vgic_cpu = &vcpu->arch.vgic_cpu;
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
- &vgic_cpu->rd_iodev.dev);
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
- &vgic_cpu->sgi_iodev.dev);
+ vgic_unregister_redist_iodev(vcpu);
}
}
return ret;
}
+int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr)
+{
+ struct vgic_dist *vgic = &kvm->arch.vgic;
+ int ret;
+
+ /* vgic_check_ioaddr makes sure we don't do this twice */
+ ret = vgic_check_ioaddr(kvm, &vgic->vgic_redist_base, addr, SZ_64K);
+ if (ret)
+ return ret;
+
+ vgic->vgic_redist_base = addr;
+ if (!vgic_v3_check_base(kvm)) {
+ vgic->vgic_redist_base = VGIC_ADDR_UNDEF;
+ return -EINVAL;
+ }
+
+ /*
+ * Register iodevs for each existing VCPU. Adding more VCPUs
+ * afterwards will register the iodevs when needed.
+ */
+ ret = vgic_register_all_redist_iodevs(kvm);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
{
const struct vgic_register_region *region;
return 0;
}
-/* Find the proper register handler entry given a certain address offset. */
-static const struct vgic_register_region *
-vgic_find_mmio_region(const struct vgic_register_region *region, int nr_regions,
- unsigned int offset)
+const struct vgic_register_region *
+vgic_find_mmio_region(const struct vgic_register_region *regions,
+ int nr_regions, unsigned int offset)
{
- return bsearch((void *)(uintptr_t)offset, region, nr_regions,
- sizeof(region[0]), match_region);
+ return bsearch((void *)(uintptr_t)offset, regions, nr_regions,
+ sizeof(regions[0]), match_region);
}
void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
};
unsigned long (*uaccess_read)(struct kvm_vcpu *vcpu, gpa_t addr,
unsigned int len);
- void (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr,
- unsigned int len, unsigned long val);
+ union {
+ void (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr,
+ unsigned int len, unsigned long val);
+ int (*uaccess_its_write)(struct kvm *kvm, struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+ };
};
extern struct kvm_io_device_ops kvm_io_gic_ops;
u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift,
u64 (*sanitise_fn)(u64));
+/* Find the proper register handler entry given a certain address offset */
+const struct vgic_register_region *
+vgic_find_mmio_region(const struct vgic_register_region *regions,
+ int nr_regions, unsigned int offset);
+
#endif
vgic_v3->vgic_hcr = ICH_HCR_EN;
}
-/* check for overlapping regions and for regions crossing the end of memory */
-static bool vgic_v3_check_base(struct kvm *kvm)
+int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
+{
+ struct kvm_vcpu *vcpu;
+ int byte_offset, bit_nr;
+ gpa_t pendbase, ptr;
+ bool status;
+ u8 val;
+ int ret;
+
+retry:
+ vcpu = irq->target_vcpu;
+ if (!vcpu)
+ return 0;
+
+ pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+
+ byte_offset = irq->intid / BITS_PER_BYTE;
+ bit_nr = irq->intid % BITS_PER_BYTE;
+ ptr = pendbase + byte_offset;
+
+ ret = kvm_read_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+
+ status = val & (1 << bit_nr);
+
+ spin_lock(&irq->irq_lock);
+ if (irq->target_vcpu != vcpu) {
+ spin_unlock(&irq->irq_lock);
+ goto retry;
+ }
+ irq->pending_latch = status;
+ vgic_queue_irq_unlock(vcpu->kvm, irq);
+
+ if (status) {
+ /* clear consumed data */
+ val &= ~(1 << bit_nr);
+ ret = kvm_write_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+/**
+ * vgic_its_save_pending_tables - Save the pending tables into guest RAM
+ * kvm lock and all vcpu lock must be held
+ */
+int vgic_v3_save_pending_tables(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ int last_byte_offset = -1;
+ struct vgic_irq *irq;
+ int ret;
+
+ list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+ int byte_offset, bit_nr;
+ struct kvm_vcpu *vcpu;
+ gpa_t pendbase, ptr;
+ bool stored;
+ u8 val;
+
+ vcpu = irq->target_vcpu;
+ if (!vcpu)
+ continue;
+
+ pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+
+ byte_offset = irq->intid / BITS_PER_BYTE;
+ bit_nr = irq->intid % BITS_PER_BYTE;
+ ptr = pendbase + byte_offset;
+
+ if (byte_offset != last_byte_offset) {
+ ret = kvm_read_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+ last_byte_offset = byte_offset;
+ }
+
+ stored = val & (1U << bit_nr);
+ if (stored == irq->pending_latch)
+ continue;
+
+ if (irq->pending_latch)
+ val |= 1 << bit_nr;
+ else
+ val &= ~(1 << bit_nr);
+
+ ret = kvm_write_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+/*
+ * Check for overlapping regions and for regions crossing the end of memory
+ * for base addresses which have already been set.
+ */
+bool vgic_v3_check_base(struct kvm *kvm)
{
struct vgic_dist *d = &kvm->arch.vgic;
gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE;
redist_size *= atomic_read(&kvm->online_vcpus);
- if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
+ if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
+ d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
return false;
- if (d->vgic_redist_base + redist_size < d->vgic_redist_base)
+
+ if (!IS_VGIC_ADDR_UNDEF(d->vgic_redist_base) &&
+ d->vgic_redist_base + redist_size < d->vgic_redist_base)
return false;
+ /* Both base addresses must be set to check if they overlap */
+ if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) ||
+ IS_VGIC_ADDR_UNDEF(d->vgic_redist_base))
+ return true;
+
if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base)
return true;
if (d->vgic_redist_base + redist_size <= d->vgic_dist_base)
goto out;
}
- ret = vgic_register_redist_iodevs(kvm, dist->vgic_redist_base);
- if (ret) {
- kvm_err("Unable to register VGICv3 redist MMIO regions\n");
- goto out;
- }
-
- if (vgic_has_its(kvm)) {
- ret = vgic_register_its_iodevs(kvm);
- if (ret) {
- kvm_err("Unable to register VGIC ITS MMIO regions\n");
- goto out;
- }
- }
-
dist->ready = true;
out:
#include "vgic.h"
#define CREATE_TRACE_POINTS
-#include "../trace.h"
+#include "trace.h"
#ifdef CONFIG_DEBUG_SPINLOCK
#define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p)
KVM_REG_ARM_VGIC_SYSREG_CRM_MASK | \
KVM_REG_ARM_VGIC_SYSREG_OP2_MASK)
+/*
+ * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt,
+ * below macros are defined for ITS table entry encoding.
+ */
+#define KVM_ITS_CTE_VALID_SHIFT 63
+#define KVM_ITS_CTE_VALID_MASK BIT_ULL(63)
+#define KVM_ITS_CTE_RDBASE_SHIFT 16
+#define KVM_ITS_CTE_ICID_MASK GENMASK_ULL(15, 0)
+#define KVM_ITS_ITE_NEXT_SHIFT 48
+#define KVM_ITS_ITE_PINTID_SHIFT 16
+#define KVM_ITS_ITE_PINTID_MASK GENMASK_ULL(47, 16)
+#define KVM_ITS_ITE_ICID_MASK GENMASK_ULL(15, 0)
+#define KVM_ITS_DTE_VALID_SHIFT 63
+#define KVM_ITS_DTE_VALID_MASK BIT_ULL(63)
+#define KVM_ITS_DTE_NEXT_SHIFT 49
+#define KVM_ITS_DTE_NEXT_MASK GENMASK_ULL(62, 49)
+#define KVM_ITS_DTE_ITTADDR_SHIFT 5
+#define KVM_ITS_DTE_ITTADDR_MASK GENMASK_ULL(48, 5)
+#define KVM_ITS_DTE_SIZE_MASK GENMASK_ULL(4, 0)
+#define KVM_ITS_L1E_VALID_MASK BIT_ULL(63)
+/* we only support 64 kB translation table page size */
+#define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16)
+
static inline bool irq_is_pending(struct vgic_irq *irq)
{
if (irq->config == VGIC_CONFIG_EDGE)
void vgic_v3_enable(struct kvm_vcpu *vcpu);
int vgic_v3_probe(const struct gic_kvm_info *info);
int vgic_v3_map_resources(struct kvm *kvm);
-int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
+int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
+int vgic_v3_save_pending_tables(struct kvm *kvm);
+int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr);
+int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
+bool vgic_v3_check_base(struct kvm *kvm);
void vgic_v3_load(struct kvm_vcpu *vcpu);
void vgic_v3_put(struct kvm_vcpu *vcpu);
-int vgic_register_its_iodevs(struct kvm *kvm);
bool vgic_has_its(struct kvm *kvm);
int kvm_vgic_register_its_device(void);
void vgic_enable_lpis(struct kvm_vcpu *vcpu);
int vgic_debug_init(struct kvm *kvm);
int vgic_debug_destroy(struct kvm *kvm);
+bool lock_all_vcpus(struct kvm *kvm);
+void unlock_all_vcpus(struct kvm *kvm);
+
#endif
[KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops,
[KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops,
#endif
-
-#ifdef CONFIG_KVM_XICS
- [KVM_DEV_TYPE_XICS] = &kvm_xics_ops,
-#endif
};
int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
.release = kvm_debugfs_release,
.read = simple_attr_read,
.write = simple_attr_write,
- .llseek = generic_file_llseek,
+ .llseek = no_llseek,
};
static int vcpu_stat_get_per_vm(void *data, u64 *val)
.release = kvm_debugfs_release,
.read = simple_attr_read,
.write = simple_attr_write,
- .llseek = generic_file_llseek,
+ .llseek = no_llseek,
};
static const struct file_operations *stat_fops_per_vm[] = {