kernel.git/drivers/gpu/drm/ttm, branch linux-6.15.y

drm/ttm: Respect the shrinker core free target

2025-08-20T16:36:15Z

[ Upstream commit eac21f8ebeb4f84d703cf41dc3f81d16fa9dc00a ] Currently the TTM shrinker aborts shrinking as soon as it frees pages from any of the page order pools and by doing so it can fail to respect the freeing target which was configured by the shrinker core. We use the wording "can fail" because the number of freed pages will depend on the presence of pages in the pools and the order of the pools on the LRU list. For example if there are no free pages in the high order pools the shrinker core may require multiple passes over the TTM shrinker before it will free the default target of 128 pages (assuming there are free pages in the low order pools). This inefficiency can be compounded by the pool LRU where multiple further calls into the TTM shrinker are required to end up looking at the pool with pages. Improve this by never freeing less than the shrinker core has requested. At the same time we start reporting the number of scanned pages (freed in this case), which prevents the core shrinker from giving up on the TTM shrinker too soon and moving on. v2: * Simplify loop logic. (Christian) * Improve commit message. Signed-off-by: Tvrtko Ursulin Cc: Christian König Cc: Thomas Hellström Reviewed-by: Christian König Signed-off-by: Tvrtko Ursulin Link: https://lore.kernel.org/r/20250603112750.34997-2-tvrtko.ursulin@igalia.com Signed-off-by: Sasha Levin

drm/ttm: Should to return the evict error

2025-08-20T16:36:14Z

[ Upstream commit 4e16a9a00239db5d819197b9a00f70665951bf50 ] For the evict fail case, the evict error should be returned. v2: Consider ENOENT case. v3: Abort directly when the eviction failed for some reason (except for -ENOENT) and not wait for the move to finish Signed-off-by: Emily Deng Reviewed-by: Christian König Signed-off-by: Christian König Link: https://lore.kernel.org/r/20250603091154.3472646-1-Emily.Deng@amd.com Signed-off-by: Sasha Levin

drm/ttm: fix error handling in ttm_buffer_object_transfer

2025-07-17T16:43:49Z

commit 97e000acf2e20a86a50a0ec8c2739f0846f37509 upstream. Unlocking the resv object was missing in the error path, additionally to that we should move over the resource only after the fence slot was reserved. Signed-off-by: Christian König Reviewed-by: Matthew Brost Fixes: c8d4c18bfbc4a ("dma-buf/drivers: make reserving a shared slot mandatory v4") Cc: Link: https://lore.kernel.org/r/20250616130726.22863-3-christian.koenig@amd.com Signed-off-by: Greg Kroah-Hartman

drm/ttm/tests: fix incorrect assert in ttm_bo_unreserve_bulk()

2025-06-27T10:13:16Z

[ Upstream commit 878516a9e62cd220379e511d43dcf58df3a6ca9f ] In the ttm_bo_unreserve_bulk() test function, resv is allocated using kunit_kzalloc(), but the subsequent assertion mistakenly verifies the ttm_dev pointer instead of the resv pointer. Fix the assertion to properly verify the resv pointer. Signed-off-by: Qasim Ijaz Link: https://patchwork.freedesktop.org/patch/msgid/20250313161424.10688-1-qasdev00@gmail.com Reviewed-by: Christian König Signed-off-by: Christian König Signed-off-by: Sasha Levin

drm/ttm: Remove the struct ttm_backup abstraction

2025-05-06T08:57:27Z

The abstraction was previously added to support separate ttm_backup implementations. However with the current implementation casting from a struct file to a struct ttm_backup, we run into trouble since struct file may have randomized the layout and gcc complains. Remove the struct ttm_backup abstraction Cc: dri-devel@lists.freedesktop.org Cc: Matthew Brost Cc: Dave Airlie Cc: Christian König Cc: Matthew Auld Cc: Al Viro Reported-by: Kees Cook Closes: https://lore.kernel.org/dri-devel/9c8dbbafdaf9f3f089da2cde5a772d69579b3795.camel@linux.intel.com/T/#mb153ab9216cb813b92bdeb36f391ad4808c2ba29 Suggested-by: Christian König Fixes: 70d645deac98 ("drm/ttm: Add helpers for shrinking") Signed-off-by: Thomas Hellström Reviewed-by: Christian König Link: https://lore.kernel.org/r/20250502130014.3156-1-thomas.hellstrom@linux.intel.com

drm/ttm: Fix ttm_backup kerneldoc

2025-05-06T08:57:11Z

The docs were not properly updated from an earlier version of the code. Fixes: e7b5d23e5d47 ("drm/ttm: Provide a shmem backup implementation") Cc: Christian König Cc: Matthew Brost Cc: Matthew Auld Cc: dri-devel@lists.freedesktop.org Signed-off-by: Thomas Hellström Reviewed-by: Matthew Brost Link: https://lore.kernel.org/r/20250502130101.3185-1-thomas.hellstrom@linux.intel.com

drm/ttm: fix the warning for hit_low and evict_low

2025-04-28T08:01:03Z

fix the below warning messages: ttm/ttm_bo.c:1098: warning: Function parameter or struct member 'hit_low' not described in 'ttm_bo_swapout_walk' ttm/ttm_bo.c:1098: warning: Function parameter or struct member 'evict_low' not described in 'ttm_bo_swapout_walk' Cc: Maarten Lankhorst Cc: Tvrtko Ursulin Signed-off-by: Sunil Khatri Reviewed-by: Maarten Lankhorst Signed-off-by: Christian König Link: https://lore.kernel.org/r/20250423042442.762108-1-sunil.khatri@amd.com

drm/ttm: Add helpers for shrinking

2025-03-05T16:08:59Z

Add a number of helpers for shrinking that access core TTM and core MM functionality in a way that make them unsuitable for driver open-coding. v11: - New patch (split off from previous) and additional helpers. v13: - Adapt to ttm_backup interface change. - Take resource off LRU when backed up. Signed-off-by: Thomas Hellström Reviewed-by: Matthew Brost Acked-by: Dave Airlie Acked-by: Christian König Link: https://lore.kernel.org/intel-xe/20250305092220.123405-6-thomas.hellstrom@linux.intel.com

drm/ttm: Add a macro to perform LRU iteration

2025-03-05T16:08:59Z

Following the design direction communicated here: https://lore.kernel.org/linux-mm/b7491378-defd-4f1c-31e2-29e4c77e2d67@amd.com/T/#ma918844aa8a6efe8768fdcda0c6590d5c93850c9 Export a LRU walker for driver shrinker use. The walker initially supports only trylocking, since that's the method used by shrinkes. The walker makes use of scoped_guard() to allow exiting from the LRU walk loop without performing any explicit unlocking or cleanup. v8: - Split out from another patch. - Use a struct for bool arguments to increase readability (Matt Brost). - Unmap user-space cpu-mappings before shrinking pages. - Explain non-fatal error codes (Matt Brost) v10: - Instead of using the existing helper, Wrap the interface inside out and provide a loop to de-midlayer things the LRU iteration (Christian König). - Removing the R-B by Matt Brost since the patch was significantly changed. v11: - Split the patch up to include just the LRU walk helper. v12: - Indent after scoped_guard() (Matt Brost) v15: - Adapt to new definition of scoped_guard() Signed-off-by: Thomas Hellström Reviewed-by: Matthew Brost Acked-by: Dave Airlie Acked-by: Christian König Link: https://lore.kernel.org/intel-xe/20250305092220.123405-5-thomas.hellstrom@linux.intel.com

drm/ttm: Use fault-injection to test error paths

2025-03-05T16:08:59Z

Use fault-injection to test partial TTM swapout and interrupted swapin. Return -EINTR for swapin to test the callers ability to handle and restart the swapin, and on swapout perform a partial swapout to test that the swapin and release_shrunken functionality. v8: - Use the core fault-injection system. v9: - Fix compliation failure for !CONFIG_FAULT_INJECTION Cc: Christian König Cc: Somalapuram Amaranath Cc: Matthew Brost Cc: Signed-off-by: Thomas Hellström Reviewed-by: Matthew Brost Reviewed-by: Christian König Link: https://lore.kernel.org/intel-xe/20250305092220.123405-4-thomas.hellstrom@linux.intel.com