kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c, branch v7.2-rc1

drm/amdgpu: Add lockdep annotations for lock ordering validation

2026-06-04T19:24:22+00:00

Add lockdep annotations to teach lockdep the correct lock hierarchy and catch ordering violations during development. This follows the pattern established by dma-resv in drivers/dma-buf/dma-resv.c. Lock ordering hierarchy (outermost to innermost): 1. userq_sch_mutex - Global userq scheduler (enforce_isolation) 2. userq_mutex - Per-context userq (held across queue create/destroy) 3. notifier_lock - MMU notifier synchronization 4. vram_lock - VRAM memory allocator 5. reset_domain->sem - GPU reset synchronization 6. reset_lock - Reset control mutex 7. srbm_mutex - SRBM register access 8. grbm_idx_mutex - GRBM index register access 9. mmio_idx_lock - MMIO index access (spinlock) The implementation provides: - Lock ordering training at module init (amdgpu_lockdep_init) - Lock class association for real driver locks (amdgpu_lockdep_set_class) Dummy locks are associated with the same class keys as real driver locks via lockdep_set_class(), ensuring lockdep connects the training ordering with actual runtime locks. Testing: Build the kernel with CONFIG_PROVE_LOCKING=y (enables CONFIG_LOCKDEP): scripts/config --enable PROVE_LOCKING scripts/config --enable DEBUG_LOCKDEP make -j$(nproc) On boot, dmesg should show: AMDGPU: Lockdep annotations initialized (9 lock levels) The companion IGT test (tests/amdgpu/amd_lockdep) exercises lock-heavy GPU code paths concurrently to trigger lockdep warnings on violations: sudo ./build/tests/amdgpu/amd_lockdep sudo dmesg | grep -A 50 "circular locking dependency" IGT subtests: concurrent-reset-and-submit - reset_sem vs submission locks concurrent-mmap-and-evict - mmap_lock vs vram_lock concurrent-userptr-and-reset - notifier_lock vs reset_sem stress-all-paths - all of the above simultaneously A clean dmesg (no "circular locking dependency" or "possible recursive locking detected" messages) confirms no lock ordering violations. For CI integration, the test should be run on kernels compiled with CONFIG_LOCKDEP=y; dmesg is scanned post-run for lockdep splats. v2: (Christian) - Move notifier_lock and vram_lock before reset locks in hierarchy. HMM invalidation holds notifier_lock and can wait for GPU reset completion, so notifier_lock must be outer to reset_domain->sem. - Associate dummy locks with lock class keys via lockdep_set_class() so lockdep connects training with real driver locks. - Update commit message to list all 9 lock levels. Requires CONFIG_PROVE_LOCKING=y to activate. Cc: Christian Konig Cc: Alex Deucher Signed-off-by: Vitaly Prosyak Reviewed-by: Christian Konig Signed-off-by: Alex Deucher

drm/amd: Reduce code duplication in runtime PM

2026-05-18T22:19:39+00:00

[Why] amdgpu_pmops_runtime_suspend() runs almost the same code that amdgpu_pmops_runtime_idle() runs. That is there is pointless code duplication. [How] Move amdgpu_pmops_runtime_idle() up, extract common code and then call from both functions. No intended functional changes. Reviewed-by: Alex Deucher Signed-off-by: Mario Limonciello Signed-off-by: Alex Deucher

drm/amdgpu: add amdgpu.ptl module parameter for PTL control

2026-05-11T19:55:56+00:00

Add a new kernel module parameter 'amdgpu.ptl' to allow users to enable or disable PTL feature at driver loading time. Parameter values: *) 0 or -1: disable PTL (default) *) 1: enable PTL *) 2: permanently disable PTL Signed-off-by: Perry Yuan Reviewed-by: Yifan Zhang Acked-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: nuke amdgpu_userq_fence_slab v2

2026-05-05T13:56:53+00:00

As preparation for independent fences remove the extra slab, kmalloc should do just fine. v2: use GFP_KERNEL instead of GFP_ATOMIC Signed-off-by: Christian König Reviewed-by: Prike Liang Reviewed-by: Sunil Khatri Signed-off-by: Alex Deucher

amdkfd: Only ignore -ENOENT for KFD init failuires

2026-04-24T14:47:04+00:00

When compiled without CONFIG_HSA_AMD KFD will return -ENOENT. As other errors will cause KFD functionality issues this is the only error code that should be ignored at init. Reviewed-by: Kent Russell Signed-off-by: Mario Limonciello (AMD) Signed-off-by: Alex Deucher

drm/amdgpu: Use amdgpu by default for CIK APUs too

2026-04-03T18:04:57+00:00

CIK APUs are: Kaveri, Kabini and Mullins from 2013~2015, which all have a second generation GCN based integrated GPU. The amdgpu driver has been working well on CIK APUs for years. Features which were previously missing have been added recently, specifically DC support for analog connectors and DP bridge encoders. Now amdgpu is at feature parity with the old radeon driver on CIK APUs. Enabling the amdgpu driver by default for CIK APUs has the following benefits: - More stable OpenGL support through RadeonSI - Vulkan support through RADV - Improved performance - Better display features through DC Users who want to keep using the old driver can do so using: amdgpu.cik_support=0 radeon.cik_support=1 Signed-off-by: Timur Kristóf Signed-off-by: Alex Deucher

drm/amdgpu: Fix wait after reset sequence in S4

2026-03-30T19:13:21+00:00

For a mode-1 reset done at the end of S4 on PSPv11 dGPUs, only check if TOS is unloaded. Fixes: 32f73741d6ee ("drm/amdgpu: Wait for bootloader after PSPv11 reset") Closes: https://gitlab.freedesktop.org/drm/amd/-/work_items/4853 Signed-off-by: Lijo Lazar Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher

drm/amdgpu: fix eviction fence and userq manager shutdown

2026-03-17T21:46:21+00:00

That is a really complicated dance and wasn't implemented fully correct. Signed-off-by: Christian König Reviewed-by: Sunil Khatri Signed-off-by: Alex Deucher

drm/amdgpu: completely rework eviction fence handling v2

2026-03-17T21:46:13+00:00

Well that was broken on multiple levels. First of all a lot of checks were placed at incorrect locations, especially if the resume worker should run or not. Then a bunch of code was just mid-layering because of incorrect assignment who should do what. And finally comments explaining what happens instead of why. Just re-write it from scratch, that should at least fix some of the hangs we are seeing. Use RCU for the eviction fence pointer in the manager, the spinlock usage was mostly incorrect as well. Then finally remove all the nonsense checks and actually add them in the correct locations. v2: some typo fixes and cleanups suggested by Sunil Signed-off-by: Christian König Reviewed-by: Sunil Khatri Signed-off-by: Alex Deucher

drm/amdgpu: Support forcing MTYPE_RW

2026-03-17T14:31:52+00:00

Set default value of module parameter amdgpu_mtype_local to -1. This allows to force MTYPE_RW on ASICs where MTYPE_RW is not default. v2: Fix SDMA get_vm_pte_pde MTYPE Signed-off-by: Harish Kasiviswanathan Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher