linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Maarten Lankhorst <dev@lankhorst.se>
To: "Lucas De Marchi" <lucas.demarchi@intel.com>,
	"'Thomas Hellström'" <thomas.hellstrom@linux.intel.com>,
	"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
	"David Airlie" <airlied@gmail.com>,
	"Simona Vetter" <simona@ffwll.ch>,
	"Maarten Lankhorst" <dev@lankhorst.se>,
	"Maxime Ripard" <mripard@kernel.org>,
	"Natalie Vock" <natalie.vock@gmx.de>, "Tejun Heo" <tj@kernel.org>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	"'Michal Koutný'" <mkoutny@suse.com>,
	"Michal Hocko" <mhocko@kernel.org>,
	"Roman Gushchin" <roman.gushchin@linux.dev>,
	"Shakeel Butt" <shakeel.butt@linux.dev>,
	"Muchun Song" <muchun.song@linux.dev>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"David Hildenbrand" <david@redhat.com>,
	"Lorenzo Stoakes" <lorenzo.stoakes@oracle.com>,
	"'Liam R . Howlett'" <Liam.Howlett@oracle.com>,
	"Vlastimil Babka" <vbabka@suse.cz>,
	"Mike Rapoport" <rppt@kernel.org>,
	"Suren Baghdasaryan" <surenb@google.com>,
	"Thomas Zimmermann" <tzimmermann@suse.de>
Cc: Michal Hocko <mhocko@suse.com>,
	intel-xe@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
	linux-mm@kvack.org
Subject: [RFC 2/3] cgroup/dmem: Implement pinning device memory
Date: Tue, 19 Aug 2025 13:49:35 +0200	[thread overview]
Message-ID: <20250819114932.597600-7-dev@lankhorst.se> (raw)
In-Reply-To: <20250819114932.597600-5-dev@lankhorst.se>

Add a function to pin, and to unipn memory and adjust the calculations
in dmem_cgroup_state_evict_valuable().

Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 include/linux/cgroup_dmem.h |  2 ++
 kernel/cgroup/dmem.c        | 57 +++++++++++++++++++++++++++++++++++--
 2 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/include/linux/cgroup_dmem.h b/include/linux/cgroup_dmem.h
index dd4869f1d736e..a981bb692ba22 100644
--- a/include/linux/cgroup_dmem.h
+++ b/include/linux/cgroup_dmem.h
@@ -21,6 +21,8 @@ int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
 			   struct dmem_cgroup_pool_state **ret_pool,
 			   struct dmem_cgroup_pool_state **ret_limit_pool);
 void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size);
+int dmem_cgroup_try_pin(struct dmem_cgroup_pool_state *pool, u64 size);
+void dmem_cgroup_unpin(struct dmem_cgroup_pool_state *pool, u64 size);
 bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
 				      struct dmem_cgroup_pool_state *test_pool,
 				      bool ignore_low, bool *ret_hit_low);
diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c
index 10b63433f0573..ec8b1ffec78de 100644
--- a/kernel/cgroup/dmem.c
+++ b/kernel/cgroup/dmem.c
@@ -147,6 +147,11 @@ static u64 get_resource_current(struct dmem_cgroup_pool_state *pool)
 	return pool ? page_counter_read(&pool->cnt) : 0;
 }
 
+static u64 get_resource_pinned(struct dmem_cgroup_pool_state *pool)
+{
+	return pool ? page_counter_pinned(&pool->cnt) : 0;
+}
+
 static void reset_all_resource_limits(struct dmem_cgroup_pool_state *rpool)
 {
 	set_resource_min(rpool, 0);
@@ -270,7 +275,7 @@ bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
 {
 	struct dmem_cgroup_pool_state *pool = test_pool;
 	struct page_counter *ctest;
-	u64 used, min, low;
+	u64 used, min, low, pinned;
 
 	/* Can always evict from current pool, despite limits */
 	if (limit_pool == test_pool)
@@ -296,16 +301,18 @@ bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
 
 	ctest = &test_pool->cnt;
 
+	/* Protection is calculated without pinned memory */
 	dmem_cgroup_calculate_protection(limit_pool, test_pool);
 
 	used = page_counter_read(ctest);
-	min = READ_ONCE(ctest->emin);
+	pinned = page_counter_pinned(ctest);
+	min = READ_ONCE(ctest->emin) + pinned;
 
 	if (used <= min)
 		return false;
 
 	if (!ignore_low) {
-		low = READ_ONCE(ctest->elow);
+		low = READ_ONCE(ctest->elow) + pinned;
 		if (used > low)
 			return true;
 
@@ -641,6 +648,41 @@ int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
 }
 EXPORT_SYMBOL_GPL(dmem_cgroup_try_charge);
 
+/**
+ * dmem_cgroup_unpin() - Unpin from a pool.
+ * @pool: Pool to unpin.
+ * @size: Size to unpin.
+ *
+ * Undoes the effects of dmem_cgroup_try_pin.
+ * Must be called with the returned pool as argument,
+ * and same @index and @size.
+ */
+void dmem_cgroup_unpin(struct dmem_cgroup_pool_state *pool, u64 size)
+{
+	if (pool)
+		page_counter_unpin(&pool->cnt, size);
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_unpin);
+
+/**
+ * dmem_cgroup_try_pin() - Try pinning an existing allocation to a region.
+ * @pool: dmem region to pin
+ * @size: Size (in bytes) to pin.
+ *
+ * This function pins in @pool for a size of @size bytes.
+ *
+ * If the function succeeds, the memory is succesfully accounted as being pinned.
+ * The memory may not be uncharged before unpin is called.
+ *
+ * Return: 0 on success, -EAGAIN on hitting a limit, or a negative errno on failure.
+ */
+int dmem_cgroup_try_pin(struct dmem_cgroup_pool_state *pool, u64 size)
+{
+	return page_counter_try_pin(&pool->cnt, size) ? 0 : -EAGAIN;
+
+}
+EXPORT_SYMBOL_GPL(dmem_cgroup_try_pin);
+
 static int dmem_cgroup_region_capacity_show(struct seq_file *sf, void *v)
 {
 	struct dmem_cgroup_region *region;
@@ -756,6 +798,11 @@ static int dmem_cgroup_region_current_show(struct seq_file *sf, void *v)
 	return dmemcg_limit_show(sf, v, get_resource_current);
 }
 
+static int dmem_cgroup_region_pinned_show(struct seq_file *sf, void *v)
+{
+	return dmemcg_limit_show(sf, v, get_resource_pinned);
+}
+
 static int dmem_cgroup_region_min_show(struct seq_file *sf, void *v)
 {
 	return dmemcg_limit_show(sf, v, get_resource_min);
@@ -799,6 +846,10 @@ static struct cftype files[] = {
 		.name = "current",
 		.seq_show = dmem_cgroup_region_current_show,
 	},
+	{
+		.name = "pinned",
+		.seq_show = dmem_cgroup_region_pinned_show,
+	},
 	{
 		.name = "min",
 		.write = dmem_cgroup_region_min_write,
-- 
2.50.0



  parent reply	other threads:[~2025-08-19 11:49 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-19 11:49 [RFC 0/3] cgroups: Add support for pinned " Maarten Lankhorst
2025-08-19 11:49 ` [RFC 1/3] page_counter: Allow for pinning some amount of memory Maarten Lankhorst
2025-08-19 11:49 ` Maarten Lankhorst [this message]
2025-08-19 11:49 ` [RFC 3/3] drm/xe: Add DRM_XE_GEM_CREATE_FLAG_PINNED flag and implementation Maarten Lankhorst
2025-08-19 16:22   ` Thomas Hellström
2025-08-21 11:41     ` Maarten Lankhorst
2025-08-26 14:20 ` [RFC 0/3] cgroups: Add support for pinned device memory Michal Koutný
2025-08-28 20:58   ` Maarten Lankhorst
2025-09-01 12:25 ` David Hildenbrand
2025-09-01 18:16   ` Maarten Lankhorst
2025-09-01 18:21     ` Thomas Hellström
2025-09-01 18:38       ` David Hildenbrand
2025-09-02 13:42         ` Thomas Hellström
2025-09-04 15:02           ` Maarten Lankhorst
2025-09-01 12:45 ` Natalie Vock
2025-09-01 14:37   ` Thomas Hellström
2025-09-01 18:22   ` Maarten Lankhorst

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=20250819114932.597600-7-dev@lankhorst.se \
    --to=dev@lankhorst.se \
    --cc=Liam.Howlett@oracle.com \
    --cc=airlied@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=david@redhat.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=hannes@cmpxchg.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=lucas.demarchi@intel.com \
    --cc=mhocko@kernel.org \
    --cc=mhocko@suse.com \
    --cc=mkoutny@suse.com \
    --cc=mripard@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=natalie.vock@gmx.de \
    --cc=rodrigo.vivi@intel.com \
    --cc=roman.gushchin@linux.dev \
    --cc=rppt@kernel.org \
    --cc=shakeel.butt@linux.dev \
    --cc=simona@ffwll.ch \
    --cc=surenb@google.com \
    --cc=thomas.hellstrom@linux.intel.com \
    --cc=tj@kernel.org \
    --cc=tzimmermann@suse.de \
    --cc=vbabka@suse.cz \
    /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