1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
|
From 3f388a8ddc43b4f785797cccd7373cad7fd0ecd3 Mon Sep 17 00:00:00 2001
From: Vladimir Davydov <vdavydov@parallels.com>
Date: Fri, 8 Aug 2014 09:20:38 +0800
Subject: [PATCH 6/7] vm_cgroup: shared memory accounting
Taken from https://lkml.org/lkml/2014/7/3/409
Address space that contributes to memory overcommit consists of two
parts - private writable mappings and shared memory. This patch adds
shared memory accounting.
Each shmem inode holds a reference to the vm cgroup it is accounted to.
The reference is initialized with the current cgroup on shmem inode
creation and released only on shmem inode destruction. For simplicity,
shmem inodes accounted to a vm cgroup are not re-charged to the parent
on css offline yet, so offline cgroups will be hanging in memory until
all inodes accounted to it die.
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: He Zhe <zhe.he@windriver.com>
Signed-off-by: Bruce Ashfield <bruce.ashfield@windriver.com>
---
include/linux/shmem_fs.h | 6 ++++++
include/linux/vm_cgroup.h | 32 ++++++++++++++++++++++++++++++++
mm/shmem.c | 39 +++++++++++++++++++++++++++++++++------
mm/vm_cgroup.c | 36 ++++++++++++++++++++++++++++++++++++
4 files changed, 107 insertions(+), 6 deletions(-)
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 9d55438bc4ad..5097001c7be1 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -7,6 +7,8 @@
#include <linux/percpu_counter.h>
#include <linux/xattr.h>
+struct vm_cgroup;
+
/* inode in-kernel data */
struct shmem_inode_info {
@@ -21,6 +23,10 @@ struct shmem_inode_info {
struct list_head swaplist; /* chain of maybes on swap */
struct simple_xattrs xattrs; /* list of xattrs */
struct inode vfs_inode;
+#ifdef CONFIG_CGROUP_VM
+ struct vm_cgroup *vmcg; /* vm_cgroup this inode is
+ accounted to */
+#endif
};
struct shmem_sb_info {
diff --git a/include/linux/vm_cgroup.h b/include/linux/vm_cgroup.h
index c591d5c477ba..6f16b57567ae 100644
--- a/include/linux/vm_cgroup.h
+++ b/include/linux/vm_cgroup.h
@@ -2,6 +2,7 @@
#define _LINUX_VM_CGROUP_H
struct mm_struct;
+struct shmem_inode_info;
#ifdef CONFIG_CGROUP_VM
static inline bool vm_cgroup_disabled(void)
@@ -17,6 +18,16 @@ extern int vm_cgroup_charge_memory_mm(struct mm_struct *mm,
unsigned long nr_pages);
extern void vm_cgroup_uncharge_memory_mm(struct mm_struct *mm,
unsigned long nr_pages);
+
+#ifdef CONFIG_SHMEM
+extern void shmem_init_vm_cgroup(struct shmem_inode_info *info);
+extern void shmem_release_vm_cgroup(struct shmem_inode_info *info);
+extern int vm_cgroup_charge_shmem(struct shmem_inode_info *info,
+ unsigned long nr_pages);
+extern void vm_cgroup_uncharge_shmem(struct shmem_inode_info *info,
+ unsigned long nr_pages);
+#endif
+
#else /* !CONFIG_CGROUP_VM */
static inline bool vm_cgroup_disabled(void)
{
@@ -42,6 +53,27 @@ static inline void vm_cgroup_uncharge_memory_mm(struct mm_struct *mm,
unsigned long nr_pages)
{
}
+
+#ifdef CONFIG_SHMEM
+static inline void shmem_init_vm_cgroup(struct shmem_inode_info *info)
+{
+}
+
+static inline void shmem_release_vm_cgroup(struct shmem_inode_info *info)
+{
+}
+
+static inline int vm_cgroup_charge_shmem(struct shmem_inode_info *info,
+ unsigned long nr_pages)
+{
+}
+
+static inline void vm_cgroup_uncharge_shmem(struct shmem_inode_info *info,
+ unsigned long nr_pages)
+{
+}
+#endif
+
#endif /* CONFIG_CGROUP_VM */
#endif /* _LINUX_VM_CGROUP_H */
diff --git a/mm/shmem.c b/mm/shmem.c
index 0d0463497bcc..64c8b9a2a8cc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -66,6 +66,7 @@ static struct vfsmount *shm_mnt;
#include <linux/highmem.h>
#include <linux/seq_file.h>
#include <linux/magic.h>
+#include <linux/vm_cgroup.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -130,6 +131,27 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
return sb->s_fs_info;
}
+static inline int __shmem_acct_memory(struct shmem_inode_info *info,
+ long pages)
+{
+ int ret;
+
+ ret = vm_cgroup_charge_shmem(info, pages);
+ if (ret)
+ return ret;
+ ret = security_vm_enough_memory_mm(current->mm, pages);
+ if (ret)
+ vm_cgroup_uncharge_shmem(info, pages);
+ return ret;
+}
+
+static inline void __shmem_unacct_memory(struct shmem_inode_info *info,
+ long pages)
+{
+ vm_unacct_memory(pages);
+ vm_cgroup_uncharge_shmem(info, pages);
+}
+
/*
* shmem_file_setup pre-accounts the whole fixed size of a VM object,
* for shared memory and for shared anonymous (/dev/zero) mappings
@@ -141,7 +163,7 @@ static inline int shmem_acct_size(struct inode *inode)
struct shmem_inode_info *info = SHMEM_I(inode);
return (info->flags & VM_NORESERVE) ?
- 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(inode->i_size));
+ 0 : __shmem_acct_memory(info, VM_ACCT(inode->i_size));
}
static inline void shmem_unacct_size(struct inode *inode)
@@ -149,7 +171,7 @@ static inline void shmem_unacct_size(struct inode *inode)
struct shmem_inode_info *info = SHMEM_I(inode);
if (!(info->flags & VM_NORESERVE))
- vm_unacct_memory(VM_ACCT(inode->i_size));
+ __shmem_unacct_memory(info, VM_ACCT(inode->i_size));
}
/*
@@ -163,7 +185,7 @@ static inline int shmem_acct_block(struct inode *inode)
struct shmem_inode_info *info = SHMEM_I(inode);
return (info->flags & VM_NORESERVE) ?
- security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_CACHE_SIZE)) : 0;
+ __shmem_acct_memory(info, VM_ACCT(PAGE_CACHE_SIZE)) : 0;
}
static inline void shmem_unacct_blocks(struct inode *inode, long pages)
@@ -171,7 +193,7 @@ static inline void shmem_unacct_blocks(struct inode *inode, long pages)
struct shmem_inode_info *info = SHMEM_I(inode);
if (info->flags & VM_NORESERVE)
- vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
+ __shmem_unacct_memory(info, pages * VM_ACCT(PAGE_CACHE_SIZE));
}
static const struct super_operations shmem_ops;
@@ -1404,6 +1426,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
inode->i_fop = &shmem_file_operations;
mpol_shared_policy_init(&info->policy,
shmem_get_sbmpol(sbinfo));
+ shmem_init_vm_cgroup(info);
break;
case S_IFDIR:
inc_nlink(inode);
@@ -2677,8 +2700,12 @@ static void shmem_destroy_callback(struct rcu_head *head)
static void shmem_destroy_inode(struct inode *inode)
{
- if (S_ISREG(inode->i_mode))
- mpol_free_shared_policy(&SHMEM_I(inode)->policy);
+ struct shmem_inode_info *info = SHMEM_I(inode);
+
+ if (S_ISREG(inode->i_mode)) {
+ mpol_free_shared_policy(&info->policy);
+ shmem_release_vm_cgroup(info);
+ }
call_rcu(&inode->i_rcu, shmem_destroy_callback);
}
diff --git a/mm/vm_cgroup.c b/mm/vm_cgroup.c
index 10a24da2951a..0292734938f7 100644
--- a/mm/vm_cgroup.c
+++ b/mm/vm_cgroup.c
@@ -3,6 +3,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/rcupdate.h>
+#include <linux/shmem_fs.h>
#include <linux/vm_cgroup.h>
struct vm_cgroup {
@@ -92,6 +93,41 @@ void vm_cgroup_uncharge_memory_mm(struct mm_struct *mm, unsigned long nr_pages)
vm_cgroup_do_uncharge(vmcg, nr_pages);
}
+#ifdef CONFIG_SHMEM
+void shmem_init_vm_cgroup(struct shmem_inode_info *info)
+{
+ if (!vm_cgroup_disabled())
+ info->vmcg = get_vm_cgroup_from_task(current);
+}
+
+void shmem_release_vm_cgroup(struct shmem_inode_info *info)
+{
+ struct vm_cgroup *vmcg = info->vmcg;
+
+ if (vmcg)
+ css_put(&vmcg->css);
+}
+
+int vm_cgroup_charge_shmem(struct shmem_inode_info *info,
+ unsigned long nr_pages)
+{
+ struct vm_cgroup *vmcg = info->vmcg;
+
+ if (vmcg)
+ return vm_cgroup_do_charge(vmcg, nr_pages);
+ return 0;
+}
+
+void vm_cgroup_uncharge_shmem(struct shmem_inode_info *info,
+ unsigned long nr_pages)
+{
+ struct vm_cgroup *vmcg = info->vmcg;
+
+ if (vmcg)
+ vm_cgroup_do_uncharge(info->vmcg, nr_pages);
+}
+#endif /* CONFIG_SHMEM */
+
static struct cgroup_subsys_state *
vm_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
{
--
1.8.1.2
|
