[PATCH 2/4] mm: support nesting memalloc_use_memcg()
From: Dan Schatzberg
Date: Mon Aug 24 2020 - 11:44:48 EST
From: Johannes Weiner <hannes@xxxxxxxxxxx>
The memalloc_use_memcg() function to override the default memcg
accounting context currently doesn't nest. But the patches to make the
loop driver cgroup-aware will end up nesting:
[ 98.137605] alloc_page_buffers+0x210/0x288
[ 98.141799] __getblk_gfp+0x1d4/0x400
[ 98.145475] ext4_read_block_bitmap_nowait+0x148/0xbc8
[ 98.150628] ext4_mb_init_cache+0x25c/0x9b0
[ 98.154821] ext4_mb_init_group+0x270/0x390
[ 98.159014] ext4_mb_good_group+0x264/0x270
[ 98.163208] ext4_mb_regular_allocator+0x480/0x798
[ 98.168011] ext4_mb_new_blocks+0x958/0x10f8
[ 98.172294] ext4_ext_map_blocks+0xec8/0x1618
[ 98.176660] ext4_map_blocks+0x1b8/0x8a0
[ 98.180592] ext4_writepages+0x830/0xf10
[ 98.184523] do_writepages+0xb4/0x198
[ 98.188195] __filemap_fdatawrite_range+0x170/0x1c8
[ 98.193086] filemap_write_and_wait_range+0x40/0xb0
[ 98.197974] ext4_punch_hole+0x4a4/0x660
[ 98.201907] ext4_fallocate+0x294/0x1190
[ 98.205839] loop_process_work+0x690/0x1100
[ 98.210032] loop_workfn+0x2c/0x110
[ 98.213529] process_one_work+0x3e0/0x648
[ 98.217546] worker_thread+0x70/0x670
[ 98.221217] kthread+0x1b8/0x1c0
[ 98.224452] ret_from_fork+0x10/0x18
where loop_process_work() sets the memcg override to the memcg that
submitted the IO request, and alloc_page_buffers() sets the override
to the memcg that instantiated the cache page, which may differ.
Make memalloc_use_memcg() return the old memcg and convert existing
users to a stacking model. Delete the unused memalloc_unuse_memcg().
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Acked-by: Roman Gushchin <guro@xxxxxx>
Reported-by: Naresh Kamboju <naresh.kamboju@xxxxxxxxxx>
---
fs/buffer.c | 6 +++---
fs/notify/fanotify/fanotify.c | 5 +++--
fs/notify/inotify/inotify_fsnotify.c | 5 +++--
include/linux/sched/mm.h | 28 +++++++++-------------------
mm/memcontrol.c | 6 +++---
5 files changed, 21 insertions(+), 29 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index d468ed9981e0..804170cb59fe 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -842,13 +842,13 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
struct buffer_head *bh, *head;
gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
long offset;
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg, *old_memcg;
if (retry)
gfp |= __GFP_NOFAIL;
memcg = get_mem_cgroup_from_page(page);
- memalloc_use_memcg(memcg);
+ old_memcg = memalloc_use_memcg(memcg);
head = NULL;
offset = PAGE_SIZE;
@@ -867,7 +867,7 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
set_bh_page(bh, page, offset);
}
out:
- memalloc_unuse_memcg();
+ memalloc_use_memcg(old_memcg);
mem_cgroup_put(memcg);
return head;
/*
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index c942910a8649..c8fd563e02a3 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -533,6 +533,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
struct inode *child = NULL;
bool name_event = false;
+ struct mem_cgroup *old_memcg;
if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) {
/*
@@ -580,7 +581,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
gfp |= __GFP_RETRY_MAYFAIL;
/* Whoever is interested in the event, pays for the allocation. */
- memalloc_use_memcg(group->memcg);
+ old_memcg = memalloc_use_memcg(group->memcg);
if (fanotify_is_perm_event(mask)) {
event = fanotify_alloc_perm_event(path, gfp);
@@ -608,7 +609,7 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
event->pid = get_pid(task_tgid(current));
out:
- memalloc_unuse_memcg();
+ memalloc_use_memcg(old_memcg);
return event;
}
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index a65cf8c9f600..8017a51561c4 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -66,6 +66,7 @@ static int inotify_one_event(struct fsnotify_group *group, u32 mask,
int ret;
int len = 0;
int alloc_len = sizeof(struct inotify_event_info);
+ struct mem_cgroup *old_memcg;
if ((inode_mark->mask & FS_EXCL_UNLINK) &&
path && d_unlinked(path->dentry))
@@ -87,9 +88,9 @@ static int inotify_one_event(struct fsnotify_group *group, u32 mask,
* trigger OOM killer in the target monitoring memcg as it may have
* security repercussion.
*/
- memalloc_use_memcg(group->memcg);
+ old_memcg = memalloc_use_memcg(group->memcg);
event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
- memalloc_unuse_memcg();
+ memalloc_use_memcg(old_memcg);
if (unlikely(!event)) {
/*
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index f889e332912f..b8fde48d44a9 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -312,31 +312,21 @@ static inline void memalloc_nocma_restore(unsigned int flags)
* __GFP_ACCOUNT allocations till the end of the scope will be charged to the
* given memcg.
*
- * NOTE: This function is not nesting safe.
+ * NOTE: This function can nest. Users must save the return value and
+ * reset the previous value after their own charging scope is over
*/
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
+static inline struct mem_cgroup *
+memalloc_use_memcg(struct mem_cgroup *memcg)
{
- WARN_ON_ONCE(current->active_memcg);
+ struct mem_cgroup *old = current->active_memcg;
current->active_memcg = memcg;
-}
-
-/**
- * memalloc_unuse_memcg - Ends the remote memcg charging scope.
- *
- * This function marks the end of the remote memcg charging scope started by
- * memalloc_use_memcg().
- */
-static inline void memalloc_unuse_memcg(void)
-{
- current->active_memcg = NULL;
+ return old;
}
#else
-static inline void memalloc_use_memcg(struct mem_cgroup *memcg)
-{
-}
-
-static inline void memalloc_unuse_memcg(void)
+static inline struct mem_cgroup *
+memalloc_use_memcg(struct mem_cgroup *memcg)
{
+ return NULL;
}
#endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b807952b4d43..b2468c80085d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5271,12 +5271,12 @@ static struct cgroup_subsys_state * __ref
mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct mem_cgroup *parent = mem_cgroup_from_css(parent_css);
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg, *old_memcg;
long error = -ENOMEM;
- memalloc_use_memcg(parent);
+ old_memcg = memalloc_use_memcg(parent);
memcg = mem_cgroup_alloc();
- memalloc_unuse_memcg();
+ memalloc_use_memcg(old_memcg);
if (IS_ERR(memcg))
return ERR_CAST(memcg);
--
2.24.1