linux-kernel - [PATCH 1/4] memcg: Track exported dma-buffers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230109213809.418135-2-tjmercier@google.com>
Date:   Mon,  9 Jan 2023 21:38:04 +0000
From:   "T.J. Mercier" <tjmercier@...gle.com>
To:     tjmercier@...gle.com, Tejun Heo <tj@...nel.org>,
        Zefan Li <lizefan.x@...edance.com>,
        Johannes Weiner <hannes@...xchg.org>,
        Jonathan Corbet <corbet@....net>,
        Sumit Semwal <sumit.semwal@...aro.org>,
        "Christian König" <christian.koenig@....com>,
        Michal Hocko <mhocko@...nel.org>,
        Roman Gushchin <roman.gushchin@...ux.dev>,
        Shakeel Butt <shakeelb@...gle.com>,
        Muchun Song <muchun.song@...ux.dev>,
        Andrew Morton <akpm@...ux-foundation.org>
Cc:     daniel.vetter@...ll.ch, android-mm@...gle.com, jstultz@...gle.com,
        cgroups@...r.kernel.org, linux-doc@...r.kernel.org,
        linux-kernel@...r.kernel.org, linux-media@...r.kernel.org,
        dri-devel@...ts.freedesktop.org, linaro-mm-sig@...ts.linaro.org,
        linux-mm@...ck.org
Subject: [PATCH 1/4] memcg: Track exported dma-buffers

When a buffer is exported to userspace, use memcg to attribute the
buffer to the allocating cgroup until all buffer references are
released.

Unlike the dmabuf sysfs stats implementation, this memcg accounting
avoids contention over the kernfs_rwsem incurred when creating or
removing nodes.

Signed-off-by: T.J. Mercier <tjmercier@...gle.com>
---
 Documentation/admin-guide/cgroup-v2.rst | 4 ++++
 drivers/dma-buf/dma-buf.c               | 5 +++++
 include/linux/dma-buf.h                 | 3 +++
 include/linux/memcontrol.h              | 1 +
 mm/memcontrol.c                         | 4 ++++
 5 files changed, 17 insertions(+)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index c8ae7c897f14..538ae22bc514 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1455,6 +1455,10 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used for storing in-kernel data
 		structures.
 
+	  dmabuf (npn)
+		Amount of memory used for exported DMA buffers allocated by the cgroup.
+		Stays with the allocating cgroup regardless of how the buffer is shared.
+
 	  workingset_refault_anon
 		Number of refaults of previously evicted anonymous pages.
 
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index e6528767efc7..ac45dd101c4d 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -75,6 +75,8 @@ static void dma_buf_release(struct dentry *dentry)
 	 */
 	BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active);
 
+	mod_memcg_state(dmabuf->memcg, MEMCG_DMABUF, -dmabuf->size);
+	mem_cgroup_put(dmabuf->memcg);
 	dma_buf_stats_teardown(dmabuf);
 	dmabuf->ops->release(dmabuf);
 
@@ -673,6 +675,9 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 	if (ret)
 		goto err_dmabuf;
 
+	dmabuf->memcg = get_mem_cgroup_from_mm(current->mm);
+	mod_memcg_state(dmabuf->memcg, MEMCG_DMABUF, dmabuf->size);
+
 	file->private_data = dmabuf;
 	file->f_path.dentry->d_fsdata = dmabuf;
 	dmabuf->file = file;
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 6fa8d4e29719..1f0ffb8e4bf5 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/dma-fence.h>
 #include <linux/wait.h>
+#include <linux/memcontrol.h>
 
 struct device;
 struct dma_buf;
@@ -446,6 +447,8 @@ struct dma_buf {
 		struct dma_buf *dmabuf;
 	} *sysfs_entry;
 #endif
+	/* The cgroup to which this buffer is currently attributed */
+	struct mem_cgroup *memcg;
 };
 
 /**
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d3c8203cab6c..1c1da2da20a6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -37,6 +37,7 @@ enum memcg_stat_item {
 	MEMCG_KMEM,
 	MEMCG_ZSWAP_B,
 	MEMCG_ZSWAPPED,
+	MEMCG_DMABUF,
 	MEMCG_NR_STAT,
 };
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ab457f0394ab..680189bec7e0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1502,6 +1502,7 @@ static const struct memory_stat memory_stats[] = {
 	{ "unevictable",		NR_UNEVICTABLE			},
 	{ "slab_reclaimable",		NR_SLAB_RECLAIMABLE_B		},
 	{ "slab_unreclaimable",		NR_SLAB_UNRECLAIMABLE_B		},
+	{ "dmabuf",			MEMCG_DMABUF			},
 
 	/* The memory events */
 	{ "workingset_refault_anon",	WORKINGSET_REFAULT_ANON		},
@@ -1519,6 +1520,7 @@ static int memcg_page_state_unit(int item)
 	switch (item) {
 	case MEMCG_PERCPU_B:
 	case MEMCG_ZSWAP_B:
+	case MEMCG_DMABUF:
 	case NR_SLAB_RECLAIMABLE_B:
 	case NR_SLAB_UNRECLAIMABLE_B:
 	case WORKINGSET_REFAULT_ANON:
@@ -4042,6 +4044,7 @@ static const unsigned int memcg1_stats[] = {
 	WORKINGSET_REFAULT_ANON,
 	WORKINGSET_REFAULT_FILE,
 	MEMCG_SWAP,
+	MEMCG_DMABUF,
 };
 
 static const char *const memcg1_stat_names[] = {
@@ -4057,6 +4060,7 @@ static const char *const memcg1_stat_names[] = {
 	"workingset_refault_anon",
 	"workingset_refault_file",
 	"swap",
+	"dmabuf",
 };
 
 /* Universal VM events cgroup1 shows, original sort order */
-- 
2.39.0.314.g84b9a713c41-goog