public inbox for cgroups@vger.kernel.org
 help / color / mirror / Atom feed
From: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
To: intel-xe@lists.freedesktop.org
Cc: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
	"Natalie Vock" <natalie.vock@gmx.de>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	"Tejun Heo" <tj@kernel.org>, "Michal Koutný" <mkoutny@suse.com>,
	cgroups@vger.kernel.org, "Huang Rui" <ray.huang@amd.com>,
	"Matthew Brost" <matthew.brost@intel.com>,
	"Matthew Auld" <matthew.auld@intel.com>,
	"Maarten Lankhorst" <maarten.lankhorst@linux.intel.com>,
	"Maxime Ripard" <mripard@kernel.org>,
	"Thomas Zimmermann" <tzimmermann@suse.de>,
	"Simona Vetter" <simona@ffwll.ch>,
	"David Airlie" <airlied@gmail.com>,
	"Christian König" <christian.koenig@amd.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
	dri-devel@lists.freedesktop.org, amd-gfx@lists.freedesktop.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH 3/5] drm/ttm: Hook up a cgroup-aware reclaim callback for the dmem controller
Date: Fri, 27 Mar 2026 09:15:58 +0100	[thread overview]
Message-ID: <20260327081600.4885-4-thomas.hellstrom@linux.intel.com> (raw)
In-Reply-To: <20260327081600.4885-1-thomas.hellstrom@linux.intel.com>

Add ttm_bo_evict_cgroup() to evict buffer objects charged to a specific
dmem cgroup pool from a resource manager's LRU until a byte target is
met.  Add ttm_resource_manager_set_dmem_region() to register the TTM
eviction path as the reclaim callback for a dmem cgroup region.

The eviction context is interruptible; signals abort the operation and
propagate back through the write() syscall.

Introduce a new mode for the bo LRU walker so that sleeping locks
can be taken. This can be used when the caller doesn't hold any
previous dma_resv locks, and where it intends to hold at most
one lock at a time.

Like the rest of the TTM eviction this should sooner than later
be converted to full WW transactions.

Assisted-by: GitHub Copilot:claude-sonnet-4.6
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c       | 95 +++++++++++++++++++++++++++++-
 drivers/gpu/drm/ttm/ttm_bo_util.c  |  3 +-
 drivers/gpu/drm/ttm/ttm_resource.c | 36 +++++++++++
 include/drm/ttm/ttm_bo.h           | 10 ++++
 include/drm/ttm/ttm_resource.h     |  4 ++
 5 files changed, 144 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index d85f0a37ac35..1745557c184c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -515,12 +515,20 @@ static s64 ttm_bo_evict_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *
 {
 	struct ttm_bo_evict_walk *evict_walk =
 		container_of(walk, typeof(*evict_walk), walk);
+	/* Capture size before eviction in case res is cleared. */
+	s64 bo_size = bo->base.size;
 	s64 lret;
 
 	if (!dmem_cgroup_state_evict_valuable(evict_walk->limit_pool, bo->resource->css,
 					      evict_walk->try_low, &evict_walk->hit_low))
 		return 0;
 
+	/*
+	 * evict_walk->place is NULL in cgroup drain mode.  Drivers'
+	 * eviction_valuable() callbacks must handle a NULL place, treating it
+	 * as "any placement": the TTM base implementation already does so via
+	 * ttm_resource_intersects().
+	 */
 	if (bo->pin_count || !bo->bdev->funcs->eviction_valuable(bo, evict_walk->place))
 		return 0;
 
@@ -536,11 +544,15 @@ static s64 ttm_bo_evict_cb(struct ttm_lru_walk *walk, struct ttm_buffer_object *
 		goto out;
 
 	evict_walk->evicted++;
-	if (evict_walk->res)
+	if (evict_walk->res) {
 		lret = ttm_resource_alloc(evict_walk->evictor, evict_walk->place,
 					  evict_walk->res, NULL);
-	if (lret == 0)
-		return 1;
+		if (lret == 0)
+			return 1;
+	} else {
+		/* Cgroup drain: return bytes freed for byte-denominated progress. */
+		return bo_size;
+	}
 out:
 	/* Errors that should terminate the walk. */
 	if (lret == -ENOSPC)
@@ -614,6 +626,83 @@ static int ttm_bo_evict_alloc(struct ttm_device *bdev,
 	return 0;
 }
 
+/**
+ * ttm_bo_evict_cgroup - Evict buffer objects charged to a specific cgroup.
+ * @bdev: The TTM device.
+ * @man: The resource manager whose LRU to walk.
+ * @limit_pool: The cgroup pool state whose members should be evicted.
+ * @target_bytes: Number of bytes to free.
+ * @ctx: The TTM operation context.
+ *
+ * Walk the LRU of @man and evict buffer objects that are charged to the
+ * cgroup identified by @limit_pool, until at least @target_bytes have been
+ * freed.  Mirrors the two-pass (trylock -> sleeping-lock, low-watermark)
+ * strategy used by ttm_bo_evict_alloc().
+ *
+ * Return: >= @target_bytes on full success, 0..target_bytes-1 if partial,
+ *         negative error code on fatal error.
+ */
+s64 ttm_bo_evict_cgroup(struct ttm_device *bdev,
+			struct ttm_resource_manager *man,
+			struct dmem_cgroup_pool_state *limit_pool,
+			s64 target_bytes,
+			struct ttm_operation_ctx *ctx)
+{
+	struct ttm_bo_evict_walk evict_walk = {
+		.walk = {
+			.ops = &ttm_evict_walk_ops,
+			.arg = { .ctx = ctx },
+		},
+		.limit_pool = limit_pool,
+		/* place, evictor, res left NULL: selects cgroup drain mode */
+	};
+	s64 lret, pass;
+
+	evict_walk.walk.arg.trylock_only = true;
+	lret = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man, target_bytes);
+	if (lret < 0 || lret >= target_bytes)
+		return lret;
+
+	/* Second pass: also evict BOs at the low watermark. */
+	if (evict_walk.hit_low) {
+		evict_walk.try_low = true;
+		pass = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man,
+					      target_bytes - lret);
+		if (pass < 0)
+			return pass;
+		lret += pass;
+		if (lret >= target_bytes)
+			return lret;
+	}
+
+	/* Full sleeping-lock pass for remaining target. */
+	evict_walk.try_low = evict_walk.hit_low = false;
+	evict_walk.walk.arg.trylock_only = false;
+
+retry:
+	evict_walk.walk.arg.sleeping_lock = true;
+	do {
+		evict_walk.evicted = 0;
+		pass = ttm_lru_walk_for_evict(&evict_walk.walk, bdev, man,
+					      target_bytes - lret);
+		if (pass < 0) {
+			lret = pass;
+			goto out;
+		}
+		lret += pass;
+	} while (lret < target_bytes && evict_walk.evicted);
+
+	/* One more attempt if we hit the low limit during sleeping-lock pass. */
+	if (lret < target_bytes && evict_walk.hit_low && !evict_walk.try_low) {
+		evict_walk.try_low = true;
+		goto retry;
+	}
+
+out:
+	return lret;
+}
+EXPORT_SYMBOL(ttm_bo_evict_cgroup);
+
 /**
  * ttm_bo_pin - Pin the buffer object.
  * @bo: The buffer object to pin
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index f83b7d5ec6c6..81c6a674c462 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -999,7 +999,8 @@ __ttm_bo_lru_cursor_next(struct ttm_bo_lru_cursor *curs)
 		bo = res->bo;
 		if (ttm_lru_walk_trylock(curs, bo))
 			bo_locked = true;
-		else if (!arg->ticket || arg->ctx->no_wait_gpu || arg->trylock_only)
+		else if ((!arg->ticket && !arg->sleeping_lock) || arg->ctx->no_wait_gpu ||
+			 arg->trylock_only)
 			continue;
 
 		if (!ttm_bo_get_unless_zero(bo)) {
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 9f36631d48b6..936552f426a7 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -937,3 +937,39 @@ void ttm_resource_manager_create_debugfs(struct ttm_resource_manager *man,
 #endif
 }
 EXPORT_SYMBOL(ttm_resource_manager_create_debugfs);
+
+static int ttm_resource_manager_dmem_reclaim(struct dmem_cgroup_pool_state *pool,
+					     u64 target_bytes, void *priv)
+{
+	struct ttm_resource_manager *man = priv;
+	struct ttm_operation_ctx ctx = { .interruptible = true };
+	s64 freed;
+
+	freed = ttm_bo_evict_cgroup(man->bdev, man, pool, target_bytes, &ctx);
+	if (freed < 0)
+		return freed;
+
+	return freed >= (s64)target_bytes ? 0 : -ENOSPC;
+}
+
+/**
+ * ttm_resource_manager_set_dmem_region - Associate a dmem cgroup region with a
+ *                                        resource manager and register a reclaim
+ *                                        callback.
+ * @man: The resource manager.
+ * @region: The dmem cgroup region to associate, may be NULL or IS_ERR().
+ *
+ * Sets @man->cg and registers ttm_resource_manager_dmem_reclaim() so that
+ * writing to dmem.max below current usage triggers TTM eviction rather than
+ * returning -EBUSY to userspace.
+ */
+void ttm_resource_manager_set_dmem_region(struct ttm_resource_manager *man,
+					  struct dmem_cgroup_region *region)
+{
+	man->cg = region;
+	if (!IS_ERR_OR_NULL(region))
+		dmem_cgroup_region_set_reclaim(region,
+					       ttm_resource_manager_dmem_reclaim,
+					       man);
+}
+EXPORT_SYMBOL(ttm_resource_manager_set_dmem_region);
diff --git a/include/drm/ttm/ttm_bo.h b/include/drm/ttm/ttm_bo.h
index 8310bc3d55f9..32791c4db2a9 100644
--- a/include/drm/ttm/ttm_bo.h
+++ b/include/drm/ttm/ttm_bo.h
@@ -226,6 +226,11 @@ struct ttm_lru_walk_arg {
 	struct ww_acquire_ctx *ticket;
 	/** @trylock_only: Only use trylock for locking. */
 	bool trylock_only;
+	/**
+	 * @sleeping_lock: Use sleeping locks even with %NULL @ticket.
+	 * @trylock_only has precedence over this field.
+	 */
+	bool sleeping_lock;
 };
 
 /**
@@ -431,6 +436,11 @@ void ttm_bo_unpin(struct ttm_buffer_object *bo);
 int ttm_bo_evict_first(struct ttm_device *bdev,
 		       struct ttm_resource_manager *man,
 		       struct ttm_operation_ctx *ctx);
+s64 ttm_bo_evict_cgroup(struct ttm_device *bdev,
+			struct ttm_resource_manager *man,
+			struct dmem_cgroup_pool_state *limit_pool,
+			s64 target_bytes,
+			struct ttm_operation_ctx *ctx);
 int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset,
 		  void *buf, int len, int write);
 vm_fault_t ttm_bo_vm_reserve(struct ttm_buffer_object *bo,
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index 33e80f30b8b8..c187e6c8b871 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -39,6 +39,7 @@
 
 struct dentry;
 struct dmem_cgroup_device;
+struct dmem_cgroup_region;
 struct drm_printer;
 struct ttm_device;
 struct ttm_resource_manager;
@@ -475,6 +476,9 @@ void ttm_resource_manager_init(struct ttm_resource_manager *man,
 			       struct ttm_device *bdev,
 			       uint64_t size);
 
+void ttm_resource_manager_set_dmem_region(struct ttm_resource_manager *man,
+					  struct dmem_cgroup_region *region);
+
 int ttm_resource_manager_evict_all(struct ttm_device *bdev,
 				   struct ttm_resource_manager *man);
 
-- 
2.53.0


  parent reply	other threads:[~2026-03-27  8:16 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-27  8:15 [PATCH 0/5] Add reclaim to the dmem cgroup controller Thomas Hellström
2026-03-27  8:15 ` [PATCH 1/5] cgroup/dmem: Return error when setting max below current usage Thomas Hellström
2026-03-27  8:15 ` [PATCH 2/5] cgroup/dmem: Add reclaim callback for lowering " Thomas Hellström
2026-03-27  8:15 ` Thomas Hellström [this message]
2026-03-27  8:15 ` [PATCH 4/5] drm/xe: Wire up dmem cgroup reclaim for VRAM manager Thomas Hellström
2026-03-27  8:16 ` [PATCH 5/5] drm/amdgpu: " Thomas Hellström
2026-03-27  8:33 ` [PATCH 0/5] Add reclaim to the dmem cgroup controller Thomas Hellström

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260327081600.4885-4-thomas.hellstrom@linux.intel.com \
    --to=thomas.hellstrom@linux.intel.com \
    --cc=airlied@gmail.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=cgroups@vger.kernel.org \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hannes@cmpxchg.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maarten.lankhorst@linux.intel.com \
    --cc=matthew.auld@intel.com \
    --cc=matthew.brost@intel.com \
    --cc=mkoutny@suse.com \
    --cc=mripard@kernel.org \
    --cc=natalie.vock@gmx.de \
    --cc=ray.huang@amd.com \
    --cc=rodrigo.vivi@intel.com \
    --cc=simona@ffwll.ch \
    --cc=tj@kernel.org \
    --cc=tzimmermann@suse.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox