kmemcg: account certain kmem allocations to memcg

Mark those kmem allocations that are known to be easily triggered from
userspace as __GFP_ACCOUNT/SLAB_ACCOUNT, which makes them accounted to
memcg.  For the list, see below:

 - threadinfo
 - task_struct
 - task_delay_info
 - pid
 - cred
 - mm_struct
 - vm_area_struct and vm_region (nommu)
 - anon_vma and anon_vma_chain
 - signal_struct
 - sighand_struct
 - fs_struct
 - files_struct
 - fdtable and fdtable->full_fds_bits
 - dentry and external_name
 - inode for all filesystems. This is the most tedious part, because
   most filesystems overwrite the alloc_inode method.

The list is far from complete, so feel free to add more objects.
Nevertheless, it should be close to "account everything" approach and
keep most workloads within bounds.  Malevolent users will be able to
breach the limit, but this was possible even with the former "account
everything" approach (simply because it did not account everything in
fact).

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Greg Thelen <gthelen@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 17 insertions, 13 deletions

diff --git a/kernel/cred.c b/kernel/cred.c
index 71179a0..0c0cd8a 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -569,8 +569,8 @@ EXPORT_SYMBOL(revert_creds);
 void __init cred_init(void)
 {
 	/* allocate a slab in which we can store credentials */
-	cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred),
-				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), 0,
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
 }
 
 /**
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index ef90b04..435c14a 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -34,7 +34,7 @@ __setup("nodelayacct", delayacct_setup_disable);
 
 void delayacct_init(void)
 {
-	delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC);
+	delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT);
 	delayacct_tsk_init(&init_task);
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 6774e6b..5191584 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -300,9 +300,9 @@ void __init fork_init(void)
 #define ARCH_MIN_TASKALIGN	L1_CACHE_BYTES
 #endif
 	/* create a slab on which task_structs can be allocated */
-	task_struct_cachep =
-		kmem_cache_create("task_struct", arch_task_struct_size,
-			ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL);
+	task_struct_cachep = kmem_cache_create("task_struct",
+			arch_task_struct_size, ARCH_MIN_TASKALIGN,
+			SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL);
 #endif
 
 	/* do the arch specific task caches init */
@@ -1848,16 +1848,19 @@ void __init proc_caches_init(void)
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU|
-			SLAB_NOTRACK, sighand_ctor);
+			SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor);
 	signal_cachep = kmem_cache_create("signal_cache",
 			sizeof(struct signal_struct), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT,
+			NULL);
 	files_cachep = kmem_cache_create("files_cache",
 			sizeof(struct files_struct), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT,
+			NULL);
 	fs_cachep = kmem_cache_create("fs_cache",
 			sizeof(struct fs_struct), 0,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT,
+			NULL);
 	/*
 	 * FIXME! The "sizeof(struct mm_struct)" currently includes the
 	 * whole struct cpumask for the OFFSTACK case. We could change
@@ -1867,8 +1870,9 @@ void __init proc_caches_init(void)
 	 */
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
-			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
-	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
+			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT,
+			NULL);
+	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
 	mmap_init();
 	nsproxy_cache_init();
 }
diff --git a/kernel/pid.c b/kernel/pid.c
index 78b3d9f..f4ad91b 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -604,5 +604,5 @@ void __init pidmap_init(void)
 	atomic_dec(&init_pid_ns.pidmap[0].nr_free);
 
 	init_pid_ns.pid_cachep = KMEM_CACHE(pid,
-			SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+			SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
 }