Loading...
1==================================================
2page owner: Tracking about who allocated each page
3==================================================
4
5Introduction
6============
7
8page owner is for the tracking about who allocated each page.
9It can be used to debug memory leak or to find a memory hogger.
10When allocation happens, information about allocation such as call stack
11and order of pages is stored into certain storage for each page.
12When we need to know about status of all pages, we can get and analyze
13this information.
14
15Although we already have tracepoint for tracing page allocation/free,
16using it for analyzing who allocate each page is rather complex. We need
17to enlarge the trace buffer for preventing overlapping until userspace
18program launched. And, launched program continually dump out the trace
19buffer for later analysis and it would change system behaviour with more
20possibility rather than just keeping it in memory, so bad for debugging.
21
22page owner can also be used for various purposes. For example, accurate
23fragmentation statistics can be obtained through gfp flag information of
24each page. It is already implemented and activated if page owner is
25enabled. Other usages are more than welcome.
26
27It can also be used to show all the stacks and their current number of
28allocated base pages, which gives us a quick overview of where the memory
29is going without the need to screen through all the pages and match the
30allocation and free operation.
31
32page owner is disabled by default. So, if you'd like to use it, you need
33to add "page_owner=on" to your boot cmdline. If the kernel is built
34with page owner and page owner is disabled in runtime due to not enabling
35boot option, runtime overhead is marginal. If disabled in runtime, it
36doesn't require memory to store owner information, so there is no runtime
37memory overhead. And, page owner inserts just two unlikely branches into
38the page allocator hotpath and if not enabled, then allocation is done
39like as the kernel without page owner. These two unlikely branches should
40not affect to allocation performance, especially if the static keys jump
41label patching functionality is available. Following is the kernel's code
42size change due to this facility.
43
44Although enabling page owner increases kernel size by several kilobytes,
45most of this code is outside page allocator and its hot path. Building
46the kernel with page owner and turning it on if needed would be great
47option to debug kernel memory problem.
48
49There is one notice that is caused by implementation detail. page owner
50stores information into the memory from struct page extension. This memory
51is initialized some time later than that page allocator starts in sparse
52memory system, so, until initialization, many pages can be allocated and
53they would have no owner information. To fix it up, these early allocated
54pages are investigated and marked as allocated in initialization phase.
55Although it doesn't mean that they have the right owner information,
56at least, we can tell whether the page is allocated or not,
57more accurately. On 2GB memory x86-64 VM box, 13343 early allocated pages
58are caught and marked, although they are mostly allocated from struct
59page extension feature. Anyway, after that, no page is left in
60un-tracking state.
61
62Usage
63=====
64
651) Build user-space helper::
66
67 cd tools/mm
68 make page_owner_sort
69
702) Enable page owner: add "page_owner=on" to boot cmdline.
71
723) Do the job that you want to debug.
73
744) Analyze information from page owner::
75
76 cat /sys/kernel/debug/page_owner_stacks/show_stacks > stacks.txt
77 cat stacks.txt
78 post_alloc_hook+0x177/0x1a0
79 get_page_from_freelist+0xd01/0xd80
80 __alloc_pages+0x39e/0x7e0
81 allocate_slab+0xbc/0x3f0
82 ___slab_alloc+0x528/0x8a0
83 kmem_cache_alloc+0x224/0x3b0
84 sk_prot_alloc+0x58/0x1a0
85 sk_alloc+0x32/0x4f0
86 inet_create+0x427/0xb50
87 __sock_create+0x2e4/0x650
88 inet_ctl_sock_create+0x30/0x180
89 igmp_net_init+0xc1/0x130
90 ops_init+0x167/0x410
91 setup_net+0x304/0xa60
92 copy_net_ns+0x29b/0x4a0
93 create_new_namespaces+0x4a1/0x820
94 nr_base_pages: 16
95 ...
96 ...
97 echo 7000 > /sys/kernel/debug/page_owner_stacks/count_threshold
98 cat /sys/kernel/debug/page_owner_stacks/show_stacks> stacks_7000.txt
99 cat stacks_7000.txt
100 post_alloc_hook+0x177/0x1a0
101 get_page_from_freelist+0xd01/0xd80
102 __alloc_pages+0x39e/0x7e0
103 alloc_pages_mpol+0x22e/0x490
104 folio_alloc+0xd5/0x110
105 filemap_alloc_folio+0x78/0x230
106 page_cache_ra_order+0x287/0x6f0
107 filemap_get_pages+0x517/0x1160
108 filemap_read+0x304/0x9f0
109 xfs_file_buffered_read+0xe6/0x1d0 [xfs]
110 xfs_file_read_iter+0x1f0/0x380 [xfs]
111 __kernel_read+0x3b9/0x730
112 kernel_read_file+0x309/0x4d0
113 __do_sys_finit_module+0x381/0x730
114 do_syscall_64+0x8d/0x150
115 entry_SYSCALL_64_after_hwframe+0x62/0x6a
116 nr_base_pages: 20824
117 ...
118
119 cat /sys/kernel/debug/page_owner > page_owner_full.txt
120 ./page_owner_sort page_owner_full.txt sorted_page_owner.txt
121
122 The general output of ``page_owner_full.txt`` is as follows::
123
124 Page allocated via order XXX, ...
125 PFN XXX ...
126 // Detailed stack
127
128 Page allocated via order XXX, ...
129 PFN XXX ...
130 // Detailed stack
131 By default, it will do full pfn dump, to start with a given pfn,
132 page_owner supports fseek.
133
134 FILE *fp = fopen("/sys/kernel/debug/page_owner", "r");
135 fseek(fp, pfn_start, SEEK_SET);
136
137 The ``page_owner_sort`` tool ignores ``PFN`` rows, puts the remaining rows
138 in buf, uses regexp to extract the page order value, counts the times
139 and pages of buf, and finally sorts them according to the parameter(s).
140
141 See the result about who allocated each page
142 in the ``sorted_page_owner.txt``. General output::
143
144 XXX times, XXX pages:
145 Page allocated via order XXX, ...
146 // Detailed stack
147
148 By default, ``page_owner_sort`` is sorted according to the times of buf.
149 If you want to sort by the page nums of buf, use the ``-m`` parameter.
150 The detailed parameters are:
151
152 fundamental function::
153
154 Sort:
155 -a Sort by memory allocation time.
156 -m Sort by total memory.
157 -p Sort by pid.
158 -P Sort by tgid.
159 -n Sort by task command name.
160 -r Sort by memory release time.
161 -s Sort by stack trace.
162 -t Sort by times (default).
163 --sort <order> Specify sorting order. Sorting syntax is [+|-]key[,[+|-]key[,...]].
164 Choose a key from the **STANDARD FORMAT SPECIFIERS** section. The "+" is
165 optional since default direction is increasing numerical or lexicographic
166 order. Mixed use of abbreviated and complete-form of keys is allowed.
167
168 Examples:
169 ./page_owner_sort <input> <output> --sort=n,+pid,-tgid
170 ./page_owner_sort <input> <output> --sort=at
171
172 additional function::
173
174 Cull:
175 --cull <rules>
176 Specify culling rules.Culling syntax is key[,key[,...]].Choose a
177 multi-letter key from the **STANDARD FORMAT SPECIFIERS** section.
178
179 <rules> is a single argument in the form of a comma-separated list,
180 which offers a way to specify individual culling rules. The recognized
181 keywords are described in the **STANDARD FORMAT SPECIFIERS** section below.
182 <rules> can be specified by the sequence of keys k1,k2, ..., as described in
183 the STANDARD SORT KEYS section below. Mixed use of abbreviated and
184 complete-form of keys is allowed.
185
186 Examples:
187 ./page_owner_sort <input> <output> --cull=stacktrace
188 ./page_owner_sort <input> <output> --cull=st,pid,name
189 ./page_owner_sort <input> <output> --cull=n,f
190
191 Filter:
192 -f Filter out the information of blocks whose memory has been released.
193
194 Select:
195 --pid <pidlist> Select by pid. This selects the blocks whose process ID
196 numbers appear in <pidlist>.
197 --tgid <tgidlist> Select by tgid. This selects the blocks whose thread
198 group ID numbers appear in <tgidlist>.
199 --name <cmdlist> Select by task command name. This selects the blocks whose
200 task command name appear in <cmdlist>.
201
202 <pidlist>, <tgidlist>, <cmdlist> are single arguments in the form of a comma-separated list,
203 which offers a way to specify individual selecting rules.
204
205
206 Examples:
207 ./page_owner_sort <input> <output> --pid=1
208 ./page_owner_sort <input> <output> --tgid=1,2,3
209 ./page_owner_sort <input> <output> --name name1,name2
210
211STANDARD FORMAT SPECIFIERS
212==========================
213::
214
215 For --sort option:
216
217 KEY LONG DESCRIPTION
218 p pid process ID
219 tg tgid thread group ID
220 n name task command name
221 st stacktrace stack trace of the page allocation
222 T txt full text of block
223 ft free_ts timestamp of the page when it was released
224 at alloc_ts timestamp of the page when it was allocated
225 ator allocator memory allocator for pages
226
227 For --cull option:
228
229 KEY LONG DESCRIPTION
230 p pid process ID
231 tg tgid thread group ID
232 n name task command name
233 f free whether the page has been released or not
234 st stacktrace stack trace of the page allocation
235 ator allocator memory allocator for pages
1==================================================
2page owner: Tracking about who allocated each page
3==================================================
4
5Introduction
6============
7
8page owner is for the tracking about who allocated each page.
9It can be used to debug memory leak or to find a memory hogger.
10When allocation happens, information about allocation such as call stack
11and order of pages is stored into certain storage for each page.
12When we need to know about status of all pages, we can get and analyze
13this information.
14
15Although we already have tracepoint for tracing page allocation/free,
16using it for analyzing who allocate each page is rather complex. We need
17to enlarge the trace buffer for preventing overlapping until userspace
18program launched. And, launched program continually dump out the trace
19buffer for later analysis and it would change system behaviour with more
20possibility rather than just keeping it in memory, so bad for debugging.
21
22page owner can also be used for various purposes. For example, accurate
23fragmentation statistics can be obtained through gfp flag information of
24each page. It is already implemented and activated if page owner is
25enabled. Other usages are more than welcome.
26
27page owner is disabled by default. So, if you'd like to use it, you need
28to add "page_owner=on" to your boot cmdline. If the kernel is built
29with page owner and page owner is disabled in runtime due to not enabling
30boot option, runtime overhead is marginal. If disabled in runtime, it
31doesn't require memory to store owner information, so there is no runtime
32memory overhead. And, page owner inserts just two unlikely branches into
33the page allocator hotpath and if not enabled, then allocation is done
34like as the kernel without page owner. These two unlikely branches should
35not affect to allocation performance, especially if the static keys jump
36label patching functionality is available. Following is the kernel's code
37size change due to this facility.
38
39Although enabling page owner increases kernel size by several kilobytes,
40most of this code is outside page allocator and its hot path. Building
41the kernel with page owner and turning it on if needed would be great
42option to debug kernel memory problem.
43
44There is one notice that is caused by implementation detail. page owner
45stores information into the memory from struct page extension. This memory
46is initialized some time later than that page allocator starts in sparse
47memory system, so, until initialization, many pages can be allocated and
48they would have no owner information. To fix it up, these early allocated
49pages are investigated and marked as allocated in initialization phase.
50Although it doesn't mean that they have the right owner information,
51at least, we can tell whether the page is allocated or not,
52more accurately. On 2GB memory x86-64 VM box, 13343 early allocated pages
53are caught and marked, although they are mostly allocated from struct
54page extension feature. Anyway, after that, no page is left in
55un-tracking state.
56
57Usage
58=====
59
601) Build user-space helper::
61
62 cd tools/mm
63 make page_owner_sort
64
652) Enable page owner: add "page_owner=on" to boot cmdline.
66
673) Do the job that you want to debug.
68
694) Analyze information from page owner::
70
71 cat /sys/kernel/debug/page_owner > page_owner_full.txt
72 ./page_owner_sort page_owner_full.txt sorted_page_owner.txt
73
74 The general output of ``page_owner_full.txt`` is as follows::
75
76 Page allocated via order XXX, ...
77 PFN XXX ...
78 // Detailed stack
79
80 Page allocated via order XXX, ...
81 PFN XXX ...
82 // Detailed stack
83 By default, it will do full pfn dump, to start with a given pfn,
84 page_owner supports fseek.
85
86 FILE *fp = fopen("/sys/kernel/debug/page_owner", "r");
87 fseek(fp, pfn_start, SEEK_SET);
88
89 The ``page_owner_sort`` tool ignores ``PFN`` rows, puts the remaining rows
90 in buf, uses regexp to extract the page order value, counts the times
91 and pages of buf, and finally sorts them according to the parameter(s).
92
93 See the result about who allocated each page
94 in the ``sorted_page_owner.txt``. General output::
95
96 XXX times, XXX pages:
97 Page allocated via order XXX, ...
98 // Detailed stack
99
100 By default, ``page_owner_sort`` is sorted according to the times of buf.
101 If you want to sort by the page nums of buf, use the ``-m`` parameter.
102 The detailed parameters are:
103
104 fundamental function::
105
106 Sort:
107 -a Sort by memory allocation time.
108 -m Sort by total memory.
109 -p Sort by pid.
110 -P Sort by tgid.
111 -n Sort by task command name.
112 -r Sort by memory release time.
113 -s Sort by stack trace.
114 -t Sort by times (default).
115 --sort <order> Specify sorting order. Sorting syntax is [+|-]key[,[+|-]key[,...]].
116 Choose a key from the **STANDARD FORMAT SPECIFIERS** section. The "+" is
117 optional since default direction is increasing numerical or lexicographic
118 order. Mixed use of abbreviated and complete-form of keys is allowed.
119
120 Examples:
121 ./page_owner_sort <input> <output> --sort=n,+pid,-tgid
122 ./page_owner_sort <input> <output> --sort=at
123
124 additional function::
125
126 Cull:
127 --cull <rules>
128 Specify culling rules.Culling syntax is key[,key[,...]].Choose a
129 multi-letter key from the **STANDARD FORMAT SPECIFIERS** section.
130
131 <rules> is a single argument in the form of a comma-separated list,
132 which offers a way to specify individual culling rules. The recognized
133 keywords are described in the **STANDARD FORMAT SPECIFIERS** section below.
134 <rules> can be specified by the sequence of keys k1,k2, ..., as described in
135 the STANDARD SORT KEYS section below. Mixed use of abbreviated and
136 complete-form of keys is allowed.
137
138 Examples:
139 ./page_owner_sort <input> <output> --cull=stacktrace
140 ./page_owner_sort <input> <output> --cull=st,pid,name
141 ./page_owner_sort <input> <output> --cull=n,f
142
143 Filter:
144 -f Filter out the information of blocks whose memory has been released.
145
146 Select:
147 --pid <pidlist> Select by pid. This selects the blocks whose process ID
148 numbers appear in <pidlist>.
149 --tgid <tgidlist> Select by tgid. This selects the blocks whose thread
150 group ID numbers appear in <tgidlist>.
151 --name <cmdlist> Select by task command name. This selects the blocks whose
152 task command name appear in <cmdlist>.
153
154 <pidlist>, <tgidlist>, <cmdlist> are single arguments in the form of a comma-separated list,
155 which offers a way to specify individual selecting rules.
156
157
158 Examples:
159 ./page_owner_sort <input> <output> --pid=1
160 ./page_owner_sort <input> <output> --tgid=1,2,3
161 ./page_owner_sort <input> <output> --name name1,name2
162
163STANDARD FORMAT SPECIFIERS
164==========================
165::
166
167 For --sort option:
168
169 KEY LONG DESCRIPTION
170 p pid process ID
171 tg tgid thread group ID
172 n name task command name
173 st stacktrace stack trace of the page allocation
174 T txt full text of block
175 ft free_ts timestamp of the page when it was released
176 at alloc_ts timestamp of the page when it was allocated
177 ator allocator memory allocator for pages
178
179 For --cull option:
180
181 KEY LONG DESCRIPTION
182 p pid process ID
183 tg tgid thread group ID
184 n name task command name
185 f free whether the page has been released or not
186 st stacktrace stack trace of the page allocation
187 ator allocator memory allocator for pages