linux-stable.git/drivers/gpu/drm/ttm, branch master

drm/ttm: Fix ttm_bo_shrink() infinite LRU walk on backup failure

2026-05-14T13:32:29+00:00

Apply the same fix as b2ed01e7ad ("drm/ttm: Fix ttm_bo_swapout()
infinite LRU walk on swapout failure") to the ttm_bo_shrink() path.

Move del_bulk_move from before the backup to after success only,
using ttm_resource_del_bulk_move_unevictable() since the resource
is now unevictable once fully backed up.

Fixes: 70d645deac98 ("drm/ttm: Add helpers for shrinking")
Cc: Christian König 
Cc: Huang Rui 
Cc: Matthew Auld 
Cc: Matthew Brost 
Cc: Dave Airlie 
Cc: dri-devel@lists.freedesktop.org
Cc: stable@vger.kernel.org # v6.15+
Assisted-by: GitHub_Copilot:claude-opus-4.6
Reviewed-by: Matthew Auld 
Link: https://patch.msgid.link/20260511162443.24352-1-thomas.hellstrom@linux.intel.com
Signed-off-by: Thomas Hellström

drm/ttm: Convert -EAGAIN from dmem_cgroup_try_charge to -ENOSPC

2026-05-14T11:12:57+00:00

dmem_cgroup_try_charge() returns -EAGAIN when the cgroup limit is
hit and the charge fails. TTM has no concept of -EAGAIN from resource
allocation; -ENOSPC is the canonical error meaning "no space, try
eviction". Convert at the source in ttm_resource_alloc() so no caller
needs to handle an unexpected error code, and clean up the now-redundant
-EAGAIN check in ttm_bo_alloc_resource().

Without this, -EAGAIN escaping ttm_resource_alloc() during an eviction
walk causes the walk to terminate early instead of continuing to the
next candidate.

Cc: Friedrich Vock 
Cc: Maarten Lankhorst 
Cc: Tejun Heo 
Cc: Maxime Ripard 
Cc: Christian Koenig 
Cc: dri-devel@lists.freedesktop.org
Cc:  # v6.14+
Fixes: 2b624a2c1865 ("drm/ttm: Handle cgroup based eviction in TTM")
Assisted-by: GitHub_Copilot:claude-sonnet-4.6
Signed-off-by: Thomas Hellström 
Reviewed-by: Maarten Lankhorst 
Link: https://patch.msgid.link/20260508160920.230339-1-thomas.hellstrom@linux.intel.com

drm/ttm: Fix ttm_bo_swapout() infinite LRU walk on swapout failure

2026-05-08T15:19:44+00:00

When ttm_tt_swapout() fails, the current code calls
ttm_resource_add_bulk_move() followed by ttm_resource_move_to_lru_tail()
to restore the resource's bulk_move membership.

However, ttm_resource_move_to_lru_tail() places the resource at the tail
of the LRU list which, relative to the walk cursor's hitch node (placed
immediately after the resource when it was yielded), puts the resource
*in front of the* the hitch. The next list_for_each_entry_continue() from
the hitch finds the same resource again, causing an infinite loop.

Fix by deferring del_bulk_move to the success path only.

On the success path, TTM_TT_FLAG_SWAPPED has just been set by
ttm_tt_swapout() but the resource is still tracked in the bulk_move range,
so ttm_resource_del_bulk_move()'s !ttm_resource_unevictable() guard would
incorrectly skip the removal. Introduce
ttm_resource_del_bulk_move_unevictable() which bypasses that guard.

Reported-by: Jatin Kataria 
Fixes: fc5d96670eb2 ("drm/ttm: Move swapped objects off the manager's LRU list")
Cc: Christian König 
Cc: Matthew Brost 
Cc: 
Cc:  # v6.13+
Assisted-by: GitHub_Copilot:claude-sonnet-4.6
Signed-off-by: Thomas Hellström 
Reviewed-by: Christian König 
Tested-by: Boqun Feng 
Link: https://patch.msgid.link/20260428094442.16985-1-thomas.hellstrom@linux.intel.com

drm/ttm: Fix GPU MM stats during pool shrinking

2026-05-04T04:05:59+00:00

TTM pool shrinking frees pages by calling __free_pages() directly,
which bypasses updates to NR_GPU_ACTIVE and leaves GPU MM accounting
out of sync.

Introduce a helper, __free_pages_gpu_account(), and use it for all page
frees in ttm_pool.c so GPU MM statistics are updated consistently.

Reported-by: Kenneth Crudup 
Fixes: ae80122f3896 ("drm/ttm: use gpu mm stats to track gpu memory allocations. (v4)")
Cc: Christian Koenig 
Cc: Huang Rui 
Cc: Matthew Auld 
Cc: David Airlie 
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Matthew Brost 
Tested-by: Kenneth Crudup 
Reviewed-by: Dave Airlie 
Link: https://patch.msgid.link/20260502065338.2720646-1-matthew.brost@intel.com

drm/ttm/tests: Remove checks from ttm_pool_free_no_dma_alloc

2026-04-09T20:54:49+00:00

On !x86, the pool type is never initialised, and the pages are freed
back to the system.

The test broke on the list_lru rewrite, but I'm not sure how that it was
supposed to work previously. In the meantime CI is broken so reverting
for now.

Fixes: 444e2a19d7fd ("ttm/pool: port to list_lru. (v2)")
Cc: Christian Koenig 
Cc: Johannes Weiner 
Cc: Dave Chinner 
Cc: Christian König 
Cc: Dave Airlie 
Signed-off-by: Maarten Lankhorst 
Signed-off-by: Dave Airlie 
Link: https://patch.msgid.link/20260409142658.1511941-2-dev@lankhorst.se

drm/ttm/tests: fix lru_count ASSERT

2026-04-09T20:53:10+00:00

On pool init we should expect the lru_count for each node to be zeroed
as per __list_lru_init -> init_one_lru, but here we are asserting the
opposite.

Currently our CI is blowing up with:

10:23:33] # ttm_device_init_pools: ASSERTION FAILED at drivers/gpu/drm/ttm/tests/ttm_device_test.c:178
[10:23:33] Expected !list_lru_count(&pt.pages) to be false, but is true
[10:23:33] [FAILED] DMA allocations, DMA32 required
[10:23:33] [PASSED] No DMA allocations, DMA32 required
[10:23:33]     # ttm_device_init_pools: ASSERTION FAILED at drivers/gpu/drm/ttm/tests/ttm_device_test.c:178
[10:23:33]     Expected !list_lru_count(&pt.pages) to be false, but is true

Fixes: 444e2a19d7fd ("ttm/pool: port to list_lru. (v2)")
Signed-off-by: Matthew Auld 
Cc: Matthew Brost 
Cc: Christian Koenig 
Cc: Dave Airlie 
Reviewed-by: Ryszard Knop 
Signed-off-by: Dave Airlie 
Link: https://patch.msgid.link/20260409121512.81298-3-matthew.auld@intel.com

ttm/pool: track allocated_pages per numa node.

2026-04-07T20:52:48+00:00

This gets the memory sizes from the nodes and stores the limit
as 50% of those. I think eventually we should drop the limits
once we have memcg aware shrinking, but this should be more NUMA
friendly, and I think seems like what people would prefer to
happen on NUMA aware systems.

Cc: Christian Koenig 
Signed-off-by: Dave Airlie

ttm/pool: make pool shrinker NUMA aware (v2)

2026-04-07T20:52:47+00:00

This enable NUMA awareness for the shrinker on the
ttm pools.

Cc: Christian Koenig 
Cc: Dave Chinner 
Reviewed-by: Christian König 
Signed-off-by: Dave Airlie

ttm/pool: drop numa specific pools

2026-04-07T20:52:47+00:00

The list_lru will now handle numa for us, so no need to keep
separate pool types for it. Just consolidate into the global ones.

This adds a debugfs change to avoid dumping non-existant orders due
to this change.

Cc: Christian Koenig 
Cc: Johannes Weiner 
Signed-off-by: Dave Airlie

ttm/pool: port to list_lru. (v2)

2026-04-07T20:52:47+00:00

This is an initial port of the TTM pools for
write combined and uncached pages to use the list_lru.

This makes the pool's more NUMA aware and avoids
needing separate NUMA pools (later commit enables this).

Cc: Christian Koenig 
Cc: Johannes Weiner 
Cc: Dave Chinner 
Reviewed-by: Christian König 
Signed-off-by: Dave Airlie