GP107 modesetting support (just recognising the chipset, no other changes until 4.12)
a couple of regression fixes, one of them a rather serious double-free issue that appeared in 4.10.
* 'linux-4.11' of git://github.com/skeggsb/linux:
drm/nouveau: initial support (display-only) for GP107
drm/nouveau/kms/nv50: fix double dma_fence_put() when destroying plane state
drm/nouveau/kms/nv50: fix setting of HeadSetRasterVertBlankDmi method
drm/nouveau/mmu/nv4a: use nv04 mmu rather than the nv44 one
drm/nouveau/mpeg: mthd returns true on success now
Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
Takashi YOSHII <takashi.yoshii.zj@renesas.com>
+Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
Yusuke Goda <goda.yusuke@renesas.com>
Gustavo Padovan <gustavo@las.ic.unicamp.br>
Gustavo Padovan <padovan@profusion.mobi>
int (*permission) (struct inode *, int, unsigned int);
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct dentry *, struct kstat *,
- u32, unsigned int);
+ int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
void (*update_time)(struct inode *, struct timespec *, int);
[recommended]
->readlink is optional for symlinks. Don't set, unless filesystem needs
to fake something for readlink(2).
+--
+[mandatory]
+ ->getattr() is now passed a struct path rather than a vfsmount and
+ dentry separately, and it now has request_mask and query_flags arguments
+ to specify the fields and sync type requested by statx. Filesystems not
+ supporting any statx-specific features may ignore the new arguments.
int (*permission) (struct inode *, int);
int (*get_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
- int (*getattr) (const struct path *, struct dentry *, struct kstat *,
- u32, unsigned int);
+ int (*getattr) (const struct path *, struct kstat *, u32, unsigned int);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
void (*update_time)(struct inode *, struct timespec *, int);
int (*atomic_open)(struct inode *, struct dentry *, struct file *,
int __init foo_probe(void)
{
+ int error;
+
struct pinctrl_dev *pctl;
- return pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+ error = pinctrl_register_and_init(&foo_desc, <PARENT>, NULL, &pctl);
+ if (error)
+ return error;
+
+ return pinctrl_enable(pctl);
}
To enable the pinctrl subsystem and the subgroups for PINMUX and PINCONF and
.. code-block:: none
- Cc: <stable@vger.kernel.org> # 3.3.x-
+ Cc: <stable@vger.kernel.org> # 3.3.x
The tag has the meaning of:
Bits for undefined preemption levels are RAZ/WI.
+ For historical reasons and to provide ABI compatibility with userspace we
+ export the GICC_PMR register in the format of the GICH_VMCR.VMPriMask
+ field in the lower 5 bits of a word, meaning that userspace must always
+ use the lower 5 bits to communicate with the KVM device and must shift the
+ value left by 3 places to obtain the actual priority mask level.
+
Limitations:
- Priorities are not implemented, and registers are RAZ/WI
- Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
F: lib/lru_cache.c
F: Documentation/blockdev/drbd/
-DRIVER CORE, KOBJECTS, DEBUGFS, KERNFS AND SYSFS
+DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
S: Supported
F: Documentation/kobject.txt
F: drivers/base/
F: fs/debugfs/
-F: fs/kernfs/
F: fs/sysfs/
F: include/linux/debugfs.h
F: include/linux/kobj*
F: net/bridge/
ETHERNET PHY LIBRARY
+M: Andrew Lunn <andrew@lunn.ch>
M: Florian Fainelli <f.fainelli@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: fs/autofs4/
KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
+M: Masahiro Yamada <yamada.masahiro@socionext.com>
M: Michal Marek <mmarek@suse.com>
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git for-next
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git rc-fixes
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git
L: linux-kbuild@vger.kernel.org
S: Maintained
F: Documentation/kbuild/
F: arch/mips/include/asm/kvm*
F: arch/mips/kvm/
+KERNFS
+M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+M: Tejun Heo <tj@kernel.org>
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
+S: Supported
+F: include/linux/kernfs.h
+F: fs/kernfs/
+
KEXEC
M: Eric Biederman <ebiederm@xmission.com>
W: http://kernel.org/pub/linux/utils/kernel/kexec/
F: block/partitions/ibm.c
S390 NETWORK DRIVERS
+M: Julian Wiedmann <jwi@linux.vnet.ibm.com>
M: Ursula Braun <ubraun@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/scsi/zfcp_*
S390 IUCV NETWORK LAYER
+M: Julian Wiedmann <jwi@linux.vnet.ibm.com>
M: Ursula Braun <ubraun@linux.vnet.ibm.com>
L: linux-s390@vger.kernel.org
W: http://www.ibm.com/developerworks/linux/linux390/
VERSION = 4
PATCHLEVEL = 11
SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Fearless Coyote
# *DOCUMENTATION*
CFLAGS_KERNEL =
AFLAGS_KERNEL =
LDFLAGS_vmlinux =
-CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im -Wno-maybe-uninitialized
+CFLAGS_GCOV := -fprofile-arcs -ftest-coverage -fno-tree-loop-im $(call cc-disable-warning,maybe-uninitialized,)
CFLAGS_KCOV := $(call cc-option,-fsanitize-coverage=trace-pc,)
# Tell gcc to never replace conditional load with a non-conditional one
KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0)
+# check for 'asm goto'
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
+ KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
+ KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
+endif
+
include scripts/Makefile.gcc-plugins
ifdef CONFIG_READABLE_ASM
# use the deterministic mode of AR if available
KBUILD_ARFLAGS := $(call ar-option,D)
-# check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
- KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
- KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
-endif
-
include scripts/Makefile.kasan
include scripts/Makefile.extrawarn
include scripts/Makefile.ubsan
/* copy relevant bits of struct timex. */
if (copy_from_user(&txc, txc_p, offsetof(struct timex32, time)) ||
copy_from_user(&txc.tick, &txc_p->tick, sizeof(struct timex32) -
- offsetof(struct timex32, time)))
+ offsetof(struct timex32, tick)))
return -EFAULT;
ret = do_adjtimex(&txc);
if (__hyp_get_vectors() == hyp_default_vectors)
cpu_init_hyp_mode(NULL);
}
+
+ if (vgic_present)
+ kvm_vgic_init_cpu_hardware();
}
static void cpu_hyp_reset(void)
phys_addr_t addr = start, end = start + size;
phys_addr_t next;
+ assert_spin_locked(&kvm->mmu_lock);
pgd = kvm->arch.pgd + stage2_pgd_index(addr);
do {
next = stage2_pgd_addr_end(addr, end);
if (!stage2_pgd_none(*pgd))
unmap_stage2_puds(kvm, pgd, addr, next);
+ /*
+ * If the range is too large, release the kvm->mmu_lock
+ * to prevent starvation and lockup detector warnings.
+ */
+ if (next != end)
+ cond_resched_lock(&kvm->mmu_lock);
} while (pgd++, addr = next, addr != end);
}
int idx;
idx = srcu_read_lock(&kvm->srcu);
+ down_read(¤t->mm->mmap_sem);
spin_lock(&kvm->mmu_lock);
slots = kvm_memslots(kvm);
stage2_unmap_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
+ up_read(¤t->mm->mmap_sem);
srcu_read_unlock(&kvm->srcu, idx);
}
if (kvm->arch.pgd == NULL)
return;
+ spin_lock(&kvm->mmu_lock);
unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+ spin_unlock(&kvm->mmu_lock);
+
/* Free the HW pgd, one page at a time */
free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
kvm->arch.pgd = NULL;
(KVM_PHYS_SIZE >> PAGE_SHIFT))
return -EFAULT;
+ down_read(¤t->mm->mmap_sem);
/*
* A memory region could potentially cover multiple VMAs, and any holes
* between them, so iterate over all of them to find out if we can map
pa += vm_start - vma->vm_start;
/* IO region dirty page logging not allowed */
- if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
- return -EINVAL;
+ if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
+ ret = -EINVAL;
+ goto out;
+ }
ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
vm_end - vm_start,
} while (hva < reg_end);
if (change == KVM_MR_FLAGS_ONLY)
- return ret;
+ goto out;
spin_lock(&kvm->mmu_lock);
if (ret)
else
stage2_flush_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
+out:
+ up_read(¤t->mm->mmap_sem);
return ret;
}
__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
}
+/*
+ * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
+ * that the intention is to allow exporting memory allocated via the
+ * coherent DMA APIs through the dma_buf API, which only accepts a
+ * scattertable. This presents a couple of problems:
+ * 1. Not all memory allocated via the coherent DMA APIs is backed by
+ * a struct page
+ * 2. Passing coherent DMA memory into the streaming APIs is not allowed
+ * as we will try to flush the memory through a different alias to that
+ * actually being used (and the flushes are redundant.)
+ */
int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t handle, size_t size,
unsigned long attrs)
{
- struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+ unsigned long pfn = dma_to_pfn(dev, handle);
+ struct page *page;
int ret;
+ /* If the PFN is not valid, we do not have a struct page */
+ if (!pfn_valid(pfn))
+ return -ENXIO;
+
+ page = pfn_to_page(pfn);
+
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
if (unlikely(ret))
return ret;
*/
static inline bool security_extensions_enabled(void)
{
- return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+ /* Check CPUID Identification Scheme before ID_PFR1 read */
+ if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
+ return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+ return 0;
}
static unsigned long __init setup_vectors_base(void)
#endif
if (p) {
- if (cur) {
+ if (!p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+ /*
+ * Probe hit but conditional execution check failed,
+ * so just skip the instruction and continue as if
+ * nothing had happened.
+ * In this case, we can skip recursing check too.
+ */
+ singlestep_skip(p, regs);
+ } else if (cur) {
/* Kprobe is pending, so we're recursing. */
switch (kcb->kprobe_status) {
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
+ case KPROBE_HIT_SS:
/* A pre- or post-handler probe got us here. */
kprobes_inc_nmissed_count(p);
save_previous_kprobe(kcb);
singlestep(p, regs, kcb);
restore_previous_kprobe(kcb);
break;
+ case KPROBE_REENTER:
+ /* A nested probe was hit in FIQ, it is a BUG */
+ pr_warn("Unrecoverable kprobe detected at %p.\n",
+ p->addr);
+ /* fall through */
default:
/* impossible cases */
BUG();
}
- } else if (p->ainsn.insn_check_cc(regs->ARM_cpsr)) {
+ } else {
/* Probe hit and conditional execution check ok. */
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
}
reset_current_kprobe();
}
- } else {
- /*
- * Probe hit but conditional execution check failed,
- * so just skip the instruction and continue as if
- * nothing had happened.
- */
- singlestep_skip(p, regs);
}
} else if (cur) {
/* We probably hit a jprobe. Call its break handler. */
struct hlist_node *tmp;
unsigned long flags, orig_ret_address = 0;
unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
+ kprobe_opcode_t *correct_ret_addr = NULL;
INIT_HLIST_HEAD(&empty_rp);
kretprobe_hash_lock(current, &head, &flags);
/* another task is sharing our hash bucket */
continue;
+ orig_ret_address = (unsigned long)ri->ret_addr;
+
+ if (orig_ret_address != trampoline_address)
+ /*
+ * This is the real return address. Any other
+ * instances associated with this task are for
+ * other calls deeper on the call stack
+ */
+ break;
+ }
+
+ kretprobe_assert(ri, orig_ret_address, trampoline_address);
+
+ correct_ret_addr = ri->ret_addr;
+ hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+ if (ri->task != current)
+ /* another task is sharing our hash bucket */
+ continue;
+
+ orig_ret_address = (unsigned long)ri->ret_addr;
if (ri->rp && ri->rp->handler) {
__this_cpu_write(current_kprobe, &ri->rp->kp);
get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
+ ri->ret_addr = correct_ret_addr;
ri->rp->handler(ri, regs);
__this_cpu_write(current_kprobe, NULL);
}
- orig_ret_address = (unsigned long)ri->ret_addr;
recycle_rp_inst(ri, &empty_rp);
if (orig_ret_address != trampoline_address)
break;
}
- kretprobe_assert(ri, orig_ret_address, trampoline_address);
kretprobe_hash_unlock(current, &flags);
hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
void __naked __kprobes_test_case_start(void)
{
__asm__ __volatile__ (
- "stmdb sp!, {r4-r11} \n\t"
+ "mov r2, sp \n\t"
+ "bic r3, r2, #7 \n\t"
+ "mov sp, r3 \n\t"
+ "stmdb sp!, {r2-r11} \n\t"
"sub sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
"bic r0, lr, #1 @ r0 = inline data \n\t"
"mov r1, sp \n\t"
"movne pc, r0 \n\t"
"mov r0, r4 \n\t"
"add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
- "ldmia sp!, {r4-r11} \n\t"
+ "ldmia sp!, {r2-r11} \n\t"
+ "mov sp, r2 \n\t"
"mov pc, r0 \n\t"
);
}
"bxne r0 \n\t"
"mov r0, r4 \n\t"
"add sp, sp, #"__stringify(TEST_MEMORY_SIZE)"\n\t"
- "ldmia sp!, {r4-r11} \n\t"
+ "ldmia sp!, {r2-r11} \n\t"
+ "mov sp, r2 \n\t"
"bx r0 \n\t"
);
}
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
-static const char *fault_name(unsigned int esr);
+struct fault_info {
+ int (*fn)(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs);
+ int sig;
+ int code;
+ const char *name;
+};
+
+static const struct fault_info fault_info[];
+
+static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
+{
+ return fault_info + (esr & 63);
+}
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
struct pt_regs *regs)
{
struct siginfo si;
+ const struct fault_info *inf;
if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
+ inf = esr_to_fault_info(esr);
pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
- tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ tsk->comm, task_pid_nr(tsk), inf->name, sig,
addr, esr);
show_pte(tsk->mm, addr);
show_regs(regs);
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
+ const struct fault_info *inf;
/*
* If we are in kernel mode at this point, we have no context to
* handle this fault with.
*/
- if (user_mode(regs))
- __do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
- else
+ if (user_mode(regs)) {
+ inf = esr_to_fault_info(esr);
+ __do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+ } else
__do_kernel_fault(mm, addr, esr, regs);
}
return 1;
}
-static const struct fault_info {
- int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
- int sig;
- int code;
- const char *name;
-} fault_info[] = {
+static const struct fault_info fault_info[] = {
{ do_bad, SIGBUS, 0, "ttbr address size fault" },
{ do_bad, SIGBUS, 0, "level 1 address size fault" },
{ do_bad, SIGBUS, 0, "level 2 address size fault" },
{ do_bad, SIGBUS, 0, "unknown 63" },
};
-static const char *fault_name(unsigned int esr)
-{
- const struct fault_info *inf = fault_info + (esr & 63);
- return inf->name;
-}
-
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
- const struct fault_info *inf = fault_info + (esr & 63);
+ const struct fault_info *inf = esr_to_fault_info(esr);
struct siginfo info;
if (!inf->fn(addr, esr, regs))
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else if (ps == (PAGE_SIZE * CONT_PTES)) {
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- } else if (ps == (PMD_SIZE * CONT_PMDS)) {
- hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
} else {
hugetlb_bad_size();
pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
-
-#ifdef CONFIG_ARM64_64K_PAGES
-static __init int add_default_hugepagesz(void)
-{
- if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- return 0;
-}
-arch_initcall(add_default_hugepagesz);
-#endif
#define strlen_user(str) strnlen_user(str, 32767)
-extern unsigned long __must_check __copy_user_zeroing(void *to,
- const void __user *from,
- unsigned long n);
+extern unsigned long raw_copy_from_user(void *to, const void __user *from,
+ unsigned long n);
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
+ unsigned long res = n;
if (likely(access_ok(VERIFY_READ, from, n)))
- return __copy_user_zeroing(to, from, n);
- memset(to, 0, n);
- return n;
+ res = raw_copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
-#define __copy_from_user(to, from, n) __copy_user_zeroing(to, from, n)
+#define __copy_from_user(to, from, n) raw_copy_from_user(to, from, n)
#define __copy_from_user_inatomic __copy_from_user
extern unsigned long __must_check __copy_user(void __user *to,
COPY \
"1:\n" \
" .section .fixup,\"ax\"\n" \
- " MOV D1Ar1,#0\n" \
FIXUP \
" MOVT D1Ar1,#HI(1b)\n" \
" JUMP D1Ar1,#LO(1b)\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"22:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "SUB %3, %3, #32\n" \
"23:\n" \
- "MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\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" \
\
"MOV RAPF, %1\n" \
- "25:\n" \
+ "27:\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "26:\n" \
+ "28:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "29:\n" \
"SUB %3, %3, #32\n" \
- "27:\n" \
+ "30:\n" \
"MGETL D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "28:\n" \
+ "31:\n" \
"MSETL [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "32:\n" \
"SUB %0, %0, #8\n" \
- "29:\n" \
+ "33:\n" \
"SETL [%0++], D0.7, D1.7\n" \
"SUB %3, %3, #32\n" \
"1:" \
" .long 26b,3b\n" \
" .long 27b,3b\n" \
" .long 28b,3b\n" \
- " .long 29b,4b\n" \
+ " .long 29b,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) \
- : "D1Ar1", "D0Ar2", "memory")
+ : "D1Ar1", "D0Ar2", "cc", "memory")
/* rewind 'to' and 'from' pointers when a fault occurs
*
#define __asm_copy_to_user_64bit_rapf_loop(to, from, ret, n, id)\
__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \
"LSR D0Ar2, D0Ar2, #8\n" \
- "AND D0Ar2, D0Ar2, #0x7\n" \
+ "ANDS D0Ar2, D0Ar2, #0x7\n" \
"ADDZ D0Ar2, D0Ar2, #4\n" \
"SUB D0Ar2, D0Ar2, #1\n" \
"MOV D1Ar1, #4\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
"22:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
- "SUB %3, %3, #16\n" \
"23:\n" \
- "MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "24:\n" \
- "MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
"SUB %3, %3, #16\n" \
- "25:\n" \
+ "24:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "26:\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" \
\
"MOV RAPF, %1\n" \
- "29:\n" \
+ "33:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "30:\n" \
+ "34:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "35:\n" \
"SUB %3, %3, #16\n" \
- "31:\n" \
+ "36:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "32:\n" \
+ "37:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "38:\n" \
"SUB %3, %3, #16\n" \
- "33:\n" \
+ "39:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "34:\n" \
+ "40:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "41:\n" \
"SUB %3, %3, #16\n" \
- "35:\n" \
+ "42:\n" \
"MGETD D0FrT, D0.5, D0.6, D0.7, [%1++]\n" \
- "36:\n" \
+ "43:\n" \
"MSETD [%0++], D0FrT, D0.5, D0.6, D0.7\n" \
+ "44:\n" \
"SUB %0, %0, #4\n" \
- "37:\n" \
+ "45:\n" \
"SETD [%0++], D0.7\n" \
"SUB %3, %3, #16\n" \
"1:" \
" .long 34b,3b\n" \
" .long 35b,3b\n" \
" .long 36b,3b\n" \
- " .long 37b,4b\n" \
+ " .long 37b,3b\n" \
+ " .long 38b,3b\n" \
+ " .long 39b,3b\n" \
+ " .long 40b,3b\n" \
+ " .long 41b,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) \
- : "D1Ar1", "D0Ar2", "memory")
+ : "D1Ar1", "D0Ar2", "cc", "memory")
/* rewind 'to' and 'from' pointers when a fault occurs
*
#define __asm_copy_to_user_32bit_rapf_loop(to, from, ret, n, id)\
__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \
"LSR D0Ar2, D0Ar2, #8\n" \
- "AND D0Ar2, D0Ar2, #0x7\n" \
+ "ANDS D0Ar2, D0Ar2, #0x7\n" \
"ADDZ D0Ar2, D0Ar2, #4\n" \
"SUB D0Ar2, D0Ar2, #1\n" \
"MOV D1Ar1, #4\n" \
if ((unsigned long) src & 1) {
__asm_copy_to_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 1) {
/* Worst case - byte copy */
while (n > 0) {
__asm_copy_to_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
}
if (((unsigned long) src & 2) && n >= 2) {
__asm_copy_to_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 2) {
/* Second worst case - word copy */
while (n >= 2) {
__asm_copy_to_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
}
while (n >= 8) {
__asm_copy_to_user_8x64(dst, src, retn);
n -= 8;
+ if (retn)
+ return retn + n;
}
}
if (n >= RAPF_MIN_BUF_SIZE) {
while (n >= 8) {
__asm_copy_to_user_8x64(dst, src, retn);
n -= 8;
+ if (retn)
+ return retn + n;
}
}
#endif
while (n >= 16) {
__asm_copy_to_user_16(dst, src, retn);
n -= 16;
+ if (retn)
+ return retn + n;
}
while (n >= 4) {
__asm_copy_to_user_4(dst, src, retn);
n -= 4;
+ if (retn)
+ return retn + n;
}
switch (n) {
break;
}
+ /*
+ * If we get here, retn correctly reflects the number of failing
+ * bytes.
+ */
return retn;
}
EXPORT_SYMBOL(__copy_user);
__asm_copy_user_cont(to, from, ret, \
" GETB D1Ar1,[%1++]\n" \
"2: SETB [%0++],D1Ar1\n", \
- "3: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
+ "3: ADD %2,%2,#1\n", \
" .long 2b,3b\n")
#define __asm_copy_from_user_2x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" GETW D1Ar1,[%1++]\n" \
"2: SETW [%0++],D1Ar1\n" COPY, \
- "3: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
+ "3: ADD %2,%2,#2\n" FIXUP, \
" .long 2b,3b\n" TENTRY)
#define __asm_copy_from_user_2(to, from, ret) \
__asm_copy_from_user_2x_cont(to, from, ret, \
" GETB D1Ar1,[%1++]\n" \
"4: SETB [%0++],D1Ar1\n", \
- "5: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
+ "5: ADD %2,%2,#1\n", \
" .long 4b,5b\n")
#define __asm_copy_from_user_4x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
__asm_copy_user_cont(to, from, ret, \
" GETD D1Ar1,[%1++]\n" \
"2: SETD [%0++],D1Ar1\n" COPY, \
- "3: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
+ "3: ADD %2,%2,#4\n" FIXUP, \
" .long 2b,3b\n" TENTRY)
#define __asm_copy_from_user_4(to, from, ret) \
__asm_copy_from_user_4x_cont(to, from, ret, "", "", "")
-#define __asm_copy_from_user_5(to, from, ret) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "4: SETB [%0++],D1Ar1\n", \
- "5: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 4b,5b\n")
-
-#define __asm_copy_from_user_6x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "4: SETW [%0++],D1Ar1\n" COPY, \
- "5: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_6(to, from, ret) \
- __asm_copy_from_user_6x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_7(to, from, ret) \
- __asm_copy_from_user_6x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "6: SETB [%0++],D1Ar1\n", \
- "7: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 6b,7b\n")
-
-#define __asm_copy_from_user_8x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_4x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "4: SETD [%0++],D1Ar1\n" COPY, \
- "5: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 4b,5b\n" TENTRY)
-
-#define __asm_copy_from_user_8(to, from, ret) \
- __asm_copy_from_user_8x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_9(to, from, ret) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "6: SETB [%0++],D1Ar1\n", \
- "7: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 6b,7b\n")
-
-#define __asm_copy_from_user_10x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "6: SETW [%0++],D1Ar1\n" COPY, \
- "7: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_10(to, from, ret) \
- __asm_copy_from_user_10x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_11(to, from, ret) \
- __asm_copy_from_user_10x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "8: SETB [%0++],D1Ar1\n", \
- "9: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 8b,9b\n")
-
-#define __asm_copy_from_user_12x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_8x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "6: SETD [%0++],D1Ar1\n" COPY, \
- "7: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 6b,7b\n" TENTRY)
-
-#define __asm_copy_from_user_12(to, from, ret) \
- __asm_copy_from_user_12x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_13(to, from, ret) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "8: SETB [%0++],D1Ar1\n", \
- "9: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 8b,9b\n")
-
-#define __asm_copy_from_user_14x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETW D1Ar1,[%1++]\n" \
- "8: SETW [%0++],D1Ar1\n" COPY, \
- "9: ADD %2,%2,#2\n" \
- " SETW [%0++],D1Ar1\n" FIXUP, \
- " .long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_14(to, from, ret) \
- __asm_copy_from_user_14x_cont(to, from, ret, "", "", "")
-
-#define __asm_copy_from_user_15(to, from, ret) \
- __asm_copy_from_user_14x_cont(to, from, ret, \
- " GETB D1Ar1,[%1++]\n" \
- "10: SETB [%0++],D1Ar1\n", \
- "11: ADD %2,%2,#1\n" \
- " SETB [%0++],D1Ar1\n", \
- " .long 10b,11b\n")
-
-#define __asm_copy_from_user_16x_cont(to, from, ret, COPY, FIXUP, TENTRY) \
- __asm_copy_from_user_12x_cont(to, from, ret, \
- " GETD D1Ar1,[%1++]\n" \
- "8: SETD [%0++],D1Ar1\n" COPY, \
- "9: ADD %2,%2,#4\n" \
- " SETD [%0++],D1Ar1\n" FIXUP, \
- " .long 8b,9b\n" TENTRY)
-
-#define __asm_copy_from_user_16(to, from, ret) \
- __asm_copy_from_user_16x_cont(to, from, ret, "", "", "")
-
#define __asm_copy_from_user_8x64(to, from, ret) \
asm volatile ( \
" GETL D0Ar2,D1Ar1,[%1++]\n" \
"2: SETL [%0++],D0Ar2,D1Ar1\n" \
"1:\n" \
" .section .fixup,\"ax\"\n" \
- " MOV D1Ar1,#0\n" \
- " MOV D0Ar2,#0\n" \
"3: ADD %2,%2,#8\n" \
- " SETL [%0++],D0Ar2,D1Ar1\n" \
" MOVT D0Ar2,#HI(1b)\n" \
" JUMP D0Ar2,#LO(1b)\n" \
" .previous\n" \
*
* Rationale:
* A fault occurs while reading from user buffer, which is the
- * source. Since the fault is at a single address, we only
- * need to rewind by 8 bytes.
+ * source.
* Since we don't write to kernel buffer until we read first,
* the kernel buffer is at the right state and needn't be
- * corrected.
+ * corrected, but the source must be rewound to the beginning of
+ * the block, which is LSM_STEP*8 bytes.
+ * LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ * and stored in D0Ar2
+ *
+ * NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ * LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ * a fault happens at the 4th write, LSM_STEP will be 0
+ * instead of 4. The code copes with that.
*/
#define __asm_copy_from_user_64bit_rapf_loop(to, from, ret, n, id) \
__asm_copy_user_64bit_rapf_loop(to, from, ret, n, id, \
- "SUB %1, %1, #8\n")
+ "LSR D0Ar2, D0Ar2, #5\n" \
+ "ANDS D0Ar2, D0Ar2, #0x38\n" \
+ "ADDZ D0Ar2, D0Ar2, #32\n" \
+ "SUB %1, %1, D0Ar2\n")
/* rewind 'from' pointer when a fault occurs
*
* Rationale:
* A fault occurs while reading from user buffer, which is the
- * source. Since the fault is at a single address, we only
- * need to rewind by 4 bytes.
+ * source.
* Since we don't write to kernel buffer until we read first,
* the kernel buffer is at the right state and needn't be
- * corrected.
+ * corrected, but the source must be rewound to the beginning of
+ * the block, which is LSM_STEP*4 bytes.
+ * LSM_STEP is bits 10:8 in TXSTATUS which is already read
+ * and stored in D0Ar2
+ *
+ * NOTE: If a fault occurs at the last operation in M{G,S}ETL
+ * LSM_STEP will be 0. ie: we do 4 writes in our case, if
+ * a fault happens at the 4th write, LSM_STEP will be 0
+ * instead of 4. The code copes with that.
*/
#define __asm_copy_from_user_32bit_rapf_loop(to, from, ret, n, id) \
__asm_copy_user_32bit_rapf_loop(to, from, ret, n, id, \
- "SUB %1, %1, #4\n")
+ "LSR D0Ar2, D0Ar2, #6\n" \
+ "ANDS D0Ar2, D0Ar2, #0x1c\n" \
+ "ADDZ D0Ar2, D0Ar2, #16\n" \
+ "SUB %1, %1, D0Ar2\n")
-/* Copy from user to kernel, zeroing the bytes that were inaccessible in
- userland. The return-value is the number of bytes that were
- inaccessible. */
-unsigned long __copy_user_zeroing(void *pdst, const void __user *psrc,
- unsigned long n)
+/*
+ * Copy from user to kernel. The return-value is the number of bytes that were
+ * inaccessible.
+ */
+unsigned long raw_copy_from_user(void *pdst, const void __user *psrc,
+ unsigned long n)
{
register char *dst asm ("A0.2") = pdst;
register const char __user *src asm ("A1.2") = psrc;
if ((unsigned long) src & 1) {
__asm_copy_from_user_1(dst, src, retn);
n--;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 1) {
/* Worst case - byte copy */
__asm_copy_from_user_1(dst, src, retn);
n--;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
if (((unsigned long) src & 2) && n >= 2) {
__asm_copy_from_user_2(dst, src, retn);
n -= 2;
+ if (retn)
+ return retn + n;
}
if ((unsigned long) dst & 2) {
/* Second worst case - word copy */
__asm_copy_from_user_2(dst, src, retn);
n -= 2;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
- /* We only need one check after the unalignment-adjustments,
- because if both adjustments were done, either both or
- neither reference had an exception. */
- if (retn != 0)
- goto copy_exception_bytes;
-
#ifdef USE_RAPF
/* 64 bit copy loop */
if (!(((unsigned long) src | (unsigned long) dst) & 7)) {
__asm_copy_from_user_8x64(dst, src, retn);
n -= 8;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
__asm_copy_from_user_8x64(dst, src, retn);
n -= 8;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
}
#endif
n -= 4;
if (retn)
- goto copy_exception_bytes;
+ return retn + n;
}
/* If we get here, there were no memory read faults. */
/* If we get here, retn correctly reflects the number of failing
bytes. */
return retn;
-
- copy_exception_bytes:
- /* We already have "retn" bytes cleared, and need to clear the
- remaining "n" bytes. A non-optimized simple byte-for-byte in-line
- memset is preferred here, since this isn't speed-critical code and
- we'd rather have this a leaf-function than calling memset. */
- {
- char *endp;
- for (endp = dst + n; dst < endp; dst++)
- *dst = 0;
- }
-
- return retn + n;
}
-EXPORT_SYMBOL(__copy_user_zeroing);
+EXPORT_SYMBOL(raw_copy_from_user);
#define __asm_clear_8x64(to, ret) \
asm volatile ( \
select CPU_SUPPORTS_HIGHMEM
select CPU_SUPPORTS_MSA
select GENERIC_CSUM
- select MIPS_O32_FP64_SUPPORT if MIPS32_O32
+ select MIPS_O32_FP64_SUPPORT if 32BIT || MIPS32_O32
select HAVE_KVM
help
Choose this option to build a kernel for release 6 or later of the
#include <asm/cpu-features.h>
#include <asm/fpu_emulator.h>
#include <asm/hazards.h>
+#include <asm/ptrace.h>
#include <asm/processor.h>
#include <asm/current.h>
#include <asm/msa.h>
#include <irq.h>
#define IRQ_STACK_SIZE THREAD_SIZE
+#define IRQ_STACK_START (IRQ_STACK_SIZE - sizeof(unsigned long))
extern void *irq_stack[NR_CPUS];
+/*
+ * The highest address on the IRQ stack contains a dummy frame put down in
+ * genex.S (handle_int & except_vec_vi_handler) which is structured as follows:
+ *
+ * top ------------
+ * | task sp | <- irq_stack[cpu] + IRQ_STACK_START
+ * ------------
+ * | | <- First frame of IRQ context
+ * ------------
+ *
+ * task sp holds a copy of the task stack pointer where the struct pt_regs
+ * from exception entry can be found.
+ */
+
static inline bool on_irq_stack(int cpu, unsigned long sp)
{
unsigned long low = (unsigned long)irq_stack[cpu];
" andi %[ticket], %[ticket], 0xffff \n"
" bne %[ticket], %[my_ticket], 4f \n"
" subu %[ticket], %[my_ticket], %[ticket] \n"
- "2: \n"
+ "2: .insn \n"
" .subsection 2 \n"
"4: andi %[ticket], %[ticket], 0xffff \n"
" sll %[ticket], 5 \n"
" sc %[ticket], %[ticket_ptr] \n"
" beqz %[ticket], 1b \n"
" li %[ticket], 1 \n"
- "2: \n"
+ "2: .insn \n"
" .subsection 2 \n"
"3: b 2b \n"
" li %[ticket], 0 \n"
" .set reorder \n"
__WEAK_LLSC_MB
" li %2, 1 \n"
- "2: \n"
+ "2: .insn \n"
: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp), "=&r" (ret)
: GCC_OFF_SMALL_ASM() (rw->lock)
: "memory");
" lui %1, 0x8000 \n"
" sc %1, %0 \n"
" li %2, 1 \n"
- "2: \n"
+ "2: .insn \n"
: "=" GCC_OFF_SMALL_ASM() (rw->lock), "=&r" (tmp),
"=&r" (ret)
: GCC_OFF_SMALL_ASM() (rw->lock)
#define __NR_pkey_mprotect (__NR_Linux + 363)
#define __NR_pkey_alloc (__NR_Linux + 364)
#define __NR_pkey_free (__NR_Linux + 365)
+#define __NR_statx (__NR_Linux + 366)
/*
* Offset of the last Linux o32 flavoured syscall
*/
-#define __NR_Linux_syscalls 365
+#define __NR_Linux_syscalls 366
#endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
#define __NR_O32_Linux 4000
-#define __NR_O32_Linux_syscalls 365
+#define __NR_O32_Linux_syscalls 366
#if _MIPS_SIM == _MIPS_SIM_ABI64
#define __NR_pkey_mprotect (__NR_Linux + 323)
#define __NR_pkey_alloc (__NR_Linux + 324)
#define __NR_pkey_free (__NR_Linux + 325)
+#define __NR_statx (__NR_Linux + 326)
/*
* Offset of the last Linux 64-bit flavoured syscall
*/
-#define __NR_Linux_syscalls 325
+#define __NR_Linux_syscalls 326
#endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
#define __NR_64_Linux 5000
-#define __NR_64_Linux_syscalls 325
+#define __NR_64_Linux_syscalls 326
#if _MIPS_SIM == _MIPS_SIM_NABI32
#define __NR_pkey_mprotect (__NR_Linux + 327)
#define __NR_pkey_alloc (__NR_Linux + 328)
#define __NR_pkey_free (__NR_Linux + 329)
+#define __NR_statx (__NR_Linux + 330)
/*
* Offset of the last N32 flavoured syscall
*/
-#define __NR_Linux_syscalls 329
+#define __NR_Linux_syscalls 330
#endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
#define __NR_N32_Linux 6000
-#define __NR_N32_Linux_syscalls 329
+#define __NR_N32_Linux_syscalls 330
#endif /* _UAPI_ASM_UNISTD_H */
DEFINE(_THREAD_SIZE, THREAD_SIZE);
DEFINE(_THREAD_MASK, THREAD_MASK);
DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE);
+ DEFINE(_IRQ_STACK_START, IRQ_STACK_START);
BLANK();
}
END(mips_cps_get_bootcfg)
LEAF(mips_cps_boot_vpes)
- PTR_L ta2, COREBOOTCFG_VPEMASK(a0)
+ lw ta2, COREBOOTCFG_VPEMASK(a0)
PTR_L ta3, COREBOOTCFG_VPECONFIG(a0)
#if defined(CONFIG_CPU_MIPSR6)
}
decode_configs(c);
- c->options |= MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
+ c->options |= MIPS_CPU_FTLB | MIPS_CPU_TLBINV | MIPS_CPU_LDPTE;
c->writecombine = _CACHE_UNCACHED_ACCELERATED;
break;
default:
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jal plat_irq_dispatch
beq t0, t1, 2f
/* Switch to IRQ stack */
- li t1, _IRQ_STACK_SIZE
+ li t1, _IRQ_STACK_START
PTR_ADD sp, t0, t1
+ /* Save task's sp on IRQ stack so that unwinding can follow it */
+ LONG_S s1, 0(sp)
2:
jalr v0
BUILD_HANDLER reserved reserved sti verbose /* others */
.align 5
- LEAF(handle_ri_rdhwr_vivt)
+ LEAF(handle_ri_rdhwr_tlbp)
.set push
.set noat
.set noreorder
.set pop
bltz k1, handle_ri /* slow path */
/* fall thru */
- END(handle_ri_rdhwr_vivt)
+ END(handle_ri_rdhwr_tlbp)
LEAF(handle_ri_rdhwr)
.set push
unsigned long pc,
unsigned long *ra)
{
+ unsigned long low, high, irq_stack_high;
struct mips_frame_info info;
unsigned long size, ofs;
+ struct pt_regs *regs;
int leaf;
- extern void ret_from_irq(void);
- extern void ret_from_exception(void);
if (!stack_page)
return 0;
/*
- * If we reached the bottom of interrupt context,
- * return saved pc in pt_regs.
+ * IRQ stacks start at IRQ_STACK_START
+ * task stacks at THREAD_SIZE - 32
*/
- if (pc == (unsigned long)ret_from_irq ||
- pc == (unsigned long)ret_from_exception) {
- struct pt_regs *regs;
- if (*sp >= stack_page &&
- *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) {
- regs = (struct pt_regs *)*sp;
- pc = regs->cp0_epc;
- if (!user_mode(regs) && __kernel_text_address(pc)) {
- *sp = regs->regs[29];
- *ra = regs->regs[31];
- return pc;
- }
+ low = stack_page;
+ if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) {
+ high = stack_page + IRQ_STACK_START;
+ irq_stack_high = high;
+ } else {
+ high = stack_page + THREAD_SIZE - 32;
+ irq_stack_high = 0;
+ }
+
+ /*
+ * If we reached the top of the interrupt stack, start unwinding
+ * the interrupted task stack.
+ */
+ if (unlikely(*sp == irq_stack_high)) {
+ unsigned long task_sp = *(unsigned long *)*sp;
+
+ /*
+ * Check that the pointer saved in the IRQ stack head points to
+ * something within the stack of the current task
+ */
+ if (!object_is_on_stack((void *)task_sp))
+ return 0;
+
+ /*
+ * Follow pointer to tasks kernel stack frame where interrupted
+ * state was saved.
+ */
+ regs = (struct pt_regs *)task_sp;
+ pc = regs->cp0_epc;
+ if (!user_mode(regs) && __kernel_text_address(pc)) {
+ *sp = regs->regs[29];
+ *ra = regs->regs[31];
+ return pc;
}
return 0;
}
if (leaf < 0)
return 0;
- if (*sp < stack_page ||
- *sp + info.frame_size > stack_page + THREAD_SIZE - 32)
+ if (*sp < low || *sp + info.frame_size > high)
return 0;
if (leaf)
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
+ PTR sys_statx
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 5325 */
+ PTR sys_statx
.size sys_call_table,.-sys_call_table
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free
+ PTR sys_statx /* 6330 */
.size sysn32_call_table,.-sysn32_call_table
PTR sys_pkey_mprotect
PTR sys_pkey_alloc
PTR sys_pkey_free /* 4365 */
+ PTR sys_statx
.size sys32_call_table,.-sys32_call_table
extern asmlinkage void handle_sys(void);
extern asmlinkage void handle_bp(void);
extern asmlinkage void handle_ri(void);
-extern asmlinkage void handle_ri_rdhwr_vivt(void);
+extern asmlinkage void handle_ri_rdhwr_tlbp(void);
extern asmlinkage void handle_ri_rdhwr(void);
extern asmlinkage void handle_cpu(void);
extern asmlinkage void handle_ov(void);
set_except_vector(EXCCODE_SYS, handle_sys);
set_except_vector(EXCCODE_BP, handle_bp);
- set_except_vector(EXCCODE_RI, rdhwr_noopt ? handle_ri :
- (cpu_has_vtag_icache ?
- handle_ri_rdhwr_vivt : handle_ri_rdhwr));
+
+ if (rdhwr_noopt)
+ set_except_vector(EXCCODE_RI, handle_ri);
+ else {
+ if (cpu_has_vtag_icache)
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+ else if (current_cpu_type() == CPU_LOONGSON3)
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr_tlbp);
+ else
+ set_except_vector(EXCCODE_RI, handle_ri_rdhwr);
+ }
+
set_except_vector(EXCCODE_CPU, handle_cpu);
set_except_vector(EXCCODE_OV, handle_ov);
set_except_vector(EXCCODE_TR, handle_tr);
if (!np_xbar)
panic("Failed to load xbar nodes from devicetree");
- if (of_address_to_resource(np_pmu, 0, &res_xbar))
+ if (of_address_to_resource(np_xbar, 0, &res_xbar))
panic("Failed to get xbar resources");
if (!request_mem_region(res_xbar.start, resource_size(&res_xbar),
res_xbar.name))
vcache_size = c->vcache.sets * c->vcache.ways * c->vcache.linesz;
c->vcache.waybit = 0;
+ c->vcache.waysize = vcache_size / c->vcache.ways;
pr_info("Unified victim cache %ldkB %s, linesize %d bytes.\n",
vcache_size >> 10, way_string[c->vcache.ways], c->vcache.linesz);
/* Loongson-3 has 4 cores, 1MB scache for each. scaches are shared */
scache_size *= 4;
c->scache.waybit = 0;
+ c->scache.waysize = scache_size / c->scache.ways;
pr_info("Unified secondary cache %ldkB %s, linesize %d bytes.\n",
scache_size >> 10, way_string[c->scache.ways], c->scache.linesz);
if (scache_size)
static void build_huge_handler_tail(u32 **p, struct uasm_reloc **r,
struct uasm_label **l,
unsigned int pte,
- unsigned int ptr)
+ unsigned int ptr,
+ unsigned int flush)
{
#ifdef CONFIG_SMP
UASM_i_SC(p, pte, 0, ptr);
#else
UASM_i_SW(p, pte, 0, ptr);
#endif
+ if (cpu_has_ftlb && flush) {
+ BUG_ON(!cpu_has_tlbinv);
+
+ UASM_i_MFC0(p, ptr, C0_ENTRYHI);
+ uasm_i_ori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+ UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+ build_tlb_write_entry(p, l, r, tlb_indexed);
+
+ uasm_i_xori(p, ptr, ptr, MIPS_ENTRYHI_EHINV);
+ UASM_i_MTC0(p, ptr, C0_ENTRYHI);
+ build_huge_update_entries(p, pte, ptr);
+ build_huge_tlb_write_entry(p, l, r, pte, tlb_random, 0);
+
+ return;
+ }
+
build_huge_update_entries(p, pte, ptr);
build_huge_tlb_write_entry(p, l, r, pte, tlb_indexed, 0);
}
uasm_l_tlbl_goaround2(&l, p);
}
uasm_i_ori(&p, wr.r1, wr.r1, (_PAGE_ACCESSED | _PAGE_VALID));
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
#endif
uasm_l_nopage_tlbl(&l, p);
build_tlb_probe_entry(&p);
uasm_i_ori(&p, wr.r1, wr.r1,
_PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 1);
#endif
uasm_l_nopage_tlbs(&l, p);
build_tlb_probe_entry(&p);
uasm_i_ori(&p, wr.r1, wr.r1,
_PAGE_ACCESSED | _PAGE_MODIFIED | _PAGE_VALID | _PAGE_DIRTY);
- build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2);
+ build_huge_handler_tail(&p, &r, &l, wr.r1, wr.r2, 0);
#endif
uasm_l_nopage_tlbm(&l, p);
static struct rt2880_pmx_func jtag_func[] = { FUNC("jtag", 0, 17, 5) };
static struct rt2880_pmx_func mdio_func[] = { FUNC("mdio", 0, 22, 2) };
static struct rt2880_pmx_func lna_a_func[] = { FUNC("lna a", 0, 32, 3) };
-static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna a", 0, 35, 3) };
+static struct rt2880_pmx_func lna_g_func[] = { FUNC("lna g", 0, 35, 3) };
static struct rt2880_pmx_func pci_func[] = {
FUNC("pci-dev", 0, 40, 32),
FUNC("pci-host2", 1, 40, 32),
FUNC("pci-fnc", 3, 40, 32)
};
static struct rt2880_pmx_func ge1_func[] = { FUNC("ge1", 0, 72, 12) };
-static struct rt2880_pmx_func ge2_func[] = { FUNC("ge1", 0, 84, 12) };
+static struct rt2880_pmx_func ge2_func[] = { FUNC("ge2", 0, 84, 12) };
static struct rt2880_pmx_group rt3883_pinmux_data[] = {
GRP("i2c", i2c_func, 1, RT3883_GPIO_MODE_I2C),
return alloc_bootmem_align(size, align);
}
+int __init early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
+ bool nomap)
+{
+ reserve_bootmem(base, size, BOOTMEM_DEFAULT);
+ return 0;
+}
+
void __init early_init_devtree(void *params)
{
__be32 *dtb = (u32 *)__dtb_start;
}
#endif /* CONFIG_BLK_DEV_INITRD */
+ early_init_fdt_reserve_self();
+ early_init_fdt_scan_reserved_mem();
+
unflatten_and_copy_device_tree();
setup_cpuinfo();
}
if (len & ~VMX_ALIGN_MASK) {
+ preempt_disable();
pagefault_disable();
enable_kernel_altivec();
crc = __crc32c_vpmsum(crc, p, len & ~VMX_ALIGN_MASK);
+ disable_kernel_altivec();
pagefault_enable();
+ preempt_enable();
}
tail = len & VMX_ALIGN_MASK;
nb = aligninfo[instr].len;
flags = aligninfo[instr].flags;
- /* ldbrx/stdbrx overlap lfs/stfs in the DSISR unfortunately */
- if (IS_XFORM(instruction) && ((instruction >> 1) & 0x3ff) == 532) {
- nb = 8;
- flags = LD+SW;
- } else if (IS_XFORM(instruction) &&
- ((instruction >> 1) & 0x3ff) == 660) {
- nb = 8;
- flags = ST+SW;
+ /*
+ * Handle some cases which give overlaps in the DSISR values.
+ */
+ if (IS_XFORM(instruction)) {
+ switch (get_xop(instruction)) {
+ case 532: /* ldbrx */
+ nb = 8;
+ flags = LD+SW;
+ break;
+ case 660: /* stdbrx */
+ nb = 8;
+ flags = ST+SW;
+ break;
+ case 20: /* lwarx */
+ case 84: /* ldarx */
+ case 116: /* lharx */
+ case 276: /* lqarx */
+ return 0; /* not emulated ever */
+ }
}
/* Byteswap little endian loads and stores */
* flush all bytes from start through stop-1 inclusive
*/
-_GLOBAL(flush_icache_range)
+_GLOBAL_TOC(flush_icache_range)
BEGIN_FTR_SECTION
PURGE_PREFETCHED_INS
blr
*
* flush all bytes from start to stop-1 inclusive
*/
-_GLOBAL(flush_dcache_range)
+_GLOBAL_TOC(flush_dcache_range)
/*
* Flush the data cache to memory
mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
}
+ /*
+ * Fixup HFSCR:TM based on CPU features. The bit is set by our
+ * early asm init because at that point we haven't updated our
+ * CPU features from firmware and device-tree. Here we have,
+ * so let's do it.
+ */
+ if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
+ mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
+
/* Set IR and DR in PACA MSR */
get_paca()->kernel_msr = MSR_KERNEL;
}
/* start new resize */
resize = kzalloc(sizeof(*resize), GFP_KERNEL);
+ if (!resize) {
+ ret = -ENOMEM;
+ goto out;
+ }
resize->order = shift;
resize->kvm = kvm;
INIT_WORK(&resize->work, resize_hpt_prepare_work);
unsigned long psize = batch->psize;
int ssize = batch->ssize;
int i;
+ unsigned int use_local;
+
+ use_local = local && mmu_has_feature(MMU_FTR_TLBIEL) &&
+ mmu_psize_defs[psize].tlbiel && !cxl_ctx_in_use();
local_irq_save(flags);
} pte_iterate_hashed_end();
}
- if (mmu_has_feature(MMU_FTR_TLBIEL) &&
- mmu_psize_defs[psize].tlbiel && local) {
+ if (use_local) {
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
vpn = batch->vpn[i];
unsigned long decompress_kernel(void)
{
- unsigned long output_addr;
- unsigned char *output;
+ void *output, *kernel_end;
- output_addr = ((unsigned long) &_end + HEAP_SIZE + 4095UL) & -4096UL;
- check_ipl_parmblock((void *) 0, output_addr + SZ__bss_start);
- memset(&_bss, 0, &_ebss - &_bss);
- free_mem_ptr = (unsigned long)&_end;
- free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
- output = (unsigned char *) output_addr;
+ output = (void *) ALIGN((unsigned long) &_end + HEAP_SIZE, PAGE_SIZE);
+ kernel_end = output + SZ__bss_start;
+ check_ipl_parmblock((void *) 0, (unsigned long) kernel_end);
#ifdef CONFIG_BLK_DEV_INITRD
/*
* Move the initrd right behind the end of the decompressed
- * kernel image.
+ * kernel image. This also prevents initrd corruption caused by
+ * bss clearing since kernel_end will always be located behind the
+ * current bss section..
*/
- if (INITRD_START && INITRD_SIZE &&
- INITRD_START < (unsigned long) output + SZ__bss_start) {
- check_ipl_parmblock(output + SZ__bss_start,
- INITRD_START + INITRD_SIZE);
- memmove(output + SZ__bss_start,
- (void *) INITRD_START, INITRD_SIZE);
- INITRD_START = (unsigned long) output + SZ__bss_start;
+ if (INITRD_START && INITRD_SIZE && kernel_end > (void *) INITRD_START) {
+ check_ipl_parmblock(kernel_end, INITRD_SIZE);
+ memmove(kernel_end, (void *) INITRD_START, INITRD_SIZE);
+ INITRD_START = (unsigned long) kernel_end;
}
#endif
+ /*
+ * Clear bss section. free_mem_ptr and free_mem_end_ptr need to be
+ * initialized afterwards since they reside in bss.
+ */
+ memset(&_bss, 0, &_ebss - &_bss);
+ free_mem_ptr = (unsigned long) &_end;
+ free_mem_end_ptr = free_mem_ptr + HEAP_SIZE;
+
puts("Uncompressing Linux... ");
__decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error);
puts("Ok, booting the kernel.\n");
" jg 2b\n" \
".popsection\n" \
EX_TABLE(0b,3b) EX_TABLE(1b,3b) \
- : "=d" (__rc), "=Q" (*(to)) \
+ : "=d" (__rc), "+Q" (*(to)) \
: "d" (size), "Q" (*(from)), \
"d" (__reg0), "K" (-EFAULT) \
: "cc"); \
{
struct pcpu *pcpu = pcpu_devices;
+ WARN_ON(!cpu_present(0) || !cpu_online(0));
pcpu->state = CPU_STATE_CONFIGURED;
- pcpu->address = stap();
pcpu->lowcore = (struct lowcore *)(unsigned long) store_prefix();
S390_lowcore.percpu_offset = __per_cpu_offset[0];
smp_cpu_set_polarization(0, POLARIZATION_UNKNOWN);
- set_cpu_present(0, true);
- set_cpu_online(0, true);
}
void __init smp_cpus_done(unsigned int max_cpus)
void __init smp_setup_processor_id(void)
{
+ pcpu_devices[0].address = stap();
S390_lowcore.cpu_nr = 0;
S390_lowcore.spinlock_lockval = arch_spin_lockval(0);
}
unsigned long z : 1; /* Zero Bit */
unsigned long i : 1; /* Page-Invalid Bit */
unsigned long p : 1; /* DAT-Protection Bit */
- unsigned long co : 1; /* Change-Recording Override */
- unsigned long : 8;
+ unsigned long : 9;
};
};
return PGM_PAGE_TRANSLATION;
if (pte.z)
return PGM_TRANSLATION_SPEC;
- if (pte.co && !edat1)
- return PGM_TRANSLATION_SPEC;
dat_protection |= pte.p;
raddr.pfra = pte.pfra;
real_address:
rc = gmap_read_table(sg->parent, pgt + vaddr.px * 8, &pte.val);
if (!rc && pte.i)
rc = PGM_PAGE_TRANSLATION;
- if (!rc && (pte.z || (pte.co && sg->edat_level < 1)))
+ if (!rc && pte.z)
rc = PGM_TRANSLATION_SPEC;
shadow_page:
pte.p |= dat_protection;
#define HPAGE_SHIFT 23
#define REAL_HPAGE_SHIFT 22
+#define HPAGE_2GB_SHIFT 31
#define HPAGE_256MB_SHIFT 28
#define HPAGE_64K_SHIFT 16
#define REAL_HPAGE_SIZE (_AC(1,UL) << REAL_HPAGE_SHIFT)
#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT)
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
#define REAL_HPAGE_PER_HPAGE (_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
-#define HUGE_MAX_HSTATE 3
+#define HUGE_MAX_HSTATE 4
#endif
#ifndef __ASSEMBLY__
return pte_pfn(pte);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline unsigned long pmd_dirty(pmd_t pmd)
+#define __HAVE_ARCH_PMD_WRITE
+static inline unsigned long pmd_write(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_dirty(pte);
+ return pte_write(pte);
}
-static inline unsigned long pmd_young(pmd_t pmd)
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_young(pte);
+ return pte_dirty(pte);
}
-static inline unsigned long pmd_write(pmd_t pmd)
+static inline unsigned long pmd_young(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
- return pte_write(pte);
+ return pte_young(pte);
}
static inline unsigned long pmd_trans_huge(pmd_t pmd)
#include <asm/signal.h>
#include <asm/page.h>
-/*
- * The sparc has no problems with write protection
- */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
/* Whee, this is STACK_TOP + PAGE_SIZE and the lowest kernel address too...
* That one page is used to protect kernel from intruders, so that
* we can make our access_ok test faster
#include <asm/ptrace.h>
#include <asm/page.h>
-/* The sparc has no problems with write protection */
-#define wp_works_ok 1
-#define wp_works_ok__is_a_macro /* for versions in ksyms.c */
-
/*
* User lives in his very own context, and cannot reference us. Note
* that TASK_SIZE is a misnomer, it really gives maximum user virtual
andn %g1, PSTATE_AM, %g1
wrpr %g1, 0x0, %pstate
ba,a,pt %xcc, 1f
+ nop
.globl prom_finddev_name, prom_chosen_path, prom_root_node
.globl prom_getprop_name, prom_mmu_name, prom_peer_name
nop
ba,a,pt %xcc, 80f
+ nop
niagara4_patch:
call niagara4_patch_copyops
nop
nop
ba,a,pt %xcc, 80f
+ nop
niagara2_patch:
call niagara2_patch_copyops
nop
ba,a,pt %xcc, 80f
+ nop
niagara_patch:
call niagara_patch_copyops
call handle_stdfmna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
+ nop
.size do_stdfmna,.-do_stdfmna
.type breakpoint_trap,#function
bne,pt %xcc, user_rtt_fill_32bit
wrpr %g1, %cwp
ba,a,pt %xcc, user_rtt_fill_64bit
+ nop
user_rtt_fill_fixup_dax:
ba,pt %xcc, user_rtt_fill_fixup_common
rd %pc, %g7
ba,a,pt %xcc, 2f
+ nop
1: ba,pt %xcc, etrap_irq
rd %pc, %g7
call sun4v_do_mna
add %sp, PTREGS_OFF, %o0
ba,a,pt %xcc, rtrap
+ nop
/* Privileged Action. */
sun4v_privact:
call sun4v_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
1: call spitfire_data_access_exception
nop
call sun4v_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
1: call spitfire_data_access_exception
nop
ba,a,pt %xcc, rtrap
+ nop
blu 170f
nop
ba,a,pt %xcc, 180f
+ nop
4: /* 32 <= low bits < 48 */
blu 150f
nop
ba,a,pt %xcc, 160f
+ nop
5: /* 0 < low bits < 32 */
blu,a 6f
cmp %g2, 8
blu 130f
nop
ba,a,pt %xcc, 140f
+ nop
6: /* 0 < low bits < 16 */
bgeu 120f
nop
brz,pt %o2, 85f
sub %o0, %o1, GLOBAL_SPARE
ba,a,pt %XCC, 90f
+ nop
.align 64
75: /* 16 < len <= 64 */
bne,pt %icc, 1b
EX_ST(STORE(stb, %g1, %o0 - 0x01), NG4_retl_o2_plus_1)
ba,a,pt %icc, .Lexit
+ nop
.size FUNC_NAME, .-FUNC_NAME
bne,pt %icc, 1b
add %o0, 0x30, %o0
ba,a,pt %icc, .Lpostloop
+ nop
.size NG4bzero,.-NG4bzero
brz,pt %i2, 85f
sub %o0, %i1, %i3
ba,a,pt %XCC, 90f
+ nop
.align 64
70: /* 16 < len <= 64 */
pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
switch (shift) {
+ case HPAGE_2GB_SHIFT:
+ hugepage_size = _PAGE_SZ2GB_4V;
+ pte_val(entry) |= _PAGE_PMD_HUGE;
+ break;
case HPAGE_256MB_SHIFT:
hugepage_size = _PAGE_SZ256MB_4V;
pte_val(entry) |= _PAGE_PMD_HUGE;
unsigned int shift;
switch (tte_szbits) {
+ case _PAGE_SZ2GB_4V:
+ shift = HPAGE_2GB_SHIFT;
+ break;
case _PAGE_SZ256MB_4V:
shift = HPAGE_256MB_SHIFT;
break;
if (!pmd)
return NULL;
- if (sz == PMD_SHIFT)
+ if (sz >= PMD_SIZE)
pte = (pte_t *)pmd;
else
pte = pte_alloc_map(mm, pmd, addr);
hugepage_shift = ilog2(hugepage_size);
switch (hugepage_shift) {
+ case HPAGE_2GB_SHIFT:
+ hv_pgsz_mask = HV_PGSZ_MASK_2GB;
+ hv_pgsz_idx = HV_PGSZ_IDX_2GB;
+ break;
case HPAGE_256MB_SHIFT:
hv_pgsz_mask = HV_PGSZ_MASK_256MB;
hv_pgsz_idx = HV_PGSZ_IDX_256MB;
if ((long)addr < 0L) {
unsigned long pa = __pa(addr);
- if ((addr >> max_phys_bits) != 0UL)
+ if ((pa >> max_phys_bits) != 0UL)
return false;
return pfn_valid(pa >> PAGE_SHIFT);
enum mbus_module srmmu_modtype;
static unsigned int hwbug_bitmask;
int vac_cache_size;
+EXPORT_SYMBOL(vac_cache_size);
int vac_line_size;
extern struct resource sparc_iomap;
if (pte_val(*pte) & _PAGE_VALID) {
bool exec = pte_exec(*pte);
- tlb_batch_add_one(mm, vaddr, exec, false);
+ tlb_batch_add_one(mm, vaddr, exec, PAGE_SHIFT);
}
pte++;
vaddr += PAGE_SIZE;
pte_t orig_pte = __pte(pmd_val(orig));
bool exec = pte_exec(orig_pte);
- tlb_batch_add_one(mm, addr, exec, true);
+ tlb_batch_add_one(mm, addr, exec, REAL_HPAGE_SHIFT);
tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec,
- true);
+ REAL_HPAGE_SHIFT);
} else {
tlb_batch_pmd_scan(mm, addr, orig);
}
spin_lock_irqsave(&mm->context.lock, flags);
- if (tb->hugepage_shift < HPAGE_SHIFT) {
+ if (tb->hugepage_shift < REAL_HPAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
spin_lock_irqsave(&mm->context.lock, flags);
- if (hugepage_shift < HPAGE_SHIFT) {
+ if (hugepage_shift < REAL_HPAGE_SHIFT) {
base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb;
nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries;
if (tlb_type == cheetah_plus || tlb_type == hypervisor)
static DEFINE_MUTEX(mce_chrdev_read_mutex);
+static int mce_chrdev_open_count; /* #times opened */
+
#define mce_log_get_idx_check(p) \
({ \
RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
if (atomic_read(&num_notifiers) > 2)
return NOTIFY_DONE;
+ /* Don't print when mcelog is running */
+ if (mce_chrdev_open_count > 0)
+ return NOTIFY_DONE;
+
__print_mce(m);
return NOTIFY_DONE;
*/
static DEFINE_SPINLOCK(mce_chrdev_state_lock);
-static int mce_chrdev_open_count; /* #times opened */
static int mce_chrdev_open_exclu; /* already open exclusive? */
static int mce_chrdev_open(struct inode *inode, struct file *file)
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
case EXIT_REASON_PREEMPTION_TIMER:
return false;
+ case EXIT_REASON_PML_FULL:
+ /* We don't expose PML support to L1. */
+ return false;
default:
return true;
}
}
+ if (enable_pml) {
+ /*
+ * Conceptually we want to copy the PML address and index from
+ * vmcs01 here, and then back to vmcs01 on nested vmexit. But,
+ * since we always flush the log on each vmexit, this happens
+ * to be equivalent to simply resetting the fields in vmcs02.
+ */
+ ASSERT(vmx->pml_pg);
+ vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
+ vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
+ }
+
if (nested_cpu_has_ept(vmcs12)) {
kvm_mmu_unload(vcpu);
nested_ept_init_mmu_context(vcpu);
#define ARCH_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT)
+#ifdef CONFIG_MMU
+static inline unsigned long ___pa(unsigned long va)
+{
+ unsigned long off = va - PAGE_OFFSET;
+
+ if (off >= XCHAL_KSEG_SIZE)
+ off -= XCHAL_KSEG_SIZE;
+
+ return off + PHYS_OFFSET;
+}
+#define __pa(x) ___pa((unsigned long)(x))
+#else
#define __pa(x) \
((unsigned long) (x) - PAGE_OFFSET + PHYS_OFFSET)
+#endif
#define __va(x) \
((void *)((unsigned long) (x) - PHYS_OFFSET + PAGE_OFFSET))
#define pfn_valid(pfn) \
#define __NR_pkey_free 350
__SYSCALL(350, sys_pkey_free, 1)
-#define __NR_syscall_count 351
+#define __NR_statx 351
+__SYSCALL(351, sys_statx, 5)
+
+#define __NR_syscall_count 352
/*
* sysxtensa syscall handler
static int show_trace_cb(struct stackframe *frame, void *data)
{
- if (kernel_text_address(frame->pc)) {
- pr_cont(" [<%08lx>]", frame->pc);
- print_symbol(" %s\n", frame->pc);
- }
+ if (kernel_text_address(frame->pc))
+ pr_cont(" [<%08lx>] %pB\n", frame->pc, (void *)frame->pc);
return 0;
}
void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
{
- struct elevator_queue *e = hctx->queue->elevator;
+ struct request_queue *q = hctx->queue;
+ struct elevator_queue *e = q->elevator;
const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
bool did_work = false;
LIST_HEAD(rq_list);
*/
if (!list_empty(&rq_list)) {
blk_mq_sched_mark_restart_hctx(hctx);
- did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
+ did_work = blk_mq_dispatch_rq_list(q, &rq_list);
} else if (!has_sched_dispatch) {
blk_mq_flush_busy_ctxs(hctx, &rq_list);
- blk_mq_dispatch_rq_list(hctx, &rq_list);
+ blk_mq_dispatch_rq_list(q, &rq_list);
}
/*
if (!rq)
break;
list_add(&rq->queuelist, &rq_list);
- } while (blk_mq_dispatch_rq_list(hctx, &rq_list));
+ } while (blk_mq_dispatch_rq_list(q, &rq_list));
}
}
return true;
}
-static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
{
if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (blk_mq_hctx_has_pending(hctx))
+ if (blk_mq_hctx_has_pending(hctx)) {
blk_mq_run_hw_queue(hctx, true);
+ return true;
+ }
}
+ return false;
}
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
- unsigned int i;
+/**
+ * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
+ * @pos: loop cursor.
+ * @skip: the list element that will not be examined. Iteration starts at
+ * @skip->next.
+ * @head: head of the list to examine. This list must have at least one
+ * element, namely @skip.
+ * @member: name of the list_head structure within typeof(*pos).
+ */
+#define list_for_each_entry_rcu_rr(pos, skip, head, member) \
+ for ((pos) = (skip); \
+ (pos = (pos)->member.next != (head) ? list_entry_rcu( \
+ (pos)->member.next, typeof(*pos), member) : \
+ list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
+ (pos) != (skip); )
- if (test_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- if (test_and_clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags)) {
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_sched_restart_hctx(hctx);
+/*
+ * Called after a driver tag has been freed to check whether a hctx needs to
+ * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
+ * queues in a round-robin fashion if the tag set of @hctx is shared with other
+ * hardware queues.
+ */
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
+{
+ struct blk_mq_tags *const tags = hctx->tags;
+ struct blk_mq_tag_set *const set = hctx->queue->tag_set;
+ struct request_queue *const queue = hctx->queue, *q;
+ struct blk_mq_hw_ctx *hctx2;
+ unsigned int i, j;
+
+ if (set->flags & BLK_MQ_F_TAG_SHARED) {
+ rcu_read_lock();
+ list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
+ tag_set_list) {
+ queue_for_each_hw_ctx(q, hctx2, i)
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ goto done;
+ }
+ j = hctx->queue_num + 1;
+ for (i = 0; i < queue->nr_hw_queues; i++, j++) {
+ if (j == queue->nr_hw_queues)
+ j = 0;
+ hctx2 = queue->queue_hw_ctx[j];
+ if (hctx2->tags == tags &&
+ blk_mq_sched_restart_hctx(hctx2))
+ break;
}
+done:
+ rcu_read_unlock();
} else {
blk_mq_sched_restart_hctx(hctx);
}
}
}
-int blk_mq_sched_setup(struct request_queue *q)
+static int blk_mq_sched_alloc_tags(struct request_queue *q,
+ struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct blk_mq_tag_set *set = q->tag_set;
+ int ret;
+
+ hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests,
+ set->reserved_tags);
+ if (!hctx->sched_tags)
+ return -ENOMEM;
+
+ ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
+ if (ret)
+ blk_mq_sched_free_tags(set, hctx, hctx_idx);
+
+ return ret;
+}
+
+static void blk_mq_sched_tags_teardown(struct request_queue *q)
{
struct blk_mq_tag_set *set = q->tag_set;
struct blk_mq_hw_ctx *hctx;
- int ret, i;
+ int i;
+
+ queue_for_each_hw_ctx(q, hctx, i)
+ blk_mq_sched_free_tags(set, hctx, i);
+}
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (!e)
+ return 0;
+
+ return blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+}
+
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (!e)
+ return;
+
+ blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+}
+
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
+{
+ struct blk_mq_hw_ctx *hctx;
+ unsigned int i;
+ int ret;
+
+ if (!e) {
+ q->elevator = NULL;
+ return 0;
+ }
/*
* Default to 256, since we don't split into sync/async like the
*/
q->nr_requests = 2 * BLKDEV_MAX_RQ;
- /*
- * We're switching to using an IO scheduler, so setup the hctx
- * scheduler tags and switch the request map from the regular
- * tags to scheduler tags. First allocate what we need, so we
- * can safely fail and fallback, if needed.
- */
- ret = 0;
queue_for_each_hw_ctx(q, hctx, i) {
- hctx->sched_tags = blk_mq_alloc_rq_map(set, i,
- q->nr_requests, set->reserved_tags);
- if (!hctx->sched_tags) {
- ret = -ENOMEM;
- break;
- }
- ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests);
+ ret = blk_mq_sched_alloc_tags(q, hctx, i);
if (ret)
- break;
+ goto err;
}
- /*
- * If we failed, free what we did allocate
- */
- if (ret) {
- queue_for_each_hw_ctx(q, hctx, i) {
- if (!hctx->sched_tags)
- continue;
- blk_mq_sched_free_tags(set, hctx, i);
- }
-
- return ret;
- }
+ ret = e->ops.mq.init_sched(q, e);
+ if (ret)
+ goto err;
return 0;
+
+err:
+ blk_mq_sched_tags_teardown(q);
+ q->elevator = NULL;
+ return ret;
}
-void blk_mq_sched_teardown(struct request_queue *q)
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
{
- struct blk_mq_tag_set *set = q->tag_set;
- struct blk_mq_hw_ctx *hctx;
- int i;
-
- queue_for_each_hw_ctx(q, hctx, i)
- blk_mq_sched_free_tags(set, hctx, i);
+ if (e->type->ops.mq.exit_sched)
+ e->type->ops.mq.exit_sched(e);
+ blk_mq_sched_tags_teardown(q);
+ q->elevator = NULL;
}
int blk_mq_sched_init(struct request_queue *q)
struct request **merged_request);
bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
-void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx);
void blk_mq_sched_insert_request(struct request *rq, bool at_head,
bool run_queue, bool async, bool can_block);
struct list_head *rq_list,
struct request *(*get_rq)(struct blk_mq_hw_ctx *));
-int blk_mq_sched_setup(struct request_queue *q);
-void blk_mq_sched_teardown(struct request_queue *q);
+int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
+void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
+
+int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx);
+void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+ unsigned int hctx_idx);
int blk_mq_sched_init(struct request_queue *q);
set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
}
-/*
- * Mark a hardware queue and the request queue it belongs to as needing a
- * restart.
- */
-static inline void blk_mq_sched_mark_restart_queue(struct blk_mq_hw_ctx *hctx)
-{
- struct request_queue *q = hctx->queue;
-
- if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
- set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
- if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
- set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
-}
-
static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
{
return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
- blk_mq_put_ctx(alloc_data.ctx);
blk_queue_exit(q);
if (!rq)
blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
if (sched_tag != -1)
blk_mq_sched_completed_request(hctx, rq);
- blk_mq_sched_restart_queues(hctx);
+ blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
};
- if (rq->tag != -1) {
-done:
- if (hctx)
- *hctx = data.hctx;
- return true;
- }
+ if (rq->tag != -1)
+ goto done;
if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
data.flags |= BLK_MQ_REQ_RESERVED;
atomic_inc(&data.hctx->nr_active);
}
data.hctx->tags->rqs[rq->tag] = rq;
- goto done;
}
- return false;
+done:
+ if (hctx)
+ *hctx = data.hctx;
+ return rq->tag != -1;
}
static void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
return true;
}
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
{
- struct request_queue *q = hctx->queue;
+ struct blk_mq_hw_ctx *hctx;
struct request *rq;
LIST_HEAD(driver_list);
struct list_head *dptr;
int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
+ if (list_empty(list))
+ return false;
+
/*
* Start off with dptr being NULL, so we start the first request
* immediately, even if we have more pending.
* Now process all the entries, sending them to the driver.
*/
errors = queued = 0;
- while (!list_empty(list)) {
+ do {
struct blk_mq_queue_data bd;
rq = list_first_entry(list, struct request, queuelist);
*/
if (!dptr && list->next != list->prev)
dptr = &driver_list;
- }
+ } while (!list_empty(list));
hctx->dispatched[queued_to_index(queued)]++;
return hctx->next_cpu;
}
-void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
+ unsigned long msecs)
{
if (unlikely(blk_mq_hctx_stopped(hctx) ||
!blk_mq_hw_queue_mapped(hctx)))
put_cpu();
}
- kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work);
+ if (msecs == 0)
+ kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->run_work);
+ else
+ kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+ &hctx->delayed_run_work,
+ msecs_to_jiffies(msecs));
+}
+
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
+{
+ __blk_mq_delay_run_hw_queue(hctx, true, msecs);
+}
+EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+{
+ __blk_mq_delay_run_hw_queue(hctx, async, 0);
}
void blk_mq_run_hw_queues(struct request_queue *q, bool async)
__blk_mq_run_hw_queue(hctx);
}
+static void blk_mq_delayed_run_work_fn(struct work_struct *work)
+{
+ struct blk_mq_hw_ctx *hctx;
+
+ hctx = container_of(work, struct blk_mq_hw_ctx, delayed_run_work.work);
+
+ __blk_mq_run_hw_queue(hctx);
+}
+
static void blk_mq_delay_work_fn(struct work_struct *work)
{
struct blk_mq_hw_ctx *hctx;
hctx->fq->flush_rq, hctx_idx,
flush_start_tag + hctx_idx);
+ blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
+
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
node = hctx->numa_node = set->numa_node;
INIT_WORK(&hctx->run_work, blk_mq_run_work_fn);
+ INIT_DELAYED_WORK(&hctx->delayed_run_work, blk_mq_delayed_run_work_fn);
INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
spin_lock_init(&hctx->lock);
INIT_LIST_HEAD(&hctx->dispatch);
set->ops->init_hctx(hctx, set->driver_data, hctx_idx))
goto free_bitmap;
+ if (blk_mq_sched_init_hctx(q, hctx, hctx_idx))
+ goto exit_hctx;
+
hctx->fq = blk_alloc_flush_queue(q, hctx->numa_node, set->cmd_size);
if (!hctx->fq)
- goto exit_hctx;
+ goto sched_exit_hctx;
if (set->ops->init_request &&
set->ops->init_request(set->driver_data,
free_fq:
kfree(hctx->fq);
+ sched_exit_hctx:
+ blk_mq_sched_exit_hctx(q, hctx, hctx_idx);
exit_hctx:
if (set->ops->exit_hctx)
set->ops->exit_hctx(hctx, hctx_idx);
struct blk_mq_hw_ctx *hctx;
unsigned int i;
- blk_mq_sched_teardown(q);
-
/* hctx kobj stays in hctx */
queue_for_each_hw_ctx(q, hctx, i) {
if (!hctx)
return 0;
}
+static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
+{
+ if (set->ops->map_queues)
+ return set->ops->map_queues(set);
+ else
+ return blk_mq_map_queues(set);
+}
+
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
if (!set->mq_map)
goto out_free_tags;
- if (set->ops->map_queues)
- ret = set->ops->map_queues(set);
- else
- ret = blk_mq_map_queues(set);
+ ret = blk_mq_update_queue_map(set);
if (ret)
goto out_free_mq_map;
blk_mq_freeze_queue(q);
set->nr_hw_queues = nr_hw_queues;
+ blk_mq_update_queue_map(set);
list_for_each_entry(q, &set->tag_list, tag_set_list) {
blk_mq_realloc_hw_ctxs(set, q);
void blk_mq_free_queue(struct request_queue *q);
int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
void blk_mq_wake_waiters(struct request_queue *q);
-bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
+bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *);
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
if (q->elevator) {
ioc_clear_queue(q);
- elevator_exit(q->elevator);
+ elevator_exit(q, q->elevator);
}
blk_exit_rl(&q->root_rl);
}
}
- if (e->uses_mq) {
- err = blk_mq_sched_setup(q);
- if (!err)
- err = e->ops.mq.init_sched(q, e);
- } else
+ if (e->uses_mq)
+ err = blk_mq_init_sched(q, e);
+ else
err = e->ops.sq.elevator_init_fn(q, e);
- if (err) {
- if (e->uses_mq)
- blk_mq_sched_teardown(q);
+ if (err)
elevator_put(e);
- }
return err;
}
EXPORT_SYMBOL(elevator_init);
-void elevator_exit(struct elevator_queue *e)
+void elevator_exit(struct request_queue *q, struct elevator_queue *e)
{
mutex_lock(&e->sysfs_lock);
if (e->uses_mq && e->type->ops.mq.exit_sched)
- e->type->ops.mq.exit_sched(e);
+ blk_mq_exit_sched(q, e);
else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
e->type->ops.sq.elevator_exit_fn(e);
mutex_unlock(&e->sysfs_lock);
}
EXPORT_SYMBOL_GPL(elv_unregister);
+static int elevator_switch_mq(struct request_queue *q,
+ struct elevator_type *new_e)
+{
+ int ret;
+
+ blk_mq_freeze_queue(q);
+ blk_mq_quiesce_queue(q);
+
+ if (q->elevator) {
+ if (q->elevator->registered)
+ elv_unregister_queue(q);
+ ioc_clear_queue(q);
+ elevator_exit(q, q->elevator);
+ }
+
+ ret = blk_mq_init_sched(q, new_e);
+ if (ret)
+ goto out;
+
+ if (new_e) {
+ ret = elv_register_queue(q);
+ if (ret) {
+ elevator_exit(q, q->elevator);
+ goto out;
+ }
+ }
+
+ if (new_e)
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+ else
+ blk_add_trace_msg(q, "elv switch: none");
+
+out:
+ blk_mq_unfreeze_queue(q);
+ blk_mq_start_stopped_hw_queues(q, true);
+ return ret;
+
+}
+
/*
* switch to new_e io scheduler. be careful not to introduce deadlocks -
* we don't free the old io scheduler, before we have allocated what we
bool old_registered = false;
int err;
- if (q->mq_ops) {
- blk_mq_freeze_queue(q);
- blk_mq_quiesce_queue(q);
- }
+ if (q->mq_ops)
+ return elevator_switch_mq(q, new_e);
/*
* Turn on BYPASS and drain all requests w/ elevator private data.
if (old) {
old_registered = old->registered;
- if (old->uses_mq)
- blk_mq_sched_teardown(q);
-
- if (!q->mq_ops)
- blk_queue_bypass_start(q);
+ blk_queue_bypass_start(q);
/* unregister and clear all auxiliary data of the old elevator */
if (old_registered)
}
/* allocate, init and register new elevator */
- if (new_e) {
- if (new_e->uses_mq) {
- err = blk_mq_sched_setup(q);
- if (!err)
- err = new_e->ops.mq.init_sched(q, new_e);
- } else
- err = new_e->ops.sq.elevator_init_fn(q, new_e);
- if (err)
- goto fail_init;
+ err = new_e->ops.sq.elevator_init_fn(q, new_e);
+ if (err)
+ goto fail_init;
- err = elv_register_queue(q);
- if (err)
- goto fail_register;
- } else
- q->elevator = NULL;
+ err = elv_register_queue(q);
+ if (err)
+ goto fail_register;
/* done, kill the old one and finish */
if (old) {
- elevator_exit(old);
- if (!q->mq_ops)
- blk_queue_bypass_end(q);
+ elevator_exit(q, old);
+ blk_queue_bypass_end(q);
}
- if (q->mq_ops) {
- blk_mq_unfreeze_queue(q);
- blk_mq_start_stopped_hw_queues(q, true);
- }
-
- if (new_e)
- blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
- else
- blk_add_trace_msg(q, "elv switch: none");
+ blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
return 0;
fail_register:
- if (q->mq_ops)
- blk_mq_sched_teardown(q);
- elevator_exit(q->elevator);
+ elevator_exit(q, q->elevator);
fail_init:
/* switch failed, restore and re-register old elevator */
if (old) {
q->elevator = old;
elv_register_queue(q);
- if (!q->mq_ops)
- blk_queue_bypass_end(q);
- }
- if (q->mq_ops) {
- blk_mq_unfreeze_queue(q);
- blk_mq_start_stopped_hw_queues(q, true);
+ blk_queue_bypass_end(q);
}
return err;
return -ENODEV;
/*
- * If the device has a _HID (or _CID) returning a valid ACPI/PNP
- * device ID, it is better to make it look less attractive here, so that
- * the other device with the same _ADR value (that may not have a valid
- * device ID) can be matched going forward. [This means a second spec
- * violation in a row, so whatever we do here is best effort anyway.]
+ * If the device has a _HID returning a valid ACPI/PNP device ID, it is
+ * better to make it look less attractive here, so that the other device
+ * with the same _ADR value (that may not have a valid device ID) can be
+ * matched going forward. [This means a second spec violation in a row,
+ * so whatever we do here is best effort anyway.]
*/
- return sta_present && list_empty(&adev->pnp.ids) ?
+ return sta_present && !adev->pnp.type.platform_id ?
FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE;
}
goto fail_free_event;
}
+ if (agpio->wake_capable == ACPI_WAKE_CAPABLE)
+ enable_irq_wake(irq);
+
list_add_tail(&event->node, &acpi_gpio->events);
return AE_OK;
list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) {
struct gpio_desc *desc;
+ if (irqd_is_wakeup_set(irq_get_irq_data(event->irq)))
+ disable_irq_wake(event->irq);
+
free_irq(event->irq, event);
desc = event->desc;
if (WARN_ON(IS_ERR(desc)))
}
desc = acpi_get_gpiod_by_index(adev, propname, idx, &info);
- if (!IS_ERR(desc) || (PTR_ERR(desc) == -EPROBE_DEFER))
+ if (!IS_ERR(desc))
break;
+ if (PTR_ERR(desc) == -EPROBE_DEFER)
+ return ERR_CAST(desc);
}
/* Then from plain _CRS GPIOs */
if (!fence) {
event_free(gpu, event);
ret = -ENOMEM;
- goto out_pm_put;
+ goto out_unlock;
}
gpu->event[event].fence = fence;
hangcheck_timer_reset(gpu);
ret = 0;
+out_unlock:
mutex_unlock(&gpu->lock);
out_pm_put:
{
int ret;
- if (vgpu->failsafe)
- return 0;
-
if (WARN_ON(bytes > 4))
return -EINVAL;
_EL_OFFSET_STATUS_PTR);
ctx_status_ptr.dw = vgpu_vreg(vgpu, ctx_status_ptr_reg);
- ctx_status_ptr.read_ptr = ctx_status_ptr.write_ptr = 0x7;
+ ctx_status_ptr.read_ptr = 0;
+ ctx_status_ptr.write_ptr = 0x7;
vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
}
struct gvt_firmware_header *h;
void *firmware;
void *p;
- unsigned long size;
+ unsigned long size, crc32_start;
int i;
int ret;
- size = sizeof(*h) + info->mmio_size + info->cfg_space_size - 1;
+ size = sizeof(*h) + info->mmio_size + info->cfg_space_size;
firmware = vzalloc(size);
if (!firmware)
return -ENOMEM;
memcpy(gvt->firmware.mmio, p, info->mmio_size);
+ crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4;
+ h->crc32 = crc32_le(0, firmware + crc32_start, size - crc32_start);
+
firmware_attr.size = size;
firmware_attr.private = firmware;
firmware->mmio = mem;
- sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%04x.golden_hw_state",
+ sprintf(path, "%s/vid_0x%04x_did_0x%04x_rid_0x%02x.golden_hw_state",
GVT_FIRMWARE_PATH, pdev->vendor, pdev->device,
pdev->revision);
.vgpu_create = intel_gvt_create_vgpu,
.vgpu_destroy = intel_gvt_destroy_vgpu,
.vgpu_reset = intel_gvt_reset_vgpu,
+ .vgpu_activate = intel_gvt_activate_vgpu,
+ .vgpu_deactivate = intel_gvt_deactivate_vgpu,
};
/**
void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
unsigned int engine_mask);
void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
-
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu);
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu);
/* validating GM functions */
#define vgpu_gmadr_is_aperture(vgpu, gmadr) \
struct intel_vgpu_type *);
void (*vgpu_destroy)(struct intel_vgpu *);
void (*vgpu_reset)(struct intel_vgpu *);
+ void (*vgpu_activate)(struct intel_vgpu *);
+ void (*vgpu_deactivate)(struct intel_vgpu *);
};
if (ret)
goto undo_group;
+ intel_gvt_ops->vgpu_activate(vgpu);
+
atomic_set(&vgpu->vdev.released, 0);
return ret;
if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1))
return;
+ intel_gvt_ops->vgpu_deactivate(vgpu);
+
ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY,
&vgpu->vdev.iommu_notifier);
WARN(ret, "vfio_unregister_notifier for iommu failed: %d\n", ret);
static bool kvmgt_guest_exit(struct kvmgt_guest_info *info)
{
- struct intel_vgpu *vgpu = info->vgpu;
-
- if (!info) {
- gvt_vgpu_err("kvmgt_guest_info invalid\n");
- return false;
- }
-
kvm_page_track_unregister_notifier(info->kvm, &info->track_node);
kvm_put_kvm(info->kvm);
kvmgt_protect_table_destroy(info);
char *name;
} vgpu_types[] = {
/* Fixed vGPU type table */
- { MB_TO_BYTES(64), MB_TO_BYTES(512), 4, GVT_EDID_1024_768, "8" },
+ { MB_TO_BYTES(64), MB_TO_BYTES(384), 4, GVT_EDID_1024_768, "8" },
{ MB_TO_BYTES(128), MB_TO_BYTES(512), 4, GVT_EDID_1920_1200, "4" },
{ MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, GVT_EDID_1920_1200, "2" },
{ MB_TO_BYTES(512), MB_TO_BYTES(2048), 4, GVT_EDID_1920_1200, "1" },
}
/**
- * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * intel_gvt_active_vgpu - activate a virtual GPU
* @vgpu: virtual GPU
*
- * This function is called when user wants to destroy a virtual GPU.
+ * This function is called when user wants to activate a virtual GPU.
*
*/
-void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
+{
+ mutex_lock(&vgpu->gvt->lock);
+ vgpu->active = true;
+ mutex_unlock(&vgpu->gvt->lock);
+}
+
+/**
+ * intel_gvt_deactive_vgpu - deactivate a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to deactivate a virtual GPU.
+ * All virtual GPU runtime information will be destroyed.
+ *
+ */
+void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu)
{
struct intel_gvt *gvt = vgpu->gvt;
mutex_lock(&gvt->lock);
vgpu->active = false;
- idr_remove(&gvt->vgpu_idr, vgpu->id);
if (atomic_read(&vgpu->running_workload_num)) {
mutex_unlock(&gvt->lock);
}
intel_vgpu_stop_schedule(vgpu);
+
+ mutex_unlock(&gvt->lock);
+}
+
+/**
+ * intel_gvt_destroy_vgpu - destroy a virtual GPU
+ * @vgpu: virtual GPU
+ *
+ * This function is called when user wants to destroy a virtual GPU.
+ *
+ */
+void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
+{
+ struct intel_gvt *gvt = vgpu->gvt;
+
+ mutex_lock(&gvt->lock);
+
+ WARN(vgpu->active, "vGPU is still active!\n");
+
+ idr_remove(&gvt->vgpu_idr, vgpu->id);
intel_vgpu_clean_sched_policy(vgpu);
intel_vgpu_clean_gvt_context(vgpu);
intel_vgpu_clean_execlist(vgpu);
if (ret)
goto out_clean_shadow_ctx;
- vgpu->active = true;
mutex_unlock(&gvt->lock);
return vgpu;
goto out;
}
- intel_guc_suspend(dev_priv);
-
intel_display_suspend(dev);
intel_dp_mst_suspend(dev);
func(has_resource_streamer); \
func(has_runtime_pm); \
func(has_snoop); \
+ func(unfenced_needs_alignment); \
func(cursor_needs_physical); \
func(hws_needs_physical); \
func(overlay_needs_physical); \
i915_gem_context_lost(dev_priv);
mutex_unlock(&dev->struct_mutex);
+ intel_guc_suspend(dev_priv);
+
cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
cancel_delayed_work_sync(&dev_priv->gt.retire_work);
struct list_head ordered_vmas;
struct list_head pinned_vmas;
bool has_fenced_gpu_access = INTEL_GEN(engine->i915) < 4;
+ bool needs_unfenced_map = INTEL_INFO(engine->i915)->unfenced_needs_alignment;
int retry;
vm = list_first_entry(vmas, struct i915_vma, exec_list)->vm;
if (!has_fenced_gpu_access)
entry->flags &= ~EXEC_OBJECT_NEEDS_FENCE;
need_fence =
- entry->flags & EXEC_OBJECT_NEEDS_FENCE &&
+ (entry->flags & EXEC_OBJECT_NEEDS_FENCE ||
+ needs_unfenced_map) &&
i915_gem_object_is_tiled(obj);
need_mappable = need_fence || need_reloc_mappable(vma);
struct i915_ggtt *ggtt = &dev_priv->ggtt;
if (unlikely(ggtt->do_idle_maps)) {
- if (i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED)) {
+ if (i915_gem_wait_for_idle(dev_priv, 0)) {
DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
/* Wait a bit, in hopes it avoids the hang */
udelay(10);
static const char *i915_fence_get_timeline_name(struct dma_fence *fence)
{
+ /* The timeline struct (as part of the ppgtt underneath a context)
+ * may be freed when the request is no longer in use by the GPU.
+ * We could extend the life of a context to beyond that of all
+ * fences, possibly keeping the hw resource around indefinitely,
+ * or we just give them a false name. Since
+ * dma_fence_ops.get_timeline_name is a debug feature, the occasional
+ * lie seems justifiable.
+ */
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
+ return "signaled";
+
return to_request(fence)->timeline->common->name;
}
BUG();
}
+static void i915_gem_shrinker_unlock(struct drm_device *dev, bool unlock)
+{
+ if (!unlock)
+ return;
+
+ mutex_unlock(&dev->struct_mutex);
+
+ /* expedite the RCU grace period to free some request slabs */
+ synchronize_rcu_expedited();
+}
+
static bool any_vma_pinned(struct drm_i915_gem_object *obj)
{
struct i915_vma *vma;
intel_runtime_pm_put(dev_priv);
i915_gem_retire_requests(dev_priv);
- if (unlock)
- mutex_unlock(&dev_priv->drm.struct_mutex);
- /* expedite the RCU grace period to free some request slabs */
- synchronize_rcu_expedited();
+ i915_gem_shrinker_unlock(&dev_priv->drm, unlock);
return count;
}
count += obj->base.size >> PAGE_SHIFT;
}
- if (unlock)
- mutex_unlock(&dev->struct_mutex);
+ i915_gem_shrinker_unlock(dev, unlock);
return count;
}
sc->nr_to_scan - freed,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND);
- if (unlock)
- mutex_unlock(&dev->struct_mutex);
+
+ i915_gem_shrinker_unlock(dev, unlock);
return freed;
}
struct shrinker_lock_uninterruptible *slu)
{
dev_priv->mm.interruptible = slu->was_interruptible;
- if (slu->unlock)
- mutex_unlock(&dev_priv->drm.struct_mutex);
+ i915_gem_shrinker_unlock(&dev_priv->drm, slu->unlock);
}
static int
.has_overlay = 1, .overlay_needs_physical = 1, \
.has_gmch_display = 1, \
.hws_needs_physical = 1, \
+ .unfenced_needs_alignment = 1, \
.ring_mask = RENDER_RING, \
GEN_DEFAULT_PIPEOFFSETS, \
CURSOR_OFFSETS
.platform = INTEL_I915G, .cursor_needs_physical = 1,
.has_overlay = 1, .overlay_needs_physical = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i915gm_info = {
.supports_tv = 1,
.has_fbc = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i945g_info = {
.has_hotplug = 1, .cursor_needs_physical = 1,
.has_overlay = 1, .overlay_needs_physical = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_i945gm_info = {
.supports_tv = 1,
.has_fbc = 1,
.hws_needs_physical = 1,
+ .unfenced_needs_alignment = 1,
};
static const struct intel_device_info intel_g33_info = {
*/
if (WARN_ON(stream->sample_flags != props->sample_flags)) {
ret = -ENODEV;
- goto err_alloc;
+ goto err_flags;
}
list_add(&stream->link, &dev_priv->perf.streams);
err_open:
list_del(&stream->link);
+err_flags:
if (stream->ops->destroy)
stream->ops->destroy(stream);
err_alloc:
if (ret)
return ret;
+ if (id == 0 || id >= DRM_I915_PERF_PROP_MAX) {
+ DRM_DEBUG("Unknown i915 perf property ID\n");
+ return -EINVAL;
+ }
+
switch ((enum drm_i915_perf_property_id)id) {
case DRM_I915_PERF_PROP_CTX_HANDLE:
props->single_context = 1;
props->oa_periodic = true;
props->oa_period_exponent = value;
break;
- default:
+ case DRM_I915_PERF_PROP_MAX:
MISSING_CASE(id);
- DRM_DEBUG("Unknown i915 perf property ID\n");
return -EINVAL;
}
static struct intel_engine_cs *
pt_lock_engine(struct i915_priotree *pt, struct intel_engine_cs *locked)
{
- struct intel_engine_cs *engine;
+ struct intel_engine_cs *engine =
+ container_of(pt, struct drm_i915_gem_request, priotree)->engine;
+
+ GEM_BUG_ON(!locked);
- engine = container_of(pt,
- struct drm_i915_gem_request,
- priotree)->engine;
if (engine != locked) {
- if (locked)
- spin_unlock_irq(&locked->timeline->lock);
- spin_lock_irq(&engine->timeline->lock);
+ spin_unlock(&locked->timeline->lock);
+ spin_lock(&engine->timeline->lock);
}
return engine;
static void execlists_schedule(struct drm_i915_gem_request *request, int prio)
{
- struct intel_engine_cs *engine = NULL;
+ struct intel_engine_cs *engine;
struct i915_dependency *dep, *p;
struct i915_dependency stack;
LIST_HEAD(dfs);
list_for_each_entry_safe(dep, p, &dfs, dfs_link) {
struct i915_priotree *pt = dep->signaler;
- list_for_each_entry(p, &pt->signalers_list, signal_link)
+ /* Within an engine, there can be no cycle, but we may
+ * refer to the same dependency chain multiple times
+ * (redundant dependencies are not eliminated) and across
+ * engines.
+ */
+ list_for_each_entry(p, &pt->signalers_list, signal_link) {
+ GEM_BUG_ON(p->signaler->priority < pt->priority);
if (prio > READ_ONCE(p->signaler->priority))
list_move_tail(&p->dfs_link, &dfs);
+ }
list_safe_reset_next(dep, p, dfs_link);
- if (!RB_EMPTY_NODE(&pt->node))
- continue;
-
- engine = pt_lock_engine(pt, engine);
-
- /* If it is not already in the rbtree, we can update the
- * priority inplace and skip over it (and its dependencies)
- * if it is referenced *again* as we descend the dfs.
- */
- if (prio > pt->priority && RB_EMPTY_NODE(&pt->node)) {
- pt->priority = prio;
- list_del_init(&dep->dfs_link);
- }
}
+ engine = request->engine;
+ spin_lock_irq(&engine->timeline->lock);
+
/* Fifo and depth-first replacement ensure our deps execute before us */
list_for_each_entry_safe_reverse(dep, p, &dfs, dfs_link) {
struct i915_priotree *pt = dep->signaler;
if (prio <= pt->priority)
continue;
- GEM_BUG_ON(RB_EMPTY_NODE(&pt->node));
-
pt->priority = prio;
- rb_erase(&pt->node, &engine->execlist_queue);
- if (insert_request(pt, &engine->execlist_queue))
- engine->execlist_first = &pt->node;
+ if (!RB_EMPTY_NODE(&pt->node)) {
+ rb_erase(&pt->node, &engine->execlist_queue);
+ if (insert_request(pt, &engine->execlist_queue))
+ engine->execlist_first = &pt->node;
+ }
}
- if (engine)
- spin_unlock_irq(&engine->timeline->lock);
+ spin_unlock_irq(&engine->timeline->lock);
/* XXX Do we need to preempt to make room for us and our deps? */
}
GEM_BUG_ON(request->ctx != port[0].request->ctx);
/* Reset WaIdleLiteRestore:bdw,skl as well */
- request->tail = request->wa_tail - WA_TAIL_DWORDS * sizeof(u32);
+ request->tail =
+ intel_ring_wrap(request->ring,
+ request->wa_tail - WA_TAIL_DWORDS*sizeof(u32));
}
static int intel_logical_ring_emit_pdps(struct drm_i915_gem_request *req)
*/
}
+static inline u32
+intel_ring_wrap(const struct intel_ring *ring, u32 pos)
+{
+ return pos & (ring->size - 1);
+}
+
static inline u32 intel_ring_offset(struct intel_ring *ring, void *addr)
{
/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
u32 offset = addr - ring->vaddr;
- return offset & (ring->size - 1);
+ return intel_ring_wrap(ring, offset);
}
int __intel_ring_space(int head, int tail, int size);
#include <linux/slab.h>
#include <linux/fb.h>
#include <linux/prefetch.h>
+#include <asm/unaligned.h>
#include <drm/drmP.h>
#include "udl_drv.h"
const u8 *const start = pixel;
const uint16_t repeating_pixel_val16 = pixel_val16;
- *(uint16_t *)cmd = cpu_to_be16(pixel_val16);
+ put_unaligned_be16(pixel_val16, cmd);
cmd += 2;
pixel += bpp;
name = "accel_3d";
channel_spec = accel_3d_channels;
channel_size = sizeof(accel_3d_channels);
+ indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
} else {
name = "gravity";
channel_spec = gravity_channels;
channel_size = sizeof(gravity_channels);
+ indio_dev->num_channels = ARRAY_SIZE(gravity_channels);
}
ret = hid_sensor_parse_common_attributes(hsdev, hsdev->usage,
&accel_state->common_attributes);
goto error_free_dev_mem;
}
- indio_dev->num_channels = ARRAY_SIZE(accel_3d_channels);
indio_dev->dev.parent = &pdev->dev;
indio_dev->info = &accel_3d_info;
indio_dev->name = name;
ret = st->core.read_ec_sensors_data(indio_dev, 1 << idx, &data);
if (ret < 0)
break;
-
+ ret = IIO_VAL_INT;
*val = data;
break;
case IIO_CHAN_INFO_CALIBBIAS:
for (i = CROS_EC_SENSOR_X; i < CROS_EC_SENSOR_MAX_AXIS; i++)
st->core.calib[i] =
st->core.resp->sensor_offset.offset[i];
-
+ ret = IIO_VAL_INT;
*val = st->core.calib[idx];
break;
case IIO_CHAN_INFO_SCALE:
{
struct hid_sensor_hub_attribute_info timestamp;
+ s32 value;
+ int ret;
hid_sensor_get_reporting_interval(hsdev, usage_id, st);
st->sensitivity.index, st->sensitivity.report_id,
timestamp.index, timestamp.report_id);
+ ret = sensor_hub_get_feature(hsdev,
+ st->power_state.report_id,
+ st->power_state.index, sizeof(value), &value);
+ if (ret < 0)
+ return ret;
+ if (value < 0)
+ return -EINVAL;
+
return 0;
}
EXPORT_SYMBOL(hid_sensor_parse_common_attributes);
#include <linux/iio/trigger_consumer.h>
#include <linux/iio/triggered_buffer.h>
#include <linux/regmap.h>
+#include <linux/delay.h>
#include "bmg160.h"
#define BMG160_IRQ_NAME "bmg160_event"
#define BMG160_DEF_BW 100
#define BMG160_REG_PMU_BW_RES BIT(7)
+#define BMG160_GYRO_REG_RESET 0x14
+#define BMG160_GYRO_RESET_VAL 0xb6
+
#define BMG160_REG_INT_MAP_0 0x17
#define BMG160_INT_MAP_0_BIT_ANY BIT(1)
int ret;
unsigned int val;
+ /*
+ * Reset chip to get it in a known good state. A delay of 30ms after
+ * reset is required according to the datasheet.
+ */
+ regmap_write(data->regmap, BMG160_GYRO_REG_RESET,
+ BMG160_GYRO_RESET_VAL);
+ usleep_range(30000, 30700);
+
ret = regmap_read(data->regmap, BMG160_REG_CHIP_ID, &val);
if (ret < 0) {
dev_err(dev, "Error reading reg_chip_id\n");
tmp0 = (int)div_s64_rem(tmp, 1000000000, &tmp1);
return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
case IIO_VAL_FRACTIONAL_LOG2:
- tmp = (s64)vals[0] * 1000000000LL >> vals[1];
- tmp1 = do_div(tmp, 1000000000LL);
- tmp0 = tmp;
- return snprintf(buf, len, "%d.%09u", tmp0, tmp1);
+ tmp = shift_right((s64)vals[0] * 1000000000LL, vals[1]);
+ tmp0 = (int)div_s64_rem(tmp, 1000000000LL, &tmp1);
+ return snprintf(buf, len, "%d.%09u", tmp0, abs(tmp1));
case IIO_VAL_INT_MULTIPLE:
{
int i;
.addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR,
},
.multi_read_bit = true,
+ .bootime = 2,
},
};
sizeof(avmb1_carddef))))
return -EFAULT;
cdef.cardtype = AVM_CARDTYPE_B1;
+ cdef.cardnr = 0;
} else {
if ((retval = copy_from_user(&cdef, data,
sizeof(avmb1_extcarddef))))
*result = true;
r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root,
- from_cblock(begin), &cmd->dirty_cursor);
+ from_cblock(cmd->cache_blocks), &cmd->dirty_cursor);
if (r) {
DMERR("%s: dm_bitset_cursor_begin for dirty failed", __func__);
return r;
return 0;
}
+ begin = to_cblock(from_cblock(begin) + 1);
+ if (begin == end)
+ break;
+
r = dm_bitset_cursor_next(&cmd->dirty_cursor);
if (r) {
DMERR("%s: dm_bitset_cursor_next for dirty failed", __func__);
dm_bitset_cursor_end(&cmd->dirty_cursor);
return r;
}
-
- begin = to_cblock(from_cblock(begin) + 1);
}
dm_bitset_cursor_end(&cmd->dirty_cursor);
return r;
/* Resize bitmap to adjust to changed region size (aka MD bitmap chunksize) */
- if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) &&
+ if (test_bit(RT_FLAG_RS_BITMAP_LOADED, &rs->runtime_flags) && mddev->bitmap &&
mddev->bitmap_info.chunksize != to_bytes(rs->requested_bitmap_chunk_sectors)) {
r = bitmap_resize(mddev->bitmap, mddev->dev_sectors,
to_bytes(rs->requested_bitmap_chunk_sectors), 0);
/* Undo dm_start_request() before requeuing */
rq_end_stats(md, rq);
rq_completed(md, rq_data_dir(rq), false);
+ blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
return BLK_MQ_RQ_QUEUE_BUSY;
}
block = fec_buffer_rs_block(v, fio, n, i);
res = fec_decode_rs8(v, fio, block, &par[offset], neras);
if (res < 0) {
- dm_bufio_release(buf);
-
r = res;
goto error;
}
done:
r = corrected;
error:
+ dm_bufio_release(buf);
+
if (r < 0 && neras)
DMERR_LIMIT("%s: FEC %llu: failed to correct: %d",
v->data_dev->name, (unsigned long long)rsb, r);
&is_zero) == 0) {
/* skip known zero blocks entirely */
if (is_zero)
- continue;
+ goto done;
/*
* skip if we have already found the theoretical
if (!verity_fec_is_enabled(v))
return -EOPNOTSUPP;
+ if (fio->level >= DM_VERITY_FEC_MAX_RECURSION) {
+ DMWARN_LIMIT("%s: FEC: recursion too deep", v->data_dev->name);
+ return -EIO;
+ }
+
+ fio->level++;
+
if (type == DM_VERITY_BLOCK_TYPE_METADATA)
block += v->data_blocks;
if (r < 0) {
r = fec_decode_rsb(v, io, fio, rsb, offset, true);
if (r < 0)
- return r;
+ goto done;
}
if (dest)
r = verity_for_bv_block(v, io, iter, fec_bv_copy);
}
+done:
+ fio->level--;
return r;
}
memset(fio->bufs, 0, sizeof(fio->bufs));
fio->nbufs = 0;
fio->output = NULL;
+ fio->level = 0;
}
/*
#define DM_VERITY_FEC_BUF_MAX \
(1 << (PAGE_SHIFT - DM_VERITY_FEC_BUF_RS_BITS))
+/* maximum recursion level for verity_fec_decode */
+#define DM_VERITY_FEC_MAX_RECURSION 4
+
#define DM_VERITY_OPT_FEC_DEV "use_fec_from_device"
#define DM_VERITY_OPT_FEC_BLOCKS "fec_blocks"
#define DM_VERITY_OPT_FEC_START "fec_start"
unsigned nbufs; /* number of buffers allocated */
u8 *output; /* buffer for corrected output */
size_t output_pos;
+ unsigned level; /* recursion level */
};
#ifdef CONFIG_DM_VERITY_FEC
goto err_exit;
ndev->mtu = new_mtu;
- if (netif_running(ndev)) {
- aq_ndev_close(ndev);
- aq_ndev_open(ndev);
- }
-
err_exit:
return err;
}
dx_buff->mss = skb_shinfo(skb)->gso_size;
dx_buff->is_txc = 1U;
+ dx_buff->is_ipv6 =
+ (ip_hdr(skb)->version == 6) ? 1U : 0U;
+
dx = aq_ring_next_dx(ring, dx);
dx_buff = &ring->buff_ring[dx];
++ret;
if (skb->ip_summed == CHECKSUM_PARTIAL) {
dx_buff->is_ip_cso = (htons(ETH_P_IP) == skb->protocol) ?
1U : 0U;
- dx_buff->is_tcp_cso =
- (ip_hdr(skb)->protocol == IPPROTO_TCP) ? 1U : 0U;
- dx_buff->is_udp_cso =
- (ip_hdr(skb)->protocol == IPPROTO_UDP) ? 1U : 0U;
+
+ if (ip_hdr(skb)->version == 4) {
+ dx_buff->is_tcp_cso =
+ (ip_hdr(skb)->protocol == IPPROTO_TCP) ?
+ 1U : 0U;
+ dx_buff->is_udp_cso =
+ (ip_hdr(skb)->protocol == IPPROTO_UDP) ?
+ 1U : 0U;
+ } else if (ip_hdr(skb)->version == 6) {
+ dx_buff->is_tcp_cso =
+ (ipv6_hdr(skb)->nexthdr == NEXTHDR_TCP) ?
+ 1U : 0U;
+ dx_buff->is_udp_cso =
+ (ipv6_hdr(skb)->nexthdr == NEXTHDR_UDP) ?
+ 1U : 0U;
+ }
}
for (; nr_frags--; ++frag_count) {
self->hw_head = 0;
self->sw_head = 0;
self->sw_tail = 0;
+ spin_lock_init(&self->header.lock);
return 0;
}
u8 len_l2;
u8 len_l3;
u8 len_l4;
- u8 rsvd2;
+ u8 is_ipv6:1;
+ u8 rsvd2:7;
u32 len_pkt;
};
};
buff->len_l3 +
buff->len_l2);
is_gso = true;
+
+ if (buff->is_ipv6)
+ txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_IPV6;
} else {
buff_pa_len = buff->len;
if (unlikely(buff->is_eop)) {
txd->ctl |= HW_ATL_A0_TXD_CTL_EOP;
txd->ctl |= HW_ATL_A0_TXD_CTL_CMD_WB;
+ is_gso = false;
}
}
buff->len_l3 +
buff->len_l2);
is_gso = true;
+
+ if (buff->is_ipv6)
+ txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_IPV6;
} else {
buff_pa_len = buff->len;
if (unlikely(buff->is_eop)) {
txd->ctl |= HW_ATL_B0_TXD_CTL_EOP;
txd->ctl |= HW_ATL_B0_TXD_CTL_CMD_WB;
+ is_gso = false;
}
}
GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RBCP) | \
GENERAL_ATTEN_OFFSET(LATCHED_ATTN_RSVD_GRC))
-#define HW_INTERRUT_ASSERT_SET_0 \
+#define HW_INTERRUPT_ASSERT_SET_0 \
(AEU_INPUTS_ATTN_BITS_TSDM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TCM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TSEMI_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TSEMI_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_TCM_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_PBCLIENT_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_1 \
+#define HW_INTERRUPT_ASSERT_SET_1 \
(AEU_INPUTS_ATTN_BITS_QM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_TIMERS_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_XSDM_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_UPB_PARITY_ERROR | \
AEU_INPUTS_ATTN_BITS_CSDM_PARITY_ERROR |\
AEU_INPUTS_ATTN_BITS_CCM_PARITY_ERROR)
-#define HW_INTERRUT_ASSERT_SET_2 \
+#define HW_INTERRUPT_ASSERT_SET_2 \
(AEU_INPUTS_ATTN_BITS_CSEMI_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_CDU_HW_INTERRUPT | \
AEU_INPUTS_ATTN_BITS_DMAE_HW_INTERRUPT | \
bnx2x_release_phy_lock(bp);
}
- if (attn & HW_INTERRUT_ASSERT_SET_0) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_0) {
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_0);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_0);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set0 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_0));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_0));
bnx2x_panic();
}
}
BNX2X_ERR("FATAL error from DORQ\n");
}
- if (attn & HW_INTERRUT_ASSERT_SET_1) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_1) {
int port = BP_PORT(bp);
int reg_offset;
MISC_REG_AEU_ENABLE1_FUNC_0_OUT_1);
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_1);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_1);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set1 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_1));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_1));
bnx2x_panic();
}
}
}
}
- if (attn & HW_INTERRUT_ASSERT_SET_2) {
+ if (attn & HW_INTERRUPT_ASSERT_SET_2) {
int port = BP_PORT(bp);
int reg_offset;
MISC_REG_AEU_ENABLE1_FUNC_0_OUT_2);
val = REG_RD(bp, reg_offset);
- val &= ~(attn & HW_INTERRUT_ASSERT_SET_2);
+ val &= ~(attn & HW_INTERRUPT_ASSERT_SET_2);
REG_WR(bp, reg_offset, val);
BNX2X_ERR("FATAL HW block attention set2 0x%x\n",
- (u32)(attn & HW_INTERRUT_ASSERT_SET_2));
+ (u32)(attn & HW_INTERRUPT_ASSERT_SET_2));
bnx2x_panic();
}
}
for (j = 0; j < max_idx; j++) {
struct bnxt_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[j];
+ dma_addr_t mapping = rx_buf->mapping;
void *data = rx_buf->data;
if (!data)
continue;
- dma_unmap_single(&pdev->dev, rx_buf->mapping,
- bp->rx_buf_use_size, bp->rx_dir);
-
rx_buf->data = NULL;
- if (BNXT_RX_PAGE_MODE(bp))
+ if (BNXT_RX_PAGE_MODE(bp)) {
+ mapping -= bp->rx_dma_offset;
+ dma_unmap_page(&pdev->dev, mapping,
+ PAGE_SIZE, bp->rx_dir);
__free_page(data);
- else
+ } else {
+ dma_unmap_single(&pdev->dev, mapping,
+ bp->rx_buf_use_size,
+ bp->rx_dir);
kfree(data);
+ }
}
for (j = 0; j < max_agg_idx; j++) {
return 0;
}
+static void bnxt_init_cp_rings(struct bnxt *bp)
+{
+ int i;
+
+ for (i = 0; i < bp->cp_nr_rings; i++) {
+ struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring;
+ struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+
+ ring->fw_ring_id = INVALID_HW_RING_ID;
+ }
+}
+
static int bnxt_init_rx_rings(struct bnxt *bp)
{
int i, rc = 0;
rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
if (rc) {
netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n",
- rc, i);
+ i, rc);
return rc;
}
}
static int bnxt_init_nic(struct bnxt *bp, bool irq_re_init)
{
+ bnxt_init_cp_rings(bp);
bnxt_init_rx_rings(bp);
bnxt_init_tx_rings(bp);
bnxt_init_ring_grps(bp, irq_re_init);
bfa_ioc_send_enable(struct bfa_ioc *ioc)
{
struct bfi_ioc_ctrl_req enable_req;
- struct timeval tv;
bfi_h2i_set(enable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_ENABLE_REQ,
bfa_ioc_portid(ioc));
enable_req.clscode = htons(ioc->clscode);
- do_gettimeofday(&tv);
- enable_req.tv_sec = ntohl(tv.tv_sec);
+ enable_req.rsvd = htons(0);
+ /* overflow in 2106 */
+ enable_req.tv_sec = ntohl(ktime_get_real_seconds());
bfa_ioc_mbox_send(ioc, &enable_req, sizeof(struct bfi_ioc_ctrl_req));
}
bfi_h2i_set(disable_req.mh, BFI_MC_IOC, BFI_IOC_H2I_DISABLE_REQ,
bfa_ioc_portid(ioc));
+ disable_req.clscode = htons(ioc->clscode);
+ disable_req.rsvd = htons(0);
+ /* overflow in 2106 */
+ disable_req.tv_sec = ntohl(ktime_get_real_seconds());
bfa_ioc_mbox_send(ioc, &disable_req, sizeof(struct bfi_ioc_ctrl_req));
}
__be_cmd_set_logical_link_config(struct be_adapter *adapter,
int link_state, int version, u8 domain)
{
- struct be_mcc_wrb *wrb;
struct be_cmd_req_set_ll_link *req;
+ struct be_mcc_wrb *wrb;
+ u32 link_config = 0;
int status;
mutex_lock(&adapter->mcc_lock);
if (link_state == IFLA_VF_LINK_STATE_ENABLE ||
link_state == IFLA_VF_LINK_STATE_AUTO)
- req->link_config |= PLINK_ENABLE;
+ link_config |= PLINK_ENABLE;
if (link_state == IFLA_VF_LINK_STATE_AUTO)
- req->link_config |= PLINK_TRACK;
+ link_config |= PLINK_TRACK;
+
+ req->link_config = cpu_to_le32(link_config);
status = be_mcc_notify_wait(adapter);
err:
nps_enet_tx_handler(ndev);
work_done = nps_enet_rx_handler(ndev);
- if (work_done < budget) {
+ if ((work_done < budget) && napi_complete_done(napi, work_done)) {
u32 buf_int_enable_value = 0;
- napi_complete_done(napi, work_done);
-
/* set tx_done and rx_rdy bits */
buf_int_enable_value |= NPS_ENET_ENABLE << RX_RDY_SHIFT;
buf_int_enable_value |= NPS_ENET_ENABLE << TX_DONE_SHIFT;
#include <linux/io.h>
#include <linux/module.h>
#include <linux/netdevice.h>
+#include <linux/of.h>
#include <linux/phy.h>
#include <linux/platform_device.h>
+#include <linux/property.h>
#include <net/ip.h>
#include <net/ncsi.h>
else
*link_status = 0;
- ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb, &sfp_prsnt);
- if (!ret)
- *link_status = *link_status && sfp_prsnt;
+ if (mac_cb->media_type == HNAE_MEDIA_TYPE_FIBER) {
+ ret = mac_cb->dsaf_dev->misc_op->get_sfp_prsnt(mac_cb,
+ &sfp_prsnt);
+ if (!ret)
+ *link_status = *link_status && sfp_prsnt;
+ }
mac_cb->link = *link_status;
}
of_node_put(np);
np = of_parse_phandle(to_of_node(mac_cb->fw_port),
- "serdes-syscon", 0);
+ "serdes-syscon", 0);
syscon = syscon_node_to_regmap(np);
of_node_put(np);
if (IS_ERR_OR_NULL(syscon)) {
mac_key->high.bits.mac_3 = addr[3];
mac_key->low.bits.mac_4 = addr[4];
mac_key->low.bits.mac_5 = addr[5];
+ mac_key->low.bits.port_vlan = 0;
dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_VLAN_M,
DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
/* find the tcam entry index for promisc */
entry_index = dsaf_promisc_tcam_entry(port);
+ memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
+ memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
+
/* config key mask */
if (enable) {
- memset(&tbl_tcam_data, 0, sizeof(tbl_tcam_data));
- memset(&tbl_tcam_mask, 0, sizeof(tbl_tcam_mask));
dsaf_set_field(tbl_tcam_data.low.bits.port_vlan,
DSAF_TBL_TCAM_KEY_PORT_M,
DSAF_TBL_TCAM_KEY_PORT_S, port);
return 0;
}
+int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+{
+ union acpi_object *obj;
+ union acpi_object obj_args, argv4;
+
+ obj_args.integer.type = ACPI_TYPE_INTEGER;
+ obj_args.integer.value = mac_cb->mac_id;
+
+ argv4.type = ACPI_TYPE_PACKAGE,
+ argv4.package.count = 1,
+ argv4.package.elements = &obj_args,
+
+ obj = acpi_evaluate_dsm(ACPI_HANDLE(mac_cb->dev),
+ hns_dsaf_acpi_dsm_uuid, 0,
+ HNS_OP_GET_SFP_STAT_FUNC, &argv4);
+
+ if (!obj || obj->type != ACPI_TYPE_INTEGER)
+ return -ENODEV;
+
+ *sfp_prsnt = obj->integer.value;
+
+ ACPI_FREE(obj);
+
+ return 0;
+}
+
/**
* hns_mac_config_sds_loopback - set loop back for serdes
* @mac_cb: mac control block
misc_op->hns_dsaf_roce_srst = hns_dsaf_roce_srst_acpi;
misc_op->get_phy_if = hns_mac_get_phy_if_acpi;
- misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt;
+ misc_op->get_sfp_prsnt = hns_mac_get_sfp_prsnt_acpi;
misc_op->cfg_serdes_loopback = hns_mac_config_sds_loopback_acpi;
} else {
/* Quiesce the device without resetting the hardware */
e1000e_down(adapter, false);
e1000_free_irq(adapter);
- e1000e_reset_interrupt_capability(adapter);
}
+ e1000e_reset_interrupt_capability(adapter);
/* Allow time for pending master requests to run */
e1000e_disable_pcie_master(&adapter->hw);
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_enable(&vsi->q_vectors[q_idx]->napi);
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+ struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_enable(&q_vector->napi);
+ }
}
/**
if (!vsi->netdev)
return;
- for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
- napi_disable(&vsi->q_vectors[q_idx]->napi);
+ for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+ struct i40e_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+ if (q_vector->rx.ring || q_vector->tx.ring)
+ napi_disable(&q_vector->napi);
+ }
}
/**
struct netdev_notifier_changeupper_info *info)
{
struct net_device *upper = info->upper_dev, *ndev_tmp;
- struct netdev_lag_upper_info *lag_upper_info;
+ struct netdev_lag_upper_info *lag_upper_info = NULL;
bool is_bonded;
int bond_status = 0;
int num_slaves = 0;
if (!netif_is_lag_master(upper))
return 0;
- lag_upper_info = info->upper_info;
+ if (info->linking)
+ lag_upper_info = info->upper_info;
/* The event may still be of interest if the slave does not belong to
* us, but is enslaved to a master which has one or more of our netdevs
#include <linux/of_irq.h>
#include <linux/crc32.h>
#include <linux/crc32c.h>
+#include <linux/circ_buf.h>
#include "moxart_ether.h"
return rx;
}
+static int moxart_tx_queue_space(struct net_device *ndev)
+{
+ struct moxart_mac_priv_t *priv = netdev_priv(ndev);
+
+ return CIRC_SPACE(priv->tx_head, priv->tx_tail, TX_DESC_NUM);
+}
+
static void moxart_tx_finished(struct net_device *ndev)
{
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
tx_tail = TX_NEXT(tx_tail);
}
priv->tx_tail = tx_tail;
+ if (netif_queue_stopped(ndev) &&
+ moxart_tx_queue_space(ndev) >= TX_WAKE_THRESHOLD)
+ netif_wake_queue(ndev);
}
static irqreturn_t moxart_mac_interrupt(int irq, void *dev_id)
struct moxart_mac_priv_t *priv = netdev_priv(ndev);
void *desc;
unsigned int len;
- unsigned int tx_head = priv->tx_head;
+ unsigned int tx_head;
u32 txdes1;
int ret = NETDEV_TX_BUSY;
+ spin_lock_irq(&priv->txlock);
+
+ tx_head = priv->tx_head;
desc = priv->tx_desc_base + (TX_REG_DESC_SIZE * tx_head);
- spin_lock_irq(&priv->txlock);
+ if (moxart_tx_queue_space(ndev) == 1)
+ netif_stop_queue(ndev);
+
if (moxart_desc_read(desc + TX_REG_OFFSET_DESC0) & TX_DESC0_DMA_OWN) {
net_dbg_ratelimited("no TX space for packet\n");
priv->stats.tx_dropped++;
#define TX_NEXT(N) (((N) + 1) & (TX_DESC_NUM_MASK))
#define TX_BUF_SIZE 1600
#define TX_BUF_SIZE_MAX (TX_DESC1_BUF_SIZE_MASK+1)
+#define TX_WAKE_THRESHOLD 16
#define RX_DESC_NUM 64
#define RX_DESC_NUM_MASK (RX_DESC_NUM-1)
{
struct nfp_net *nn = netdev_priv(netdev);
+ unregister_netdev(nn->netdev);
+
if (nn->xdp_prog)
bpf_prog_put(nn->xdp_prog);
if (nn->bpf_offload_xdp)
nfp_net_xdp_offload(nn, NULL);
- unregister_netdev(nn->netdev);
}
{
bool want[OFDPA_CTRL_MAX] = { 0, };
bool prev_ctrls[OFDPA_CTRL_MAX];
- u8 uninitialized_var(prev_state);
+ u8 prev_state;
int err;
int i;
- if (switchdev_trans_ph_prepare(trans)) {
- memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
- prev_state = ofdpa_port->stp_state;
- }
-
- if (ofdpa_port->stp_state == state)
+ prev_state = ofdpa_port->stp_state;
+ if (prev_state == state)
return 0;
+ memcpy(prev_ctrls, ofdpa_port->ctrls, sizeof(prev_ctrls));
ofdpa_port->stp_state = state;
switch (state) {
static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
{
u32 slave_port;
+ struct phy_device *phy;
struct cpsw_common *cpsw = priv->cpsw;
soft_reset_slave(slave);
1 << slave_port, 0, 0, ALE_MCAST_FWD_2);
if (slave->data->phy_node) {
- slave->phy = of_phy_connect(priv->ndev, slave->data->phy_node,
+ phy = of_phy_connect(priv->ndev, slave->data->phy_node,
&cpsw_adjust_link, 0, slave->data->phy_if);
- if (!slave->phy) {
+ if (!phy) {
dev_err(priv->dev, "phy \"%s\" not found on slave %d\n",
slave->data->phy_node->full_name,
slave->slave_num);
return;
}
} else {
- slave->phy = phy_connect(priv->ndev, slave->data->phy_id,
+ phy = phy_connect(priv->ndev, slave->data->phy_id,
&cpsw_adjust_link, slave->data->phy_if);
- if (IS_ERR(slave->phy)) {
+ if (IS_ERR(phy)) {
dev_err(priv->dev,
"phy \"%s\" not found on slave %d, err %ld\n",
slave->data->phy_id, slave->slave_num,
- PTR_ERR(slave->phy));
- slave->phy = NULL;
+ PTR_ERR(phy));
return;
}
}
+ slave->phy = phy;
+
phy_attached_info(slave->phy);
phy_start(slave->phy);
}
cpsw_intr_enable(cpsw);
+ netif_trans_update(ndev);
+ netif_tx_wake_all_queues(ndev);
}
static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p)
memset(rd, 0, sizeof(*rd));
rd->hw = hwmap + i;
rd->buf = kmalloc(len, GFP_KERNEL|GFP_DMA);
- if (rd->buf == NULL ||
- !(busaddr = pci_map_single(pdev, rd->buf, len, dir))) {
+ if (rd->buf)
+ busaddr = pci_map_single(pdev, rd->buf, len, dir);
+ if (rd->buf == NULL || pci_dma_mapping_error(pdev, busaddr)) {
if (rd->buf) {
net_err_ratelimited("%s: failed to create PCI-MAP for %p\n",
__func__, rd->buf);
rd = r->rd + j;
busaddr = rd_get_addr(rd);
rd_set_addr_status(rd, 0, 0);
- if (busaddr)
- pci_unmap_single(pdev, busaddr, len, dir);
+ pci_unmap_single(pdev, busaddr, len, dir);
kfree(rd->buf);
rd->buf = NULL;
}
return 0;
}
+EXPORT_SYMBOL(mdiobus_register_board_info);
cancel_delayed_work_sync(&phydev->state_queue);
mutex_lock(&phydev->lock);
- if (phydev->state > PHY_UP)
+ if (phydev->state > PHY_UP && phydev->state != PHY_HALTED)
phydev->state = PHY_UP;
mutex_unlock(&phydev->lock);
}
#define LENOVO_VENDOR_ID 0x17ef
#define NVIDIA_VENDOR_ID 0x0955
#define HP_VENDOR_ID 0x03f0
+#define MICROSOFT_VENDOR_ID 0x045e
static const struct usb_device_id products[] = {
/* BLACKLIST !!
.driver_info = 0,
},
+/* Microsoft Surface 2 dock (based on Realtek RTL8152) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07ab, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
+/* Microsoft Surface 3 dock (based on Realtek RTL8153) */
+{
+ USB_DEVICE_AND_INTERFACE_INFO(MICROSOFT_VENDOR_ID, 0x07c6, USB_CLASS_COMM,
+ USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+ .driver_info = 0,
+},
+
/* WHITELIST!!!
*
* CDC Ether uses two interfaces, not necessarily consecutive.
/* Define these values to match your device */
#define VENDOR_ID_REALTEK 0x0bda
+#define VENDOR_ID_MICROSOFT 0x045e
#define VENDOR_ID_SAMSUNG 0x04e8
#define VENDOR_ID_LENOVO 0x17ef
#define VENDOR_ID_NVIDIA 0x0955
}
} else {
if (netif_carrier_ok(tp->netdev)) {
+ netif_stop_queue(tp->netdev);
set_bit(RTL8152_LINK_CHG, &tp->flags);
schedule_delayed_work(&tp->schedule, 0);
}
napi_enable(&tp->napi);
netif_wake_queue(netdev);
netif_info(tp, link, netdev, "carrier on\n");
+ } else if (netif_queue_stopped(netdev) &&
+ skb_queue_len(&tp->tx_queue) < tp->tx_qlen) {
+ netif_wake_queue(netdev);
}
} else {
if (netif_carrier_ok(netdev)) {
tp->rtl_ops.autosuspend_en(tp, false);
napi_disable(&tp->napi);
set_bit(WORK_ENABLE, &tp->flags);
- if (netif_carrier_ok(tp->netdev))
- rtl_start_rx(tp);
+
+ if (netif_carrier_ok(tp->netdev)) {
+ if (rtl8152_get_speed(tp) & LINK_STATUS) {
+ rtl_start_rx(tp);
+ } else {
+ netif_carrier_off(tp->netdev);
+ tp->rtl_ops.disable(tp);
+ netif_info(tp, link, tp->netdev,
+ "linking down\n");
+ }
+ }
+
napi_enable(&tp->napi);
clear_bit(SELECTIVE_SUSPEND, &tp->flags);
smp_mb__after_atomic();
static struct usb_device_id rtl8152_table[] = {
{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8152)},
{REALTEK_USB_DEVICE(VENDOR_ID_REALTEK, 0x8153)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab)},
+ {REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6)},
{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)},
{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3062)},
struct brcmf_cfg80211_info *cfg = wiphy_priv(wiphy);
struct brcmf_p2p_info *p2p = &cfg->p2p;
struct brcmf_cfg80211_vif *vif;
+ enum nl80211_iftype iftype;
bool wait_for_disable = false;
int err;
brcmf_dbg(TRACE, "delete P2P vif\n");
vif = container_of(wdev, struct brcmf_cfg80211_vif, wdev);
+ iftype = vif->wdev.iftype;
brcmf_cfg80211_arm_vif_event(cfg, vif);
- switch (vif->wdev.iftype) {
+ switch (iftype) {
case NL80211_IFTYPE_P2P_CLIENT:
if (test_bit(BRCMF_VIF_STATUS_DISCONNECTING, &vif->sme_state))
wait_for_disable = true;
BRCMF_P2P_DISABLE_TIMEOUT);
err = 0;
- if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE) {
+ if (iftype != NL80211_IFTYPE_P2P_DEVICE) {
brcmf_vif_clear_mgmt_ies(vif);
err = brcmf_p2p_release_p2p_if(vif);
}
brcmf_remove_interface(vif->ifp, true);
brcmf_cfg80211_arm_vif_event(cfg, NULL);
- if (vif->wdev.iftype != NL80211_IFTYPE_P2P_DEVICE)
+ if (iftype != NL80211_IFTYPE_P2P_DEVICE)
p2p->bss_idx[P2PAPI_BSSCFG_CONNECTION].vif = NULL;
return err;
if (ret)
return ret;
+ if (count == 0)
+ return 0;
iwl_mvm_fw_dbg_collect(mvm, FW_DBG_TRIGGER_USER, buf,
(count - 1), NULL);
qmask |= BIT(vif->hw_queue[ac]);
}
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
qmask |= BIT(vif->cab_queue);
return qmask;
return;
rcu_read_lock();
- sta = mvm->fw_id_to_mac_id[notif->sta_id];
+ sta = rcu_dereference(mvm->fw_id_to_mac_id[notif->sta_id]);
if (WARN_ON(IS_ERR_OR_NULL(sta))) {
rcu_read_unlock();
return;
iwl_mvm_get_wd_timeout(mvm, vif, false, false);
int queue;
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
queue = IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
else if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
queue = IWL_MVM_DQA_P2P_DEVICE_QUEUE;
* enabled-cab_queue to the mask)
*/
if (iwl_mvm_is_dqa_supported(mvm) &&
- vif->type == NL80211_IFTYPE_AP) {
+ (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)) {
struct iwl_trans_txq_scd_cfg cfg = {
.fifo = IWL_MVM_TX_FIFO_MCAST,
.sta_id = mvmvif->bcast_sta.sta_id,
lockdep_assert_held(&mvm->mutex);
- if (vif->type == NL80211_IFTYPE_AP)
+ if (vif->type == NL80211_IFTYPE_AP ||
+ vif->type == NL80211_IFTYPE_ADHOC)
iwl_mvm_disable_txq(mvm, vif->cab_queue, vif->cab_queue,
IWL_MAX_TID_COUNT, 0);
switch (info->control.vif->type) {
case NL80211_IFTYPE_AP:
+ case NL80211_IFTYPE_ADHOC:
/*
* Handle legacy hostapd as well, where station may be added
* only after assoc. Take care of the case where we send a
if (info->hw_queue == info->control.vif->cab_queue)
return info->hw_queue;
- WARN_ONCE(1, "fc=0x%02x", le16_to_cpu(fc));
+ WARN_ONCE(info->control.vif->type != NL80211_IFTYPE_ADHOC,
+ "fc=0x%02x", le16_to_cpu(fc));
return IWL_MVM_DQA_AP_PROBE_RESP_QUEUE;
case NL80211_IFTYPE_P2P_DEVICE:
if (ieee80211_is_mgmt(fc))
iwl_mvm_vif_from_mac80211(info.control.vif);
if (info.control.vif->type == NL80211_IFTYPE_P2P_DEVICE ||
- info.control.vif->type == NL80211_IFTYPE_AP) {
+ info.control.vif->type == NL80211_IFTYPE_AP ||
+ info.control.vif->type == NL80211_IFTYPE_ADHOC) {
sta_id = mvmvif->bcast_sta.sta_id;
queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info,
hdr->frame_control);
unsigned long flags;
struct rtl_c2hcmd *c2hcmd;
- c2hcmd = kmalloc(sizeof(*c2hcmd), GFP_KERNEL);
+ c2hcmd = kmalloc(sizeof(*c2hcmd),
+ in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
if (!c2hcmd)
goto label_err;
- c2hcmd->val = kmalloc(len, GFP_KERNEL);
+ c2hcmd->val = kmalloc(len,
+ in_interrupt() ? GFP_ATOMIC : GFP_KERNEL);
if (!c2hcmd->val)
goto label_err2;
memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
- cmnd->dsm.nr = segments - 1;
+ cmnd->dsm.nr = cpu_to_le32(segments - 1);
cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
req->special_vec.bv_page = virt_to_page(range);
u16 status;
WARN_ON(req == NULL || slog == NULL);
- if (req->cmd->get_log_page.nsid == 0xFFFFFFFF)
+ if (req->cmd->get_log_page.nsid == cpu_to_le32(0xFFFFFFFF))
status = nvmet_get_smart_log_all(req, slog);
else
status = nvmet_get_smart_log_nsid(req, slog);
sector = le64_to_cpu(write_zeroes->slba) <<
(req->ns->blksize_shift - 9);
- nr_sector = (((sector_t)le32_to_cpu(write_zeroes->length)) <<
+ nr_sector = (((sector_t)le16_to_cpu(write_zeroes->length)) <<
(req->ns->blksize_shift - 9)) + 1;
if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
return 0;
case nvme_cmd_dsm:
req->execute = nvmet_execute_dsm;
- req->data_len = le32_to_cpu(cmd->dsm.nr + 1) *
+ req->data_len = (le32_to_cpu(cmd->dsm.nr) + 1) *
sizeof(struct nvme_dsm_range);
return 0;
case nvme_cmd_write_zeroes:
depends on PCI_MSI_IRQ_DOMAIN
select PCIEPORTBUS
select PCIE_DW_HOST
+ select PCI_HOST_COMMON
help
Say Y here if you want PCIe controller support on HiSilicon
Hip05 and Hip06 SoCs
return 0;
}
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
static int artpec6_pcie_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
return -ENOMEM;
pci->dev = dev;
+ pci->ops = &dw_pcie_ops;
artpec6_pcie->pci = pci;
return 0;
}
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
static int dw_plat_pcie_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
return -ENOMEM;
pci->dev = dev;
+ pci->ops = &dw_pcie_ops;
dw_plat_pcie->pci = pci;
index -= node * PEM_MAX_DOM_IN_NODE;
res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) |
FIELD_PREP(PEM_INDX_MASK, index);
- res_pem->end = res_pem->start + SZ_16M - 1;
res_pem->flags = IORESOURCE_MEM;
}
*/
if (ret) {
thunder_pem_legacy_fw(root, res_pem);
- /* Reserve PEM-specific resources and PCI configuration space */
+ /*
+ * Reserve 64K size PEM specific resources. The full 16M range
+ * size is required for thunder_pem_init() call.
+ */
+ res_pem->end = res_pem->start + SZ_64K - 1;
thunder_pem_reserve_range(dev, root->segment, res_pem);
+ res_pem->end = res_pem->start + SZ_16M - 1;
+
+ /* Reserve PCI configuration space as well. */
thunder_pem_reserve_range(dev, root->segment, &cfg->res);
}
return ERR_PTR(ret);
}
-static int pinctrl_create_and_start(struct pinctrl_dev *pctldev)
+static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev)
{
pctldev->p = create_pinctrl(pctldev->dev, pctldev);
- if (!IS_ERR(pctldev->p)) {
- kref_get(&pctldev->p->users);
- pctldev->hog_default =
- pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
- if (IS_ERR(pctldev->hog_default)) {
- dev_dbg(pctldev->dev,
- "failed to lookup the default state\n");
- } else {
- if (pinctrl_select_state(pctldev->p,
- pctldev->hog_default))
- dev_err(pctldev->dev,
- "failed to select default state\n");
- }
+ if (PTR_ERR(pctldev->p) == -ENODEV) {
+ dev_dbg(pctldev->dev, "no hogs found\n");
- pctldev->hog_sleep =
- pinctrl_lookup_state(pctldev->p,
- PINCTRL_STATE_SLEEP);
- if (IS_ERR(pctldev->hog_sleep))
- dev_dbg(pctldev->dev,
- "failed to lookup the sleep state\n");
+ return 0;
+ }
+
+ if (IS_ERR(pctldev->p)) {
+ dev_err(pctldev->dev, "error claiming hogs: %li\n",
+ PTR_ERR(pctldev->p));
+
+ return PTR_ERR(pctldev->p);
+ }
+
+ kref_get(&pctldev->p->users);
+ pctldev->hog_default =
+ pinctrl_lookup_state(pctldev->p, PINCTRL_STATE_DEFAULT);
+ if (IS_ERR(pctldev->hog_default)) {
+ dev_dbg(pctldev->dev,
+ "failed to lookup the default state\n");
+ } else {
+ if (pinctrl_select_state(pctldev->p,
+ pctldev->hog_default))
+ dev_err(pctldev->dev,
+ "failed to select default state\n");
+ }
+
+ pctldev->hog_sleep =
+ pinctrl_lookup_state(pctldev->p,
+ PINCTRL_STATE_SLEEP);
+ if (IS_ERR(pctldev->hog_sleep))
+ dev_dbg(pctldev->dev,
+ "failed to lookup the sleep state\n");
+
+ return 0;
+}
+
+int pinctrl_enable(struct pinctrl_dev *pctldev)
+{
+ int error;
+
+ error = pinctrl_claim_hogs(pctldev);
+ if (error) {
+ dev_err(pctldev->dev, "could not claim hogs: %i\n",
+ error);
+ mutex_destroy(&pctldev->mutex);
+ kfree(pctldev);
+
+ return error;
}
mutex_lock(&pinctrldev_list_mutex);
return 0;
}
+EXPORT_SYMBOL_GPL(pinctrl_enable);
/**
* pinctrl_register() - register a pin controller device
if (IS_ERR(pctldev))
return pctldev;
- error = pinctrl_create_and_start(pctldev);
- if (error) {
- mutex_destroy(&pctldev->mutex);
- kfree(pctldev);
-
+ error = pinctrl_enable(pctldev);
+ if (error)
return ERR_PTR(error);
- }
return pctldev;
}
EXPORT_SYMBOL_GPL(pinctrl_register);
+/**
+ * pinctrl_register_and_init() - register and init pin controller device
+ * @pctldesc: descriptor for this pin controller
+ * @dev: parent device for this pin controller
+ * @driver_data: private pin controller data for this pin controller
+ * @pctldev: pin controller device
+ *
+ * Note that pinctrl_enable() still needs to be manually called after
+ * this once the driver is ready.
+ */
int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data,
struct pinctrl_dev **pctldev)
{
struct pinctrl_dev *p;
- int error;
p = pinctrl_init_controller(pctldesc, dev, driver_data);
if (IS_ERR(p))
*/
*pctldev = p;
- error = pinctrl_create_and_start(p);
- if (error) {
- mutex_destroy(&p->mutex);
- kfree(p);
- *pctldev = NULL;
-
- return error;
- }
-
return 0;
}
EXPORT_SYMBOL_GPL(pinctrl_register_and_init);
dev_info(&pdev->dev, "initialized IMX pinctrl driver\n");
- return 0;
+ return pinctrl_enable(ipctl->pctl);
free:
imx_free_resources(ipctl);
dev_info(pcs->dev, "%i pins at pa %p size %u\n",
pcs->desc.npins, pcs->base, pcs->size);
- return 0;
+ return pinctrl_enable(pcs->pctl);
free:
pcs_free_resources(pcs);
pmx->pctl_desc.pins = pmx->pins;
pmx->pctl_desc.npins = pfc->info->nr_pins;
- return devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
- &pmx->pctl);
+ ret = devm_pinctrl_register_and_init(pfc->dev, &pmx->pctl_desc, pmx,
+ &pmx->pctl);
+ if (ret) {
+ dev_err(pfc->dev, "could not register: %i\n", ret);
+
+ return ret;
+ }
+
+ return pinctrl_enable(pmx->pctl);
}
platform_set_drvdata(pdev, iod);
+ return pinctrl_enable(iod->pctl);
+
exit_out:
of_node_put(np);
return ret;
rc = -EIO;
goto out;
}
+ if (prepcblk->ccp_rscode != 0) {
+ DEBUG_WARN(
+ "pkey_sec2protkey unwrap secure key warning, card response %d/%d\n",
+ (int) prepcblk->ccp_rtcode,
+ (int) prepcblk->ccp_rscode);
+ }
/* process response cprb param block */
prepcblk->rpl_parmb = ((u8 *) prepcblk) + sizeof(struct CPRBX);
}
/*
- * Fetch just the mkvp value via query_crypto_facility from adapter.
+ * Fetch the current and old mkvp values via
+ * query_crypto_facility from adapter.
*/
-static int fetch_mkvp(u16 cardnr, u16 domain, u64 *mkvp)
+static int fetch_mkvp(u16 cardnr, u16 domain, u64 mkvp[2])
{
int rc, found = 0;
size_t rlen, vlen;
rc = query_crypto_facility(cardnr, domain, "STATICSA",
rarray, &rlen, varray, &vlen);
if (rc == 0 && rlen > 8*8 && vlen > 184+8) {
- if (rarray[64] == '2') {
+ if (rarray[8*8] == '2') {
/* current master key state is valid */
- *mkvp = *((u64 *)(varray + 184));
+ mkvp[0] = *((u64 *)(varray + 184));
+ mkvp[1] = *((u64 *)(varray + 172));
found = 1;
}
}
struct list_head list;
u16 cardnr;
u16 domain;
- u64 mkvp;
+ u64 mkvp[2];
};
/* a list with mkvp_info entries */
static LIST_HEAD(mkvp_list);
static DEFINE_SPINLOCK(mkvp_list_lock);
-static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 *mkvp)
+static int mkvp_cache_fetch(u16 cardnr, u16 domain, u64 mkvp[2])
{
int rc = -ENOENT;
struct mkvp_info *ptr;
list_for_each_entry(ptr, &mkvp_list, list) {
if (ptr->cardnr == cardnr &&
ptr->domain == domain) {
- *mkvp = ptr->mkvp;
+ memcpy(mkvp, ptr->mkvp, 2 * sizeof(u64));
rc = 0;
break;
}
return rc;
}
-static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp)
+static void mkvp_cache_update(u16 cardnr, u16 domain, u64 mkvp[2])
{
int found = 0;
struct mkvp_info *ptr;
list_for_each_entry(ptr, &mkvp_list, list) {
if (ptr->cardnr == cardnr &&
ptr->domain == domain) {
- ptr->mkvp = mkvp;
+ memcpy(ptr->mkvp, mkvp, 2 * sizeof(u64));
found = 1;
break;
}
}
ptr->cardnr = cardnr;
ptr->domain = domain;
- ptr->mkvp = mkvp;
+ memcpy(ptr->mkvp, mkvp, 2 * sizeof(u64));
list_add(&ptr->list, &mkvp_list);
}
spin_unlock_bh(&mkvp_list_lock);
struct secaeskeytoken *t = (struct secaeskeytoken *) seckey;
struct zcrypt_device_matrix *device_matrix;
u16 card, dom;
- u64 mkvp;
- int i, rc;
+ u64 mkvp[2];
+ int i, rc, oi = -1;
/* mkvp must not be zero */
if (t->mkvp == 0)
device_matrix->device[i].functions & 0x04) {
/* an enabled CCA Coprocessor card */
/* try cached mkvp */
- if (mkvp_cache_fetch(card, dom, &mkvp) == 0 &&
- t->mkvp == mkvp) {
+ if (mkvp_cache_fetch(card, dom, mkvp) == 0 &&
+ t->mkvp == mkvp[0]) {
if (!verify)
break;
/* verify: fetch mkvp from adapter */
- if (fetch_mkvp(card, dom, &mkvp) == 0) {
+ if (fetch_mkvp(card, dom, mkvp) == 0) {
mkvp_cache_update(card, dom, mkvp);
- if (t->mkvp == mkvp)
+ if (t->mkvp == mkvp[0])
break;
}
}
card = AP_QID_CARD(device_matrix->device[i].qid);
dom = AP_QID_QUEUE(device_matrix->device[i].qid);
/* fresh fetch mkvp from adapter */
- if (fetch_mkvp(card, dom, &mkvp) == 0) {
+ if (fetch_mkvp(card, dom, mkvp) == 0) {
mkvp_cache_update(card, dom, mkvp);
- if (t->mkvp == mkvp)
+ if (t->mkvp == mkvp[0])
break;
+ if (t->mkvp == mkvp[1] && oi < 0)
+ oi = i;
}
}
+ if (i >= MAX_ZDEV_ENTRIES && oi >= 0) {
+ /* old mkvp matched, use this card then */
+ card = AP_QID_CARD(device_matrix->device[oi].qid);
+ dom = AP_QID_QUEUE(device_matrix->device[oi].qid);
+ }
}
- if (i < MAX_ZDEV_ENTRIES) {
+ if (i < MAX_ZDEV_ENTRIES || oi >= 0) {
if (pcardnr)
*pcardnr = card;
if (pdomain)
int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
-int qeth_get_elements_no(struct qeth_card *, struct sk_buff *, int);
+int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
+ int extra_elems, int data_offset);
int qeth_get_elements_for_frags(struct sk_buff *);
int qeth_do_send_packet_fast(struct qeth_card *, struct qeth_qdio_out_q *,
struct sk_buff *, struct qeth_hdr *, int, int, int);
* @card: qeth card structure, to check max. elems.
* @skb: SKB address
* @extra_elems: extra elems needed, to check against max.
+ * @data_offset: range starts at skb->data + data_offset
*
* Returns the number of pages, and thus QDIO buffer elements, needed to cover
* skb data, including linear part and fragments. Checks if the result plus
* Note: extra_elems is not included in the returned result.
*/
int qeth_get_elements_no(struct qeth_card *card,
- struct sk_buff *skb, int extra_elems)
+ struct sk_buff *skb, int extra_elems, int data_offset)
{
int elements = qeth_get_elements_for_range(
- (addr_t)skb->data,
+ (addr_t)skb->data + data_offset,
(addr_t)skb->data + skb_headlen(skb)) +
qeth_get_elements_for_frags(skb);
* chaining we can not send long frag lists
*/
if ((card->info.type != QETH_CARD_TYPE_IQD) &&
- !qeth_get_elements_no(card, new_skb, 0)) {
+ !qeth_get_elements_no(card, new_skb, 0, 0)) {
int lin_rc = skb_linearize(new_skb);
if (card->options.performance_stats) {
}
}
- elements = qeth_get_elements_no(card, new_skb, elements_needed);
+ elements = qeth_get_elements_no(card, new_skb, elements_needed,
+ (data_offset > 0) ? data_offset : 0);
if (!elements) {
if (data_offset >= 0)
kmem_cache_free(qeth_core_header_cache, hdr);
char daddr[16];
struct af_iucv_trans_hdr *iucv_hdr;
- skb_pull(skb, 14);
- card->dev->header_ops->create(skb, card->dev, 0,
- card->dev->dev_addr, card->dev->dev_addr,
- card->dev->addr_len);
- skb_pull(skb, 14);
- iucv_hdr = (struct af_iucv_trans_hdr *)skb->data;
memset(hdr, 0, sizeof(struct qeth_hdr));
hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
hdr->hdr.l3.ext_flags = 0;
- hdr->hdr.l3.length = skb->len;
+ hdr->hdr.l3.length = skb->len - ETH_HLEN;
hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
+
+ iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
memset(daddr, 0, sizeof(daddr));
daddr[0] = 0xfe;
daddr[1] = 0x80;
if ((card->info.type == QETH_CARD_TYPE_IQD) &&
!skb_is_nonlinear(skb)) {
new_skb = skb;
- if (new_skb->protocol == ETH_P_AF_IUCV)
- data_offset = 0;
- else
- data_offset = ETH_HLEN;
+ data_offset = ETH_HLEN;
hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
if (!hdr)
goto tx_drop;
*/
if ((card->info.type != QETH_CARD_TYPE_IQD) &&
((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
- (!use_tso && !qeth_get_elements_no(card, new_skb, 0)))) {
+ (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
int lin_rc = skb_linearize(new_skb);
if (card->options.performance_stats) {
elements = use_tso ?
qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
- qeth_get_elements_no(card, new_skb, hdr_elements);
+ qeth_get_elements_no(card, new_skb, hdr_elements,
+ (data_offset > 0) ? data_offset : 0);
if (!elements) {
if (data_offset >= 0)
kmem_cache_free(qeth_core_header_cache, hdr);
scsi_starved_list_run(sdev->host);
if (q->mq_ops)
- blk_mq_start_stopped_hw_queues(q, false);
+ blk_mq_run_hw_queues(q, false);
else
blk_run_queue(q);
}
!list_empty(&sdev->host->starved_list))
kblockd_schedule_work(&sdev->requeue_work);
else
- blk_mq_start_stopped_hw_queues(q, true);
+ blk_mq_run_hw_queues(q, true);
} else {
unsigned long flags;
case BLK_MQ_RQ_QUEUE_BUSY:
if (atomic_read(&sdev->device_busy) == 0 &&
!scsi_device_blocked(sdev))
- blk_mq_delay_queue(hctx, SCSI_QUEUE_DELAY);
+ blk_mq_delay_run_hw_queue(hctx, SCSI_QUEUE_DELAY);
break;
case BLK_MQ_RQ_QUEUE_ERROR:
/*
ret = PTR_ERR(vmfile);
goto out;
}
+ vmfile->f_mode |= FMODE_LSEEK;
asma->file = vmfile;
}
get_file(asma->file);
return xenbus_command_reply(u, XS_ERROR, "ENOENT");
rc = xenbus_dev_request_and_reply(&u->u.msg, u);
- if (rc)
+ if (rc && trans) {
+ list_del(&trans->list);
kfree(trans);
+ }
out:
return rc;
return rc;
}
+ssize_t cifs_file_copychunk_range(unsigned int xid,
+ struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags)
+{
+ struct inode *src_inode = file_inode(src_file);
+ struct inode *target_inode = file_inode(dst_file);
+ struct cifsFileInfo *smb_file_src;
+ struct cifsFileInfo *smb_file_target;
+ struct cifs_tcon *src_tcon;
+ struct cifs_tcon *target_tcon;
+ ssize_t rc;
+
+ cifs_dbg(FYI, "copychunk range\n");
+
+ if (src_inode == target_inode) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ if (!src_file->private_data || !dst_file->private_data) {
+ rc = -EBADF;
+ cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+ goto out;
+ }
+
+ rc = -EXDEV;
+ smb_file_target = dst_file->private_data;
+ smb_file_src = src_file->private_data;
+ src_tcon = tlink_tcon(smb_file_src->tlink);
+ target_tcon = tlink_tcon(smb_file_target->tlink);
+
+ if (src_tcon->ses != target_tcon->ses) {
+ cifs_dbg(VFS, "source and target of copy not on same server\n");
+ goto out;
+ }
+
+ /*
+ * Note: cifs case is easier than btrfs since server responsible for
+ * checks for proper open modes and file type and if it wants
+ * server could even support copy of range where source = target
+ */
+ lock_two_nondirectories(target_inode, src_inode);
+
+ cifs_dbg(FYI, "about to flush pages\n");
+ /* should we flush first and last page first */
+ truncate_inode_pages(&target_inode->i_data, 0);
+
+ if (target_tcon->ses->server->ops->copychunk_range)
+ rc = target_tcon->ses->server->ops->copychunk_range(xid,
+ smb_file_src, smb_file_target, off, len, destoff);
+ else
+ rc = -EOPNOTSUPP;
+
+ /* force revalidate of size and timestamps of target file now
+ * that target is updated on the server
+ */
+ CIFS_I(target_inode)->time = 0;
+ /* although unlocking in the reverse order from locking is not
+ * strictly necessary here it is a little cleaner to be consistent
+ */
+ unlock_two_nondirectories(src_inode, target_inode);
+
+out:
+ return rc;
+}
+
+static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags)
+{
+ unsigned int xid = get_xid();
+ ssize_t rc;
+
+ rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff,
+ len, flags);
+ free_xid(xid);
+ return rc;
+}
+
const struct file_operations cifs_file_ops = {
.read_iter = cifs_loose_read_iter,
.write_iter = cifs_file_write_iter,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.splice_read = generic_file_splice_read,
.llseek = cifs_llseek,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.setlease = cifs_setlease,
.fallocate = cifs_fallocate,
.mmap = cifs_file_mmap,
.splice_read = generic_file_splice_read,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = cifs_llseek,
.setlease = cifs_setlease,
.release = cifs_closedir,
.read = generic_read_dir,
.unlocked_ioctl = cifs_ioctl,
+ .copy_file_range = cifs_copy_file_range,
.clone_file_range = cifs_clone_file_range,
.llseek = generic_file_llseek,
};
# define cifs_listxattr NULL
#endif
+extern ssize_t cifs_file_copychunk_range(unsigned int xid,
+ struct file *src_file, loff_t off,
+ struct file *dst_file, loff_t destoff,
+ size_t len, unsigned int flags);
+
extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
#ifdef CONFIG_CIFS_NFSD_EXPORT
extern const struct export_operations cifs_export_ops;
/* verify the message */
int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+ int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
void (*downgrade_oplock)(struct TCP_Server_Info *,
struct cifsInodeInfo *, bool);
/* process transaction2 response */
char * (*create_lease_buf)(u8 *, u8);
/* parse lease context buffer and return oplock/epoch info */
__u8 (*parse_lease_buf)(void *, unsigned int *);
- int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file,
- struct cifsFileInfo *target_file, u64 src_off, u64 len,
- u64 dest_off);
+ ssize_t (*copychunk_range)(const unsigned int,
+ struct cifsFileInfo *src_file,
+ struct cifsFileInfo *target_file,
+ u64 src_off, u64 len, u64 dest_off);
int (*duplicate_extents)(const unsigned int, struct cifsFileInfo *src,
struct cifsFileInfo *target_file, u64 src_off, u64 len,
u64 dest_off);
void *callback_data; /* general purpose pointer for callback */
void *resp_buf; /* pointer to received SMB header */
int mid_state; /* wish this were enum but can not pass to wait_event */
+ unsigned int mid_flags;
__le16 command; /* smb command code */
bool large_buf:1; /* if valid response, is pointer to large buf */
bool multiRsp:1; /* multiple trans2 responses for one request */
bool decrypted:1; /* decrypted entry */
};
+struct close_cancelled_open {
+ struct cifs_fid fid;
+ struct cifs_tcon *tcon;
+ struct work_struct work;
+};
+
/* Make code in transport.c a little cleaner by moving
update of optional stats into function below */
#ifdef CONFIG_CIFS_STATS2
#define MID_RESPONSE_MALFORMED 0x10
#define MID_SHUTDOWN 0x20
+/* Flags */
+#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */
+
/* Types of response buffer returned from SendReceive2 */
#define CIFS_NO_BUFFER 0 /* Response buffer not returned */
#define CIFS_SMALL_BUFFER 1
extern void cifs_wake_up_task(struct mid_q_entry *mid);
extern int cifs_handle_standard(struct TCP_Server_Info *server,
struct mid_q_entry *mid);
-extern int cifs_discard_remaining_data(struct TCP_Server_Info *server);
+extern int cifs_discard_remaining_data(struct TCP_Server_Info *server,
+ char *buf);
extern int cifs_call_async(struct TCP_Server_Info *server,
struct smb_rqst *rqst,
mid_receive_t *receive, mid_callback_t *callback,
* current bigbuf.
*/
int
-cifs_discard_remaining_data(struct TCP_Server_Info *server)
+cifs_discard_remaining_data(struct TCP_Server_Info *server, char *buf)
{
- unsigned int rfclen = get_rfc1002_length(server->smallbuf);
+ unsigned int rfclen = get_rfc1002_length(buf);
int remaining = rfclen + 4 - server->total_read;
while (remaining > 0) {
int length;
struct cifs_readdata *rdata = mid->callback_data;
- length = cifs_discard_remaining_data(server);
+ length = cifs_discard_remaining_data(server, mid->resp_buf);
dequeue_mid(mid, rdata->result);
return length;
}
if (server->ops->is_status_pending &&
server->ops->is_status_pending(buf, server, 0)) {
- cifs_discard_remaining_data(server);
+ cifs_discard_remaining_data(server, buf);
return -1;
}
cifs_dbg(FYI, "0: iov_base=%p iov_len=%u\n",
rdata->iov[0].iov_base, server->total_read);
+ mid->resp_buf = server->smallbuf;
+ server->smallbuf = NULL;
+
/* how much data is in the response? */
data_len = server->ops->read_data_length(buf);
if (data_offset + data_len > buflen) {
server->lstrp = jiffies;
if (mid_entry != NULL) {
+ if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
+ mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
+ server->ops->handle_cancelled_mid)
+ server->ops->handle_cancelled_mid(
+ mid_entry->resp_buf,
+ server);
+
if (!mid_entry->multiRsp || mid_entry->multiEnd)
mid_entry->callback(mid_entry);
- } else if (!server->ops->is_oplock_break ||
- !server->ops->is_oplock_break(buf, server)) {
+ } else if (server->ops->is_oplock_break &&
+ server->ops->is_oplock_break(buf, server)) {
+ cifs_dbg(FYI, "Received oplock break\n");
+ } else {
cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
atomic_read(&midCount));
cifs_dump_mem("Received Data is: ", buf,
#include "cifs_ioctl.h"
#include <linux/btrfs.h>
-static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
- struct file *dst_file)
-{
- struct inode *src_inode = file_inode(src_file);
- struct inode *target_inode = file_inode(dst_file);
- struct cifsFileInfo *smb_file_src;
- struct cifsFileInfo *smb_file_target;
- struct cifs_tcon *src_tcon;
- struct cifs_tcon *target_tcon;
- int rc;
-
- cifs_dbg(FYI, "ioctl clone range\n");
-
- if (!src_file->private_data || !dst_file->private_data) {
- rc = -EBADF;
- cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
- goto out;
- }
-
- rc = -EXDEV;
- smb_file_target = dst_file->private_data;
- smb_file_src = src_file->private_data;
- src_tcon = tlink_tcon(smb_file_src->tlink);
- target_tcon = tlink_tcon(smb_file_target->tlink);
-
- if (src_tcon->ses != target_tcon->ses) {
- cifs_dbg(VFS, "source and target of copy not on same server\n");
- goto out;
- }
-
- /*
- * Note: cifs case is easier than btrfs since server responsible for
- * checks for proper open modes and file type and if it wants
- * server could even support copy of range where source = target
- */
- lock_two_nondirectories(target_inode, src_inode);
-
- cifs_dbg(FYI, "about to flush pages\n");
- /* should we flush first and last page first */
- truncate_inode_pages(&target_inode->i_data, 0);
-
- if (target_tcon->ses->server->ops->clone_range)
- rc = target_tcon->ses->server->ops->clone_range(xid,
- smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
- else
- rc = -EOPNOTSUPP;
-
- /* force revalidate of size and timestamps of target file now
- that target is updated on the server */
- CIFS_I(target_inode)->time = 0;
- /* although unlocking in the reverse order from locking is not
- strictly necessary here it is a little cleaner to be consistent */
- unlock_two_nondirectories(src_inode, target_inode);
-out:
- return rc;
-}
-
-static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
+static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
unsigned long srcfd)
{
int rc;
struct fd src_file;
struct inode *src_inode;
- cifs_dbg(FYI, "ioctl clone range\n");
+ cifs_dbg(FYI, "ioctl copychunk range\n");
/* the destination must be opened for writing */
if (!(dst_file->f_mode & FMODE_WRITE)) {
cifs_dbg(FYI, "file target not open for write\n");
if (S_ISDIR(src_inode->i_mode))
goto out_fput;
- rc = cifs_file_clone_range(xid, src_file.file, dst_file);
+ rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0,
+ src_inode->i_size, 0);
out_fput:
fdput(src_file);
}
break;
case CIFS_IOC_COPYCHUNK_FILE:
- rc = cifs_ioctl_clone(xid, filep, arg);
+ rc = cifs_ioctl_copychunk(xid, filep, arg);
break;
case CIFS_IOC_SET_INTEGRITY:
if (pSMBFile == NULL)
cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
return false;
}
+
+void
+smb2_cancelled_close_fid(struct work_struct *work)
+{
+ struct close_cancelled_open *cancelled = container_of(work,
+ struct close_cancelled_open, work);
+
+ cifs_dbg(VFS, "Close unmatched open\n");
+
+ SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
+ cancelled->fid.volatile_fid);
+ cifs_put_tcon(cancelled->tcon);
+ kfree(cancelled);
+}
+
+int
+smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+{
+ struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer);
+ struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+ struct cifs_tcon *tcon;
+ struct close_cancelled_open *cancelled;
+
+ if (sync_hdr->Command != SMB2_CREATE ||
+ sync_hdr->Status != STATUS_SUCCESS)
+ return 0;
+
+ cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+ if (!cancelled)
+ return -ENOMEM;
+
+ tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
+ sync_hdr->TreeId);
+ if (!tcon) {
+ kfree(cancelled);
+ return -ENOENT;
+ }
+
+ cancelled->fid.persistent_fid = rsp->PersistentFileId;
+ cancelled->fid.volatile_fid = rsp->VolatileFileId;
+ cancelled->tcon = tcon;
+ INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+ queue_work(cifsiod_wq, &cancelled->work);
+
+ return 0;
+}
#include <linux/vfs.h>
#include <linux/falloc.h>
#include <linux/scatterlist.h>
+#include <linux/uuid.h>
#include <crypto/aead.h>
#include "cifsglob.h"
#include "smb2pdu.h"
return rc;
}
-static int
-smb2_clone_range(const unsigned int xid,
+static ssize_t
+smb2_copychunk_range(const unsigned int xid,
struct cifsFileInfo *srcfile,
struct cifsFileInfo *trgtfile, u64 src_off,
u64 len, u64 dest_off)
struct cifs_tcon *tcon;
int chunks_copied = 0;
bool chunk_sizes_updated = false;
+ ssize_t bytes_written, total_bytes_written = 0;
pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
if (pcchunk == NULL)
return -ENOMEM;
- cifs_dbg(FYI, "in smb2_clone_range - about to call request res key\n");
+ cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n");
/* Request a key from the server to identify the source of the copy */
rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink),
srcfile->fid.persistent_fid,
}
chunks_copied++;
- src_off += le32_to_cpu(retbuf->TotalBytesWritten);
- dest_off += le32_to_cpu(retbuf->TotalBytesWritten);
- len -= le32_to_cpu(retbuf->TotalBytesWritten);
+ bytes_written = le32_to_cpu(retbuf->TotalBytesWritten);
+ src_off += bytes_written;
+ dest_off += bytes_written;
+ len -= bytes_written;
+ total_bytes_written += bytes_written;
- cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n",
+ cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n",
le32_to_cpu(retbuf->ChunksWritten),
le32_to_cpu(retbuf->ChunkBytesWritten),
- le32_to_cpu(retbuf->TotalBytesWritten));
+ bytes_written);
} else if (rc == -EINVAL) {
if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
goto cchunk_out;
cchunk_out:
kfree(pcchunk);
kfree(retbuf);
- return rc;
+ if (rc)
+ return rc;
+ else
+ return total_bytes_written;
}
static int
if (rc)
goto free_pages;
- rc = cifs_discard_remaining_data(server);
+ rc = cifs_discard_remaining_data(server, buf);
if (rc)
goto free_pages;
kfree(pages);
return rc;
discard_data:
- cifs_discard_remaining_data(server);
+ cifs_discard_remaining_data(server, buf);
goto free_pages;
}
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb2_set_oplock_level,
.create_lease_buf = smb2_create_lease_buf,
.parse_lease_buf = smb2_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.get_dfs_refer = smb2_get_dfs_refer,
.clear_stats = smb2_clear_stats,
.print_stats = smb2_print_stats,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb21_set_oplock_level,
.create_lease_buf = smb2_create_lease_buf,
.parse_lease_buf = smb2_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.wp_retry_size = smb2_wp_retry_size,
.dir_needs_close = smb2_dir_needs_close,
.enum_snapshots = smb3_enum_snapshots,
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb3_set_oplock_level,
.create_lease_buf = smb3_create_lease_buf,
.parse_lease_buf = smb3_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.duplicate_extents = smb2_duplicate_extents,
.validate_negotiate = smb3_validate_negotiate,
.wp_retry_size = smb2_wp_retry_size,
.print_stats = smb2_print_stats,
.dump_share_caps = smb2_dump_share_caps,
.is_oplock_break = smb2_is_valid_oplock_break,
+ .handle_cancelled_mid = smb2_handle_cancelled_mid,
.downgrade_oplock = smb2_downgrade_oplock,
.need_neg = smb2_need_neg,
.negotiate = smb2_negotiate,
.set_oplock_level = smb3_set_oplock_level,
.create_lease_buf = smb3_create_lease_buf,
.parse_lease_buf = smb3_parse_lease_buf,
- .clone_range = smb2_clone_range,
+ .copychunk_range = smb2_copychunk_range,
.duplicate_extents = smb2_duplicate_extents,
/* .validate_negotiate = smb3_validate_negotiate, */ /* not used in 3.11 */
.wp_retry_size = smb2_wp_retry_size,
return -EINVAL;
}
+ /* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+ if (tcon)
+ tcon->tid = 0;
+
rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
if (rc) {
kfree(unc_path);
struct smb_rqst *rqst);
extern struct mid_q_entry *smb2_setup_async_request(
struct TCP_Server_Info *server, struct smb_rqst *rqst);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+ __u64 ses_id);
+extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
+ __u64 ses_id, __u32 tid);
extern int smb2_calc_signature(struct smb_rqst *rqst,
struct TCP_Server_Info *server);
extern int smb3_calc_signature(struct smb_rqst *rqst,
extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
const u64 persistent_fid, const u64 volatile_fid,
const __u8 oplock_level);
+extern int smb2_handle_cancelled_mid(char *buffer,
+ struct TCP_Server_Info *server);
+void smb2_cancelled_close_fid(struct work_struct *work);
extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id,
struct kstatfs *FSData);
return 0;
}
-struct cifs_ses *
-smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+static struct cifs_ses *
+smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
{
struct cifs_ses *ses;
- spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
if (ses->Suid != ses_id)
continue;
- spin_unlock(&cifs_tcp_ses_lock);
return ses;
}
+
+ return NULL;
+}
+
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+{
+ struct cifs_ses *ses;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
spin_unlock(&cifs_tcp_ses_lock);
+ return ses;
+}
+
+static struct cifs_tcon *
+smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32 tid)
+{
+ struct cifs_tcon *tcon;
+
+ list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+ if (tcon->tid != tid)
+ continue;
+ ++tcon->tc_count;
+ return tcon;
+ }
+
return NULL;
}
+/*
+ * Obtain tcon corresponding to the tid in the given
+ * cifs_ses
+ */
+
+struct cifs_tcon *
+smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid)
+{
+ struct cifs_ses *ses;
+ struct cifs_tcon *tcon;
+
+ spin_lock(&cifs_tcp_ses_lock);
+ ses = smb2_find_smb_ses_unlocked(server, ses_id);
+ if (!ses) {
+ spin_unlock(&cifs_tcp_ses_lock);
+ return NULL;
+ }
+ tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
+ spin_unlock(&cifs_tcp_ses_lock);
+
+ return tcon;
+}
+
int
smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
{
rc = wait_for_response(ses->server, midQ);
if (rc != 0) {
+ cifs_dbg(FYI, "Cancelling wait for mid %llu\n", midQ->mid);
send_cancel(ses->server, rqst, midQ);
spin_lock(&GlobalMid_Lock);
if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
+ midQ->mid_flags |= MID_WAIT_CANCELLED;
midQ->callback = DeleteMidQEntry;
spin_unlock(&GlobalMid_Lock);
add_credits(ses->server, 1, optype);
}
spin_lock_irq(&mapping->tree_lock);
+ if (!entry) {
+ /*
+ * We needed to drop the page_tree lock while calling
+ * radix_tree_preload() and we didn't have an entry to
+ * lock. See if another thread inserted an entry at
+ * our index during this time.
+ */
+ entry = __radix_tree_lookup(&mapping->page_tree, index,
+ NULL, &slot);
+ if (entry) {
+ radix_tree_preload_end();
+ spin_unlock_irq(&mapping->tree_lock);
+ goto restart;
+ }
+ }
+
if (pmd_downgrade) {
radix_tree_delete(&mapping->page_tree, index);
mapping->nrexceptional--;
if (err) {
spin_unlock_irq(&mapping->tree_lock);
/*
- * Someone already created the entry? This is a
- * normal failure when inserting PMDs in a range
- * that already contains PTEs. In that case we want
- * to return -EEXIST immediately.
- */
- if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD))
- goto restart;
- /*
- * Our insertion of a DAX PMD entry failed, most
- * likely because it collided with a PTE sized entry
- * at a different index in the PMD range. We haven't
- * inserted anything into the radix tree and have no
- * waiters to wake.
+ * Our insertion of a DAX entry failed, most likely
+ * because we were inserting a PMD entry and it
+ * collided with a PTE sized entry at a different
+ * index in the PMD range. We haven't inserted
+ * anything into the radix tree and have no waiters to
+ * wake.
*/
return ERR_PTR(err);
}
extern int ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern void ext4_evict_inode(struct inode *);
extern void ext4_clear_inode(struct inode *);
+extern int ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
- .getattr = ext4_getattr,
+ .getattr = ext4_file_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
int ext4_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- struct inode *inode;
- unsigned long long delalloc_blocks;
+ struct inode *inode = d_inode(path->dentry);
+ struct ext4_inode *raw_inode;
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ unsigned int flags;
+
+ if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = ei->i_crtime.tv_sec;
+ stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
+ }
+
+ flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+ if (flags & EXT4_APPEND_FL)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (flags & EXT4_COMPR_FL)
+ stat->attributes |= STATX_ATTR_COMPRESSED;
+ if (flags & EXT4_ENCRYPT_FL)
+ stat->attributes |= STATX_ATTR_ENCRYPTED;
+ if (flags & EXT4_IMMUTABLE_FL)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (flags & EXT4_NODUMP_FL)
+ stat->attributes |= STATX_ATTR_NODUMP;
+
+ stat->attributes_mask |= (STATX_ATTR_APPEND |
+ STATX_ATTR_COMPRESSED |
+ STATX_ATTR_ENCRYPTED |
+ STATX_ATTR_IMMUTABLE |
+ STATX_ATTR_NODUMP);
- inode = d_inode(path->dentry);
generic_fillattr(inode, stat);
+ return 0;
+}
+
+int ext4_file_getattr(const struct path *path, struct kstat *stat,
+ u32 request_mask, unsigned int query_flags)
+{
+ struct inode *inode = d_inode(path->dentry);
+ u64 delalloc_blocks;
+
+ ext4_getattr(path, stat, request_mask, query_flags);
/*
* If there is inline data in the inode, the inode will normally not
.tmpfile = ext4_tmpfile,
.rename = ext4_rename2,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
const struct inode_operations ext4_special_inode_operations = {
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
const struct inode_operations ext4_encrypted_symlink_inode_operations = {
.get_link = ext4_encrypted_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
const struct inode_operations ext4_symlink_inode_operations = {
.get_link = page_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
const struct inode_operations ext4_fast_symlink_inode_operations = {
.get_link = simple_get_link,
.setattr = ext4_setattr,
+ .getattr = ext4_getattr,
.listxattr = ext4_listxattr,
};
if (!new_op)
return -ENOMEM;
new_op->upcall.req.features.features = 0;
- ret = service_operation(new_op, "orangefs_features", 0);
- orangefs_features = new_op->downcall.resp.features.features;
+ ret = service_operation(new_op, "orangefs_features",
+ ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX);
+ if (!ret)
+ orangefs_features =
+ new_op->downcall.resp.features.features;
+ else
+ orangefs_features = 0;
op_release(new_op);
} else {
orangefs_features = 0;
if ((table->proc_handler == proc_dostring) ||
(table->proc_handler == proc_dointvec) ||
+ (table->proc_handler == proc_douintvec) ||
(table->proc_handler == proc_dointvec_minmax) ||
(table->proc_handler == proc_dointvec_jiffies) ||
(table->proc_handler == proc_dointvec_userhz_jiffies) ||
int vfs_statx_fd(unsigned int fd, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- struct fd f = fdget_raw(fd);
+ struct fd f;
int error = -EBADF;
+ if (query_flags & ~KSTAT_QUERY_FLAGS)
+ return -EINVAL;
+
+ f = fdget_raw(fd);
if (f.file) {
error = vfs_getattr(&f.file->f_path, stat,
request_mask, query_flags);
* Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
* at the given name from being referenced.
*
- * The caller must have preset stat->request_mask as for vfs_getattr(). The
- * flags are also used to load up stat->query_flags.
- *
* 0 will be returned on success, and a -ve error code if unsuccessful.
*/
int vfs_statx(int dfd, const char __user *filename, int flags,
}
#endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
-static inline int __put_timestamp(struct timespec *kts,
- struct statx_timestamp __user *uts)
-{
- return (__put_user(kts->tv_sec, &uts->tv_sec ) ||
- __put_user(kts->tv_nsec, &uts->tv_nsec ) ||
- __put_user(0, &uts->__reserved ));
-}
-
-/*
- * Set the statx results.
- */
-static long statx_set_result(struct kstat *stat, struct statx __user *buffer)
+static noinline_for_stack int
+cp_statx(const struct kstat *stat, struct statx __user *buffer)
{
- uid_t uid = from_kuid_munged(current_user_ns(), stat->uid);
- gid_t gid = from_kgid_munged(current_user_ns(), stat->gid);
-
- if (__put_user(stat->result_mask, &buffer->stx_mask ) ||
- __put_user(stat->mode, &buffer->stx_mode ) ||
- __clear_user(&buffer->__spare0, sizeof(buffer->__spare0)) ||
- __put_user(stat->nlink, &buffer->stx_nlink ) ||
- __put_user(uid, &buffer->stx_uid ) ||
- __put_user(gid, &buffer->stx_gid ) ||
- __put_user(stat->attributes, &buffer->stx_attributes ) ||
- __put_user(stat->blksize, &buffer->stx_blksize ) ||
- __put_user(MAJOR(stat->rdev), &buffer->stx_rdev_major ) ||
- __put_user(MINOR(stat->rdev), &buffer->stx_rdev_minor ) ||
- __put_user(MAJOR(stat->dev), &buffer->stx_dev_major ) ||
- __put_user(MINOR(stat->dev), &buffer->stx_dev_minor ) ||
- __put_timestamp(&stat->atime, &buffer->stx_atime ) ||
- __put_timestamp(&stat->btime, &buffer->stx_btime ) ||
- __put_timestamp(&stat->ctime, &buffer->stx_ctime ) ||
- __put_timestamp(&stat->mtime, &buffer->stx_mtime ) ||
- __put_user(stat->ino, &buffer->stx_ino ) ||
- __put_user(stat->size, &buffer->stx_size ) ||
- __put_user(stat->blocks, &buffer->stx_blocks ) ||
- __clear_user(&buffer->__spare1, sizeof(buffer->__spare1)) ||
- __clear_user(&buffer->__spare2, sizeof(buffer->__spare2)))
- return -EFAULT;
-
- return 0;
+ struct statx tmp;
+
+ memset(&tmp, 0, sizeof(tmp));
+
+ tmp.stx_mask = stat->result_mask;
+ tmp.stx_blksize = stat->blksize;
+ tmp.stx_attributes = stat->attributes;
+ tmp.stx_nlink = stat->nlink;
+ tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid);
+ tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid);
+ tmp.stx_mode = stat->mode;
+ tmp.stx_ino = stat->ino;
+ tmp.stx_size = stat->size;
+ tmp.stx_blocks = stat->blocks;
+ tmp.stx_attributes_mask = stat->attributes_mask;
+ tmp.stx_atime.tv_sec = stat->atime.tv_sec;
+ tmp.stx_atime.tv_nsec = stat->atime.tv_nsec;
+ tmp.stx_btime.tv_sec = stat->btime.tv_sec;
+ tmp.stx_btime.tv_nsec = stat->btime.tv_nsec;
+ tmp.stx_ctime.tv_sec = stat->ctime.tv_sec;
+ tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec;
+ tmp.stx_mtime.tv_sec = stat->mtime.tv_sec;
+ tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec;
+ tmp.stx_rdev_major = MAJOR(stat->rdev);
+ tmp.stx_rdev_minor = MINOR(stat->rdev);
+ tmp.stx_dev_major = MAJOR(stat->dev);
+ tmp.stx_dev_minor = MINOR(stat->dev);
+
+ return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
}
/**
struct kstat stat;
int error;
+ if (mask & STATX__RESERVED)
+ return -EINVAL;
if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
return -EINVAL;
- if (!access_ok(VERIFY_WRITE, buffer, sizeof(*buffer)))
- return -EFAULT;
if (filename)
error = vfs_statx(dfd, filename, flags, &stat, mask);
error = vfs_statx_fd(dfd, &stat, mask, flags);
if (error)
return error;
- return statx_set_result(&stat, buffer);
+
+ return cp_statx(&stat, buffer);
}
/* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
{
const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
struct kobject *kobj = of->kn->parent->priv;
- size_t len;
+ ssize_t len;
/*
* If buf != of->prealloc_buf, we don't know how
if (WARN_ON_ONCE(buf != of->prealloc_buf))
return 0;
len = ops->show(kobj, of->kn->priv, buf);
+ if (len < 0)
+ return len;
if (pos) {
if (len <= pos)
return 0;
len -= pos;
memmove(buf, buf + pos, len);
}
- return min(count, len);
+ return min_t(ssize_t, count, len);
}
/* kernfs write callback for regular sysfs files */
* protocols: aa:... bb:...
*/
seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
- pending, total, UFFD_API, UFFD_API_FEATURES,
+ pending, total, UFFD_API, ctx->features,
UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
}
#endif
extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
-extern int xfs_dir2_sf_verify(struct xfs_mount *mp, struct xfs_dir2_sf_hdr *sfp,
- int size);
+extern int xfs_dir2_sf_verify(struct xfs_inode *ip);
/* xfs_dir2_readdir.c */
extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
/* Verify the consistency of an inline directory. */
int
xfs_dir2_sf_verify(
- struct xfs_mount *mp,
- struct xfs_dir2_sf_hdr *sfp,
- int size)
+ struct xfs_inode *ip)
{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_dir2_sf_hdr *sfp;
struct xfs_dir2_sf_entry *sfep;
struct xfs_dir2_sf_entry *next_sfep;
char *endp;
const struct xfs_dir_ops *dops;
+ struct xfs_ifork *ifp;
xfs_ino_t ino;
int i;
int i8count;
int offset;
+ int size;
+ int error;
__uint8_t filetype;
+ ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
+ /*
+ * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops,
+ * so we can only trust the mountpoint to have the right pointer.
+ */
dops = xfs_dir_get_ops(mp, NULL);
+ ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+ sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+ size = ifp->if_bytes;
+
/*
* Give up if the directory is way too short.
*/
- XFS_WANT_CORRUPTED_RETURN(mp, size >
- offsetof(struct xfs_dir2_sf_hdr, parent));
- XFS_WANT_CORRUPTED_RETURN(mp, size >=
- xfs_dir2_sf_hdr_size(sfp->i8count));
+ if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) ||
+ size < xfs_dir2_sf_hdr_size(sfp->i8count))
+ return -EFSCORRUPTED;
endp = (char *)sfp + size;
/* Check .. entry */
ino = dops->sf_get_parent_ino(sfp);
i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
- XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+ error = xfs_dir_ino_validate(mp, ino);
+ if (error)
+ return error;
offset = dops->data_first_offset;
/* Check all reported entries */
* Check the fixed-offset parts of the structure are
* within the data buffer.
*/
- XFS_WANT_CORRUPTED_RETURN(mp,
- ((char *)sfep + sizeof(*sfep)) < endp);
+ if (((char *)sfep + sizeof(*sfep)) >= endp)
+ return -EFSCORRUPTED;
/* Don't allow names with known bad length. */
- XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen > 0);
- XFS_WANT_CORRUPTED_RETURN(mp, sfep->namelen < MAXNAMELEN);
+ if (sfep->namelen == 0)
+ return -EFSCORRUPTED;
/*
* Check that the variable-length part of the structure is
* name component, so nextentry is an acceptable test.
*/
next_sfep = dops->sf_nextentry(sfp, sfep);
- XFS_WANT_CORRUPTED_RETURN(mp, endp >= (char *)next_sfep);
+ if (endp < (char *)next_sfep)
+ return -EFSCORRUPTED;
/* Check that the offsets always increase. */
- XFS_WANT_CORRUPTED_RETURN(mp,
- xfs_dir2_sf_get_offset(sfep) >= offset);
+ if (xfs_dir2_sf_get_offset(sfep) < offset)
+ return -EFSCORRUPTED;
/* Check the inode number. */
ino = dops->sf_get_ino(sfp, sfep);
i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
- XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, ino));
+ error = xfs_dir_ino_validate(mp, ino);
+ if (error)
+ return error;
/* Check the file type. */
filetype = dops->sf_get_ftype(sfep);
- XFS_WANT_CORRUPTED_RETURN(mp, filetype < XFS_DIR3_FT_MAX);
+ if (filetype >= XFS_DIR3_FT_MAX)
+ return -EFSCORRUPTED;
offset = xfs_dir2_sf_get_offset(sfep) +
dops->data_entsize(sfep->namelen);
sfep = next_sfep;
}
- XFS_WANT_CORRUPTED_RETURN(mp, i8count == sfp->i8count);
- XFS_WANT_CORRUPTED_RETURN(mp, (void *)sfep == (void *)endp);
+ if (i8count != sfp->i8count)
+ return -EFSCORRUPTED;
+ if ((void *)sfep != (void *)endp)
+ return -EFSCORRUPTED;
/* Make sure this whole thing ought to be in local format. */
- XFS_WANT_CORRUPTED_RETURN(mp, offset +
- (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
- (uint)sizeof(xfs_dir2_block_tail_t) <= mp->m_dir_geo->blksize);
+ if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
+ (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize)
+ return -EFSCORRUPTED;
return 0;
}
if (error)
return error;
+ /* Check inline dir contents. */
+ if (S_ISDIR(VFS_I(ip)->i_mode) &&
+ dip->di_format == XFS_DINODE_FMT_LOCAL) {
+ error = xfs_dir2_sf_verify(ip);
+ if (error) {
+ xfs_idestroy_fork(ip, XFS_DATA_FORK);
+ return error;
+ }
+ }
+
if (xfs_is_reflink_inode(ip)) {
ASSERT(ip->i_cowfp == NULL);
xfs_ifork_init_cow(ip);
int whichfork,
int size)
{
- int error;
-
/*
* If the size is unreasonable, then something
* is wrong and we just bail out rather than crash in
return -EFSCORRUPTED;
}
- if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
- error = xfs_dir2_sf_verify(ip->i_mount,
- (struct xfs_dir2_sf_hdr *)XFS_DFORK_DPTR(dip),
- size);
- if (error)
- return error;
- }
-
xfs_init_local_fork(ip, whichfork, XFS_DFORK_PTR(dip, whichfork), size);
return 0;
}
* In these cases, the format always takes precedence, because the
* format indicates the current state of the fork.
*/
-int
+void
xfs_iflush_fork(
xfs_inode_t *ip,
xfs_dinode_t *dip,
char *cp;
xfs_ifork_t *ifp;
xfs_mount_t *mp;
- int error;
static const short brootflag[2] =
{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
static const short dataflag[2] =
{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
if (!iip)
- return 0;
+ return;
ifp = XFS_IFORK_PTR(ip, whichfork);
/*
* This can happen if we gave up in iformat in an error path,
*/
if (!ifp) {
ASSERT(whichfork == XFS_ATTR_FORK);
- return 0;
+ return;
}
cp = XFS_DFORK_PTR(dip, whichfork);
mp = ip->i_mount;
switch (XFS_IFORK_FORMAT(ip, whichfork)) {
case XFS_DINODE_FMT_LOCAL:
- if (S_ISDIR(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK) {
- error = xfs_dir2_sf_verify(mp,
- (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data,
- ifp->if_bytes);
- if (error)
- return error;
- }
if ((iip->ili_fields & dataflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(ifp->if_u1.if_data != NULL);
ASSERT(0);
break;
}
- return 0;
}
/*
struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
int xfs_iformat_fork(struct xfs_inode *, struct xfs_dinode *);
-int xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
+void xfs_iflush_fork(struct xfs_inode *, struct xfs_dinode *,
struct xfs_inode_log_item *, int);
void xfs_idestroy_fork(struct xfs_inode *, int);
void xfs_idata_realloc(struct xfs_inode *, int, int);
/*
* Now that we've unmap all full blocks we'll have to zero out any
* partial block at the beginning and/or end. xfs_zero_range is
- * smart enough to skip any holes, including those we just created.
+ * smart enough to skip any holes, including those we just created,
+ * but we must take care not to zero beyond EOF and enlarge i_size.
*/
+
+ if (offset >= XFS_ISIZE(ip))
+ return 0;
+
+ if (offset + len > XFS_ISIZE(ip))
+ len = XFS_ISIZE(ip) - offset;
+
return xfs_zero_range(ip, offset, len, NULL);
}
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"
+#include "xfs_dir2_priv.h"
kmem_zone_t *xfs_inode_zone;
struct xfs_inode_log_item *iip = ip->i_itemp;
struct xfs_dinode *dip;
struct xfs_mount *mp = ip->i_mount;
- int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(xfs_isiflocked(ip));
if (ip->i_d.di_version < 3)
ip->i_d.di_flushiter++;
+ /* Check the inline directory data. */
+ if (S_ISDIR(VFS_I(ip)->i_mode) &&
+ ip->i_d.di_format == XFS_DINODE_FMT_LOCAL &&
+ xfs_dir2_sf_verify(ip))
+ goto corrupt_out;
+
/*
* Copy the dirty parts of the inode into the on-disk inode. We always
* copy out the core of the inode, because if the inode is dirty at all
if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
ip->i_d.di_flushiter = 0;
- error = xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
- if (error)
- return error;
- if (XFS_IFORK_Q(ip)) {
- error = xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
- if (error)
- return error;
- }
+ xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
+ if (XFS_IFORK_Q(ip))
+ xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
xfs_inobp_check(mp, bp);
/*
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
+ if (ip->i_d.di_version == 3) {
+ if (request_mask & STATX_BTIME) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = ip->i_d.di_crtime.t_sec;
+ stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec;
+ }
+ }
+
+ if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+ stat->attributes |= STATX_ATTR_NODUMP;
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
return error;
bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
- buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+ buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
do {
struct xfs_inobt_rec_incore r;
int stat;
*/
#ifndef RO_AFTER_INIT_DATA
#define RO_AFTER_INIT_DATA \
- __start_ro_after_init = .; \
+ VMLINUX_SYMBOL(__start_ro_after_init) = .; \
*(.data..ro_after_init) \
- __end_ro_after_init = .;
+ VMLINUX_SYMBOL(__end_ro_after_init) = .;
#endif
/*
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
int kvm_vgic_map_resources(struct kvm *kvm);
int kvm_vgic_hyp_init(void);
+void kvm_vgic_init_cpu_hardware(void);
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
bool level);
atomic_t nr_active;
+ struct delayed_work delayed_run_work;
struct delayed_work delay_work;
struct hlist_node cpuhp_dead;
void blk_mq_start_hw_queues(struct request_queue *q);
void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
+void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
void blk_mq_run_hw_queues(struct request_queue *q, bool async);
void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */
#define QUEUE_FLAG_DAX 26 /* device supports DAX */
#define QUEUE_FLAG_STATS 27 /* track rq completion times */
-#define QUEUE_FLAG_RESTART 28 /* queue needs restart at completion */
#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_STACKABLE) | \
extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
extern int elevator_init(struct request_queue *, char *);
-extern void elevator_exit(struct elevator_queue *);
+extern void elevator_exit(struct request_queue *, struct elevator_queue *);
extern int elevator_change(struct request_queue *, const char *);
extern bool elv_bio_merge_ok(struct request *, struct bio *);
extern struct elevator_queue *elevator_alloc(struct request_queue *,
#define GICH_MISR_EOI (1 << 0)
#define GICH_MISR_U (1 << 1)
+#define GICV_PMR_PRIORITY_SHIFT 3
+#define GICV_PMR_PRIORITY_MASK (0x1f << GICV_PMR_PRIORITY_SHIFT)
+
#ifndef __ASSEMBLY__
#include <linux/irqdomain.h>
* Max bus-specific overhead incurred by request/responses.
* I2C requires 1 additional byte for requests.
* I2C requires 2 additional bytes for responses.
+ * SPI requires up to 32 additional bytes for responses.
* */
#define EC_PROTO_VERSION_UNKNOWN 0
#define EC_MAX_REQUEST_OVERHEAD 1
-#define EC_MAX_RESPONSE_OVERHEAD 2
+#define EC_MAX_RESPONSE_OVERHEAD 32
/*
* Command interface between EC and AP, for LPC, I2C and SPI interfaces.
* RDMA_QPTYPE field
*/
enum {
- NVMF_RDMA_QPTYPE_CONNECTED = 0, /* Reliable Connected */
- NVMF_RDMA_QPTYPE_DATAGRAM = 1, /* Reliable Datagram */
+ NVMF_RDMA_QPTYPE_CONNECTED = 1, /* Reliable Connected */
+ NVMF_RDMA_QPTYPE_DATAGRAM = 2, /* Reliable Datagram */
};
/* RDMA QP Service Type codes for Discovery Log Page entry TSAS
* RDMA_QPTYPE field
*/
enum {
- NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 0, /* No Provider Specified */
- NVMF_RDMA_PRTYPE_IB = 1, /* InfiniBand */
- NVMF_RDMA_PRTYPE_ROCE = 2, /* InfiniBand RoCE */
- NVMF_RDMA_PRTYPE_ROCEV2 = 3, /* InfiniBand RoCEV2 */
- NVMF_RDMA_PRTYPE_IWARP = 4, /* IWARP */
+ NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 1, /* No Provider Specified */
+ NVMF_RDMA_PRTYPE_IB = 2, /* InfiniBand */
+ NVMF_RDMA_PRTYPE_ROCE = 3, /* InfiniBand RoCE */
+ NVMF_RDMA_PRTYPE_ROCEV2 = 4, /* InfiniBand RoCEV2 */
+ NVMF_RDMA_PRTYPE_IWARP = 5, /* IWARP */
};
/* RDMA Connection Management Service Type codes for Discovery Log Page
* entry TSAS RDMA_CMS field
*/
enum {
- NVMF_RDMA_CMS_RDMA_CM = 0, /* Sockets based enpoint addressing */
+ NVMF_RDMA_CMS_RDMA_CM = 1, /* Sockets based endpoint addressing */
};
#define NVMF_AQ_DEPTH 32
extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data,
struct pinctrl_dev **pctldev);
+extern int pinctrl_enable(struct pinctrl_dev *pctldev);
-/* Please use pinctrl_register_and_init() instead */
+/* Please use pinctrl_register_and_init() and pinctrl_enable() instead */
extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
struct device *dev, void *driver_data);
unsigned int nlink;
uint32_t blksize; /* Preferred I/O size */
u64 attributes;
+ u64 attributes_mask;
#define KSTAT_ATTR_FS_IOC_FLAGS \
(STATX_ATTR_COMPRESSED | \
STATX_ATTR_IMMUTABLE | \
return frag;
}
-static inline void sctp_assoc_pending_pmtu(struct sock *sk, struct sctp_association *asoc)
+static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc)
{
-
- sctp_assoc_sync_pmtu(sk, asoc);
+ sctp_assoc_sync_pmtu(asoc);
asoc->pmtu_pending = 0;
}
*/
static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t)
{
- if (t->dst && (!dst_check(t->dst, t->dst_cookie) ||
- t->pathmtu != max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
- SCTP_DEFAULT_MINSEGMENT)))
+ if (t->dst && !dst_check(t->dst, t->dst_cookie))
sctp_transport_dst_release(t);
return t->dst;
}
+static inline bool sctp_transport_pmtu_check(struct sctp_transport *t)
+{
+ __u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)),
+ SCTP_DEFAULT_MINSEGMENT);
+
+ if (t->pathmtu == pmtu)
+ return true;
+
+ t->pathmtu = pmtu;
+
+ return false;
+}
+
#endif /* __net_sctp_h__ */
__u64 hb_nonce;
} sctp_sender_hb_info_t;
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp);
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp);
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp);
void sctp_stream_free(struct sctp_stream *stream);
void sctp_stream_clear(struct sctp_stream *stream);
/* Did the messenge fail to send? */
int send_error;
u8 send_failed:1,
- force_delay:1,
can_delay; /* should this message be Nagle delayed */
};
void sctp_transport_burst_limited(struct sctp_transport *);
void sctp_transport_burst_reset(struct sctp_transport *);
unsigned long sctp_transport_timeout(struct sctp_transport *);
-void sctp_transport_reset(struct sctp_transport *);
-void sctp_transport_update_pmtu(struct sock *, struct sctp_transport *, u32);
+void sctp_transport_reset(struct sctp_transport *t);
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu);
void sctp_transport_immediate_rtx(struct sctp_transport *);
void sctp_transport_dst_release(struct sctp_transport *t);
void sctp_transport_dst_confirm(struct sctp_transport *t);
__u8 need_ecne:1, /* Need to send an ECNE Chunk? */
temp:1, /* Is it a temporary association? */
+ force_delay:1,
prsctp_enable:1,
reconf_enable:1;
__u32 sctp_association_get_next_tsn(struct sctp_association *);
-void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *);
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc);
void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int);
void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int);
void sctp_assoc_set_primary(struct sctp_association *,
__u64 stx_ino; /* Inode number */
__u64 stx_size; /* File size */
__u64 stx_blocks; /* Number of 512-byte blocks allocated */
- __u64 __spare1[1];
+ __u64 stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
/* 0x40 */
struct statx_timestamp stx_atime; /* Last access time */
struct statx_timestamp stx_btime; /* File creation time */
#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
#define STATX_ALL 0x00000fffU /* All currently supported flags */
+#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
/*
- * Attributes to be found in stx_attributes
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
*
* These give information about the features or the state of a file that might
* be of use to ordinary userspace programs such as GUIs or ls rather than
extern int audit_filter(int msgtype, unsigned int listtype);
#ifdef CONFIG_AUDITSYSCALL
-extern int __audit_signal_info(int sig, struct task_struct *t);
-static inline int audit_signal_info(int sig, struct task_struct *t)
-{
- if (auditd_test_task(t) || (audit_signals && !audit_dummy_context()))
- return __audit_signal_info(sig, t);
- return 0;
-}
+extern int audit_signal_info(int sig, struct task_struct *t);
extern void audit_filter_inodes(struct task_struct *, struct audit_context *);
extern struct list_head *audit_killed_trees(void);
#else
* If the audit subsystem is being terminated, record the task (pid)
* and uid that is doing that.
*/
-int __audit_signal_info(int sig, struct task_struct *t)
+int audit_signal_info(int sig, struct task_struct *t)
{
struct audit_aux_data_pids *axp;
struct task_struct *tsk = current;
struct audit_context *ctx = tsk->audit_context;
kuid_t uid = current_uid(), t_uid = task_uid(t);
- if (auditd_test_task(t)) {
- if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) {
- audit_sig_pid = task_tgid_nr(tsk);
- if (uid_valid(tsk->loginuid))
- audit_sig_uid = tsk->loginuid;
- else
- audit_sig_uid = uid;
- security_task_getsecid(tsk, &audit_sig_sid);
- }
- if (!audit_signals || audit_dummy_context())
- return 0;
+ if (auditd_test_task(t) &&
+ (sig == SIGTERM || sig == SIGHUP ||
+ sig == SIGUSR1 || sig == SIGUSR2)) {
+ audit_sig_pid = task_tgid_nr(tsk);
+ if (uid_valid(tsk->loginuid))
+ audit_sig_uid = tsk->loginuid;
+ else
+ audit_sig_uid = uid;
+ security_task_getsecid(tsk, &audit_sig_sid);
}
+ if (!audit_signals || audit_dummy_context())
+ return 0;
+
/* optimize the common case by putting first signal recipient directly
* in audit_context */
if (!ctx->target_pid) {
}
}
-static int check_ptr_alignment(struct bpf_verifier_env *env,
- struct bpf_reg_state *reg, int off, int size)
+static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
+ int off, int size)
{
- if (reg->type != PTR_TO_PACKET && reg->type != PTR_TO_MAP_VALUE_ADJ) {
- if (off % size != 0) {
- verbose("misaligned access off %d size %d\n",
- off, size);
- return -EACCES;
- } else {
- return 0;
- }
- }
-
- if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
- /* misaligned access to packet is ok on x86,arm,arm64 */
- return 0;
-
if (reg->id && size != 1) {
- verbose("Unknown packet alignment. Only byte-sized access allowed\n");
+ verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
return -EACCES;
}
/* skb->data is NET_IP_ALIGN-ed */
- if (reg->type == PTR_TO_PACKET &&
- (NET_IP_ALIGN + reg->off + off) % size != 0) {
+ if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
NET_IP_ALIGN, reg->off, off, size);
return -EACCES;
}
+
return 0;
}
+static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
+ int size)
+{
+ if (size != 1) {
+ verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+static int check_ptr_alignment(const struct bpf_reg_state *reg,
+ int off, int size)
+{
+ switch (reg->type) {
+ case PTR_TO_PACKET:
+ return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+ check_pkt_ptr_alignment(reg, off, size);
+ case PTR_TO_MAP_VALUE_ADJ:
+ return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
+ check_val_ptr_alignment(reg, size);
+ default:
+ if (off % size != 0) {
+ verbose("misaligned access off %d size %d\n",
+ off, size);
+ return -EACCES;
+ }
+
+ return 0;
+ }
+}
+
/* check whether memory at (regno + off) is accessible for t = (read | write)
* if t==write, value_regno is a register which value is stored into memory
* if t==read, value_regno is a register which will receive the value from memory
if (size < 0)
return size;
- err = check_ptr_alignment(env, reg, off, size);
+ err = check_ptr_alignment(reg, off, size);
if (err)
return err;
* register as unknown.
*/
if (env->allow_ptr_leaks &&
+ BPF_CLASS(insn->code) == BPF_ALU64 && opcode == BPF_ADD &&
(dst_reg->type == PTR_TO_MAP_VALUE ||
dst_reg->type == PTR_TO_MAP_VALUE_ADJ))
dst_reg->type = PTR_TO_MAP_VALUE_ADJ;
for (i = 0; i < MAX_BPF_REG; i++)
if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id)
- regs[i].range = dst_reg->off;
+ /* keep the maximum range already checked */
+ regs[i].range = max(regs[i].range, dst_reg->off);
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (state->stack_slot_type[i] != STACK_SPILL)
continue;
reg = &state->spilled_regs[i / BPF_REG_SIZE];
if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id)
- reg->range = dst_reg->off;
+ reg->range = max(reg->range, dst_reg->off);
}
}
WARN_ON(!task->ptrace || task->parent != current);
+ /*
+ * PTRACE_LISTEN can allow ptrace_trap_notify to wake us up remotely.
+ * Recheck state under the lock to close this race.
+ */
spin_lock_irq(&task->sighand->siglock);
- if (__fatal_signal_pending(task))
- wake_up_state(task, __TASK_TRACED);
- else
- task->state = TASK_TRACED;
+ if (task->state == __TASK_TRACED) {
+ if (__fatal_signal_pending(task))
+ wake_up_state(task, __TASK_TRACED);
+ else
+ task->state = TASK_TRACED;
+ }
spin_unlock_irq(&task->sighand->siglock);
}
if (write) {
if (*negp)
return -EINVAL;
+ if (*lvalp > UINT_MAX)
+ return -EINVAL;
*valp = *lvalp;
} else {
unsigned int val = *valp;
+ *negp = false;
*lvalp = (unsigned long)val;
}
return 0;
rb_data[cpu].cnt = cpu;
rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
"rbtester/%d", cpu);
- if (WARN_ON(!rb_threads[cpu])) {
+ if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_threads[cpu]);
goto out_free;
}
/* Now create the rb hammer! */
rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
- if (WARN_ON(!rb_hammer)) {
+ if (WARN_ON(IS_ERR(rb_hammer))) {
pr_cont("FAILED\n");
- ret = -1;
+ ret = PTR_ERR(rb_hammer);
goto out_free;
}
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- } else if (!memcmp("defer", buf,
- min(sizeof("defer")-1, count))) {
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
- clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
- set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
} else if (!memcmp("defer+madvise", buf,
min(sizeof("defer+madvise")-1, count))) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+ } else if (!memcmp("defer", buf,
+ min(sizeof("defer")-1, count))) {
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags);
+ clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags);
+ set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags);
} else if (!memcmp("madvise", buf,
min(sizeof("madvise")-1, count))) {
clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags);
enum ttu_flags;
struct tlbflush_unmap_batch;
+
+/*
+ * only for MM internal work items which do not depend on
+ * any allocations or locks which might depend on allocations
+ */
+extern struct workqueue_struct *mm_percpu_wq;
+
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
COMPAT_SYSCALL_DEFINE3(set_mempolicy, int, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
DECLARE_BITMAP(bm, MAX_NUMNODES);
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(bm, nmask, nr_bits);
+ if (compat_get_bitmap(bm, nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, bm, alloc_size);
+ if (copy_to_user(nm, bm, alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_set_mempolicy(mode, nm, nr_bits+1);
}
compat_ulong_t, mode, compat_ulong_t __user *, nmask,
compat_ulong_t, maxnode, compat_ulong_t, flags)
{
- long err = 0;
unsigned long __user *nm = NULL;
unsigned long nr_bits, alloc_size;
nodemask_t bm;
alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8;
if (nmask) {
- err = compat_get_bitmap(nodes_addr(bm), nmask, nr_bits);
+ if (compat_get_bitmap(nodes_addr(bm), nmask, nr_bits))
+ return -EFAULT;
nm = compat_alloc_user_space(alloc_size);
- err |= copy_to_user(nm, nodes_addr(bm), alloc_size);
+ if (copy_to_user(nm, nodes_addr(bm), alloc_size))
+ return -EFAULT;
}
- if (err)
- return -EFAULT;
-
return sys_mbind(start, len, mode, nm, nr_bits+1, flags);
}
*/
static cpumask_t cpus_with_pcps;
+ /*
+ * Make sure nobody triggers this path before mm_percpu_wq is fully
+ * initialized.
+ */
+ if (WARN_ON_ONCE(!mm_percpu_wq))
+ return;
+
/* Workqueues cannot recurse */
if (current->flags & PF_WQ_WORKER)
return;
for_each_cpu(cpu, &cpus_with_pcps) {
struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
INIT_WORK(work, drain_local_pages_wq);
- schedule_work_on(cpu, work);
+ queue_work_on(cpu, mm_percpu_wq, work);
}
for_each_cpu(cpu, &cpus_with_pcps)
flush_work(per_cpu_ptr(&pcpu_drain, cpu));
K(node_page_state(pgdat, NR_FILE_MAPPED)),
K(node_page_state(pgdat, NR_FILE_DIRTY)),
K(node_page_state(pgdat, NR_WRITEBACK)),
+ K(node_page_state(pgdat, NR_SHMEM)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
* HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
#endif
- K(node_page_state(pgdat, NR_SHMEM)),
K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
node_page_state(pgdat, NR_PAGES_SCANNED),
if (pvmw->pmd && !pvmw->pte)
return not_found(pvmw);
- /* Only for THP, seek to next pte entry makes sense */
- if (pvmw->pte) {
- if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
- return not_found(pvmw);
+ if (pvmw->pte)
goto next_pte;
- }
if (unlikely(PageHuge(pvmw->page))) {
/* when pud is not present, pte will be NULL */
while (1) {
if (check_pte(pvmw))
return true;
-next_pte: do {
+next_pte:
+ /* Seek to next pte only makes sense for THP */
+ if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
+ return not_found(pvmw);
+ do {
pvmw->address += PAGE_SIZE;
- if (pvmw->address >=
+ if (pvmw->address >= pvmw->vma->vm_end ||
+ pvmw->address >=
__vma_address(pvmw->page, pvmw->vma) +
hpage_nr_pages(pvmw->page) * PAGE_SIZE)
return not_found(pvmw);
static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
-/*
- * lru_add_drain_wq is used to do lru_add_drain_all() from a WQ_MEM_RECLAIM
- * workqueue, aiding in getting memory freed.
- */
-static struct workqueue_struct *lru_add_drain_wq;
-
-static int __init lru_init(void)
-{
- lru_add_drain_wq = alloc_workqueue("lru-add-drain", WQ_MEM_RECLAIM, 0);
-
- if (WARN(!lru_add_drain_wq,
- "Failed to create workqueue lru_add_drain_wq"))
- return -ENOMEM;
-
- return 0;
-}
-early_initcall(lru_init);
-
void lru_add_drain_all(void)
{
static DEFINE_MUTEX(lock);
static struct cpumask has_work;
int cpu;
+ /*
+ * Make sure nobody triggers this path before mm_percpu_wq is fully
+ * initialized.
+ */
+ if (WARN_ON(!mm_percpu_wq))
+ return;
+
mutex_lock(&lock);
get_online_cpus();
cpumask_clear(&has_work);
pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
need_activate_page_drain(cpu)) {
INIT_WORK(work, lru_add_drain_per_cpu);
- queue_work_on(cpu, lru_add_drain_wq, work);
+ queue_work_on(cpu, mm_percpu_wq, work);
cpumask_set_cpu(cpu, &has_work);
}
}
struct page *page = map[i];
if (page)
__free_page(page);
+ if (!(i % SWAP_CLUSTER_MAX))
+ cond_resched();
}
vfree(map);
}
#endif /* CONFIG_PROC_FS */
#ifdef CONFIG_SMP
-static struct workqueue_struct *vmstat_wq;
static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
int sysctl_stat_interval __read_mostly = HZ;
* to occur in the future. Keep on running the
* update worker thread.
*/
- queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+ queue_delayed_work_on(smp_processor_id(), mm_percpu_wq,
this_cpu_ptr(&vmstat_work),
round_jiffies_relative(sysctl_stat_interval));
}
struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
if (!delayed_work_pending(dw) && need_update(cpu))
- queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
+ queue_delayed_work_on(cpu, mm_percpu_wq, dw, 0);
}
put_online_cpus();
INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
vmstat_update);
- vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
schedule_delayed_work(&shepherd,
round_jiffies_relative(sysctl_stat_interval));
}
#endif
+struct workqueue_struct *mm_percpu_wq;
+
void __init init_mm_internals(void)
{
-#ifdef CONFIG_SMP
- int ret;
+ int ret __maybe_unused;
+ mm_percpu_wq = alloc_workqueue("mm_percpu_wq",
+ WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+
+#ifdef CONFIG_SMP
ret = cpuhp_setup_state_nocalls(CPUHP_MM_VMSTAT_DEAD, "mm/vmstat:dead",
NULL, vmstat_cpu_dead);
if (ret < 0)
unsigned char ar_tip[4];
} *arp_eth, _arp_eth;
const struct arphdr *arp;
- struct arphdr *_arp;
+ struct arphdr _arp;
arp = __skb_header_pointer(skb, nhoff, sizeof(_arp), data,
hlen, &_arp);
if (skb)
skb = skb_clone(skb, GFP_ATOMIC);
write_unlock(&neigh->lock);
- neigh->ops->solicit(neigh, skb);
+ if (neigh->ops->solicit)
+ neigh->ops->solicit(neigh, skb);
atomic_inc(&neigh->probes);
kfree_skb(skb);
}
#include <net/tcp.h>
static siphash_key_t net_secret __read_mostly;
+static siphash_key_t ts_secret __read_mostly;
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));
}
#endif
#endif
#if IS_ENABLED(CONFIG_IPV6)
+static u32 secure_tcpv6_ts_off(const __be32 *saddr, const __be32 *daddr)
+{
+ const struct {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ } __aligned(SIPHASH_ALIGNMENT) combined = {
+ .saddr = *(struct in6_addr *)saddr,
+ .daddr = *(struct in6_addr *)daddr,
+ };
+
+ if (sysctl_tcp_timestamps != 1)
+ return 0;
+
+ return siphash(&combined, offsetofend(typeof(combined), daddr),
+ &ts_secret);
+}
+
u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
__be16 sport, __be16 dport, u32 *tsoff)
{
net_secret_init();
hash = siphash(&combined, offsetofend(typeof(combined), dport),
&net_secret);
- *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ *tsoff = secure_tcpv6_ts_off(saddr, daddr);
return seq_scale(hash);
}
EXPORT_SYMBOL(secure_tcpv6_sequence_number);
#endif
#ifdef CONFIG_INET
+static u32 secure_tcp_ts_off(__be32 saddr, __be32 daddr)
+{
+ if (sysctl_tcp_timestamps != 1)
+ return 0;
+
+ return siphash_2u32((__force u32)saddr, (__force u32)daddr,
+ &ts_secret);
+}
/* secure_tcp_sequence_number(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d),
* but fortunately, `sport' cannot be 0 in any circumstances. If this changes,
hash = siphash_3u32((__force u32)saddr, (__force u32)daddr,
(__force u32)sport << 16 | (__force u32)dport,
&net_secret);
- *tsoff = sysctl_tcp_timestamps == 1 ? (hash >> 32) : 0;
+ *tsoff = secure_tcp_ts_off(saddr, daddr);
return seq_scale(hash);
}
.data = &sysctl_net_busy_poll,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
{
.procname = "busy_read",
.data = &sysctl_net_busy_read,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
},
#endif
#ifdef CONFIG_NET_SCHED
while ((d = next)) {
next = d->next;
dev = d->dev;
- if ((!ic_dev || dev != ic_dev->dev) && !netdev_uses_dsa(dev)) {
+ if (d != ic_dev && !netdev_uses_dsa(dev)) {
pr_debug("IP-Config: Downing %s\n", dev->name);
dev_change_flags(dev, d->flags);
}
.timeout = 180,
};
-static struct nf_conntrack_helper snmp_helper __read_mostly = {
- .me = THIS_MODULE,
- .help = help,
- .expect_policy = &snmp_exp_policy,
- .name = "snmp",
- .tuple.src.l3num = AF_INET,
- .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT),
- .tuple.dst.protonum = IPPROTO_UDP,
-};
-
static struct nf_conntrack_helper snmp_trap_helper __read_mostly = {
.me = THIS_MODULE,
.help = help,
static int __init nf_nat_snmp_basic_init(void)
{
- int ret = 0;
-
BUG_ON(nf_nat_snmp_hook != NULL);
RCU_INIT_POINTER(nf_nat_snmp_hook, help);
- ret = nf_conntrack_helper_register(&snmp_trap_helper);
- if (ret < 0) {
- nf_conntrack_helper_unregister(&snmp_helper);
- return ret;
- }
- return ret;
+ return nf_conntrack_helper_register(&snmp_trap_helper);
}
static void __exit nf_nat_snmp_basic_fini(void)
{
RCU_INIT_POINTER(nf_nat_snmp_hook, NULL);
+ synchronize_rcu();
nf_conntrack_helper_unregister(&snmp_trap_helper);
}
void ping_unhash(struct sock *sk)
{
struct inet_sock *isk = inet_sk(sk);
+
pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+ write_lock_bh(&ping_table.lock);
if (sk_hashed(sk)) {
- write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
sk_nulls_node_init(&sk->sk_nulls_node);
sock_put(sk);
isk->inet_num = 0;
isk->inet_sport = 0;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- write_unlock_bh(&ping_table.lock);
}
+ write_unlock_bh(&ping_table.lock);
}
EXPORT_SYMBOL_GPL(ping_unhash);
#define REXMIT_LOST 1 /* retransmit packets marked lost */
#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
-static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb)
+static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
+ unsigned int len)
{
static bool __once __read_mostly;
rcu_read_lock();
dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif);
- pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
- dev ? dev->name : "Unknown driver");
+ if (!dev || len >= dev->mtu)
+ pr_warn("%s: Driver has suspect GRO implementation, TCP performance may be compromised.\n",
+ dev ? dev->name : "Unknown driver");
rcu_read_unlock();
}
}
if (len >= icsk->icsk_ack.rcv_mss) {
icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
tcp_sk(sk)->advmss);
- if (unlikely(icsk->icsk_ack.rcv_mss != len))
- tcp_gro_dev_warn(sk, skb);
+ /* Account for possibly-removed options */
+ if (unlikely(len > icsk->icsk_ack.rcv_mss +
+ MAX_TCP_OPTION_SPACE))
+ tcp_gro_dev_warn(sk, skb, len);
} else {
/* Otherwise, we make more careful check taking into account,
* that SACKs block is variable.
const int ts)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (metric > tp->reordering) {
- int mib_idx;
+ int mib_idx;
+ if (metric > tp->reordering) {
tp->reordering = min(sysctl_tcp_max_reordering, metric);
- /* This exciting event is worth to be remembered. 8) */
- if (ts)
- mib_idx = LINUX_MIB_TCPTSREORDER;
- else if (tcp_is_reno(tp))
- mib_idx = LINUX_MIB_TCPRENOREORDER;
- else if (tcp_is_fack(tp))
- mib_idx = LINUX_MIB_TCPFACKREORDER;
- else
- mib_idx = LINUX_MIB_TCPSACKREORDER;
-
- NET_INC_STATS(sock_net(sk), mib_idx);
#if FASTRETRANS_DEBUG > 1
pr_debug("Disorder%d %d %u f%u s%u rr%d\n",
tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
}
tp->rack.reord = 1;
+
+ /* This exciting event is worth to be remembered. 8) */
+ if (ts)
+ mib_idx = LINUX_MIB_TCPTSREORDER;
+ else if (tcp_is_reno(tp))
+ mib_idx = LINUX_MIB_TCPRENOREORDER;
+ else if (tcp_is_fack(tp))
+ mib_idx = LINUX_MIB_TCPFACKREORDER;
+ else
+ mib_idx = LINUX_MIB_TCPSACKREORDER;
+
+ NET_INC_STATS(sock_net(sk), mib_idx);
}
/* This must be called before lost_out is incremented */
/* Account for retransmits that are lost again */
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+ tcp_skb_pcount(skb));
}
}
struct kcm_attach info;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_attach_ioctl(sock, &info);
struct kcm_unattach info;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_unattach_ioctl(sock, &info);
struct socket *newsock = NULL;
if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
- err = -EFAULT;
+ return -EFAULT;
err = kcm_clone(sock, &info, &newsock);
}
EXPORT_SYMBOL_GPL(l2tp_session_find);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth)
+/* Like l2tp_session_find() but takes a reference on the returned session.
+ * Optionally calls session->ref() too if do_ref is true.
+ */
+struct l2tp_session *l2tp_session_get(struct net *net,
+ struct l2tp_tunnel *tunnel,
+ u32 session_id, bool do_ref)
+{
+ struct hlist_head *session_list;
+ struct l2tp_session *session;
+
+ if (!tunnel) {
+ struct l2tp_net *pn = l2tp_pernet(net);
+
+ session_list = l2tp_session_id_hash_2(pn, session_id);
+
+ rcu_read_lock_bh();
+ hlist_for_each_entry_rcu(session, session_list, global_hlist) {
+ if (session->session_id == session_id) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
+ rcu_read_unlock_bh();
+
+ return session;
+ }
+ }
+ rcu_read_unlock_bh();
+
+ return NULL;
+ }
+
+ session_list = l2tp_session_id_hash(tunnel, session_id);
+ read_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session, session_list, hlist) {
+ if (session->session_id == session_id) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return session;
+ }
+ }
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_get);
+
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+ bool do_ref)
{
int hash;
struct l2tp_session *session;
for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
hlist_for_each_entry(session, &tunnel->session_hlist[hash], hlist) {
if (++count > nth) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
read_unlock_bh(&tunnel->hlist_lock);
return session;
}
return NULL;
}
-EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+EXPORT_SYMBOL_GPL(l2tp_session_get_nth);
/* Lookup a session by interface name.
* This is very inefficient but is only used by management interfaces.
*/
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
+struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname,
+ bool do_ref)
{
struct l2tp_net *pn = l2tp_pernet(net);
int hash;
for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) {
if (!strcmp(session->ifname, ifname)) {
+ l2tp_session_inc_refcount(session);
+ if (do_ref && session->ref)
+ session->ref(session);
rcu_read_unlock_bh();
+
return session;
}
}
return NULL;
}
-EXPORT_SYMBOL_GPL(l2tp_session_find_by_ifname);
+EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname);
+
+static int l2tp_session_add_to_tunnel(struct l2tp_tunnel *tunnel,
+ struct l2tp_session *session)
+{
+ struct l2tp_session *session_walk;
+ struct hlist_head *g_head;
+ struct hlist_head *head;
+ struct l2tp_net *pn;
+
+ head = l2tp_session_id_hash(tunnel, session->session_id);
+
+ write_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session_walk, head, hlist)
+ if (session_walk->session_id == session->session_id)
+ goto exist;
+
+ if (tunnel->version == L2TP_HDR_VER_3) {
+ pn = l2tp_pernet(tunnel->l2tp_net);
+ g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net),
+ session->session_id);
+
+ spin_lock_bh(&pn->l2tp_session_hlist_lock);
+ hlist_for_each_entry(session_walk, g_head, global_hlist)
+ if (session_walk->session_id == session->session_id)
+ goto exist_glob;
+
+ hlist_add_head_rcu(&session->global_hlist, g_head);
+ spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+ }
+
+ hlist_add_head(&session->hlist, head);
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ return 0;
+
+exist_glob:
+ spin_unlock_bh(&pn->l2tp_session_hlist_lock);
+exist:
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ return -EEXIST;
+}
/* Lookup a tunnel by id
*/
* a data (not control) frame before coming here. Fields up to the
* session-id have already been parsed and ptr points to the data
* after the session-id.
+ *
+ * session->ref() must have been called prior to l2tp_recv_common().
+ * session->deref() will be called automatically after skb is processed.
*/
void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
unsigned char *ptr, unsigned char *optr, u16 hdrflags,
int offset;
u32 ns, nr;
- /* The ref count is increased since we now hold a pointer to
- * the session. Take care to decrement the refcnt when exiting
- * this function from now on...
- */
- l2tp_session_inc_refcount(session);
- if (session->ref)
- (*session->ref)(session);
-
/* Parse and check optional cookie */
if (session->peer_cookie_len > 0) {
if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
/* Try to dequeue as many skbs from reorder_q as we can. */
l2tp_recv_dequeue(session);
- l2tp_session_dec_refcount(session);
-
return;
discard:
if (session->deref)
(*session->deref)(session);
-
- l2tp_session_dec_refcount(session);
}
EXPORT_SYMBOL(l2tp_recv_common);
}
/* Find the session context */
- session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id);
+ session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id, true);
if (!session || !session->recv_skb) {
+ if (session) {
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ }
+
/* Not found? Pass to userspace to deal with */
l2tp_info(tunnel, L2TP_MSG_DATA,
"%s: no session found (%u/%u). Passing up.\n",
}
l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook);
+ l2tp_session_dec_refcount(session);
return 0;
struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
struct l2tp_session *session;
+ int err;
session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL);
if (session != NULL) {
l2tp_session_set_header_len(session, tunnel->version);
+ err = l2tp_session_add_to_tunnel(tunnel, session);
+ if (err) {
+ kfree(session);
+
+ return ERR_PTR(err);
+ }
+
/* Bump the reference count. The session context is deleted
* only when this drops to zero.
*/
/* Ensure tunnel socket isn't deleted */
sock_hold(tunnel->sock);
- /* Add session to the tunnel's hash list */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_add_head(&session->hlist,
- l2tp_session_id_hash(tunnel, session_id));
- write_unlock_bh(&tunnel->hlist_lock);
-
- /* And to the global session list if L2TPv3 */
- if (tunnel->version != L2TP_HDR_VER_2) {
- struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
-
- spin_lock_bh(&pn->l2tp_session_hlist_lock);
- hlist_add_head_rcu(&session->global_hlist,
- l2tp_session_id_hash_2(pn, session_id));
- spin_unlock_bh(&pn->l2tp_session_hlist_lock);
- }
-
/* Ignore management session in session count value */
if (session->session_id != 0)
atomic_inc(&l2tp_session_count);
+
+ return session;
}
- return session;
+ return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL_GPL(l2tp_session_create);
return tunnel;
}
+struct l2tp_session *l2tp_session_get(struct net *net,
+ struct l2tp_tunnel *tunnel,
+ u32 session_id, bool do_ref);
struct l2tp_session *l2tp_session_find(struct net *net,
struct l2tp_tunnel *tunnel,
u32 session_id);
-struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth);
-struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
+struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth,
+ bool do_ref);
+struct l2tp_session *l2tp_session_get_by_ifname(struct net *net, char *ifname,
+ bool do_ref);
struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd)
{
- pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+ pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
pd->session_idx++;
if (pd->session == NULL) {
}
/* Show the tunnel or session context */
- if (pd->session == NULL)
+ if (!pd->session) {
l2tp_dfs_seq_tunnel_show(m, pd->tunnel);
- else
+ } else {
l2tp_dfs_seq_session_show(m, pd->session);
+ if (pd->session->deref)
+ pd->session->deref(pd->session);
+ l2tp_session_dec_refcount(pd->session);
+ }
out:
return 0;
goto out;
}
- session = l2tp_session_find(net, tunnel, session_id);
- if (session) {
- rc = -EEXIST;
- goto out;
- }
-
if (cfg->ifname) {
dev = dev_get_by_name(net, cfg->ifname);
if (dev) {
session = l2tp_session_create(sizeof(*spriv), tunnel, session_id,
peer_session_id, cfg);
- if (!session) {
- rc = -ENOMEM;
+ if (IS_ERR(session)) {
+ rc = PTR_ERR(session);
goto out;
}
}
/* Ok, this is a data packet. Lookup the session. */
- session = l2tp_session_find(net, NULL, session_id);
- if (session == NULL)
+ session = l2tp_session_get(net, NULL, session_id, true);
+ if (!session)
goto discard;
tunnel = session->tunnel;
- if (tunnel == NULL)
- goto discard;
+ if (!tunnel)
+ goto discard_sess;
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
- goto discard;
+ goto discard_sess;
/* Point to L2TP header */
optr = ptr = skb->data;
}
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
+ l2tp_session_dec_refcount(session);
return 0;
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
- if (tunnel != NULL)
+ if (tunnel) {
sk = tunnel->sock;
- else {
+ sock_hold(sk);
+ } else {
struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
read_lock_bh(&l2tp_ip_lock);
return sk_receive_skb(sk, skb, 1);
+discard_sess:
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ goto discard;
+
discard_put:
sock_put(sk);
}
/* Ok, this is a data packet. Lookup the session. */
- session = l2tp_session_find(net, NULL, session_id);
- if (session == NULL)
+ session = l2tp_session_get(net, NULL, session_id, true);
+ if (!session)
goto discard;
tunnel = session->tunnel;
- if (tunnel == NULL)
- goto discard;
+ if (!tunnel)
+ goto discard_sess;
/* Trace packet contents, if enabled */
if (tunnel->debug & L2TP_MSG_DATA) {
length = min(32u, skb->len);
if (!pskb_may_pull(skb, length))
- goto discard;
+ goto discard_sess;
/* Point to L2TP header */
optr = ptr = skb->data;
l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
tunnel->recv_payload_hook);
+ l2tp_session_dec_refcount(session);
+
return 0;
pass_up:
tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
- if (tunnel != NULL)
+ if (tunnel) {
sk = tunnel->sock;
- else {
+ sock_hold(sk);
+ } else {
struct ipv6hdr *iph = ipv6_hdr(skb);
read_lock_bh(&l2tp_ip6_lock);
return sk_receive_skb(sk, skb, 1);
+discard_sess:
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ goto discard;
+
discard_put:
sock_put(sk);
/* Accessed under genl lock */
static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
-static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info)
+static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info,
+ bool do_ref)
{
u32 tunnel_id;
u32 session_id;
if (info->attrs[L2TP_ATTR_IFNAME]) {
ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
- session = l2tp_session_find_by_ifname(net, ifname);
+ session = l2tp_session_get_by_ifname(net, ifname, do_ref);
} else if ((info->attrs[L2TP_ATTR_SESSION_ID]) &&
(info->attrs[L2TP_ATTR_CONN_ID])) {
tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
tunnel = l2tp_tunnel_find(net, tunnel_id);
if (tunnel)
- session = l2tp_session_find(net, tunnel, session_id);
+ session = l2tp_session_get(net, tunnel, session_id,
+ do_ref);
}
return session;
session_id, peer_session_id, &cfg);
if (ret >= 0) {
- session = l2tp_session_find(net, tunnel, session_id);
- if (session)
+ session = l2tp_session_get(net, tunnel, session_id, false);
+ if (session) {
ret = l2tp_session_notify(&l2tp_nl_family, info, session,
L2TP_CMD_SESSION_CREATE);
+ l2tp_session_dec_refcount(session);
+ }
}
out:
struct l2tp_session *session;
u16 pw_type;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, true);
if (session == NULL) {
ret = -ENODEV;
goto out;
if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session);
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+
out:
return ret;
}
int ret = 0;
struct l2tp_session *session;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, false);
if (session == NULL) {
ret = -ENODEV;
goto out;
ret = l2tp_session_notify(&l2tp_nl_family, info,
session, L2TP_CMD_SESSION_MODIFY);
+ l2tp_session_dec_refcount(session);
+
out:
return ret;
}
struct sk_buff *msg;
int ret;
- session = l2tp_nl_session_find(info);
+ session = l2tp_nl_session_get(info, false);
if (session == NULL) {
ret = -ENODEV;
- goto out;
+ goto err;
}
msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
if (!msg) {
ret = -ENOMEM;
- goto out;
+ goto err_ref;
}
ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq,
0, session, L2TP_CMD_SESSION_GET);
if (ret < 0)
- goto err_out;
+ goto err_ref_msg;
- return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
+ ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid);
-err_out:
- nlmsg_free(msg);
+ l2tp_session_dec_refcount(session);
-out:
+ return ret;
+
+err_ref_msg:
+ nlmsg_free(msg);
+err_ref:
+ l2tp_session_dec_refcount(session);
+err:
return ret;
}
goto out;
}
- session = l2tp_session_find_nth(tunnel, si);
+ session = l2tp_session_get_nth(tunnel, si, false);
if (session == NULL) {
ti++;
tunnel = NULL;
if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- session, L2TP_CMD_SESSION_GET) < 0)
+ session, L2TP_CMD_SESSION_GET) < 0) {
+ l2tp_session_dec_refcount(session);
break;
+ }
+ l2tp_session_dec_refcount(session);
si++;
}
static void pppol2tp_session_destruct(struct sock *sk)
{
struct l2tp_session *session = sk->sk_user_data;
+
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_queue_purge(&sk->sk_write_queue);
+
if (session) {
sk->sk_user_data = NULL;
BUG_ON(session->magic != L2TP_SESSION_MAGIC);
l2tp_session_queue_purge(session);
sock_put(sk);
}
- skb_queue_purge(&sk->sk_receive_queue);
- skb_queue_purge(&sk->sk_write_queue);
-
release_sock(sk);
/* This will delete the session context via
int error = 0;
u32 tunnel_id, peer_tunnel_id;
u32 session_id, peer_session_id;
+ bool drop_refcnt = false;
int ver = 2;
int fd;
if (tunnel->peer_tunnel_id == 0)
tunnel->peer_tunnel_id = peer_tunnel_id;
- /* Create session if it doesn't already exist. We handle the
- * case where a session was previously created by the netlink
- * interface by checking that the session doesn't already have
- * a socket and its tunnel socket are what we expect. If any
- * of those checks fail, return EEXIST to the caller.
- */
- session = l2tp_session_find(sock_net(sk), tunnel, session_id);
- if (session == NULL) {
- /* Default MTU must allow space for UDP/L2TP/PPP
- * headers.
+ session = l2tp_session_get(sock_net(sk), tunnel, session_id, false);
+ if (session) {
+ drop_refcnt = true;
+ ps = l2tp_session_priv(session);
+
+ /* Using a pre-existing session is fine as long as it hasn't
+ * been connected yet.
*/
- cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ if (ps->sock) {
+ error = -EEXIST;
+ goto end;
+ }
- /* Allocate and initialize a new session context. */
- session = l2tp_session_create(sizeof(struct pppol2tp_session),
- tunnel, session_id,
- peer_session_id, &cfg);
- if (session == NULL) {
- error = -ENOMEM;
+ /* consistency checks */
+ if (ps->tunnel_sock != tunnel->sock) {
+ error = -EEXIST;
goto end;
}
} else {
- ps = l2tp_session_priv(session);
- error = -EEXIST;
- if (ps->sock != NULL)
- goto end;
+ /* Default MTU must allow space for UDP/L2TP/PPP headers */
+ cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ cfg.mru = cfg.mtu;
- /* consistency checks */
- if (ps->tunnel_sock != tunnel->sock)
+ session = l2tp_session_create(sizeof(struct pppol2tp_session),
+ tunnel, session_id,
+ peer_session_id, &cfg);
+ if (IS_ERR(session)) {
+ error = PTR_ERR(session);
goto end;
+ }
}
/* Associate session with its PPPoL2TP socket */
session->name);
end:
+ if (drop_refcnt)
+ l2tp_session_dec_refcount(session);
release_sock(sk);
return error;
if (tunnel->sock == NULL)
goto out;
- /* Check that this session doesn't already exist */
- error = -EEXIST;
- session = l2tp_session_find(net, tunnel, session_id);
- if (session != NULL)
- goto out;
-
/* Default MTU values. */
if (cfg->mtu == 0)
cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
cfg->mru = cfg->mtu;
/* Allocate and initialize a new session context. */
- error = -ENOMEM;
session = l2tp_session_create(sizeof(struct pppol2tp_session),
tunnel, session_id,
peer_session_id, cfg);
- if (session == NULL)
+ if (IS_ERR(session)) {
+ error = PTR_ERR(session);
goto out;
+ }
ps = l2tp_session_priv(session);
ps->tunnel_sock = tunnel->sock;
if (stats.session_id != 0) {
/* resend to session ioctl handler */
struct l2tp_session *session =
- l2tp_session_find(sock_net(sk), tunnel, stats.session_id);
- if (session != NULL)
- err = pppol2tp_session_ioctl(session, cmd, arg);
- else
+ l2tp_session_get(sock_net(sk), tunnel,
+ stats.session_id, true);
+
+ if (session) {
+ err = pppol2tp_session_ioctl(session, cmd,
+ arg);
+ if (session->deref)
+ session->deref(session);
+ l2tp_session_dec_refcount(session);
+ } else {
err = -EBADR;
+ }
break;
}
#ifdef CONFIG_XFRM
static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
{
- pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+ pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx, true);
pd->session_idx++;
if (pd->session == NULL) {
/* Show the tunnel or session context.
*/
- if (pd->session == NULL)
+ if (!pd->session) {
pppol2tp_seq_tunnel_show(m, pd->tunnel);
- else
+ } else {
pppol2tp_seq_session_show(m, pd->session);
+ if (pd->session->deref)
+ pd->session->deref(pd->session);
+ l2tp_session_dec_refcount(pd->session);
+ }
out:
return 0;
MODULE_LICENSE("GPL");
MODULE_VERSION(PPPOL2TP_DRV_VERSION);
MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OL2TP);
-MODULE_ALIAS_L2TP_PWTYPE(11);
+MODULE_ALIAS_L2TP_PWTYPE(7);
ieee80211_recalc_ps(local);
if (sdata->vif.type == NL80211_IFTYPE_MONITOR ||
- sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+ sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+ local->ops->wake_tx_queue) {
/* XXX: for AP_VLAN, actually track AP queues */
netif_tx_start_all_queues(dev);
} else if (dev) {
BUG_ON(notify != new);
RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
+ /* synchronize_rcu() is called from ctnetlink_exit. */
}
EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
BUG_ON(notify != new);
RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
mutex_unlock(&nf_ct_ecache_mutex);
+ /* synchronize_rcu() is called from ctnetlink_exit. */
}
EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
- BUG_ON(t == NULL);
+ if (!t) {
+ rcu_read_unlock();
+ return NULL;
+ }
+
off = ALIGN(sizeof(struct nf_ct_ext), t->align);
len = off + t->len + var_alloc_len;
alloc_size = t->alloc_size + var_alloc_len;
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
- BUG_ON(t == NULL);
+ if (!t) {
+ rcu_read_unlock();
+ return NULL;
+ }
newoff = ALIGN(old->len, t->align);
newlen = newoff + t->len + var_alloc_len;
RCU_INIT_POINTER(nf_ct_ext_types[type->id], NULL);
update_alloc_size(type);
mutex_unlock(&nf_ct_ext_type_mutex);
- rcu_barrier(); /* Wait for completion of call_rcu()'s */
+ synchronize_rcu();
}
EXPORT_SYMBOL_GPL(nf_ct_extend_unregister);
#ifdef CONFIG_NETFILTER_NETLINK_GLUE_CT
RCU_INIT_POINTER(nfnl_ct_hook, NULL);
#endif
+ synchronize_rcu();
}
module_init(ctnetlink_init);
#ifdef CONFIG_XFRM
RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL);
#endif
+ synchronize_rcu();
+
for (i = 0; i < NFPROTO_NUMPROTO; i++)
kfree(nf_nat_l4protos[i]);
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
MODULE_DESCRIPTION("nfnl_cthelper: User-space connection tracking helpers");
+struct nfnl_cthelper {
+ struct list_head list;
+ struct nf_conntrack_helper helper;
+};
+
+static LIST_HEAD(nfnl_cthelper_list);
+
static int
nfnl_userspace_cthelper(struct sk_buff *skb, unsigned int protoff,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
int i, ret;
struct nf_conntrack_expect_policy *expect_policy;
struct nlattr *tb[NFCTH_POLICY_SET_MAX+1];
+ unsigned int class_max;
ret = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
nfnl_cthelper_expect_policy_set);
if (!tb[NFCTH_POLICY_SET_NUM])
return -EINVAL;
- helper->expect_class_max =
- ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
-
- if (helper->expect_class_max != 0 &&
- helper->expect_class_max > NF_CT_MAX_EXPECT_CLASSES)
+ class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+ if (class_max == 0)
+ return -EINVAL;
+ if (class_max > NF_CT_MAX_EXPECT_CLASSES)
return -EOVERFLOW;
expect_policy = kzalloc(sizeof(struct nf_conntrack_expect_policy) *
- helper->expect_class_max, GFP_KERNEL);
+ class_max, GFP_KERNEL);
if (expect_policy == NULL)
return -ENOMEM;
- for (i=0; i<helper->expect_class_max; i++) {
+ for (i = 0; i < class_max; i++) {
if (!tb[NFCTH_POLICY_SET+i])
goto err;
if (ret < 0)
goto err;
}
+
+ helper->expect_class_max = class_max - 1;
helper->expect_policy = expect_policy;
return 0;
err:
struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_helper *helper;
+ struct nfnl_cthelper *nfcth;
int ret;
if (!tb[NFCTH_TUPLE] || !tb[NFCTH_POLICY] || !tb[NFCTH_PRIV_DATA_LEN])
return -EINVAL;
- helper = kzalloc(sizeof(struct nf_conntrack_helper), GFP_KERNEL);
- if (helper == NULL)
+ nfcth = kzalloc(sizeof(*nfcth), GFP_KERNEL);
+ if (nfcth == NULL)
return -ENOMEM;
+ helper = &nfcth->helper;
ret = nfnl_cthelper_parse_expect_policy(helper, tb[NFCTH_POLICY]);
if (ret < 0)
- goto err;
+ goto err1;
strncpy(helper->name, nla_data(tb[NFCTH_NAME]), NF_CT_HELPER_NAME_LEN);
helper->data_len = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
ret = nf_conntrack_helper_register(helper);
if (ret < 0)
- goto err;
+ goto err2;
+ list_add_tail(&nfcth->list, &nfnl_cthelper_list);
return 0;
-err:
- kfree(helper);
+err2:
+ kfree(helper->expect_policy);
+err1:
+ kfree(nfcth);
return ret;
}
+static int
+nfnl_cthelper_update_policy_one(const struct nf_conntrack_expect_policy *policy,
+ struct nf_conntrack_expect_policy *new_policy,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_POLICY_MAX + 1];
+ int err;
+
+ err = nla_parse_nested(tb, NFCTH_POLICY_MAX, attr,
+ nfnl_cthelper_expect_pol);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFCTH_POLICY_NAME] ||
+ !tb[NFCTH_POLICY_EXPECT_MAX] ||
+ !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
+ return -EINVAL;
+
+ if (nla_strcmp(tb[NFCTH_POLICY_NAME], policy->name))
+ return -EBUSY;
+
+ new_policy->max_expected =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
+ new_policy->timeout =
+ ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_TIMEOUT]));
+
+ return 0;
+}
+
+static int nfnl_cthelper_update_policy_all(struct nlattr *tb[],
+ struct nf_conntrack_helper *helper)
+{
+ struct nf_conntrack_expect_policy new_policy[helper->expect_class_max + 1];
+ struct nf_conntrack_expect_policy *policy;
+ int i, err;
+
+ /* Check first that all policy attributes are well-formed, so we don't
+ * leave things in inconsistent state on errors.
+ */
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
+
+ if (!tb[NFCTH_POLICY_SET + i])
+ return -EINVAL;
+
+ err = nfnl_cthelper_update_policy_one(&helper->expect_policy[i],
+ &new_policy[i],
+ tb[NFCTH_POLICY_SET + i]);
+ if (err < 0)
+ return err;
+ }
+ /* Now we can safely update them. */
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
+ policy = (struct nf_conntrack_expect_policy *)
+ &helper->expect_policy[i];
+ policy->max_expected = new_policy->max_expected;
+ policy->timeout = new_policy->timeout;
+ }
+
+ return 0;
+}
+
+static int nfnl_cthelper_update_policy(struct nf_conntrack_helper *helper,
+ const struct nlattr *attr)
+{
+ struct nlattr *tb[NFCTH_POLICY_SET_MAX + 1];
+ unsigned int class_max;
+ int err;
+
+ err = nla_parse_nested(tb, NFCTH_POLICY_SET_MAX, attr,
+ nfnl_cthelper_expect_policy_set);
+ if (err < 0)
+ return err;
+
+ if (!tb[NFCTH_POLICY_SET_NUM])
+ return -EINVAL;
+
+ class_max = ntohl(nla_get_be32(tb[NFCTH_POLICY_SET_NUM]));
+ if (helper->expect_class_max + 1 != class_max)
+ return -EBUSY;
+
+ return nfnl_cthelper_update_policy_all(tb, helper);
+}
+
static int
nfnl_cthelper_update(const struct nlattr * const tb[],
struct nf_conntrack_helper *helper)
return -EBUSY;
if (tb[NFCTH_POLICY]) {
- ret = nfnl_cthelper_parse_expect_policy(helper,
- tb[NFCTH_POLICY]);
+ ret = nfnl_cthelper_update_policy(helper, tb[NFCTH_POLICY]);
if (ret < 0)
return ret;
}
const char *helper_name;
struct nf_conntrack_helper *cur, *helper = NULL;
struct nf_conntrack_tuple tuple;
- int ret = 0, i;
+ struct nfnl_cthelper *nlcth;
+ int ret = 0;
if (!tb[NFCTH_NAME] || !tb[NFCTH_TUPLE])
return -EINVAL;
if (ret < 0)
return ret;
- rcu_read_lock();
- for (i = 0; i < nf_ct_helper_hsize && !helper; i++) {
- hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+ list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ if (strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- if (strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0)
- continue;
+ if ((tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- if ((tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
+ if (nlh->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
- if (nlh->nlmsg_flags & NLM_F_EXCL) {
- ret = -EEXIST;
- goto err;
- }
- helper = cur;
- break;
- }
+ helper = cur;
+ break;
}
- rcu_read_unlock();
if (helper == NULL)
ret = nfnl_cthelper_create(tb, &tuple);
ret = nfnl_cthelper_update(tb, helper);
return ret;
-err:
- rcu_read_unlock();
- return ret;
}
static int
goto nla_put_failure;
if (nla_put_be32(skb, NFCTH_POLICY_SET_NUM,
- htonl(helper->expect_class_max)))
+ htonl(helper->expect_class_max + 1)))
goto nla_put_failure;
- for (i=0; i<helper->expect_class_max; i++) {
+ for (i = 0; i < helper->expect_class_max + 1; i++) {
nest_parms2 = nla_nest_start(skb,
(NFCTH_POLICY_SET+i) | NLA_F_NESTED);
if (nest_parms2 == NULL)
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const tb[])
{
- int ret = -ENOENT, i;
+ int ret = -ENOENT;
struct nf_conntrack_helper *cur;
struct sk_buff *skb2;
char *helper_name = NULL;
struct nf_conntrack_tuple tuple;
+ struct nfnl_cthelper *nlcth;
bool tuple_set = false;
if (nlh->nlmsg_flags & NLM_F_DUMP) {
tuple_set = true;
}
- for (i = 0; i < nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_rcu(cur, &nf_ct_helper_hash[i], hnode) {
+ list_for_each_entry(nlcth, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
+ if (helper_name &&
+ strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- if (helper_name && strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0) {
- continue;
- }
- if (tuple_set &&
- (tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
-
- skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
- if (skb2 == NULL) {
- ret = -ENOMEM;
- break;
- }
+ skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (skb2 == NULL) {
+ ret = -ENOMEM;
+ break;
+ }
- ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq,
- NFNL_MSG_TYPE(nlh->nlmsg_type),
- NFNL_MSG_CTHELPER_NEW, cur);
- if (ret <= 0) {
- kfree_skb(skb2);
- break;
- }
+ ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq,
+ NFNL_MSG_TYPE(nlh->nlmsg_type),
+ NFNL_MSG_CTHELPER_NEW, cur);
+ if (ret <= 0) {
+ kfree_skb(skb2);
+ break;
+ }
- ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
- MSG_DONTWAIT);
- if (ret > 0)
- ret = 0;
+ ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid,
+ MSG_DONTWAIT);
+ if (ret > 0)
+ ret = 0;
- /* this avoids a loop in nfnetlink. */
- return ret == -EAGAIN ? -ENOBUFS : ret;
- }
+ /* this avoids a loop in nfnetlink. */
+ return ret == -EAGAIN ? -ENOBUFS : ret;
}
return ret;
}
{
char *helper_name = NULL;
struct nf_conntrack_helper *cur;
- struct hlist_node *tmp;
struct nf_conntrack_tuple tuple;
bool tuple_set = false, found = false;
- int i, j = 0, ret;
+ struct nfnl_cthelper *nlcth, *n;
+ int j = 0, ret;
if (tb[NFCTH_NAME])
helper_name = nla_data(tb[NFCTH_NAME]);
tuple_set = true;
}
- for (i = 0; i < nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
- hnode) {
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
+ j++;
- j++;
+ if (helper_name &&
+ strncmp(cur->name, helper_name, NF_CT_HELPER_NAME_LEN))
+ continue;
- if (helper_name && strncmp(cur->name, helper_name,
- NF_CT_HELPER_NAME_LEN) != 0) {
- continue;
- }
- if (tuple_set &&
- (tuple.src.l3num != cur->tuple.src.l3num ||
- tuple.dst.protonum != cur->tuple.dst.protonum))
- continue;
+ if (tuple_set &&
+ (tuple.src.l3num != cur->tuple.src.l3num ||
+ tuple.dst.protonum != cur->tuple.dst.protonum))
+ continue;
- found = true;
- nf_conntrack_helper_unregister(cur);
- }
+ found = true;
+ nf_conntrack_helper_unregister(cur);
+ kfree(cur->expect_policy);
+
+ list_del(&nlcth->list);
+ kfree(nlcth);
}
+
/* Make sure we return success if we flush and there is no helpers */
return (found || j == 0) ? 0 : -ENOENT;
}
static void __exit nfnl_cthelper_exit(void)
{
struct nf_conntrack_helper *cur;
- struct hlist_node *tmp;
- int i;
+ struct nfnl_cthelper *nlcth, *n;
nfnetlink_subsys_unregister(&nfnl_cthelper_subsys);
- for (i=0; i<nf_ct_helper_hsize; i++) {
- hlist_for_each_entry_safe(cur, tmp, &nf_ct_helper_hash[i],
- hnode) {
- /* skip non-userspace conntrack helpers. */
- if (!(cur->flags & NF_CT_HELPER_F_USERSPACE))
- continue;
+ list_for_each_entry_safe(nlcth, n, &nfnl_cthelper_list, list) {
+ cur = &nlcth->helper;
- nf_conntrack_helper_unregister(cur);
- }
+ nf_conntrack_helper_unregister(cur);
+ kfree(cur->expect_policy);
+ kfree(nlcth);
}
}
#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL);
RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL);
+ synchronize_rcu();
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
- rcu_barrier();
}
module_init(cttimeout_init);
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb) {
skb_tx_error(entskb);
- return NULL;
+ goto nlmsg_failure;
}
nlh = nlmsg_put(skb, 0, 0,
if (!nlh) {
skb_tx_error(entskb);
kfree_skb(skb);
- return NULL;
+ goto nlmsg_failure;
}
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = entry->state.pf;
}
nlh->nlmsg_len = skb->len;
+ if (seclen)
+ security_release_secctx(secdata, seclen);
return skb;
nla_put_failure:
skb_tx_error(entskb);
kfree_skb(skb);
net_err_ratelimited("nf_queue: error creating packet message\n");
+nlmsg_failure:
+ if (seclen)
+ security_release_secctx(secdata, seclen);
return NULL;
}
*/
if (nf_ct_is_confirmed(ct))
nf_ct_delete(ct, 0, 0);
- else
- nf_conntrack_put(&ct->ct_general);
+
+ nf_conntrack_put(&ct->ct_general);
nf_ct_set(skb, NULL, 0);
return false;
}
/* Link layer. */
clear_vlan(key);
- if (key->mac_proto == MAC_PROTO_NONE) {
+ if (ovs_key_mac_proto(key) == MAC_PROTO_NONE) {
if (unlikely(eth_type_vlan(skb->protocol)))
return -EINVAL;
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
{
- return key_extract(skb, key);
+ int res;
+
+ res = key_extract(skb, key);
+ if (!res)
+ key->mac_proto &= ~SW_FLOW_KEY_INVALID;
+
+ return res;
}
static int key_extract_mac_proto(struct sk_buff *skb)
return -EBUSY;
if (copy_from_user(&val, optval, sizeof(val)))
return -EFAULT;
+ if (val > INT_MAX)
+ return -EINVAL;
po->tp_reserve = val;
return 0;
}
if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
goto out;
if (po->tp_version >= TPACKET_V3 &&
- (int)(req->tp_block_size -
- BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+ req->tp_block_size <=
+ BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
goto out;
if (unlikely(req->tp_frame_size < po->tp_hdrlen +
po->tp_reserve))
rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
if (unlikely(rb->frames_per_block == 0))
goto out;
+ if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+ goto out;
if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
req->tp_frame_nr))
goto out;
if (!sctp_ulpq_init(&asoc->ulpq, asoc))
goto fail_init;
+ if (sctp_stream_new(asoc, gfp))
+ goto fail_init;
+
/* Assume that peer would support both address types unless we are
* told otherwise.
*/
/* AUTH related initializations */
INIT_LIST_HEAD(&asoc->endpoint_shared_keys);
if (sctp_auth_asoc_copy_shkeys(ep, asoc, gfp))
- goto fail_init;
+ goto stream_free;
asoc->active_key_id = ep->active_key_id;
asoc->prsctp_enable = ep->prsctp_enable;
return asoc;
+stream_free:
+ sctp_stream_free(asoc->stream);
fail_init:
sock_put(asoc->base.sk);
sctp_endpoint_put(asoc->ep);
/* Update the association's pmtu and frag_point by going through all the
* transports. This routine is called when a transport's PMTU has changed.
*/
-void sctp_assoc_sync_pmtu(struct sock *sk, struct sctp_association *asoc)
+void sctp_assoc_sync_pmtu(struct sctp_association *asoc)
{
struct sctp_transport *t;
__u32 pmtu = 0;
list_for_each_entry(t, &asoc->peer.transport_addr_list,
transports) {
if (t->pmtu_pending && t->dst) {
- sctp_transport_update_pmtu(sk, t,
- SCTP_TRUNC4(dst_mtu(t->dst)));
+ sctp_transport_update_pmtu(
+ t, SCTP_TRUNC4(dst_mtu(t->dst)));
t->pmtu_pending = 0;
}
if (!pmtu || (t->pathmtu < pmtu))
if (t->param_flags & SPP_PMTUD_ENABLE) {
/* Update transports view of the MTU */
- sctp_transport_update_pmtu(sk, t, pmtu);
+ sctp_transport_update_pmtu(t, pmtu);
/* Update association pmtu. */
- sctp_assoc_sync_pmtu(sk, asoc);
+ sctp_assoc_sync_pmtu(asoc);
}
/* Retransmit with the new pmtu setting.
{
struct sctp_transport *tp = packet->transport;
struct sctp_association *asoc = tp->asoc;
+ struct sock *sk;
pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag);
-
packet->vtag = vtag;
- if (asoc && tp->dst) {
- struct sock *sk = asoc->base.sk;
-
- rcu_read_lock();
- if (__sk_dst_get(sk) != tp->dst) {
- dst_hold(tp->dst);
- sk_setup_caps(sk, tp->dst);
- }
-
- if (sk_can_gso(sk)) {
- struct net_device *dev = tp->dst->dev;
+ /* do the following jobs only once for a flush schedule */
+ if (!sctp_packet_empty(packet))
+ return;
- packet->max_size = dev->gso_max_size;
- } else {
- packet->max_size = asoc->pathmtu;
- }
- rcu_read_unlock();
+ /* set packet max_size with pathmtu */
+ packet->max_size = tp->pathmtu;
+ if (!asoc)
+ return;
- } else {
- packet->max_size = tp->pathmtu;
+ /* update dst or transport pathmtu if in need */
+ sk = asoc->base.sk;
+ if (!sctp_transport_dst_check(tp)) {
+ sctp_transport_route(tp, NULL, sctp_sk(sk));
+ if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(asoc);
+ } else if (!sctp_transport_pmtu_check(tp)) {
+ if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ sctp_assoc_sync_pmtu(asoc);
}
- if (ecn_capable && sctp_packet_empty(packet)) {
- struct sctp_chunk *chunk;
+ /* If there a is a prepend chunk stick it on the list before
+ * any other chunks get appended.
+ */
+ if (ecn_capable) {
+ struct sctp_chunk *chunk = sctp_get_ecne_prepend(asoc);
- /* If there a is a prepend chunk stick it on the list before
- * any other chunks get appended.
- */
- chunk = sctp_get_ecne_prepend(asoc);
if (chunk)
sctp_packet_append_chunk(packet, chunk);
}
+
+ if (!tp->dst)
+ return;
+
+ /* set packet max_size with gso_max_size if gso is enabled*/
+ rcu_read_lock();
+ if (__sk_dst_get(sk) != tp->dst) {
+ dst_hold(tp->dst);
+ sk_setup_caps(sk, tp->dst);
+ }
+ packet->max_size = sk_can_gso(sk) ? tp->dst->dev->gso_max_size
+ : asoc->pathmtu;
+ rcu_read_unlock();
}
/* Initialize the packet structure. */
sh->vtag = htonl(packet->vtag);
sh->checksum = 0;
- /* update dst if in need */
- if (!sctp_transport_dst_check(tp)) {
- sctp_transport_route(tp, NULL, sctp_sk(sk));
- if (asoc && asoc->param_flags & SPP_PMTUD_ENABLE)
- sctp_assoc_sync_pmtu(sk, asoc);
- }
+ /* drop packet if no dst */
dst = dst_clone(tp->dst);
if (!dst) {
IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
*/
if ((sctp_sk(asoc->base.sk)->nodelay || inflight == 0) &&
- !chunk->msg->force_delay)
+ !asoc->force_delay)
/* Nothing unacked */
return SCTP_XMIT_OK;
/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
* stream identifier.
*/
- if (chunk->sinfo.sinfo_stream >=
- asoc->c.sinit_num_ostreams) {
+ if (chunk->sinfo.sinfo_stream >= asoc->stream->outcnt) {
/* Mark as failed send. */
sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
sctp_seq_dump_remote_addrs(seq, assoc);
seq_printf(seq, "\t%8lu %5d %5d %4d %4d %4d %8d "
"%8d %8d %8d %8d",
- assoc->hbinterval, assoc->c.sinit_max_instreams,
- assoc->c.sinit_num_ostreams, assoc->max_retrans,
+ assoc->hbinterval, assoc->stream->incnt,
+ assoc->stream->outcnt, assoc->max_retrans,
assoc->init_retries, assoc->shutdown_retries,
assoc->rtx_data_chunks,
atomic_read(&sk->sk_wmem_alloc),
* association.
*/
if (!asoc->temp) {
- int error;
-
- asoc->stream = sctp_stream_new(asoc->c.sinit_max_instreams,
- asoc->c.sinit_num_ostreams, gfp);
- if (!asoc->stream)
+ if (sctp_stream_init(asoc, gfp))
goto clean_up;
- error = sctp_assoc_set_id(asoc, gfp);
- if (error)
+ if (sctp_assoc_set_id(asoc, gfp))
goto clean_up;
}
/* Silently discard the chunk if stream-id is not valid */
sctp_walk_fwdtsn(skip, chunk) {
- if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+ if (ntohs(skip->stream) >= asoc->stream->incnt)
goto discard_noforce;
}
/* Silently discard the chunk if stream-id is not valid */
sctp_walk_fwdtsn(skip, chunk) {
- if (ntohs(skip->stream) >= asoc->c.sinit_max_instreams)
+ if (ntohs(skip->stream) >= asoc->stream->incnt)
goto gen_shutdown;
}
* and discard the DATA chunk.
*/
sid = ntohs(data_hdr->stream);
- if (sid >= asoc->c.sinit_max_instreams) {
+ if (sid >= asoc->stream->incnt) {
/* Mark tsn as received even though we drop it */
sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn));
}
if (asoc->pmtu_pending)
- sctp_assoc_pending_pmtu(sk, asoc);
+ sctp_assoc_pending_pmtu(asoc);
/* If fragmentation is disabled and the message length exceeds the
* association fragmentation point, return EMSGSIZE. The I-D
}
/* Check for invalid stream. */
- if (sinfo->sinfo_stream >= asoc->c.sinit_num_ostreams) {
+ if (sinfo->sinfo_stream >= asoc->stream->outcnt) {
err = -EINVAL;
goto out_free;
}
err = PTR_ERR(datamsg);
goto out_free;
}
- datamsg->force_delay = !!(msg->msg_flags & MSG_MORE);
+ asoc->force_delay = !!(msg->msg_flags & MSG_MORE);
/* Now send the (possibly) fragmented message. */
list_for_each_entry(chunk, &datamsg->chunks, frag_list) {
if ((params->spp_flags & SPP_PMTUD_DISABLE) && params->spp_pathmtu) {
if (trans) {
trans->pathmtu = params->spp_pathmtu;
- sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+ sctp_assoc_sync_pmtu(asoc);
} else if (asoc) {
asoc->pathmtu = params->spp_pathmtu;
} else {
(trans->param_flags & ~SPP_PMTUD) | pmtud_change;
if (update) {
sctp_transport_pmtu(trans, sctp_opt2sk(sp));
- sctp_assoc_sync_pmtu(sctp_opt2sk(sp), asoc);
+ sctp_assoc_sync_pmtu(asoc);
}
} else if (asoc) {
asoc->param_flags =
info->sctpi_rwnd = asoc->a_rwnd;
info->sctpi_unackdata = asoc->unack_data;
info->sctpi_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
- info->sctpi_instrms = asoc->c.sinit_max_instreams;
- info->sctpi_outstrms = asoc->c.sinit_num_ostreams;
+ info->sctpi_instrms = asoc->stream->incnt;
+ info->sctpi_outstrms = asoc->stream->outcnt;
list_for_each(pos, &asoc->base.inqueue.in_chunk_list)
info->sctpi_inqueue++;
list_for_each(pos, &asoc->outqueue.out_chunk_list)
status.sstat_unackdata = asoc->unack_data;
status.sstat_penddata = sctp_tsnmap_pending(&asoc->peer.tsn_map);
- status.sstat_instrms = asoc->c.sinit_max_instreams;
- status.sstat_outstrms = asoc->c.sinit_num_ostreams;
+ status.sstat_instrms = asoc->stream->incnt;
+ status.sstat_outstrms = asoc->stream->outcnt;
status.sstat_fragmentation_point = asoc->frag_point;
status.sstat_primary.spinfo_assoc_id = sctp_assoc2id(transport->asoc);
memcpy(&status.sstat_primary.spinfo_address, &transport->ipaddr,
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>
-struct sctp_stream *sctp_stream_new(__u16 incnt, __u16 outcnt, gfp_t gfp)
+int sctp_stream_new(struct sctp_association *asoc, gfp_t gfp)
{
struct sctp_stream *stream;
int i;
stream = kzalloc(sizeof(*stream), gfp);
if (!stream)
- return NULL;
+ return -ENOMEM;
- stream->outcnt = outcnt;
+ stream->outcnt = asoc->c.sinit_num_ostreams;
stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
if (!stream->out) {
kfree(stream);
- return NULL;
+ return -ENOMEM;
}
for (i = 0; i < stream->outcnt; i++)
stream->out[i].state = SCTP_STREAM_OPEN;
- stream->incnt = incnt;
+ asoc->stream = stream;
+
+ return 0;
+}
+
+int sctp_stream_init(struct sctp_association *asoc, gfp_t gfp)
+{
+ struct sctp_stream *stream = asoc->stream;
+ int i;
+
+ /* Initial stream->out size may be very big, so free it and alloc
+ * a new one with new outcnt to save memory.
+ */
+ kfree(stream->out);
+ stream->outcnt = asoc->c.sinit_num_ostreams;
+ stream->out = kcalloc(stream->outcnt, sizeof(*stream->out), gfp);
+ if (!stream->out)
+ goto nomem;
+
+ for (i = 0; i < stream->outcnt; i++)
+ stream->out[i].state = SCTP_STREAM_OPEN;
+
+ stream->incnt = asoc->c.sinit_max_instreams;
stream->in = kcalloc(stream->incnt, sizeof(*stream->in), gfp);
if (!stream->in) {
kfree(stream->out);
- kfree(stream);
- return NULL;
+ goto nomem;
}
- return stream;
+ return 0;
+
+nomem:
+ asoc->stream = NULL;
+ kfree(stream);
+
+ return -ENOMEM;
}
void sctp_stream_free(struct sctp_stream *stream)
transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
}
-void sctp_transport_update_pmtu(struct sock *sk, struct sctp_transport *t, u32 pmtu)
+void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
{
- struct dst_entry *dst;
+ struct dst_entry *dst = sctp_transport_dst_check(t);
if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) {
pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n",
- __func__, pmtu,
- SCTP_DEFAULT_MINSEGMENT);
+ __func__, pmtu, SCTP_DEFAULT_MINSEGMENT);
/* Use default minimum segment size and disable
* pmtu discovery on this transport.
*/
t->pathmtu = pmtu;
}
- dst = sctp_transport_dst_check(t);
- if (!dst)
- t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
-
if (dst) {
- dst->ops->update_pmtu(dst, sk, NULL, pmtu);
-
+ dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu);
dst = sctp_transport_dst_check(t);
- if (!dst)
- t->af_specific->get_dst(t, &t->saddr, &t->fl, sk);
}
+
+ if (!dst)
+ t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk);
}
/* Caches the dst entry and source address for a transport's destination
/* Age scan results with time spent in suspend */
cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at);
- if (rdev->ops->resume) {
- rtnl_lock();
- if (rdev->wiphy.registered)
- ret = rdev_resume(rdev);
- rtnl_unlock();
- }
+ rtnl_lock();
+ if (rdev->wiphy.registered && rdev->ops->resume)
+ ret = rdev_resume(rdev);
+ rtnl_unlock();
return ret;
}
if (stx->stx_mask & STATX_BTIME)
print_time(" Birth: ", &stx->stx_btime);
- if (stx->stx_attributes) {
- unsigned char bits;
+ if (stx->stx_attributes_mask) {
+ unsigned char bits, mbits;
int loop, byte;
static char attr_representation[64 + 1] =
printf("Attributes: %016llx (", stx->stx_attributes);
for (byte = 64 - 8; byte >= 0; byte -= 8) {
bits = stx->stx_attributes >> byte;
+ mbits = stx->stx_attributes_mask >> byte;
for (loop = 7; loop >= 0; loop--) {
int bit = byte + loop;
- if (bits & 0x80)
+ if (!(mbits & 0x80))
+ putchar('.'); /* Not supported */
+ else if (bits & 0x80)
putchar(attr_representation[63 - bit]);
else
- putchar('-');
+ putchar('-'); /* Not set */
bits <<= 1;
+ mbits <<= 1;
}
if (byte)
putchar(' ');
# $(call addtree,-I$(obj)) locates .h files in srctree, from generated .c files
# and locates generated .h files
# FIXME: Replace both with specific CFLAGS* statements in the makefiles
-__c_flags = $(if $(obj),-I$(srctree)/$(src) -I$(obj)) \
+__c_flags = $(if $(obj),$(call addtree,-I$(src)) -I$(obj)) \
$(call flags,_c_flags)
__a_flags = $(call flags,_a_flags)
__cpp_flags = $(call flags,_cpp_flags)
current = menu;
display_tree_part();
gtk_widget_set_sensitive(back_btn, TRUE);
- } else if ((col == COL_OPTION)) {
+ } else if (col == COL_OPTION) {
toggle_sym_value(menu);
gtk_tree_view_expand_row(view, path, TRUE);
}
.off = OFF, \
.imm = 0 })
+/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
+
+#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \
+ .dst_reg = DST, \
+ .src_reg = SRC, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
LIBDIR := ../../../lib
BPFDIR := $(LIBDIR)/bpf
+APIDIR := ../../../include/uapi
+GENDIR := ../../../../include/generated
+GENHDR := $(GENDIR)/autoconf.h
-CFLAGS += -Wall -O2 -I../../../include/uapi -I$(LIBDIR)
+ifneq ($(wildcard $(GENHDR)),)
+ GENFLAGS := -DHAVE_GENHDR
+endif
+
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS)
LDLIBS += -lcap
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map
#include <bpf/bpf.h>
+#ifdef HAVE_GENHDR
+# include "autoconf.h"
+#else
+# if defined(__i386) || defined(__x86_64) || defined(__s390x__) || defined(__aarch64__)
+# define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS 1
+# endif
+#endif
+
#include "../../../include/linux/filter.h"
#ifndef ARRAY_SIZE
#define MAX_INSNS 512
#define MAX_FIXUPS 8
+#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0)
+
struct bpf_test {
const char *descr;
struct bpf_insn insns[MAX_INSNS];
REJECT
} result, result_unpriv;
enum bpf_prog_type prog_type;
+ uint8_t flags;
};
/* Note we want this to be 64 bit aligned so that the end of our array is
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
+ {
+ "direct packet access: test15 (spill with xadd)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_5, 4096),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ BPF_STX_XADD(BPF_DW, BPF_REG_4, BPF_REG_5, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_2, BPF_REG_5, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R2 invalid mem access 'inv'",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ },
{
"helper access to packet: test1, valid packet_ptr range",
.insns = {
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"valid map access into an array with a variable",
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"valid map access into an array with a signed variable",
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
.result = ACCEPT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a constant",
.errstr = "R0 min value is outside of the array range",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a variable",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with no floor check",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a invalid max check",
.errstr = "invalid access to map value, value_size=48 off=44 size=8",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid map access into an array with a invalid max check",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result_unpriv = REJECT,
.result = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"multiple registers share map_lookup_elem result",
.result = REJECT,
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"constant register |= constant should keep constant type",
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_LWT_XMIT,
},
+ {
+ "overlapping checks for direct packet access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_2, 6),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_LWT_XMIT,
+ },
{
"invalid access of tc_classid for LWT_IN",
.insns = {
.result_unpriv = REJECT,
},
{
- "map element value (adjusted) is preserved across register spilling",
+ "map element value or null is marked on register spilling",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -152),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_1, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_3, 0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 leaks addr",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value store of cleared call register",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R1 !read_ok",
+ .errstr = "R1 !read_ok",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value with unaligned store",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 17),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 43),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, -2, 44),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 32),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 2, 33),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, -2, 34),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 5),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 0, 22),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, 4, 23),
+ BPF_ST_MEM(BPF_DW, BPF_REG_8, -7, 24),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 3),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 0, 22),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, 4, 23),
+ BPF_ST_MEM(BPF_DW, BPF_REG_7, -4, 24),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ },
+ {
+ "map element value with unaligned load",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JGE, BPF_REG_1, MAX_ENTRIES, 9),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 3),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 2),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_8, 2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 5),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 4),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+ },
+ {
+ "map element value illegal alu op, 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 3",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_IMM(BPF_DIV, BPF_REG_0, 42),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ENDIAN(BPF_FROM_BE, BPF_REG_0, 64),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 pointer arithmetic prohibited",
+ .errstr = "invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value illegal alu op, 5",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_MOV64_IMM(BPF_REG_3, 4096),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+ BPF_STX_XADD(BPF_DW, BPF_REG_2, BPF_REG_3, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 22),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 3 },
+ .errstr_unpriv = "R0 invalid mem access 'inv'",
+ .errstr = "R0 invalid mem access 'inv'",
+ .result = REJECT,
+ .result_unpriv = REJECT,
+ },
+ {
+ "map element value is preserved across register spilling",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
.errstr_unpriv = "R0 pointer arithmetic prohibited",
.result = ACCEPT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"helper access to variable memory: stack, bitwise AND + JMP, correct bounds",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result = REJECT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid range check",
.errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.",
.result = REJECT,
.result_unpriv = REJECT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
}
};
static void do_test_single(struct bpf_test *test, bool unpriv,
int *passes, int *errors)
{
+ int fd_prog, expected_ret, reject_from_alignment;
struct bpf_insn *prog = test->insns;
int prog_len = probe_filter_length(prog);
int prog_type = test->prog_type;
int fd_f1 = -1, fd_f2 = -1, fd_f3 = -1;
- int fd_prog, expected_ret;
const char *expected_err;
do_test_fixup(test, prog, &fd_f1, &fd_f2, &fd_f3);
test->result_unpriv : test->result;
expected_err = unpriv && test->errstr_unpriv ?
test->errstr_unpriv : test->errstr;
+
+ reject_from_alignment = fd_prog < 0 &&
+ (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
+ strstr(bpf_vlog, "Unknown alignment.");
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ if (reject_from_alignment) {
+ printf("FAIL\nFailed due to alignment despite having efficient unaligned access: '%s'!\n",
+ strerror(errno));
+ goto fail_log;
+ }
+#endif
if (expected_ret == ACCEPT) {
- if (fd_prog < 0) {
+ if (fd_prog < 0 && !reject_from_alignment) {
printf("FAIL\nFailed to load prog '%s'!\n",
strerror(errno));
goto fail_log;
printf("FAIL\nUnexpected success to load!\n");
goto fail_log;
}
- if (!strstr(bpf_vlog, expected_err)) {
+ if (!strstr(bpf_vlog, expected_err) && !reject_from_alignment) {
printf("FAIL\nUnexpected error message!\n");
goto fail_log;
}
}
(*passes)++;
- printf("OK\n");
+ printf("OK%s\n", reject_from_alignment ?
+ " (NOTE: reject due to unknown alignment)" : "");
close_fds:
close(fd_prog);
close(fd_f1);
all: $(SUB_DIRS)
$(SUB_DIRS):
- BUILD_TARGET=$$OUTPUT/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
+ BUILD_TARGET=$(OUTPUT)/$@; mkdir -p $$BUILD_TARGET; $(MAKE) OUTPUT=$$BUILD_TARGET -k -C $@ all
include ../lib.mk
override define RUN_TESTS
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
done;
endef
override define INSTALL_RULE
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET install;\
done;
endef
override define EMIT_TESTS
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -s -C $$TARGET emit_tests;\
done;
endef
clean:
@for TARGET in $(SUB_DIRS); do \
- BUILD_TARGET=$$OUTPUT/$$TARGET; \
+ BUILD_TARGET=$(OUTPUT)/$$TARGET; \
$(MAKE) OUTPUT=$$BUILD_TARGET -C $$TARGET clean; \
done;
rm -f tags
return IRQ_HANDLED;
}
+/**
+ * kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
+ *
+ * For a specific CPU, initialize the GIC VE hardware.
+ */
+void kvm_vgic_init_cpu_hardware(void)
+{
+ BUG_ON(preemptible());
+
+ /*
+ * We want to make sure the list registers start out clear so that we
+ * only have the program the used registers.
+ */
+ if (kvm_vgic_global_state.type == VGIC_V2)
+ vgic_v2_init_lrs();
+ else
+ kvm_call_hyp(__vgic_v3_init_lrs);
+}
+
/**
* kvm_vgic_hyp_init: populates the kvm_vgic_global_state variable
* according to the host GIC model. Accordingly calls either
val = vmcr.ctlr;
break;
case GIC_CPU_PRIMASK:
- val = vmcr.pmr;
+ /*
+ * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+ * the PMR field as GICH_VMCR.VMPriMask rather than
+ * GICC_PMR.Priority, so we expose the upper five bits of
+ * priority mask to userspace using the lower bits in the
+ * unsigned long.
+ */
+ val = (vmcr.pmr & GICV_PMR_PRIORITY_MASK) >>
+ GICV_PMR_PRIORITY_SHIFT;
break;
case GIC_CPU_BINPOINT:
val = vmcr.bpr;
vmcr.ctlr = val;
break;
case GIC_CPU_PRIMASK:
- vmcr.pmr = val;
+ /*
+ * Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
+ * the PMR field as GICH_VMCR.VMPriMask rather than
+ * GICC_PMR.Priority, so we expose the upper five bits of
+ * priority mask to userspace using the lower bits in the
+ * unsigned long.
+ */
+ vmcr.pmr = (val << GICV_PMR_PRIORITY_SHIFT) &
+ GICV_PMR_PRIORITY_MASK;
break;
case GIC_CPU_BINPOINT:
vmcr.bpr = val;
return (unsigned long *)val;
}
+static inline void vgic_v2_write_lr(int lr, u32 val)
+{
+ void __iomem *base = kvm_vgic_global_state.vctrl_base;
+
+ writel_relaxed(val, base + GICH_LR0 + (lr * 4));
+}
+
+void vgic_v2_init_lrs(void)
+{
+ int i;
+
+ for (i = 0; i < kvm_vgic_global_state.nr_lr; i++)
+ vgic_v2_write_lr(i, 0);
+}
+
void vgic_v2_process_maintenance(struct kvm_vcpu *vcpu)
{
struct vgic_v2_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v2;
GICH_VMCR_ALIAS_BINPOINT_MASK;
vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
GICH_VMCR_BINPOINT_MASK;
- vmcr |= (vmcrp->pmr << GICH_VMCR_PRIMASK_SHIFT) &
- GICH_VMCR_PRIMASK_MASK;
+ vmcr |= ((vmcrp->pmr >> GICV_PMR_PRIORITY_SHIFT) <<
+ GICH_VMCR_PRIMASK_SHIFT) & GICH_VMCR_PRIMASK_MASK;
vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = vmcr;
}
GICH_VMCR_ALIAS_BINPOINT_SHIFT;
vmcrp->bpr = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
GICH_VMCR_BINPOINT_SHIFT;
- vmcrp->pmr = (vmcr & GICH_VMCR_PRIMASK_MASK) >>
- GICH_VMCR_PRIMASK_SHIFT;
+ vmcrp->pmr = ((vmcr & GICH_VMCR_PRIMASK_MASK) >>
+ GICH_VMCR_PRIMASK_SHIFT) << GICV_PMR_PRIORITY_SHIFT;
}
void vgic_v2_enable(struct kvm_vcpu *vcpu)
return irq->pending_latch || irq->line_level;
}
+/*
+ * This struct provides an intermediate representation of the fields contained
+ * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC
+ * state to userspace can generate either GICv2 or GICv3 CPU interface
+ * registers regardless of the hardware backed GIC used.
+ */
struct vgic_vmcr {
u32 ctlr;
u32 abpr;
u32 bpr;
- u32 pmr;
+ u32 pmr; /* Priority mask field in the GICC_PMR and
+ * ICC_PMR_EL1 priority field format */
/* Below member variable are valid only for GICv3 */
u32 grpen0;
u32 grpen1;
int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
enum vgic_type);
+void vgic_v2_init_lrs(void);
+
static inline void vgic_get_irq_kref(struct vgic_irq *irq)
{
if (irq->intid < VGIC_MIN_LPI)
git.samba.org / sfrench / cifs-2.6.git / commitdiff