kernel/linux.git/drivers/gpu/drm/etnaviv, branch v6.12.80

drm/etnaviv: fix flush sequence logic

2025-11-13T20:33:58+00:00

[ Upstream commit a042beac6e6f8ac1e923784cfff98b47cbabb185 ] The current logic uses the flush sequence from the current address space. This is harmless when deducing the flush requirements for the current submit, as either the incoming address space is the same one as the currently active one or we switch context, in which case the flush is unconditional. However, this sequence is also stored as the current flush sequence of the GPU. If we switch context the stored flush sequence will no longer belong to the currently active address space. This incoherency can then cause missed flushes, resulting in translation errors. Fixes: 27b67278e007 ("drm/etnaviv: rework MMU handling") Signed-off-by: Tomeu Vizoso Signed-off-by: Lucas Stach Reviewed-by: Christian Gmeiner Link: https://lore.kernel.org/r/20251021093723.3887980-1-l.stach@pengutronix.de Signed-off-by: Sasha Levin

drm/etnaviv: Protect the scheduler's pending list with its lock

2025-07-06T09:01:44+00:00

commit 61ee19dedb8d753249e20308782bf4e9e2fb7344 upstream. Commit 704d3d60fec4 ("drm/etnaviv: don't block scheduler when GPU is still active") ensured that active jobs are returned to the pending list when extending the timeout. However, it didn't use the pending list's lock to manipulate the list, which causes a race condition as the scheduler's workqueues are running. Hold the lock while manipulating the scheduler's pending list to prevent a race. Cc: stable@vger.kernel.org Fixes: 704d3d60fec4 ("drm/etnaviv: don't block scheduler when GPU is still active") Reported-by: Philipp Stanner Closes: https://lore.kernel.org/dri-devel/964e59ba1539083ef29b06d3c78f5e2e9b138ab8.camel@mailbox.org/ Reviewed-by: Lucas Stach Reviewed-by: Philipp Stanner Link: https://lore.kernel.org/r/20250602132240.93314-1-mcanal@igalia.com Signed-off-by: Maíra Canal Signed-off-by: Greg Kroah-Hartman

drm/etnaviv: Fix page property being used for non writecombine buffers

2025-02-08T08:56:55+00:00

[ Upstream commit 834f304192834d6f0941954f3277ae0ba11a9a86 ] In the etnaviv_gem_vmap_impl() function, the driver vmap whatever buffers with write combine(WC) page property, this is incorrect. Cached buffers should be mapped with the cached page property and uncached buffers should be mapped with the uncached page property. Fixes: a0a5ab3e99b8 ("drm/etnaviv: call correct function when trying to vmap a DMABUF") Signed-off-by: Sui Jingfeng Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin

drm/etnaviv: flush shader L1 cache after user commandstream

2024-12-09T09:41:13+00:00

commit 4f8dbadef085ab447a01a8d4806a3f629fea05ed upstream. The shader L1 cache is a writeback cache for shader loads/stores and thus must be flushed before any BOs backing the shader buffers are potentially freed. Cc: stable@vger.kernel.org Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Signed-off-by: Greg Kroah-Hartman

drm/etnaviv: hold GPU lock across perfmon sampling

2024-12-05T13:01:50+00:00

[ Upstream commit 37dc4737447a7667f8e9ec790dac251da057eb27 ] The perfmon sampling mutates shared GPU state (e.g. VIVS_HI_CLOCK_CONTROL to select the pipe for the perf counter reads). To avoid clashing with other functions mutating the same state (e.g. etnaviv_gpu_update_clock) the perfmon sampling needs to hold the GPU lock. Fixes: 68dc0b295dcb ("drm/etnaviv: use 'sync points' for performance monitor requests") Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin

drm/etnaviv: Request pages from DMA32 zone on addressing_limited

2024-12-05T13:01:50+00:00

[ Upstream commit 13c96ac9a3f0f1c7ba1ff0656ea508e7fa065e7e ] Remove __GFP_HIGHMEM when requesting a page from DMA32 zone, and since all vivante GPUs in the system will share the same DMA constraints, move the check of whether to get a page from DMA32 to etnaviv_bind(). Fixes: b72af445cd38 ("drm/etnaviv: request pages from DMA32 zone when needed") Suggested-by: Sui Jingfeng Signed-off-by: Xiaolei Wang Reviewed-by: Christian Gmeiner Signed-off-by: Lucas Stach Signed-off-by: Sasha Levin

Merge drm/drm-next into drm-misc-next

2024-07-29T07:35:54+00:00

Backmerging to get a late RC of v6.10 before moving into v6.11. Signed-off-by: Thomas Zimmermann

drm/scheduler: remove full_recover from drm_sched_start

2024-07-25T12:05:12+00:00

This was basically just another one of amdgpus hacks. The parameter allowed to restart the scheduler without turning fence signaling on again. That this is absolutely not a good idea should be obvious by now since the fences will then just sit there and never signal. While at it cleanup the code a bit. Signed-off-by: Christian König Reviewed-by: Matthew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20240722083816.99685-1-christian.koenig@amd.com

drm/etnaviv: don't block scheduler when GPU is still active

2024-06-26T13:33:25+00:00

Since 45ecaea73883 ("drm/sched: Partial revert of 'drm/sched: Keep s_fence->parent pointer'") still active jobs aren't put back in the pending list on drm_sched_start(), as they don't have a active parent fence anymore, so if the GPU is still working and the timeout is extended, all currently active jobs will be freed. To avoid prematurely freeing jobs that are still active on the GPU, don't block the scheduler until we are fully committed to actually reset the GPU. As the current job is already removed from the pending list and will not be put back when drm_sched_start() isn't called, we must make sure to put the job back on the pending list when extending the timeout. Cc: stable@vger.kernel.org #6.0 Signed-off-by: Lucas Stach Reviewed-by: Philipp Zabel Reviewed-by: Christian Gmeiner

drm/etnaviv: reduce number of ktime_get calls in IRQ handler

2024-06-26T13:32:47+00:00

A single IRQ might signal the completion of multiple jobs/fences at once. There is no point in attaching a new timestamp to each fence that only differs in when exactly the IRQ handler was able to process this fence. Get a single timestamp when the IRQ handler has determined that there are completed jobs and reuse this for all fences that get signalled by the handler. Signed-off-by: Lucas Stach Reviewed-by: Philipp Zabel Reviewed-by: Christian Gmeiner