user/sven/linux.git/drivers/gpu, branch v6.8.9

drm/amdkfd: Fix eviction fence handling

2024-05-02T14:35:29Z

commit 37865e02e6ccecdda240f33b4332105a5c734984 upstream. Handle case that dma_fence_get_rcu_safe returns NULL. If restore work is already scheduled, only update its timer. The same work item cannot be queued twice, so undo the extra queue eviction. Fixes: 9a1c1339abf9 ("drm/amdkfd: Run restore_workers on freezable WQs") Signed-off-by: Felix Kuehling Reviewed-by: Philip Yang Tested-by: Gang BA Reviewed-by: Gang BA Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: Fix rescheduling of restore worker

2024-05-02T14:35:29Z

commit e26305f369ed0e087a043c2cdc76f3d9a6efb3bd upstream. Handle the case that the restore worker was already scheduled by another eviction while the restore was in progress. Fixes: 9a1c1339abf9 ("drm/amdkfd: Run restore_workers on freezable WQs") Signed-off-by: Felix Kuehling Reviewed-by: Philip Yang Tested-by: Yunxiang Li Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: Fix leak when GPU memory allocation fails

2024-05-02T14:35:29Z

commit 25e9227c6afd200bed6774c866980b8e36d033af upstream. Free the sync object if the memory allocation fails for any reason. Signed-off-by: Mukul Joshi Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu/umsch: don't execute umsch test when GPU is in reset/suspend

2024-05-02T14:35:29Z

commit 661d71ee5a010bdc0663e0db701931aff920e8e1 upstream. umsch test needs full GPU functionality(e.g., VM update, TLB flush, possibly buffer moving under memory pressure) which may be not ready under these states. Just skip it to avoid potential issues. Signed-off-by: Lang Yu Reviewed-by: Christian König Reviewed-by: Veerabadhran Gopalakrishnan Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu/pm: Remove gpu_od if it's an empty directory

2024-05-02T14:35:29Z

commit 0e95ed6452cb079cf9587c774a475a7d83c7e040 upstream. gpu_od should be removed if it's an empty directory Signed-off-by: Ma Jun Reported-by: Yang Wang Reviewed-by: Yang Wang Suggested-by: Lijo Lazar Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/atomic-helper: fix parameter order in drm_format_conv_state_copy() call

2024-05-02T14:35:29Z

commit a386c30410450ea87cd38070f9feaca49dadce29 upstream. Old and new state parameters are swapped, so the old state was cleared instead of the new duplicated state. Fixes: 903674588a48 ("drm/atomic-helper: Add format-conversion state to shadow-plane state") Signed-off-by: Lucas Stach Tested-by: Leonard Göhrs Reviewed-by: Thomas Zimmermann Cc: # v6.8+ Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20240404081756.2714424-1-l.stach@pengutronix.de Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: Assign correct bits for SDMA HDP flush

2024-05-02T14:35:29Z

commit aebd3eb9d3ae017e6260043f6bcace2f5ef60694 upstream. HDP Flush request bit can be kept unique per AID, and doesn't need to be unique SOC-wide. Assign only bits 10-13 for SDMA v4.4.2. Signed-off-by: Lijo Lazar Acked-by: Alex Deucher Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu/sdma5.2: use legacy HDP flush for SDMA2/3

2024-05-02T14:35:29Z

commit 9792b7cc18aaa0c2acae6af5d0acf249bcb1ab0d upstream. This avoids a potential conflict with firmwares with the newer HDP flush mechanism. Reviewed-by: Christian König Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdgpu: fix visible VRAM handling during faults

2024-05-02T14:35:24Z

[ Upstream commit a6ff969fe9cbf369e3cd0ac54261fec1122682ec ] When we removed the hacky start code check we actually didn't took into account that *all* VRAM pages needs to be CPU accessible. Clean up the code and unify the handling into a single helper which checks if the whole resource is CPU accessible. The only place where a partial check would make sense is during eviction, but that is neglitible. Signed-off-by: Christian König Fixes: aed01a68047b ("drm/amdgpu: Remove TTM resource->start visible VRAM condition v2") Reviewed-by: Alex Deucher Signed-off-by: Alex Deucher CC: stable@vger.kernel.org Signed-off-by: Sasha Levin

drm/amdgpu: add shared fdinfo stats

2024-05-02T14:35:24Z

[ Upstream commit ba1a58d5b907bdf1814f8f57434aebc86233430f ] Add shared stats. Useful for seeing shared memory. v2: take dma-buf into account as well v3: use the new gem helper Link: https://lore.kernel.org/all/20231207180225.439482-1-alexander.deucher@amd.com/ Signed-off-by: Alex Deucher Cc: Rob Clark Reviewed-by: Christian König Signed-off-by: Christian König Stable-dep-of: a6ff969fe9cb ("drm/amdgpu: fix visible VRAM handling during faults") Signed-off-by: Sasha Levin