Commit Graph

37 Commits

Author SHA1 Message Date
Dave Airlie
fb51bf0255 Merge tag 'v6.14-rc4' into drm-next
Backmerge Linux 6.14-rc4 at the request of tzimmermann so misc-next
can base on rc4.

Signed-off-by: Dave Airlie <airlied@redhat.com>
2025-02-25 17:36:09 +10:00
Su Hui
838c17fd07 accel/amdxdna: Add missing include linux/slab.h
When compiling without CONFIG_IA32_EMULATION, there can be some errors:

drivers/accel/amdxdna/amdxdna_mailbox.c: In function ‘mailbox_release_msg’:
drivers/accel/amdxdna/amdxdna_mailbox.c:197:2: error: implicit declaration
of function ‘kfree’.
  197 |  kfree(mb_msg);
      |  ^~~~~
drivers/accel/amdxdna/amdxdna_mailbox.c: In function ‘xdna_mailbox_send_msg’:
drivers/accel/amdxdna/amdxdna_mailbox.c:418:11: error:implicit declaration
of function ‘kzalloc’.
  418 |  mb_msg = kzalloc(sizeof(*mb_msg) + pkg_size, GFP_KERNEL);
      |           ^~~~~~~

Add the missing include.

Fixes: b87f920b93 ("accel/amdxdna: Support hardware mailbox")
Signed-off-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250211015354.3388171-1-suhui@nfschina.com
2025-02-19 09:42:17 -08:00
Thomas Zimmermann
8bd1a8e757 Merge drm/drm-next into drm-misc-next
Backmerging to get bugfixes from v6.14-rc2.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
2025-02-18 07:43:43 +01:00
Lizhi Hou
4fd6ca90fc accel/amdxdna: Refactor hardware context destroy routine
It is required by firmware to wait up to 2 seconds for pending commands
before sending the destroy hardware context command. After 2 seconds
wait, if there are still pending commands, driver needs to cancel them.

So the context destroy steps need to be:
  1. Stop drm scheduler. (drm_sched_entity_destroy)
  2. Wait up to 2 seconds for pending commands.
  3. Destroy hardware context and cancel the rest pending requests.
  4. Wait all jobs associated with the hwctx are freed.
  5. Free job resources.

Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250124173536.148676-1-lizhi.hou@amd.com
2025-02-14 08:36:07 -07:00
Dave Airlie
0ed1356af8 Merge tag 'drm-misc-next-2025-02-12' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-next
drm-misc-next for v6.15:

UAPI Changes:

fourcc:
- Add modifiers for MediaTek tiled formats

Cross-subsystem Changes:

bus:
- mhi: Enable image transfer via BHIe in PBL

dma-buf:
- Add fast-path for single-fence merging

Core Changes:

atomic helper:
- Allow full modeset on connector changes
- Clarify semantics of allow_modeset
- Clarify semantics of drm_atomic_helper_check()

buddy allocator:
- Fix multi-root cleanup

ci:
- Update IGT

display:
- dp: Support Extendeds Wake Timeout
- dp_mst: Fix RAD-to-string conversion

panic:
- Encode QR code according to Fido 2.2

probe helper:
- Cleanups

scheduler:
- Cleanups

ttm:
- Refactor pool-allocation code
- Cleanups

Driver Changes:

amdxdma:
- Fix error handling
- Cleanups

ast:
- Refactor detection of transmitter chips
- Refactor support of VBIOS display-mode handling
- astdp: Fix connection status; Filter unsupported display modes

bridge:
- adv7511: Report correct capabilities
- it6505: Fix HDCP V compare
- sn65dsi86: Fix device IDs
- Cleanups

i915:
- Enable Extendeds Wake Timeout

imagination:
- Check job dependencies with DRM-sched helper

ivpu:
- Improve command-queue handling
- Use workqueue for IRQ handling
- Add suport for HW fault injection
- Locking fixes
- Cleanups

mgag200:
- Add support for G200eH5 chips

msm:
- dpu: Add concurrent writeback support for DPU 10.x+

nouveau:
- Move drm_slave_encoder interface into driver
- nvkm: Refactor GSP RPC

omapdrm:
- Cleanups

panel:
- Convert several panels to multi-style functions to improve error
  handling
- edp: Add support for B140UAN04.4, BOE NV140FHM-NZ, CSW MNB601LS1-3,
  LG LP079QX1-SP0V, MNE007QS3-7, STA 116QHD024002, Starry 116KHD024006,
  Lenovo T14s Gen6 Snapdragon
- himax-hx83102: Add support for CSOT PNA957QT1-1, Kingdisplay
  kd110n11-51ie, Starry 2082109qfh040022-50e

panthor:
- Expose sizes of intenral BOs via fdinfo
- Fix race between reset and suspend
- Cleanups

qaic:
- Add support for AIC200
- Cleanups

renesas:
- Fix limits in DT bindings

rockchip:
- rk3576: Add HDMI support
- vop2: Add new display modes on RK3588 HDMI0 up to 4K
- Don't change HDMI reference clock rate
- Fix DT bindings

solomon:
- Set SPI device table to silence warnings
- Fix pixel and scanline encoding

v3d:
- Cleanups

vc4:
- Use drm_exec
- Use dma-resv for wait-BO ioctl
- Remove seqno infrastructure

virtgpu:
- Support partial mappings of GEM objects
- Reserve VGA resources during initialization
- Fix UAF in virtgpu_dma_buf_free_obj()
- Add panic support

vkms:
- Switch to a managed modesetting pipeline
- Add support for ARGB8888

xlnx:
- Set correct DMA segment size
- Fix error handling
- Fix docs

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20250212090625.GA24865@linux.fritz.box
2025-02-14 10:24:02 +10:00
Philipp Stanner
796a9f55a8 drm/sched: Use struct for drm_sched_init() params
drm_sched_init() has a great many parameters and upcoming new
functionality for the scheduler might add even more. Generally, the
great number of parameters reduces readability and has already caused
one missnaming, addressed in:

commit 6f1cacf4eb ("drm/nouveau: Improve variable name in
nouveau_sched_init()").

Introduce a new struct for the scheduler init parameters and port all
users.

Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Acked-by: Matthew Brost <matthew.brost@intel.com> # for Xe
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com> # for Panfrost and Panthor
Reviewed-by: Christian Gmeiner <cgmeiner@igalia.com> # for Etnaviv
Reviewed-by: Frank Binns <frank.binns@imgtec.com> # for Imagination
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com> # for Sched
Reviewed-by: Maíra Canal <mcanal@igalia.com> # for v3d
Reviewed-by: Danilo Krummrich <dakr@kernel.org>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com> # for amdxdna
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250211111422.21235-2-phasta@kernel.org
2025-02-12 11:59:52 +01:00
Mario Limonciello
ecee4d0695 accel/amdxdna: Add MODULE_FIRMWARE() declarations
Initramfs building tools such as dracut will look for a MODULE_FIRMWARE()
declaration to determine which firmware to include in the initramfs
when a driver is included in the initramfs.

As amdxdna doesn't declare any firmware this causes the driver to fail
to load with -ENOENT when in the initramfs.  Add the missing declaration
for possible firmware.

Reported-by: Renjith Pananchikkal <Renjith.Pananchikkal@amd.com>
Suggested-by: Alexander Deucher <Alexander.Deucher@amd.com>
Fixes: 8c9ff1b181 ("accel/amdxdna: Add a new driver for AMD AI Engine")
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://lore.kernel.org/r/20250204174031.3425762-1-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250204174031.3425762-1-superm1@kernel.org
2025-02-04 13:05:48 -06:00
Lizhi Hou
b3dff598e7 accel/amdxdna: Declare sched_ops as static
Fix sparse warning:
  symbol 'sched_ops' was not declared. Should it be static?

Fixes: aac243092b ("accel/amdxdna: Add command execution")
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250113182617.1256094-2-lizhi.hou@amd.com
2025-01-13 14:21:53 -06:00
Lizhi Hou
412576293c accel/amdxdna: Remove casting mailbox payload pointer
The mailbox payload pointer is void __iomem *. Casting it to u32 * is
incorrect and causes sparse warning.
  cast removes address space '__iomem' of expression

Fixes: b87f920b93 ("accel/amdxdna: Support hardware mailbox")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501130921.ktqwsMLH-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250113182617.1256094-1-lizhi.hou@amd.com
2025-01-13 14:21:39 -06:00
Lizhi Hou
0c2768bf81 accel/amdxdna: Return error when setting clock failed for npu1
Due to miss returning error when setting clock, the smatch static
checker reports warning:
  drivers/accel/amdxdna/aie2_smu.c:68 npu1_set_dpm()
  error: uninitialized symbol 'freq'.

Fixes: f4d7b8a6bc ("accel/amdxdna: Enhance power management settings")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/dri-devel/202267d0-882e-4593-b58d-be9274592f9b@stanley.mountain/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250109194811.499505-1-lizhi.hou@amd.com
2025-01-09 13:53:22 -06:00
Lizhi Hou
fee7aaee11 accel/amdxdna: Declare npu6_dev_priv as static
Fix sparse warning:
  symbol 'npu6_dev_priv' was not declared. Should it be static?

Fixes: 273b5176ac ("accel/amdxdna: Add RyzenAI-npu6 support")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412311819.9mz11Uak-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250102212244.1586340-7-lizhi.hou@amd.com
2025-01-03 23:38:22 -06:00
Lizhi Hou
3b5bcf64a6 accel/amdxdna: Add __user to second parameter of aie2_query_status
The second parameter of aie2_query_status() is a userspace pointer.
Declaring it as 'char __user *' to fix sparse warning.

Fixes: 850d71f6bf ("accel/amdxdna: Add query functions")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412311655.YBvq2wJb-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250102212244.1586340-6-lizhi.hou@amd.com
2025-01-03 23:38:19 -06:00
Lizhi Hou
72e487b47d accel/amdxdna: Declare force_cmdlist as static
Fix sparse warning:
  symbol 'force_cmdlist' was not declared. Should it be static?

Fixes: aac243092b ("accel/amdxdna: Add command execution")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412311448.GKQj7uPZ-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250102212244.1586340-5-lizhi.hou@amd.com
2025-01-03 23:38:16 -06:00
Lizhi Hou
1f74400529 accel/amdxdna: Use rcu_access_pointer for __rcu pointer
Use rcu_access_pointer for pid in struct drm_file. This fixes sparse
warning.

Fixes: be462c97b7 ("accel/amdxdna: Add hardware context")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412311210.LfeHTzLw-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250102212244.1586340-4-lizhi.hou@amd.com
2025-01-03 23:38:13 -06:00
Lizhi Hou
c199310be2 accel/amdxdna: Declare aie2_max_col as static
Fix the sparse warning:
  symbol 'aie2_max_col' was not declared. Should it be static?

Fixes: c88d3325ae ("accel/amdxdna: Add hardware resource solver")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412311028.x2UtcSHm-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250102212244.1586340-3-lizhi.hou@amd.com
2025-01-03 23:38:10 -06:00
Lizhi Hou
3c8cfec3fc accel/amdxdna: Declare mailbox register base as __iomem pointer
Declare mailbox ringbuf_base and mbox_base as 'void __iomem *' to fix
sparse warnings:
  cast removes address space '__iomem' of expression
  incorrect type in argument 2 (different address spaces)

Fixes: b87f920b93 ("accel/amdxdna: Support hardware mailbox")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412310857.syD1sXXO-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250102212244.1586340-2-lizhi.hou@amd.com
2025-01-03 23:38:07 -06:00
Lizhi Hou
71486e4837 accel/amdxdna: Declare npu device profile as static variables
Declare the variables as static to fix the sparse warnings:
symbol 'npu5_dev_priv' was not declared. Should it be static?
symbol 'npu1_dev_priv' was not declared. Should it be static?
symbol 'npu4_dev_priv' was not declared. Should it be static?
symbol 'npu2_dev_priv' was not declared. Should it be static?

Fixes: 8c9ff1b181 ("accel/amdxdna: Add a new driver for AMD AI Engine")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412310648.dtMHgGem-lkp@intel.com/
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250102212244.1586340-1-lizhi.hou@amd.com
2025-01-03 23:37:52 -06:00
Arnd Bergmann
221e29e197 accel/amdxdna: include linux/slab.h
This driver fails to build in random configurations:

drivers/accel/amdxdna/aie2_solver.c: In function 'remove_partition_node':
drivers/accel/amdxdna/aie2_solver.c:121:9: error: implicit declaration of function 'kfree' [-Wimplicit-function-declaration]
  121 |         kfree(pt_node);
      |         ^~~~~
drivers/accel/amdxdna/aie2_solver.c: In function 'get_free_partition':
drivers/accel/amdxdna/aie2_solver.c:153:19: error: implicit declaration of function 'kzalloc' [-Wimplicit-function-declaration]
  153 |         pt_node = kzalloc(sizeof(*pt_node), GFP_KERNEL);

Add the missing include.

Fixes: c88d3325ae ("accel/amdxdna: Add hardware resource solver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241218085902.2684002-1-arnd@kernel.org
2024-12-18 08:14:12 -06:00
Lizhi Hou
03c318a0af accel/amdxdna: Add zero check for pad in ioctl input structures
For input ioctl structures, it is better to check if the pad is zero.
Thus, the pad bytes might be usable in the future.

Suggested-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241217165446.2607585-1-lizhi.hou@amd.com
2024-12-17 12:10:05 -06:00
Lizhi Hou
b1dcfe6205 accel/amdxdna: Read firmware interface version from registers
The latest released firmware supports reading firmware interface version
from registers directly. The driver's probe routine reads the major and
minor version numbers. If the firmware interface is not compatible with
the driver, the driver's probe routine returns failure.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241213232933.1545388-5-lizhi.hou@amd.com
2024-12-16 15:50:32 -06:00
Lizhi Hou
f4d7b8a6bc accel/amdxdna: Enhance power management settings
Add SET_STATE ioctl to configure device power mode for aie2 device.
Three modes are supported initially.

POWER_MODE_DEFAULT: Enable clock gating and set DPM (Dynamic Power
Management) level to value which has been set by resource solver or
maximum DPM level the device supports.

POWER_MODE_HIGH: Enable clock gating and set DPM level to maximum DPM
level the device supports.

POWER_MODE_TURBO: Disable clock gating and set DPM level to maximum DPM
level the device supports.

Disabling clock gating means all clocks always run on full speed. And
the different clock frequency are used based on DPM level been set.
Initially, the driver set the power mode to default mode.

Co-developed-by: Narendra Gutta <VenkataNarendraKumar.Gutta@amd.com>
Signed-off-by: Narendra Gutta <VenkataNarendraKumar.Gutta@amd.com>
Co-developed-by: George Yang <George.Yang@amd.com>
Signed-off-by: George Yang <George.Yang@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241213232933.1545388-4-lizhi.hou@amd.com
2024-12-16 15:50:32 -06:00
Lizhi Hou
a37d78470b accel/amdxdna: Replace idr api with xarray
Switch mailbox message id and hardware context id management over from
the idr api to the xarray api.

Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241213232933.1545388-3-lizhi.hou@amd.com
2024-12-16 15:50:22 -06:00
Lizhi Hou
273b5176ac accel/amdxdna: Add RyzenAI-npu6 support
Add NPU6 registers and other private configurations.

Co-developed-by: Xiaoming Ren <xiaoming.ren@amd.com>
Signed-off-by: Xiaoming Ren <xiaoming.ren@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241213232933.1545388-2-lizhi.hou@amd.com
2024-12-16 15:49:47 -06:00
Arnd Bergmann
e5a8f19c39 accel/amdxdna: use modern PM helpers
The old SET_SYSTEM_SLEEP_PM_OPS and SET_RUNTIME_PM_OPS macros cause a build
warning when CONFIG_PM is disabled:

drivers/accel/amdxdna/amdxdna_pci_drv.c:343:12: error: 'amdxdna_pmops_resume' defined but not used [-Werror=unused-function]
  343 | static int amdxdna_pmops_resume(struct device *dev)
      |            ^~~~~~~~~~~~~~~~~~~~
drivers/accel/amdxdna/amdxdna_pci_drv.c:328:12: error: 'amdxdna_pmops_suspend' defined but not used [-Werror=unused-function]
  328 | static int amdxdna_pmops_suspend(struct device *dev)
      |            ^~~~~~~~~~~~~~~~~~~~~

Change these to the modern replacements.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Tested-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241213090259.68492-1-arnd@kernel.org
2024-12-13 11:09:42 -07:00
Mike Lothian
d408916885 accel/amdxdna: Add include interrupt.h to amdxdna_mailbox.c
For amdxdna_mailbox.c, linux/interrupt.h is indirectly included by
trace/events/amdxdna.h. So if TRACING is disabled, driver compiling will
fail.

Fixes: b87f920b93 ("accel/amdxdna: Support hardware mailbox")
Reported-by: Mike Lothian <mike@fireburn.co.uk>
Closes: https://lore.kernel.org/dri-devel/CAHbf0-E+Z2O7rW-x+-EKNQ-nLbf=_ohaNzXxE7WD2cj9kFJERQ@mail.gmail.com/
Signed-off-by: Mike Lothian <mike@fireburn.co.uk>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241213163856.1472207-1-lizhi.hou@amd.com
2024-12-13 10:02:36 -07:00
Lizhi Hou
c1e9a0ff94 accel/amdxdna: Add query firmware version
Enhance GET_INFO ioctl to support retrieving firmware version.

Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241206220001.164049-6-lizhi.hou@amd.com
2024-12-13 09:49:20 -07:00
Lizhi Hou
cfc722fc1c accel/amdxdna: Replace mmput with mmput_async to avoid dead lock
Hardware mailbox message receiving handler calls mmput to release the
process mm. If the process has already exited, the mmput here may call mmu
notifier handler, amdxdna_hmm_invalidate, which will cause a dead lock.
Using mmput_async instead prevents this dead lock.

Fixes: aac243092b ("accel/amdxdna: Add command execution")
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241206220001.164049-3-lizhi.hou@amd.com
2024-12-13 09:32:57 -07:00
Lizhi Hou
c3772d6c04 accel/amdxdna: Add device status for aie2 devices
Add device status to track if aie2_hw_start() or aie2_hw_stop() is
re-entered. In aie2_hw_stop(), call drmm_kfree to free mbox.

Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241206220001.164049-2-lizhi.hou@amd.com
2024-12-13 09:29:04 -07:00
Lizhi Hou
850d71f6bf accel/amdxdna: Add query functions
Add GET_INFO ioctl to retrieve hardware information, including
AIE, clock, hardware context etc.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-11-lizhi.hou@amd.com
2024-11-22 11:45:07 -07:00
Lizhi Hou
4fd4ca984b accel/amdxdna: Add error handling
When there is a hardware error, the NPU firmware notifies the host through
a mailbox message. The message includes details of the error, such as the
tile and column indexes where the error occurred.

The driver starts a thread to handle the NPU error message. The thread
stops the clients which are using the column where error occurred. Then
the driver resets that column.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-10-lizhi.hou@amd.com
2024-11-22 11:44:47 -07:00
Lizhi Hou
bed4c73e59 accel/amdxdna: Add suspend and resume
Implement PCI power management suspend and resume callbacks.

Co-developed-by: Narendra Gutta <VenkataNarendraKumar.Gutta@amd.com>
Signed-off-by: Narendra Gutta <VenkataNarendraKumar.Gutta@amd.com>
Co-developed-by: Xiaoming Ren <xiaoming.ren@amd.com>
Signed-off-by: Xiaoming Ren <xiaoming.ren@amd.com>
Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-9-lizhi.hou@amd.com
2024-11-22 11:44:17 -07:00
Lizhi Hou
aac243092b accel/amdxdna: Add command execution
Add interfaces for user application to submit command and wait for its
completion.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-8-lizhi.hou@amd.com
2024-11-22 11:43:27 -07:00
Lizhi Hou
ac49797c18 accel/amdxdna: Add GEM buffer object management
There different types of BOs are supported:

- shmem
A user application uses shmem BOs as input/output for its workload running
on NPU.

- device memory heap
The fixed size buffer dedicated to the device.

- device buffer
The buffer object allocated from device memory heap.

- command buffer
The buffer object created for delivering commands. The command buffer
object is small and pinned on creation.

New IOCTLs are added: CREATE_BO, GET_BO_INFO, SYNC_BO. SYNC_BO is used
to explicitly flush CPU cache for BO memory.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-7-lizhi.hou@amd.com
2024-11-22 11:43:04 -07:00
Lizhi Hou
be462c97b7 accel/amdxdna: Add hardware context
The hardware can be shared among multiple user applications. The
hardware resources are allocated/freed based on the request from
user application via driver IOCTLs.

DRM_IOCTL_AMDXDNA_CREATE_HWCTX
Allocate tile columns and create a hardware context structure to track the
usage and status of the resources. A hardware context ID is returned for
XDNA command execution.

DRM_IOCTL_AMDXDNA_DESTROY_HWCTX
Release hardware context based on its ID. The tile columns belong to
this hardware context will be reclaimed.

DRM_IOCTL_AMDXDNA_CONFIG_HWCTX
Config hardware context. Bind the hardware context to the required
resources.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-6-lizhi.hou@amd.com
2024-11-22 11:42:42 -07:00
Lizhi Hou
c88d3325ae accel/amdxdna: Add hardware resource solver
The AI Engine consists of 2D array of tiles arranged as columns. Provides
the basic column allocation and release functions for the tile columns.

Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-5-lizhi.hou@amd.com
2024-11-22 11:42:17 -07:00
Lizhi Hou
b87f920b93 accel/amdxdna: Support hardware mailbox
The hardware mailboxes are used by the driver to submit requests to
firmware and receive the completion notices from hardware.

Initially, a management mailbox channel is up and running. The driver may
request firmware to create/destroy more channels dynamically through
management channel.

Add driver internal mailbox interfaces.
  - create/destroy a mailbox channel instance
  - send a message to the firmware through a specific channel
  - wait for a notification from the specific channel

Co-developed-by: George Yang <George.Yang@amd.com>
Signed-off-by: George Yang <George.Yang@amd.com>
Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-4-lizhi.hou@amd.com
2024-11-22 11:41:54 -07:00
Lizhi Hou
8c9ff1b181 accel/amdxdna: Add a new driver for AMD AI Engine
AMD AI Engine forms the core of AMD NPU and can be used for accelerating
machine learning applications.

Add the driver to support AI Engine integrated to AMD CPU.
Only very basic functionalities are added.
  - module and PCI device initialization
  - firmware load
  - power up
  - low level hardware initialization

Co-developed-by: Narendra Gutta <VenkataNarendraKumar.Gutta@amd.com>
Signed-off-by: Narendra Gutta <VenkataNarendraKumar.Gutta@amd.com>
Co-developed-by: George Yang <George.Yang@amd.com>
Signed-off-by: George Yang <George.Yang@amd.com>
Co-developed-by: Min Ma <min.ma@amd.com>
Signed-off-by: Min Ma <min.ma@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241118172942.2014541-3-lizhi.hou@amd.com
2024-11-22 11:41:26 -07:00