- 'apei_estatus_for_each_section'
- 'ata_for_each_dev'
- 'ata_for_each_link'
+ - '__ata_qc_for_each'
+ - 'ata_qc_for_each'
+ - 'ata_qc_for_each_raw'
+ - 'ata_qc_for_each_with_internal'
- 'ax25_for_each'
- 'ax25_uid_for_each'
- 'bio_for_each_integrity_vec'
- 'blk_queue_for_each_rl'
- 'bond_for_each_slave'
- 'bond_for_each_slave_rcu'
+ - 'bpf_for_each_spilled_reg'
- 'btree_for_each_safe128'
- 'btree_for_each_safe32'
- 'btree_for_each_safe64'
- 'drm_atomic_crtc_for_each_plane'
- 'drm_atomic_crtc_state_for_each_plane'
- 'drm_atomic_crtc_state_for_each_plane_state'
+ - 'drm_atomic_for_each_plane_damage'
+ - 'drm_connector_for_each_possible_encoder'
- 'drm_for_each_connector_iter'
- 'drm_for_each_crtc'
- 'drm_for_each_encoder'
- 'for_each_bio'
- 'for_each_board_func_rsrc'
- 'for_each_bvec'
+ - 'for_each_card_components'
+ - 'for_each_card_links'
+ - 'for_each_card_links_safe'
+ - 'for_each_card_prelinks'
+ - 'for_each_card_rtds'
+ - 'for_each_card_rtds_safe'
+ - 'for_each_cgroup_storage_type'
- 'for_each_child_of_node'
- 'for_each_clear_bit'
- 'for_each_clear_bit_from'
- 'for_each_cmsghdr'
- 'for_each_compatible_node'
+ - 'for_each_component_dais'
+ - 'for_each_component_dais_safe'
+ - 'for_each_comp_order'
- 'for_each_console'
- 'for_each_cpu'
- 'for_each_cpu_and'
- 'for_each_cpu_wrap'
- 'for_each_dev_addr'
- 'for_each_dma_cap_mask'
+ - 'for_each_dpcm_be'
+ - 'for_each_dpcm_be_rollback'
+ - 'for_each_dpcm_be_safe'
+ - 'for_each_dpcm_fe'
- 'for_each_drhd_unit'
- 'for_each_dss_dev'
- 'for_each_efi_memory_desc'
- 'for_each_iommu'
- 'for_each_ip_tunnel_rcu'
- 'for_each_irq_nr'
+ - 'for_each_link_codecs'
- 'for_each_lru'
- 'for_each_matching_node'
- 'for_each_matching_node_and_match'
- 'for_each_mem_range_rev'
- 'for_each_migratetype_order'
- 'for_each_msi_entry'
+ - 'for_each_msi_entry_safe'
- 'for_each_net'
- 'for_each_netdev'
- 'for_each_netdev_continue'
- 'for_each_node_with_property'
- 'for_each_of_allnodes'
- 'for_each_of_allnodes_from'
+ - 'for_each_of_cpu_node'
- 'for_each_of_pci_range'
- 'for_each_old_connector_in_state'
- 'for_each_old_crtc_in_state'
- 'for_each_oldnew_connector_in_state'
- 'for_each_oldnew_crtc_in_state'
- 'for_each_oldnew_plane_in_state'
+ - 'for_each_oldnew_plane_in_state_reverse'
- 'for_each_oldnew_private_obj_in_state'
- 'for_each_old_plane_in_state'
- 'for_each_old_private_obj_in_state'
- 'for_each_process'
- 'for_each_process_thread'
- 'for_each_property_of_node'
+ - 'for_each_registered_fb'
- 'for_each_reserved_mem_region'
- - 'for_each_resv_unavail_range'
+ - 'for_each_rtd_codec_dai'
+ - 'for_each_rtd_codec_dai_rollback'
- 'for_each_rtdcom'
- 'for_each_rtdcom_safe'
- 'for_each_set_bit'
- 'for_each_set_bit_from'
- 'for_each_sg'
- 'for_each_sg_page'
+ - 'for_each_sibling_event'
- '__for_each_thread'
- 'for_each_thread'
- 'for_each_zone'
- 'hlist_nulls_for_each_entry_from'
- 'hlist_nulls_for_each_entry_rcu'
- 'hlist_nulls_for_each_entry_safe'
+ - 'i3c_bus_for_each_i2cdev'
+ - 'i3c_bus_for_each_i3cdev'
- 'ide_host_for_each_port'
- 'ide_port_for_each_dev'
- 'ide_port_for_each_present_dev'
- 'kvm_for_each_memslot'
- 'kvm_for_each_vcpu'
- 'list_for_each'
+ - 'list_for_each_codec'
+ - 'list_for_each_codec_safe'
- 'list_for_each_entry'
- 'list_for_each_entry_continue'
- 'list_for_each_entry_continue_rcu'
- 'list_for_each_entry_continue_reverse'
- 'list_for_each_entry_from'
+ - 'list_for_each_entry_from_rcu'
- 'list_for_each_entry_from_reverse'
- 'list_for_each_entry_lockless'
- 'list_for_each_entry_rcu'
- 'media_device_for_each_intf'
- 'media_device_for_each_link'
- 'media_device_for_each_pad'
+ - 'nanddev_io_for_each_page'
- 'netdev_for_each_lower_dev'
- 'netdev_for_each_lower_private'
- 'netdev_for_each_lower_private_rcu'
- 'sk_nulls_for_each'
- 'sk_nulls_for_each_from'
- 'sk_nulls_for_each_rcu'
+ - 'snd_array_for_each'
- 'snd_pcm_group_for_each_entry'
- 'snd_soc_dapm_widget_for_each_path'
- 'snd_soc_dapm_widget_for_each_path_safe'
- 'snd_soc_dapm_widget_for_each_sink_path'
- 'snd_soc_dapm_widget_for_each_source_path'
- 'tb_property_for_each'
+ - 'tcf_exts_for_each_action'
- 'udp_portaddr_for_each_entry'
- 'udp_portaddr_for_each_entry_rcu'
- 'usb_hub_for_each_child'
- 'v4l2_m2m_for_each_dst_buf_safe'
- 'v4l2_m2m_for_each_src_buf'
- 'v4l2_m2m_for_each_src_buf_safe'
+ - 'virtio_device_for_each_vq'
+ - 'xa_for_each'
+ - 'xas_for_each'
+ - 'xas_for_each_conflict'
+ - 'xas_for_each_marked'
- 'zorro_for_each_dev'
#IncludeBlocks: Preserve # Unknown to clang-format-5.0
------------------------------
A: YES. BPF instructions, arguments to BPF programs, set of helper
functions and their arguments, recognized return codes are all part
-of ABI. However when tracing programs are using bpf_probe_read() helper
-to walk kernel internal datastructures and compile with kernel
-internal headers these accesses can and will break with newer
-kernels. The union bpf_attr -> kern_version is checked at load time
-to prevent accidentally loading kprobe-based bpf programs written
-for a different kernel. Networking programs don't do kern_version check.
+of ABI. However there is one specific exception to tracing programs
+which are using helpers like bpf_probe_read() to walk kernel internal
+data structures and compile with kernel internal headers. Both of these
+kernel internals are subject to change and can break with newer kernels
+such that the program needs to be adapted accordingly.
Q: How much stack space a BPF program uses?
-------------------------------------------
Sometimes you need to ensure that a subsequent call to :c:func:`xa_store`
will not need to allocate memory. The :c:func:`xa_reserve` function
-will store a reserved entry at the indicated index. Users of the normal
-API will see this entry as containing ``NULL``. If you do not need to
-use the reserved entry, you can call :c:func:`xa_release` to remove the
-unused entry. If another user has stored to the entry in the meantime,
-:c:func:`xa_release` will do nothing; if instead you want the entry to
-become ``NULL``, you should use :c:func:`xa_erase`.
+will store a reserved entry at the indicated index. Users of the
+normal API will see this entry as containing ``NULL``. If you do
+not need to use the reserved entry, you can call :c:func:`xa_release`
+to remove the unused entry. If another user has stored to the entry
+in the meantime, :c:func:`xa_release` will do nothing; if instead you
+want the entry to become ``NULL``, you should use :c:func:`xa_erase`.
+Using :c:func:`xa_insert` on a reserved entry will fail.
If all entries in the array are ``NULL``, the :c:func:`xa_empty` function
will return ``true``.
* :c:func:`xa_store_bh`
* :c:func:`xa_store_irq`
* :c:func:`xa_insert`
+ * :c:func:`xa_insert_bh`
+ * :c:func:`xa_insert_irq`
* :c:func:`xa_erase`
* :c:func:`xa_erase_bh`
* :c:func:`xa_erase_irq`
===========================================
[1] ARM Linux Kernel documentation - CPUs bindings
- Documentation/devicetree/bindings/arm/cpus.txt
+ Documentation/devicetree/bindings/arm/cpus.yaml
===========================================
[1] ARM Linux Kernel documentation - CPUs bindings
- Documentation/devicetree/bindings/arm/cpus.txt
+ Documentation/devicetree/bindings/arm/cpus.yaml
[2] ARM Linux Kernel documentation - PSCI bindings
Documentation/devicetree/bindings/arm/psci.txt
Required properties:
- compatible: standard compatible string for a Primecell peripheral,
- see Documentation/devicetree/bindings/arm/primecell.txt
+ see Documentation/devicetree/bindings/arm/primecell.yaml
for more details
should be: "arm,sp810", "arm,primecell"
===============================================================================
[1] ARM Linux kernel documentation
- Documentation/devicetree/bindings/arm/cpus.txt
+ Documentation/devicetree/bindings/arm/cpus.yaml
Each clock is assigned an identifier and client nodes use this identifier
to specify the clock which they consume.
-All these identifier could be found in <dt-bindings/clock/marvell-mmp2.h>.
+All these identifiers could be found in <dt-bindings/clock/marvell,mmp2.h>.
* ARM PrimeCell Color LCD Controller PL110/PL111
-See also Documentation/devicetree/bindings/arm/primecell.txt
+See also Documentation/devicetree/bindings/arm/primecell.yaml
Required properties:
reg = <0x04300000 0x20000>;
reg-names = "kgsl_3d0_reg_memory";
interrupts = <GIC_SPI 80 0>;
- interrupt-names = "kgsl_3d0_irq";
clock-names =
"core",
"iface",
"marvell,armada-8k-gpio" should be used for the Armada 7K and 8K
SoCs (either from AP or CP), see
- Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
- and
Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
for specific details about the offset property.
PPI affinity can be expressed as a single "ppi-partitions" node,
containing a set of sub-nodes, each with the following property:
- affinity: Should be a list of phandles to CPU nodes (as described in
-Documentation/devicetree/bindings/arm/cpus.txt).
+ Documentation/devicetree/bindings/arm/cpus.yaml).
GICv3 has one or more Interrupt Translation Services (ITS) that are
used to route Message Signalled Interrupts (MSI) to the CPUs.
= EXAMPLE
The following example represents the GLINK RPM node on a MSM8996 device, with
the function for the "rpm_request" channel defined, which is used for
-regualtors and root clocks.
+regulators and root clocks.
apcs_glb: mailbox@9820000 {
compatible = "qcom,msm8996-apcs-hmss-global";
- qcom,local-pid:
Usage: required
Value type: <u32>
- Definition: specifies the identfier of the local endpoint of this edge
+ Definition: specifies the identifier of the local endpoint of this edge
- qcom,remote-pid:
Usage: required
Value type: <u32>
- Definition: specifies the identfier of the remote endpoint of this edge
+ Definition: specifies the identifier of the remote endpoint of this edge
= SUBNODES
Each SMP2P pair contain a set of inbound and outbound entries, these are
be preserved until there actually is some text is output to the console.
This option causes fbcon to bind immediately to the fbdev device.
+7. fbcon=logo-pos:<location>
+
+ The only possible 'location' is 'center' (without quotes), and when
+ given, the bootup logo is moved from the default top-left corner
+ location to the center of the framebuffer. If more than one logo is
+ displayed due to multiple CPUs, the collected line of logos is moved
+ as a whole.
+
C. Attaching, Detaching and Unloading
Before going on to how to attach, detach and unload the framebuffer console, an
batman-adv
can
can_ucan_protocol
- dpaa2/index
- e100
- e1000
- e1000e
- fm10k
- igb
- igbvf
- ixgb
- ixgbe
- ixgbevf
- i40e
- iavf
- ice
+ device_drivers/freescale/dpaa2/index
+ device_drivers/intel/e100
+ device_drivers/intel/e1000
+ device_drivers/intel/e1000e
+ device_drivers/intel/fm10k
+ device_drivers/intel/igb
+ device_drivers/intel/igbvf
+ device_drivers/intel/ixgb
+ device_drivers/intel/ixgbe
+ device_drivers/intel/ixgbevf
+ device_drivers/intel/i40e
+ device_drivers/intel/iavf
+ device_drivers/intel/ice
kapi
z8530book
msg_zerocopy
size should be set when the call is begun. tx_total_len may not be less
than zero.
- (*) Check to see the completion state of a call so that the caller can assess
- whether it needs to be retried.
-
- enum rxrpc_call_completion {
- RXRPC_CALL_SUCCEEDED,
- RXRPC_CALL_REMOTELY_ABORTED,
- RXRPC_CALL_LOCALLY_ABORTED,
- RXRPC_CALL_LOCAL_ERROR,
- RXRPC_CALL_NETWORK_ERROR,
- };
-
- int rxrpc_kernel_check_call(struct socket *sock, struct rxrpc_call *call,
- enum rxrpc_call_completion *_compl,
- u32 *_abort_code);
-
- On return, -EINPROGRESS will be returned if the call is still ongoing; if
- it is finished, *_compl will be set to indicate the manner of completion,
- *_abort_code will be set to any abort code that occurred. 0 will be
- returned on a successful completion, -ECONNABORTED will be returned if the
- client failed due to a remote abort and anything else will return an
- appropriate error code.
-
- The caller should look at this information to decide if it's worth
- retrying the call.
-
- (*) Retry a client call.
-
- int rxrpc_kernel_retry_call(struct socket *sock,
- struct rxrpc_call *call,
- struct sockaddr_rxrpc *srx,
- struct key *key);
-
- This attempts to partially reinitialise a call and submit it again while
- reusing the original call's Tx queue to avoid the need to repackage and
- re-encrypt the data to be sent. call indicates the call to retry, srx the
- new address to send it to and key the encryption key to use for signing or
- encrypting the packets.
-
- For this to work, the first Tx data packet must still be in the transmit
- queue, and currently this is only permitted for local and network errors
- and the call must not have been aborted. Any partially constructed Tx
- packet is left as is and can continue being filled afterwards.
-
- It returns 0 if the call was requeued and an error otherwise.
-
(*) Get call RTT.
u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call);
to the accept queue.
-TCP Fast Open
+* TcpEstabResets
+Defined in `RFC1213 tcpEstabResets`_.
+
+.. _RFC1213 tcpEstabResets: https://tools.ietf.org/html/rfc1213#page-48
+
+* TcpAttemptFails
+Defined in `RFC1213 tcpAttemptFails`_.
+
+.. _RFC1213 tcpAttemptFails: https://tools.ietf.org/html/rfc1213#page-48
+
+* TcpOutRsts
+Defined in `RFC1213 tcpOutRsts`_. The RFC says this counter indicates
+the 'segments sent containing the RST flag', but in linux kernel, this
+couner indicates the segments kerenl tried to send. The sending
+process might be failed due to some errors (e.g. memory alloc failed).
+
+.. _RFC1213 tcpOutRsts: https://tools.ietf.org/html/rfc1213#page-52
+
+
+TCP Fast Path
============
When kernel receives a TCP packet, it has two paths to handler the
packet, one is fast path, another is slow path. The comment in kernel
TCP abort
========
-
-
* TcpExtTCPAbortOnData
It means TCP layer has data in flight, but need to close the
connection. So TCP layer sends a RST to the other side, indicate the
stack of kernel will increase TcpExtTCPSACKReorder for both of the
above scenarios.
-
DSACK
=====
The DSACK is defined in `RFC2883`_. The receiver uses DSACK to report
DSACK to the sender.
* TcpExtTCPDSACKRecv
-The TCP stack receives a DSACK, which indicate an acknowledged
+The TCP stack receives a DSACK, which indicates an acknowledged
duplicate packet is received.
* TcpExtTCPDSACKOfoRecv
The TCP stack receives a DSACK, which indicate an out of order
duplicate packet is received.
+invalid SACK and DSACK
+====================
+When a SACK (or DSACK) block is invalid, a corresponding counter would
+be updated. The validation method is base on the start/end sequence
+number of the SACK block. For more details, please refer the comment
+of the function tcp_is_sackblock_valid in the kernel source code. A
+SACK option could have up to 4 blocks, they are checked
+individually. E.g., if 3 blocks of a SACk is invalid, the
+corresponding counter would be updated 3 times. The comment of the
+`Add counters for discarded SACK blocks`_ patch has additional
+explaination:
+
+.. _Add counters for discarded SACK blocks: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=18f02545a9a16c9a89778b91a162ad16d510bb32
+
+* TcpExtTCPSACKDiscard
+This counter indicates how many SACK blocks are invalid. If the invalid
+SACK block is caused by ACK recording, the TCP stack will only ignore
+it and won't update this counter.
+
+* TcpExtTCPDSACKIgnoredOld and TcpExtTCPDSACKIgnoredNoUndo
+When a DSACK block is invalid, one of these two counters would be
+updated. Which counter will be updated depends on the undo_marker flag
+of the TCP socket. If the undo_marker is not set, the TCP stack isn't
+likely to re-transmit any packets, and we still receive an invalid
+DSACK block, the reason might be that the packet is duplicated in the
+middle of the network. In such scenario, TcpExtTCPDSACKIgnoredNoUndo
+will be updated. If the undo_marker is set, TcpExtTCPDSACKIgnoredOld
+will be updated. As implied in its name, it might be an old packet.
+
+SACK shift
+=========
+The linux networking stack stores data in sk_buff struct (skb for
+short). If a SACK block acrosses multiple skb, the TCP stack will try
+to re-arrange data in these skb. E.g. if a SACK block acknowledges seq
+10 to 15, skb1 has seq 10 to 13, skb2 has seq 14 to 20. The seq 14 and
+15 in skb2 would be moved to skb1. This operation is 'shift'. If a
+SACK block acknowledges seq 10 to 20, skb1 has seq 10 to 13, skb2 has
+seq 14 to 20. All data in skb2 will be moved to skb1, and skb2 will be
+discard, this operation is 'merge'.
+
+* TcpExtTCPSackShifted
+A skb is shifted
+
+* TcpExtTCPSackMerged
+A skb is merged
+
+* TcpExtTCPSackShiftFallback
+A skb should be shifted or merged, but the TCP stack doesn't do it for
+some reasons.
+
TCP out of order
===============
* TcpExtTCPOFOQueue
.. _RFC 5961 section 4.2: https://tools.ietf.org/html/rfc5961#page-9
.. _RFC 5961 section 5.2: https://tools.ietf.org/html/rfc5961#page-11
+TCP receive window
+=================
+* TcpExtTCPWantZeroWindowAdv
+Depending on current memory usage, the TCP stack tries to set receive
+window to zero. But the receive window might still be a no-zero
+value. For example, if the previous window size is 10, and the TCP
+stack receives 3 bytes, the current window size would be 7 even if the
+window size calculated by the memory usage is zero.
+
+* TcpExtTCPToZeroWindowAdv
+The TCP receive window is set to zero from a no-zero value.
+
+* TcpExtTCPFromZeroWindowAdv
+The TCP receive window is set to no-zero value from zero.
+
+
+Delayed ACK
+==========
+The TCP Delayed ACK is a technique which is used for reducing the
+packet count in the network. For more details, please refer the
+`Delayed ACK wiki`_
+
+.. _Delayed ACK wiki: https://en.wikipedia.org/wiki/TCP_delayed_acknowledgment
+
+* TcpExtDelayedACKs
+A delayed ACK timer expires. The TCP stack will send a pure ACK packet
+and exit the delayed ACK mode.
+
+* TcpExtDelayedACKLocked
+A delayed ACK timer expires, but the TCP stack can't send an ACK
+immediately due to the socket is locked by a userspace program. The
+TCP stack will send a pure ACK later (after the userspace program
+unlock the socket). When the TCP stack sends the pure ACK later, the
+TCP stack will also update TcpExtDelayedACKs and exit the delayed ACK
+mode.
+
+* TcpExtDelayedACKLost
+It will be updated when the TCP stack receives a packet which has been
+ACKed. A Delayed ACK loss might cause this issue, but it would also be
+triggered by other reasons, such as a packet is duplicated in the
+network.
+
+Tail Loss Probe (TLP)
+===================
+TLP is an algorithm which is used to detect TCP packet loss. For more
+details, please refer the `TLP paper`_.
+
+.. _TLP paper: https://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01
+
+* TcpExtTCPLossProbes
+A TLP probe packet is sent.
+
+* TcpExtTCPLossProbeRecovery
+A packet loss is detected and recovered by TLP.
examples
=======
Hardware time stamping must also be initialized for each device driver
that is expected to do hardware time stamping. The parameter is defined in
-/include/linux/net_tstamp.h as:
+include/uapi/linux/net_tstamp.h as:
struct hwtstamp_config {
int flags; /* no flags defined right now, must be zero */
HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
/* for the complete list of values, please check
- * the include file /include/linux/net_tstamp.h
+ * the include file include/uapi/linux/net_tstamp.h
*/
};
F: include/linux/bcm963xx_tag.h
BROADCOM BNX2 GIGABIT ETHERNET DRIVER
-M: Rasesh Mody <rasesh.mody@cavium.com>
-M: Dept-GELinuxNICDev@cavium.com
+M: Rasesh Mody <rmody@marvell.com>
+M: GR-Linux-NIC-Dev@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/broadcom/bnx2.*
F: drivers/scsi/bnx2i/
BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M: Ariel Elior <ariel.elior@cavium.com>
-M: Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
-M: everest-linux-l2@cavium.com
+M: Ariel Elior <aelior@marvell.com>
+M: Sudarsana Kalluru <skalluru@marvell.com>
+M: GR-everest-linux-l2@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/broadcom/bnx2x/
F: drivers/scsi/bfa/
BROCADE BNA 10 GIGABIT ETHERNET DRIVER
-M: Rasesh Mody <rasesh.mody@cavium.com>
-M: Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
-M: Dept-GELinuxNICDev@cavium.com
+M: Rasesh Mody <rmody@marvell.com>
+M: Sudarsana Kalluru <skalluru@marvell.com>
+M: GR-Linux-NIC-Dev@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/brocade/bna/
F: drivers/i2c/busses/i2c-thunderx*
CAVIUM LIQUIDIO NETWORK DRIVER
-M: Derek Chickles <derek.chickles@caviumnetworks.com>
-M: Satanand Burla <satananda.burla@caviumnetworks.com>
-M: Felix Manlunas <felix.manlunas@caviumnetworks.com>
-M: Raghu Vatsavayi <raghu.vatsavayi@caviumnetworks.com>
+M: Derek Chickles <dchickles@marvell.com>
+M: Satanand Burla <sburla@marvell.com>
+M: Felix Manlunas <fmanlunas@marvell.com>
L: netdev@vger.kernel.org
W: http://www.cavium.com
S: Supported
CPU POWER MONITORING SUBSYSTEM
M: Thomas Renninger <trenn@suse.com>
M: Shuah Khan <shuah@kernel.org>
+M: Shuah Khan <skhan@linuxfoundation.org>
L: linux-pm@vger.kernel.org
S: Maintained
F: tools/power/cpupower/
KERNEL SELFTEST FRAMEWORK
M: Shuah Khan <shuah@kernel.org>
+M: Shuah Khan <skhan@linuxfoundation.org>
L: linux-kselftest@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git
Q: https://patchwork.kernel.org/project/linux-kselftest/list/
F: drivers/net/netdevsim/*
NETXEN (1/10) GbE SUPPORT
-M: Manish Chopra <manish.chopra@cavium.com>
-M: Rahul Verma <rahul.verma@cavium.com>
-M: Dept-GELinuxNICDev@cavium.com
+M: Manish Chopra <manishc@marvell.com>
+M: Rahul Verma <rahulv@marvell.com>
+M: GR-Linux-NIC-Dev@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/netxen/
F: drivers/scsi/qedi/
QLOGIC QL4xxx ETHERNET DRIVER
-M: Ariel Elior <Ariel.Elior@cavium.com>
-M: everest-linux-l2@cavium.com
+M: Ariel Elior <aelior@marvell.com>
+M: GR-everest-linux-l2@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qed/
F: drivers/net/ethernet/qlogic/qede/
QLOGIC QL4xxx RDMA DRIVER
-M: Michal Kalderon <Michal.Kalderon@cavium.com>
-M: Ariel Elior <Ariel.Elior@cavium.com>
+M: Michal Kalderon <mkalderon@marvell.com>
+M: Ariel Elior <aelior@marvell.com>
L: linux-rdma@vger.kernel.org
S: Supported
F: drivers/infiniband/hw/qedr/
F: drivers/scsi/qla2xxx/
QLOGIC QLA3XXX NETWORK DRIVER
-M: Dept-GELinuxNICDev@cavium.com
+M: GR-Linux-NIC-Dev@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
F: drivers/scsi/qla4xxx/
QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M: Shahed Shaikh <Shahed.Shaikh@cavium.com>
-M: Manish Chopra <manish.chopra@cavium.com>
-M: Dept-GELinuxNICDev@cavium.com
+M: Shahed Shaikh <shshaikh@marvell.com>
+M: Manish Chopra <manishc@marvell.com>
+M: GR-Linux-NIC-Dev@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qlcnic/
QLOGIC QLGE 10Gb ETHERNET DRIVER
-M: Manish Chopra <manish.chopra@cavium.com>
-M: Dept-GELinuxNICDev@cavium.com
+M: Manish Chopra <manishc@marvell.com>
+M: GR-Linux-NIC-Dev@marvell.com
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/qlogic/qlge/
USB OVER IP DRIVER
M: Valentina Manea <valentina.manea.m@gmail.com>
M: Shuah Khan <shuah@kernel.org>
+M: Shuah Khan <skhan@linuxfoundation.org>
L: linux-usb@vger.kernel.org
S: Maintained
F: Documentation/usb/usbip_protocol.txt
VERSION = 5
PATCHLEVEL = 0
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
NAME = Shy Crocodile
# *DOCUMENTATION*
endif
endif
+PHONY += prepare0
ifeq ($(KBUILD_EXTMOD),)
core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ block/
# archprepare is used in arch Makefiles and when processed asm symlink,
# version.h and scripts_basic is processed / created.
-# Listed in dependency order
-PHONY += prepare archprepare prepare0 prepare1 prepare2 prepare3
+PHONY += prepare archprepare prepare1 prepare2 prepare3
# prepare3 is used to check if we are building in a separate output directory,
# and if so do:
mrproper: rm-files := $(wildcard $(MRPROPER_FILES))
mrproper-dirs := $(addprefix _mrproper_,scripts)
-PHONY += $(mrproper-dirs) mrproper archmrproper
+PHONY += $(mrproper-dirs) mrproper
$(mrproper-dirs):
$(Q)$(MAKE) $(clean)=$(patsubst _mrproper_%,%,$@)
-mrproper: clean archmrproper $(mrproper-dirs)
+mrproper: clean $(mrproper-dirs)
$(call cmd,rmdirs)
$(call cmd,rmfiles)
generic-y += compat.h
generic-y += device.h
generic-y += div64.h
-generic-y += dma-mapping.h
generic-y += emergency-restart.h
generic-y += extable.h
-generic-y += fb.h
generic-y += ftrace.h
generic-y += hardirq.h
generic-y += hw_irq.h
generic-y += irq_regs.h
generic-y += irq_work.h
-generic-y += kmap_types.h
generic-y += local.h
generic-y += local64.h
generic-y += mcs_spinlock.h
generic-y += mm-arch-hooks.h
generic-y += msi.h
generic-y += parport.h
-generic-y += pci.h
generic-y += percpu.h
generic-y += preempt.h
generic-y += topology.h
#endif
};
+struct bcr_actionpoint {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ unsigned int pad:21, min:1, num:2, ver:8;
+#else
+ unsigned int ver:8, num:2, min:1, pad:21;
+#endif
+};
+
#include <soc/arc/timers.h>
struct bcr_bpu_arcompact {
};
struct cpuinfo_arc_bpu {
- unsigned int ver, full, num_cache, num_pred;
+ unsigned int ver, full, num_cache, num_pred, ret_stk;
};
struct cpuinfo_arc_ccm {
struct {
unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
fpu_sp:1, fpu_dp:1, dual:1, dual_enb:1, pad2:4,
- debug:1, ap:1, smart:1, rtt:1, pad3:4,
+ ap_num:4, ap_full:1, smart:1, rtt:1, pad3:1,
timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
} extn;
struct bcr_mpy extn_mpy;
/*
* __ffs: Similar to ffs, but zero based (0-31)
*/
-static inline __attribute__ ((const)) int __ffs(unsigned long word)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long word)
{
if (!word)
return word;
/*
* __ffs: Similar to ffs, but zero based (0-31)
*/
-static inline __attribute__ ((const)) int __ffs(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
{
- int n;
+ unsigned long n;
asm volatile(
" ffs.f %0, %1 \n" /* 0:31; 31(Z) if src 0 */
/* counts condition */
[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
+ /* All jump instructions that are taken */
+ [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
[PERF_COUNT_ARC_BPOK] = "bpok", /* NP-NT, PT-T, PNT-NT */
#ifdef CONFIG_ISA_ARCV2
[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
-/*
- * Linux performance counter support for ARC700 series
- *
- * Copyright (C) 2013-2015 Synopsys, Inc. (www.synopsys.com)
- *
- * This code is inspired by the perf support of various other architectures.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Linux performance counter support for ARC CPUs.
+// This code is inspired by the perf support of various other architectures.
+//
+// Copyright (C) 2013-2018 Synopsys, Inc. (www.synopsys.com)
+
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <asm/arcregs.h>
#include <asm/stacktrace.h>
+/* HW holds 8 symbols + one for null terminator */
+#define ARCPMU_EVENT_NAME_LEN 9
+
+enum arc_pmu_attr_groups {
+ ARCPMU_ATTR_GR_EVENTS,
+ ARCPMU_ATTR_GR_FORMATS,
+ ARCPMU_NR_ATTR_GR
+};
+
+struct arc_pmu_raw_event_entry {
+ char name[ARCPMU_EVENT_NAME_LEN];
+};
+
struct arc_pmu {
struct pmu pmu;
unsigned int irq;
int n_counters;
+ int n_events;
u64 max_period;
int ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
+
+ struct arc_pmu_raw_event_entry *raw_entry;
+ struct attribute **attrs;
+ struct perf_pmu_events_attr *attr;
+ const struct attribute_group *attr_groups[ARCPMU_NR_ATTR_GR + 1];
};
struct arc_pmu_cpu {
{
struct arc_callchain_trace *ctrl = data;
struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
+
perf_callchain_store(entry, addr);
if (ctrl->depth++ < 3)
return -1;
}
-void
-perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+ struct pt_regs *regs)
{
struct arc_callchain_trace ctrl = {
.depth = 0,
arc_unwind_core(NULL, regs, callchain_trace, &ctrl);
}
-void
-perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+ struct pt_regs *regs)
{
/*
* User stack can't be unwound trivially with kernel dwarf unwinder
static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu);
/* read counter #idx; note that counter# != event# on ARC! */
-static uint64_t arc_pmu_read_counter(int idx)
+static u64 arc_pmu_read_counter(int idx)
{
- uint32_t tmp;
- uint64_t result;
+ u32 tmp;
+ u64 result;
/*
* ARC supports making 'snapshots' of the counters, so we don't
write_aux_reg(ARC_REG_PCT_INDEX, idx);
tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN);
- result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
+ result = (u64) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
result |= read_aux_reg(ARC_REG_PCT_SNAPL);
return result;
static void arc_perf_event_update(struct perf_event *event,
struct hw_perf_event *hwc, int idx)
{
- uint64_t prev_raw_count = local64_read(&hwc->prev_count);
- uint64_t new_raw_count = arc_pmu_read_counter(idx);
- int64_t delta = new_raw_count - prev_raw_count;
+ u64 prev_raw_count = local64_read(&hwc->prev_count);
+ u64 new_raw_count = arc_pmu_read_counter(idx);
+ s64 delta = new_raw_count - prev_raw_count;
/*
* We aren't afraid of hwc->prev_count changing beneath our feet
int ret;
if (!is_sampling_event(event)) {
- hwc->sample_period = arc_pmu->max_period;
+ hwc->sample_period = arc_pmu->max_period;
hwc->last_period = hwc->sample_period;
local64_set(&hwc->period_left, hwc->sample_period);
}
pr_debug("init cache event with h/w %08x \'%s\'\n",
(int)hwc->config, arc_pmu_ev_hw_map[ret]);
return 0;
+
+ case PERF_TYPE_RAW:
+ if (event->attr.config >= arc_pmu->n_events)
+ return -ENOENT;
+
+ hwc->config |= event->attr.config;
+ pr_debug("init raw event with idx %lld \'%s\'\n",
+ event->attr.config,
+ arc_pmu->raw_entry[event->attr.config].name);
+
+ return 0;
+
default:
return -ENOENT;
}
/* starts all counters */
static void arc_pmu_enable(struct pmu *pmu)
{
- uint32_t tmp;
+ u32 tmp;
tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1);
}
/* stops all counters */
static void arc_pmu_disable(struct pmu *pmu)
{
- uint32_t tmp;
+ u32 tmp;
tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0);
}
local64_set(&hwc->period_left, left);
hwc->last_period = period;
overflow = 1;
- } else if (unlikely(left <= 0)) {
+ } else if (unlikely(left <= 0)) {
/* left underflowed by less than period. */
left += period;
local64_set(&hwc->period_left, left);
write_aux_reg(ARC_REG_PCT_INDEX, idx);
/* Write value */
- write_aux_reg(ARC_REG_PCT_COUNTL, (u32)value);
- write_aux_reg(ARC_REG_PCT_COUNTH, (value >> 32));
+ write_aux_reg(ARC_REG_PCT_COUNTL, lower_32_bits(value));
+ write_aux_reg(ARC_REG_PCT_COUNTH, upper_32_bits(value));
perf_event_update_userpage(event);
/* Enable interrupt for this counter */
if (is_sampling_event(event))
write_aux_reg(ARC_REG_PCT_INT_CTRL,
- read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+ read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
/* enable ARC pmu here */
write_aux_reg(ARC_REG_PCT_INDEX, idx); /* counter # */
* Reset interrupt flag by writing of 1. This is required
* to make sure pending interrupt was not left.
*/
- write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+ write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
write_aux_reg(ARC_REG_PCT_INT_CTRL,
- read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~(1 << idx));
+ read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~BIT(idx));
}
if (!(event->hw.state & PERF_HES_STOPPED)) {
if (is_sampling_event(event)) {
/* Mimic full counter overflow as other arches do */
- write_aux_reg(ARC_REG_PCT_INT_CNTL, (u32)arc_pmu->max_period);
+ write_aux_reg(ARC_REG_PCT_INT_CNTL,
+ lower_32_bits(arc_pmu->max_period));
write_aux_reg(ARC_REG_PCT_INT_CNTH,
- (arc_pmu->max_period >> 32));
+ upper_32_bits(arc_pmu->max_period));
}
write_aux_reg(ARC_REG_PCT_CONFIG, 0);
idx = __ffs(active_ints);
/* Reset interrupt flag by writing of 1 */
- write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+ write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
/*
* On reset of "interrupt active" bit corresponding
* Now we need to re-enable interrupt for the counter.
*/
write_aux_reg(ARC_REG_PCT_INT_CTRL,
- read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+ read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
event = pmu_cpu->act_counter[idx];
hwc = &event->hw;
arc_pmu_stop(event, 0);
}
- active_ints &= ~(1U << idx);
+ active_ints &= ~BIT(idx);
} while (active_ints);
done:
write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
}
+/* Event field occupies the bottom 15 bits of our config field */
+PMU_FORMAT_ATTR(event, "config:0-14");
+static struct attribute *arc_pmu_format_attrs[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group arc_pmu_format_attr_gr = {
+ .name = "format",
+ .attrs = arc_pmu_format_attrs,
+};
+
+static ssize_t arc_pmu_events_sysfs_show(struct device *dev,
+ struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+ return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
+}
+
+/*
+ * We don't add attrs here as we don't have pre-defined list of perf events.
+ * We will generate and add attrs dynamically in probe() after we read HW
+ * configuration.
+ */
+static struct attribute_group arc_pmu_events_attr_gr = {
+ .name = "events",
+};
+
+static void arc_pmu_add_raw_event_attr(int j, char *str)
+{
+ memmove(arc_pmu->raw_entry[j].name, str, ARCPMU_EVENT_NAME_LEN - 1);
+ arc_pmu->attr[j].attr.attr.name = arc_pmu->raw_entry[j].name;
+ arc_pmu->attr[j].attr.attr.mode = VERIFY_OCTAL_PERMISSIONS(0444);
+ arc_pmu->attr[j].attr.show = arc_pmu_events_sysfs_show;
+ arc_pmu->attr[j].id = j;
+ arc_pmu->attrs[j] = &(arc_pmu->attr[j].attr.attr);
+}
+
+static int arc_pmu_raw_alloc(struct device *dev)
+{
+ arc_pmu->attr = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+ sizeof(*arc_pmu->attr), GFP_KERNEL | __GFP_ZERO);
+ if (!arc_pmu->attr)
+ return -ENOMEM;
+
+ arc_pmu->attrs = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+ sizeof(*arc_pmu->attrs), GFP_KERNEL | __GFP_ZERO);
+ if (!arc_pmu->attrs)
+ return -ENOMEM;
+
+ arc_pmu->raw_entry = devm_kmalloc_array(dev, arc_pmu->n_events,
+ sizeof(*arc_pmu->raw_entry), GFP_KERNEL | __GFP_ZERO);
+ if (!arc_pmu->raw_entry)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static inline bool event_in_hw_event_map(int i, char *name)
+{
+ if (!arc_pmu_ev_hw_map[i])
+ return false;
+
+ if (!strlen(arc_pmu_ev_hw_map[i]))
+ return false;
+
+ if (strcmp(arc_pmu_ev_hw_map[i], name))
+ return false;
+
+ return true;
+}
+
+static void arc_pmu_map_hw_event(int j, char *str)
+{
+ int i;
+
+ /* See if HW condition has been mapped to a perf event_id */
+ for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
+ if (event_in_hw_event_map(i, str)) {
+ pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
+ i, str, j);
+ arc_pmu->ev_hw_idx[i] = j;
+ }
+ }
+}
+
static int arc_pmu_device_probe(struct platform_device *pdev)
{
struct arc_reg_pct_build pct_bcr;
struct arc_reg_cc_build cc_bcr;
- int i, j, has_interrupts;
+ int i, has_interrupts;
int counter_size; /* in bits */
union cc_name {
struct {
- uint32_t word0, word1;
+ u32 word0, word1;
char sentinel;
} indiv;
- char str[9];
+ char str[ARCPMU_EVENT_NAME_LEN];
} cc_name;
return -ENODEV;
}
BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32);
- BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS);
+ if (WARN_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS))
+ return -EINVAL;
READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
- BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */
+ if (WARN(!cc_bcr.v, "Counters exist but No countable conditions?"))
+ return -EINVAL;
arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), GFP_KERNEL);
if (!arc_pmu)
return -ENOMEM;
+ arc_pmu->n_events = cc_bcr.c;
+
+ if (arc_pmu_raw_alloc(&pdev->dev))
+ return -ENOMEM;
+
has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0;
arc_pmu->n_counters = pct_bcr.c;
pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n",
arc_pmu->n_counters, counter_size, cc_bcr.c,
- has_interrupts ? ", [overflow IRQ support]":"");
+ has_interrupts ? ", [overflow IRQ support]" : "");
- cc_name.str[8] = 0;
+ cc_name.str[ARCPMU_EVENT_NAME_LEN - 1] = 0;
for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++)
arc_pmu->ev_hw_idx[i] = -1;
/* loop thru all available h/w condition indexes */
- for (j = 0; j < cc_bcr.c; j++) {
- write_aux_reg(ARC_REG_CC_INDEX, j);
+ for (i = 0; i < cc_bcr.c; i++) {
+ write_aux_reg(ARC_REG_CC_INDEX, i);
cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
- /* See if it has been mapped to a perf event_id */
- for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
- if (arc_pmu_ev_hw_map[i] &&
- !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) &&
- strlen(arc_pmu_ev_hw_map[i])) {
- pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
- i, cc_name.str, j);
- arc_pmu->ev_hw_idx[i] = j;
- }
- }
+ arc_pmu_map_hw_event(i, cc_name.str);
+ arc_pmu_add_raw_event_attr(i, cc_name.str);
}
+ arc_pmu_events_attr_gr.attrs = arc_pmu->attrs;
+ arc_pmu->attr_groups[ARCPMU_ATTR_GR_EVENTS] = &arc_pmu_events_attr_gr;
+ arc_pmu->attr_groups[ARCPMU_ATTR_GR_FORMATS] = &arc_pmu_format_attr_gr;
+
arc_pmu->pmu = (struct pmu) {
.pmu_enable = arc_pmu_enable,
.pmu_disable = arc_pmu_disable,
.start = arc_pmu_start,
.stop = arc_pmu_stop,
.read = arc_pmu_read,
+ .attr_groups = arc_pmu->attr_groups,
};
if (has_interrupts) {
} else
arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
- return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
+ /*
+ * perf parser doesn't really like '-' symbol in events name, so let's
+ * use '_' in arc pct name as it goes to kernel PMU event prefix.
+ */
+ return perf_pmu_register(&arc_pmu->pmu, "arc_pct", PERF_TYPE_RAW);
}
-#ifdef CONFIG_OF
static const struct of_device_id arc_pmu_match[] = {
{ .compatible = "snps,arc700-pct" },
{ .compatible = "snps,archs-pct" },
{},
};
MODULE_DEVICE_TABLE(of, arc_pmu_match);
-#endif
static struct platform_driver arc_pmu_driver = {
.driver = {
struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
const struct id_to_str *tbl;
struct bcr_isa_arcv2 isa;
+ struct bcr_actionpoint ap;
FIX_PTR(cpu);
cpu->bpu.full = bpu.ft;
cpu->bpu.num_cache = 256 << bpu.bce;
cpu->bpu.num_pred = 2048 << bpu.pte;
+ cpu->bpu.ret_stk = 4 << bpu.rse;
if (cpu->core.family >= 0x54) {
unsigned int exec_ctrl;
}
}
- READ_BCR(ARC_REG_AP_BCR, bcr);
- cpu->extn.ap = bcr.ver ? 1 : 0;
+ READ_BCR(ARC_REG_AP_BCR, ap);
+ if (ap.ver) {
+ cpu->extn.ap_num = 2 << ap.num;
+ cpu->extn.ap_full = !!ap.min;
+ }
READ_BCR(ARC_REG_SMART_BCR, bcr);
cpu->extn.smart = bcr.ver ? 1 : 0;
READ_BCR(ARC_REG_RTT_BCR, bcr);
cpu->extn.rtt = bcr.ver ? 1 : 0;
- cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
-
READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
/* some hacks for lack of feature BCR info in old ARC700 cores */
if (cpu->bpu.ver)
n += scnprintf(buf + n, len - n,
- "BPU\t\t: %s%s match, cache:%d, Predict Table:%d",
+ "BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d",
IS_AVAIL1(cpu->bpu.full, "full"),
IS_AVAIL1(!cpu->bpu.full, "partial"),
- cpu->bpu.num_cache, cpu->bpu.num_pred);
+ cpu->bpu.num_cache, cpu->bpu.num_pred, cpu->bpu.ret_stk);
if (is_isa_arcv2()) {
struct bcr_lpb lpb;
IS_AVAIL1(cpu->extn.fpu_sp, "SP "),
IS_AVAIL1(cpu->extn.fpu_dp, "DP "));
- if (cpu->extn.debug)
- n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s%s\n",
- IS_AVAIL1(cpu->extn.ap, "ActionPoint "),
+ if (cpu->extn.ap_num | cpu->extn.smart | cpu->extn.rtt) {
+ n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s",
IS_AVAIL1(cpu->extn.smart, "smaRT "),
IS_AVAIL1(cpu->extn.rtt, "RTT "));
+ if (cpu->extn.ap_num) {
+ n += scnprintf(buf + n, len - n, "ActionPoint %d/%s",
+ cpu->extn.ap_num,
+ cpu->extn.ap_full ? "full":"min");
+ }
+ n += scnprintf(buf + n, len - n, "\n");
+ }
if (cpu->dccm.sz || cpu->iccm.sz)
n += scnprintf(buf + n, len - n, "Extn [CCM]\t: DCCM @ %x, %d KB / ICCM: @ %x, %d KB\n",
#include <asm/arcregs.h>
#include <asm/irqflags.h>
+#define ARC_PATH_MAX 256
+
/*
* Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
* -Prints 3 regs per line and a CR.
print_reg_file(&(cregs->r13), 13);
}
-static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
+static void print_task_path_n_nm(struct task_struct *tsk)
{
char *path_nm = NULL;
struct mm_struct *mm;
struct file *exe_file;
+ char buf[ARC_PATH_MAX];
mm = get_task_mm(tsk);
if (!mm)
mmput(mm);
if (exe_file) {
- path_nm = file_path(exe_file, buf, 255);
+ path_nm = file_path(exe_file, buf, ARC_PATH_MAX-1);
fput(exe_file);
}
pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
}
-static void show_faulting_vma(unsigned long address, char *buf)
+static void show_faulting_vma(unsigned long address)
{
struct vm_area_struct *vma;
- char *nm = buf;
struct mm_struct *active_mm = current->active_mm;
/* can't use print_vma_addr() yet as it doesn't check for
* if the container VMA is not found
*/
if (vma && (vma->vm_start <= address)) {
+ char buf[ARC_PATH_MAX];
+ char *nm = "?";
+
if (vma->vm_file) {
- nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1);
+ nm = file_path(vma->vm_file, buf, ARC_PATH_MAX-1);
if (IS_ERR(nm))
nm = "?";
}
{
struct task_struct *tsk = current;
struct callee_regs *cregs;
- char *buf;
- buf = (char *)__get_free_page(GFP_KERNEL);
- if (!buf)
- return;
+ /*
+ * generic code calls us with preemption disabled, but some calls
+ * here could sleep, so re-enable to avoid lockdep splat
+ */
+ preempt_enable();
- print_task_path_n_nm(tsk, buf);
+ print_task_path_n_nm(tsk);
show_regs_print_info(KERN_INFO);
show_ecr_verbose(regs);
(void *)regs->blink, (void *)regs->ret);
if (user_mode(regs))
- show_faulting_vma(regs->ret, buf); /* faulting code, not data */
+ show_faulting_vma(regs->ret); /* faulting code, not data */
pr_info("[STAT32]: 0x%08lx", regs->status32);
if (cregs)
show_callee_regs(cregs);
- free_page((unsigned long)buf);
+ preempt_disable();
}
void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
*/
#include <linux/linkage.h>
+#include <asm/cache.h>
-#undef PREALLOC_NOT_AVAIL
+/*
+ * The memset implementation below is optimized to use prefetchw and prealloc
+ * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6)
+ * If you want to implement optimized memset for other possible L1 data cache
+ * line lengths (32B and 128B) you should rewrite code carefully checking
+ * we don't call any prefetchw/prealloc instruction for L1 cache lines which
+ * don't belongs to memset area.
+ */
+
+#if L1_CACHE_SHIFT == 6
+
+.macro PREALLOC_INSTR reg, off
+ prealloc [\reg, \off]
+.endm
+
+.macro PREFETCHW_INSTR reg, off
+ prefetchw [\reg, \off]
+.endm
+
+#else
+
+.macro PREALLOC_INSTR
+.endm
+
+.macro PREFETCHW_INSTR
+.endm
+
+#endif
ENTRY_CFI(memset)
- prefetchw [r0] ; Prefetch the write location
+ PREFETCHW_INSTR r0, 0 ; Prefetch the first write location
mov.f 0, r2
;;; if size is zero
jz.d [blink]
lpnz @.Lset64bytes
;; LOOP START
-#ifdef PREALLOC_NOT_AVAIL
- prefetchw [r3, 64] ;Prefetch the next write location
-#else
- prealloc [r3, 64]
-#endif
+ PREALLOC_INSTR r3, 64 ; alloc next line w/o fetching
+
#ifdef CONFIG_ARC_HAS_LL64
std.ab r4, [r3, 8]
std.ab r4, [r3, 8]
lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes
lpnz .Lset32bytes
;; LOOP START
- prefetchw [r3, 32] ;Prefetch the next write location
#ifdef CONFIG_ARC_HAS_LL64
std.ab r4, [r3, 8]
std.ab r4, [r3, 8]
*/
fault = handle_mm_fault(vma, address, flags);
- /* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
if (fatal_signal_pending(current)) {
- if ((fault & VM_FAULT_ERROR) && !(fault & VM_FAULT_RETRY))
- up_read(&mm->mmap_sem);
- if (user_mode(regs))
+
+ /*
+ * if fault retry, mmap_sem already relinquished by core mm
+ * so OK to return to user mode (with signal handled first)
+ */
+ if (fault & VM_FAULT_RETRY) {
+ if (!user_mode(regs))
+ goto no_context;
return;
+ }
}
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
*/
memblock_add_node(low_mem_start, low_mem_sz, 0);
- memblock_reserve(low_mem_start, __pa(_end) - low_mem_start);
+ memblock_reserve(CONFIG_LINUX_LINK_BASE,
+ __pa(_end) - CONFIG_LINUX_LINK_BASE);
#ifdef CONFIG_BLK_DEV_INITRD
if (phys_initrd_size) {
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
+#define _ASM_ARM_XEN_PAGE_COHERENT_H
+
+#include <linux/dma-mapping.h>
+#include <asm/page.h>
#include <xen/arm/page-coherent.h>
+
+static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
+{
+ if (dev && dev->archdata.dev_dma_ops)
+ return dev->archdata.dev_dma_ops;
+ return get_arch_dma_ops(NULL);
+}
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
+{
+ return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+ void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
+{
+ xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+ dma_addr_t dev_addr, unsigned long offset, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ unsigned long page_pfn = page_to_xen_pfn(page);
+ unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+ unsigned long compound_pages =
+ (1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+ bool local = (page_pfn <= dev_pfn) &&
+ (dev_pfn - page_pfn < compound_pages);
+
+ /*
+ * Dom0 is mapped 1:1, while the Linux page can span across
+ * multiple Xen pages, it's not possible for it to contain a
+ * mix of local and foreign Xen pages. So if the first xen_pfn
+ * == mfn the page is local otherwise it's a foreign page
+ * grant-mapped in dom0. If the page is local we can safely
+ * call the native dma_ops function, otherwise we call the xen
+ * specific function.
+ */
+ if (local)
+ xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+ else
+ __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ unsigned long pfn = PFN_DOWN(handle);
+ /*
+ * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+ * multiple Xen page, it's not possible to have a mix of local and
+ * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+ * foreign mfn will always return false. If the page is local we can
+ * safely call the native dma_ops function, otherwise we call the xen
+ * specific function.
+ */
+ if (pfn_valid(pfn)) {
+ if (xen_get_dma_ops(hwdev)->unmap_page)
+ xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+ } else
+ __xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ unsigned long pfn = PFN_DOWN(handle);
+ if (pfn_valid(pfn)) {
+ if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
+ xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+ } else
+ __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ unsigned long pfn = PFN_DOWN(handle);
+ if (pfn_valid(pfn)) {
+ if (xen_get_dma_ops(hwdev)->sync_single_for_device)
+ xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+ } else
+ __xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
#ifdef CONFIG_KASAN_SW_TAGS
#define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT)
-#else
-#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
#endif
#ifndef __ASSEMBLY__
#ifdef CONFIG_IOMMU_API
void *iommu; /* private IOMMU data */
#endif
-#ifdef CONFIG_XEN
- const struct dma_map_ops *dev_dma_ops;
-#endif
};
struct pdev_archdata {
* later determine that kpti is required, then
* kpti_install_ng_mappings() will make them non-global.
*/
+ if (arm64_kernel_unmapped_at_el0())
+ return true;
+
if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
- return arm64_kernel_unmapped_at_el0();
+ return false;
/*
* KASLR is enabled so we're going to be enabling kpti on non-broken
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H
+#define _ASM_ARM64_XEN_PAGE_COHERENT_H
+
+#include <linux/dma-mapping.h>
+#include <asm/page.h>
#include <xen/arm/page-coherent.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
+{
+ return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+ void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
+{
+ dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ unsigned long pfn = PFN_DOWN(handle);
+
+ if (pfn_valid(pfn))
+ dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
+ else
+ __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+ dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+ unsigned long pfn = PFN_DOWN(handle);
+ if (pfn_valid(pfn))
+ dma_direct_sync_single_for_device(hwdev, handle, size, dir);
+ else
+ __xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+ dma_addr_t dev_addr, unsigned long offset, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ unsigned long page_pfn = page_to_xen_pfn(page);
+ unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+ unsigned long compound_pages =
+ (1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+ bool local = (page_pfn <= dev_pfn) &&
+ (dev_pfn - page_pfn < compound_pages);
+
+ if (local)
+ dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
+ else
+ __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ unsigned long pfn = PFN_DOWN(handle);
+ /*
+ * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+ * multiple Xen page, it's not possible to have a mix of local and
+ * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+ * foreign mfn will always return false. If the page is local we can
+ * safely call the native dma_ops function, otherwise we call the xen
+ * specific function.
+ */
+ if (pfn_valid(pfn))
+ dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
+ else
+ __xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
#include <linux/sched.h>
#include <linux/types.h>
+#include <asm/cacheflush.h>
#include <asm/fixmap.h>
#include <asm/kernel-pgtable.h>
#include <asm/memory.h>
return ret;
}
-static __init const u8 *get_cmdline(void *fdt)
+static __init const u8 *kaslr_get_cmdline(void *fdt)
{
static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE;
* Check if 'nokaslr' appears on the command line, and
* return 0 if that is the case.
*/
- cmdline = get_cmdline(fdt);
+ cmdline = kaslr_get_cmdline(fdt);
str = strstr(cmdline, "nokaslr");
if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
return 0;
module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
module_alloc_base &= PAGE_MASK;
+ __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+ __flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+
return offset;
}
__iommu_setup_dma_ops(dev, dma_base, size, iommu);
#ifdef CONFIG_XEN
- if (xen_initial_domain()) {
- dev->archdata.dev_dma_ops = dev->dma_ops;
+ if (xen_initial_domain())
dev->dma_ops = xen_dma_ops;
- }
#endif
}
boot := arch/h8300/boot
-archmrproper:
-
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
NM := $(CROSS_COMPILE)nm -B
READELF := $(CROSS_COMPILE)readelf
-export AWK
-
CHECKFLAGS += -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__
OBJCOPYFLAGS := --strip-all
config MIPS32_N32
bool "Kernel support for n32 binaries"
depends on 64BIT
+ select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
select COMPAT
select MIPS32_COMPAT
select SYSVIPC_COMPAT if SYSVIPC
pm_power_off = bcm47xx_machine_halt;
}
+#ifdef CONFIG_BCM47XX_BCMA
+static struct device * __init bcm47xx_setup_device(void)
+{
+ struct device *dev;
+ int err;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev)
+ return NULL;
+
+ err = dev_set_name(dev, "bcm47xx_soc");
+ if (err) {
+ pr_err("Failed to set SoC device name: %d\n", err);
+ kfree(dev);
+ return NULL;
+ }
+
+ err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+ if (err)
+ pr_err("Failed to set SoC DMA mask: %d\n", err);
+
+ return dev;
+}
+#endif
+
/*
* This finishes bus initialization doing things that were not possible without
* kmalloc. Make sure to call it late enough (after mm_init).
if (bcm47xx_bus_type == BCM47XX_BUS_TYPE_BCMA) {
int err;
+ bcm47xx_bus.bcma.dev = bcm47xx_setup_device();
+ if (!bcm47xx_bus.bcma.dev)
+ panic("Failed to setup SoC device\n");
+
err = bcma_host_soc_init(&bcm47xx_bus.bcma);
if (err)
panic("Failed to initialize BCMA bus (err %d)", err);
#endif
#ifdef CONFIG_BCM47XX_BCMA
case BCM47XX_BUS_TYPE_BCMA:
+ if (device_register(bcm47xx_bus.bcma.dev))
+ pr_err("Failed to register SoC device\n");
bcma_bus_register(&bcm47xx_bus.bcma.bus);
break;
#endif
" sync \n"
" synci ($0) \n");
- relocated_kexec_smp_wait(NULL);
+ kexec_reboot();
}
#endif
# CONFIG_SERIAL_8250_PCI is not set
CONFIG_SERIAL_8250_NR_UARTS=1
CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
CONFIG_SERIAL_AR933X=y
CONFIG_SERIAL_AR933X_CONSOLE=y
# CONFIG_HW_RANDOM is not set
#define INT_NUM_EXTRA_START (INT_NUM_IM4_IRL0 + 32)
#define INT_NUM_IM_OFFSET (INT_NUM_IM1_IRL0 - INT_NUM_IM0_IRL0)
-#define MIPS_CPU_TIMER_IRQ 7
-
#define MAX_IM 5
#endif /* _FALCON_IRQ__ */
#define LTQ_DMA_CH0_INT (INT_NUM_IM2_IRL0)
-#define MIPS_CPU_TIMER_IRQ 7
-
#define MAX_IM 5
#endif
get_order(VDMA_PGTBL_SIZE));
BUG_ON(!pgtbl);
dma_cache_wback_inv((unsigned long)pgtbl, VDMA_PGTBL_SIZE);
- pgtbl = (VDMA_PGTBL_ENTRY *)KSEG1ADDR(pgtbl);
+ pgtbl = (VDMA_PGTBL_ENTRY *)CKSEG1ADDR((unsigned long)pgtbl);
/*
* Clear the R4030 translation table
*/
vdma_pgtbl_init();
- r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE, CPHYSADDR(pgtbl));
+ r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE,
+ CPHYSADDR((unsigned long)pgtbl));
r4030_write_reg32(JAZZ_R4030_TRSTBL_LIM, VDMA_PGTBL_SIZE);
r4030_write_reg32(JAZZ_R4030_TRSTBL_INV, 0);
.irq_set_type = ltq_eiu_settype,
};
-static void ltq_hw_irqdispatch(int module)
+static void ltq_hw_irq_handler(struct irq_desc *desc)
{
+ int module = irq_desc_get_irq(desc) - 2;
u32 irq;
+ int hwirq;
irq = ltq_icu_r32(module, LTQ_ICU_IM0_IOSR);
if (irq == 0)
* other bits might be bogus
*/
irq = __fls(irq);
- do_IRQ((int)irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module));
+ hwirq = irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module);
+ generic_handle_irq(irq_linear_revmap(ltq_domain, hwirq));
/* if this is a EBU irq, we need to ack it or get a deadlock */
if ((irq == LTQ_ICU_EBU_IRQ) && (module == 0) && LTQ_EBU_PCC_ISTAT)
LTQ_EBU_PCC_ISTAT);
}
-#define DEFINE_HWx_IRQDISPATCH(x) \
- static void ltq_hw ## x ## _irqdispatch(void) \
- { \
- ltq_hw_irqdispatch(x); \
- }
-DEFINE_HWx_IRQDISPATCH(0)
-DEFINE_HWx_IRQDISPATCH(1)
-DEFINE_HWx_IRQDISPATCH(2)
-DEFINE_HWx_IRQDISPATCH(3)
-DEFINE_HWx_IRQDISPATCH(4)
-
-#if MIPS_CPU_TIMER_IRQ == 7
-static void ltq_hw5_irqdispatch(void)
-{
- do_IRQ(MIPS_CPU_TIMER_IRQ);
-}
-#else
-DEFINE_HWx_IRQDISPATCH(5)
-#endif
-
-static void ltq_hw_irq_handler(struct irq_desc *desc)
-{
- ltq_hw_irqdispatch(irq_desc_get_irq(desc) - 2);
-}
-
-asmlinkage void plat_irq_dispatch(void)
-{
- unsigned int pending = read_c0_status() & read_c0_cause() & ST0_IM;
- int irq;
-
- if (!pending) {
- spurious_interrupt();
- return;
- }
-
- pending >>= CAUSEB_IP;
- while (pending) {
- irq = fls(pending) - 1;
- do_IRQ(MIPS_CPU_IRQ_BASE + irq);
- pending &= ~BIT(irq);
- }
-}
-
static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
{
struct irq_chip *chip = <q_irq_type;
for (i = 0; i < MAX_IM; i++)
irq_set_chained_handler(i + 2, ltq_hw_irq_handler);
- if (cpu_has_vint) {
- pr_info("Setting up vectored interrupts\n");
- set_vi_handler(2, ltq_hw0_irqdispatch);
- set_vi_handler(3, ltq_hw1_irqdispatch);
- set_vi_handler(4, ltq_hw2_irqdispatch);
- set_vi_handler(5, ltq_hw3_irqdispatch);
- set_vi_handler(6, ltq_hw4_irqdispatch);
- set_vi_handler(7, ltq_hw5_irqdispatch);
- }
-
ltq_domain = irq_domain_add_linear(node,
(MAX_IM * INT_NUM_IM_OFFSET) + MIPS_CPU_IRQ_CASCADE,
&irq_domain_ops, 0);
-#ifndef CONFIG_MIPS_MT_SMP
- set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 |
- IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#else
- set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ0 | IE_IRQ1 |
- IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#endif
-
/* tell oprofile which irq to use */
ltq_perfcount_irq = irq_create_mapping(ltq_domain, LTQ_PERF_IRQ);
- /*
- * if the timer irq is not one of the mips irqs we need to
- * create a mapping
- */
- if (MIPS_CPU_TIMER_IRQ != 7)
- irq_create_mapping(ltq_domain, MIPS_CPU_TIMER_IRQ);
-
/* the external interrupts are optional and xway only */
eiu_node = of_find_compatible_node(NULL, NULL, "lantiq,eiu-xway");
if (eiu_node && !of_address_to_resource(eiu_node, 0, &res)) {
unsigned int get_c0_compare_int(void)
{
- return MIPS_CPU_TIMER_IRQ;
+ return CP0_LEGACY_COMPARE_IRQ;
}
static struct of_device_id __initdata of_irq_ids[] = {
int irq;
struct irq_chip *msi;
- if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
+ if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) {
+ return 0;
+ } else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0;
msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1;
msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;
KBUILD_DEFCONFIG := defconfig
-comma = ,
-
-
ifdef CONFIG_FUNCTION_TRACER
arch-y += -malways-save-lp -mno-relax
endif
boot := arch/nds32/boot
core-y += $(boot)/dts/
-.PHONY: FORCE
-
Image: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
vdso_prepare: prepare0
$(Q)$(MAKE) $(build)=arch/nds32/kernel/vdso include/generated/vdso-offsets.h
-CLEAN_FILES += include/asm-nds32/constants.h*
-
-# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
KBUILD_DEFCONFIG := or1ksim_defconfig
OBJCOPYFLAGS := -O binary -R .note -R .comment -S
-LDFLAGS_vmlinux :=
LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
KBUILD_CFLAGS += -pipe -ffixed-r10 -D__linux__
BUILTIN_DTB := n
endif
core-$(BUILTIN_DTB) += arch/openrisc/boot/dts/
-
-all: vmlinux
PERF_REG_POWERPC_DAR,
PERF_REG_POWERPC_DSISR,
PERF_REG_POWERPC_SIER,
+ PERF_REG_POWERPC_MMCRA,
PERF_REG_POWERPC_MAX,
};
#endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
/* set up the PTE pointers for the Abatron bdiGDB.
*/
- tovirt(r6,r6)
lis r5, abatron_pteptrs@h
ori r5, r5, abatron_pteptrs@l
stw r5, 0xf0(0) /* Must match your Abatron config file */
tophys(r5,r5)
+ lis r6, swapper_pg_dir@h
+ ori r6, r6, swapper_pg_dir@l
stw r6, 0(r5)
/* Now turn on the MMU for real! */
if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
&uc_transact->uc_mcontext))
goto badframe;
- }
+ } else
#endif
- /* Fall through, for non-TM restore */
- if (!MSR_TM_ACTIVE(msr)) {
+ {
/*
+ * Fall through, for non-TM restore
+ *
* Unset MSR[TS] on the thread regs since MSR from user
* context does not have MSR active, and recheckpoint was
* not called since restore_tm_sigcontexts() was not called
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
-unsigned long __init arch_syscall_addr(int nr)
-{
- return sys_call_table[nr*2];
-}
-#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
-
#ifdef PPC64_ELF_ABI_v1
char *arch_ftrace_match_adjust(char *str, const char *search)
{
PT_REGS_OFFSET(PERF_REG_POWERPC_DAR, dar),
PT_REGS_OFFSET(PERF_REG_POWERPC_DSISR, dsisr),
PT_REGS_OFFSET(PERF_REG_POWERPC_SIER, dar),
+ PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr),
};
u64 perf_reg_value(struct pt_regs *regs, int idx)
!is_sier_available()))
return 0;
+ if (idx == PERF_REG_POWERPC_MMCRA &&
+ (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
+ IS_ENABLED(CONFIG_PPC32)))
+ return 0;
+
return regs_get_register(regs, pt_regs_offset[idx]);
}
continue;
seq_printf(m, "PPC4XX OCM : %d\n", ocm->index);
- seq_printf(m, "PhysAddr : %pa[p]\n", &(ocm->phys));
+ seq_printf(m, "PhysAddr : %pa\n", &(ocm->phys));
seq_printf(m, "MemTotal : %d Bytes\n", ocm->memtotal);
seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal);
seq_printf(m, "MemTotal(C) : %d Bytes\n\n", ocm->c.memtotal);
- seq_printf(m, "NC.PhysAddr : %pa[p]\n", &(ocm->nc.phys));
+ seq_printf(m, "NC.PhysAddr : %pa\n", &(ocm->nc.phys));
seq_printf(m, "NC.VirtAddr : 0x%p\n", ocm->nc.virt);
seq_printf(m, "NC.MemTotal : %d Bytes\n", ocm->nc.memtotal);
seq_printf(m, "NC.MemFree : %d Bytes\n", ocm->nc.memfree);
blk->size, blk->owner);
}
- seq_printf(m, "\nC.PhysAddr : %pa[p]\n", &(ocm->c.phys));
+ seq_printf(m, "\nC.PhysAddr : %pa\n", &(ocm->c.phys));
seq_printf(m, "C.VirtAddr : 0x%p\n", ocm->c.virt);
seq_printf(m, "C.MemTotal : %d Bytes\n", ocm->c.memtotal);
seq_printf(m, "C.MemFree : %d Bytes\n", ocm->c.memfree);
/* see if there is a keyboard in the device tree
with a parent of type "adb" */
for_each_node_by_name(kbd, "keyboard")
- if (kbd->parent && kbd->parent->type
- && strcmp(kbd->parent->type, "adb") == 0)
+ if (of_node_is_type(kbd->parent, "adb"))
break;
of_node_put(kbd);
if (kbd)
}
} else {
/* Create a group for 1 GPU and attached NPUs for POWER8 */
- pe->npucomp = kzalloc(sizeof(pe->npucomp), GFP_KERNEL);
+ pe->npucomp = kzalloc(sizeof(*pe->npucomp), GFP_KERNEL);
table_group = &pe->npucomp->table_group;
table_group->ops = &pnv_npu_peers_ops;
iommu_register_group(table_group, hose->global_number,
list_for_each_entry(hose, &hose_list, list_node) {
phb = hose->private_data;
- if (phb->type == PNV_PHB_NPU_NVLINK)
+ if (phb->type == PNV_PHB_NPU_NVLINK ||
+ phb->type == PNV_PHB_NPU_OCAPI)
continue;
list_for_each_entry(pe, &phb->ioda.pe_list, list) {
if (!of_device_is_compatible(nvdn->parent,
"ibm,power9-npu"))
continue;
+#ifdef CONFIG_PPC_POWERNV
WARN_ON_ONCE(pnv_npu2_init(hose));
+#endif
break;
}
}
atomic_set(&mm->context.flush_count, 0);
mm->context.gmap_asce = 0;
mm->context.flush_mm = 0;
- mm->context.compat_mm = 0;
+ mm->context.compat_mm = test_thread_flag(TIF_31BIT);
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste ||
test_thread_flag(TIF_PGSTE) ||
{
int cpu = smp_processor_id();
- if (prev == next)
- return;
S390_lowcore.user_asce = next->context.asce;
cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
/* Clear previous user-ASCE from CR1 and CR7 */
__ctl_load(S390_lowcore.vdso_asce, 7, 7);
clear_cpu_flag(CIF_ASCE_SECONDARY);
}
- cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+ if (prev != next)
+ cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
}
#define finish_arch_post_lock_switch finish_arch_post_lock_switch
if (stsi(vmms, 3, 2, 2) || !vmms->count)
return;
- /* Running under KVM? If not we assume z/VM */
+ /* Detect known hypervisors */
if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
S390_lowcore.machine_flags |= MACHINE_FLAG_KVM;
- else
+ else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
}
pr_info("Linux is running under KVM in 64-bit mode\n");
else if (MACHINE_IS_LPAR)
pr_info("Linux is running natively in 64-bit mode\n");
+ else
+ pr_info("Linux is running as a guest in 64-bit mode\n");
/* Have one command line that is parsed and saved in /proc/cmdline */
/* boot_command_line has been already set up in early.c */
*/
void smp_call_ipl_cpu(void (*func)(void *), void *data)
{
+ struct lowcore *lc = pcpu_devices->lowcore;
+
+ if (pcpu_devices[0].address == stap())
+ lc = &S390_lowcore;
+
pcpu_delegate(&pcpu_devices[0], func, data,
- pcpu_devices->lowcore->nodat_stack);
+ lc->nodat_stack);
}
int smp_find_processor_id(u16 address)
{
int rc;
+ rc = lock_device_hotplug_sysfs();
+ if (rc)
+ return rc;
rc = smp_rescan_cpus();
+ unlock_device_hotplug();
return rc ? rc : count;
}
static DEVICE_ATTR_WO(rescan);
vdso_pages = vdso64_pages;
#ifdef CONFIG_COMPAT
- if (is_compat_task()) {
+ mm->context.compat_mm = is_compat_task();
+ if (mm->context.compat_mm)
vdso_pages = vdso32_pages;
- mm->context.compat_mm = 1;
- }
#endif
/*
* vDSO has a problem and was disabled, just don't "enable" it for
config X86_INTEL_LPSS
bool "Intel Low Power Subsystem Support"
- depends on X86 && ACPI
+ depends on X86 && ACPI && PCI
select COMMON_CLK
select PINCTRL
select IOSF_MBI
{
if (unlikely(!access_ok(ptr,len)))
return 0;
- __uaccess_begin();
+ __uaccess_begin_nospec();
return 1;
}
#define user_access_begin(a,b) user_access_begin(a,b)
#else
u64 ipi_bitmap = 0;
#endif
+ long ret;
if (cpumask_empty(mask))
return;
} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
max = apic_id < max ? max : apic_id;
} else {
- kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+ ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+ WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
min = max = apic_id;
ipi_bitmap = 0;
}
}
if (ipi_bitmap) {
- kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+ ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+ WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
}
local_irq_restore(flags);
ccflags-y += -Iarch/x86/kvm
-CFLAGS_x86.o := -I.
-CFLAGS_svm.o := -I.
-CFLAGS_vmx.o := -I.
-
KVM := ../../../virt/kvm
kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
if (ret != HV_STATUS_INVALID_PORT_ID)
break;
- /* maybe userspace knows this conn_id: fall through */
+ /* fall through - maybe userspace knows this conn_id. */
case HVCALL_POST_MESSAGE:
/* don't bother userspace if it has no way to handle it */
if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE;
ent->eax |= HV_X64_MSR_RESET_AVAILABLE;
ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE;
- ent->eax |= HV_X64_MSR_GUEST_IDLE_AVAILABLE;
ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS;
ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT;
case HYPERV_CPUID_ENLIGHTMENT_INFO:
ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
- ent->eax |= HV_X64_SYSTEM_RESET_RECOMMENDED;
ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
- ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
+ if (evmcs_ver)
+ ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
/*
* Default number of spinlock retry attempts, matches
switch (delivery_mode) {
case APIC_DM_LOWEST:
vcpu->arch.apic_arb_prio++;
+ /* fall through */
case APIC_DM_FIXED:
if (unlikely(trig_mode && !level))
break;
case APIC_LVT0:
apic_manage_nmi_watchdog(apic, val);
+ /* fall through */
case APIC_LVTTHMR:
case APIC_LVTPC:
case APIC_LVT1:
rsvd_bits(maxphyaddr, 51);
rsvd_check->rsvd_bits_mask[1][4] =
rsvd_check->rsvd_bits_mask[0][4];
+ /* fall through */
case PT64_ROOT_4LEVEL:
rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
kvm_mmu_reset_context(&svm->vcpu);
kvm_mmu_load(&svm->vcpu);
+ /*
+ * Drop what we picked up for L2 via svm_complete_interrupts() so it
+ * doesn't end up in L1.
+ */
+ svm->vcpu.arch.nmi_injected = false;
+ kvm_clear_exception_queue(&svm->vcpu);
+ kvm_clear_interrupt_queue(&svm->vcpu);
+
return 0;
}
case MSR_IA32_APICBASE:
if (kvm_vcpu_apicv_active(vcpu))
avic_update_vapic_bar(to_svm(vcpu), data);
- /* Follow through */
+ /* Fall through */
default:
return kvm_set_msr_common(vcpu, msr);
}
kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
- int i;
- struct kvm_vcpu *vcpu;
- struct kvm *kvm = svm->vcpu.kvm;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
/*
- * At this point, we expect that the AVIC HW has already
- * set the appropriate IRR bits on the valid target
- * vcpus. So, we just need to kick the appropriate vcpu.
+ * Update ICR high and low, then emulate sending IPI,
+ * which is handled when writing APIC_ICR.
*/
- kvm_for_each_vcpu(i, vcpu, kvm) {
- bool m = kvm_apic_match_dest(vcpu, apic,
- icrl & KVM_APIC_SHORT_MASK,
- GET_APIC_DEST_FIELD(icrh),
- icrl & KVM_APIC_DEST_MASK);
-
- if (m && !avic_vcpu_is_running(vcpu))
- kvm_vcpu_wake_up(vcpu);
- }
+ kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
+ kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
}
case AVIC_IPI_FAILURE_INVALID_TARGET:
+ WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n",
+ index, svm->vcpu.vcpu_id, icrh, icrl);
break;
case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
WARN_ONCE(1, "Invalid backing page\n");
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH arch/x86/kvm
+#define TRACE_INCLUDE_PATH ../../arch/x86/kvm
#undef TRACE_INCLUDE_FILE
#define TRACE_INCLUDE_FILE trace
uint16_t *vmcs_version)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled;
+
+ vmx->nested.enlightened_vmcs_enabled = true;
if (vmcs_version)
*vmcs_version = nested_get_evmcs_version(vcpu);
/* We don't support disabling the feature for simplicity. */
- if (vmx->nested.enlightened_vmcs_enabled)
+ if (evmcs_already_enabled)
return 0;
- vmx->nested.enlightened_vmcs_enabled = true;
-
vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
static int max_shadow_read_write_fields =
ARRAY_SIZE(shadow_read_write_fields);
-void init_vmcs_shadow_fields(void)
+static void init_vmcs_shadow_fields(void)
{
int i, j;
if (r < 0)
goto out_vmcs02;
- vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+ vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_vmcs12)
goto out_cached_vmcs12;
- vmx->nested.cached_shadow_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+ vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_shadow_vmcs12)
goto out_cached_shadow_vmcs12;
copy_shadow_to_vmcs12(vmx);
}
- if (copy_to_user(user_kvm_nested_state->data, vmcs12, sizeof(*vmcs12)))
+ /*
+ * Copy over the full allocated size of vmcs12 rather than just the size
+ * of the struct.
+ */
+ if (copy_to_user(user_kvm_nested_state->data, vmcs12, VMCS12_SIZE))
return -EFAULT;
if (nested_cpu_has_shadow_vmcs(vmcs12) &&
vmcs12->vmcs_link_pointer != -1ull) {
if (copy_to_user(user_kvm_nested_state->data + VMCS12_SIZE,
- get_shadow_vmcs12(vcpu), sizeof(*vmcs12)))
+ get_shadow_vmcs12(vcpu), VMCS12_SIZE))
return -EFAULT;
}
to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH;
}
-int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
+static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
void *data)
{
struct kvm_tlb_range *range = data;
if (!msr_info->host_initiated &&
!guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
return 1;
- /* Otherwise falls through */
+ /* Else, falls through */
default:
msr = find_msr_entry(vmx, msr_info->index);
if (msr) {
/* Check reserved bit, higher 32 bits should be zero */
if ((data >> 32) != 0)
return 1;
- /* Otherwise falls through */
+ /* Else, falls through */
default:
msr = find_msr_entry(vmx, msr_index);
if (msr) {
case 37: /* AAT100 */
case 44: /* BC86,AAY89,BD102 */
case 46: /* BA97 */
- _vmexit_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ _vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
_vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
"does not work properly. Using workaround\n");
vmx->loaded_vmcs->hv_timer_armed = false;
}
-static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
+static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long cr3, cr4, evmcs_rsp;
-
- /* Record the guest's net vcpu time for enforced NMI injections. */
- if (unlikely(!enable_vnmi &&
- vmx->loaded_vmcs->soft_vnmi_blocked))
- vmx->loaded_vmcs->entry_time = ktime_get();
-
- /* Don't enter VMX if guest state is invalid, let the exit handler
- start emulation until we arrive back to a valid state */
- if (vmx->emulation_required)
- return;
-
- if (vmx->ple_window_dirty) {
- vmx->ple_window_dirty = false;
- vmcs_write32(PLE_WINDOW, vmx->ple_window);
- }
-
- if (vmx->nested.need_vmcs12_sync)
- nested_sync_from_vmcs12(vcpu);
-
- if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
- vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
- if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
- vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
-
- cr3 = __get_current_cr3_fast();
- if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
- vmcs_writel(HOST_CR3, cr3);
- vmx->loaded_vmcs->host_state.cr3 = cr3;
- }
-
- cr4 = cr4_read_shadow();
- if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
- vmcs_writel(HOST_CR4, cr4);
- vmx->loaded_vmcs->host_state.cr4 = cr4;
- }
-
- /* When single-stepping over STI and MOV SS, we must clear the
- * corresponding interruptibility bits in the guest state. Otherwise
- * vmentry fails as it then expects bit 14 (BS) in pending debug
- * exceptions being set, but that's not correct for the guest debugging
- * case. */
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
- vmx_set_interrupt_shadow(vcpu, 0);
-
- if (static_cpu_has(X86_FEATURE_PKU) &&
- kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
- vcpu->arch.pkru != vmx->host_pkru)
- __write_pkru(vcpu->arch.pkru);
-
- pt_guest_enter(vmx);
-
- atomic_switch_perf_msrs(vmx);
-
- vmx_update_hv_timer(vcpu);
-
- /*
- * If this vCPU has touched SPEC_CTRL, restore the guest's value if
- * it's non-zero. Since vmentry is serialising on affected CPUs, there
- * is no need to worry about the conditional branch over the wrmsr
- * being speculatively taken.
- */
- x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+ unsigned long evmcs_rsp;
vmx->__launched = vmx->loaded_vmcs->launched;
, "eax", "ebx", "edi"
#endif
);
+}
+STACK_FRAME_NON_STANDARD(__vmx_vcpu_run);
+
+static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long cr3, cr4;
+
+ /* Record the guest's net vcpu time for enforced NMI injections. */
+ if (unlikely(!enable_vnmi &&
+ vmx->loaded_vmcs->soft_vnmi_blocked))
+ vmx->loaded_vmcs->entry_time = ktime_get();
+
+ /* Don't enter VMX if guest state is invalid, let the exit handler
+ start emulation until we arrive back to a valid state */
+ if (vmx->emulation_required)
+ return;
+
+ if (vmx->ple_window_dirty) {
+ vmx->ple_window_dirty = false;
+ vmcs_write32(PLE_WINDOW, vmx->ple_window);
+ }
+
+ if (vmx->nested.need_vmcs12_sync)
+ nested_sync_from_vmcs12(vcpu);
+
+ if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
+ vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
+ if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
+ vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
+
+ cr3 = __get_current_cr3_fast();
+ if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+ vmcs_writel(HOST_CR3, cr3);
+ vmx->loaded_vmcs->host_state.cr3 = cr3;
+ }
+
+ cr4 = cr4_read_shadow();
+ if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+ vmcs_writel(HOST_CR4, cr4);
+ vmx->loaded_vmcs->host_state.cr4 = cr4;
+ }
+
+ /* When single-stepping over STI and MOV SS, we must clear the
+ * corresponding interruptibility bits in the guest state. Otherwise
+ * vmentry fails as it then expects bit 14 (BS) in pending debug
+ * exceptions being set, but that's not correct for the guest debugging
+ * case. */
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+ vmx_set_interrupt_shadow(vcpu, 0);
+
+ if (static_cpu_has(X86_FEATURE_PKU) &&
+ kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+ vcpu->arch.pkru != vmx->host_pkru)
+ __write_pkru(vcpu->arch.pkru);
+
+ pt_guest_enter(vmx);
+
+ atomic_switch_perf_msrs(vmx);
+
+ vmx_update_hv_timer(vcpu);
+
+ /*
+ * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+ * it's non-zero. Since vmentry is serialising on affected CPUs, there
git.samba.org / sfrench / cifs-2.6.git / commitdiff