[PATCH 2/4] mm: support nesting memalloc_use_memcg()
From: Dan Schatzberg
Date: Thu May 28 2020 - 09:55:28 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 +++++++++-------------------
4 files changed, 18 insertions(+), 26 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index a60f60396cfa..585416dec6a2 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -851,13 +851,13 @@ 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;
@@ -876,7 +876,7 @@ 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 5435a40f82be..6b869d95bfb6 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -353,6 +353,7 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
gfp_t gfp = GFP_KERNEL_ACCOUNT;
struct inode *id = fanotify_fid_inode(inode, mask, data, data_type);
const struct path *path = fsnotify_data_path(data, data_type);
+ struct mem_cgroup *old_memcg;
/*
* For queues with unlimited length lost events are not expected and
@@ -366,7 +367,7 @@ 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)) {
struct fanotify_perm_event *pevent;
@@ -451,7 +452,7 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group,
}
}
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 2ebc89047153..52f38e6e81b7 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -69,6 +69,7 @@ int inotify_handle_event(struct fsnotify_group *group,
int ret;
int len = 0;
int alloc_len = sizeof(struct inotify_event_info);
+ struct mem_cgroup *old_memcg;
if (WARN_ON(fsnotify_iter_vfsmount_mark(iter_info)))
return 0;
@@ -93,9 +94,9 @@ int inotify_handle_event(struct fsnotify_group *group,
* 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 c49257a3b510..95e8bfb0cab1 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -316,31 +316,21 @@ 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
--
2.24.1