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.
v4: - Rebased on drm-tip; dropped the XE_PL_STOLEN guard as stolen memory uses a separate TTM manager and never calls __xe_ttm_vram_mgr_init(). v5: - Rebased on the introduction of struct dmem_cgroup_init. - Register the fini drmm action before drmm_cgroup_register_region() so that devres LIFO teardown runs unregister_region() first (draining any in-flight reclaim callbacks via the rwsem) and xe_ttm_vram_mgr_fini() second, ensuring the manager is never accessed by a reclaim callback after teardown. (Sashiko-bot) - Wrap the reclaim callback in xe_ttm_vram_mgr_dmem_reclaim() using drm_dev_enter()/drm_dev_exit() to prevent TTM reclaim from running after driver unbind. Assisted-by: GitHub_Copilot:claude-sonnet-4.6 Signed-off-by: Thomas Hellström <[email protected]> --- drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 54 +++++++++++++++++++++++----- 1 file changed, 45 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c index 308fda4248eb..b2500344cd57 100644 --- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c @@ -276,6 +276,28 @@ static const struct ttm_resource_manager_func xe_ttm_vram_mgr_func = { .debug = xe_ttm_vram_mgr_debug }; +static const struct dmem_cgroup_ops xe_ttm_vram_mgr_dmem_ops; + +static int xe_ttm_vram_mgr_dmem_reclaim(struct dmem_cgroup_pool_state *pool, + u64 target_bytes, void *priv) +{ + struct ttm_resource_manager *man = priv; + struct xe_device *xe = ttm_to_xe_device(man->bdev); + int ret, idx; + + if (!drm_dev_enter(&xe->drm, &idx)) + return -ENODEV; + + ret = ttm_resource_manager_dmem_reclaim(pool, target_bytes, priv); + + drm_dev_exit(idx); + return ret; +} + +static const struct dmem_cgroup_ops xe_ttm_vram_mgr_dmem_ops = { + .reclaim = xe_ttm_vram_mgr_dmem_reclaim, +}; + static void xe_ttm_vram_mgr_fini(struct drm_device *dev, void *arg) { struct xe_device *xe = to_xe_device(dev); @@ -301,17 +323,10 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr, u64 default_page_size) { struct ttm_resource_manager *man = &mgr->manager; + struct dmem_cgroup_region *cg; const char *name; int err; - name = mem_type == XE_PL_VRAM0 ? "vram0" : "vram1"; - man->cg = drmm_cgroup_register_region(&xe->drm, name, - &(struct dmem_cgroup_init){ - .size = size, - }); - if (IS_ERR(man->cg)) - return PTR_ERR(man->cg); - man->func = &xe_ttm_vram_mgr_func; mgr->mem_type = mem_type; err = drmm_mutex_init(&xe->drm, &mgr->lock); @@ -330,7 +345,28 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr, ttm_set_driver_manager(&xe->ttm, mem_type, &mgr->manager); ttm_resource_manager_set_used(&mgr->manager, true); - return drmm_add_action_or_reset(&xe->drm, xe_ttm_vram_mgr_fini, mgr); + /* + * Register the fini action before the cgroup region so that devres + * LIFO teardown runs unregister_region first (draining any in-flight + * reclaim callbacks) and the manager fini second. + */ + err = drmm_add_action_or_reset(&xe->drm, xe_ttm_vram_mgr_fini, mgr); + if (err) + return err; + + name = mem_type == XE_PL_VRAM0 ? "vram0" : "vram1"; + cg = drmm_cgroup_register_region(&xe->drm, name, + &(struct dmem_cgroup_init){ + .size = size, + .ops = &xe_ttm_vram_mgr_dmem_ops, + .reclaim_priv = man, + }); + if (IS_ERR(cg)) + return PTR_ERR(cg); + + ttm_resource_manager_set_dmem_region(man, cg); + + return 0; } /** -- 2.54.0
