drm/amdgpu: Wire up dmem cgroup reclaim for VRAM manager

Register the VRAM manager with the dmem cgroup reclaim infrastructure
so that lowering dmem.max below current VRAM usage triggers TTM
eviction rather than failing with -EBUSY.

Guard place->flags in amdgpu_ttm_bo_eviction_valuable() against NULL,
as the TTM reclaim path passes a NULL place in cgroup drain mode.

Use drmm_cgroup_register_region() so that the region is automatically
unregistered at DRM device release, after drm_dev_unplug() has already
made drm_dev_enter() return false.  The drm_dev_enter/exit guard in the
reclaim callback ensures no reclaim work touches the TTM manager after
driver unbind, closing the window between vram_mgr_fini() (called from
drm_driver.release) and the drmm cleanup that unregisters the region.

v3:
- Rebased on fix for uninitialized list and buddy allocator on the
  drmm_cgroup_register_region() error path.

v5:
- Rebased on the introduction of struct dmem_cgroup_init.
- Clear the reclaim callback in amdgpu_vram_mgr_fini() to prevent
  use-after-free if cgroup reclaim is triggered after driver unbind
  while userspace holds an open DRM file descriptor. (Sashiko-bot)
- Switch from drmm_cgroup_register_region() to the raw
  dmem_cgroup_register_region() and store the region in
  amdgpu_vram_mgr.cg_region. Call dmem_cgroup_unregister_region()
  in amdgpu_vram_mgr_fini() after ttm_resource_manager_evict_all()
  to drain in-flight reclaim callbacks, and clear man->cg afterwards.
  This is required because amdgpu's vram manager fini is called
  explicitly during driver unbind, which may precede the DRM device
  release and thus precede any drmm-based cleanup. (Sashiko-bot)

v6:
- Fix mgr->cg_region never being assigned, so
  dmem_cgroup_unregister_region() in fini silently no-ops on NULL
  and leaks the region. (Sashiko-bot)
- Reorder fini to call set_used(false) and evict_all() before
  dmem_cgroup_unregister_region(), so ttm_resource_free() can
  uncharge via man->cg during eviction; clear man->cg after
  unregister. (Sashiko-bot)

v7:
- Move dmem_cgroup_unregister_region() before the early return on
  evict_all() failure; not doing so leaves a dangling reclaim callback
  pointing to the partially-torn-down VRAM manager, causing a
  use-after-free when the cgroup later triggers reclaim. (Sashiko-bot)
- Switch back to drmm_cgroup_register_region() with a drm_dev_enter/
  exit guard in the reclaim callback (matching xe), rather than manual
  register/unregister.  drm_dev_unplug() fires before vram_mgr_fini(),
  so drm_dev_enter() returning false prevents any reclaim from touching
  the manager during teardown.  This also fixes the "vram" name
  collision on multi-GPU systems, since drmm_cgroup_register_region()
  automatically prefixes with "drm/<pci-addr>/". (Sashiko-bot)

v8:
- Move the dmem cgroup region teardown back into
  amdgpu_vram_mgr_fini(): register the region with
  dmem_cgroup_register_region() (keeping the "drm/<unique>/vram"
  prefix), store it in amdgpu_vram_mgr.cg_region, and unregister it
  explicitly after ttm_resource_manager_evict_all(). The v7
  drmm-only approach left a use-after-free on the probe-error
  teardown path: drm_dev_unplug() is not called there, so the
  drm_dev_enter() guard stays open while drm_driver.release destroys
  the manager before the drmm action unregisters the region. The
  explicit unregister drains in-flight reclaim on every teardown
  path; the drm_dev_enter() guard is kept as defense against reclaim
  after unplug. (Sashiko-bot)

v9:
- Don't leak a gpu buddy manager on cgroup init failure. (Sashiko-bot)
- Acquire a runtime PM reference (pm_runtime_get_sync/put_autosuspend)
  around the TTM reclaim call in amdgpu_vram_mgr_dmem_reclaim().
  (Sashiko-bot)

Assisted-by: GitHub_Copilot:claude-sonnet-4.6
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Tested-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Link: https://patch.msgid.link/20260725100036.2372-7-thomas.hellstrom@linux.intel.com
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>

drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c

@@ -1507,7 +1507,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 	dma_resv_for_each_fence(&resv_cursor, bo->base.resv,
 				DMA_RESV_USAGE_BOOKKEEP, f) {
 		if (amdkfd_fence_check_mm(f, current->mm) &&
-		    !(place->flags & TTM_PL_FLAG_CONTIGUOUS))
+		    !(place && (place->flags & TTM_PL_FLAG_CONTIGUOUS)))
 			return false;
 	}
 

drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c

@@ -24,6 +24,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/cgroup_dmem.h>
+#include <linux/pm_runtime.h>
 #include <drm/ttm/ttm_range_manager.h>
 #include <drm/drm_drv.h>
 #include <drm/drm_buddy.h>
@@ -906,6 +907,38 @@ static const struct ttm_resource_manager_func amdgpu_vram_mgr_func = {
 	.debug	= amdgpu_vram_mgr_debug
 };
 
+static const struct dmem_cgroup_ops amdgpu_vram_mgr_dmem_ops;
+
+static int amdgpu_vram_mgr_dmem_reclaim(struct dmem_cgroup_pool_state *pool,
+					u64 target_bytes, void *priv)
+{
+	struct ttm_resource_manager *man = priv;
+	struct amdgpu_device *adev = amdgpu_ttm_adev(man->bdev);
+	int ret, idx;
+
+	if (!drm_dev_enter(adev_to_drm(adev), &idx))
+		return -ENODEV;
+
+	ret = pm_runtime_get_sync(adev_to_drm(adev)->dev);
+	if (ret < 0) {
+		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		goto out;
+	}
+
+	ret = ttm_resource_manager_dmem_reclaim(pool, target_bytes, priv);
+
+	pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
+	pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+
+out:
+	drm_dev_exit(idx);
+	return ret;
+}
+
+static const struct dmem_cgroup_ops amdgpu_vram_mgr_dmem_ops = {
+	.reclaim = amdgpu_vram_mgr_dmem_reclaim,
+};
+
 /**
  * amdgpu_vram_mgr_init - init VRAM manager and DRM MM
  *
@@ -917,6 +950,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr;
 	struct ttm_resource_manager *man = &mgr->manager;
+	struct dmem_cgroup_region *cg;
 	int err;
 
 	ttm_resource_manager_init(man, &adev->mman.bdev,
@@ -933,12 +967,19 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
 	if (err)
 		return err;
 
-	man->cg = drmm_cgroup_register_region(adev_to_drm(adev), "vram",
-					      &(struct dmem_cgroup_init){
+	cg = dmem_cgroup_register_region(&(struct dmem_cgroup_init){
 						.size = adev->gmc.real_vram_size,
-					      });
-	if (IS_ERR(man->cg))
-		return PTR_ERR(man->cg);
+						.ops = &amdgpu_vram_mgr_dmem_ops,
+						.reclaim_priv = man,
+					 },
+					 "drm/%s/vram", adev_to_drm(adev)->unique);
+	if (IS_ERR(cg)) {
+		gpu_buddy_fini(&mgr->mm);
+		return PTR_ERR(cg);
+	}
+
+	mgr->cg_region = cg;
+	ttm_resource_manager_set_dmem_region(man, cg);
 
 	ttm_set_driver_manager(&adev->mman.bdev, TTM_PL_VRAM, &mgr->manager);
 	ttm_resource_manager_set_used(man, true);
@@ -963,6 +1004,19 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
 	ttm_resource_manager_set_used(man, false);
 
 	ret = ttm_resource_manager_evict_all(&adev->mman.bdev, man);
+
+	/*
+	 * Unregister the dmem cgroup region regardless of the evict_all()
+	 * result and before any further teardown.  This drains in-flight
+	 * reclaim callbacks and blocks new ones, so no reclaim can reference
+	 * the manager once we start freeing it.  It must run after evict_all()
+	 * so that ttm_resource_free() can still uncharge via man->cg during
+	 * eviction.  Clear man->cg afterwards.
+	 */
+	dmem_cgroup_unregister_region(mgr->cg_region);
+	mgr->cg_region = NULL;
+	ttm_resource_manager_set_dmem_region(man, NULL);
+
 	if (ret)
 		return;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h

@@ -26,6 +26,8 @@
 
 #include <linux/gpu_buddy.h>
 
+struct dmem_cgroup_region;
+
 struct amdgpu_vram_mgr {
 	struct ttm_resource_manager manager;
 	struct gpu_buddy mm;
@@ -36,6 +38,7 @@ struct amdgpu_vram_mgr {
 	atomic64_t vis_usage;
 	u64 default_page_size;
 	struct list_head allocated_vres_list;
+	struct dmem_cgroup_region *cg_region;
 };
 
 struct amdgpu_vres_task {