Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-12-28 13:51:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

arm64 updates for 6.2

Browse Source 
ACPI:
 	* Enable FPDT support for boot-time profiling
 	* Fix CPU PMU probing to work better with PREEMPT_RT
 	* Update SMMUv3 MSI DeviceID parsing to latest IORT spec
 	* APMT support for probing Arm CoreSight PMU devices
 
 CPU features:
 	* Advertise new SVE instructions (v2.1)
 	* Advertise range prefetch instruction
 	* Advertise CSSC ("Common Short Sequence Compression") scalar
 	  instructions, adding things like min, max, abs, popcount
 	* Enable DIT (Data Independent Timing) when running in the kernel
 	* More conversion of system register fields over to the generated
 	  header
 
 CPU misfeatures:
 	* Workaround for Cortex-A715 erratum #2645198
 
 Dynamic SCS:
 	* Support for dynamic shadow call stacks to allow switching at
 	  runtime between Clang's SCS implementation and the CPU's
 	  pointer authentication feature when it is supported (complete
 	  with scary DWARF parser!)
 
 Tracing and debug:
 	* Remove static ftrace in favour of, err, dynamic ftrace!
 	* Seperate 'struct ftrace_regs' from 'struct pt_regs' in core
 	  ftrace and existing arch code
 	* Introduce and implement FTRACE_WITH_ARGS on arm64 to replace
 	  the old FTRACE_WITH_REGS
 	* Extend 'crashkernel=' parameter with default value and fallback
 	  to placement above 4G physical if initial (low) allocation
 	  fails
 
 SVE:
 	* Optimisation to avoid disabling SVE unconditionally on syscall
 	  entry and just zeroing the non-shared state on return instead
 
 Exceptions:
 	* Rework of undefined instruction handling to avoid serialisation
 	  on global lock (this includes emulation of user accesses to the
 	  ID registers)
 
 Perf and PMU:
 	* Support for TLP filters in Hisilicon's PCIe PMU device
 	* Support for the DDR PMU present in Amlogic Meson G12 SoCs
 	* Support for the terribly-named "CoreSight PMU" architecture
 	  from Arm (and Nvidia's implementation of said architecture)
 
 Misc:
 	* Tighten up our boot protocol for systems with memory above
           52 bits physical
 	* Const-ify static keys to satisty jump label asm constraints
 	* Trivial FFA driver cleanups in preparation for v1.1 support
 	* Export the kernel_neon_* APIs as GPL symbols
 	* Harden our instruction generation routines against
 	  instrumentation
 	* A bunch of robustness improvements to our arch-specific selftests
 	* Minor cleanups and fixes all over (kbuild, kprobes, kfence, PMU, ...)
 -----BEGIN PGP SIGNATURE-----
 
 iQFEBAABCgAuFiEEPxTL6PPUbjXGY88ct6xw3ITBYzQFAmOPLFAQHHdpbGxAa2Vy
 bmVsLm9yZwAKCRC3rHDchMFjNPRcCACLyDTvkimiqfoPxzzgdkx/6QOvw9s3/mXg
 UcTORSZBR1VnYkiMYEKVz/tTfG99dnWtD8/0k/rz48NbhBfsF2sN4ukyBBXVf0zR
 fjnaVyVC11LUgBgZKPo6maV+jf/JWf9hJtpPl06KTiPb2Hw2JX4DXg+PeF8t2hGx
 NLH4ekQOrlDM8mlsN5mc0YsHbiuO7Xe/NRuet8TsgU4bEvLAwO6bzOLVUMqDQZNq
 bQe2ENcGVAzAf7iRJb38lj9qB/5hrQTHRXqLXMSnJyyVjQEwYca0PeJMa7x30bXF
 ZZ+xQ8Wq0mxiffZraf6SE34yD4gaYS4Fziw7rqvydC15vYhzJBH1
 =hV+2
 -----END PGP SIGNATURE-----

Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "The highlights this time are support for dynamically enabling and
  disabling Clang's Shadow Call Stack at boot and a long-awaited
  optimisation to the way in which we handle the SVE register state on
  system call entry to avoid taking unnecessary traps from userspace.

  Summary:

  ACPI:
   - Enable FPDT support for boot-time profiling
   - Fix CPU PMU probing to work better with PREEMPT_RT
   - Update SMMUv3 MSI DeviceID parsing to latest IORT spec
   - APMT support for probing Arm CoreSight PMU devices

  CPU features:
   - Advertise new SVE instructions (v2.1)
   - Advertise range prefetch instruction
   - Advertise CSSC ("Common Short Sequence Compression") scalar
     instructions, adding things like min, max, abs, popcount
   - Enable DIT (Data Independent Timing) when running in the kernel
   - More conversion of system register fields over to the generated
     header

  CPU misfeatures:
   - Workaround for Cortex-A715 erratum #2645198

  Dynamic SCS:
   - Support for dynamic shadow call stacks to allow switching at
     runtime between Clang's SCS implementation and the CPU's pointer
     authentication feature when it is supported (complete with scary
     DWARF parser!)

  Tracing and debug:
   - Remove static ftrace in favour of, err, dynamic ftrace!
   - Seperate 'struct ftrace_regs' from 'struct pt_regs' in core ftrace
     and existing arch code
   - Introduce and implement FTRACE_WITH_ARGS on arm64 to replace the
     old FTRACE_WITH_REGS
   - Extend 'crashkernel=' parameter with default value and fallback to
     placement above 4G physical if initial (low) allocation fails

  SVE:
   - Optimisation to avoid disabling SVE unconditionally on syscall
     entry and just zeroing the non-shared state on return instead

  Exceptions:
   - Rework of undefined instruction handling to avoid serialisation on
     global lock (this includes emulation of user accesses to the ID
     registers)

  Perf and PMU:
   - Support for TLP filters in Hisilicon's PCIe PMU device
   - Support for the DDR PMU present in Amlogic Meson G12 SoCs
   - Support for the terribly-named "CoreSight PMU" architecture from
     Arm (and Nvidia's implementation of said architecture)

  Misc:
   - Tighten up our boot protocol for systems with memory above 52 bits
     physical
   - Const-ify static keys to satisty jump label asm constraints
   - Trivial FFA driver cleanups in preparation for v1.1 support
   - Export the kernel_neon_* APIs as GPL symbols
   - Harden our instruction generation routines against instrumentation
   - A bunch of robustness improvements to our arch-specific selftests
   - Minor cleanups and fixes all over (kbuild, kprobes, kfence, PMU, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (151 commits)
  arm64: kprobes: Return DBG_HOOK_ERROR if kprobes can not handle a BRK
  arm64: kprobes: Let arch do_page_fault() fix up page fault in user handler
  arm64: Prohibit instrumentation on arch_stack_walk()
  arm64:uprobe fix the uprobe SWBP_INSN in big-endian
  arm64: alternatives: add __init/__initconst to some functions/variables
  arm_pmu: Drop redundant armpmu->map_event() in armpmu_event_init()
  kselftest/arm64: Allow epoll_wait() to return more than one result
  kselftest/arm64: Don't drain output while spawning children
  kselftest/arm64: Hold fp-stress children until they're all spawned
  arm64/sysreg: Remove duplicate definitions from asm/sysreg.h
  arm64/sysreg: Convert ID_DFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_DFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_AFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_MMFR5_EL1 to automatic generation
  arm64/sysreg: Convert MVFR2_EL1 to automatic generation
  arm64/sysreg: Convert MVFR1_EL1 to automatic generation
  arm64/sysreg: Convert MVFR0_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR2_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR1_EL1 to automatic generation
  arm64/sysreg: Convert ID_PFR0_EL1 to automatic generation
  ...
This commit is contained in:
Linus Torvalds 2022-12-12 09:50:05 -08:00
commit 06cff4a58e
138 changed files with 6542 additions and 1590 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
Documentation/admin-guide/kernel-parameters.txt
View File

@ -831,7 +831,7 @@
memory region [offset, offset + size] for that kernel
image. If '@offset' is omitted, then a suitable offset
is selected automatically.
[KNL, X86-64] Select a region under 4G first, and
[KNL, X86-64, ARM64] Select a region under 4G first, and
fall back to reserve region above 4G when '@offset'
hasn't been specified.
See Documentation/admin-guide/kdump/kdump.rst for further details.
@ -851,26 +851,23 @@
available.
It will be ignored if crashkernel=X is specified.
crashkernel=size[KMG],low
[KNL, X86-64] range under 4G. When crashkernel=X,high
[KNL, X86-64, ARM64] range under 4G. When crashkernel=X,high
is passed, kernel could allocate physical memory region
above 4G, that cause second kernel crash on system
that require some amount of low memory, e.g. swiotlb
requires at least 64M+32K low memory, also enough extra
low memory is needed to make sure DMA buffers for 32-bit
devices won't run out. Kernel would try to allocate
at least 256M below 4G automatically.
default size of memory below 4G automatically. The default
size is platform dependent.
--> x86: max(swiotlb_size_or_default() + 8MiB, 256MiB)
--> arm64: 128MiB
This one lets the user specify own low range under 4G
for second kernel instead.
0: to disable low allocation.
It will be ignored when crashkernel=X,high is not used
or memory reserved is below 4G.
[KNL, ARM64] range in low memory.
This one lets the user specify a low range in the
DMA zone for the crash dump kernel.
It will be ignored when crashkernel=X,high is not used
or memory reserved is located in the DMA zones.
cryptomgr.notests
[KNL] Disable crypto self-tests

112
Documentation/admin-guide/perf/hisi-pcie-pmu.rst
View File

@ -15,10 +15,10 @@ HiSilicon PCIe PMU driver
The PCIe PMU driver registers a perf PMU with the name of its sicl-id and PCIe
Core id.::
/sys/bus/event_source/hisi_pcie<sicl>_<core>
/sys/bus/event_source/hisi_pcie<sicl>_core<core>
PMU driver provides description of available events and filter options in sysfs,
see /sys/bus/event_source/devices/hisi_pcie<sicl>_<core>.
see /sys/bus/event_source/devices/hisi_pcie<sicl>_core<core>.
The "format" directory describes all formats of the config (events) and config1
(filter options) fields of the perf_event_attr structure. The "events" directory
@ -33,13 +33,13 @@ monitored by PMU.
Example usage of perf::
$# perf list
hisi_pcie0_0/rx_mwr_latency/ [kernel PMU event]
hisi_pcie0_0/rx_mwr_cnt/ [kernel PMU event]
hisi_pcie0_core0/rx_mwr_latency/ [kernel PMU event]
hisi_pcie0_core0/rx_mwr_cnt/ [kernel PMU event]
------------------------------------------
$# perf stat -e hisi_pcie0_0/rx_mwr_latency/
$# perf stat -e hisi_pcie0_0/rx_mwr_cnt/
$# perf stat -g -e hisi_pcie0_0/rx_mwr_latency/ -e hisi_pcie0_0/rx_mwr_cnt/
$# perf stat -e hisi_pcie0_core0/rx_mwr_latency/
$# perf stat -e hisi_pcie0_core0/rx_mwr_cnt/
$# perf stat -g -e hisi_pcie0_core0/rx_mwr_latency/ -e hisi_pcie0_core0/rx_mwr_cnt/
The current driver does not support sampling. So "perf record" is unsupported.
Also attach to a task is unsupported for PCIe PMU.
@ -48,59 +48,83 @@ Filter options
--------------
1. Target filter
PMU could only monitor the performance of traffic downstream target Root Ports
or downstream target Endpoint. PCIe PMU driver support "port" and "bdf"
interfaces for users, and these two interfaces aren't supported at the same
time.
-port
"port" filter can be used in all PCIe PMU events, target Root Port can be
selected by configuring the 16-bits-bitmap "port". Multi ports can be selected
for AP-layer-events, and only one port can be selected for TL/DL-layer-events.
PMU could only monitor the performance of traffic downstream target Root
Ports or downstream target Endpoint. PCIe PMU driver support "port" and
"bdf" interfaces for users, and these two interfaces aren't supported at the
same time.
For example, if target Root Port is 0000:00:00.0 (x8 lanes), bit0 of bitmap
should be set, port=0x1; if target Root Port is 0000:00:04.0 (x4 lanes),
bit8 is set, port=0x100; if these two Root Ports are both monitored, port=0x101.
- port
Example usage of perf::
"port" filter can be used in all PCIe PMU events, target Root Port can be
selected by configuring the 16-bits-bitmap "port". Multi ports can be
selected for AP-layer-events, and only one port can be selected for
TL/DL-layer-events.
$# perf stat -e hisi_pcie0_0/rx_mwr_latency,port=0x1/ sleep 5
For example, if target Root Port is 0000:00:00.0 (x8 lanes), bit0 of
bitmap should be set, port=0x1; if target Root Port is 0000:00:04.0 (x4
lanes), bit8 is set, port=0x100; if these two Root Ports are both
monitored, port=0x101.
-bdf
Example usage of perf::
"bdf" filter can only be used in bandwidth events, target Endpoint is selected
by configuring BDF to "bdf". Counter only counts the bandwidth of message
requested by target Endpoint.
$# perf stat -e hisi_pcie0_core0/rx_mwr_latency,port=0x1/ sleep 5
For example, "bdf=0x3900" means BDF of target Endpoint is 0000:39:00.0.
- bdf
Example usage of perf::
"bdf" filter can only be used in bandwidth events, target Endpoint is
selected by configuring BDF to "bdf". Counter only counts the bandwidth of
message requested by target Endpoint.
$# perf stat -e hisi_pcie0_0/rx_mrd_flux,bdf=0x3900/ sleep 5
For example, "bdf=0x3900" means BDF of target Endpoint is 0000:39:00.0.
Example usage of perf::
$# perf stat -e hisi_pcie0_core0/rx_mrd_flux,bdf=0x3900/ sleep 5
2. Trigger filter
Event statistics start when the first time TLP length is greater/smaller
than trigger condition. You can set the trigger condition by writing "trig_len",
and set the trigger mode by writing "trig_mode". This filter can only be used
in bandwidth events.
For example, "trig_len=4" means trigger condition is 2^4 DW, "trig_mode=0"
means statistics start when TLP length > trigger condition, "trig_mode=1"
means start when TLP length < condition.
Event statistics start when the first time TLP length is greater/smaller
than trigger condition. You can set the trigger condition by writing
"trig_len", and set the trigger mode by writing "trig_mode". This filter can
only be used in bandwidth events.
Example usage of perf::
For example, "trig_len=4" means trigger condition is 2^4 DW, "trig_mode=0"
means statistics start when TLP length > trigger condition, "trig_mode=1"
means start when TLP length < condition.
$# perf stat -e hisi_pcie0_0/rx_mrd_flux,trig_len=0x4,trig_mode=1/ sleep 5
Example usage of perf::
$# perf stat -e hisi_pcie0_core0/rx_mrd_flux,trig_len=0x4,trig_mode=1/ sleep 5
3. Threshold filter
Counter counts when TLP length within the specified range. You can set the
threshold by writing "thr_len", and set the threshold mode by writing
"thr_mode". This filter can only be used in bandwidth events.
For example, "thr_len=4" means threshold is 2^4 DW, "thr_mode=0" means
counter counts when TLP length >= threshold, and "thr_mode=1" means counts
when TLP length < threshold.
Counter counts when TLP length within the specified range. You can set the
threshold by writing "thr_len", and set the threshold mode by writing
"thr_mode". This filter can only be used in bandwidth events.
Example usage of perf::
For example, "thr_len=4" means threshold is 2^4 DW, "thr_mode=0" means
counter counts when TLP length >= threshold, and "thr_mode=1" means counts
when TLP length < threshold.
$# perf stat -e hisi_pcie0_0/rx_mrd_flux,thr_len=0x4,thr_mode=1/ sleep 5
Example usage of perf::
$# perf stat -e hisi_pcie0_core0/rx_mrd_flux,thr_len=0x4,thr_mode=1/ sleep 5
4. TLP Length filter
When counting bandwidth, the data can be composed of certain parts of TLP
packets. You can specify it through "len_mode":
- 2'b00: Reserved (Do not use this since the behaviour is undefined)
- 2'b01: Bandwidth of TLP payloads
- 2'b10: Bandwidth of TLP headers
- 2'b11: Bandwidth of both TLP payloads and headers
For example, "len_mode=2" means only counting the bandwidth of TLP headers
and "len_mode=3" means the final bandwidth data is composed of both TLP
headers and payloads. Default value if not specified is 2'b11.
Example usage of perf::
$# perf stat -e hisi_pcie0_core0/rx_mrd_flux,len_mode=0x1/ sleep 5

2
Documentation/admin-guide/perf/index.rst
View File

@ -19,3 +19,5 @@ Performance monitor support
arm_dsu_pmu
thunderx2-pmu
alibaba_pmu
nvidia-pmu
meson-ddr-pmu

70
Documentation/admin-guide/perf/meson-ddr-pmu.rst Normal file
View File

@ -0,0 +1,70 @@
.. SPDX-License-Identifier: GPL-2.0
===========================================================
Amlogic SoC DDR Bandwidth Performance Monitoring Unit (PMU)
===========================================================
The Amlogic Meson G12 SoC contains a bandwidth monitor inside DRAM controller.
The monitor includes 4 channels. Each channel can count the request accessing
DRAM. The channel can count up to 3 AXI port simultaneously. It can be helpful
to show if the performance bottleneck is on DDR bandwidth.
Currently, this driver supports the following 5 perf events:
+ meson_ddr_bw/total_rw_bytes/
+ meson_ddr_bw/chan_1_rw_bytes/
+ meson_ddr_bw/chan_2_rw_bytes/
+ meson_ddr_bw/chan_3_rw_bytes/
+ meson_ddr_bw/chan_4_rw_bytes/
meson_ddr_bw/chan_{1,2,3,4}_rw_bytes/ events are channel-specific events.
Each channel support filtering, which can let the channel to monitor
individual IP module in SoC.
Below are DDR access request event filter keywords:
+ arm - from CPU
+ vpu_read1 - from OSD + VPP read
+ gpu - from 3D GPU
+ pcie - from PCIe controller
+ hdcp - from HDCP controller
+ hevc_front - from HEVC codec front end
+ usb3_0 - from USB3.0 controller
+ hevc_back - from HEVC codec back end
+ h265enc - from HEVC encoder
+ vpu_read2 - from DI read
+ vpu_write1 - from VDIN write
+ vpu_write2 - from di write
+ vdec - from legacy codec video decoder
+ hcodec - from H264 encoder
+ ge2d - from ge2d
+ spicc1 - from SPI controller 1
+ usb0 - from USB2.0 controller 0
+ dma - from system DMA controller 1
+ arb0 - from arb0
+ sd_emmc_b - from SD eMMC b controller
+ usb1 - from USB2.0 controller 1
+ audio - from Audio module
+ sd_emmc_c - from SD eMMC c controller
+ spicc2 - from SPI controller 2
+ ethernet - from Ethernet controller
Examples:
+ Show the total DDR bandwidth per seconds:
.. code-block:: bash
perf stat -a -e meson_ddr_bw/total_rw_bytes/ -I 1000 sleep 10
+ Show individual DDR bandwidth from CPU and GPU respectively, as well as
sum of them:
.. code-block:: bash
perf stat -a -e meson_ddr_bw/chan_1_rw_bytes,arm=1/ -I 1000 sleep 10
perf stat -a -e meson_ddr_bw/chan_2_rw_bytes,gpu=1/ -I 1000 sleep 10
perf stat -a -e meson_ddr_bw/chan_3_rw_bytes,arm=1,gpu=1/ -I 1000 sleep 10

299
Documentation/admin-guide/perf/nvidia-pmu.rst Normal file
View File

@ -0,0 +1,299 @@
=========================================================
NVIDIA Tegra SoC Uncore Performance Monitoring Unit (PMU)
=========================================================
The NVIDIA Tegra SoC includes various system PMUs to measure key performance
metrics like memory bandwidth, latency, and utilization:
* Scalable Coherency Fabric (SCF)
* NVLink-C2C0
* NVLink-C2C1
* CNVLink
* PCIE
PMU Driver
----------
The PMUs in this document are based on ARM CoreSight PMU Architecture as
described in document: ARM IHI 0091. Since this is a standard architecture, the
PMUs are managed by a common driver "arm-cs-arch-pmu". This driver describes
the available events and configuration of each PMU in sysfs. Please see the
sections below to get the sysfs path of each PMU. Like other uncore PMU drivers,
the driver provides "cpumask" sysfs attribute to show the CPU id used to handle
the PMU event. There is also "associated_cpus" sysfs attribute, which contains a
list of CPUs associated with the PMU instance.
.. _SCF_PMU_Section:
SCF PMU
-------
The SCF PMU monitors system level cache events, CPU traffic, and
strongly-ordered (SO) PCIE write traffic to local/remote memory. Please see
:ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section` for more info about the PMU
traffic coverage.
The events and configuration options of this PMU device are described in sysfs,
see /sys/bus/event_sources/devices/nvidia_scf_pmu_<socket-id>.
Example usage:
* Count event id 0x0 in socket 0::
perf stat -a -e nvidia_scf_pmu_0/event=0x0/
* Count event id 0x0 in socket 1::
perf stat -a -e nvidia_scf_pmu_1/event=0x0/
NVLink-C2C0 PMU
--------------------
The NVLink-C2C0 PMU monitors incoming traffic from a GPU/CPU connected with
NVLink-C2C (Chip-2-Chip) interconnect. The type of traffic captured by this PMU
varies dependent on the chip configuration:
* NVIDIA Grace Hopper Superchip: Hopper GPU is connected with Grace SoC.
In this config, the PMU captures GPU ATS translated or EGM traffic from the GPU.
* NVIDIA Grace CPU Superchip: two Grace CPU SoCs are connected.
In this config, the PMU captures read and relaxed ordered (RO) writes from
PCIE device of the remote SoC.
Please see :ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section` for more info about
the PMU traffic coverage.
The events and configuration options of this PMU device are described in sysfs,
see /sys/bus/event_sources/devices/nvidia_nvlink_c2c0_pmu_<socket-id>.
Example usage:
* Count event id 0x0 from the GPU/CPU connected with socket 0::
perf stat -a -e nvidia_nvlink_c2c0_pmu_0/event=0x0/
* Count event id 0x0 from the GPU/CPU connected with socket 1::
perf stat -a -e nvidia_nvlink_c2c0_pmu_1/event=0x0/
* Count event id 0x0 from the GPU/CPU connected with socket 2::
perf stat -a -e nvidia_nvlink_c2c0_pmu_2/event=0x0/
* Count event id 0x0 from the GPU/CPU connected with socket 3::
perf stat -a -e nvidia_nvlink_c2c0_pmu_3/event=0x0/
NVLink-C2C1 PMU
-------------------
The NVLink-C2C1 PMU monitors incoming traffic from a GPU connected with
NVLink-C2C (Chip-2-Chip) interconnect. This PMU captures untranslated GPU
traffic, in contrast with NvLink-C2C0 PMU that captures ATS translated traffic.
Please see :ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section` for more info about
the PMU traffic coverage.
The events and configuration options of this PMU device are described in sysfs,
see /sys/bus/event_sources/devices/nvidia_nvlink_c2c1_pmu_<socket-id>.
Example usage:
* Count event id 0x0 from the GPU connected with socket 0::
perf stat -a -e nvidia_nvlink_c2c1_pmu_0/event=0x0/
* Count event id 0x0 from the GPU connected with socket 1::
perf stat -a -e nvidia_nvlink_c2c1_pmu_1/event=0x0/
* Count event id 0x0 from the GPU connected with socket 2::
perf stat -a -e nvidia_nvlink_c2c1_pmu_2/event=0x0/
* Count event id 0x0 from the GPU connected with socket 3::
perf stat -a -e nvidia_nvlink_c2c1_pmu_3/event=0x0/
CNVLink PMU
---------------
The CNVLink PMU monitors traffic from GPU and PCIE device on remote sockets
to local memory. For PCIE traffic, this PMU captures read and relaxed ordered
(RO) write traffic. Please see :ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section`
for more info about the PMU traffic coverage.
The events and configuration options of this PMU device are described in sysfs,
see /sys/bus/event_sources/devices/nvidia_cnvlink_pmu_<socket-id>.
Each SoC socket can be connected to one or more sockets via CNVLink. The user can
use "rem_socket" bitmap parameter to select the remote socket(s) to monitor.
Each bit represents the socket number, e.g. "rem_socket=0xE" corresponds to
socket 1 to 3.
/sys/bus/event_sources/devices/nvidia_cnvlink_pmu_<socket-id>/format/rem_socket
shows the valid bits that can be set in the "rem_socket" parameter.
The PMU can not distinguish the remote traffic initiator, therefore it does not
provide filter to select the traffic source to monitor. It reports combined
traffic from remote GPU and PCIE devices.
Example usage:
* Count event id 0x0 for the traffic from remote socket 1, 2, and 3 to socket 0::
perf stat -a -e nvidia_cnvlink_pmu_0/event=0x0,rem_socket=0xE/
* Count event id 0x0 for the traffic from remote socket 0, 2, and 3 to socket 1::
perf stat -a -e nvidia_cnvlink_pmu_1/event=0x0,rem_socket=0xD/
* Count event id 0x0 for the traffic from remote socket 0, 1, and 3 to socket 2::
perf stat -a -e nvidia_cnvlink_pmu_2/event=0x0,rem_socket=0xB/
* Count event id 0x0 for the traffic from remote socket 0, 1, and 2 to socket 3::
perf stat -a -e nvidia_cnvlink_pmu_3/event=0x0,rem_socket=0x7/
PCIE PMU
------------
The PCIE PMU monitors all read/write traffic from PCIE root ports to
local/remote memory. Please see :ref:`NVIDIA_Uncore_PMU_Traffic_Coverage_Section`
for more info about the PMU traffic coverage.
The events and configuration options of this PMU device are described in sysfs,
see /sys/bus/event_sources/devices/nvidia_pcie_pmu_<socket-id>.
Each SoC socket can support multiple root ports. The user can use
"root_port" bitmap parameter to select the port(s) to monitor, i.e.
"root_port=0xF" corresponds to root port 0 to 3.
/sys/bus/event_sources/devices/nvidia_pcie_pmu_<socket-id>/format/root_port
shows the valid bits that can be set in the "root_port" parameter.
Example usage:
* Count event id 0x0 from root port 0 and 1 of socket 0::
perf stat -a -e nvidia_pcie_pmu_0/event=0x0,root_port=0x3/
* Count event id 0x0 from root port 0 and 1 of socket 1::
perf stat -a -e nvidia_pcie_pmu_1/event=0x0,root_port=0x3/
.. _NVIDIA_Uncore_PMU_Traffic_Coverage_Section:
Traffic Coverage
----------------
The PMU traffic coverage may vary dependent on the chip configuration:
* **NVIDIA Grace Hopper Superchip**: Hopper GPU is connected with Grace SoC.
Example configuration with two Grace SoCs::
********************************* *********************************
* SOCKET-A * * SOCKET-B *
* * * *
* :::::::: * * :::::::: *
* : PCIE : * * : PCIE : *
* :::::::: * * :::::::: *
* | * * | *
* | * * | *
* ::::::: ::::::::: * * ::::::::: ::::::: *
* : : : : * * : : : : *
* : GPU :<--NVLink-->: Grace :<---CNVLink--->: Grace :<--NVLink-->: GPU : *
* : : C2C : SoC : * * : SoC : C2C : : *
* ::::::: ::::::::: * * ::::::::: ::::::: *
* | | * * | | *
* | | * * | | *
* &&&&&&&& &&&&&&&& * * &&&&&&&& &&&&&&&& *
* & GMEM & & CMEM & * * & CMEM & & GMEM & *
* &&&&&&&& &&&&&&&& * * &&&&&&&& &&&&&&&& *
* * * *
********************************* *********************************
GMEM = GPU Memory (e.g. HBM)
CMEM = CPU Memory (e.g. LPDDR5X)
|
| Following table contains traffic coverage of Grace SoC PMU in socket-A:
::
+--------------+-------+-----------+-----------+-----+----------+----------+
| | Source |
+ +-------+-----------+-----------+-----+----------+----------+
| Destination | |GPU ATS |GPU Not-ATS| | Socket-B | Socket-B |
| |PCI R/W|Translated,|Translated | CPU | CPU/PCIE1| GPU/PCIE2|
| | |EGM | | | | |
+==============+=======+===========+===========+=====+==========+==========+
| Local | PCIE |NVLink-C2C0|NVLink-C2C1| SCF | SCF PMU | CNVLink |
| SYSRAM/CMEM | PMU |PMU |PMU | PMU | | PMU |
+--------------+-------+-----------+-----------+-----+----------+----------+
| Local GMEM | PCIE | N/A |NVLink-C2C1| SCF | SCF PMU | CNVLink |
| | PMU | |PMU | PMU | | PMU |
+--------------+-------+-----------+-----------+-----+----------+----------+
| Remote | PCIE |NVLink-C2C0|NVLink-C2C1| SCF | | |
| SYSRAM/CMEM | PMU |PMU |PMU | PMU | N/A | N/A |
| over CNVLink | | | | | | |
+--------------+-------+-----------+-----------+-----+----------+----------+
| Remote GMEM | PCIE |NVLink-C2C0|NVLink-C2C1| SCF | | |
| over CNVLink | PMU |PMU |PMU | PMU | N/A | N/A |
+--------------+-------+-----------+-----------+-----+----------+----------+
PCIE1 traffic represents strongly ordered (SO) writes.
PCIE2 traffic represents reads and relaxed ordered (RO) writes.
* **NVIDIA Grace CPU Superchip**: two Grace CPU SoCs are connected.
Example configuration with two Grace SoCs::
******************* *******************
* SOCKET-A * * SOCKET-B *
* * * *
* :::::::: * * :::::::: *
* : PCIE : * * : PCIE : *
* :::::::: * * :::::::: *
* | * * | *
* | * * | *
* ::::::::: * * ::::::::: *
* : : * * : : *
* : Grace :<--------NVLink------->: Grace : *
* : SoC : * C2C * : SoC : *
* ::::::::: * * ::::::::: *
* | * * | *
* | * * | *
* &&&&&&&& * * &&&&&&&& *
* & CMEM & * * & CMEM & *
* &&&&&&&& * * &&&&&&&& *
* * * *
******************* *******************
GMEM = GPU Memory (e.g. HBM)
CMEM = CPU Memory (e.g. LPDDR5X)
|
| Following table contains traffic coverage of Grace SoC PMU in socket-A:
::
+-----------------+-----------+---------+----------+-------------+
| | Source |
+ +-----------+---------+----------+-------------+
| Destination | | | Socket-B | Socket-B |
| | PCI R/W | CPU | CPU/PCIE1| PCIE2 |
| | | | | |
+=================+===========+=========+==========+=============+
| Local | PCIE PMU | SCF PMU | SCF PMU | NVLink-C2C0 |
| SYSRAM/CMEM | | | | PMU |
+-----------------+-----------+---------+----------+-------------+
| Remote | | | | |
| SYSRAM/CMEM | PCIE PMU | SCF PMU | N/A | N/A |
| over NVLink-C2C | | | | |
+-----------------+-----------+---------+----------+-------------+
PCIE1 traffic represents strongly ordered (SO) writes.
PCIE2 traffic represents reads and relaxed ordered (RO) writes.

2
Documentation/arm64/acpi_object_usage.rst
View File

@ -163,7 +163,7 @@ FPDT Section 5.2.23 (signature == "FPDT")
**Firmware Performance Data Table**
Optional, not currently supported.
Optional, useful for boot performance profiling.
GTDT Section 5.2.24 (signature == "GTDT")

7
Documentation/arm64/booting.rst
View File

@ -121,8 +121,9 @@ Header notes:
to the base of DRAM, since memory below it is not
accessible via the linear mapping
1
2MB aligned base may be anywhere in physical
memory
2MB aligned base such that all image_size bytes
counted from the start of the image are within
the 48-bit addressable range of physical memory
Bits 4-63 Reserved.
============= ===============================================================
@ -348,7 +349,7 @@ Before jumping into the kernel, the following conditions must be met:
- HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64)
For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64):
- If EL3 is present:

9
Documentation/arm64/elf_hwcaps.rst
View File

@ -275,6 +275,15 @@ HWCAP2_EBF16
HWCAP2_SVE_EBF16
Functionality implied by ID_AA64ZFR0_EL1.BF16 == 0b0010.
HWCAP2_CSSC
Functionality implied by ID_AA64ISAR2_EL1.CSSC == 0b0001.
HWCAP2_RPRFM
Functionality implied by ID_AA64ISAR2_EL1.RPRFM == 0b0001.
HWCAP2_SVE2P1
Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0010.
4. Unused AT_HWCAP bits
-----------------------

2
Documentation/arm64/silicon-errata.rst
View File

@ -120,6 +120,8 @@ stable kernels.
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 |
+----------------+-----------------+-----------------+-----------------------------+
| ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 |

1
Documentation/arm64/sve.rst
View File

@ -52,6 +52,7 @@ model features for SVE is included in Appendix A.
HWCAP2_SVEBITPERM
HWCAP2_SVESHA3
HWCAP2_SVESM4
HWCAP2_SVE2P1
This list may be extended over time as the SVE architecture evolves.

54
Documentation/devicetree/bindings/perf/amlogic,g12-ddr-pmu.yaml Normal file
View File

@ -0,0 +1,54 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
%YAML 1.2
---
$id: http://devicetree.org/schemas/perf/amlogic,g12-ddr-pmu.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Amlogic G12 DDR performance monitor
maintainers:
- Jiucheng Xu <jiucheng.xu@amlogic.com>
description: |
Amlogic G12 series SoC integrate DDR bandwidth monitor.
A timer is inside and can generate interrupt when timeout.
The bandwidth is counted in the timer ISR. Different platform
has different subset of event format attribute.
properties:
compatible:
enum:
- amlogic,g12a-ddr-pmu
- amlogic,g12b-ddr-pmu
- amlogic,sm1-ddr-pmu
reg:
items:
- description: DMC bandwidth register space.
- description: DMC PLL register space.
interrupts:
items:
- description: The IRQ of the inside timer timeout.
required:
- compatible
- reg
- interrupts
additionalProperties: false
examples:
- |
#include <dt-bindings/interrupt-controller/arm-gic.h>
pmu {
#address-cells=<2>;
#size-cells=<2>;
pmu@ff638000 {
compatible = "amlogic,g12a-ddr-pmu";
reg = <0x0 0xff638000 0x0 0x100>,
<0x0 0xff638c00 0x0 0x100>;
interrupts = <GIC_SPI 52 IRQ_TYPE_EDGE_RISING>;
};
};

12
MAINTAINERS
View File

@ -1093,6 +1093,16 @@ S: Maintained
F: Documentation/hid/amd-sfh*
F: drivers/hid/amd-sfh-hid/
AMLOGIC DDR PMU DRIVER
M: Jiucheng Xu <jiucheng.xu@amlogic.com>
L: linux-amlogic@lists.infradead.org
S: Supported
W: http://www.amlogic.com
F: Documentation/admin-guide/perf/meson-ddr-pmu.rst
F: Documentation/devicetree/bindings/perf/amlogic,g12-ddr-pmu.yaml
F: drivers/perf/amlogic/
F: include/soc/amlogic/
AMPHION VPU CODEC V4L2 DRIVER
M: Ming Qian <ming.qian@nxp.com>
M: Shijie Qin <shijie.qin@nxp.com>
@ -9244,7 +9254,7 @@ F: drivers/misc/hisi_hikey_usb.c
HISILICON PMU DRIVER
M: Shaokun Zhang <zhangshaokun@hisilicon.com>
M: Qi Liu <liuqi115@huawei.com>
M: Jonathan Cameron <jonathan.cameron@huawei.com>
S: Supported
W: http://www.hisilicon.com
F: Documentation/admin-guide/perf/hisi-pcie-pmu.rst

2
Makefile
View File

@ -966,8 +966,10 @@ LDFLAGS_vmlinux += --gc-sections
endif
ifdef CONFIG_SHADOW_CALL_STACK
ifndef CONFIG_DYNAMIC_SCS
CC_FLAGS_SCS := -fsanitize=shadow-call-stack
KBUILD_CFLAGS += $(CC_FLAGS_SCS)
endif
export CC_FLAGS_SCS
endif

7
arch/Kconfig
View File

@ -654,6 +654,13 @@ config SHADOW_CALL_STACK
reading and writing arbitrary memory may be able to locate them
and hijack control flow by modifying the stacks.
config DYNAMIC_SCS
bool
help
Set by the arch code if it relies on code patching to insert the
shadow call stack push and pop instructions rather than on the
compiler.
config LTO
bool
help

49
arch/arm64/Kconfig
View File

@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
config ARM64
def_bool y
select ACPI_APMT if ACPI
select ACPI_CCA_REQUIRED if ACPI
select ACPI_GENERIC_GSI if ACPI
select ACPI_GTDT if ACPI
@ -118,6 +119,7 @@ config ARM64
select CPU_PM if (SUSPEND || CPU_IDLE)
select CRC32
select DCACHE_WORD_ACCESS
select DYNAMIC_FTRACE if FUNCTION_TRACER
select DMA_DIRECT_REMAP
select EDAC_SUPPORT
select FRAME_POINTER
@ -182,8 +184,10 @@ config ARM64
select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
if $(cc-option,-fpatchable-function-entry=2)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
if DYNAMIC_FTRACE_WITH_REGS
if DYNAMIC_FTRACE_WITH_ARGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
@ -234,16 +238,16 @@ config ARM64
help
ARM 64-bit (AArch64) Linux support.
config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS
config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS
def_bool CC_IS_CLANG
# https://github.com/ClangBuiltLinux/linux/issues/1507
depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600))
select HAVE_DYNAMIC_FTRACE_WITH_REGS
select HAVE_DYNAMIC_FTRACE_WITH_ARGS
config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS
config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS
def_bool CC_IS_GCC
depends on $(cc-option,-fpatchable-function-entry=2)
select HAVE_DYNAMIC_FTRACE_WITH_REGS
select HAVE_DYNAMIC_FTRACE_WITH_ARGS
config 64BIT
def_bool y
@ -371,6 +375,9 @@ config KASAN_SHADOW_OFFSET
default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS
default 0xffffffffffffffff
config UNWIND_TABLES
bool
source "arch/arm64/Kconfig.platforms"
menu "Kernel Features"
@ -965,6 +972,22 @@ config ARM64_ERRATUM_2457168
If unsure, say Y.
config ARM64_ERRATUM_2645198
bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption"
default y
help
This option adds the workaround for ARM Cortex-A715 erratum 2645198.
If a Cortex-A715 cpu sees a page mapping permissions change from executable
to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the
next instruction abort caused by permission fault.
Only user-space does executable to non-executable permission transition via
mprotect() system call. Workaround the problem by doing a break-before-make
TLB invalidation, for all changes to executable user space mappings.
If unsure, say Y.
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
@ -1715,7 +1738,6 @@ config ARM64_LSE_ATOMICS
config ARM64_USE_LSE_ATOMICS
bool "Atomic instructions"
depends on JUMP_LABEL
default y
help
As part of the Large System Extensions, ARMv8.1 introduces new
@ -1817,7 +1839,7 @@ config ARM64_PTR_AUTH_KERNEL
# which is only understood by binutils starting with version 2.33.1.
depends on LD_IS_LLD || LD_VERSION >= 23301 || (CC_IS_GCC && GCC_VERSION < 90100)
depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE
depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_ARGS)
help
If the compiler supports the -mbranch-protection or
-msign-return-address flag (e.g. GCC 7 or later), then this option
@ -1827,7 +1849,7 @@ config ARM64_PTR_AUTH_KERNEL
disabled with minimal loss of protection.
This feature works with FUNCTION_GRAPH_TRACER option only if
DYNAMIC_FTRACE_WITH_REGS is enabled.
DYNAMIC_FTRACE_WITH_ARGS is enabled.
config CC_HAS_BRANCH_PROT_PAC_RET
# GCC 9 or later, clang 8 or later
@ -1925,7 +1947,7 @@ config ARM64_BTI_KERNEL
depends on !CC_IS_GCC
# https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9
depends on !CC_IS_CLANG || CLANG_VERSION >= 120000
depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_ARGS)
help
Build the kernel with Branch Target Identification annotations
and enable enforcement of this for kernel code. When this option
@ -2158,6 +2180,15 @@ config ARCH_NR_GPIO
If unsure, leave the default value.
config UNWIND_PATCH_PAC_INTO_SCS
bool "Enable shadow call stack dynamically using code patching"
# needs Clang with https://reviews.llvm.org/D111780 incorporated
depends on CC_IS_CLANG && CLANG_VERSION >= 150000
depends on ARM64_PTR_AUTH_KERNEL && CC_HAS_BRANCH_PROT_PAC_RET
depends on SHADOW_CALL_STACK
select UNWIND_TABLES
select DYNAMIC_SCS
endmenu # "Kernel Features"
menu "Boot options"

17
arch/arm64/Makefile
View File

@ -45,8 +45,13 @@ KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
# Avoid generating .eh_frame* sections.
ifneq ($(CONFIG_UNWIND_TABLES),y)
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
KBUILD_AFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
else
KBUILD_CFLAGS += -fasynchronous-unwind-tables
KBUILD_AFLAGS += -fasynchronous-unwind-tables
endif
ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
prepare: stack_protector_prepare
@ -72,10 +77,16 @@ branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=
# We enable additional protection for leaf functions as there is some
# narrow potential for ROP protection benefits and no substantial
# performance impact has been observed.
PACRET-y := pac-ret+leaf
# Using a shadow call stack in leaf functions is too costly, so avoid PAC there
# as well when we may be patching PAC into SCS
PACRET-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) := pac-ret
ifeq ($(CONFIG_ARM64_BTI_KERNEL),y)
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=pac-ret+leaf+bti
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=$(PACRET-y)+bti
else
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf
branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=$(PACRET-y)
endif
# -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the
# compiler to generate them and consequently to break the single image contract
@ -128,7 +139,7 @@ endif
CHECKFLAGS += -D__aarch64__
ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y)
ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y)
KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY
CC_FLAGS_FTRACE := -fpatchable-function-entry=2
endif

4
arch/arm64/include/asm/alternative-macros.h
View File

@ -224,7 +224,7 @@ alternative_endif
#include <linux/types.h>
static __always_inline bool
alternative_has_feature_likely(unsigned long feature)
alternative_has_feature_likely(const unsigned long feature)
{
compiletime_assert(feature < ARM64_NCAPS,
"feature must be < ARM64_NCAPS");
@ -242,7 +242,7 @@ l_no:
}
static __always_inline bool
alternative_has_feature_unlikely(unsigned long feature)
alternative_has_feature_unlikely(const unsigned long feature)
{
compiletime_assert(feature < ARM64_NCAPS,
"feature must be < ARM64_NCAPS");

33
arch/arm64/include/asm/assembler.h
View File

@ -34,11 +34,6 @@
wx\n .req w\n
.endr
.macro save_and_disable_daif, flags
mrs \flags, daif
msr daifset, #0xf
.endm
.macro disable_daif
msr daifset, #0xf
.endm
@ -47,15 +42,6 @@
msr daifclr, #0xf
.endm
.macro restore_daif, flags:req
msr daif, \flags
.endm
/* IRQ/FIQ are the lowest priority flags, unconditionally unmask the rest. */
.macro enable_da
msr daifclr, #(8 | 4)
.endm
/*
* Save/restore interrupts.
*/
@ -619,17 +605,6 @@ alternative_endif
#endif
.endm
/*
* Perform the reverse of offset_ttbr1.
* bic is used as it can cover the immediate value and, in future, won't need
* to be nop'ed out when dealing with 52-bit kernel VAs.
*/
.macro restore_ttbr1, ttbr
#ifdef CONFIG_ARM64_VA_BITS_52
bic \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
#endif
.endm
/*
* Arrange a physical address in a TTBR register, taking care of 52-bit
* addresses.
@ -660,12 +635,10 @@ alternative_endif
.endm
.macro pte_to_phys, phys, pte
#ifdef CONFIG_ARM64_PA_BITS_52
ubfiz \phys, \pte, #(48 - 16 - 12), #16
bfxil \phys, \pte, #16, #32
lsl \phys, \phys, #16
#else
and \phys, \pte, #PTE_ADDR_MASK
#ifdef CONFIG_ARM64_PA_BITS_52
orr \phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT
and \phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT)
#endif
.endm

3
arch/arm64/include/asm/cpufeature.h
View File

@ -832,7 +832,8 @@ static inline bool system_supports_tlb_range(void)
cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
}
extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
{

2
arch/arm64/include/asm/cputype.h
View File

@ -80,6 +80,7 @@
#define ARM_CPU_PART_CORTEX_X1 0xD44
#define ARM_CPU_PART_CORTEX_A510 0xD46
#define ARM_CPU_PART_CORTEX_A710 0xD47
#define ARM_CPU_PART_CORTEX_A715 0xD4D
#define ARM_CPU_PART_CORTEX_X2 0xD48
#define ARM_CPU_PART_NEOVERSE_N2 0xD49
#define ARM_CPU_PART_CORTEX_A78C 0xD4B
@ -142,6 +143,7 @@
#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
#define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)

7
arch/arm64/include/asm/exception.h
View File

@ -58,7 +58,8 @@ asmlinkage void call_on_irq_stack(struct pt_regs *regs,
asmlinkage void asm_exit_to_user_mode(struct pt_regs *regs);
void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs);
void do_undefinstr(struct pt_regs *regs, unsigned long esr);
void do_el0_undef(struct pt_regs *regs, unsigned long esr);
void do_el1_undef(struct pt_regs *regs, unsigned long esr);
void do_el0_bti(struct pt_regs *regs);
void do_el1_bti(struct pt_regs *regs, unsigned long esr);
void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
@ -67,10 +68,10 @@ void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs);
void do_sve_acc(unsigned long esr, struct pt_regs *regs);
void do_sme_acc(unsigned long esr, struct pt_regs *regs);
void do_fpsimd_exc(unsigned long esr, struct pt_regs *regs);
void do_sysinstr(unsigned long esr, struct pt_regs *regs);
void do_el0_sys(unsigned long esr, struct pt_regs *regs);
void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs);
void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr);
void do_cp15instr(unsigned long esr, struct pt_regs *regs);
void do_el0_cp15(unsigned long esr, struct pt_regs *regs);
int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs);
void do_el0_svc(struct pt_regs *regs);
void do_el0_svc_compat(struct pt_regs *regs);

17
arch/arm64/include/asm/fpsimd.h
View File

@ -56,11 +56,20 @@ extern void fpsimd_signal_preserve_current_state(void);
extern void fpsimd_preserve_current_state(void);
extern void fpsimd_restore_current_state(void);
extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
extern void fpsimd_kvm_prepare(void);
extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state,
void *sve_state, unsigned int sve_vl,
void *za_state, unsigned int sme_vl,
u64 *svcr);
struct cpu_fp_state {
struct user_fpsimd_state *st;
void *sve_state;
void *za_state;
u64 *svcr;
unsigned int sve_vl;
unsigned int sme_vl;
enum fp_type *fp_type;
enum fp_type to_save;
};
extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state);
extern void fpsimd_flush_task_state(struct task_struct *target);
extern void fpsimd_save_and_flush_cpu_state(void);

72
arch/arm64/include/asm/ftrace.h
View File

@ -23,7 +23,7 @@
*/
#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
#define ARCH_SUPPORTS_FTRACE_OPS 1
#else
#define MCOUNT_ADDR ((unsigned long)_mcount)
@ -33,8 +33,7 @@
#define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE
#define FTRACE_PLT_IDX 0
#define FTRACE_REGS_PLT_IDX 1
#define NR_FTRACE_PLTS 2
#define NR_FTRACE_PLTS 1
/*
* Currently, gcc tends to save the link register after the local variables
@ -69,7 +68,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
* Adjust addr to point at the BL in the callsite.
* See ftrace_init_nop() for the callsite sequence.
*/
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS))
return addr + AARCH64_INSN_SIZE;
/*
* addr is the address of the mcount call instruction.
@ -78,10 +77,71 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
return addr;
}
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
struct dyn_ftrace;
struct ftrace_ops;
struct ftrace_regs;
#define arch_ftrace_get_regs(regs) NULL
struct ftrace_regs {
/* x0 - x8 */
unsigned long regs[9];
unsigned long __unused;
unsigned long fp;
unsigned long lr;
unsigned long sp;
unsigned long pc;
};
static __always_inline unsigned long
ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs)
{
return fregs->pc;
}
static __always_inline void
ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
unsigned long pc)
{
fregs->pc = pc;
}
static __always_inline unsigned long
ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
{
return fregs->sp;
}
static __always_inline unsigned long
ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n)
{
if (n < 8)
return fregs->regs[n];
return 0;
}
static __always_inline unsigned long
ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
{
return fregs->regs[0];
}
static __always_inline void
ftrace_regs_set_return_value(struct ftrace_regs *fregs,
unsigned long ret)
{
fregs->regs[0] = ret;
}
static __always_inline void
ftrace_override_function_with_return(struct ftrace_regs *fregs)
{
fregs->pc = fregs->lr;
}
int ftrace_regs_query_register_offset(const char *name);
int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
#define ftrace_init_nop ftrace_init_nop

9
arch/arm64/include/asm/hugetlb.h
View File

@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep);
void __init arm64_hugetlb_cma_reserve(void);
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t new_pte);
#include <asm-generic/hugetlb.h>
#endif /* __ASM_HUGETLB_H */

3
arch/arm64/include/asm/hwcap.h
View File

@ -120,6 +120,9 @@
#define KERNEL_HWCAP_WFXT __khwcap2_feature(WFXT)
#define KERNEL_HWCAP_EBF16 __khwcap2_feature(EBF16)
#define KERNEL_HWCAP_SVE_EBF16 __khwcap2_feature(SVE_EBF16)
#define KERNEL_HWCAP_CSSC __khwcap2_feature(CSSC)
#define KERNEL_HWCAP_RPRFM __khwcap2_feature(RPRFM)
#define KERNEL_HWCAP_SVE2P1 __khwcap2_feature(SVE2P1)
/*
* This yields a mask that user programs can use to figure out what

158
arch/arm64/include/asm/insn.h
View File

@ -13,31 +13,6 @@
#include <asm/insn-def.h>
#ifndef __ASSEMBLY__
/*
* ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
* Section C3.1 "A64 instruction index by encoding":
* AArch64 main encoding table
* Bit position
* 28 27 26 25 Encoding Group
* 0 0 - - Unallocated
* 1 0 0 - Data processing, immediate
* 1 0 1 - Branch, exception generation and system instructions
* - 1 - 0 Loads and stores
* - 1 0 1 Data processing - register
* 0 1 1 1 Data processing - SIMD and floating point
* 1 1 1 1 Data processing - SIMD and floating point
* "-" means "don't care"
*/
enum aarch64_insn_encoding_class {
AARCH64_INSN_CLS_UNKNOWN, /* UNALLOCATED */
AARCH64_INSN_CLS_SVE, /* SVE instructions */
AARCH64_INSN_CLS_DP_IMM, /* Data processing - immediate */
AARCH64_INSN_CLS_DP_REG, /* Data processing - register */
AARCH64_INSN_CLS_DP_FPSIMD, /* Data processing - SIMD and FP */
AARCH64_INSN_CLS_LDST, /* Loads and stores */
AARCH64_INSN_CLS_BR_SYS, /* Branch, exception generation and
* system instructions */
};
enum aarch64_insn_hint_cr_op {
AARCH64_INSN_HINT_NOP = 0x0 << 5,
@ -326,6 +301,23 @@ static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
return (val); \
}
/*
* ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
* Section C3.1 "A64 instruction index by encoding":
* AArch64 main encoding table
* Bit position
* 28 27 26 25 Encoding Group
* 0 0 - - Unallocated
* 1 0 0 - Data processing, immediate
* 1 0 1 - Branch, exception generation and system instructions
* - 1 - 0 Loads and stores
* - 1 0 1 Data processing - register
* 0 1 1 1 Data processing - SIMD and floating point
* 1 1 1 1 Data processing - SIMD and floating point
* "-" means "don't care"
*/
__AARCH64_INSN_FUNCS(class_branch_sys, 0x1c000000, 0x14000000)
__AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000)
__AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000)
__AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000)
@ -431,58 +423,122 @@ __AARCH64_INSN_FUNCS(pssbb, 0xFFFFFFFF, 0xD503349F)
#undef __AARCH64_INSN_FUNCS
bool aarch64_insn_is_steppable_hint(u32 insn);
bool aarch64_insn_is_branch_imm(u32 insn);
static inline bool aarch64_insn_is_adr_adrp(u32 insn)
static __always_inline bool aarch64_insn_is_steppable_hint(u32 insn)
{
return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
if (!aarch64_insn_is_hint(insn))
return false;
switch (insn & 0xFE0) {
case AARCH64_INSN_HINT_XPACLRI:
case AARCH64_INSN_HINT_PACIA_1716:
case AARCH64_INSN_HINT_PACIB_1716:
case AARCH64_INSN_HINT_PACIAZ:
case AARCH64_INSN_HINT_PACIASP:
case AARCH64_INSN_HINT_PACIBZ:
case AARCH64_INSN_HINT_PACIBSP:
case AARCH64_INSN_HINT_BTI:
case AARCH64_INSN_HINT_BTIC:
case AARCH64_INSN_HINT_BTIJ:
case AARCH64_INSN_HINT_BTIJC:
case AARCH64_INSN_HINT_NOP:
return true;
default:
return false;
}
}
static inline bool aarch64_insn_is_dsb(u32 insn)
static __always_inline bool aarch64_insn_is_branch(u32 insn)
{
return aarch64_insn_is_dsb_base(insn) || aarch64_insn_is_dsb_nxs(insn);
/* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */
return aarch64_insn_is_b(insn) ||
aarch64_insn_is_bl(insn) ||
aarch64_insn_is_cbz(insn) ||
aarch64_insn_is_cbnz(insn) ||
aarch64_insn_is_tbz(insn) ||
aarch64_insn_is_tbnz(insn) ||
aarch64_insn_is_ret(insn) ||
aarch64_insn_is_ret_auth(insn) ||
aarch64_insn_is_br(insn) ||
aarch64_insn_is_br_auth(insn) ||
aarch64_insn_is_blr(insn) ||
aarch64_insn_is_blr_auth(insn) ||
aarch64_insn_is_bcond(insn);
}
static inline bool aarch64_insn_is_barrier(u32 insn)
static __always_inline bool aarch64_insn_is_branch_imm(u32 insn)
{
return aarch64_insn_is_dmb(insn) || aarch64_insn_is_dsb(insn) ||
aarch64_insn_is_isb(insn) || aarch64_insn_is_sb(insn) ||
aarch64_insn_is_clrex(insn) || aarch64_insn_is_ssbb(insn) ||
return aarch64_insn_is_b(insn) ||
aarch64_insn_is_bl(insn) ||
aarch64_insn_is_tbz(insn) ||
aarch64_insn_is_tbnz(insn) ||
aarch64_insn_is_cbz(insn) ||
aarch64_insn_is_cbnz(insn) ||
aarch64_insn_is_bcond(insn);
}
static __always_inline bool aarch64_insn_is_adr_adrp(u32 insn)
{
return aarch64_insn_is_adr(insn) ||
aarch64_insn_is_adrp(insn);
}
static __always_inline bool aarch64_insn_is_dsb(u32 insn)
{
return aarch64_insn_is_dsb_base(insn) ||
aarch64_insn_is_dsb_nxs(insn);
}
static __always_inline bool aarch64_insn_is_barrier(u32 insn)
{
return aarch64_insn_is_dmb(insn) ||
aarch64_insn_is_dsb(insn) ||
aarch64_insn_is_isb(insn) ||
aarch64_insn_is_sb(insn) ||
aarch64_insn_is_clrex(insn) ||
aarch64_insn_is_ssbb(insn) ||
aarch64_insn_is_pssbb(insn);
}
static inline bool aarch64_insn_is_store_single(u32 insn)
static __always_inline bool aarch64_insn_is_store_single(u32 insn)
{
return aarch64_insn_is_store_imm(insn) ||
aarch64_insn_is_store_pre(insn) ||
aarch64_insn_is_store_post(insn);
}
static inline bool aarch64_insn_is_store_pair(u32 insn)
static __always_inline bool aarch64_insn_is_store_pair(u32 insn)
{
return aarch64_insn_is_stp(insn) ||
aarch64_insn_is_stp_pre(insn) ||
aarch64_insn_is_stp_post(insn);
}
static inline bool aarch64_insn_is_load_single(u32 insn)
static __always_inline bool aarch64_insn_is_load_single(u32 insn)
{
return aarch64_insn_is_load_imm(insn) ||
aarch64_insn_is_load_pre(insn) ||
aarch64_insn_is_load_post(insn);
}
static inline bool aarch64_insn_is_load_pair(u32 insn)
static __always_inline bool aarch64_insn_is_load_pair(u32 insn)
{
return aarch64_insn_is_ldp(insn) ||
aarch64_insn_is_ldp_pre(insn) ||
aarch64_insn_is_ldp_post(insn);
}
static __always_inline bool aarch64_insn_uses_literal(u32 insn)
{
/* ldr/ldrsw (literal), prfm */
return aarch64_insn_is_ldr_lit(insn) ||
aarch64_insn_is_ldrsw_lit(insn) ||
aarch64_insn_is_adr_adrp(insn) ||
aarch64_insn_is_prfm_lit(insn);
}
enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
bool aarch64_insn_uses_literal(u32 insn);
bool aarch64_insn_is_branch(u32 insn);
u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn);
u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type,
u32 insn, u64 imm);
@ -496,8 +552,18 @@ u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr,
enum aarch64_insn_branch_type type);
u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
enum aarch64_insn_condition cond);
u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op);
u32 aarch64_insn_gen_nop(void);
static __always_inline u32
aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op)
{
return aarch64_insn_get_hint_value() | op;
}
static __always_inline u32 aarch64_insn_gen_nop(void)
{
return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP);
}
u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
enum aarch64_insn_branch_type type);
u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
@ -580,10 +646,6 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant,
enum aarch64_insn_register Rn,
enum aarch64_insn_register Rd,
u8 lsb);
u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
enum aarch64_insn_prfm_type type,
enum aarch64_insn_prfm_target target,
enum aarch64_insn_prfm_policy policy);
#ifdef CONFIG_ARM64_LSE_ATOMICS
u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result,
enum aarch64_insn_register address,

8
arch/arm64/include/asm/jump_label.h
View File

@ -15,8 +15,8 @@
#define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE
static __always_inline bool arch_static_branch(struct static_key *key,
bool branch)
static __always_inline bool arch_static_branch(struct static_key * const key,
const bool branch)
{
asm_volatile_goto(
"1: nop \n\t"
@ -32,8 +32,8 @@ l_yes:
return true;
}
static __always_inline bool arch_static_branch_jump(struct static_key *key,
bool branch)
static __always_inline bool arch_static_branch_jump(struct static_key * const key,
const bool branch)
{
asm_volatile_goto(
"1: b %l[l_yes] \n\t"

11
arch/arm64/include/asm/kernel-pgtable.h
View File

@ -18,11 +18,6 @@
* with 4K (section size = 2M) but not with 16K (section size = 32M) or
* 64K (section size = 512M).
*/
#ifdef CONFIG_ARM64_4K_PAGES
#define ARM64_KERNEL_USES_PMD_MAPS 1
#else
#define ARM64_KERNEL_USES_PMD_MAPS 0
#endif
/*
* The idmap and swapper page tables need some space reserved in the kernel
@ -34,7 +29,7 @@
* VA range, so pages required to map highest possible PA are reserved in all
* cases.
*/
#if ARM64_KERNEL_USES_PMD_MAPS
#ifdef CONFIG_ARM64_4K_PAGES
#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1)
#else
#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS)
@ -96,7 +91,7 @@
#define INIT_IDMAP_DIR_PAGES EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1)
/* Initial memory map size */
#if ARM64_KERNEL_USES_PMD_MAPS
#ifdef CONFIG_ARM64_4K_PAGES
#define SWAPPER_BLOCK_SHIFT PMD_SHIFT
#define SWAPPER_BLOCK_SIZE PMD_SIZE
#define SWAPPER_TABLE_SHIFT PUD_SHIFT
@ -112,7 +107,7 @@
#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
#if ARM64_KERNEL_USES_PMD_MAPS
#ifdef CONFIG_ARM64_4K_PAGES
#define SWAPPER_RW_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS)
#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY)
#else

12
arch/arm64/include/asm/kvm_host.h
View File

@ -306,8 +306,18 @@ struct vcpu_reset_state {
struct kvm_vcpu_arch {
struct kvm_cpu_context ctxt;
/* Guest floating point state */
/*
* Guest floating point state
*
* The architecture has two main floating point extensions,
* the original FPSIMD and SVE. These have overlapping
* register views, with the FPSIMD V registers occupying the
* low 128 bits of the SVE Z registers. When the core
* floating point code saves the register state of a task it
* records which view it saved in fp_type.
*/
void *sve_state;
enum fp_type fp_type;
unsigned int sve_max_vl;
u64 svcr;

1
arch/arm64/include/asm/lse.h
View File

@ -10,7 +10,6 @@
#include <linux/compiler_types.h>
#include <linux/export.h>
#include <linux/jump_label.h>
#include <linux/stringify.h>
#include <asm/alternative.h>
#include <asm/alternative-macros.h>

10
arch/arm64/include/asm/mmu_context.h
View File

@ -18,6 +18,7 @@
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/daifflags.h>
#include <asm/proc-fns.h>
#include <asm-generic/mm_hooks.h>
#include <asm/cputype.h>
@ -152,6 +153,7 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
typedef void (ttbr_replace_func)(phys_addr_t);
extern ttbr_replace_func idmap_cpu_replace_ttbr1;
ttbr_replace_func *replace_phys;
unsigned long daif;
/* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
@ -171,7 +173,15 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap)
replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
__cpu_install_idmap(idmap);
/*
* We really don't want to take *any* exceptions while TTBR1 is
* in the process of being replaced so mask everything.
*/
daif = local_daif_save();
replace_phys(ttbr1);
local_daif_restore(daif);
cpu_uninstall_idmap();
}

8
arch/arm64/include/asm/module.lds.h
View File

@ -17,4 +17,12 @@ SECTIONS {
*/
.text.hot : { *(.text.hot) }
#endif
#ifdef CONFIG_UNWIND_TABLES
/*
* Currently, we only use unwind info at module load time, so we can
* put it into the .init allocation.
*/
.init.eh_frame : { *(.eh_frame) }
#endif
}

1
arch/arm64/include/asm/pgtable-hwdef.h
View File

@ -159,6 +159,7 @@
#ifdef CONFIG_ARM64_PA_BITS_52
#define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12)
#define PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH)
#define PTE_ADDR_HIGH_SHIFT 36
#else
#define PTE_ADDR_MASK PTE_ADDR_LOW
#endif

14
arch/arm64/include/asm/pgtable.h
View File

@ -77,11 +77,11 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
static inline phys_addr_t __pte_to_phys(pte_t pte)
{
return (pte_val(pte) & PTE_ADDR_LOW) |
((pte_val(pte) & PTE_ADDR_HIGH) << 36);
((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT);
}
static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
{
return (phys | (phys >> 36)) & PTE_ADDR_MASK;
return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PTE_ADDR_MASK;
}
#else
#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_MASK)
@ -609,7 +609,6 @@ extern pgd_t init_pg_dir[PTRS_PER_PGD];
extern pgd_t init_pg_end[];
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_end[];
extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
extern pgd_t reserved_pg_dir[PTRS_PER_PGD];
@ -1096,6 +1095,15 @@ static inline bool pud_sect_supported(void)
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
#define ptep_modify_prot_start ptep_modify_prot_start
extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
#define ptep_modify_prot_commit ptep_modify_prot_commit
extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t new_pte);
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */

24
arch/arm64/include/asm/processor.h
View File

@ -122,6 +122,12 @@ enum vec_type {
ARM64_VEC_MAX,
};
enum fp_type {
FP_STATE_CURRENT, /* Save based on current task state. */
FP_STATE_FPSIMD,
FP_STATE_SVE,
};
struct cpu_context {
unsigned long x19;
unsigned long x20;
@ -152,6 +158,7 @@ struct thread_struct {
struct user_fpsimd_state fpsimd_state;
} uw;
enum fp_type fp_type; /* registers FPSIMD or SVE? */
unsigned int fpsimd_cpu;
void *sve_state; /* SVE registers, if any */
void *za_state; /* ZA register, if any */
@ -308,13 +315,13 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
}
#endif
static inline bool is_ttbr0_addr(unsigned long addr)
static __always_inline bool is_ttbr0_addr(unsigned long addr)
{
/* entry assembly clears tags for TTBR0 addrs */
return addr < TASK_SIZE;
}
static inline bool is_ttbr1_addr(unsigned long addr)
static __always_inline bool is_ttbr1_addr(unsigned long addr)
{
/* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */
return arch_kasan_reset_tag(addr) >= PAGE_OFFSET;
@ -396,18 +403,5 @@ long get_tagged_addr_ctrl(struct task_struct *task);
#define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current)
#endif
/*
* For CONFIG_GCC_PLUGIN_STACKLEAK
*
* These need to be macros because otherwise we get stuck in a nightmare
* of header definitions for the use of task_stack_page.
*/
/*
* The top of the current task's task stack
*/
#define current_top_of_stack() ((unsigned long)current->stack + THREAD_SIZE)
#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1))
#endif /* __ASSEMBLY__ */
#endif /* __ASM_PROCESSOR_H */

49
arch/arm64/include/asm/scs.h
View File

@ -5,6 +5,7 @@
#ifdef __ASSEMBLY__
#include <asm/asm-offsets.h>
#include <asm/sysreg.h>
#ifdef CONFIG_SHADOW_CALL_STACK
scs_sp .req x18
@ -24,6 +25,54 @@
.endm
#endif /* CONFIG_SHADOW_CALL_STACK */
#else
#include <linux/scs.h>
#include <asm/cpufeature.h>
#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
static inline bool should_patch_pac_into_scs(void)
{
u64 reg;
/*
* We only enable the shadow call stack dynamically if we are running
* on a system that does not implement PAC or BTI. PAC and SCS provide
* roughly the same level of protection, and BTI relies on the PACIASP
* instructions serving as landing pads, preventing us from patching
* those instructions into something else.
*/
reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1);
if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) |
SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg))
return false;
reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1);
if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg))
return false;
if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) {
reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1);
if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT))
return false;
}
return true;
}
static inline void dynamic_scs_init(void)
{
if (should_patch_pac_into_scs()) {
pr_info("Enabling dynamic shadow call stack\n");
static_branch_enable(&dynamic_scs_enabled);
}
}
#else
static inline void dynamic_scs_init(void) {}
#endif
int scs_patch(const u8 eh_frame[], int size);
#endif /* __ASSEMBLY __ */
#endif /* _ASM_SCS_H */

2
arch/arm64/include/asm/spectre.h
View File

@ -26,6 +26,7 @@ enum mitigation_state {
SPECTRE_VULNERABLE,
};
struct pt_regs;
struct task_struct;
/*
@ -98,5 +99,6 @@ enum mitigation_state arm64_get_spectre_bhb_state(void);
bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope);
u8 spectre_bhb_loop_affected(int scope);
void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused);
bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr);
#endif /* __ASSEMBLY__ */
#endif /* __ASM_SPECTRE_H */

2
arch/arm64/include/asm/stacktrace.h
View File

@ -57,6 +57,8 @@ static inline bool on_task_stack(const struct task_struct *tsk,
return stackinfo_on_stack(&info, sp, size);
}
#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1))
#ifdef CONFIG_VMAP_STACK
DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);

150
arch/arm64/include/asm/sysreg.h
View File

@ -90,20 +90,24 @@
*/
#define pstate_field(op1, op2) ((op1) << Op1_shift | (op2) << Op2_shift)
#define PSTATE_Imm_shift CRm_shift
#define SET_PSTATE(x, r) __emit_inst(0xd500401f | PSTATE_ ## r | ((!!x) << PSTATE_Imm_shift))
#define PSTATE_PAN pstate_field(0, 4)
#define PSTATE_UAO pstate_field(0, 3)
#define PSTATE_SSBS pstate_field(3, 1)
#define PSTATE_DIT pstate_field(3, 2)
#define PSTATE_TCO pstate_field(3, 4)
#define SET_PSTATE_PAN(x) __emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
#define SET_PSTATE_UAO(x) __emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
#define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
#define SET_PSTATE_TCO(x) __emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift))
#define SET_PSTATE_PAN(x) SET_PSTATE((x), PAN)
#define SET_PSTATE_UAO(x) SET_PSTATE((x), UAO)
#define SET_PSTATE_SSBS(x) SET_PSTATE((x), SSBS)
#define SET_PSTATE_DIT(x) SET_PSTATE((x), DIT)
#define SET_PSTATE_TCO(x) SET_PSTATE((x), TCO)
#define set_pstate_pan(x) asm volatile(SET_PSTATE_PAN(x))
#define set_pstate_uao(x) asm volatile(SET_PSTATE_UAO(x))
#define set_pstate_ssbs(x) asm volatile(SET_PSTATE_SSBS(x))
#define set_pstate_dit(x) asm volatile(SET_PSTATE_DIT(x))
#define __SYS_BARRIER_INSN(CRm, op2, Rt) \
__emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
@ -165,31 +169,6 @@
#define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5)
#define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6)
#define SYS_ID_PFR0_EL1 sys_reg(3, 0, 0, 1, 0)
#define SYS_ID_PFR1_EL1 sys_reg(3, 0, 0, 1, 1)
#define SYS_ID_PFR2_EL1 sys_reg(3, 0, 0, 3, 4)
#define SYS_ID_DFR0_EL1 sys_reg(3, 0, 0, 1, 2)
#define SYS_ID_DFR1_EL1 sys_reg(3, 0, 0, 3, 5)
#define SYS_ID_AFR0_EL1 sys_reg(3, 0, 0, 1, 3)
#define SYS_ID_MMFR0_EL1 sys_reg(3, 0, 0, 1, 4)
#define SYS_ID_MMFR1_EL1 sys_reg(3, 0, 0, 1, 5)
#define SYS_ID_MMFR2_EL1 sys_reg(3, 0, 0, 1, 6)
#define SYS_ID_MMFR3_EL1 sys_reg(3, 0, 0, 1, 7)
#define SYS_ID_MMFR4_EL1 sys_reg(3, 0, 0, 2, 6)
#define SYS_ID_MMFR5_EL1 sys_reg(3, 0, 0, 3, 6)
#define SYS_ID_ISAR0_EL1 sys_reg(3, 0, 0, 2, 0)
#define SYS_ID_ISAR1_EL1 sys_reg(3, 0, 0, 2, 1)
#define SYS_ID_ISAR2_EL1 sys_reg(3, 0, 0, 2, 2)
#define SYS_ID_ISAR3_EL1 sys_reg(3, 0, 0, 2, 3)
#define SYS_ID_ISAR4_EL1 sys_reg(3, 0, 0, 2, 4)
#define SYS_ID_ISAR5_EL1 sys_reg(3, 0, 0, 2, 5)
#define SYS_ID_ISAR6_EL1 sys_reg(3, 0, 0, 2, 7)
#define SYS_MVFR0_EL1 sys_reg(3, 0, 0, 3, 0)
#define SYS_MVFR1_EL1 sys_reg(3, 0, 0, 3, 1)
#define SYS_MVFR2_EL1 sys_reg(3, 0, 0, 3, 2)
#define SYS_ACTLR_EL1 sys_reg(3, 0, 1, 0, 1)
#define SYS_RGSR_EL1 sys_reg(3, 0, 1, 0, 5)
#define SYS_GCR_EL1 sys_reg(3, 0, 1, 0, 6)
@ -692,112 +671,6 @@
#define ID_AA64MMFR0_EL1_PARANGE_MAX ID_AA64MMFR0_EL1_PARANGE_48
#endif
#define ID_DFR0_PERFMON_SHIFT 24
#define ID_DFR0_PERFMON_8_0 0x3
#define ID_DFR0_PERFMON_8_1 0x4
#define ID_DFR0_PERFMON_8_4 0x5
#define ID_DFR0_PERFMON_8_5 0x6
#define ID_ISAR4_SWP_FRAC_SHIFT 28
#define ID_ISAR4_PSR_M_SHIFT 24
#define ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT 20
#define ID_ISAR4_BARRIER_SHIFT 16
#define ID_ISAR4_SMC_SHIFT 12
#define ID_ISAR4_WRITEBACK_SHIFT 8
#define ID_ISAR4_WITHSHIFTS_SHIFT 4
#define ID_ISAR4_UNPRIV_SHIFT 0
#define ID_DFR1_MTPMU_SHIFT 0
#define ID_ISAR0_DIVIDE_SHIFT 24
#define ID_ISAR0_DEBUG_SHIFT 20
#define ID_ISAR0_COPROC_SHIFT 16
#define ID_ISAR0_CMPBRANCH_SHIFT 12
#define ID_ISAR0_BITFIELD_SHIFT 8
#define ID_ISAR0_BITCOUNT_SHIFT 4
#define ID_ISAR0_SWAP_SHIFT 0
#define ID_ISAR5_RDM_SHIFT 24
#define ID_ISAR5_CRC32_SHIFT 16
#define ID_ISAR5_SHA2_SHIFT 12
#define ID_ISAR5_SHA1_SHIFT 8
#define ID_ISAR5_AES_SHIFT 4
#define ID_ISAR5_SEVL_SHIFT 0
#define ID_ISAR6_I8MM_SHIFT 24
#define ID_ISAR6_BF16_SHIFT 20
#define ID_ISAR6_SPECRES_SHIFT 16
#define ID_ISAR6_SB_SHIFT 12
#define ID_ISAR6_FHM_SHIFT 8
#define ID_ISAR6_DP_SHIFT 4
#define ID_ISAR6_JSCVT_SHIFT 0
#define ID_MMFR0_INNERSHR_SHIFT 28
#define ID_MMFR0_FCSE_SHIFT 24
#define ID_MMFR0_AUXREG_SHIFT 20
#define ID_MMFR0_TCM_SHIFT 16
#define ID_MMFR0_SHARELVL_SHIFT 12
#define ID_MMFR0_OUTERSHR_SHIFT 8
#define ID_MMFR0_PMSA_SHIFT 4
#define ID_MMFR0_VMSA_SHIFT 0
#define ID_MMFR4_EVT_SHIFT 28
#define ID_MMFR4_CCIDX_SHIFT 24
#define ID_MMFR4_LSM_SHIFT 20
#define ID_MMFR4_HPDS_SHIFT 16
#define ID_MMFR4_CNP_SHIFT 12
#define ID_MMFR4_XNX_SHIFT 8
#define ID_MMFR4_AC2_SHIFT 4
#define ID_MMFR4_SPECSEI_SHIFT 0
#define ID_MMFR5_ETS_SHIFT 0
#define ID_PFR0_DIT_SHIFT 24
#define ID_PFR0_CSV2_SHIFT 16
#define ID_PFR0_STATE3_SHIFT 12
#define ID_PFR0_STATE2_SHIFT 8
#define ID_PFR0_STATE1_SHIFT 4
#define ID_PFR0_STATE0_SHIFT 0
#define ID_DFR0_PERFMON_SHIFT 24
#define ID_DFR0_MPROFDBG_SHIFT 20
#define ID_DFR0_MMAPTRC_SHIFT 16
#define ID_DFR0_COPTRC_SHIFT 12
#define ID_DFR0_MMAPDBG_SHIFT 8
#define ID_DFR0_COPSDBG_SHIFT 4
#define ID_DFR0_COPDBG_SHIFT 0
#define ID_PFR2_SSBS_SHIFT 4
#define ID_PFR2_CSV3_SHIFT 0
#define MVFR0_FPROUND_SHIFT 28
#define MVFR0_FPSHVEC_SHIFT 24
#define MVFR0_FPSQRT_SHIFT 20
#define MVFR0_FPDIVIDE_SHIFT 16
#define MVFR0_FPTRAP_SHIFT 12
#define MVFR0_FPDP_SHIFT 8
#define MVFR0_FPSP_SHIFT 4
#define MVFR0_SIMD_SHIFT 0
#define MVFR1_SIMDFMAC_SHIFT 28
#define MVFR1_FPHP_SHIFT 24
#define MVFR1_SIMDHP_SHIFT 20
#define MVFR1_SIMDSP_SHIFT 16
#define MVFR1_SIMDINT_SHIFT 12
#define MVFR1_SIMDLS_SHIFT 8
#define MVFR1_FPDNAN_SHIFT 4
#define MVFR1_FPFTZ_SHIFT 0
#define ID_PFR1_GIC_SHIFT 28
#define ID_PFR1_VIRT_FRAC_SHIFT 24
#define ID_PFR1_SEC_FRAC_SHIFT 20
#define ID_PFR1_GENTIMER_SHIFT 16
#define ID_PFR1_VIRTUALIZATION_SHIFT 12
#define ID_PFR1_MPROGMOD_SHIFT 8
#define ID_PFR1_SECURITY_SHIFT 4
#define ID_PFR1_PROGMOD_SHIFT 0
#if defined(CONFIG_ARM64_4K_PAGES)
#define ID_AA64MMFR0_EL1_TGRAN_SHIFT ID_AA64MMFR0_EL1_TGRAN4_SHIFT
#define ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN
@ -815,9 +688,6 @@
#define ID_AA64MMFR0_EL1_TGRAN_2_SHIFT ID_AA64MMFR0_EL1_TGRAN64_2_SHIFT
#endif
#define MVFR2_FPMISC_SHIFT 4
#define MVFR2_SIMDMISC_SHIFT 0
#define CPACR_EL1_FPEN_EL1EN (BIT(20)) /* enable EL1 access */
#define CPACR_EL1_FPEN_EL0EN (BIT(21)) /* enable EL0 access, if EL1EN set */
@ -851,10 +721,6 @@
#define SYS_RGSR_EL1_SEED_SHIFT 8
#define SYS_RGSR_EL1_SEED_MASK 0xffffUL
/* GMID_EL1 field definitions */
#define GMID_EL1_BS_SHIFT 0
#define GMID_EL1_BS_SIZE 4
/* TFSR{,E0}_EL1 bit definitions */
#define SYS_TFSR_EL1_TF0_SHIFT 0
#define SYS_TFSR_EL1_TF1_SHIFT 1

19
arch/arm64/include/asm/traps.h
View File

@ -13,17 +13,16 @@
struct pt_regs;
struct undef_hook {
struct list_head node;
u32 instr_mask;
u32 instr_val;
u64 pstate_mask;
u64 pstate_val;
int (*fn)(struct pt_regs *regs, u32 instr);
};
#ifdef CONFIG_ARMV8_DEPRECATED
bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn);
#else
static inline bool
try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn)
{
return false;
}
#endif /* CONFIG_ARMV8_DEPRECATED */
void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
void force_signal_inject(int signal, int code, unsigned long address, unsigned long err);
void arm64_notify_segfault(unsigned long addr);
void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str);

2
arch/arm64/include/asm/uprobes.h
View File

@ -12,7 +12,7 @@
#define MAX_UINSN_BYTES AARCH64_INSN_SIZE
#define UPROBE_SWBP_INSN BRK64_OPCODE_UPROBES
#define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES)
#define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE
#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES

3
arch/arm64/include/uapi/asm/hwcap.h
View File

@ -93,5 +93,8 @@
#define HWCAP2_WFXT (1UL << 31)
#define HWCAP2_EBF16 (1UL << 32)
#define HWCAP2_SVE_EBF16 (1UL << 33)
#define HWCAP2_CSSC (1UL << 34)
#define HWCAP2_RPRFM (1UL << 35)
#define HWCAP2_SVE2P1 (1UL << 36)
#endif /* _UAPI__ASM_HWCAP_H */

4
arch/arm64/include/uapi/asm/sigcontext.h
View File

@ -62,6 +62,10 @@ struct sigcontext {
* context. Such structures must be placed after the rt_sigframe on the stack
* and be 16-byte aligned. The last structure must be a dummy one with the
* magic and size set to 0.
*
* Note that the values allocated for use as magic should be chosen to
* be meaningful in ASCII to aid manual parsing, ZA doesn't follow this
* convention due to oversight but it should be observed for future additions.
*/
struct _aarch64_ctx {
__u32 magic;

2
arch/arm64/kernel/Makefile
View File

@ -80,6 +80,8 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o
obj-$(CONFIG_ARM64_MTE) += mte.o
obj-y += vdso-wrap.o
obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o
obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o
CFLAGS_patch-scs.o += -mbranch-protection=none
# Force dependency (vdso*-wrap.S includes vdso.so through incbin)
$(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so

6
arch/arm64/kernel/alternative.c
View File

@ -196,7 +196,7 @@ static void __apply_alternatives(const struct alt_region *region,
}
}
void apply_alternatives_vdso(void)
static void __init apply_alternatives_vdso(void)
{
struct alt_region region;
const struct elf64_hdr *hdr;
@ -220,7 +220,7 @@ void apply_alternatives_vdso(void)
__apply_alternatives(&region, false, &all_capabilities[0]);
}
static const struct alt_region kernel_alternatives = {
static const struct alt_region kernel_alternatives __initconst = {
.begin = (struct alt_instr *)__alt_instructions,
.end = (struct alt_instr *)__alt_instructions_end,
};
@ -229,7 +229,7 @@ static const struct alt_region kernel_alternatives = {
* We might be patching the stop_machine state machine, so implement a
* really simple polling protocol here.
*/
static int __apply_alternatives_multi_stop(void *unused)
static int __init __apply_alternatives_multi_stop(void *unused)
{
/* We always have a CPU 0 at this point (__init) */
if (smp_processor_id()) {

569
arch/arm64/kernel/armv8_deprecated.c
View File

@ -17,7 +17,6 @@
#include <asm/sysreg.h>
#include <asm/system_misc.h>
#include <asm/traps.h>
#include <asm/kprobes.h>
#define CREATE_TRACE_POINTS
#include "trace-events-emulation.h"
@ -39,226 +38,46 @@ enum insn_emulation_mode {
enum legacy_insn_status {
INSN_DEPRECATED,
INSN_OBSOLETE,
};
struct insn_emulation_ops {
const char *name;
enum legacy_insn_status status;
struct undef_hook *hooks;
int (*set_hw_mode)(bool enable);
INSN_UNAVAILABLE,
};
struct insn_emulation {
struct list_head node;
struct insn_emulation_ops *ops;
const char *name;
enum legacy_insn_status status;
bool (*try_emulate)(struct pt_regs *regs,
u32 insn);
int (*set_hw_mode)(bool enable);
int current_mode;
int min;
int max;
/*
* sysctl for this emulation + a sentinal entry.
*/
struct ctl_table sysctl[2];
};
static LIST_HEAD(insn_emulation);
static int nr_insn_emulated __initdata;
static DEFINE_RAW_SPINLOCK(insn_emulation_lock);
static DEFINE_MUTEX(insn_emulation_mutex);
#define ARM_OPCODE_CONDTEST_FAIL 0
#define ARM_OPCODE_CONDTEST_PASS 1
#define ARM_OPCODE_CONDTEST_UNCOND 2
static void register_emulation_hooks(struct insn_emulation_ops *ops)
#define ARM_OPCODE_CONDITION_UNCOND 0xf
static unsigned int __maybe_unused aarch32_check_condition(u32 opcode, u32 psr)
{
struct undef_hook *hook;
u32 cc_bits = opcode >> 28;
BUG_ON(!ops->hooks);
for (hook = ops->hooks; hook->instr_mask; hook++)
register_undef_hook(hook);
pr_notice("Registered %s emulation handler\n", ops->name);
}
static void remove_emulation_hooks(struct insn_emulation_ops *ops)
{
struct undef_hook *hook;
BUG_ON(!ops->hooks);
for (hook = ops->hooks; hook->instr_mask; hook++)
unregister_undef_hook(hook);
pr_notice("Removed %s emulation handler\n", ops->name);
}
static void enable_insn_hw_mode(void *data)
{
struct insn_emulation *insn = (struct insn_emulation *)data;
if (insn->ops->set_hw_mode)
insn->ops->set_hw_mode(true);
}
static void disable_insn_hw_mode(void *data)
{
struct insn_emulation *insn = (struct insn_emulation *)data;
if (insn->ops->set_hw_mode)
insn->ops->set_hw_mode(false);
}
/* Run set_hw_mode(mode) on all active CPUs */
static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable)
{
if (!insn->ops->set_hw_mode)
return -EINVAL;
if (enable)
on_each_cpu(enable_insn_hw_mode, (void *)insn, true);
else
on_each_cpu(disable_insn_hw_mode, (void *)insn, true);
return 0;
}
/*
* Run set_hw_mode for all insns on a starting CPU.
* Returns:
* 0 - If all the hooks ran successfully.
* -EINVAL - At least one hook is not supported by the CPU.
*/
static int run_all_insn_set_hw_mode(unsigned int cpu)
{
int rc = 0;
unsigned long flags;
struct insn_emulation *insn;
raw_spin_lock_irqsave(&insn_emulation_lock, flags);
list_for_each_entry(insn, &insn_emulation, node) {
bool enable = (insn->current_mode == INSN_HW);
if (insn->ops->set_hw_mode && insn->ops->set_hw_mode(enable)) {
pr_warn("CPU[%u] cannot support the emulation of %s",
cpu, insn->ops->name);
rc = -EINVAL;
}
if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
if ((*aarch32_opcode_cond_checks[cc_bits])(psr))
return ARM_OPCODE_CONDTEST_PASS;
else
return ARM_OPCODE_CONDTEST_FAIL;
}
raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
return rc;
}
static int update_insn_emulation_mode(struct insn_emulation *insn,
enum insn_emulation_mode prev)
{
int ret = 0;
switch (prev) {
case INSN_UNDEF: /* Nothing to be done */
break;
case INSN_EMULATE:
remove_emulation_hooks(insn->ops);
break;
case INSN_HW:
if (!run_all_cpu_set_hw_mode(insn, false))
pr_notice("Disabled %s support\n", insn->ops->name);
break;
}
switch (insn->current_mode) {
case INSN_UNDEF:
break;
case INSN_EMULATE:
register_emulation_hooks(insn->ops);
break;
case INSN_HW:
ret = run_all_cpu_set_hw_mode(insn, true);
if (!ret)
pr_notice("Enabled %s support\n", insn->ops->name);
break;
}
return ret;
}
static void __init register_insn_emulation(struct insn_emulation_ops *ops)
{
unsigned long flags;
struct insn_emulation *insn;
insn = kzalloc(sizeof(*insn), GFP_KERNEL);
if (!insn)
return;
insn->ops = ops;
insn->min = INSN_UNDEF;
switch (ops->status) {
case INSN_DEPRECATED:
insn->current_mode = INSN_EMULATE;
/* Disable the HW mode if it was turned on at early boot time */
run_all_cpu_set_hw_mode(insn, false);
insn->max = INSN_HW;
break;
case INSN_OBSOLETE:
insn->current_mode = INSN_UNDEF;
insn->max = INSN_EMULATE;
break;
}
raw_spin_lock_irqsave(&insn_emulation_lock, flags);
list_add(&insn->node, &insn_emulation);
nr_insn_emulated++;
raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
/* Register any handlers if required */
update_insn_emulation_mode(insn, INSN_UNDEF);
}
static int emulation_proc_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp,
loff_t *ppos)
{
int ret = 0;
struct insn_emulation *insn = container_of(table->data, struct insn_emulation, current_mode);
enum insn_emulation_mode prev_mode = insn->current_mode;
mutex_lock(&insn_emulation_mutex);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write || prev_mode == insn->current_mode)
goto ret;
ret = update_insn_emulation_mode(insn, prev_mode);
if (ret) {
/* Mode change failed, revert to previous mode. */
insn->current_mode = prev_mode;
update_insn_emulation_mode(insn, INSN_UNDEF);
}
ret:
mutex_unlock(&insn_emulation_mutex);
return ret;
}
static void __init register_insn_emulation_sysctl(void)
{
unsigned long flags;
int i = 0;
struct insn_emulation *insn;
struct ctl_table *insns_sysctl, *sysctl;
insns_sysctl = kcalloc(nr_insn_emulated + 1, sizeof(*sysctl),
GFP_KERNEL);
if (!insns_sysctl)
return;
raw_spin_lock_irqsave(&insn_emulation_lock, flags);
list_for_each_entry(insn, &insn_emulation, node) {
sysctl = &insns_sysctl[i];
sysctl->mode = 0644;
sysctl->maxlen = sizeof(int);
sysctl->procname = insn->ops->name;
sysctl->data = &insn->current_mode;
sysctl->extra1 = &insn->min;
sysctl->extra2 = &insn->max;
sysctl->proc_handler = emulation_proc_handler;
i++;
}
raw_spin_unlock_irqrestore(&insn_emulation_lock, flags);
register_sysctl("abi", insns_sysctl);
return ARM_OPCODE_CONDTEST_UNCOND;
}
#ifdef CONFIG_SWP_EMULATION
/*
* Implement emulation of the SWP/SWPB instructions using load-exclusive and
* store-exclusive.
@ -339,25 +158,6 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
return res;
}
#define ARM_OPCODE_CONDTEST_FAIL 0
#define ARM_OPCODE_CONDTEST_PASS 1
#define ARM_OPCODE_CONDTEST_UNCOND 2
#define ARM_OPCODE_CONDITION_UNCOND 0xf
static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr)
{
u32 cc_bits = opcode >> 28;
if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) {
if ((*aarch32_opcode_cond_checks[cc_bits])(psr))
return ARM_OPCODE_CONDTEST_PASS;
else
return ARM_OPCODE_CONDTEST_FAIL;
}
return ARM_OPCODE_CONDTEST_UNCOND;
}
/*
* swp_handler logs the id of calling process, dissects the instruction, sanity
* checks the memory location, calls emulate_swpX for the actual operation and
@ -430,28 +230,27 @@ fault:
return 0;
}
/*
* Only emulate SWP/SWPB executed in ARM state/User mode.
* The kernel must be SWP free and SWP{B} does not exist in Thumb.
*/
static struct undef_hook swp_hooks[] = {
{
.instr_mask = 0x0fb00ff0,
.instr_val = 0x01000090,
.pstate_mask = PSR_AA32_MODE_MASK,
.pstate_val = PSR_AA32_MODE_USR,
.fn = swp_handler
},
{ }
};
static bool try_emulate_swp(struct pt_regs *regs, u32 insn)
{
/* SWP{B} only exists in ARM state and does not exist in Thumb */
if (!compat_user_mode(regs) || compat_thumb_mode(regs))
return false;
static struct insn_emulation_ops swp_ops = {
if ((insn & 0x0fb00ff0) != 0x01000090)
return false;
return swp_handler(regs, insn) == 0;
}
static struct insn_emulation insn_swp = {
.name = "swp",
.status = INSN_OBSOLETE,
.hooks = swp_hooks,
.try_emulate = try_emulate_swp,
.set_hw_mode = NULL,
};
#endif /* CONFIG_SWP_EMULATION */
#ifdef CONFIG_CP15_BARRIER_EMULATION
static int cp15barrier_handler(struct pt_regs *regs, u32 instr)
{
perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc);
@ -514,31 +313,29 @@ static int cp15_barrier_set_hw_mode(bool enable)
return 0;
}
static struct undef_hook cp15_barrier_hooks[] = {
{
.instr_mask = 0x0fff0fdf,
.instr_val = 0x0e070f9a,
.pstate_mask = PSR_AA32_MODE_MASK,
.pstate_val = PSR_AA32_MODE_USR,
.fn = cp15barrier_handler,
},
{
.instr_mask = 0x0fff0fff,
.instr_val = 0x0e070f95,
.pstate_mask = PSR_AA32_MODE_MASK,
.pstate_val = PSR_AA32_MODE_USR,
.fn = cp15barrier_handler,
},
{ }
};
static bool try_emulate_cp15_barrier(struct pt_regs *regs, u32 insn)
{
if (!compat_user_mode(regs) || compat_thumb_mode(regs))
return false;
static struct insn_emulation_ops cp15_barrier_ops = {
if ((insn & 0x0fff0fdf) == 0x0e070f9a)
return cp15barrier_handler(regs, insn) == 0;
if ((insn & 0x0fff0fff) == 0x0e070f95)
return cp15barrier_handler(regs, insn) == 0;
return false;
}
static struct insn_emulation insn_cp15_barrier = {
.name = "cp15_barrier",
.status = INSN_DEPRECATED,
.hooks = cp15_barrier_hooks,
.try_emulate = try_emulate_cp15_barrier,
.set_hw_mode = cp15_barrier_set_hw_mode,
};
#endif /* CONFIG_CP15_BARRIER_EMULATION */
#ifdef CONFIG_SETEND_EMULATION
static int setend_set_hw_mode(bool enable)
{
if (!cpu_supports_mixed_endian_el0())
@ -586,31 +383,218 @@ static int t16_setend_handler(struct pt_regs *regs, u32 instr)
return rc;
}
static struct undef_hook setend_hooks[] = {
{
.instr_mask = 0xfffffdff,
.instr_val = 0xf1010000,
.pstate_mask = PSR_AA32_MODE_MASK,
.pstate_val = PSR_AA32_MODE_USR,
.fn = a32_setend_handler,
},
{
/* Thumb mode */
.instr_mask = 0xfffffff7,
.instr_val = 0x0000b650,
.pstate_mask = (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK),
.pstate_val = (PSR_AA32_T_BIT | PSR_AA32_MODE_USR),
.fn = t16_setend_handler,
},
{}
};
static bool try_emulate_setend(struct pt_regs *regs, u32 insn)
{
if (compat_thumb_mode(regs) &&
(insn & 0xfffffff7) == 0x0000b650)
return t16_setend_handler(regs, insn) == 0;
static struct insn_emulation_ops setend_ops = {
if (compat_user_mode(regs) &&
(insn & 0xfffffdff) == 0xf1010000)
return a32_setend_handler(regs, insn) == 0;
return false;
}
static struct insn_emulation insn_setend = {
.name = "setend",
.status = INSN_DEPRECATED,
.hooks = setend_hooks,
.try_emulate = try_emulate_setend,
.set_hw_mode = setend_set_hw_mode,
};
#endif /* CONFIG_SETEND_EMULATION */
static struct insn_emulation *insn_emulations[] = {
#ifdef CONFIG_SWP_EMULATION
&insn_swp,
#endif
#ifdef CONFIG_CP15_BARRIER_EMULATION
&insn_cp15_barrier,
#endif
#ifdef CONFIG_SETEND_EMULATION
&insn_setend,
#endif
};
static DEFINE_MUTEX(insn_emulation_mutex);
static void enable_insn_hw_mode(void *data)
{
struct insn_emulation *insn = (struct insn_emulation *)data;
if (insn->set_hw_mode)
insn->set_hw_mode(true);
}
static void disable_insn_hw_mode(void *data)
{
struct insn_emulation *insn = (struct insn_emulation *)data;
if (insn->set_hw_mode)
insn->set_hw_mode(false);
}
/* Run set_hw_mode(mode) on all active CPUs */
static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable)
{
if (!insn->set_hw_mode)
return -EINVAL;
if (enable)
on_each_cpu(enable_insn_hw_mode, (void *)insn, true);
else
on_each_cpu(disable_insn_hw_mode, (void *)insn, true);
return 0;
}
/*
* Run set_hw_mode for all insns on a starting CPU.
* Returns:
* 0 - If all the hooks ran successfully.
* -EINVAL - At least one hook is not supported by the CPU.
*/
static int run_all_insn_set_hw_mode(unsigned int cpu)
{
int rc = 0;
unsigned long flags;
/*
* Disable IRQs to serialize against an IPI from
* run_all_cpu_set_hw_mode(), ensuring the HW is programmed to the most
* recent enablement state if the two race with one another.
*/
local_irq_save(flags);
for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) {
struct insn_emulation *insn = insn_emulations[i];
bool enable = READ_ONCE(insn->current_mode) == INSN_HW;
if (insn->set_hw_mode && insn->set_hw_mode(enable)) {
pr_warn("CPU[%u] cannot support the emulation of %s",
cpu, insn->name);
rc = -EINVAL;
}
}
local_irq_restore(flags);
return rc;
}
static int update_insn_emulation_mode(struct insn_emulation *insn,
enum insn_emulation_mode prev)
{
int ret = 0;
switch (prev) {
case INSN_UNDEF: /* Nothing to be done */
break;
case INSN_EMULATE:
break;
case INSN_HW:
if (!run_all_cpu_set_hw_mode(insn, false))
pr_notice("Disabled %s support\n", insn->name);
break;
}
switch (insn->current_mode) {
case INSN_UNDEF:
break;
case INSN_EMULATE:
break;
case INSN_HW:
ret = run_all_cpu_set_hw_mode(insn, true);
if (!ret)
pr_notice("Enabled %s support\n", insn->name);
break;
}
return ret;
}
static int emulation_proc_handler(struct ctl_table *table, int write,
void *buffer, size_t *lenp,
loff_t *ppos)
{
int ret = 0;
struct insn_emulation *insn = container_of(table->data, struct insn_emulation, current_mode);
enum insn_emulation_mode prev_mode = insn->current_mode;
mutex_lock(&insn_emulation_mutex);
ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret || !write || prev_mode == insn->current_mode)
goto ret;
ret = update_insn_emulation_mode(insn, prev_mode);
if (ret) {
/* Mode change failed, revert to previous mode. */
WRITE_ONCE(insn->current_mode, prev_mode);
update_insn_emulation_mode(insn, INSN_UNDEF);
}
ret:
mutex_unlock(&insn_emulation_mutex);
return ret;
}
static void __init register_insn_emulation(struct insn_emulation *insn)
{
struct ctl_table *sysctl;
insn->min = INSN_UNDEF;
switch (insn->status) {
case INSN_DEPRECATED:
insn->current_mode = INSN_EMULATE;
/* Disable the HW mode if it was turned on at early boot time */
run_all_cpu_set_hw_mode(insn, false);
insn->max = INSN_HW;
break;
case INSN_OBSOLETE:
insn->current_mode = INSN_UNDEF;
insn->max = INSN_EMULATE;
break;
case INSN_UNAVAILABLE:
insn->current_mode = INSN_UNDEF;
insn->max = INSN_UNDEF;
break;
}
/* Program the HW if required */
update_insn_emulation_mode(insn, INSN_UNDEF);
if (insn->status != INSN_UNAVAILABLE) {
sysctl = &insn->sysctl[0];
sysctl->mode = 0644;
sysctl->maxlen = sizeof(int);
sysctl->procname = insn->name;
sysctl->data = &insn->current_mode;
sysctl->extra1 = &insn->min;
sysctl->extra2 = &insn->max;
sysctl->proc_handler = emulation_proc_handler;
register_sysctl("abi", sysctl);
}
}
bool try_emulate_armv8_deprecated(struct pt_regs *regs, u32 insn)
{
for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) {
struct insn_emulation *ie = insn_emulations[i];
if (ie->status == INSN_UNAVAILABLE)
continue;
/*
* A trap may race with the mode being changed
* INSN_EMULATE<->INSN_HW. Try to emulate the instruction to
* avoid a spurious UNDEF.
*/
if (READ_ONCE(ie->current_mode) == INSN_UNDEF)
continue;
if (ie->try_emulate(regs, insn))
return true;
}
return false;
}
/*
* Invoked as core_initcall, which guarantees that the instruction
@ -618,24 +602,25 @@ static struct insn_emulation_ops setend_ops = {
*/
static int __init armv8_deprecated_init(void)
{
if (IS_ENABLED(CONFIG_SWP_EMULATION))
register_insn_emulation(&swp_ops);
#ifdef CONFIG_SETEND_EMULATION
if (!system_supports_mixed_endian_el0()) {
insn_setend.status = INSN_UNAVAILABLE;
pr_info("setend instruction emulation is not supported on this system\n");
}
if (IS_ENABLED(CONFIG_CP15_BARRIER_EMULATION))
register_insn_emulation(&cp15_barrier_ops);
#endif
for (int i = 0; i < ARRAY_SIZE(insn_emulations); i++) {
struct insn_emulation *ie = insn_emulations[i];
if (IS_ENABLED(CONFIG_SETEND_EMULATION)) {
if (system_supports_mixed_endian_el0())
register_insn_emulation(&setend_ops);
else
pr_info("setend instruction emulation is not supported on this system\n");
if (ie->status == INSN_UNAVAILABLE)
continue;
register_insn_emulation(ie);
}
cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING,
"arm64/isndep:starting",
run_all_insn_set_hw_mode, NULL);
register_insn_emulation_sysctl();
return 0;
}

13
arch/arm64/kernel/asm-offsets.c
View File

@ -82,6 +82,19 @@ int main(void)
DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs));
BLANK();
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
DEFINE(FREGS_X0, offsetof(struct ftrace_regs, regs[0]));
DEFINE(FREGS_X2, offsetof(struct ftrace_regs, regs[2]));
DEFINE(FREGS_X4, offsetof(struct ftrace_regs, regs[4]));
DEFINE(FREGS_X6, offsetof(struct ftrace_regs, regs[6]));
DEFINE(FREGS_X8, offsetof(struct ftrace_regs, regs[8]));
DEFINE(FREGS_FP, offsetof(struct ftrace_regs, fp));
DEFINE(FREGS_LR, offsetof(struct ftrace_regs, lr));
DEFINE(FREGS_SP, offsetof(struct ftrace_regs, sp));
DEFINE(FREGS_PC, offsetof(struct ftrace_regs, pc));
DEFINE(FREGS_SIZE, sizeof(struct ftrace_regs));
BLANK();
#endif
#ifdef CONFIG_COMPAT
DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0));

7
arch/arm64/kernel/cpu_errata.c
View File

@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus),
},
#endif
#ifdef CONFIG_ARM64_ERRATUM_2645198
{
.desc = "ARM erratum 2645198",
.capability = ARM64_WORKAROUND_2645198,
ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715)
},
#endif
#ifdef CONFIG_ARM64_ERRATUM_2077057
{
.desc = "ARM erratum 2077057",

253
arch/arm64/kernel/cpufeature.c
View File

@ -212,6 +212,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0),
@ -402,14 +404,14 @@ struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
};
static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_INNERSHR_SHIFT, 4, 0xf),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_FCSE_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_MMFR0_AUXREG_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_TCM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_SHARELVL_SHIFT, 4, 0),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_OUTERSHR_SHIFT, 4, 0xf),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_PMSA_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_VMSA_SHIFT, 4, 0),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_InnerShr_SHIFT, 4, 0xf),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_FCSE_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_AuxReg_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_TCM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_ShareLvl_SHIFT, 4, 0),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_OuterShr_SHIFT, 4, 0xf),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_PMSA_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR0_EL1_VMSA_SHIFT, 4, 0),
ARM64_FTR_END,
};
@ -429,32 +431,32 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
};
static const struct arm64_ftr_bits ftr_mvfr0[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPROUND_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSHVEC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSQRT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDIVIDE_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPTRAP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_SIMD_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPRound_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPShVec_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPSqrt_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPDivide_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPTrap_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPDP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_FPSP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_EL1_SIMDReg_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_mvfr1[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDFMAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDSP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDINT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDLS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPDNAN_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPFTZ_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDFMAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDSP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDInt_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDLS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPDNaN_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPFtZ_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_mvfr2[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_EL1_FPMisc_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_EL1_SIMDMisc_SHIFT, 4, 0),
ARM64_FTR_END,
};
@ -470,34 +472,34 @@ static const struct arm64_ftr_bits ftr_gmid[] = {
};
static const struct arm64_ftr_bits ftr_id_isar0[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DIVIDE_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_DEBUG_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_COPROC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_CMPBRANCH_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_BITFIELD_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_BITCOUNT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_SWAP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Divide_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Debug_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Coproc_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_CmpBranch_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_BitField_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_BitCount_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR0_EL1_Swap_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_isar5[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_RDM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_CRC32_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SHA2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SHA1_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_AES_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_EL1_SEVL_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EVT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CCIDX_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_LSM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_HPDS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_CNP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_XNX_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_AC2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_EVT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_CCIDX_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_LSM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_HPDS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_CnP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_XNX_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR4_EL1_AC2_SHIFT, 4, 0),
/*
* SpecSEI = 1 indicates that the PE might generate an SError on an
@ -505,80 +507,80 @@ static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
* SError might be generated than it will not be. Hence it has been
* classified as FTR_HIGHER_SAFE.
*/
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_MMFR4_SPECSEI_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_MMFR4_EL1_SpecSEI_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_isar4[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SWP_FRAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_PSR_M_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_BARRIER_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_SMC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_WRITEBACK_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_WITHSHIFTS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_UNPRIV_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SWP_frac_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_PSR_M_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SynchPrim_frac_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Barrier_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_SMC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Writeback_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_WithShifts_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR4_EL1_Unpriv_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_mmfr5[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR5_ETS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_MMFR5_EL1_ETS_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_isar6[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_I8MM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_BF16_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SPECRES_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_FHM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_DP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_JSCVT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SPECRES_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_JSCVT_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_pfr0[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_DIT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_CSV2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE3_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE1_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_STATE0_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_DIT_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_CSV2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State3_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State2_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State1_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR0_EL1_State0_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_pfr1[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_GIC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_VIRT_FRAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_SEC_FRAC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_GENTIMER_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_VIRTUALIZATION_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_MPROGMOD_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_SECURITY_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_PROGMOD_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_GIC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Virt_frac_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Sec_frac_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_GenTimer_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Virtualization_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_MProgMod_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_Security_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_PFR1_EL1_ProgMod_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_pfr2[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_SSBS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_CSV3_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_CSV3_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_dfr0[] = {
/* [31:28] TraceFilt */
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_PERFMON_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MPROFDBG_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPTRC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPTRC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_MMAPDBG_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPSDBG_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_COPDBG_SHIFT, 4, 0),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_DFR0_EL1_PerfMon_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MProfDbg_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MMapTrc_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopTrc_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_MMapDbg_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopSDbg_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR0_EL1_CopDbg_SHIFT, 4, 0),
ARM64_FTR_END,
};
static const struct arm64_ftr_bits ftr_id_dfr1[] = {
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR1_MTPMU_SHIFT, 4, 0),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_DFR1_EL1_MTPMU_SHIFT, 4, 0),
ARM64_FTR_END,
};
@ -1119,12 +1121,12 @@ static int update_32bit_cpu_features(int cpu, struct cpuinfo_32bit *info,
* EL1-dependent register fields to avoid spurious sanity check fails.
*/
if (!id_aa64pfr0_32bit_el1(pfr0)) {
relax_cpu_ftr_reg(SYS_ID_ISAR4_EL1, ID_ISAR4_SMC_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_VIRT_FRAC_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_SEC_FRAC_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_VIRTUALIZATION_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_SECURITY_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_PROGMOD_SHIFT);
relax_cpu_ftr_reg(SYS_ID_ISAR4_EL1, ID_ISAR4_EL1_SMC_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Virt_frac_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Sec_frac_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Virtualization_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_Security_SHIFT);
relax_cpu_ftr_reg(SYS_ID_PFR1_EL1, ID_PFR1_EL1_ProgMod_SHIFT);
}
taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
@ -2101,6 +2103,11 @@ static void cpu_trap_el0_impdef(const struct arm64_cpu_capabilities *__unused)
sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_TIDCP);
}
static void cpu_enable_dit(const struct arm64_cpu_capabilities *__unused)
{
set_pstate_dit(1);
}
/* Internal helper functions to match cpu capability type */
static bool
cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@ -2664,6 +2671,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = has_cpuid_feature,
.cpu_enable = cpu_trap_el0_impdef,
},
{
.desc = "Data independent timing control (DIT)",
.capability = ARM64_HAS_DIT,
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.sys_reg = SYS_ID_AA64PFR0_EL1,
.sign = FTR_UNSIGNED,
.field_pos = ID_AA64PFR0_EL1_DIT_SHIFT,
.field_width = 4,
.min_field_value = ID_AA64PFR0_EL1_DIT_IMP,
.matches = has_cpuid_feature,
.cpu_enable = cpu_enable_dit,
},
{},
};
@ -2772,6 +2791,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
#ifdef CONFIG_ARM64_SVE
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_EL1_SVE_IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
@ -2798,6 +2818,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
#endif /* CONFIG_ARM64_MTE */
HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV),
HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_CSSC_IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_RPRFM_IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES),
HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_WFxT_IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
#ifdef CONFIG_ARM64_SME
@ -2829,24 +2851,24 @@ static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope)
else
mvfr1 = read_sysreg_s(SYS_MVFR1_EL1);
return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDSP_SHIFT) &&
cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDINT_SHIFT) &&
cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDLS_SHIFT);
return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDSP_SHIFT) &&
cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDInt_SHIFT) &&
cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_EL1_SIMDLS_SHIFT);
}
#endif
static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = {
#ifdef CONFIG_COMPAT
HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON),
HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_EL1_SIMDFMAC_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4),
/* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */
HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP),
HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2),
HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32),
#endif
{},
};
@ -3435,35 +3457,22 @@ int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt)
return rc;
}
static int emulate_mrs(struct pt_regs *regs, u32 insn)
bool try_emulate_mrs(struct pt_regs *regs, u32 insn)
{
u32 sys_reg, rt;
if (compat_user_mode(regs) || !aarch64_insn_is_mrs(insn))
return false;
/*
* sys_reg values are defined as used in mrs/msr instruction.
* shift the imm value to get the encoding.
*/
sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5;
rt = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
return do_emulate_mrs(regs, sys_reg, rt);
return do_emulate_mrs(regs, sys_reg, rt) == 0;
}
static struct undef_hook mrs_hook = {
.instr_mask = 0xffff0000,
.instr_val = 0xd5380000,
.pstate_mask = PSR_AA32_MODE_MASK,
.pstate_val = PSR_MODE_EL0t,
.fn = emulate_mrs,
};
static int __init enable_mrs_emulation(void)
{
register_undef_hook(&mrs_hook);
return 0;
}
core_initcall(enable_mrs_emulation);
enum mitigation_state arm64_get_meltdown_state(void)
{
if (__meltdown_safe)

3
arch/arm64/kernel/cpuinfo.c
View File

@ -116,6 +116,9 @@ static const char *const hwcap_str[] = {
[KERNEL_HWCAP_WFXT] = "wfxt",
[KERNEL_HWCAP_EBF16] = "ebf16",
[KERNEL_HWCAP_SVE_EBF16] = "sveebf16",
[KERNEL_HWCAP_CSSC] = "cssc",
[KERNEL_HWCAP_RPRFM] = "rprfm",
[KERNEL_HWCAP_SVE2P1] = "sve2p1",
};
#ifdef CONFIG_COMPAT

24
arch/arm64/kernel/entry-common.c
View File

@ -30,7 +30,7 @@
/*
* Handle IRQ/context state management when entering from kernel mode.
* Before this function is called it is not safe to call regular kernel code,
* intrumentable code, or any code which may trigger an exception.
* instrumentable code, or any code which may trigger an exception.
*
* This is intended to match the logic in irqentry_enter(), handling the kernel
* mode transitions only.
@ -63,7 +63,7 @@ static void noinstr enter_from_kernel_mode(struct pt_regs *regs)
/*
* Handle IRQ/context state management when exiting to kernel mode.
* After this function returns it is not safe to call regular kernel code,
* intrumentable code, or any code which may trigger an exception.
* instrumentable code, or any code which may trigger an exception.
*
* This is intended to match the logic in irqentry_exit(), handling the kernel
* mode transitions only, and with preemption handled elsewhere.
@ -97,7 +97,7 @@ static void noinstr exit_to_kernel_mode(struct pt_regs *regs)
/*
* Handle IRQ/context state management when entering from user mode.
* Before this function is called it is not safe to call regular kernel code,
* intrumentable code, or any code which may trigger an exception.
* instrumentable code, or any code which may trigger an exception.
*/
static __always_inline void __enter_from_user_mode(void)
{
@ -116,7 +116,7 @@ static __always_inline void enter_from_user_mode(struct pt_regs *regs)
/*
* Handle IRQ/context state management when exiting to user mode.
* After this function returns it is not safe to call regular kernel code,
* intrumentable code, or any code which may trigger an exception.
* instrumentable code, or any code which may trigger an exception.
*/
static __always_inline void __exit_to_user_mode(void)
{
@ -152,7 +152,7 @@ asmlinkage void noinstr asm_exit_to_user_mode(struct pt_regs *regs)
/*
* Handle IRQ/context state management when entering an NMI from user/kernel
* mode. Before this function is called it is not safe to call regular kernel
* code, intrumentable code, or any code which may trigger an exception.
* code, instrumentable code, or any code which may trigger an exception.
*/
static void noinstr arm64_enter_nmi(struct pt_regs *regs)
{
@ -170,7 +170,7 @@ static void noinstr arm64_enter_nmi(struct pt_regs *regs)
/*
* Handle IRQ/context state management when exiting an NMI from user/kernel
* mode. After this function returns it is not safe to call regular kernel
* code, intrumentable code, or any code which may trigger an exception.
* code, instrumentable code, or any code which may trigger an exception.
*/
static void noinstr arm64_exit_nmi(struct pt_regs *regs)
{
@ -192,7 +192,7 @@ static void noinstr arm64_exit_nmi(struct pt_regs *regs)
/*
* Handle IRQ/context state management when entering a debug exception from
* kernel mode. Before this function is called it is not safe to call regular
* kernel code, intrumentable code, or any code which may trigger an exception.
* kernel code, instrumentable code, or any code which may trigger an exception.
*/
static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
{
@ -207,7 +207,7 @@ static void noinstr arm64_enter_el1_dbg(struct pt_regs *regs)
/*
* Handle IRQ/context state management when exiting a debug exception from
* kernel mode. After this function returns it is not safe to call regular
* kernel code, intrumentable code, or any code which may trigger an exception.
* kernel code, instrumentable code, or any code which may trigger an exception.
*/
static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
{
@ -384,7 +384,7 @@ static void noinstr el1_undef(struct pt_regs *regs, unsigned long esr)
{
enter_from_kernel_mode(regs);
local_daif_inherit(regs);
do_undefinstr(regs, esr);
do_el1_undef(regs, esr);
local_daif_mask();
exit_to_kernel_mode(regs);
}
@ -570,7 +570,7 @@ static void noinstr el0_sys(struct pt_regs *regs, unsigned long esr)
{
enter_from_user_mode(regs);
local_daif_restore(DAIF_PROCCTX);
do_sysinstr(esr, regs);
do_el0_sys(esr, regs);
exit_to_user_mode(regs);
}
@ -599,7 +599,7 @@ static void noinstr el0_undef(struct pt_regs *regs, unsigned long esr)
{
enter_from_user_mode(regs);
local_daif_restore(DAIF_PROCCTX);
do_undefinstr(regs, esr);
do_el0_undef(regs, esr);
exit_to_user_mode(regs);
}
@ -762,7 +762,7 @@ static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr)
{
enter_from_user_mode(regs);
local_daif_restore(DAIF_PROCCTX);
do_cp15instr(esr, regs);
do_el0_cp15(esr, regs);
exit_to_user_mode(regs);
}

162
arch/arm64/kernel/entry-ftrace.S
View File

@ -13,83 +13,58 @@
#include <asm/ftrace.h>
#include <asm/insn.h>
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
/*
* Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before
* the regular function prologue. For an enabled callsite, ftrace_init_nop() and
* ftrace_make_call() have patched those NOPs to:
*
* MOV X9, LR
* BL <entry>
*
* ... where <entry> is either ftrace_caller or ftrace_regs_caller.
* BL ftrace_caller
*
* Each instrumented function follows the AAPCS, so here x0-x8 and x18-x30 are
* live (x18 holds the Shadow Call Stack pointer), and x9-x17 are safe to
* clobber.
*
* We save the callsite's context into a pt_regs before invoking any ftrace
* callbacks. So that we can get a sensible backtrace, we create a stack record
* for the callsite and the ftrace entry assembly. This is not sufficient for
* reliable stacktrace: until we create the callsite stack record, its caller
* is missing from the LR and existing chain of frame records.
* We save the callsite's context into a struct ftrace_regs before invoking any
* ftrace callbacks. So that we can get a sensible backtrace, we create frame
* records for the callsite and the ftrace entry assembly. This is not
* sufficient for reliable stacktrace: until we create the callsite stack
* record, its caller is missing from the LR and existing chain of frame
* records.
*/
.macro ftrace_regs_entry, allregs=0
/* Make room for pt_regs, plus a callee frame */
sub sp, sp, #(PT_REGS_SIZE + 16)
/* Save function arguments (and x9 for simplicity) */
stp x0, x1, [sp, #S_X0]
stp x2, x3, [sp, #S_X2]
stp x4, x5, [sp, #S_X4]
stp x6, x7, [sp, #S_X6]
stp x8, x9, [sp, #S_X8]
/* Optionally save the callee-saved registers, always save the FP */
.if \allregs == 1
stp x10, x11, [sp, #S_X10]
stp x12, x13, [sp, #S_X12]
stp x14, x15, [sp, #S_X14]
stp x16, x17, [sp, #S_X16]
stp x18, x19, [sp, #S_X18]
stp x20, x21, [sp, #S_X20]
stp x22, x23, [sp, #S_X22]
stp x24, x25, [sp, #S_X24]
stp x26, x27, [sp, #S_X26]
stp x28, x29, [sp, #S_X28]
.else
str x29, [sp, #S_FP]
.endif
/* Save the callsite's SP and LR */
add x10, sp, #(PT_REGS_SIZE + 16)
stp x9, x10, [sp, #S_LR]
/* Save the PC after the ftrace callsite */
str x30, [sp, #S_PC]
/* Create a frame record for the callsite above pt_regs */
stp x29, x9, [sp, #PT_REGS_SIZE]
add x29, sp, #PT_REGS_SIZE
/* Create our frame record within pt_regs. */
stp x29, x30, [sp, #S_STACKFRAME]
add x29, sp, #S_STACKFRAME
.endm
SYM_CODE_START(ftrace_regs_caller)
bti c
ftrace_regs_entry 1
b ftrace_common
SYM_CODE_END(ftrace_regs_caller)
SYM_CODE_START(ftrace_caller)
bti c
ftrace_regs_entry 0
b ftrace_common
SYM_CODE_END(ftrace_caller)
SYM_CODE_START(ftrace_common)
/* Save original SP */
mov x10, sp
/* Make room for ftrace regs, plus two frame records */
sub sp, sp, #(FREGS_SIZE + 32)
/* Save function arguments */
stp x0, x1, [sp, #FREGS_X0]
stp x2, x3, [sp, #FREGS_X2]
stp x4, x5, [sp, #FREGS_X4]
stp x6, x7, [sp, #FREGS_X6]
str x8, [sp, #FREGS_X8]
/* Save the callsite's FP, LR, SP */
str x29, [sp, #FREGS_FP]
str x9, [sp, #FREGS_LR]
str x10, [sp, #FREGS_SP]
/* Save the PC after the ftrace callsite */
str x30, [sp, #FREGS_PC]
/* Create a frame record for the callsite above the ftrace regs */
stp x29, x9, [sp, #FREGS_SIZE + 16]
add x29, sp, #FREGS_SIZE + 16
/* Create our frame record above the ftrace regs */
stp x29, x30, [sp, #FREGS_SIZE]
add x29, sp, #FREGS_SIZE
sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
mov x1, x9 // parent_ip (callsite's LR)
ldr_l x2, function_trace_op // op
@ -104,24 +79,24 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
* to restore x0-x8, x29, and x30.
*/
/* Restore function arguments */
ldp x0, x1, [sp]
ldp x2, x3, [sp, #S_X2]
ldp x4, x5, [sp, #S_X4]
ldp x6, x7, [sp, #S_X6]
ldr x8, [sp, #S_X8]
ldp x0, x1, [sp, #FREGS_X0]
ldp x2, x3, [sp, #FREGS_X2]
ldp x4, x5, [sp, #FREGS_X4]
ldp x6, x7, [sp, #FREGS_X6]
ldr x8, [sp, #FREGS_X8]
/* Restore the callsite's FP, LR, PC */
ldr x29, [sp, #S_FP]
ldr x30, [sp, #S_LR]
ldr x9, [sp, #S_PC]
ldr x29, [sp, #FREGS_FP]
ldr x30, [sp, #FREGS_LR]
ldr x9, [sp, #FREGS_PC]
/* Restore the callsite's SP */
add sp, sp, #PT_REGS_SIZE + 16
add sp, sp, #FREGS_SIZE + 32
ret x9
SYM_CODE_END(ftrace_common)
SYM_CODE_END(ftrace_caller)
#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
/*
* Gcc with -pg will put the following code in the beginning of each function:
@ -195,44 +170,6 @@ SYM_CODE_END(ftrace_common)
add \reg, \reg, #8
.endm
#ifndef CONFIG_DYNAMIC_FTRACE
/*
* void _mcount(unsigned long return_address)
* @return_address: return address to instrumented function
*
* This function makes calls, if enabled, to:
* - tracer function to probe instrumented function's entry,
* - ftrace_graph_caller to set up an exit hook
*/
SYM_FUNC_START(_mcount)
mcount_enter
ldr_l x2, ftrace_trace_function
adr x0, ftrace_stub
cmp x0, x2 // if (ftrace_trace_function
b.eq skip_ftrace_call // != ftrace_stub) {
mcount_get_pc x0 // function's pc
mcount_get_lr x1 // function's lr (= parent's pc)
blr x2 // (*ftrace_trace_function)(pc, lr);
skip_ftrace_call: // }
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ldr_l x2, ftrace_graph_return
cmp x0, x2 // if ((ftrace_graph_return
b.ne ftrace_graph_caller // != ftrace_stub)
ldr_l x2, ftrace_graph_entry // || (ftrace_graph_entry
adr_l x0, ftrace_graph_entry_stub // != ftrace_graph_entry_stub))
cmp x0, x2
b.ne ftrace_graph_caller // ftrace_graph_caller();
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
mcount_exit
SYM_FUNC_END(_mcount)
EXPORT_SYMBOL(_mcount)
NOKPROBE(_mcount)
#else /* CONFIG_DYNAMIC_FTRACE */
/*
* _mcount() is used to build the kernel with -pg option, but all the branch
* instructions to _mcount() are replaced to NOP initially at kernel start up,
@ -272,7 +209,6 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller();
mcount_exit
SYM_FUNC_END(ftrace_caller)
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
@ -293,7 +229,7 @@ SYM_FUNC_START(ftrace_graph_caller)
mcount_exit
SYM_FUNC_END(ftrace_graph_caller)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
SYM_TYPED_FUNC_START(ftrace_stub)
ret

3
arch/arm64/kernel/entry.S
View File

@ -197,6 +197,9 @@ alternative_cb_end
.endm
.macro kernel_entry, el, regsize = 64
.if \el == 0
alternative_insn nop, SET_PSTATE_DIT(1), ARM64_HAS_DIT
.endif
.if \regsize == 32
mov w0, w0 // zero upper 32 bits of x0
.endif

169
arch/arm64/kernel/fpsimd.c
View File

@ -118,16 +118,8 @@
* returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so
* whatever is in the FPSIMD registers is not saved to memory, but discarded.
*/
struct fpsimd_last_state_struct {
struct user_fpsimd_state *st;
void *sve_state;
void *za_state;
u64 *svcr;
unsigned int sve_vl;
unsigned int sme_vl;
};
static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state);
static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
__ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
#ifdef CONFIG_ARM64_SVE
@ -330,15 +322,6 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
* The task can execute SVE instructions while in userspace without
* trapping to the kernel.
*
* When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the
* corresponding Zn), P0-P15 and FFR are encoded in
* task->thread.sve_state, formatted appropriately for vector
* length task->thread.sve_vl or, if SVCR.SM is set,
* task->thread.sme_vl.
*
* task->thread.sve_state must point to a valid buffer at least
* sve_state_size(task) bytes in size.
*
* During any syscall, the kernel may optionally clear TIF_SVE and
* discard the vector state except for the FPSIMD subset.
*
@ -348,7 +331,15 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
* do_sve_acc() to be called, which does some preparation and then
* sets TIF_SVE.
*
* When stored, FPSIMD registers V0-V31 are encoded in
* During any syscall, the kernel may optionally clear TIF_SVE and
* discard the vector state except for the FPSIMD subset.
*
* The data will be stored in one of two formats:
*
* * FPSIMD only - FP_STATE_FPSIMD:
*
* When the FPSIMD only state stored task->thread.fp_type is set to
* FP_STATE_FPSIMD, the FPSIMD registers V0-V31 are encoded in
* task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are
* logically zero but not stored anywhere; P0-P15 and FFR are not
* stored and have unspecified values from userspace's point of
@ -356,7 +347,23 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type,
* but userspace is discouraged from relying on this.
*
* task->thread.sve_state does not need to be non-NULL, valid or any
* particular size: it must not be dereferenced.
* particular size: it must not be dereferenced and any data stored
* there should be considered stale and not referenced.
*
* * SVE state - FP_STATE_SVE:
*
* When the full SVE state is stored task->thread.fp_type is set to
* FP_STATE_SVE and Z0-Z31 (incorporating Vn in bits[127:0] or the
* corresponding Zn), P0-P15 and FFR are encoded in in
* task->thread.sve_state, formatted appropriately for vector
* length task->thread.sve_vl or, if SVCR.SM is set,
* task->thread.sme_vl. The storage for the vector registers in
* task->thread.uw.fpsimd_state should be ignored.
*
* task->thread.sve_state must point to a valid buffer at least
* sve_state_size(task) bytes in size. The data stored in
* task->thread.uw.fpsimd_state.vregs should be considered stale
* and not referenced.
*
* * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state
* irrespective of whether TIF_SVE is clear or set, since these are
@ -378,11 +385,37 @@ static void task_fpsimd_load(void)
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
/* Check if we should restore SVE first */
if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) {
sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
restore_sve_regs = true;
restore_ffr = true;
if (system_supports_sve()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
/* Stop tracking SVE for this task until next use. */
if (test_and_clear_thread_flag(TIF_SVE))
sve_user_disable();
break;
case FP_STATE_SVE:
if (!thread_sm_enabled(&current->thread) &&
!WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE)))
sve_user_enable();
if (test_thread_flag(TIF_SVE))
sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
restore_sve_regs = true;
restore_ffr = true;
break;
default:
/*
* This indicates either a bug in
* fpsimd_save() or memory corruption, we
* should always record an explicit format
* when we save. We always at least have the
* memory allocated for FPSMID registers so
* try that and hope for the best.
*/
WARN_ON_ONCE(1);
clear_thread_flag(TIF_SVE);
break;
}
}
/* Restore SME, override SVE register configuration if needed */
@ -398,18 +431,19 @@ static void task_fpsimd_load(void)
if (thread_za_enabled(&current->thread))
za_load_state(current->thread.za_state);
if (thread_sm_enabled(&current->thread)) {
restore_sve_regs = true;
if (thread_sm_enabled(&current->thread))
restore_ffr = system_supports_fa64();
}
}
if (restore_sve_regs)
if (restore_sve_regs) {
WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE);
sve_load_state(sve_pffr(&current->thread),
&current->thread.uw.fpsimd_state.fpsr,
restore_ffr);
else
} else {
WARN_ON_ONCE(current->thread.fp_type != FP_STATE_FPSIMD);
fpsimd_load_state(&current->thread.uw.fpsimd_state);
}
}
/*
@ -419,12 +453,12 @@ static void task_fpsimd_load(void)
* last, if KVM is involved this may be the guest VM context rather
* than the host thread for the VM pointed to by current. This means
* that we must always reference the state storage via last rather
* than via current, other than the TIF_ flags which KVM will
* carefully maintain for us.
* than via current, if we are saving KVM state then it will have
* ensured that the type of registers to save is set in last->to_save.
*/
static void fpsimd_save(void)
{
struct fpsimd_last_state_struct const *last =
struct cpu_fp_state const *last =
this_cpu_ptr(&fpsimd_last_state);
/* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */
bool save_sve_regs = false;
@ -437,7 +471,14 @@ static void fpsimd_save(void)
if (test_thread_flag(TIF_FOREIGN_FPSTATE))
return;
if (test_thread_flag(TIF_SVE)) {
/*
* If a task is in a syscall the ABI allows us to only
* preserve the state shared with FPSIMD so don't bother
* saving the full SVE state in that case.
*/
if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) &&
!in_syscall(current_pt_regs())) ||
last->to_save == FP_STATE_SVE) {
save_sve_regs = true;
save_ffr = true;
vl = last->sve_vl;
@ -474,8 +515,10 @@ static void fpsimd_save(void)
sve_save_state((char *)last->sve_state +
sve_ffr_offset(vl),
&last->st->fpsr, save_ffr);
*last->fp_type = FP_STATE_SVE;
} else {
fpsimd_save_state(last->st);
*last->fp_type = FP_STATE_FPSIMD;
}
}
@ -768,8 +811,7 @@ void fpsimd_sync_to_sve(struct task_struct *task)
*/
void sve_sync_to_fpsimd(struct task_struct *task)
{
if (test_tsk_thread_flag(task, TIF_SVE) ||
thread_sm_enabled(&task->thread))
if (task->thread.fp_type == FP_STATE_SVE)
sve_to_fpsimd(task);
}
@ -848,8 +890,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
fpsimd_flush_task_state(task);
if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
thread_sm_enabled(&task->thread))
thread_sm_enabled(&task->thread)) {
sve_to_fpsimd(task);
task->thread.fp_type = FP_STATE_FPSIMD;
}
if (system_supports_sme() && type == ARM64_VEC_SME) {
task->thread.svcr &= ~(SVCR_SM_MASK |
@ -1368,6 +1412,7 @@ static void sve_init_regs(void)
fpsimd_bind_task_to_cpu();
} else {
fpsimd_to_sve(current);
current->thread.fp_type = FP_STATE_SVE;
}
}
@ -1596,6 +1641,8 @@ void fpsimd_flush_thread(void)
current->thread.svcr = 0;
}
current->thread.fp_type = FP_STATE_FPSIMD;
put_cpu_fpsimd_context();
kfree(sve_state);
kfree(za_state);
@ -1627,6 +1674,31 @@ void fpsimd_signal_preserve_current_state(void)
sve_to_fpsimd(current);
}
/*
* Called by KVM when entering the guest.
*/
void fpsimd_kvm_prepare(void)
{
if (!system_supports_sve())
return;
/*
* KVM does not save host SVE state since we can only enter
* the guest from a syscall so the ABI means that only the
* non-saved SVE state needs to be saved. If we have left
* SVE enabled for performance reasons then update the task
* state to be FPSIMD only.
*/
get_cpu_fpsimd_context();
if (test_and_clear_thread_flag(TIF_SVE)) {
sve_to_fpsimd(current);
current->thread.fp_type = FP_STATE_FPSIMD;
}
put_cpu_fpsimd_context();
}
/*
* Associate current's FPSIMD context with this cpu
* The caller must have ownership of the cpu FPSIMD context before calling
@ -1634,8 +1706,7 @@ void fpsimd_signal_preserve_current_state(void)
*/
static void fpsimd_bind_task_to_cpu(void)
{
struct fpsimd_last_state_struct *last =
this_cpu_ptr(&fpsimd_last_state);
struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
WARN_ON(!system_supports_fpsimd());
last->st = &current->thread.uw.fpsimd_state;
@ -1644,6 +1715,8 @@ static void fpsimd_bind_task_to_cpu(void)
last->sve_vl = task_get_sve_vl(current);
last->sme_vl = task_get_sme_vl(current);
last->svcr = &current->thread.svcr;
last->fp_type = &current->thread.fp_type;
last->to_save = FP_STATE_CURRENT;
current->thread.fpsimd_cpu = smp_processor_id();
/*
@ -1665,22 +1738,14 @@ static void fpsimd_bind_task_to_cpu(void)
}
}
void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state,
unsigned int sve_vl, void *za_state,
unsigned int sme_vl, u64 *svcr)
void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state)
{
struct fpsimd_last_state_struct *last =
this_cpu_ptr(&fpsimd_last_state);
struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state);
WARN_ON(!system_supports_fpsimd());
WARN_ON(!in_softirq() && !irqs_disabled());
last->st = st;
last->svcr = svcr;
last->sve_state = sve_state;
last->za_state = za_state;
last->sve_vl = sve_vl;
last->sme_vl = sme_vl;
*last = *state;
}
/*
@ -1838,7 +1903,7 @@ void kernel_neon_begin(void)
/* Invalidate any task state remaining in the fpsimd regs: */
fpsimd_flush_cpu_state();
}
EXPORT_SYMBOL(kernel_neon_begin);
EXPORT_SYMBOL_GPL(kernel_neon_begin);
/*
* kernel_neon_end(): give the CPU FPSIMD registers back to the current task
@ -1856,7 +1921,7 @@ void kernel_neon_end(void)
put_cpu_fpsimd_context();
}
EXPORT_SYMBOL(kernel_neon_end);
EXPORT_SYMBOL_GPL(kernel_neon_end);
#ifdef CONFIG_EFI

87
arch/arm64/kernel/ftrace.c
View File

@ -17,7 +17,49 @@
#include <asm/insn.h>
#include <asm/patching.h>
#ifdef CONFIG_DYNAMIC_FTRACE
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
struct fregs_offset {
const char *name;
int offset;
};
#define FREGS_OFFSET(n, field) \
{ \
.name = n, \
.offset = offsetof(struct ftrace_regs, field), \
}
static const struct fregs_offset fregs_offsets[] = {
FREGS_OFFSET("x0", regs[0]),
FREGS_OFFSET("x1", regs[1]),
FREGS_OFFSET("x2", regs[2]),
FREGS_OFFSET("x3", regs[3]),
FREGS_OFFSET("x4", regs[4]),
FREGS_OFFSET("x5", regs[5]),
FREGS_OFFSET("x6", regs[6]),
FREGS_OFFSET("x7", regs[7]),
FREGS_OFFSET("x8", regs[8]),
FREGS_OFFSET("x29", fp),
FREGS_OFFSET("x30", lr),
FREGS_OFFSET("lr", lr),
FREGS_OFFSET("sp", sp),
FREGS_OFFSET("pc", pc),
};
int ftrace_regs_query_register_offset(const char *name)
{
for (int i = 0; i < ARRAY_SIZE(fregs_offsets); i++) {
const struct fregs_offset *roff = &fregs_offsets[i];
if (!strcmp(roff->name, name))
return roff->offset;
}
return -EINVAL;
}
#endif
/*
* Replace a single instruction, which may be a branch or NOP.
* If @validate == true, a replaced instruction is checked against 'old'.
@ -70,9 +112,6 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
if (addr == FTRACE_ADDR)
return &plt[FTRACE_PLT_IDX];
if (addr == FTRACE_REGS_ADDR &&
IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
return &plt[FTRACE_REGS_PLT_IDX];
#endif
return NULL;
}
@ -154,25 +193,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
return ftrace_modify_code(pc, old, new, true);
}
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long addr)
{
unsigned long pc = rec->ip;
u32 old, new;
if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
return -EINVAL;
if (!ftrace_find_callable_addr(rec, NULL, &addr))
return -EINVAL;
old = aarch64_insn_gen_branch_imm(pc, old_addr,
AARCH64_INSN_BRANCH_LINK);
new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
return ftrace_modify_code(pc, old, new, true);
}
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
/*
* The compiler has inserted two NOPs before the regular function prologue.
* All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live,
@ -228,7 +249,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
*
* Note: 'mod' is only set at module load time.
*/
if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) &&
if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) &&
IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) {
return aarch64_insn_patch_text_nosync((void *)pc, new);
}
@ -246,7 +267,6 @@ void arch_ftrace_update_code(int command)
command |= FTRACE_MAY_SLEEP;
ftrace_modify_all_code(command);
}
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
/*
@ -277,21 +297,11 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
}
}
#ifdef CONFIG_DYNAMIC_FTRACE
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
/*
* When DYNAMIC_FTRACE_WITH_REGS is selected, `fregs` can never be NULL
* and arch_ftrace_get_regs(fregs) will always give a non-NULL pt_regs
* in which we can safely modify the LR.
*/
struct pt_regs *regs = arch_ftrace_get_regs(fregs);
unsigned long *parent = (unsigned long *)&procedure_link_pointer(regs);
prepare_ftrace_return(ip, parent, frame_pointer(regs));
prepare_ftrace_return(ip, &fregs->lr, fregs->fp);
}
#else
/*
@ -323,6 +333,5 @@ int ftrace_disable_ftrace_graph_caller(void)
{
return ftrace_modify_graph_caller(false);
}
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */

3
arch/arm64/kernel/head.S
View File

@ -462,6 +462,9 @@ SYM_FUNC_START_LOCAL(__primary_switched)
bl early_fdt_map // Try mapping the FDT early
mov x0, x20 // pass the full boot status
bl init_feature_override // Parse cpu feature overrides
#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS
bl scs_patch_vmlinux
#endif
mov x0, x20
bl finalise_el2 // Prefer VHE if possible
ldp x29, x30, [sp], #16

11
arch/arm64/kernel/irq.c
View File

@ -10,20 +10,21 @@
* Copyright (C) 2012 ARM Ltd.
*/
#include <linux/irq.h>
#include <linux/memory.h>
#include <linux/smp.h>
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/irqchip.h>
#include <linux/kprobes.h>
#include <linux/memory.h>
#include <linux/scs.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/vmalloc.h>
#include <asm/daifflags.h>
#include <asm/exception.h>
#include <asm/vmap_stack.h>
#include <asm/softirq_stack.h>
#include <asm/stacktrace.h>
#include <asm/vmap_stack.h>
/* Only access this in an NMI enter/exit */
DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts);
@ -41,7 +42,7 @@ static void init_irq_scs(void)
{
int cpu;
if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
if (!scs_is_enabled())
return;
for_each_possible_cpu(cpu)

11
arch/arm64/kernel/module.c
View File

@ -15,9 +15,11 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/moduleloader.h>
#include <linux/scs.h>
#include <linux/vmalloc.h>
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/scs.h>
#include <asm/sections.h>
void *module_alloc(unsigned long size)
@ -497,9 +499,6 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr,
__init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR);
if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS))
__init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR);
mod->arch.ftrace_trampolines = plts;
#endif
return 0;
@ -514,5 +513,11 @@ int module_finalize(const Elf_Ehdr *hdr,
if (s)
apply_alternatives_module((void *)s->sh_addr, s->sh_size);
if (scs_is_dynamic()) {
s = find_section(hdr, sechdrs, ".init.eh_frame");
if (s)
scs_patch((void *)s->sh_addr, s->sh_size);
}
return module_init_ftrace_plt(hdr, sechdrs, me);
}

4
arch/arm64/kernel/paravirt.c
View File

@ -141,10 +141,6 @@ static bool __init has_pv_steal_clock(void)
{
struct arm_smccc_res res;
/* To detect the presence of PV time support we require SMCCC 1.1+ */
if (arm_smccc_1_1_get_conduit() == SMCCC_CONDUIT_NONE)
return false;
arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
ARM_SMCCC_HV_PV_TIME_FEATURES, &res);

257
arch/arm64/kernel/patch-scs.c Normal file
View File

@ -0,0 +1,257 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2022 - Google LLC
* Author: Ard Biesheuvel <ardb@google.com>
*/
#include <linux/bug.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/linkage.h>
#include <linux/printk.h>
#include <linux/types.h>
#include <asm/cacheflush.h>
#include <asm/scs.h>
//
// This minimal DWARF CFI parser is partially based on the code in
// arch/arc/kernel/unwind.c, and on the document below:
// https://refspecs.linuxbase.org/LSB_4.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html
//
#define DW_CFA_nop 0x00
#define DW_CFA_set_loc 0x01
#define DW_CFA_advance_loc1 0x02
#define DW_CFA_advance_loc2 0x03
#define DW_CFA_advance_loc4 0x04
#define DW_CFA_offset_extended 0x05
#define DW_CFA_restore_extended 0x06
#define DW_CFA_undefined 0x07
#define DW_CFA_same_value 0x08
#define DW_CFA_register 0x09
#define DW_CFA_remember_state 0x0a
#define DW_CFA_restore_state 0x0b
#define DW_CFA_def_cfa 0x0c
#define DW_CFA_def_cfa_register 0x0d
#define DW_CFA_def_cfa_offset 0x0e
#define DW_CFA_def_cfa_expression 0x0f
#define DW_CFA_expression 0x10
#define DW_CFA_offset_extended_sf 0x11
#define DW_CFA_def_cfa_sf 0x12
#define DW_CFA_def_cfa_offset_sf 0x13
#define DW_CFA_val_offset 0x14
#define DW_CFA_val_offset_sf 0x15
#define DW_CFA_val_expression 0x16
#define DW_CFA_lo_user 0x1c
#define DW_CFA_negate_ra_state 0x2d
#define DW_CFA_GNU_args_size 0x2e
#define DW_CFA_GNU_negative_offset_extended 0x2f
#define DW_CFA_hi_user 0x3f
extern const u8 __eh_frame_start[], __eh_frame_end[];
enum {
PACIASP = 0xd503233f,
AUTIASP = 0xd50323bf,
SCS_PUSH = 0xf800865e,
SCS_POP = 0xf85f8e5e,
};
static void __always_inline scs_patch_loc(u64 loc)
{
u32 insn = le32_to_cpup((void *)loc);
switch (insn) {
case PACIASP:
*(u32 *)loc = cpu_to_le32(SCS_PUSH);
break;
case AUTIASP:
*(u32 *)loc = cpu_to_le32(SCS_POP);
break;
default:
/*
* While the DW_CFA_negate_ra_state directive is guaranteed to
* appear right after a PACIASP/AUTIASP instruction, it may
* also appear after a DW_CFA_restore_state directive that
* restores a state that is only partially accurate, and is
* followed by DW_CFA_negate_ra_state directive to toggle the
* PAC bit again. So we permit other instructions here, and ignore
* them.
*/
return;
}
dcache_clean_pou(loc, loc + sizeof(u32));
}
/*
* Skip one uleb128/sleb128 encoded quantity from the opcode stream. All bytes
* except the last one have bit #7 set.
*/
static int __always_inline skip_xleb128(const u8 **opcode, int size)
{
u8 c;
do {
c = *(*opcode)++;
size--;
} while (c & BIT(7));
return size;
}
struct eh_frame {
/*
* The size of this frame if 0 < size < U32_MAX, 0 terminates the list.
*/
u32 size;
/*
* The first frame is a Common Information Entry (CIE) frame, followed
* by one or more Frame Description Entry (FDE) frames. In the former
* case, this field is 0, otherwise it is the negated offset relative
* to the associated CIE frame.
*/
u32 cie_id_or_pointer;
union {
struct { // CIE
u8 version;
u8 augmentation_string[];
};
struct { // FDE
s32 initial_loc;
s32 range;
u8 opcodes[];
};
};
};
static int noinstr scs_handle_fde_frame(const struct eh_frame *frame,
bool fde_has_augmentation_data,
int code_alignment_factor)
{
int size = frame->size - offsetof(struct eh_frame, opcodes) + 4;
u64 loc = (u64)offset_to_ptr(&frame->initial_loc);
const u8 *opcode = frame->opcodes;
if (fde_has_augmentation_data) {
int l;
// assume single byte uleb128_t
if (WARN_ON(*opcode & BIT(7)))
return -ENOEXEC;
l = *opcode++;
opcode += l;
size -= l + 1;
}
/*
* Starting from 'loc', apply the CFA opcodes that advance the location
* pointer, and identify the locations of the PAC instructions.
*/
while (size-- > 0) {
switch (*opcode++) {
case DW_CFA_nop:
case DW_CFA_remember_state:
case DW_CFA_restore_state:
break;
case DW_CFA_advance_loc1:
loc += *opcode++ * code_alignment_factor;
size--;
break;
case DW_CFA_advance_loc2:
loc += *opcode++ * code_alignment_factor;
loc += (*opcode++ << 8) * code_alignment_factor;
size -= 2;
break;
case DW_CFA_def_cfa:
case DW_CFA_offset_extended:
size = skip_xleb128(&opcode, size);
fallthrough;
case DW_CFA_def_cfa_offset:
case DW_CFA_def_cfa_offset_sf:
case DW_CFA_def_cfa_register:
case DW_CFA_same_value:
case DW_CFA_restore_extended:
case 0x80 ... 0xbf:
size = skip_xleb128(&opcode, size);
break;
case DW_CFA_negate_ra_state:
scs_patch_loc(loc - 4);
break;
case 0x40 ... 0x7f:
// advance loc
loc += (opcode[-1] & 0x3f) * code_alignment_factor;
break;
case 0xc0 ... 0xff:
break;
default:
pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame);
return -ENOEXEC;
}
}
return 0;
}
int noinstr scs_patch(const u8 eh_frame[], int size)
{
const u8 *p = eh_frame;
while (size > 4) {
const struct eh_frame *frame = (const void *)p;
bool fde_has_augmentation_data = true;
int code_alignment_factor = 1;
int ret;
if (frame->size == 0 ||
frame->size == U32_MAX ||
frame->size > size)
break;
if (frame->cie_id_or_pointer == 0) {
const u8 *p = frame->augmentation_string;
/* a 'z' in the augmentation string must come first */
fde_has_augmentation_data = *p == 'z';
/*
* The code alignment factor is a uleb128 encoded field
* but given that the only sensible values are 1 or 4,
* there is no point in decoding the whole thing.
*/
p += strlen(p) + 1;
if (!WARN_ON(*p & BIT(7)))
code_alignment_factor = *p;
} else {
ret = scs_handle_fde_frame(frame,
fde_has_augmentation_data,
code_alignment_factor);
if (ret)
return ret;
}
p += sizeof(frame->size) + frame->size;
size -= sizeof(frame->size) + frame->size;
}
return 0;
}
asmlinkage void __init scs_patch_vmlinux(void)
{
if (!should_patch_pac_into_scs())
return;
WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start));
icache_inval_all_pou();
isb();
}

3
arch/arm64/kernel/perf_event.c
View File

@ -1146,7 +1146,8 @@ static void __armv8pmu_probe_pmu(void *info)
dfr0 = read_sysreg(id_aa64dfr0_el1);
pmuver = cpuid_feature_extract_unsigned_field(dfr0,
ID_AA64DFR0_EL1_PMUVer_SHIFT);
if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF || pmuver == 0)
if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF ||
pmuver == ID_AA64DFR0_EL1_PMUVer_NI)
return;
cpu_pmu->pmuver = pmuver;

1
arch/arm64/kernel/pi/Makefile
View File

@ -7,6 +7,7 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \
-I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \
-include $(srctree)/include/linux/hidden.h \
-D__DISABLE_EXPORTS -ffreestanding -D__NO_FORTIFY \
-fno-asynchronous-unwind-tables -fno-unwind-tables \
$(call cc-option,-fno-addrsig)
# remove SCS flags from all objects in this directory

2
arch/arm64/kernel/probes/decode-insn.c
View File

@ -24,7 +24,7 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn)
* currently safe. Lastly, MSR instructions can do any number of nasty
* things we can't handle during single-stepping.
*/
if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) {
if (aarch64_insn_is_class_branch_sys(insn)) {
if (aarch64_insn_is_branch(insn) ||
aarch64_insn_is_msr_imm(insn) ||
aarch64_insn_is_msr_reg(insn) ||

88
arch/arm64/kernel/probes/kprobes.c
View File

@ -294,19 +294,12 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
}
break;
case KPROBE_HIT_ACTIVE:
case KPROBE_HIT_SSDONE:
/*
* In case the user-specified fault handler returned
* zero, try to fix up.
*/
if (fixup_exception(regs))
return 1;
}
return 0;
}
static void __kprobes kprobe_handler(struct pt_regs *regs)
static int __kprobes
kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr)
{
struct kprobe *p, *cur_kprobe;
struct kprobe_ctlblk *kcb;
@ -316,39 +309,44 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
cur_kprobe = kprobe_running();
p = get_kprobe((kprobe_opcode_t *) addr);
if (p) {
if (cur_kprobe) {
if (reenter_kprobe(p, regs, kcb))
return;
} else {
/* Probe hit */
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
/*
* If we have no pre-handler or it returned 0, we
* continue with normal processing. If we have a
* pre-handler and it returned non-zero, it will
* modify the execution path and no need to single
* stepping. Let's just reset current kprobe and exit.
*/
if (!p->pre_handler || !p->pre_handler(p, regs)) {
setup_singlestep(p, regs, kcb, 0);
} else
reset_current_kprobe();
}
if (WARN_ON_ONCE(!p)) {
/*
* Something went wrong. This BRK used an immediate reserved
* for kprobes, but we couldn't find any corresponding probe.
*/
return DBG_HOOK_ERROR;
}
/*
* The breakpoint instruction was removed right
* after we hit it. Another cpu has removed
* either a probepoint or a debugger breakpoint
* at this address. In either case, no further
* handling of this interrupt is appropriate.
* Return back to original instruction, and continue.
*/
if (cur_kprobe) {
/* Hit a kprobe inside another kprobe */
if (!reenter_kprobe(p, regs, kcb))
return DBG_HOOK_ERROR;
} else {
/* Probe hit */
set_current_kprobe(p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
/*
* If we have no pre-handler or it returned 0, we
* continue with normal processing. If we have a
* pre-handler and it returned non-zero, it will
* modify the execution path and not need to single-step
* Let's just reset current kprobe and exit.
*/
if (!p->pre_handler || !p->pre_handler(p, regs))
setup_singlestep(p, regs, kcb, 0);
else
reset_current_kprobe();
}
return DBG_HOOK_HANDLED;
}
static struct break_hook kprobes_break_hook = {
.imm = KPROBES_BRK_IMM,
.fn = kprobe_breakpoint_handler,
};
static int __kprobes
kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned long esr)
{
@ -373,18 +371,6 @@ static struct break_hook kprobes_break_ss_hook = {
.fn = kprobe_breakpoint_ss_handler,
};
static int __kprobes
kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr)
{
kprobe_handler(regs);
return DBG_HOOK_HANDLED;
}
static struct break_hook kprobes_break_hook = {
.imm = KPROBES_BRK_IMM,
.fn = kprobe_breakpoint_handler,
};
/*
* Provide a blacklist of symbols identifying ranges which cannot be kprobed.
* This blacklist is exposed to userspace via debugfs (kprobes/blacklist).

2
arch/arm64/kernel/process.c
View File

@ -331,6 +331,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
clear_tsk_thread_flag(dst, TIF_SME);
}
dst->thread.fp_type = FP_STATE_FPSIMD;
/* clear any pending asynchronous tag fault raised by the parent */
clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);

26
arch/arm64/kernel/proton-pack.c
View File

@ -521,10 +521,13 @@ bool has_spectre_v4(const struct arm64_cpu_capabilities *cap, int scope)
return state != SPECTRE_UNAFFECTED;
}
static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr)
{
if (user_mode(regs))
return 1;
const u32 instr_mask = ~(1U << PSTATE_Imm_shift);
const u32 instr_val = 0xd500401f | PSTATE_SSBS;
if ((instr & instr_mask) != instr_val)
return false;
if (instr & BIT(PSTATE_Imm_shift))
regs->pstate |= PSR_SSBS_BIT;
@ -532,19 +535,11 @@ static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
regs->pstate &= ~PSR_SSBS_BIT;
arm64_skip_faulting_instruction(regs, 4);
return 0;
return true;
}
static struct undef_hook ssbs_emulation_hook = {
.instr_mask = ~(1U << PSTATE_Imm_shift),
.instr_val = 0xd500401f | PSTATE_SSBS,
.fn = ssbs_emulation_handler,
};
static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
{
static bool undef_hook_registered = false;
static DEFINE_RAW_SPINLOCK(hook_lock);
enum mitigation_state state;
/*
@ -555,13 +550,6 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
if (state != SPECTRE_MITIGATED || !this_cpu_has_cap(ARM64_SSBS))
return state;
raw_spin_lock(&hook_lock);
if (!undef_hook_registered) {
register_undef_hook(&ssbs_emulation_hook);
undef_hook_registered = true;
}
raw_spin_unlock(&hook_lock);
if (spectre_v4_mitigations_off()) {
sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
set_pstate_ssbs(1);

5
arch/arm64/kernel/ptrace.c
View File

@ -907,8 +907,7 @@ static int sve_set_common(struct task_struct *target,
ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
SVE_PT_FPSIMD_OFFSET);
clear_tsk_thread_flag(target, TIF_SVE);
if (type == ARM64_VEC_SME)
fpsimd_force_sync_to_sve(target);
target->thread.fp_type = FP_STATE_FPSIMD;
goto out;
}
@ -931,6 +930,7 @@ static int sve_set_common(struct task_struct *target,
if (!target->thread.sve_state) {
ret = -ENOMEM;
clear_tsk_thread_flag(target, TIF_SVE);
target->thread.fp_type = FP_STATE_FPSIMD;
goto out;
}
@ -942,6 +942,7 @@ static int sve_set_common(struct task_struct *target,
*/
fpsimd_sync_to_sve(target);
set_tsk_thread_flag(target, TIF_SVE);
target->thread.fp_type = FP_STATE_SVE;
BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
start = SVE_PT_SVE_OFFSET;

2
arch/arm64/kernel/sdei.c
View File

@ -144,7 +144,7 @@ static int init_sdei_scs(void)
int cpu;
int err = 0;
if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK))
if (!scs_is_enabled())
return 0;
for_each_possible_cpu(cpu) {

4
arch/arm64/kernel/setup.c
View File

@ -30,6 +30,7 @@
#include <linux/efi.h>
#include <linux/psci.h>
#include <linux/sched/task.h>
#include <linux/scs.h>
#include <linux/mm.h>
#include <asm/acpi.h>
@ -42,6 +43,7 @@
#include <asm/cpu_ops.h>
#include <asm/kasan.h>
#include <asm/numa.h>
#include <asm/scs.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/smp_plat.h>
@ -312,6 +314,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
jump_label_init();
parse_early_param();
dynamic_scs_init();
/*
* Unmask asynchronous aborts and fiq after bringing up possible
* earlycon. (Report possible System Errors once we can report this

7
arch/arm64/kernel/signal.c
View File

@ -207,6 +207,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx)
__get_user_error(fpsimd.fpcr, &ctx->fpcr, err);
clear_thread_flag(TIF_SVE);
current->thread.fp_type = FP_STATE_FPSIMD;
/* load the hardware registers from the fpsimd_state structure */
if (!err)
@ -292,6 +293,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
if (sve.head.size <= sizeof(*user->sve)) {
clear_thread_flag(TIF_SVE);
current->thread.svcr &= ~SVCR_SM_MASK;
current->thread.fp_type = FP_STATE_FPSIMD;
goto fpsimd_only;
}
@ -327,6 +329,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
current->thread.svcr |= SVCR_SM_MASK;
else
set_thread_flag(TIF_SVE);
current->thread.fp_type = FP_STATE_SVE;
fpsimd_only:
/* copy the FP and status/control registers */
@ -932,9 +935,11 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
* FPSIMD register state - flush the saved FPSIMD
* register state in case it gets loaded.
*/
if (current->thread.svcr & SVCR_SM_MASK)
if (current->thread.svcr & SVCR_SM_MASK) {
memset(&current->thread.uw.fpsimd_state, 0,
sizeof(current->thread.uw.fpsimd_state));
current->thread.fp_type = FP_STATE_FPSIMD;
}
current->thread.svcr &= ~(SVCR_ZA_MASK |
SVCR_SM_MASK);

10
arch/arm64/kernel/stacktrace.c
View File

@ -23,8 +23,8 @@
*
* The regs must be on a stack currently owned by the calling task.
*/
static inline void unwind_init_from_regs(struct unwind_state *state,
struct pt_regs *regs)
static __always_inline void unwind_init_from_regs(struct unwind_state *state,
struct pt_regs *regs)
{
unwind_init_common(state, current);
@ -58,8 +58,8 @@ static __always_inline void unwind_init_from_caller(struct unwind_state *state)
* duration of the unwind, or the unwind will be bogus. It is never valid to
* call this for the current task.
*/
static inline void unwind_init_from_task(struct unwind_state *state,
struct task_struct *task)
static __always_inline void unwind_init_from_task(struct unwind_state *state,
struct task_struct *task)
{
unwind_init_common(state, task);
@ -186,7 +186,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
: stackinfo_get_unknown(); \
})
noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry,
noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task,
struct pt_regs *regs)
{

2
arch/arm64/kernel/suspend.c
View File

@ -60,6 +60,8 @@ void notrace __cpu_suspend_exit(void)
* PSTATE was not saved over suspend/resume, re-enable any detected
* features that might not have been set correctly.
*/
if (cpus_have_const_cap(ARM64_HAS_DIT))
set_pstate_dit(1);
__uaccess_enable_hw_pan();
/*

19
arch/arm64/kernel/syscall.c
View File

@ -183,21 +183,12 @@ static inline void fp_user_discard(void)
if (!system_supports_sve())
return;
/*
* If SME is not active then disable SVE, the registers will
* be cleared when userspace next attempts to access them and
* we do not need to track the SVE register state until then.
*/
clear_thread_flag(TIF_SVE);
if (test_thread_flag(TIF_SVE)) {
unsigned int sve_vq_minus_one;
/*
* task_fpsimd_load() won't be called to update CPACR_EL1 in
* ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
* happens if a context switch or kernel_neon_begin() or context
* modification (sigreturn, ptrace) intervenes.
* So, ensure that CPACR_EL1 is already correct for the fast-path case.
*/
sve_user_disable();
sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1;
sve_flush_live(true, sve_vq_minus_one);
}
}
void do_el0_svc(struct pt_regs *regs)

93
arch/arm64/kernel/traps.c
View File

@ -373,51 +373,22 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
regs->pstate &= ~PSR_BTYPE_MASK;
}
static LIST_HEAD(undef_hook);
static DEFINE_RAW_SPINLOCK(undef_lock);
void register_undef_hook(struct undef_hook *hook)
static int user_insn_read(struct pt_regs *regs, u32 *insnp)
{
unsigned long flags;
raw_spin_lock_irqsave(&undef_lock, flags);
list_add(&hook->node, &undef_hook);
raw_spin_unlock_irqrestore(&undef_lock, flags);
}
void unregister_undef_hook(struct undef_hook *hook)
{
unsigned long flags;
raw_spin_lock_irqsave(&undef_lock, flags);
list_del(&hook->node);
raw_spin_unlock_irqrestore(&undef_lock, flags);
}
static int call_undef_hook(struct pt_regs *regs)
{
struct undef_hook *hook;
unsigned long flags;
u32 instr;
int (*fn)(struct pt_regs *regs, u32 instr) = NULL;
unsigned long pc = instruction_pointer(regs);
if (!user_mode(regs)) {
__le32 instr_le;
if (get_kernel_nofault(instr_le, (__le32 *)pc))
goto exit;
instr = le32_to_cpu(instr_le);
} else if (compat_thumb_mode(regs)) {
if (compat_thumb_mode(regs)) {
/* 16-bit Thumb instruction */
__le16 instr_le;
if (get_user(instr_le, (__le16 __user *)pc))
goto exit;
return -EFAULT;
instr = le16_to_cpu(instr_le);
if (aarch32_insn_is_wide(instr)) {
u32 instr2;
if (get_user(instr_le, (__le16 __user *)(pc + 2)))
goto exit;
return -EFAULT;
instr2 = le16_to_cpu(instr_le);
instr = (instr << 16) | instr2;
}
@ -425,19 +396,12 @@ static int call_undef_hook(struct pt_regs *regs)
/* 32-bit ARM instruction */
__le32 instr_le;
if (get_user(instr_le, (__le32 __user *)pc))
goto exit;
return -EFAULT;
instr = le32_to_cpu(instr_le);
}
raw_spin_lock_irqsave(&undef_lock, flags);
list_for_each_entry(hook, &undef_hook, node)
if ((instr & hook->instr_mask) == hook->instr_val &&
(regs->pstate & hook->pstate_mask) == hook->pstate_val)
fn = hook->fn;
raw_spin_unlock_irqrestore(&undef_lock, flags);
exit:
return fn ? fn(regs, instr) : 1;
*insnp = instr;
return 0;
}
void force_signal_inject(int signal, int code, unsigned long address, unsigned long err)
@ -486,21 +450,40 @@ void arm64_notify_segfault(unsigned long addr)
force_signal_inject(SIGSEGV, code, addr, 0);
}
void do_undefinstr(struct pt_regs *regs, unsigned long esr)
void do_el0_undef(struct pt_regs *regs, unsigned long esr)
{
u32 insn;
/* check for AArch32 breakpoint instructions */
if (!aarch32_break_handler(regs))
return;
if (call_undef_hook(regs) == 0)
if (user_insn_read(regs, &insn))
goto out_err;
if (try_emulate_mrs(regs, insn))
return;
if (!user_mode(regs))
die("Oops - Undefined instruction", regs, esr);
if (try_emulate_armv8_deprecated(regs, insn))
return;
out_err:
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
}
NOKPROBE_SYMBOL(do_undefinstr);
void do_el1_undef(struct pt_regs *regs, unsigned long esr)
{
u32 insn;
if (aarch64_insn_read((void *)regs->pc, &insn))
goto out_err;
if (try_emulate_el1_ssbs(regs, insn))
return;
out_err:
die("Oops - Undefined instruction", regs, esr);
}
void do_el0_bti(struct pt_regs *regs)
{
@ -511,7 +494,6 @@ void do_el1_bti(struct pt_regs *regs, unsigned long esr)
{
die("Oops - BTI", regs, esr);
}
NOKPROBE_SYMBOL(do_el1_bti);
void do_el0_fpac(struct pt_regs *regs, unsigned long esr)
{
@ -526,7 +508,6 @@ void do_el1_fpac(struct pt_regs *regs, unsigned long esr)
*/
die("Oops - FPAC", regs, esr);
}
NOKPROBE_SYMBOL(do_el1_fpac)
#define __user_cache_maint(insn, address, res) \
if (address >= TASK_SIZE_MAX) { \
@ -748,7 +729,7 @@ static const struct sys64_hook cp15_64_hooks[] = {
{},
};
void do_cp15instr(unsigned long esr, struct pt_regs *regs)
void do_el0_cp15(unsigned long esr, struct pt_regs *regs)
{
const struct sys64_hook *hook, *hook_base;
@ -769,7 +750,7 @@ void do_cp15instr(unsigned long esr, struct pt_regs *regs)
hook_base = cp15_64_hooks;
break;
default:
do_undefinstr(regs, esr);
do_el0_undef(regs, esr);
return;
}
@ -784,12 +765,11 @@ void do_cp15instr(unsigned long esr, struct pt_regs *regs)
* EL0. Fall back to our usual undefined instruction handler
* so that we handle these consistently.
*/
do_undefinstr(regs, esr);
do_el0_undef(regs, esr);
}
NOKPROBE_SYMBOL(do_cp15instr);
#endif
void do_sysinstr(unsigned long esr, struct pt_regs *regs)
void do_el0_sys(unsigned long esr, struct pt_regs *regs)
{
const struct sys64_hook *hook;
@ -804,9 +784,8 @@ void do_sysinstr(unsigned long esr, struct pt_regs *regs)
* back to our usual undefined instruction handler so that we handle
* these consistently.
*/
do_undefinstr(regs, esr);
do_el0_undef(regs, esr);
}
NOKPROBE_SYMBOL(do_sysinstr);
static const char *esr_class_str[] = {
[0 ... ESR_ELx_EC_MAX] = "UNRECOGNIZED EC",

13
arch/arm64/kernel/vmlinux.lds.S
View File

@ -121,6 +121,17 @@ jiffies = jiffies_64;
#define TRAMP_TEXT
#endif
#ifdef CONFIG_UNWIND_TABLES
#define UNWIND_DATA_SECTIONS \
.eh_frame : { \
__eh_frame_start = .; \
*(.eh_frame) \
__eh_frame_end = .; \
}
#else
#define UNWIND_DATA_SECTIONS
#endif
/*
* The size of the PE/COFF section that covers the kernel image, which
* runs from _stext to _edata, must be a round multiple of the PE/COFF
@ -231,6 +242,8 @@ SECTIONS
__alt_instructions_end = .;
}
UNWIND_DATA_SECTIONS
. = ALIGN(SEGMENT_ALIGN);
__inittext_end = .;
__initdata_begin = .;

26
arch/arm64/kvm/fpsimd.c
View File

@ -75,11 +75,12 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
{
BUG_ON(!current->mm);
BUG_ON(test_thread_flag(TIF_SVE));
if (!system_supports_fpsimd())
return;
fpsimd_kvm_prepare();
vcpu->arch.fp_state = FP_STATE_HOST_OWNED;
vcpu_clear_flag(vcpu, HOST_SVE_ENABLED);
@ -129,20 +130,31 @@ void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu)
*/
void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
{
struct cpu_fp_state fp_state;
WARN_ON_ONCE(!irqs_disabled());
if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) {
/*
* Currently we do not support SME guests so SVCR is
* always 0 and we just need a variable to point to.
*/
fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs,
vcpu->arch.sve_state,
vcpu->arch.sve_max_vl,
NULL, 0, &vcpu->arch.svcr);
fp_state.st = &vcpu->arch.ctxt.fp_regs;
fp_state.sve_state = vcpu->arch.sve_state;
fp_state.sve_vl = vcpu->arch.sve_max_vl;
fp_state.za_state = NULL;
fp_state.svcr = &vcpu->arch.svcr;
fp_state.fp_type = &vcpu->arch.fp_type;
if (vcpu_has_sve(vcpu))
fp_state.to_save = FP_STATE_SVE;
else
fp_state.to_save = FP_STATE_FPSIMD;
fpsimd_bind_state_to_cpu(&fp_state);
clear_thread_flag(TIF_FOREIGN_FPSTATE);
update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));
}
}
@ -199,7 +211,5 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
}
update_thread_flag(TIF_SVE, 0);
local_irq_restore(flags);
}

1
arch/arm64/kvm/hyp/nvhe/Makefile
View File

@ -96,6 +96,7 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI)
# when profile optimization is applied. gen-hyprel does not support SHT_REL and
# causes a build failure. Remove profile optimization flags.
KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS))
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
# KVM nVHE code is run at a different exception code with a different map, so
# compiler instrumentation that inserts callbacks or checks into the code may

4
arch/arm64/kvm/sys_regs.c
View File

@ -1121,8 +1121,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r
case SYS_ID_DFR0_EL1:
/* Limit guests to PMUv3 for ARMv8.4 */
val = cpuid_feature_cap_perfmon_field(val,
ID_DFR0_PERFMON_SHIFT,
kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_PERFMON_8_4 : 0);
ID_DFR0_EL1_PerfMon_SHIFT,
kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_EL1_PerfMon_PMUv3p4 : 0);
break;
}

165
arch/arm64/lib/insn.c
View File

@ -20,91 +20,6 @@
#define AARCH64_INSN_N_BIT BIT(22)
#define AARCH64_INSN_LSL_12 BIT(22)
static const int aarch64_insn_encoding_class[] = {
AARCH64_INSN_CLS_UNKNOWN,
AARCH64_INSN_CLS_UNKNOWN,
AARCH64_INSN_CLS_SVE,
AARCH64_INSN_CLS_UNKNOWN,
AARCH64_INSN_CLS_LDST,
AARCH64_INSN_CLS_DP_REG,
AARCH64_INSN_CLS_LDST,
AARCH64_INSN_CLS_DP_FPSIMD,
AARCH64_INSN_CLS_DP_IMM,
AARCH64_INSN_CLS_DP_IMM,
AARCH64_INSN_CLS_BR_SYS,
AARCH64_INSN_CLS_BR_SYS,
AARCH64_INSN_CLS_LDST,
AARCH64_INSN_CLS_DP_REG,
AARCH64_INSN_CLS_LDST,
AARCH64_INSN_CLS_DP_FPSIMD,
};
enum aarch64_insn_encoding_class __kprobes aarch64_get_insn_class(u32 insn)
{
return aarch64_insn_encoding_class[(insn >> 25) & 0xf];
}
bool __kprobes aarch64_insn_is_steppable_hint(u32 insn)
{
if (!aarch64_insn_is_hint(insn))
return false;
switch (insn & 0xFE0) {
case AARCH64_INSN_HINT_XPACLRI:
case AARCH64_INSN_HINT_PACIA_1716:
case AARCH64_INSN_HINT_PACIB_1716:
case AARCH64_INSN_HINT_PACIAZ:
case AARCH64_INSN_HINT_PACIASP:
case AARCH64_INSN_HINT_PACIBZ:
case AARCH64_INSN_HINT_PACIBSP:
case AARCH64_INSN_HINT_BTI:
case AARCH64_INSN_HINT_BTIC:
case AARCH64_INSN_HINT_BTIJ:
case AARCH64_INSN_HINT_BTIJC:
case AARCH64_INSN_HINT_NOP:
return true;
default:
return false;
}
}
bool aarch64_insn_is_branch_imm(u32 insn)
{
return (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) ||
aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) ||
aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) ||
aarch64_insn_is_bcond(insn));
}
bool __kprobes aarch64_insn_uses_literal(u32 insn)
{
/* ldr/ldrsw (literal), prfm */
return aarch64_insn_is_ldr_lit(insn) ||
aarch64_insn_is_ldrsw_lit(insn) ||
aarch64_insn_is_adr_adrp(insn) ||
aarch64_insn_is_prfm_lit(insn);
}
bool __kprobes aarch64_insn_is_branch(u32 insn)
{
/* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */
return aarch64_insn_is_b(insn) ||
aarch64_insn_is_bl(insn) ||
aarch64_insn_is_cbz(insn) ||
aarch64_insn_is_cbnz(insn) ||
aarch64_insn_is_tbz(insn) ||
aarch64_insn_is_tbnz(insn) ||
aarch64_insn_is_ret(insn) ||
aarch64_insn_is_ret_auth(insn) ||
aarch64_insn_is_br(insn) ||
aarch64_insn_is_br_auth(insn) ||
aarch64_insn_is_blr(insn) ||
aarch64_insn_is_blr_auth(insn) ||
aarch64_insn_is_bcond(insn);
}
static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type,
u32 *maskp, int *shiftp)
{
@ -435,16 +350,6 @@ u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr,
offset >> 2);
}
u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op)
{
return aarch64_insn_get_hint_value() | op;
}
u32 __kprobes aarch64_insn_gen_nop(void)
{
return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP);
}
u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
enum aarch64_insn_branch_type type)
{
@ -816,76 +721,6 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result,
}
#endif
static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type,
enum aarch64_insn_prfm_target target,
enum aarch64_insn_prfm_policy policy,
u32 insn)
{
u32 imm_type = 0, imm_target = 0, imm_policy = 0;
switch (type) {
case AARCH64_INSN_PRFM_TYPE_PLD:
break;
case AARCH64_INSN_PRFM_TYPE_PLI:
imm_type = BIT(0);
break;
case AARCH64_INSN_PRFM_TYPE_PST:
imm_type = BIT(1);
break;
default:
pr_err("%s: unknown prfm type encoding %d\n", __func__, type);
return AARCH64_BREAK_FAULT;
}
switch (target) {
case AARCH64_INSN_PRFM_TARGET_L1:
break;
case AARCH64_INSN_PRFM_TARGET_L2:
imm_target = BIT(0);
break;
case AARCH64_INSN_PRFM_TARGET_L3:
imm_target = BIT(1);
break;
default:
pr_err("%s: unknown prfm target encoding %d\n", __func__, target);
return AARCH64_BREAK_FAULT;
}
switch (policy) {
case AARCH64_INSN_PRFM_POLICY_KEEP:
break;
case AARCH64_INSN_PRFM_POLICY_STRM:
imm_policy = BIT(0);
break;
default:
pr_err("%s: unknown prfm policy encoding %d\n", __func__, policy);
return AARCH64_BREAK_FAULT;
}
/* In this case, imm5 is encoded into Rt field. */
insn &= ~GENMASK(4, 0);
insn |= imm_policy | (imm_target << 1) | (imm_type << 3);
return insn;
}
u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
enum aarch64_insn_prfm_type type,
enum aarch64_insn_prfm_target target,
enum aarch64_insn_prfm_policy policy)
{
u32 insn = aarch64_insn_get_prfm_value();
insn = aarch64_insn_encode_ldst_size(AARCH64_INSN_SIZE_64, insn);
insn = aarch64_insn_encode_prfm_imm(type, target, policy, insn);
insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
base);
return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, 0);
}
u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
enum aarch64_insn_register src,
int imm, enum aarch64_insn_variant variant,

2
arch/arm64/lib/mte.S
View File

@ -18,7 +18,7 @@
*/
.macro multitag_transfer_size, reg, tmp
mrs_s \reg, SYS_GMID_EL1
ubfx \reg, \reg, #GMID_EL1_BS_SHIFT, #GMID_EL1_BS_SIZE
ubfx \reg, \reg, #GMID_EL1_BS_SHIFT, #GMID_EL1_BS_WIDTH
mov \tmp, #4
lsl \reg, \tmp, \reg
.endm

8
arch/arm64/mm/fault.c
View File

@ -353,6 +353,11 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned long esr)
return false;
}
static bool is_translation_fault(unsigned long esr)
{
return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT;
}
static void __do_kernel_fault(unsigned long addr, unsigned long esr,
struct pt_regs *regs)
{
@ -385,7 +390,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
} else if (addr < PAGE_SIZE) {
msg = "NULL pointer dereference";
} else {
if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs))
if (is_translation_fault(esr) &&
kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs))
return;
msg = "paging request";

21
arch/arm64/mm/hugetlbpage.c
View File

@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
{
return __hugetlb_valid_size(size);
}
pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
{
if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_2645198) &&
cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
/*
* Break-before-make (BBM) is required for all user space mappings
* when the permission changes from executable to non-executable
* in cases where cpu is affected with errata #2645198.
*/
if (pte_user_exec(READ_ONCE(*ptep)))
return huge_ptep_clear_flush(vma, addr, ptep);
}
return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}

25
arch/arm64/mm/init.c
View File

@ -96,6 +96,8 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
#define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit
#define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1)
#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20)
static int __init reserve_crashkernel_low(unsigned long long low_size)
{
unsigned long long low_base;
@ -130,6 +132,7 @@ static void __init reserve_crashkernel(void)
unsigned long long crash_max = CRASH_ADDR_LOW_MAX;
char *cmdline = boot_command_line;
int ret;
bool fixed_base = false;
if (!IS_ENABLED(CONFIG_KEXEC_CORE))
return;
@ -147,7 +150,9 @@ static void __init reserve_crashkernel(void)
* is not allowed.
*/
ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
if (ret && (ret != -ENOENT))
if (ret == -ENOENT)
crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
else if (ret)
return;
crash_max = CRASH_ADDR_HIGH_MAX;
@ -159,18 +164,32 @@ static void __init reserve_crashkernel(void)
crash_size = PAGE_ALIGN(crash_size);
/* User specifies base address explicitly. */
if (crash_base)
if (crash_base) {
fixed_base = true;
crash_max = crash_base + crash_size;
}
retry:
crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN,
crash_base, crash_max);
if (!crash_base) {
/*
* If the first attempt was for low memory, fall back to
* high memory, the minimum required low memory will be
* reserved later.
*/
if (!fixed_base && (crash_max == CRASH_ADDR_LOW_MAX)) {
crash_max = CRASH_ADDR_HIGH_MAX;
crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
goto retry;
}
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
crash_size);
return;
}
if ((crash_base >= CRASH_ADDR_LOW_MAX) &&
if ((crash_base > CRASH_ADDR_LOW_MAX - crash_low_size) &&
crash_low_size && reserve_crashkernel_low(crash_low_size)) {
memblock_phys_free(crash_base, crash_size);
return;

23
arch/arm64/mm/mmu.c
View File

@ -1196,7 +1196,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
if (!ARM64_KERNEL_USES_PMD_MAPS)
if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES))
return vmemmap_populate_basepages(start, end, node, altmap);
do {
@ -1702,3 +1702,24 @@ static int __init prevent_bootmem_remove_init(void)
}
early_initcall(prevent_bootmem_remove_init);
#endif
pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
{
if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_2645198) &&
cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
/*
* Break-before-make (BBM) is required for all user space mappings
* when the permission changes from executable to non-executable
* in cases where cpu is affected with errata #2645198.
*/
if (pte_user_exec(READ_ONCE(*ptep)))
return ptep_clear_flush(vma, addr, ptep);
}
return ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
set_pte_at(vma->vm_mm, addr, ptep, pte);
}

4
arch/arm64/mm/proc.S
View File

@ -189,16 +189,12 @@ SYM_FUNC_END(cpu_do_resume)
* called by anything else. It can only be executed from a TTBR0 mapping.
*/
SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1)
save_and_disable_daif flags=x2
__idmap_cpu_set_reserved_ttbr1 x1, x3
offset_ttbr1 x0, x3
msr ttbr1_el1, x0
isb
restore_daif x2
ret
SYM_FUNC_END(idmap_cpu_replace_ttbr1)
.popsection

2
arch/arm64/tools/cpucaps
View File

@ -20,6 +20,7 @@ HAS_CNP
HAS_CRC32
HAS_DCPODP
HAS_DCPOP
HAS_DIT
HAS_E0PD
HAS_ECV
HAS_EPAN
@ -70,6 +71,7 @@ WORKAROUND_2038923
WORKAROUND_2064142
WORKAROUND_2077057
WORKAROUND_2457168
WORKAROUND_2645198
WORKAROUND_2658417
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE

2
arch/arm64/tools/gen-sysreg.awk
View File

@ -33,7 +33,7 @@ function expect_fields(nf) {
# Print a CPP macro definition, padded with spaces so that the macro bodies
# line up in a column
function define(name, val) {
printf "%-48s%s\n", "#define " name, val
printf "%-56s%s\n", "#define " name, val
}
# Print standard BITMASK/SHIFT/WIDTH CPP definitions for a field

766
arch/arm64/tools/sysreg
View File

@ -46,6 +46,760 @@
# feature that introduces them (eg, FEAT_LS64_ACCDATA introduces enumeration
# item ACCDATA) though it may be more taseful to do something else.
Sysreg ID_PFR0_EL1 3 0 0 1 0
Res0 63:32
Enum 31:28 RAS
0b0000 NI
0b0001 RAS
0b0010 RASv1p1
EndEnum
Enum 27:24 DIT
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 AMU
0b0000 NI
0b0001 AMUv1
0b0010 AMUv1p1
EndEnum
Enum 19:16 CSV2
0b0000 UNDISCLOSED
0b0001 IMP
0b0010 CSV2p1
EndEnum
Enum 15:12 State3
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 State2
0b0000 NI
0b0001 NO_CV
0b0010 CV
EndEnum
Enum 7:4 State1
0b0000 NI
0b0001 THUMB
0b0010 THUMB2
EndEnum
Enum 3:0 State0
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_PFR1_EL1 3 0 0 1 1
Res0 63:32
Enum 31:28 GIC
0b0000 NI
0b0001 GICv3
0b0010 GICv4p1
EndEnum
Enum 27:24 Virt_frac
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 Sec_frac
0b0000 NI
0b0001 WALK_DISABLE
0b0010 SECURE_MEMORY
EndEnum
Enum 19:16 GenTimer
0b0000 NI
0b0001 IMP
0b0010 ECV
EndEnum
Enum 15:12 Virtualization
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 MProgMod
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 Security
0b0000 NI
0b0001 EL3
0b0001 NSACR_RFR
EndEnum
Enum 3:0 ProgMod
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_DFR0_EL1 3 0 0 1 2
Res0 63:32
Enum 31:28 TraceFilt
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 PerfMon
0b0000 NI
0b0001 PMUv1
0b0010 PMUv2
0b0011 PMUv3
0b0100 PMUv3p1
0b0101 PMUv3p4
0b0110 PMUv3p5
0b0111 PMUv3p7
0b1000 PMUv3p8
0b1111 IMPDEF
EndEnum
Enum 23:20 MProfDbg
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 MMapTrc
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 CopTrc
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 MMapDbg
0b0000 NI
0b0100 Armv7
0b0101 Armv7p1
EndEnum
Field 7:4 CopSDbg
Enum 3:0 CopDbg
0b0000 NI
0b0010 Armv6
0b0011 Armv6p1
0b0100 Armv7
0b0101 Armv7p1
0b0110 Armv8
0b0111 VHE
0b1000 Debugv8p2
0b1001 Debugv8p4
0b1010 Debugv8p8
EndEnum
EndSysreg
Sysreg ID_AFR0_EL1 3 0 0 1 3
Res0 63:16
Field 15:12 IMPDEF3
Field 11:8 IMPDEF2
Field 7:4 IMPDEF1
Field 3:0 IMPDEF0
EndSysreg
Sysreg ID_MMFR0_EL1 3 0 0 1 4
Res0 63:32
Enum 31:28 InnerShr
0b0000 NC
0b0001 HW
0b1111 IGNORED
EndEnum
Enum 27:24 FCSE
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 AuxReg
0b0000 NI
0b0001 ACTLR
0b0010 AIFSR
EndEnum
Enum 19:16 TCM
0b0000 NI
0b0001 IMPDEF
0b0010 TCM
0b0011 TCM_DMA
EndEnum
Enum 15:12 ShareLvl
0b0000 ONE
0b0001 TWO
EndEnum
Enum 11:8 OuterShr
0b0000 NC
0b0001 HW
0b1111 IGNORED
EndEnum
Enum 7:4 PMSA
0b0000 NI
0b0001 IMPDEF
0b0010 PMSAv6
0b0011 PMSAv7
EndEnum
Enum 3:0 VMSA
0b0000 NI
0b0001 IMPDEF
0b0010 VMSAv6
0b0011 VMSAv7
0b0100 VMSAv7_PXN
0b0101 VMSAv7_LONG
EndEnum
EndSysreg
Sysreg ID_MMFR1_EL1 3 0 0 1 5
Res0 63:32
Enum 31:28 BPred
0b0000 NI
0b0001 BP_SW_MANGED
0b0010 BP_ASID_AWARE
0b0011 BP_NOSNOOP
0b0100 BP_INVISIBLE
EndEnum
Enum 27:24 L1TstCln
0b0000 NI
0b0001 NOINVALIDATE
0b0010 INVALIDATE
EndEnum
Enum 23:20 L1Uni
0b0000 NI
0b0001 INVALIDATE
0b0010 CLEAN_AND_INVALIDATE
EndEnum
Enum 19:16 L1Hvd
0b0000 NI
0b0001 INVALIDATE_ISIDE_ONLY
0b0010 INVALIDATE
0b0011 CLEAN_AND_INVALIDATE
EndEnum
Enum 15:12 L1UniSW
0b0000 NI
0b0001 CLEAN
0b0010 CLEAN_AND_INVALIDATE
0b0011 INVALIDATE
EndEnum
Enum 11:8 L1HvdSW
0b0000 NI
0b0001 CLEAN_AND_INVALIDATE
0b0010 INVALIDATE_DSIDE_ONLY
0b0011 INVALIDATE
EndEnum
Enum 7:4 L1UniVA
0b0000 NI
0b0001 CLEAN_AND_INVALIDATE
0b0010 INVALIDATE_BP
EndEnum
Enum 3:0 L1HvdVA
0b0000 NI
0b0001 CLEAN_AND_INVALIDATE
0b0010 INVALIDATE_BP
EndEnum
EndSysreg
Sysreg ID_MMFR2_EL1 3 0 0 1 6
Res0 63:32
Enum 31:28 HWAccFlg
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 WFIStall
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 MemBarr
0b0000 NI
0b0001 DSB_ONLY
0b0010 IMP
EndEnum
Enum 19:16 UniTLB
0b0000 NI
0b0001 BY_VA
0b0010 BY_MATCH_ASID
0b0011 BY_ALL_ASID
0b0100 OTHER_TLBS
0b0101 BROADCAST
0b0110 BY_IPA
EndEnum
Enum 15:12 HvdTLB
0b0000 NI
EndEnum
Enum 11:8 L1HvdRng
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 L1HvdBG
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 L1HvdFG
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_MMFR3_EL1 3 0 0 1 7
Res0 63:32
Enum 31:28 Supersec
0b0000 IMP
0b1111 NI
EndEnum
Enum 27:24 CMemSz
0b0000 4GB
0b0001 64GB
0b0010 1TB
EndEnum
Enum 23:20 CohWalk
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 PAN
0b0000 NI
0b0001 PAN
0b0010 PAN2
EndEnum
Enum 15:12 MaintBcst
0b0000 NI
0b0001 NO_TLB
0b0010 ALL
EndEnum
Enum 11:8 BPMaint
0b0000 NI
0b0001 ALL
0b0010 BY_VA
EndEnum
Enum 7:4 CMaintSW
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 CMaintVA
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_ISAR0_EL1 3 0 0 2 0
Res0 63:28
Enum 27:24 Divide
0b0000 NI
0b0001 xDIV_T32
0b0010 xDIV_A32
EndEnum
Enum 23:20 Debug
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 Coproc
0b0000 NI
0b0001 MRC
0b0010 MRC2
0b0011 MRRC
0b0100 MRRC2
EndEnum
Enum 15:12 CmpBranch
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 BitField
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 BitCount
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 Swap
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_ISAR1_EL1 3 0 0 2 1
Res0 63:32
Enum 31:28 Jazelle
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 Interwork
0b0000 NI
0b0001 BX
0b0010 BLX
0b0011 A32_BX
EndEnum
Enum 23:20 Immediate
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 IfThen
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 Extend
0b0000 NI
0b0001 SXTB
0b0010 SXTB16
EndEnum
Enum 11:8 Except_AR
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 Except
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 Endian
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_ISAR2_EL1 3 0 0 2 2
Res0 63:32
Enum 31:28 Reversal
0b0000 NI
0b0001 REV
0b0010 RBIT
EndEnum
Enum 27:24 PSR_AR
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 MultU
0b0000 NI
0b0001 UMULL
0b0010 UMAAL
EndEnum
Enum 19:16 MultS
0b0000 NI
0b0001 SMULL
0b0010 SMLABB
0b0011 SMLAD
EndEnum
Enum 15:12 Mult
0b0000 NI
0b0001 MLA
0b0010 MLS
EndEnum
Enum 11:8 MultiAccessInt
0b0000 NI
0b0001 RESTARTABLE
0b0010 CONTINUABLE
EndEnum
Enum 7:4 MemHint
0b0000 NI
0b0001 PLD
0b0010 PLD2
0b0011 PLI
0b0100 PLDW
EndEnum
Enum 3:0 LoadStore
0b0000 NI
0b0001 DOUBLE
0b0010 ACQUIRE
EndEnum
EndSysreg
Sysreg ID_ISAR3_EL1 3 0 0 2 3
Res0 63:32
Enum 31:28 T32EE
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 TrueNOP
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 T32Copy
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 TabBranch
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 SynchPrim
0b0000 NI
0b0001 EXCLUSIVE
0b0010 DOUBLE
EndEnum
Enum 11:8 SVC
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 SIMD
0b0000 NI
0b0001 SSAT
0b0011 PKHBT
EndEnum
Enum 3:0 Saturate
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_ISAR4_EL1 3 0 0 2 4
Res0 63:32
Enum 31:28 SWP_frac
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 PSR_M
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 SynchPrim_frac
0b0000 NI
0b0011 IMP
EndEnum
Enum 19:16 Barrier
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 SMC
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 Writeback
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 WithShifts
0b0000 NI
0b0001 LSL3
0b0011 LS
0b0100 REG
EndEnum
Enum 3:0 Unpriv
0b0000 NI
0b0001 REG_BYTE
0b0010 SIGNED_HALFWORD
EndEnum
EndSysreg
Sysreg ID_ISAR5_EL1 3 0 0 2 5
Res0 63:32
Enum 31:28 VCMA
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 RDM
0b0000 NI
0b0001 IMP
EndEnum
Res0 23:20
Enum 19:16 CRC32
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 SHA2
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 SHA1
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 AES
0b0000 NI
0b0001 IMP
0b0010 VMULL
EndEnum
Enum 3:0 SEVL
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_ISAR6_EL1 3 0 0 2 7
Res0 63:28
Enum 27:24 I8MM
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 BF16
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 SPECRES
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 SB
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 FHM
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 DP
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 JSCVT
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_MMFR4_EL1 3 0 0 2 6
Res0 63:32
Enum 31:28 EVT
0b0000 NI
0b0001 NO_TLBIS
0b0010 TLBIS
EndEnum
Enum 27:24 CCIDX
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 LSM
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 HPDS
0b0000 NI
0b0001 AA32HPD
0b0010 HPDS2
EndEnum
Enum 15:12 CnP
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 XNX
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 AC2
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 SpecSEI
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg MVFR0_EL1 3 0 0 3 0
Res0 63:32
Enum 31:28 FPRound
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 FPShVec
0b0000 NI
0b0001 IMP
EndEnum
Enum 23:20 FPSqrt
0b0000 NI
0b0001 IMP
EndEnum
Enum 19:16 FPDivide
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 FPTrap
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 FPDP
0b0000 NI
0b0001 VFPv2
0b0001 VFPv3
EndEnum
Enum 7:4 FPSP
0b0000 NI
0b0001 VFPv2
0b0001 VFPv3
EndEnum
Enum 3:0 SIMDReg
0b0000 NI
0b0001 IMP_16x64
0b0001 IMP_32x64
EndEnum
EndSysreg
Sysreg MVFR1_EL1 3 0 0 3 1
Res0 63:32
Enum 31:28 SIMDFMAC
0b0000 NI
0b0001 IMP
EndEnum
Enum 27:24 FPHP
0b0000 NI
0b0001 FPHP
0b0010 FPHP_CONV
0b0011 FP16
EndEnum
Enum 23:20 SIMDHP
0b0000 NI
0b0001 SIMDHP
0b0001 SIMDHP_FLOAT
EndEnum
Enum 19:16 SIMDSP
0b0000 NI
0b0001 IMP
EndEnum
Enum 15:12 SIMDInt
0b0000 NI
0b0001 IMP
EndEnum
Enum 11:8 SIMDLS
0b0000 NI
0b0001 IMP
EndEnum
Enum 7:4 FPDNaN
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 FPFtZ
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg MVFR2_EL1 3 0 0 3 2
Res0 63:8
Enum 7:4 FPMisc
0b0000 NI
0b0001 FP
0b0010 FP_DIRECTED_ROUNDING
0b0011 FP_ROUNDING
0b0100 FP_MAX_MIN
EndEnum
Enum 3:0 SIMDMisc
0b0000 NI
0b0001 SIMD_DIRECTED_ROUNDING
0b0010 SIMD_ROUNDING
0b0011 SIMD_MAX_MIN
EndEnum
EndSysreg
Sysreg ID_PFR2_EL1 3 0 0 3 4
Res0 63:12
Enum 11:8 RAS_frac
0b0000 NI
0b0001 RASv1p1
EndEnum
Enum 7:4 SSBS
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 CSV3
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_DFR1_EL1 3 0 0 3 5
Res0 63:8
Enum 7:4 HPMN0
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 MTPMU
0b0000 IMPDEF
0b0001 IMP
0b1111 NI
EndEnum
EndSysreg
Sysreg ID_MMFR5_EL1 3 0 0 3 6
Res0 63:8
Enum 7:4 nTLBPA
0b0000 NI
0b0001 IMP
EndEnum
Enum 3:0 ETS
0b0000 NI
0b0001 IMP
EndEnum
EndSysreg
Sysreg ID_AA64PFR0_EL1 3 0 0 4 0
Enum 63:60 CSV3
0b0000 NI
@ -210,6 +964,7 @@ EndEnum
Enum 3:0 SVEver
0b0000 IMP
0b0001 SVE2
0b0010 SVE2p1
EndEnum
EndSysreg
@ -484,7 +1239,16 @@ EndEnum
EndSysreg
Sysreg ID_AA64ISAR2_EL1 3 0 0 6 2
Res0 63:28
Res0 63:56
Enum 55:52 CSSC
0b0000 NI
0b0001 IMP
EndEnum
Enum 51:48 RPRFM
0b0000 NI
0b0001 IMP
EndEnum
Res0 47:28
Enum 27:24 PAC_frac
0b0000 NI
0b0001 IMP

24
arch/powerpc/include/asm/ftrace.h
View File

@ -37,12 +37,32 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
return fregs->regs.msr ? &fregs->regs : NULL;
}
static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs,
unsigned long ip)
static __always_inline void
ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
unsigned long ip)
{
regs_set_return_ip(&fregs->regs, ip);
}
static __always_inline unsigned long
ftrace_regs_get_instruction_pointer(struct ftrace_regs *fregs)
{
return instruction_pointer(&fregs->regs);
}
#define ftrace_regs_get_argument(fregs, n) \
regs_get_kernel_argument(&(fregs)->regs, n)
#define ftrace_regs_get_stack_pointer(fregs) \
kernel_stack_pointer(&(fregs)->regs)
#define ftrace_regs_return_value(fregs) \
regs_return_value(&(fregs)->regs)
#define ftrace_regs_set_return_value(fregs, ret) \
regs_set_return_value(&(fregs)->regs, ret)
#define ftrace_override_function_with_return(fregs) \
override_function_with_return(&(fregs)->regs)
#define ftrace_regs_query_register_offset(name) \
regs_query_register_offset(name)
struct ftrace_ops;
#define ftrace_graph_func ftrace_graph_func

29
arch/s390/include/asm/ftrace.h
View File

@ -54,12 +54,33 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
return NULL;
}
static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs,
unsigned long ip)
static __always_inline unsigned long
ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs)
{
return fregs->regs.psw.addr;
}
static __always_inline void
ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
unsigned long ip)
{
fregs->regs.psw.addr = ip;
}
#define ftrace_regs_get_argument(fregs, n) \
regs_get_kernel_argument(&(fregs)->regs, n)
#define ftrace_regs_get_stack_pointer(fregs) \
kernel_stack_pointer(&(fregs)->regs)
#define ftrace_regs_return_value(fregs) \
regs_return_value(&(fregs)->regs)
#define ftrace_regs_set_return_value(fregs, ret) \
regs_set_return_value(&(fregs)->regs, ret)
#define ftrace_override_function_with_return(fregs) \
override_function_with_return(&(fregs)->regs)
#define ftrace_regs_query_register_offset(name) \
regs_query_register_offset(name)
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
/*
* When an ftrace registered caller is tracing a function that is
* also set by a register_ftrace_direct() call, it needs to be
@ -67,10 +88,12 @@ static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *f
* place the direct caller in the ORIG_GPR2 part of pt_regs. This
* tells the ftrace_caller that there's a direct caller.
*/
static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
{
struct pt_regs *regs = &fregs->regs;
regs->orig_gpr2 = addr;
}
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
/*
* Even though the system call numbers are identical for s390/s390x a

49
arch/x86/include/asm/ftrace.h
View File

@ -34,19 +34,6 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
return addr;
}
/*
* When a ftrace registered caller is tracing a function that is
* also set by a register_ftrace_direct() call, it needs to be
* differentiated in the ftrace_caller trampoline. To do this, we
* place the direct caller in the ORIG_AX part of pt_regs. This
* tells the ftrace_caller that there's a direct caller.
*/
static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
{
/* Emulate a call */
regs->orig_ax = addr;
}
#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
struct ftrace_regs {
struct pt_regs regs;
@ -61,9 +48,25 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
return &fregs->regs;
}
#define ftrace_instruction_pointer_set(fregs, _ip) \
#define ftrace_regs_set_instruction_pointer(fregs, _ip) \
do { (fregs)->regs.ip = (_ip); } while (0)
#define ftrace_regs_get_instruction_pointer(fregs) \
((fregs)->regs.ip)
#define ftrace_regs_get_argument(fregs, n) \
regs_get_kernel_argument(&(fregs)->regs, n)
#define ftrace_regs_get_stack_pointer(fregs) \
kernel_stack_pointer(&(fregs)->regs)
#define ftrace_regs_return_value(fregs) \
regs_return_value(&(fregs)->regs)
#define ftrace_regs_set_return_value(fregs, ret) \
regs_set_return_value(&(fregs)->regs, ret)
#define ftrace_override_function_with_return(fregs) \
override_function_with_return(&(fregs)->regs)
#define ftrace_regs_query_register_offset(name) \
regs_query_register_offset(name)
struct ftrace_ops;
#define ftrace_graph_func ftrace_graph_func
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
@ -72,6 +75,24 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR
#endif
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
/*
* When a ftrace registered caller is tracing a function that is
* also set by a register_ftrace_direct() call, it needs to be
* differentiated in the ftrace_caller trampoline. To do this, we
* place the direct caller in the ORIG_AX part of pt_regs. This
* tells the ftrace_caller that there's a direct caller.
*/
static inline void
__arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
{
/* Emulate a call */
regs->orig_ax = addr;
}
#define arch_ftrace_set_direct_caller(fregs, addr) \
__arch_ftrace_set_direct_caller(&(fregs)->regs, addr)
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
#ifdef CONFIG_DYNAMIC_FTRACE
struct dyn_arch_ftrace {

2
drivers/acpi/Kconfig
View File

@ -90,7 +90,7 @@ config ACPI_SPCR_TABLE
config ACPI_FPDT
bool "ACPI Firmware Performance Data Table (FPDT) support"
depends on X86_64
depends on X86_64 || ARM64
help
Enable support for the Firmware Performance Data Table (FPDT).
This table provides information on the timing of the system

3
drivers/acpi/arm64/Kconfig
View File

@ -18,3 +18,6 @@ config ACPI_AGDI
reset command.
If set, the kernel parses AGDI table and listens for the command.
config ACPI_APMT
bool

1
drivers/acpi/arm64/Makefile
View File

@ -2,4 +2,5 @@
obj-$(CONFIG_ACPI_AGDI) += agdi.o
obj-$(CONFIG_ACPI_IORT) += iort.o
obj-$(CONFIG_ACPI_GTDT) += gtdt.o
obj-$(CONFIG_ACPI_APMT) += apmt.o
obj-y += dma.o

178
drivers/acpi/arm64/apmt.c Normal file
View File

@ -0,0 +1,178 @@
// SPDX-License-Identifier: GPL-2.0
/*
* ARM APMT table support.
* Design document number: ARM DEN0117.
*
* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES.
*
*/
#define pr_fmt(fmt) "ACPI: APMT: " fmt
#include <linux/acpi.h>
#include <linux/acpi_apmt.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/platform_device.h>
#define DEV_NAME "arm-cs-arch-pmu"
/* There can be up to 3 resources: page 0 and 1 address, and interrupt. */
#define DEV_MAX_RESOURCE_COUNT 3
/* Root pointer to the mapped APMT table */
static struct acpi_table_header *apmt_table;
static int __init apmt_init_resources(struct resource *res,
struct acpi_apmt_node *node)
{
int irq, trigger;
int num_res = 0;
res[num_res].start = node->base_address0;
res[num_res].end = node->base_address0 + SZ_4K - 1;
res[num_res].flags = IORESOURCE_MEM;
num_res++;
res[num_res].start = node->base_address1;
res[num_res].end = node->base_address1 + SZ_4K - 1;
res[num_res].flags = IORESOURCE_MEM;
num_res++;
if (node->ovflw_irq != 0) {
trigger = (node->ovflw_irq_flags & ACPI_APMT_OVFLW_IRQ_FLAGS_MODE);
trigger = (trigger == ACPI_APMT_OVFLW_IRQ_FLAGS_MODE_LEVEL) ?
ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
irq = acpi_register_gsi(NULL, node->ovflw_irq, trigger,
ACPI_ACTIVE_HIGH);
if (irq <= 0) {
pr_warn("APMT could not register gsi hwirq %d\n", irq);
return num_res;
}
res[num_res].start = irq;
res[num_res].end = irq;
res[num_res].flags = IORESOURCE_IRQ;
num_res++;
}
return num_res;
}
/**
* apmt_add_platform_device() - Allocate a platform device for APMT node
* @node: Pointer to device ACPI APMT node
* @fwnode: fwnode associated with the APMT node
*
* Returns: 0 on success, <0 failure
*/
static int __init apmt_add_platform_device(struct acpi_apmt_node *node,
struct fwnode_handle *fwnode)
{
struct platform_device *pdev;
int ret, count;
struct resource res[DEV_MAX_RESOURCE_COUNT];
pdev = platform_device_alloc(DEV_NAME, PLATFORM_DEVID_AUTO);
if (!pdev)
return -ENOMEM;
memset(res, 0, sizeof(res));
count = apmt_init_resources(res, node);
ret = platform_device_add_resources(pdev, res, count);
if (ret)
goto dev_put;
/*
* Add a copy of APMT node pointer to platform_data to be used to
* retrieve APMT data information.
*/
ret = platform_device_add_data(pdev, &node, sizeof(node));
if (ret)
goto dev_put;
pdev->dev.fwnode = fwnode;
ret = platform_device_add(pdev);
if (ret)
goto dev_put;
return 0;
dev_put:
platform_device_put(pdev);
return ret;
}
static int __init apmt_init_platform_devices(void)
{
struct acpi_apmt_node *apmt_node;
struct acpi_table_apmt *apmt;
struct fwnode_handle *fwnode;
u64 offset, end;
int ret;
/*
* apmt_table and apmt both point to the start of APMT table, but
* have different struct types
*/
apmt = (struct acpi_table_apmt *)apmt_table;
offset = sizeof(*apmt);
end = apmt->header.length;
while (offset < end) {
apmt_node = ACPI_ADD_PTR(struct acpi_apmt_node, apmt,
offset);
fwnode = acpi_alloc_fwnode_static();
if (!fwnode)
return -ENOMEM;
ret = apmt_add_platform_device(apmt_node, fwnode);
if (ret) {
acpi_free_fwnode_static(fwnode);
return ret;
}
offset += apmt_node->length;
}
return 0;
}
void __init acpi_apmt_init(void)
{
acpi_status status;
int ret;
/**
* APMT table nodes will be used at runtime after the apmt init,
* so we don't need to call acpi_put_table() to release
* the APMT table mapping.
*/
status = acpi_get_table(ACPI_SIG_APMT, 0, &apmt_table);
if (ACPI_FAILURE(status)) {
if (status != AE_NOT_FOUND) {
const char *msg = acpi_format_exception(status);
pr_err("Failed to get APMT table, %s\n", msg);
}
return;
}
ret = apmt_init_platform_devices();
if (ret) {
pr_err("Failed to initialize APMT platform devices, ret: %d\n", ret);
acpi_put_table(apmt_table);
}
}

16
drivers/acpi/arm64/iort.c
View File

@ -402,6 +402,10 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
return NULL;
}
#ifndef ACPI_IORT_SMMU_V3_DEVICEID_VALID
#define ACPI_IORT_SMMU_V3_DEVICEID_VALID (1 << 4)
#endif
static int iort_get_id_mapping_index(struct acpi_iort_node *node)
{
struct acpi_iort_smmu_v3 *smmu;
@ -418,12 +422,16 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
/*
* ID mapping index is only ignored if all interrupts are
* GSIV based
* Until IORT E.e (node rev. 5), the ID mapping index was
* defined to be valid unless all interrupts are GSIV-based.
*/
if (smmu->event_gsiv && smmu->pri_gsiv && smmu->gerr_gsiv
&& smmu->sync_gsiv)
if (node->revision < 5) {
if (smmu->event_gsiv && smmu->pri_gsiv &&
smmu->gerr_gsiv && smmu->sync_gsiv)
return -EINVAL;
} else if (!(smmu->flags & ACPI_IORT_SMMU_V3_DEVICEID_VALID)) {
return -EINVAL;
}
if (smmu->id_mapping_index >= node->mapping_count) {
pr_err(FW_BUG "[node %p type %d] ID mapping index overflows valid mappings\n",

2
drivers/acpi/bus.c
View File

@ -27,6 +27,7 @@
#include <linux/dmi.h>
#endif
#include <linux/acpi_agdi.h>
#include <linux/acpi_apmt.h>
#include <linux/acpi_iort.h>
#include <linux/acpi_viot.h>
#include <linux/pci.h>
@ -1423,6 +1424,7 @@ static int __init acpi_init(void)
acpi_setup_sb_notify_handler();
acpi_viot_init();
acpi_agdi_init();
acpi_apmt_init();
return 0;
}

101
drivers/firmware/arm_ffa/driver.c
View File

@ -36,81 +36,6 @@
#include "common.h"
#define FFA_DRIVER_VERSION FFA_VERSION_1_0
#define FFA_SMC(calling_convention, func_num) \
ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, (calling_convention), \
ARM_SMCCC_OWNER_STANDARD, (func_num))
#define FFA_SMC_32(func_num) FFA_SMC(ARM_SMCCC_SMC_32, (func_num))
#define FFA_SMC_64(func_num) FFA_SMC(ARM_SMCCC_SMC_64, (func_num))
#define FFA_ERROR FFA_SMC_32(0x60)
#define FFA_SUCCESS FFA_SMC_32(0x61)
#define FFA_INTERRUPT FFA_SMC_32(0x62)
#define FFA_VERSION FFA_SMC_32(0x63)
#define FFA_FEATURES FFA_SMC_32(0x64)
#define FFA_RX_RELEASE FFA_SMC_32(0x65)
#define FFA_RXTX_MAP FFA_SMC_32(0x66)
#define FFA_FN64_RXTX_MAP FFA_SMC_64(0x66)
#define FFA_RXTX_UNMAP FFA_SMC_32(0x67)
#define FFA_PARTITION_INFO_GET FFA_SMC_32(0x68)
#define FFA_ID_GET FFA_SMC_32(0x69)
#define FFA_MSG_POLL FFA_SMC_32(0x6A)
#define FFA_MSG_WAIT FFA_SMC_32(0x6B)
#define FFA_YIELD FFA_SMC_32(0x6C)
#define FFA_RUN FFA_SMC_32(0x6D)
#define FFA_MSG_SEND FFA_SMC_32(0x6E)
#define FFA_MSG_SEND_DIRECT_REQ FFA_SMC_32(0x6F)
#define FFA_FN64_MSG_SEND_DIRECT_REQ FFA_SMC_64(0x6F)
#define FFA_MSG_SEND_DIRECT_RESP FFA_SMC_32(0x70)
#define FFA_FN64_MSG_SEND_DIRECT_RESP FFA_SMC_64(0x70)
#define FFA_MEM_DONATE FFA_SMC_32(0x71)
#define FFA_FN64_MEM_DONATE FFA_SMC_64(0x71)
#define FFA_MEM_LEND FFA_SMC_32(0x72)
#define FFA_FN64_MEM_LEND FFA_SMC_64(0x72)
#define FFA_MEM_SHARE FFA_SMC_32(0x73)
#define FFA_FN64_MEM_SHARE FFA_SMC_64(0x73)
#define FFA_MEM_RETRIEVE_REQ FFA_SMC_32(0x74)
#define FFA_FN64_MEM_RETRIEVE_REQ FFA_SMC_64(0x74)
#define FFA_MEM_RETRIEVE_RESP FFA_SMC_32(0x75)
#define FFA_MEM_RELINQUISH FFA_SMC_32(0x76)
#define FFA_MEM_RECLAIM FFA_SMC_32(0x77)
#define FFA_MEM_OP_PAUSE FFA_SMC_32(0x78)
#define FFA_MEM_OP_RESUME FFA_SMC_32(0x79)
#define FFA_MEM_FRAG_RX FFA_SMC_32(0x7A)
#define FFA_MEM_FRAG_TX FFA_SMC_32(0x7B)
#define FFA_NORMAL_WORLD_RESUME FFA_SMC_32(0x7C)
/*
* For some calls it is necessary to use SMC64 to pass or return 64-bit values.
* For such calls FFA_FN_NATIVE(name) will choose the appropriate
* (native-width) function ID.
*/
#ifdef CONFIG_64BIT
#define FFA_FN_NATIVE(name) FFA_FN64_##name
#else
#define FFA_FN_NATIVE(name) FFA_##name
#endif
/* FFA error codes. */
#define FFA_RET_SUCCESS (0)
#define FFA_RET_NOT_SUPPORTED (-1)
#define FFA_RET_INVALID_PARAMETERS (-2)
#define FFA_RET_NO_MEMORY (-3)
#define FFA_RET_BUSY (-4)
#define FFA_RET_INTERRUPTED (-5)
#define FFA_RET_DENIED (-6)
#define FFA_RET_RETRY (-7)
#define FFA_RET_ABORTED (-8)
#define MAJOR_VERSION_MASK GENMASK(30, 16)
#define MINOR_VERSION_MASK GENMASK(15, 0)
#define MAJOR_VERSION(x) ((u16)(FIELD_GET(MAJOR_VERSION_MASK, (x))))
#define MINOR_VERSION(x) ((u16)(FIELD_GET(MINOR_VERSION_MASK, (x))))
#define PACK_VERSION_INFO(major, minor) \
(FIELD_PREP(MAJOR_VERSION_MASK, (major)) | \
FIELD_PREP(MINOR_VERSION_MASK, (minor)))
#define FFA_VERSION_1_0 PACK_VERSION_INFO(1, 0)
#define FFA_MIN_VERSION FFA_VERSION_1_0
#define SENDER_ID_MASK GENMASK(31, 16)
@ -120,12 +45,6 @@
#define PACK_TARGET_INFO(s, r) \
(FIELD_PREP(SENDER_ID_MASK, (s)) | FIELD_PREP(RECEIVER_ID_MASK, (r)))
/*
* FF-A specification mentions explicitly about '4K pages'. This should
* not be confused with the kernel PAGE_SIZE, which is the translation
* granule kernel is configured and may be one among 4K, 16K and 64K.
*/
#define FFA_PAGE_SIZE SZ_4K
/*
* Keeping RX TX buffer size as 4K for now
* 64K may be preferred to keep it min a page in 64K PAGE_SIZE config
@ -178,9 +97,9 @@ static struct ffa_drv_info *drv_info;
*/
static u32 ffa_compatible_version_find(u32 version)
{
u16 major = MAJOR_VERSION(version), minor = MINOR_VERSION(version);
u16 drv_major = MAJOR_VERSION(FFA_DRIVER_VERSION);
u16 drv_minor = MINOR_VERSION(FFA_DRIVER_VERSION);
u16 major = FFA_MAJOR_VERSION(version), minor = FFA_MINOR_VERSION(version);
u16 drv_major = FFA_MAJOR_VERSION(FFA_DRIVER_VERSION);
u16 drv_minor = FFA_MINOR_VERSION(FFA_DRIVER_VERSION);
if ((major < drv_major) || (major == drv_major && minor <= drv_minor))
return version;
@ -204,16 +123,16 @@ static int ffa_version_check(u32 *version)
if (ver.a0 < FFA_MIN_VERSION) {
pr_err("Incompatible v%d.%d! Earliest supported v%d.%d\n",
MAJOR_VERSION(ver.a0), MINOR_VERSION(ver.a0),
MAJOR_VERSION(FFA_MIN_VERSION),
MINOR_VERSION(FFA_MIN_VERSION));
FFA_MAJOR_VERSION(ver.a0), FFA_MINOR_VERSION(ver.a0),
FFA_MAJOR_VERSION(FFA_MIN_VERSION),
FFA_MINOR_VERSION(FFA_MIN_VERSION));
return -EINVAL;
}
pr_info("Driver version %d.%d\n", MAJOR_VERSION(FFA_DRIVER_VERSION),
MINOR_VERSION(FFA_DRIVER_VERSION));
pr_info("Firmware version %d.%d found\n", MAJOR_VERSION(ver.a0),
MINOR_VERSION(ver.a0));
pr_info("Driver version %d.%d\n", FFA_MAJOR_VERSION(FFA_DRIVER_VERSION),
FFA_MINOR_VERSION(FFA_DRIVER_VERSION));
pr_info("Firmware version %d.%d found\n", FFA_MAJOR_VERSION(ver.a0),
FFA_MINOR_VERSION(ver.a0));
*version = ffa_compatible_version_find(ver.a0);
return 0;

1
drivers/firmware/efi/libstub/Makefile
View File

@ -20,6 +20,7 @@ cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \
# disable the stackleak plugin
cflags-$(CONFIG_ARM64) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
-fpie $(DISABLE_STACKLEAK_PLUGIN) \
-fno-unwind-tables -fno-asynchronous-unwind-tables \
$(call cc-option,-mbranch-protection=none)
cflags-$(CONFIG_ARM) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
-fno-builtin -fpic \

4
drivers/perf/Kconfig
View File

@ -199,4 +199,8 @@ config MARVELL_CN10K_DDR_PMU
Enable perf support for Marvell DDR Performance monitoring
event on CN10K platform.
source "drivers/perf/arm_cspmu/Kconfig"
source "drivers/perf/amlogic/Kconfig"
endmenu

Some files were not shown because too many files have changed in this diff Show More