fs: fsnotify: account fsnotify metadata to kmemcg

Patch series "Directed kmem charging", v8.

The Linux kernel's memory cgroup allows limiting the memory usage of the
jobs running on the system to provide isolation between the jobs.  All
the kernel memory allocated in the context of the job and marked with
__GFP_ACCOUNT will also be included in the memory usage and be limited
by the job's limit.

The kernel memory can only be charged to the memcg of the process in
whose context kernel memory was allocated.  However there are cases
where the allocated kernel memory should be charged to the memcg
different from the current processes's memcg.  This patch series
contains two such concrete use-cases i.e.  fsnotify and buffer_head.

The fsnotify event objects can consume a lot of system memory for large
or unlimited queues if there is either no or slow listener.  The events
are allocated in the context of the event producer.  However they should
be charged to the event consumer.  Similarly the buffer_head objects can
be allocated in a memcg different from the memcg of the page for which
buffer_head objects are being allocated.

To solve this issue, this patch series introduces mechanism to charge
kernel memory to a given memcg.  In case of fsnotify events, the memcg
of the consumer can be used for charging and for buffer_head, the memcg
of the page can be charged.  For directed charging, the caller can use
the scope API memalloc_[un]use_memcg() to specify the memcg to charge
for all the __GFP_ACCOUNT allocations within the scope.

This patch (of 2):

A lot of memory can be consumed by the events generated for the huge or
unlimited queues if there is either no or slow listener.  This can cause
system level memory pressure or OOMs.  So, it's better to account the
fsnotify kmem caches to the memcg of the listener.

However the listener can be in a different memcg than the memcg of the
producer and these allocations happen in the context of the event
producer.  This patch introduces remote memcg charging API which the
producer can use to charge the allocations to the memcg of the listener.

There are seven fsnotify kmem caches and among them allocations from
dnotify_struct_cache, dnotify_mark_cache, fanotify_mark_cache and
inotify_inode_mark_cachep happens in the context of syscall from the
listener.  So, SLAB_ACCOUNT is enough for these caches.

The objects from fsnotify_mark_connector_cachep are not accounted as
they are small compared to the notification mark or events and it is
unclear whom to account connector to since it is shared by all events
attached to the inode.

The allocations from the event caches happen in the context of the event
producer.  For such caches we will need to remote charge the allocations
to the listener's memcg.  Thus we save the memcg reference in the
fsnotify_group structure of the listener.

This patch has also moved the members of fsnotify_group to keep the size
same, at least for 64 bit build, even with additional member by filling
the holes.

[shakeelb@google.com: use GFP_KERNEL_ACCOUNT rather than open-coding it]
  Link: http://lkml.kernel.org/r/20180702215439.211597-1-shakeelb@google.com
Link: http://lkml.kernel.org/r/20180627191250.209150-2-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 30 insertions, 9 deletions

diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index e2bea2ac5dfb..a6365e6bc047 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -384,8 +384,9 @@ out_err:
 
 static int __init dnotify_init(void)
 {
-	dnotify_struct_cache = KMEM_CACHE(dnotify_struct, SLAB_PANIC);
-	dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC);
+	dnotify_struct_cache = KMEM_CACHE(dnotify_struct,
+					  SLAB_PANIC|SLAB_ACCOUNT);
+	dnotify_mark_cache = KMEM_CACHE(dnotify_mark, SLAB_PANIC|SLAB_ACCOUNT);
 
 	dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops);
 	if (IS_ERR(dnotify_group))
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index f90842efea13..eb4e75175cfb 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 #include <linux/audit.h>
+#include <linux/sched/mm.h>
 
 #include "fanotify.h"
 
@@ -140,8 +141,8 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
 						 struct inode *inode, u32 mask,
 						 const struct path *path)
 {
-	struct fanotify_event_info *event;
-	gfp_t gfp = GFP_KERNEL;
+	struct fanotify_event_info *event = NULL;
+	gfp_t gfp = GFP_KERNEL_ACCOUNT;
 
 	/*
 	 * For queues with unlimited length lost events are not expected and
@@ -151,19 +152,22 @@ struct fanotify_event_info *fanotify_alloc_event(struct fsnotify_group *group,
 	if (group->max_events == UINT_MAX)
 		gfp |= __GFP_NOFAIL;
 
+	/* Whoever is interested in the event, pays for the allocation. */
+	memalloc_use_memcg(group->memcg);
+
 	if (fanotify_is_perm_event(mask)) {
 		struct fanotify_perm_event_info *pevent;
 
 		pevent = kmem_cache_alloc(fanotify_perm_event_cachep, gfp);
 		if (!pevent)
-			return NULL;
+			goto out;
 		event = &pevent->fae;
 		pevent->response = 0;
 		goto init;
 	}
 	event = kmem_cache_alloc(fanotify_event_cachep, gfp);
 	if (!event)
-		return NULL;
+		goto out;
 init: __maybe_unused
 	fsnotify_init_event(&event->fse, inode, mask);
 	event->tgid = get_pid(task_tgid(current));
@@ -174,6 +178,8 @@ init: __maybe_unused
 		event->path.mnt = NULL;
 		event->path.dentry = NULL;
 	}
+out:
+	memalloc_unuse_memcg();
 	return event;
 }
 
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index ec4d8c59d0e3..0cf45041dc32 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -16,6 +16,7 @@
 #include <linux/uaccess.h>
 #include <linux/compat.h>
 #include <linux/sched/signal.h>
+#include <linux/memcontrol.h>
 
 #include <asm/ioctls.h>
 
@@ -756,6 +757,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
+	group->memcg = get_mem_cgroup_from_mm(current->mm);
 
 	oevent = fanotify_alloc_event(group, NULL, FS_Q_OVERFLOW, NULL);
 	if (unlikely(!oevent)) {
@@ -957,7 +959,8 @@ COMPAT_SYSCALL_DEFINE6(fanotify_mark,
  */
 static int __init fanotify_user_setup(void)
 {
-	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, SLAB_PANIC);
+	fanotify_mark_cache = KMEM_CACHE(fsnotify_mark,
+					 SLAB_PANIC|SLAB_ACCOUNT);
 	fanotify_event_cachep = KMEM_CACHE(fanotify_event_info, SLAB_PANIC);
 	if (IS_ENABLED(CONFIG_FANOTIFY_ACCESS_PERMISSIONS)) {
 		fanotify_perm_event_cachep =
diff --git a/fs/notify/group.c b/fs/notify/group.c
index aa5468f23e45..c03b83662876 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -22,6 +22,7 @@
 #include <linux/srcu.h>
 #include <linux/rculist.h>
 #include <linux/wait.h>
+#include <linux/memcontrol.h>
 
 #include <linux/fsnotify_backend.h>
 #include "fsnotify.h"
@@ -36,6 +37,8 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
 	if (group->ops->free_group_priv)
 		group->ops->free_group_priv(group);
 
+	mem_cgroup_put(group->memcg);
+
 	kfree(group);
 }
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 9ab6dde38a14..f4184b4f3815 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -31,6 +31,7 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/sched/user.h>
+#include <linux/sched/mm.h>
 
 #include "inotify.h"
 
@@ -98,7 +99,11 @@ int inotify_handle_event(struct fsnotify_group *group,
 	i_mark = container_of(inode_mark, struct inotify_inode_mark,
 			      fsn_mark);
 
-	event = kmalloc(alloc_len, GFP_KERNEL);
+	/* Whoever is interested in the event, pays for the allocation. */
+	memalloc_use_memcg(group->memcg);
+	event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT);
+	memalloc_unuse_memcg();
+
 	if (unlikely(!event)) {
 		/*
 		 * Treat lost event due to ENOMEM the same way as queue
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 1cf5b779d862..749c46ababa0 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -38,6 +38,7 @@
 #include <linux/uaccess.h>
 #include <linux/poll.h>
 #include <linux/wait.h>
+#include <linux/memcontrol.h>
 
 #include "inotify.h"
 #include "../fdinfo.h"
@@ -636,6 +637,7 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 	oevent->name_len = 0;
 
 	group->max_events = max_events;
+	group->memcg = get_mem_cgroup_from_mm(current->mm);
 
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
@@ -808,7 +810,8 @@ static int __init inotify_user_setup(void)
 
 	BUG_ON(hweight32(ALL_INOTIFY_BITS) != 21);
 
-	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC);
+	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark,
+					       SLAB_PANIC|SLAB_ACCOUNT);
 
 	inotify_max_queued_events = 16384;
 	init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;