From 28293c0845cb6c9615e1fe229ff01e73234ee672 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sat, 17 Oct 2020 16:13:40 -0700 Subject: [PATCH] BACKPORT: mm, memcg: rework remote charging API to support nesting Currently the remote memcg charging API consists of two functions: memalloc_use_memcg() and memalloc_unuse_memcg(), which set and clear the memcg value, which overwrites the memcg of the current task. memalloc_use_memcg(target_memcg); <...> memalloc_unuse_memcg(); It works perfectly for allocations performed from a normal context, however an attempt to call it from an interrupt context or just nest two remote charging blocks will lead to an incorrect accounting. On exit from the inner block the active memcg will be cleared instead of being restored. memalloc_use_memcg(target_memcg); memalloc_use_memcg(target_memcg_2); <...> memalloc_unuse_memcg(); Error: allocation here are charged to the memcg of the current process instead of target_memcg. memalloc_unuse_memcg(); This patch extends the remote charging API by switching to a single function: struct mem_cgroup *set_active_memcg(struct mem_cgroup *memcg), which sets the new value and returns the old one. So a remote charging block will look like: old_memcg = set_active_memcg(target_memcg); <...> set_active_memcg(old_memcg); This patch is heavily based on the patch by Johannes Weiner, which can be found here: https://lkml.org/lkml/2020/5/28/806 . Change-Id: I560f99ee032b96ef8bd19640c6b047380e1665a4 Signed-off-by: Roman Gushchin Signed-off-by: Andrew Morton Reviewed-by: Shakeel Butt Cc: Johannes Weiner Cc: Dan Schatzberg Link: https://lkml.kernel.org/r/20200821212056.3769116-1-guro@fb.com Signed-off-by: Linus Torvalds --- fs/buffer.c | 6 +++--- fs/notify/fanotify/fanotify.c | 4 ++-- fs/notify/inotify/inotify_fsnotify.c | 5 +++-- include/linux/sched/mm.h | 30 ++++++++++------------------ 4 files changed, 18 insertions(+), 27 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index 666c7561a1d4..f5d273e380f4 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -817,13 +817,13 @@ 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 = set_active_memcg(memcg); head = NULL; offset = PAGE_SIZE; @@ -842,7 +842,7 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, set_bh_page(bh, page, offset); } out: - memalloc_unuse_memcg(); + set_active_memcg(old_memcg); mem_cgroup_put(memcg); return head; /* diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index ca3405f73264..139e5a363e3d 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -160,7 +160,7 @@ struct fanotify_event_info *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 = set_active_memcg(group->memcg); if (fanotify_is_perm_event(mask)) { struct fanotify_perm_event_info *pevent; @@ -186,7 +186,7 @@ init: __maybe_unused event->path.dentry = NULL; } out: - memalloc_unuse_memcg(); + set_active_memcg(old_memcg); return event; } diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 16b8702af0e7..70a7e8f307ff 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -77,6 +77,7 @@ 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; @@ -104,9 +105,9 @@ 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 = set_active_memcg(group->memcg); event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); - memalloc_unuse_memcg(); + set_active_memcg(old_memcg); if (unlikely(!event)) { /* diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index ef54f4b3f1e4..bc53de16ae7d 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -280,38 +280,28 @@ static inline void memalloc_noreclaim_restore(unsigned int flags) #ifdef CONFIG_MEMCG /** - * memalloc_use_memcg - Starts the remote memcg charging scope. + * set_active_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __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 * +set_active_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 * +set_active_memcg(struct mem_cgroup *memcg) { + return NULL; } #endif