The basic question we would like to have a reliable and efficient answer
to is: is this anonymous page exclusive to a single process or might it be
shared? We need that information for ordinary/single pages, hugetlb
pages, and possibly each subpage of a THP.
Introduce a way to mark an anonymous page as exclusive, with the ultimate
goal of teaching our COW logic to not do "wrong COWs", whereby GUP pins
lose consistency with the pages mapped into the page table, resulting in
reported memory corruptions.
Most pageflags already have semantics for anonymous pages, however,
PG_mappedtodisk should never apply to pages in the swapcache, so let's
reuse that flag.
As PG_has_hwpoisoned also uses that flag on the second tail page of a
compound page, convert it to PG_error instead, which is marked as
PF_NO_TAIL, so never used for tail pages.
Use custom page flag modification functions such that we can do additional
sanity checks. The semantics we'll put into some kernel doc in the future
are:
"
PG_anon_exclusive is *usually* only expressive in combination with a
page table entry. Depending on the page table entry type it might
store the following information:
Is what's mapped via this page table entry exclusive to the
single process and can be mapped writable without further
checks? If not, it might be shared and we might have to COW.
For now, we only expect PTE-mapped THPs to make use of
PG_anon_exclusive in subpages. For other anonymous compound
folios (i.e., hugetlb), only the head page is logically mapped and
holds this information.
For example, an exclusive, PMD-mapped THP only has PG_anon_exclusive
set on the head page. When replacing the PMD by a page table full
of PTEs, PG_anon_exclusive, if set on the head page, will be set on
all tail pages accordingly. Note that converting from a PTE-mapping
to a PMD mapping using the same compound page is currently not
possible and consequently doesn't require care.
If GUP wants to take a reliable pin (FOLL_PIN) on an anonymous page,
it should only pin if the relevant PG_anon_exclusive is set. In that
case, the pin will be fully reliable and stay consistent with the pages
mapped into the page table, as the bit cannot get cleared (e.g., by
fork(), KSM) while the page is pinned. For anonymous pages that
are mapped R/W, PG_anon_exclusive can be assumed to always be set
because such pages cannot possibly be shared.
The page table lock protecting the page table entry is the primary
synchronization mechanism for PG_anon_exclusive; GUP-fast that does
not take the PT lock needs special care when trying to clear the
flag.
Page table entry types and PG_anon_exclusive:
* Present: PG_anon_exclusive applies.
* Swap: the information is lost. PG_anon_exclusive was cleared.
* Migration: the entry holds this information instead.
PG_anon_exclusive was cleared.
* Device private: PG_anon_exclusive applies.
* Device exclusive: PG_anon_exclusive applies.
* HW Poison: PG_anon_exclusive is stale and not changed.
If the page may be pinned (FOLL_PIN), clearing PG_anon_exclusive is
not allowed and the flag will stick around until the page is freed
and folio->mapping is cleared.
"
We won't be clearing PG_anon_exclusive on destructive unmapping (i.e.,
zapping) of page table entries, page freeing code will handle that when
also invalidate page->mapping to not indicate PageAnon() anymore. Letting
information about exclusivity stick around will be an important property
when adding sanity checks to unpinning code.
Note that we properly clear the flag in free_pages_prepare() via
PAGE_FLAGS_CHECK_AT_PREP for each individual subpage of a compound page,
so there is no need to manually clear the flag.
Link: https://lkml.kernel.org/r/20220428083441.37290-12-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Rientjes <rientjes@google.com>
Cc: Don Dutile <ddutile@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Khalid Aziz <khalid.aziz@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Liang Zhang <zhangliang5@huawei.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Oded Gabbay <oded.gabbay@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pedro Demarchi Gomes <pedrodemargomes@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
An application is suspected of having memory leak when its memory
consumption is high and keeps increasing. There are several commonly used
memory allocators: slab, cma, vmalloc, etc. The memory leak
identification can be sped up if the page information allocated by an
allocator can be analyzed separately.
This patch provides supports for memory allocator labelling for slab,
vmalloc, and cma. The pages allocated by slab and cma can be confirmed
from the "PFN" line according to the kernel codes, and the label of the
vmalloc allocator can be obtained by analyzing the stack trace. Thanks
for Vlastimil Babka's constructive suggestions.
Based on Yinan Zhang's study, the call chain of vmalloc() is vmalloc() ->
... -> __vmalloc_node_range() -> __vmalloc_area_node().
__vmalloc_area_node() requests memory through the interface of buddy
allocation system. In the current version, __vmalloc_area_node() uses
four interfaces: alloc_pages_bulk_array_mempolicy(),
alloc_pages_bulk_array_node(), alloc_pages() and alloc_pages_node(). By
disassembling the code, we find that __vmalloc_area_node() is expanded in
__vmalloc_node_range(). So __vmalloc_area_node is not in the stack trace.
On the test machine, the stack trace of pages allocated by vmalloc has the
following four forms:
__alloc_pages_bulk+0x230/0x6a0
__vmalloc_node_range+0x19c/0x598
alloc_pages_bulk_array_mempolicy+0xbc/0x278
__vmalloc_node_range+0x1e8/0x598
__alloc_pages+0x160/0x2b0
__vmalloc_node_range+0x234/0x598
alloc_pages+0xac/0x150
__vmalloc_node_range+0x44c/0x598
Therefore, in two consecutive lines of stacktrace, if the first line
contains the word "alloc_pages" and the second line contains the word
"__vmalloc_node_range", it can be determined that the page is allocated by
vmalloc. And the function offset and size are not the same on different
machines, so there is no need to match them.
At the same time, this patch updates the --cull and --sort options to
support allocator-based merge statistics and sorting. The added functions
are fully compatible with the original work. When using, you can use
"allocator", or abbreviated as "ator". Relevant updates have also been
made in the documentation(Documentation/vm/page_owner.rst).
Example:
./page_owner_sort <input> <output> --cull=st,pid,name,allocator
./page_owner_sort <input> <output> --sort=ator,pid,name
This work is coauthored by Jiajian Ye, Yinan Zhang, Shenghong Han,
Chongxi Zhao, Yuhong Feng and Yongqiang Liu.
Link: https://lkml.kernel.org/r/20220410132932.9402-1-caoyixuan2019@email.szu.edu.cn
Signed-off-by: Yixuan Cao <caoyixuan2019@email.szu.edu.cn>
Cc: Chongxi Zhao <zhaochongxi2019@email.szu.edu.cn>
Cc: Haowen Bai <baihaowen@meizu.com>
Cc: Jiajian Ye <yejiajian2018@email.szu.edu.cn>
Cc: Sean Anderson <seanga2@gmail.com>
Cc: Shenghong Han <hanshenghong2019@email.szu.edu.cn>
Cc: Yinan Zhang <zhangyinan2019@email.szu.edu.cn>
Cc: Yongqiang Liu <liuyongqiang13@huawei.com>
Cc: Yuhong Feng <yuhongf@szu.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When viewing page owner information, we may want to sort blocks of
information by multiple keys, since one single key does not uniquely
identify a block. Therefore, following adjustments are made:
1. Add a new --sort option to support sorting blocks of information by
multiple keys.
./page_owner_sort <input> <output> --sort=<order>
./page_owner_sort <input> <output> --sort <order>
<order> is a single argument in the form of a comma-separated list,
which offers a way to specify sorting order.
Sorting syntax is [+|-]key[,[+|-]key[,...]]. The ascending or descending
order can be specified by adding the + (ascending, default) or - (descend
-ing) prefix to the key:
./page_owner_sort <input> <output> [option] --sort -key1,+key2,key3...
For example, to sort the blocks first by task command name in lexicographic
order and then by pid in ascending numerical order, use the following:
./page_owner_sort <input> <output> --sort=name,+pid
To sort the blocks first by pid in ascending order and then by timestamp
of the page when it is allocated in descending order, use the following:
./page_owner_sort <input> <output> --sort=pid,-alloc_ts
2. Add explanations of a newly added --sort option in the function usage()
and the document(Documentation/vm/page_owner.rst).
This work is coauthored by
Yixuan Cao
Shenghong Han
Yinan Zhang
Chongxi Zhao
Yuhong Feng
Yongqiang Liu
Link: https://lkml.kernel.org/r/20220401024856.767-3-yejiajian2018@email.szu.edu.cn
Signed-off-by: Jiajian Ye <yejiajian2018@email.szu.edu.cn>
Cc: Chongxi Zhao <zhaochongxi2019@email.szu.edu.cn>
Cc: Shenghong Han <hanshenghong2019@email.szu.edu.cn>
Cc: Yinan Zhang <zhangyinan2019@email.szu.edu.cn>
Cc: Yixuan Cao <caoyixuan2019@email.szu.edu.cn>
Cc: Yongqiang Liu <liuyongqiang13@huawei.com>
Cc: Yuhong Feng <yuhongf@szu.edu.cn>
Cc: Haowen Bai <baihaowen@meizu.com>
Cc: Sean Anderson <seanga2@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When viewing page owner information, we may want to select blocks whose
PID/TGID/TASK_COMM_NAME appears in a user-specified list for data analysis
and aggregation. But currently page_owner_sort only supports selecting
blocks associated with only one specified PID/TGID/TASK_COMM_NAME.
Therefore, following adjustments are made to fix the problem:
1. Enhance selecting function to support the selection of multiple
PIDs/TGIDs/TASK_COMM_NAMEs.
The enhanced usages are as follows:
--pid <pidlist> Select by pid. This selects the blocks whose PID
numbers appear in <pidlist>.
--tgid <tgidlist> Select by tgid. This selects the blocks whose
TGID numbers appear in <tgidlist>.
--name <cmdlist> Select by task command name. This selects the
blocks whose task command name appear in <cmdlist>.
Where <pidlist>, <tgidlist>, <cmdlist> are single arguments in the form of
a comma-separated list,which offers a way to specify individual selecting
rules.
For example, if you want to select blocks whose tgids are 1, 2 or 3, you
have to use 4 commands as follows:
./page_owner_sort <input> <output1> --tgid=1
./page_owner_sort <input> <output2> --tgid=2
./page_owner_sort <input> <output3> --tgid=3
cat <output1> <output2> <output3> > <output>
With this patch, you can use only 1 command to obtain the same result as
above:
./page_owner_sort <input> <output1> --tgid=1,2,3
2. Update explanations of --pid, --tgid and --name in the function
usage() and the document(Documents/vm/page_owner.rst).
This work is coauthored by
Yixuan Cao
Shenghong Han
Yinan Zhang
Chongxi Zhao
Yuhong Feng
Yongqiang Liu
Link: https://lkml.kernel.org/r/20220401024856.767-2-yejiajian2018@email.szu.edu.cn
Signed-off-by: Jiajian Ye <yejiajian2018@email.szu.edu.cn>
Cc: Chongxi Zhao <zhaochongxi2019@email.szu.edu.cn>
Cc: Shenghong Han <hanshenghong2019@email.szu.edu.cn>
Cc: Yinan Zhang <zhangyinan2019@email.szu.edu.cn>
Cc: Yixuan Cao <caoyixuan2019@email.szu.edu.cn>
Cc: Yongqiang Liu <liuyongqiang13@huawei.com>
Cc: Yuhong Feng <yuhongf@szu.edu.cn>
Cc: Haowen Bai <baihaowen@meizu.com>
Cc: Sean Anderson <seanga2@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
When viewing page owner information, we may want to cull blocks of
information with our own rules. So it is important to enhance culling
function to provide the support for customizing culling rules.
Therefore, following adjustments are made:
1. Add --cull option to support the culling of blocks of information
with user-defined culling rules.
./page_owner_sort <input> <output> --cull=<rules>
./page_owner_sort <input> <output> --cull <rules>
<rules> is a single argument in the form of a comma-separated list to
specify individual culling rules, by the sequence of keys k1,k2, ....
Mixed use of abbreviated and complete-form of keys is allowed.
For reference, please see the document(Documentation/vm/page_owner.rst).
Now, assuming two blocks in the input file are as follows:
Page allocated via order 0, mask xxxx, pid 1, tgid 1 (task_name_demo)
PFN xxxx
prep_new_page+0xd0/0xf8
get_page_from_freelist+0x4a0/0x1290
__alloc_pages+0x168/0x340
alloc_pages+0xb0/0x158
Page allocated via order 0, mask xxxx, pid 32, tgid 32 (task_name_demo)
PFN xxxx
prep_new_page+0xd0/0xf8
get_page_from_freelist+0x4a0/0x1290
__alloc_pages+0x168/0x340
alloc_pages+0xb0/0x158
If we want to cull the blocks by stacktrace and task command name, we can
use this command:
./page_owner_sort <input> <output> --cull=stacktrace,name
The output would be like:
2 times, 2 pages, task_comm_name: task_name_demo
prep_new_page+0xd0/0xf8
get_page_from_freelist+0x4a0/0x1290
__alloc_pages+0x168/0x340
alloc_pages+0xb0/0x158
As we can see, these two blocks are culled successfully, for they share
the same pid and task command name.
However, if we want to cull the blocks by pid, stacktrace and task command
name, we can this command:
./page_owner_sort <input> <output> --cull=stacktrace,name,pid
The output would be like:
1 times, 1 pages, PID 1, task_comm_name: task_name_demo
prep_new_page+0xd0/0xf8
get_page_from_freelist+0x4a0/0x1290
__alloc_pages+0x168/0x340
alloc_pages+0xb0/0x158
1 times, 1 pages, PID 32, task_comm_name: task_name_demo
prep_new_page+0xd0/0xf8
get_page_from_freelist+0x4a0/0x1290
__alloc_pages+0x168/0x340
alloc_pages+0xb0/0x158
As we can see, these two blocks are failed to cull, for their PIDs are
different.
2. Add explanations of --cull options to the document.
This work is coauthored by
Yixuan Cao
Shenghong Han
Yinan Zhang
Chongxi Zhao
Yuhong Feng
Link: https://lkml.kernel.org/r/20220312145834.624-1-yejiajian2018@email.szu.edu.cn
Signed-off-by: Jiajian Ye <yejiajian2018@email.szu.edu.cn>
Cc: Yixuan Cao <caoyixuan2019@email.szu.edu.cn>
Cc: Shenghong Han <hanshenghong2019@email.szu.edu.cn>
Cc: Yinan Zhang <zhangyinan2019@email.szu.edu.cn>
Cc: Chongxi Zhao <zhaochongxi2019@email.szu.edu.cn>
Cc: Yuhong Feng <yuhongf@szu.edu.cn>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Sean Anderson <seanga2@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When viewing page owner information, we may also need to select the blocks
by PID, TGID or task command name, which helps to get more accurate page
allocation information as needed.
Therefore, following adjustments are made:
1. Add three new options, including --pid, --tgid and --name, to support
the selection of information blocks by a specific pid, tgid and task
command name. In addtion, multiple options are allowed to be used at
the same time.
./page_owner_sort [input] [output] --pid <PID>
./page_owner_sort [input] [output] --tgid <TGID>
./page_owner_sort [input] [output] --name <TASK_COMMAND_NAME>
Assuming a scenario when a multi-threaded program, ./demo (PID =
5280), is running, and ./demo creates a child process (PID = 5281).
$ps
PID TTY TIME CMD
5215 pts/0 00:00:00 bash
5280 pts/0 00:00:00 ./demo
5281 pts/0 00:00:00 ./demo
5282 pts/0 00:00:00 ps
It would be better to filter out the records with tgid=5280 and the
task name "demo" when debugging the parent process, and the specific
usage is
./page_owner_sort [input] [output] --tgid 5280 --name demo
2. Add explanations of three new options, including --pid, --tgid and
--name, to the document.
This work is coauthored by
Shenghong Han <hanshenghong2019@email.szu.edu.cn>,
Yixuan Cao <caoyixuan2019@email.szu.edu.cn>,
Yinan Zhang <zhangyinan2019@email.szu.edu.cn>,
Chongxi Zhao <zhaochongxi2019@email.szu.edu.cn>,
Yuhong Feng <yuhongf@szu.edu.cn>.
Link: https://lkml.kernel.org/r/1646835223-7584-1-git-send-email-yejiajian2018@email.szu.edu.cn
Signed-off-by: Jiajian Ye <yejiajian2018@email.szu.edu.cn>
Cc: Sean Anderson <seanga2@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Zhenliang Wei <weizhenliang@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When viewing the page owner information, we expect that the information
can be sorted by PID, so that we can quickly combine PID with the program
to check the information together.
We also expect that the information can be sorted by time. Time sorting
helps to view the running status of the program according to the time
interval when the program hangs up.
Finally, we hope to pass the page_ owner_ Sort. C can reduce part of the
output and only output the plate information whose memory has not been
released, which can make us locate the problem of the program faster.
Therefore, the following adjustments have been made:
1. Add the static functions search_pattern and check_regcomp to
improve the cleanliness.
2. Add member attributes and their corresponding sorting methods. In
terms of comparison time, int will overflow because the data of ull is
too large, so the ternary operator is used
3. Add the -f parameter to filter out the information of blocks whose
memory has not been released
Link: https://lkml.kernel.org/r/20211206165653.5093-1-zhaochongxi2019@email.szu.edu.cn
Signed-off-by: Chongxi Zhao <zhaochongxi2019@email.szu.edu.cn>
Reviewed-by: Sean Anderson <seanga2@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Culling by comparing stacktrace would casue loss of some information. For
example, if there exists 2 blocks which have the same stacktrace and the
different head info
Page allocated via order 0, mask 0x108c48(...), pid 73696,
ts 1578829190639010 ns, free_ts 1576583851324450 ns
prep_new_page+0x80/0xb8
get_page_from_freelist+0x924/0xee8
__alloc_pages+0x138/0xc18
alloc_pages+0x80/0xf0
__page_cache_alloc+0x90/0xc8
Page allocated via order 0, mask 0x108c48(...), pid 61806,
ts 1354113726046100 ns, free_ts 1354104926841400 ns
prep_new_page+0x80/0xb8
get_page_from_freelist+0x924/0xee8
__alloc_pages+0x138/0xc18
alloc_pages+0x80/0xf0
__page_cache_alloc+0x90/0xc8
After culling, it would be like this
2 times, 2 pages:
Page allocated via order 0, mask 0x108c48(...), pid 73696,
ts 1578829190639010 ns, free_ts 1576583851324450 ns
prep_new_page+0x80/0xb8
get_page_from_freelist+0x924/0xee8
__alloc_pages+0x138/0xc18
alloc_pages+0x80/0xf0
__page_cache_alloc+0x90/0xc8
The info of second block missed. So, add -c to turn on culling by
stacktrace. By default, it will cull by txt.
Link: https://lkml.kernel.org/r/20211129145658.2491-1-zhangyinan2019@email.szu.edu.cn
Signed-off-by: Yinan Zhang <zhangyinan2019@email.szu.edu.cn>
Cc: Changhee Han <ch0.han@lge.com>
Cc: Sean Anderson <seanga2@gmail.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Tang Bin <tangbin@cmss.chinamobile.com>
Cc: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Cc: Zhenliang Wei <weizhenliang@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When viewing page owner information, we may be more concerned about the
total memory rather than the times of stack appears. Therefore, the
following adjustments are made:
1. Added the statistics on the total number of pages.
2. Added the optional parameter "-m" to configure the program to sort by
memory (total pages).
The general output of page_owner is as follows:
Page allocated via order XXX, ...
PFN XXX ...
// Detailed stack
Page allocated via order XXX, ...
PFN XXX ...
// Detailed stack
The original page_owner_sort ignores PFN rows, puts the remaining rows
in buf, counts the times of buf, and finally sorts them according to the
times. General output:
XXX times:
Page allocated via order XXX, ...
// Detailed stack
Now, we use regexp to extract the page order value from the buf, and
count the total pages for the buf. General output:
XXX times, XXX pages:
Page allocated via order XXX, ...
// Detailed stack
By default, it is still sorted by the times of buf; If you want to sort
by the pages nums of buf, use the new -m parameter.
Link: https://lkml.kernel.org/r/1631678242-41033-1-git-send-email-weizhenliang@huawei.com
Signed-off-by: Zhenliang Wei <weizhenliang@huawei.com>
Cc: Tang Bin <tangbin@cmss.chinamobile.com>
Cc: Zhang Shengju <zhangshengju@cmss.chinamobile.com>
Cc: Zhenliang Wei <weizhenliang@huawei.com>
Cc: Xiaoming Ni <nixiaoming@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
David Hildenbrand
Yixuan Cao
Haowen Bai
Jiajian Ye
Yinan Zhang
Shenghong Han
Chongxi Zhao
Sean Anderson
Naoya Horiguchi
Zhenliang Wei