xref: /linux/Documentation/mm/page_owner.rst (revision 64ed7d8190611c96744fd2b89afe6aeb3054902b)
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
236