aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu
AgeCommit message (Collapse)AuthorFilesLines
2024-08-16drm/amdgpu: Make enforce_isolation setting per GPUSrinivasan Shanmugam5-8/+21
This commit makes enforce_isolation setting to be per GPU and per partition by adding the enforce_isolation array to the adev structure. The adev variable is set based on the global enforce_isolation module parameter during device initialization. In amdgpu_ids.c, the adev->enforce_isolation value for the current GPU is used to determine whether to enforce isolation between graphics and compute processes on that GPU. In amdgpu_ids.c, the adev->enforce_isolation value for the current GPU and partition is used to determine whether to enforce isolation between graphics and compute processes on that GPU and partition. This allows the enforce_isolation setting to be controlled individually for each GPU and each partition, which is useful in a system with multiple GPUs and partitions where different isolation settings might be desired for different GPUs and partitions. v2: fix loop in amdgpu_vmid_mgr_init() (Alex) Cc: Christian König <[email protected]> Cc: Alex Deucher <[email protected]> Signed-off-by: Srinivasan Shanmugam <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Suggested-by: Christian König <[email protected]>
2024-08-16drm/amdgpu: Emit cleaner shader at end of IB submissionAlex Deucher2-0/+6
This commit introduces the emission of a cleaner shader at the end of the IB submission process. This is achieved by adding a new function pointer, `emit_cleaner_shader`, to the `amdgpu_ring_funcs` structure. If the `emit_cleaner_shader` function is set in the ring functions, it is called during the VM flush process. The cleaner shader is only emitted if the `enable_cleaner_shader` flag is set in the `amdgpu_device` structure. This allows the cleaner shader emission to be controlled on a per-device basis. By emitting a cleaner shader at the end of the IB submission, we can ensure that the VM state is properly cleaned up after each submission. Cc: Christian König <[email protected]> Cc: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Signed-off-by: Srinivasan Shanmugam <[email protected]> Suggested-by: Christian König <[email protected]>
2024-08-16drm/amdgpu: Add infrastructure for Cleaner Shader featureSrinivasan Shanmugam2-0/+49
The cleaner shader is used by the CP firmware to clean LDS and GPRs between processes on the CUs. This adds an internal API for GFX IP code to allocate and initialize the cleaner shader. Cc: Christian König <[email protected]> Cc: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Signed-off-by: Srinivasan Shanmugam <[email protected]> Suggested-by: Christian König <[email protected]>
2024-08-16drm/amdgpu: handle enforce isolation on non-0 gfxhubAlex Deucher1-1/+1
Some chips have more than one gfxhub so check if we are a gfxhub rather than just gfxhub 0. Acked-by: Srinivasan Shanmugam <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/sdma5.2: limit wptr workaround to sdma 5.2.1Alex Deucher1-8/+10
The workaround seems to cause stability issues on other SDMA 5.2.x IPs. Fixes: a03ebf116303 ("drm/amdgpu/sdma5.2: Update wptr registers as well as doorbell") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3556 Acked-by: Ruijing Dong <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn ip dump support for vcn_v2_6Sunil Khatri1-2/+2
Add support for logging the registers in devcoredump buffer for vcn_v2_6. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v2_5 ip dumpSunil Khatri1-1/+33
Add support for logging the registers in devcoredump buffer for vcn_v2_5. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v2_5 ip dump supportSunil Khatri1-1/+79
Add support of vcn ip dump in the devcoredump for vcn_v2_5. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v2_0 ip dumpSunil Khatri1-1/+33
Add support for logging the registers in devcoredump buffer for vcn_v2_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v2_0 ip dump supportSunil Khatri1-1/+78
Add support of vcn ip dump in the devcoredump for vcn_v2_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v1_0 ip dumpSunil Khatri1-1/+33
Add support for logging the registers in devcoredump buffer for vcn_v1_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v1_0 ip dump supportSunil Khatri1-1/+77
Add support of vcn ip dump in the devcoredump for vcn_v1_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v4_0_5 ip dumpSunil Khatri1-1/+33
Add support for logging the registers in devcoredump buffer for vcn_v4_0_5. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v4_0 ip dumpSunil Khatri1-1/+33
Add support for logging the registers in devcoredump buffer for vcn_v4_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v4_0_3 ip dumpSunil Khatri1-1/+33
Add support for logging the registers in devcoredump buffer for vcn_v4_0_3. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v4_0_5 ip dump supportSunil Khatri1-1/+78
Add support of vcn ip dump in the devcoredump for vcn_v4_0_5. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v4_0 ip dump supportSunil Khatri1-1/+79
Add support of vcn ip dump in the devcoredump for vcn_v4_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v4_0_3 ip dump supportSunil Khatri1-1/+80
Add support of vcn ip dump in the devcoredump for vcn_v4_0_3. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v5_0 ip dumpSunil Khatri1-1/+33
Add support for logging the registers in devcoredump buffer for vcn_v5_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/mes12: add API for user queue resetAlex Deucher1-0/+27
Add API for resetting user queues. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/mes11: add API for user queue resetAlex Deucher1-0/+21
Add API for resetting user queues. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/mes: add API for user queue resetAlex Deucher2-0/+52
Add API for resetting user queues. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx11: export gfx_v11_0_request_gfx_index_mutex()Alex Deucher2-2/+5
It will be used by the queue reset code. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx11: add a mutex for the gfx semaphoreAlex Deucher3-3/+10
This will be used in more places in the future so add a mutex. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx11: enter safe mode before touching CP_INT_CNTLAlex Deucher1-2/+2
Need to enter safe mode before touching GC MMIO. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx7: add ring reset callback for gfxAlex Deucher2-1/+76
Add ring reset callback for gfx. v2: fix operator precedence (kernel test robot) Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx8: add ring reset callback for gfxAlex Deucher2-1/+75
Add ring reset callback for gfx. v2: fix operator precedence (kernel test robot) Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v5_0 ip dump supportSunil Khatri1-1/+75
Add support of vcn ip dump in the devcoredump for vcn_v5_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add print support for vcn_v3_0 ip dumpSunil Khatri1-1/+34
Add support for logging the registers in devcoredump buffer for vcn_v3_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn_v3_0 ip dump supportSunil Khatri1-1/+77
Add support of vcn ip dump in the devcoredump for vcn_v3_0. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: add vcn ip dump ptr in vcn global structSunil Khatri1-0/+3
Add pointer to the vcn ip dump in the vcn global structure to be accessible for all vcn version via global adev. Signed-off-by: Sunil Khatri <[email protected]> Acked-by: Leo Liu <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amd: Remove unused declarationsZhang Zekun2-9/+0
amdgpu_gart_table_vram_pin() and amdgpu_gart_table_vram_unpin() has been removed since commit 575e55ee4fbc ("drm/amdgpu: recover gart table at resume") remain the declarations untouched in the header files. Besides, amdgpu_dm_display_resume() has also beed removed since commit a80aa93de1a0 ("drm/amd/display: Unify dm resume sequence into a single call"). So, let's remove this unused declarations. Signed-off-by: Zhang Zekun <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/radeon/evergreen_cs: fix int overflow errors in cs track offsetsNikita Zhandarovich1-31/+31
Several cs track offsets (such as 'track->db_s_read_offset') either are initialized with or plainly take big enough values that, once shifted 8 bits left, may be hit with integer overflow if the resulting values end up going over u32 limit. Same goes for a few instances of 'surf.layer_size * mslice' multiplications that are added to 'offset' variable - they may potentially overflow as well and need to be validated properly. While some debug prints in this code section take possible overflow issues into account, simply casting to (unsigned long) may be erroneous in its own way, as depending on CPU architecture one is liable to get different results. Fix said problems by: - casting 'offset' to fixed u64 data type instead of ambiguous unsigned long. - casting one of the operands in vulnerable to integer overflow cases to u64. - adjust format specifiers in debug prints to properly represent 'offset' values. Found by Linux Verification Center (linuxtesting.org) with static analysis tool SVACE. Fixes: 285484e2d55e ("drm/radeon: add support for evergreen/ni tiling informations v11") Signed-off-by: Nikita Zhandarovich <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: fixing rlc firmware loading failure issueYang Wang1-2/+3
Skip rlc firmware validation to ignore firmware header size mismatch issues. This restores the workaround added in commit 849e133c973c ("drm/amdgpu: Fix the null pointer when load rlc firmware") Fixes: 3af2c80ae2f5 ("drm/amdgpu: refine gfx10 firmware loading") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3551 Signed-off-by: Yang Wang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu: remove ME0 registers from mi300 dumpSunil Khatri1-37/+0
Remove ME0 registers from MI300 gfx_9_4_3 ipdump MI300 does not have gfx ME and hence those register are just empty one and could be dropped. Signed-off-by: Sunil Khatri <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: use rlc safe mode for soft recoveryAlex Deucher1-0/+2
Protect the MMIO access with safe mode. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9.4.3: use rlc safe mode for soft recoveryAlex Deucher1-0/+2
Protect the MMIO access with safe mode. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9.4.3: use proper rlc safe mode helpersAlex Deucher1-4/+4
Rather than open coding it for the queue reset. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: use proper rlc safe mode helpersAlex Deucher1-4/+4
Rather than open coding it for the queue reset. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: add ring reset callback for gfxAlex Deucher1-0/+46
Add ring reset callback for gfx. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: per queue reset only on bare metalAlex Deucher2-0/+6
It's not supported under SR-IOV at the moment. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9.4.3: implement reset_hw_queue for gfx9.4.3Jiadong Zhu1-0/+36
Using mmio to do queue reset. Enter safe mode before writing mmio registers. v2: set register instance offset according to xcc id. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: implement reset_hw_queue for gfx9Jiadong Zhu1-0/+37
Using mmio to do queue reset. Enter safe mode when writing registers. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx: add a new kiq_pm4_funcs callback for reset_hw_queueJiadong Zhu1-0/+4
Add reset_hw_queue in kiq_pm4_funcs callbacks. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx_9.4.3: wait for reset done before remapJiadong Zhu1-6/+33
There is a racing condition that cp firmware modifies MQD in reset sequence after driver updates it for remapping. We have to wait till CP_HQD_ACTIVE becoming false then remap the queue. v2: fix KIQ locking (Alex) v3: fix KIQ locking harder Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9.4.3: remap queue after reset successfullyJiadong Zhu1-9/+27
Kiq command unmap_queues only does the dequeueing action. We have to map the queue back with clean mqd. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9.4.3: add ring reset callbackAlex Deucher1-0/+38
Add ring reset callback for compute. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: wait for reset done before remapJiadong Zhu1-5/+31
There is a racing condition that cp firmware modifies MQD in reset sequence after driver updates it for remapping. We have to wait till CP_HQD_ACTIVE becoming false then remap the queue. v2: fix KIQ locking (Alex) v3: fix KIQ locking harder Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: remap queue after reset successfullyJiadong Zhu1-9/+27
Kiq command unmap_queues only does the dequeueing action. We have to map the queue back with clean mqd. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Jiadong Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2024-08-16drm/amdgpu/gfx9: add ring reset callbackAlex Deucher1-0/+38
Add ring reset callback for compute. Acked-by: Vitaly Prosyak <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.