License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:07:57 +00:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 */
|
2005-04-16 22:20:36 +00:00
|
|
|
#ifndef _LINUX_SWAP_H
|
|
|
|
|
#define _LINUX_SWAP_H
|
|
|
|
|
|
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
|
#include <linux/linkage.h>
|
|
|
|
|
#include <linux/mmzone.h>
|
|
|
|
|
#include <linux/list.h>
|
2008-02-07 08:13:56 +00:00
|
|
|
#include <linux/memcontrol.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <linux/sched.h>
|
2008-10-19 03:26:53 +00:00
|
|
|
#include <linux/node.h>
|
2013-02-23 00:34:37 +00:00
|
|
|
#include <linux/fs.h>
|
2021-05-07 01:02:27 +00:00
|
|
|
#include <linux/pagemap.h>
|
2011-07-26 23:09:06 +00:00
|
|
|
#include <linux/atomic.h>
|
2013-07-03 22:02:34 +00:00
|
|
|
#include <linux/page-flags.h>
|
2021-05-05 01:36:04 +00:00
|
|
|
#include <uapi/linux/mempolicy.h>
|
2005-04-16 22:20:36 +00:00
|
|
|
#include <asm/page.h>
|
|
|
|
|
|
2006-09-26 06:31:20 +00:00
|
|
|
struct notifier_block;
|
|
|
|
|
|
2006-09-26 06:32:42 +00:00
|
|
|
struct bio;
|
|
|
|
|
|
2018-11-06 13:23:24 +00:00
|
|
|
struct pagevec;
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
#define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */
|
|
|
|
|
#define SWAP_FLAG_PRIO_MASK 0x7fff
|
|
|
|
|
#define SWAP_FLAG_PRIO_SHIFT 0
|
swap: discard while swapping only if SWAP_FLAG_DISCARD_PAGES
Considering the use cases where the swap device supports discard:
a) and can do it quickly;
b) but it's slow to do in small granularities (or concurrent with other
I/O);
c) but the implementation is so horrendous that you don't even want to
send one down;
And assuming that the sysadmin considers it useful to send the discards down
at all, we would (probably) want the following solutions:
i. do the fine-grained discards for freed swap pages, if device is
capable of doing so optimally;
ii. do single-time (batched) swap area discards, either at swapon
or via something like fstrim (not implemented yet);
iii. allow doing both single-time and fine-grained discards; or
iv. turn it off completely (default behavior)
As implemented today, one can only enable/disable discards for swap, but
one cannot select, for instance, solution (ii) on a swap device like (b)
even though the single-time discard is regarded to be interesting, or
necessary to the workload because it would imply (1), and the device is
not capable of performing it optimally.
This patch addresses the scenario depicted above by introducing a way to
ensure the (probably) wanted solutions (i, ii, iii and iv) can be flexibly
flagged through swapon(8) to allow a sysadmin to select the best suitable
swap discard policy accordingly to system constraints.
This patch introduces SWAP_FLAG_DISCARD_PAGES and SWAP_FLAG_DISCARD_ONCE
new flags to allow more flexibe swap discard policies being flagged
through swapon(8). The default behavior is to keep both single-time, or
batched, area discards (SWAP_FLAG_DISCARD_ONCE) and fine-grained discards
for page-clusters (SWAP_FLAG_DISCARD_PAGES) enabled, in order to keep
consistentcy with older kernel behavior, as well as maintain compatibility
with older swapon(8). However, through the new introduced flags the best
suitable discard policy can be selected accordingly to any given swap
device constraint.
[akpm@linux-foundation.org: tweak comments]
Signed-off-by: Rafael Aquini <aquini@redhat.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Karel Zak <kzak@redhat.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-03 22:02:46 +00:00
|
|
|
#define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */
|
|
|
|
|
#define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */
|
|
|
|
|
#define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2012-03-28 21:42:42 +00:00
|
|
|
#define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \
|
swap: discard while swapping only if SWAP_FLAG_DISCARD_PAGES
Considering the use cases where the swap device supports discard:
a) and can do it quickly;
b) but it's slow to do in small granularities (or concurrent with other
I/O);
c) but the implementation is so horrendous that you don't even want to
send one down;
And assuming that the sysadmin considers it useful to send the discards down
at all, we would (probably) want the following solutions:
i. do the fine-grained discards for freed swap pages, if device is
capable of doing so optimally;
ii. do single-time (batched) swap area discards, either at swapon
or via something like fstrim (not implemented yet);
iii. allow doing both single-time and fine-grained discards; or
iv. turn it off completely (default behavior)
As implemented today, one can only enable/disable discards for swap, but
one cannot select, for instance, solution (ii) on a swap device like (b)
even though the single-time discard is regarded to be interesting, or
necessary to the workload because it would imply (1), and the device is
not capable of performing it optimally.
This patch addresses the scenario depicted above by introducing a way to
ensure the (probably) wanted solutions (i, ii, iii and iv) can be flexibly
flagged through swapon(8) to allow a sysadmin to select the best suitable
swap discard policy accordingly to system constraints.
This patch introduces SWAP_FLAG_DISCARD_PAGES and SWAP_FLAG_DISCARD_ONCE
new flags to allow more flexibe swap discard policies being flagged
through swapon(8). The default behavior is to keep both single-time, or
batched, area discards (SWAP_FLAG_DISCARD_ONCE) and fine-grained discards
for page-clusters (SWAP_FLAG_DISCARD_PAGES) enabled, in order to keep
consistentcy with older kernel behavior, as well as maintain compatibility
with older swapon(8). However, through the new introduced flags the best
suitable discard policy can be selected accordingly to any given swap
device constraint.
[akpm@linux-foundation.org: tweak comments]
Signed-off-by: Rafael Aquini <aquini@redhat.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Karel Zak <kzak@redhat.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-03 22:02:46 +00:00
|
|
|
SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \
|
|
|
|
|
SWAP_FLAG_DISCARD_PAGES)
|
2017-02-22 23:45:33 +00:00
|
|
|
#define SWAP_BATCH 64
|
2012-03-28 21:42:42 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
static inline int current_is_kswapd(void)
|
|
|
|
|
{
|
|
|
|
|
return current->flags & PF_KSWAPD;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* MAX_SWAPFILES defines the maximum number of swaptypes: things which can
|
|
|
|
|
* be swapped to. The swap type and the offset into that swap type are
|
|
|
|
|
* encoded into pte's and into pgoff_t's in the swapcache. Using five bits
|
|
|
|
|
* for the type means that the maximum number of swapcache pages is 27 bits
|
|
|
|
|
* on 32-bit-pgoff_t architectures. And that assumes that the architecture packs
|
|
|
|
|
* the type/offset into the pte as 5/27 as well.
|
|
|
|
|
*/
|
|
|
|
|
#define MAX_SWAPFILES_SHIFT 5
|
2009-09-16 09:50:05 +00:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Use some of the swap files numbers for other purposes. This
|
|
|
|
|
* is a convenient way to hook into the VM to trigger special
|
|
|
|
|
* actions on faults.
|
|
|
|
|
*/
|
|
|
|
|
|
mm: introduce PTE_MARKER swap entry
Patch series "userfaultfd-wp: Support shmem and hugetlbfs", v8.
Overview
========
Userfaultfd-wp anonymous support was merged two years ago. There're quite
a few applications that started to leverage this capability either to take
snapshots for user-app memory, or use it for full user controled swapping.
This series tries to complete the feature for uffd-wp so as to cover all
the RAM-based memory types. So far uffd-wp is the only missing piece of
the rest features (uffd-missing & uffd-minor mode).
One major reason to do so is that anonymous pages are sometimes not
satisfying the need of applications, and there're growing users of either
shmem and hugetlbfs for either sharing purpose (e.g., sharing guest mem
between hypervisor process and device emulation process, shmem local live
migration for upgrades), or for performance on tlb hits.
All these mean that if a uffd-wp app wants to switch to any of the memory
types, it'll stop working. I think it's worthwhile to have the kernel to
cover all these aspects.
This series chose to protect pages in pte level not page level.
One major reason is safety. I have no idea how we could make it safe if
any of the uffd-privileged app can wr-protect a page that any other
application can use. It means this app can block any process potentially
for any time it wants.
The other reason is that it aligns very well with not only the anonymous
uffd-wp solution, but also uffd as a whole. For example, userfaultfd is
implemented fundamentally based on VMAs. We set flags to VMAs showing the
status of uffd tracking. For another per-page based protection solution,
it'll be crossing the fundation line on VMA-based, and it could simply be
too far away already from what's called userfaultfd.
PTE markers
===========
The patchset is based on the idea called PTE markers. It was discussed in
one of the mm alignment sessions, proposed starting from v6, and this is
the 2nd version of it using PTE marker idea.
PTE marker is a new type of swap entry that is ony applicable to file
backed memories like shmem and hugetlbfs. It's used to persist some
pte-level information even if the original present ptes in pgtable are
zapped.
Logically pte markers can store more than uffd-wp information, but so far
only one bit is used for uffd-wp purpose. When the pte marker is
installed with uffd-wp bit set, it means this pte is wr-protected by uffd.
It solves the problem on e.g. file-backed memory mapped ptes got zapped
due to any reason (e.g. thp split, or swapped out), we can still keep the
wr-protect information in the ptes. Then when the page fault triggers
again, we'll know this pte is wr-protected so we can treat the pte the
same as a normal uffd wr-protected pte.
The extra information is encoded into the swap entry, or swp_offset to be
explicit, with the swp_type being PTE_MARKER. So far uffd-wp only uses
one bit out of the swap entry, the rest bits of swp_offset are still
reserved for other purposes.
There're two configs to enable/disable PTE markers:
CONFIG_PTE_MARKER
CONFIG_PTE_MARKER_UFFD_WP
We can set !PTE_MARKER to completely disable all the PTE markers, along
with uffd-wp support. I made two config so we can also enable PTE marker
but disable uffd-wp file-backed for other purposes. At the end of current
series, I'll enable CONFIG_PTE_MARKER by default, but that patch is
standalone and if anyone worries about having it by default, we can also
consider turn it off by dropping that oneliner patch. So far I don't see
a huge risk of doing so, so I kept that patch.
In most cases, PTE markers should be treated as none ptes. It is because
that unlike most of the other swap entry types, there's no PFN or block
offset information encoded into PTE markers but some extra well-defined
bits showing the status of the pte. These bits should only be used as
extra data when servicing an upcoming page fault, and then we behave as if
it's a none pte.
I did spend a lot of time observing all the pte_none() users this time.
It is indeed a challenge because there're a lot, and I hope I didn't miss
a single of them when we should take care of pte markers. Luckily, I
don't think it'll need to be considered in many cases, for example: boot
code, arch code (especially non-x86), kernel-only page handlings (e.g.
CPA), or device driver codes when we're tackling with pure PFN mappings.
I introduced pte_none_mostly() in this series when we need to handle pte
markers the same as none pte, the "mostly" is the other way to write
"either none pte or a pte marker".
I didn't replace pte_none() to cover pte markers for below reasons:
- Very rare case of pte_none() callers will handle pte markers. E.g., all
the kernel pages do not require knowledge of pte markers. So we don't
pollute the major use cases.
- Unconditionally change pte_none() semantics could confuse people, because
pte_none() existed for so long a time.
- Unconditionally change pte_none() semantics could make pte_none() slower
even if in many cases pte markers do not exist.
- There're cases where we'd like to handle pte markers differntly from
pte_none(), so a full replace is also impossible. E.g. khugepaged should
still treat pte markers as normal swap ptes rather than none ptes, because
pte markers will always need a fault-in to merge the marker with a valid
pte. Or the smap code will need to parse PTE markers not none ptes.
Patch Layout
============
Introducing PTE marker and uffd-wp bit in PTE marker:
mm: Introduce PTE_MARKER swap entry
mm: Teach core mm about pte markers
mm: Check against orig_pte for finish_fault()
mm/uffd: PTE_MARKER_UFFD_WP
Adding support for shmem uffd-wp:
mm/shmem: Take care of UFFDIO_COPY_MODE_WP
mm/shmem: Handle uffd-wp special pte in page fault handler
mm/shmem: Persist uffd-wp bit across zapping for file-backed
mm/shmem: Allow uffd wr-protect none pte for file-backed mem
mm/shmem: Allows file-back mem to be uffd wr-protected on thps
mm/shmem: Handle uffd-wp during fork()
Adding support for hugetlbfs uffd-wp:
mm/hugetlb: Introduce huge pte version of uffd-wp helpers
mm/hugetlb: Hook page faults for uffd write protection
mm/hugetlb: Take care of UFFDIO_COPY_MODE_WP
mm/hugetlb: Handle UFFDIO_WRITEPROTECT
mm/hugetlb: Handle pte markers in page faults
mm/hugetlb: Allow uffd wr-protect none ptes
mm/hugetlb: Only drop uffd-wp special pte if required
mm/hugetlb: Handle uffd-wp during fork()
Misc handling on the rest mm for uffd-wp file-backed:
mm/khugepaged: Don't recycle vma pgtable if uffd-wp registered
mm/pagemap: Recognize uffd-wp bit for shmem/hugetlbfs
Enabling of uffd-wp on file-backed memory:
mm/uffd: Enable write protection for shmem & hugetlbfs
mm: Enable PTE markers by default
selftests/uffd: Enable uffd-wp for shmem/hugetlbfs
Tests
=====
- Compile test on x86_64 and aarch64 on different configs
- Kernel selftests
- uffd-test [0]
- Umapsort [1,2] test for shmem/hugetlb, with swap on/off
[0] https://github.com/xzpeter/clibs/tree/master/uffd-test
[1] https://github.com/xzpeter/umap-apps/tree/peter
[2] https://github.com/xzpeter/umap/tree/peter-shmem-hugetlbfs
This patch (of 23):
Introduces a new swap entry type called PTE_MARKER. It can be installed
for any pte that maps a file-backed memory when the pte is temporarily
zapped, so as to maintain per-pte information.
The information that kept in the pte is called a "marker". Here we define
the marker as "unsigned long" just to match pgoff_t, however it will only
work if it still fits in swp_offset(), which is e.g. currently 58 bits on
x86_64.
A new config CONFIG_PTE_MARKER is introduced too; it's by default off. A
bunch of helpers are defined altogether to service the rest of the pte
marker code.
[peterx@redhat.com: fixup]
Link: https://lkml.kernel.org/r/Yk2rdB7SXZf+2BDF@xz-m1.local
Link: https://lkml.kernel.org/r/20220405014646.13522-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20220405014646.13522-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-13 03:22:52 +00:00
|
|
|
/*
|
2022-10-30 21:41:50 +00:00
|
|
|
* PTE markers are used to persist information onto PTEs that otherwise
|
|
|
|
|
* should be a none pte. As its name "PTE" hints, it should only be
|
|
|
|
|
* applied to the leaves of pgtables.
|
mm: introduce PTE_MARKER swap entry
Patch series "userfaultfd-wp: Support shmem and hugetlbfs", v8.
Overview
========
Userfaultfd-wp anonymous support was merged two years ago. There're quite
a few applications that started to leverage this capability either to take
snapshots for user-app memory, or use it for full user controled swapping.
This series tries to complete the feature for uffd-wp so as to cover all
the RAM-based memory types. So far uffd-wp is the only missing piece of
the rest features (uffd-missing & uffd-minor mode).
One major reason to do so is that anonymous pages are sometimes not
satisfying the need of applications, and there're growing users of either
shmem and hugetlbfs for either sharing purpose (e.g., sharing guest mem
between hypervisor process and device emulation process, shmem local live
migration for upgrades), or for performance on tlb hits.
All these mean that if a uffd-wp app wants to switch to any of the memory
types, it'll stop working. I think it's worthwhile to have the kernel to
cover all these aspects.
This series chose to protect pages in pte level not page level.
One major reason is safety. I have no idea how we could make it safe if
any of the uffd-privileged app can wr-protect a page that any other
application can use. It means this app can block any process potentially
for any time it wants.
The other reason is that it aligns very well with not only the anonymous
uffd-wp solution, but also uffd as a whole. For example, userfaultfd is
implemented fundamentally based on VMAs. We set flags to VMAs showing the
status of uffd tracking. For another per-page based protection solution,
it'll be crossing the fundation line on VMA-based, and it could simply be
too far away already from what's called userfaultfd.
PTE markers
===========
The patchset is based on the idea called PTE markers. It was discussed in
one of the mm alignment sessions, proposed starting from v6, and this is
the 2nd version of it using PTE marker idea.
PTE marker is a new type of swap entry that is ony applicable to file
backed memories like shmem and hugetlbfs. It's used to persist some
pte-level information even if the original present ptes in pgtable are
zapped.
Logically pte markers can store more than uffd-wp information, but so far
only one bit is used for uffd-wp purpose. When the pte marker is
installed with uffd-wp bit set, it means this pte is wr-protected by uffd.
It solves the problem on e.g. file-backed memory mapped ptes got zapped
due to any reason (e.g. thp split, or swapped out), we can still keep the
wr-protect information in the ptes. Then when the page fault triggers
again, we'll know this pte is wr-protected so we can treat the pte the
same as a normal uffd wr-protected pte.
The extra information is encoded into the swap entry, or swp_offset to be
explicit, with the swp_type being PTE_MARKER. So far uffd-wp only uses
one bit out of the swap entry, the rest bits of swp_offset are still
reserved for other purposes.
There're two configs to enable/disable PTE markers:
CONFIG_PTE_MARKER
CONFIG_PTE_MARKER_UFFD_WP
We can set !PTE_MARKER to completely disable all the PTE markers, along
with uffd-wp support. I made two config so we can also enable PTE marker
but disable uffd-wp file-backed for other purposes. At the end of current
series, I'll enable CONFIG_PTE_MARKER by default, but that patch is
standalone and if anyone worries about having it by default, we can also
consider turn it off by dropping that oneliner patch. So far I don't see
a huge risk of doing so, so I kept that patch.
In most cases, PTE markers should be treated as none ptes. It is because
that unlike most of the other swap entry types, there's no PFN or block
offset information encoded into PTE markers but some extra well-defined
bits showing the status of the pte. These bits should only be used as
extra data when servicing an upcoming page fault, and then we behave as if
it's a none pte.
I did spend a lot of time observing all the pte_none() users this time.
It is indeed a challenge because there're a lot, and I hope I didn't miss
a single of them when we should take care of pte markers. Luckily, I
don't think it'll need to be considered in many cases, for example: boot
code, arch code (especially non-x86), kernel-only page handlings (e.g.
CPA), or device driver codes when we're tackling with pure PFN mappings.
I introduced pte_none_mostly() in this series when we need to handle pte
markers the same as none pte, the "mostly" is the other way to write
"either none pte or a pte marker".
I didn't replace pte_none() to cover pte markers for below reasons:
- Very rare case of pte_none() callers will handle pte markers. E.g., all
the kernel pages do not require knowledge of pte markers. So we don't
pollute the major use cases.
- Unconditionally change pte_none() semantics could confuse people, because
pte_none() existed for so long a time.
- Unconditionally change pte_none() semantics could make pte_none() slower
even if in many cases pte markers do not exist.
- There're cases where we'd like to handle pte markers differntly from
pte_none(), so a full replace is also impossible. E.g. khugepaged should
still treat pte markers as normal swap ptes rather than none ptes, because
pte markers will always need a fault-in to merge the marker with a valid
pte. Or the smap code will need to parse PTE markers not none ptes.
Patch Layout
============
Introducing PTE marker and uffd-wp bit in PTE marker:
mm: Introduce PTE_MARKER swap entry
mm: Teach core mm about pte markers
mm: Check against orig_pte for finish_fault()
mm/uffd: PTE_MARKER_UFFD_WP
Adding support for shmem uffd-wp:
mm/shmem: Take care of UFFDIO_COPY_MODE_WP
mm/shmem: Handle uffd-wp special pte in page fault handler
mm/shmem: Persist uffd-wp bit across zapping for file-backed
mm/shmem: Allow uffd wr-protect none pte for file-backed mem
mm/shmem: Allows file-back mem to be uffd wr-protected on thps
mm/shmem: Handle uffd-wp during fork()
Adding support for hugetlbfs uffd-wp:
mm/hugetlb: Introduce huge pte version of uffd-wp helpers
mm/hugetlb: Hook page faults for uffd write protection
mm/hugetlb: Take care of UFFDIO_COPY_MODE_WP
mm/hugetlb: Handle UFFDIO_WRITEPROTECT
mm/hugetlb: Handle pte markers in page faults
mm/hugetlb: Allow uffd wr-protect none ptes
mm/hugetlb: Only drop uffd-wp special pte if required
mm/hugetlb: Handle uffd-wp during fork()
Misc handling on the rest mm for uffd-wp file-backed:
mm/khugepaged: Don't recycle vma pgtable if uffd-wp registered
mm/pagemap: Recognize uffd-wp bit for shmem/hugetlbfs
Enabling of uffd-wp on file-backed memory:
mm/uffd: Enable write protection for shmem & hugetlbfs
mm: Enable PTE markers by default
selftests/uffd: Enable uffd-wp for shmem/hugetlbfs
Tests
=====
- Compile test on x86_64 and aarch64 on different configs
- Kernel selftests
- uffd-test [0]
- Umapsort [1,2] test for shmem/hugetlb, with swap on/off
[0] https://github.com/xzpeter/clibs/tree/master/uffd-test
[1] https://github.com/xzpeter/umap-apps/tree/peter
[2] https://github.com/xzpeter/umap/tree/peter-shmem-hugetlbfs
This patch (of 23):
Introduces a new swap entry type called PTE_MARKER. It can be installed
for any pte that maps a file-backed memory when the pte is temporarily
zapped, so as to maintain per-pte information.
The information that kept in the pte is called a "marker". Here we define
the marker as "unsigned long" just to match pgoff_t, however it will only
work if it still fits in swp_offset(), which is e.g. currently 58 bits on
x86_64.
A new config CONFIG_PTE_MARKER is introduced too; it's by default off. A
bunch of helpers are defined altogether to service the rest of the pte
marker code.
[peterx@redhat.com: fixup]
Link: https://lkml.kernel.org/r/Yk2rdB7SXZf+2BDF@xz-m1.local
Link: https://lkml.kernel.org/r/20220405014646.13522-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20220405014646.13522-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-05-13 03:22:52 +00:00
|
|
|
*/
|
|
|
|
|
#define SWP_PTE_MARKER_NUM 1
|
|
|
|
|
#define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \
|
|
|
|
|
SWP_MIGRATION_NUM + SWP_DEVICE_NUM)
|
|
|
|
|
|
2017-09-08 23:11:43 +00:00
|
|
|
/*
|
|
|
|
|
* Unaddressable device memory support. See include/linux/hmm.h and
|
2022-06-27 06:00:26 +00:00
|
|
|
* Documentation/mm/hmm.rst. Short description is we need struct pages for
|
2017-09-08 23:11:43 +00:00
|
|
|
* device memory that is unaddressable (inaccessible) by CPU, so that we can
|
|
|
|
|
* migrate part of a process memory to device memory.
|
|
|
|
|
*
|
|
|
|
|
* When a page is migrated from CPU to device, we set the CPU page table entry
|
2021-07-01 01:54:25 +00:00
|
|
|
* to a special SWP_DEVICE_{READ|WRITE} entry.
|
|
|
|
|
*
|
|
|
|
|
* When a page is mapped by the device for exclusive access we set the CPU page
|
|
|
|
|
* table entries to special SWP_DEVICE_EXCLUSIVE_* entries.
|
2017-09-08 23:11:43 +00:00
|
|
|
*/
|
|
|
|
|
#ifdef CONFIG_DEVICE_PRIVATE
|
2021-07-01 01:54:25 +00:00
|
|
|
#define SWP_DEVICE_NUM 4
|
2017-09-08 23:11:43 +00:00
|
|
|
#define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM)
|
|
|
|
|
#define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1)
|
2021-07-01 01:54:25 +00:00
|
|
|
#define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2)
|
|
|
|
|
#define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3)
|
2017-09-08 23:11:43 +00:00
|
|
|
#else
|
|
|
|
|
#define SWP_DEVICE_NUM 0
|
|
|
|
|
#endif
|
|
|
|
|
|
2009-09-16 09:50:05 +00:00
|
|
|
/*
|
mm: remember exclusively mapped anonymous pages with PG_anon_exclusive
Let's mark exclusively mapped anonymous pages with PG_anon_exclusive as
exclusive, and use that information to make GUP pins reliable and stay
consistent with the page mapped into the page table even if the page table
entry gets write-protected.
With that information at hand, we can extend our COW logic to always reuse
anonymous pages that are exclusive. For anonymous pages that might be
shared, the existing logic applies.
As already documented, PG_anon_exclusive is usually only expressive in
combination with a page table entry. Especially PTE vs. PMD-mapped
anonymous pages require more thought, some examples: due to mremap() we
can easily have a single compound page PTE-mapped into multiple page
tables exclusively in a single process -- multiple page table locks apply.
Further, due to MADV_WIPEONFORK we might not necessarily write-protect
all PTEs, and only some subpages might be pinned. Long story short: once
PTE-mapped, we have to track information about exclusivity per sub-page,
but until then, we can just track it for the compound page in the head
page and not having to update a whole bunch of subpages all of the time
for a simple PMD mapping of a THP.
For simplicity, this commit mostly talks about "anonymous pages", while
it's for THP actually "the part of an anonymous folio referenced via a
page table entry".
To not spill PG_anon_exclusive code all over the mm code-base, we let the
anon rmap code to handle all PG_anon_exclusive logic it can easily handle.
If a writable, present page table entry points at an anonymous (sub)page,
that (sub)page must be PG_anon_exclusive. If GUP wants to take a reliably
pin (FOLL_PIN) on an anonymous page references via a present page table
entry, it must only pin if PG_anon_exclusive is set for the mapped
(sub)page.
This commit doesn't adjust GUP, so this is only implicitly handled for
FOLL_WRITE, follow-up commits will teach GUP to also respect it for
FOLL_PIN without FOLL_WRITE, to make all GUP pins of anonymous pages fully
reliable.
Whenever an anonymous page is to be shared (fork(), KSM), or when
temporarily unmapping an anonymous page (swap, migration), the relevant
PG_anon_exclusive bit has to be cleared to mark the anonymous page
possibly shared. Clearing will fail if there are GUP pins on the page:
* For fork(), this means having to copy the page and not being able to
share it. fork() protects against concurrent GUP using the PT lock and
the src_mm->write_protect_seq.
* For KSM, this means sharing will fail. For swap this means, unmapping
will fail, For migration this means, migration will fail early. All
three cases protect against concurrent GUP using the PT lock and a
proper clear/invalidate+flush of the relevant page table entry.
This fixes memory corruptions reported for FOLL_PIN | FOLL_WRITE, when a
pinned page gets mapped R/O and the successive write fault ends up
replacing the page instead of reusing it. It improves the situation for
O_DIRECT/vmsplice/... that still use FOLL_GET instead of FOLL_PIN, if
fork() is *not* involved, however swapout and fork() are still
problematic. Properly using FOLL_PIN instead of FOLL_GET for these GUP
users will fix the issue for them.
I. Details about basic handling
I.1. Fresh anonymous pages
page_add_new_anon_rmap() and hugepage_add_new_anon_rmap() will mark the
given page exclusive via __page_set_anon_rmap(exclusive=1). As that is
the mechanism fresh anonymous pages come into life (besides migration code
where we copy the page->mapping), all fresh anonymous pages will start out
as exclusive.
I.2. COW reuse handling of anonymous pages
When a COW handler stumbles over a (sub)page that's marked exclusive, it
simply reuses it. Otherwise, the handler tries harder under page lock to
detect if the (sub)page is exclusive and can be reused. If exclusive,
page_move_anon_rmap() will mark the given (sub)page exclusive.
Note that hugetlb code does not yet check for PageAnonExclusive(), as it
still uses the old COW logic that is prone to the COW security issue
because hugetlb code cannot really tolerate unnecessary/wrong COW as huge
pages are a scarce resource.
I.3. Migration handling
try_to_migrate() has to try marking an exclusive anonymous page shared via
page_try_share_anon_rmap(). If it fails because there are GUP pins on the
page, unmap fails. migrate_vma_collect_pmd() and
__split_huge_pmd_locked() are handled similarly.
Writable migration entries implicitly point at shared anonymous pages.
For readable migration entries that information is stored via a new
"readable-exclusive" migration entry, specific to anonymous pages.
When restoring a migration entry in remove_migration_pte(), information
about exlusivity is detected via the migration entry type, and
RMAP_EXCLUSIVE is set accordingly for
page_add_anon_rmap()/hugepage_add_anon_rmap() to restore that information.
I.4. Swapout handling
try_to_unmap() has to try marking the mapped page possibly shared via
page_try_share_anon_rmap(). If it fails because there are GUP pins on the
page, unmap fails. For now, information about exclusivity is lost. In
the future, we might want to remember that information in the swap entry
in some cases, however, it requires more thought, care, and a way to store
that information in swap entries.
I.5. Swapin handling
do_swap_page() will never stumble over exclusive anonymous pages in the
swap cache, as try_to_migrate() prohibits that. do_swap_page() always has
to detect manually if an anonymous page is exclusive and has to set
RMAP_EXCLUSIVE for page_add_anon_rmap() accordingly.
I.6. THP handling
__split_huge_pmd_locked() has to move the information about exclusivity
from the PMD to the PTEs.
a) In case we have a readable-exclusive PMD migration entry, simply
insert readable-exclusive PTE migration entries.
b) In case we have a present PMD entry and we don't want to freeze
("convert to migration entries"), simply forward PG_anon_exclusive to
all sub-pages, no need to temporarily clear the bit.
c) In case we have a present PMD entry and want to freeze, handle it
similar to try_to_migrate(): try marking the page shared first. In
case we fail, we ignore the "freeze" instruction and simply split
ordinarily. try_to_migrate() will properly fail because the THP is
still mapped via PTEs.
When splitting a compound anonymous folio (THP), the information about
exclusivity is implicitly handled via the migration entries: no need to
replicate PG_anon_exclusive manually.
I.7. fork() handling fork() handling is relatively easy, because
PG_anon_exclusive is only expressive for some page table entry types.
a) Present anonymous pages
page_try_dup_anon_rmap() will mark the given subpage shared -- which will
fail if the page is pinned. If it failed, we have to copy (or PTE-map a
PMD to handle it on the PTE level).
Note that device exclusive entries are just a pointer at a PageAnon()
page. fork() will first convert a device exclusive entry to a present
page table and handle it just like present anonymous pages.
b) Device private entry
Device private entries point at PageAnon() pages that cannot be mapped
directly and, therefore, cannot get pinned.
page_try_dup_anon_rmap() will mark the given subpage shared, which cannot
fail because they cannot get pinned.
c) HW poison entries
PG_anon_exclusive will remain untouched and is stale -- the page table
entry is just a placeholder after all.
d) Migration entries
Writable and readable-exclusive entries are converted to readable entries:
possibly shared.
I.8. mprotect() handling
mprotect() only has to properly handle the new readable-exclusive
migration entry:
When write-protecting a migration entry that points at an anonymous page,
remember the information about exclusivity via the "readable-exclusive"
migration entry type.
II. Migration and GUP-fast
Whenever replacing a present page table entry that maps an exclusive
anonymous page by a migration entry, we have to mark the page possibly
shared and synchronize against GUP-fast by a proper clear/invalidate+flush
to make the following scenario impossible:
1. try_to_migrate() places a migration entry after checking for GUP pins
and marks the page possibly shared.
2. GUP-fast pins the page due to lack of synchronization
3. fork() converts the "writable/readable-exclusive" migration entry into a
readable migration entry
4. Migration fails due to the GUP pin (failing to freeze the refcount)
5. Migration entries are restored. PG_anon_exclusive is lost
-> We have a pinned page that is not marked exclusive anymore.
Note that we move information about exclusivity from the page to the
migration entry as it otherwise highly overcomplicates fork() and
PTE-mapping a THP.
III. Swapout and GUP-fast
Whenever replacing a present page table entry that maps an exclusive
anonymous page by a swap entry, we have to mark the page possibly shared
and synchronize against GUP-fast by a proper clear/invalidate+flush to
make the following scenario impossible:
1. try_to_unmap() places a swap entry after checking for GUP pins and
clears exclusivity information on the page.
2. GUP-fast pins the page due to lack of synchronization.
-> We have a pinned page that is not marked exclusive anymore.
If we'd ever store information about exclusivity in the swap entry,
similar to migration handling, the same considerations as in II would
apply. This is future work.
Link: https://lkml.kernel.org/r/20220428083441.37290-13-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>
2022-05-10 01:20:44 +00:00
|
|
|
* Page migration support.
|
|
|
|
|
*
|
|
|
|
|
* SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and
|
|
|
|
|
* indicates that the referenced (part of) an anonymous page is exclusive to
|
|
|
|
|
* a single process. For SWP_MIGRATION_WRITE, that information is implicit:
|
|
|
|
|
* (part of) an anonymous page that are mapped writable are exclusive to a
|
|
|
|
|
* single process.
|
2009-09-16 09:50:05 +00:00
|
|
|
*/
|
|
|
|
|
#ifdef CONFIG_MIGRATION
|
mm: remember exclusively mapped anonymous pages with PG_anon_exclusive
Let's mark exclusively mapped anonymous pages with PG_anon_exclusive as
exclusive, and use that information to make GUP pins reliable and stay
consistent with the page mapped into the page table even if the page table
entry gets write-protected.
With that information at hand, we can extend our COW logic to always reuse
anonymous pages that are exclusive. For anonymous pages that might be
shared, the existing logic applies.
As already documented, PG_anon_exclusive is usually only expressive in
combination with a page table entry. Especially PTE vs. PMD-mapped
anonymous pages require more thought, some examples: due to mremap() we
can easily have a single compound page PTE-mapped into multiple page
tables exclusively in a single process -- multiple page table locks apply.
Further, due to MADV_WIPEONFORK we might not necessarily write-protect
all PTEs, and only some subpages might be pinned. Long story short: once
PTE-mapped, we have to track information about exclusivity per sub-page,
but until then, we can just track it for the compound page in the head
page and not having to update a whole bunch of subpages all of the time
for a simple PMD mapping of a THP.
For simplicity, this commit mostly talks about "anonymous pages", while
it's for THP actually "the part of an anonymous folio referenced via a
page table entry".
To not spill PG_anon_exclusive code all over the mm code-base, we let the
anon rmap code to handle all PG_anon_exclusive logic it can easily handle.
If a writable, present page table entry points at an anonymous (sub)page,
that (sub)page must be PG_anon_exclusive. If GUP wants to take a reliably
pin (FOLL_PIN) on an anonymous page references via a present page table
entry, it must only pin if PG_anon_exclusive is set for the mapped
(sub)page.
This commit doesn't adjust GUP, so this is only implicitly handled for
FOLL_WRITE, follow-up commits will teach GUP to also respect it for
FOLL_PIN without FOLL_WRITE, to make all GUP pins of anonymous pages fully
reliable.
Whenever an anonymous page is to be shared (fork(), KSM), or when
temporarily unmapping an anonymous page (swap, migration), the relevant
PG_anon_exclusive bit has to be cleared to mark the anonymous page
possibly shared. Clearing will fail if there are GUP pins on the page:
* For fork(), this means having to copy the page and not being able to
share it. fork() protects against concurrent GUP using the PT lock and
the src_mm->write_protect_seq.
* For KSM, this means sharing will fail. For swap this means, unmapping
will fail, For migration this means, migration will fail early. All
three cases protect against concurrent GUP using the PT lock and a
proper clear/invalidate+flush of the relevant page table entry.
This fixes memory corruptions reported for FOLL_PIN | FOLL_WRITE, when a
pinned page gets mapped R/O and the successive write fault ends up
replacing the page instead of reusing it. It improves the situation for
O_DIRECT/vmsplice/... that still use FOLL_GET instead of FOLL_PIN, if
fork() is *not* involved, however swapout and fork() are still
problematic. Properly using FOLL_PIN instead of FOLL_GET for these GUP
users will fix the issue for them.
I. Details about basic handling
I.1. Fresh anonymous pages
page_add_new_anon_rmap() and hugepage_add_new_anon_rmap() will mark the
given page exclusive via __page_set_anon_rmap(exclusive=1). As that is
the mechanism fresh anonymous pages come into life (besides migration code
where we copy the page->mapping), all fresh anonymous pages will start out
as exclusive.
I.2. COW reuse handling of anonymous pages
When a COW handler stumbles over a (sub)page that's marked exclusive, it
simply reuses it. Otherwise, the handler tries harder under page lock to
detect if the (sub)page is exclusive and can be reused. If exclusive,
page_move_anon_rmap() will mark the given (sub)page exclusive.
Note that hugetlb code does not yet check for PageAnonExclusive(), as it
still uses the old COW logic that is prone to the COW security issue
because hugetlb code cannot really tolerate unnecessary/wrong COW as huge
pages are a scarce resource.
I.3. Migration handling
try_to_migrate() has to try marking an exclusive anonymous page shared via
page_try_share_anon_rmap(). If it fails because there are GUP pins on the
page, unmap fails. migrate_vma_collect_pmd() and
__split_huge_pmd_locked() are handled similarly.
Writable migration entries implicitly point at shared anonymous pages.
For readable migration entries that information is stored via a new
"readable-exclusive" migration entry, specific to anonymous pages.
When restoring a migration entry in remove_migration_pte(), information
about exlusivity is detected via the migration entry type, and
RMAP_EXCLUSIVE is set accordingly for
page_add_anon_rmap()/hugepage_add_anon_rmap() to restore that information.
I.4. Swapout handling
try_to_unmap() has to try marking the mapped page possibly shared via
page_try_share_anon_rmap(). If it fails because there are GUP pins on the
page, unmap fails. For now, information about exclusivity is lost. In
the future, we might want to remember that information in the swap entry
in some cases, however, it requires more thought, care, and a way to store
that information in swap entries.
I.5. Swapin handling
do_swap_page() will never stumble over exclusive anonymous pages in the
swap cache, as try_to_migrate() prohibits that. do_swap_page() always has
to detect manually if an anonymous page is exclusive and has to set
RMAP_EXCLUSIVE for page_add_anon_rmap() accordingly.
I.6. THP handling
__split_huge_pmd_locked() has to move the information about exclusivity
from the PMD to the PTEs.
a) In case we have a readable-exclusive PMD migration entry, simply
insert readable-exclusive PTE migration entries.
b) In case we have a present PMD entry and we don't want to freeze
("convert to migration entries"), simply forward PG_anon_exclusive to
all sub-pages, no need to temporarily clear the bit.
c) In case we have a present PMD entry and want to freeze, handle it
similar to try_to_migrate(): try marking the page shared first. In
case we fail, we ignore the "freeze" instruction and simply split
ordinarily. try_to_migrate() will properly fail because the THP is
still mapped via PTEs.
When splitting a compound anonymous folio (THP), the information about
exclusivity is implicitly handled via the migration entries: no need to
replicate PG_anon_exclusive manually.
I.7. fork() handling fork() handling is relatively easy, because
PG_anon_exclusive is only expressive for some page table entry types.
a) Present anonymous pages
page_try_dup_anon_rmap() will mark the given subpage shared -- which will
fail if the page is pinned. If it failed, we have to copy (or PTE-map a
PMD to handle it on the PTE level).
Note that device exclusive entries are just a pointer at a PageAnon()
page. fork() will first convert a device exclusive entry to a present
page table and handle it just like present anonymous pages.
b) Device private entry
Device private entries point at PageAnon() pages that cannot be mapped
directly and, therefore, cannot get pinned.
page_try_dup_anon_rmap() will mark the given subpage shared, which cannot
fail because they cannot get pinned.
c) HW poison entries
PG_anon_exclusive will remain untouched and is stale -- the page table
entry is just a placeholder after all.
d) Migration entries
Writable and readable-exclusive entries are converted to readable entries:
possibly shared.
I.8. mprotect() handling
mprotect() only has to properly handle the new readable-exclusive
migration entry:
When write-protecting a migration entry that points at an anonymous page,
remember the information about exclusivity via the "readable-exclusive"
migration entry type.
II. Migration and GUP-fast
Whenever replacing a present page table entry that maps an exclusive
anonymous page by a migration entry, we have to mark the page possibly
shared and synchronize against GUP-fast by a proper clear/invalidate+flush
to make the following scenario impossible:
1. try_to_migrate() places a migration entry after checking for GUP pins
and marks the page possibly shared.
2. GUP-fast pins the page due to lack of synchronization
3. fork() converts the "writable/readable-exclusive" migration entry into a
readable migration entry
4. Migration fails due to the GUP pin (failing to freeze the refcount)
5. Migration entries are restored. PG_anon_exclusive is lost
-> We have a pinned page that is not marked exclusive anymore.
Note that we move information about exclusivity from the page to the
migration entry as it otherwise highly overcomplicates fork() and
PTE-mapping a THP.
III. Swapout and GUP-fast
Whenever replacing a present page table entry that maps an exclusive
anonymous page by a swap entry, we have to mark the page possibly shared
and synchronize against GUP-fast by a proper clear/invalidate+flush to
make the following scenario impossible:
1. try_to_unmap() places a swap entry after checking for GUP pins and
clears exclusivity information on the page.
2. GUP-fast pins the page due to lack of synchronization.
-> We have a pinned page that is not marked exclusive anymore.
If we'd ever store information about exclusivity in the swap entry,
similar to migration handling, the same considerations as in II would
apply. This is future work.
Link: https://lkml.kernel.org/r/20220428083441.37290-13-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>
2022-05-10 01:20:44 +00:00
|
|
|
#define SWP_MIGRATION_NUM 3
|
|
|
|
|
#define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
|
|
|
|
|
#define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
|
|
|
|
|
#define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2)
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:35 +00:00
|
|
|
#else
|
2009-09-16 09:50:05 +00:00
|
|
|
#define SWP_MIGRATION_NUM 0
|
[PATCH] Swapless page migration: add R/W migration entries
Implement read/write migration ptes
We take the upper two swapfiles for the two types of migration ptes and define
a series of macros in swapops.h.
The VM is modified to handle the migration entries. migration entries can
only be encountered when the page they are pointing to is locked. This limits
the number of places one has to fix. We also check in copy_pte_range and in
mprotect_pte_range() for migration ptes.
We check for migration ptes in do_swap_cache and call a function that will
then wait on the page lock. This allows us to effectively stop all accesses
to apge.
Migration entries are created by try_to_unmap if called for migration and
removed by local functions in migrate.c
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration (I've no NUMA, just
hacking it up to migrate recklessly while running load), I've hit the
BUG_ON(!PageLocked(p)) in migration_entry_to_page.
This comes from an orphaned migration entry, unrelated to the current
correctly locked migration, but hit by remove_anon_migration_ptes as it
checks an address in each vma of the anon_vma list.
Such an orphan may be left behind if an earlier migration raced with fork:
copy_one_pte can duplicate a migration entry from parent to child, after
remove_anon_migration_ptes has checked the child vma, but before it has
removed it from the parent vma. (If the process were later to fault on this
orphaned entry, it would hit the same BUG from migration_entry_wait.)
This could be fixed by locking anon_vma in copy_one_pte, but we'd rather
not. There's no such problem with file pages, because vma_prio_tree_add
adds child vma after parent vma, and the page table locking at each end is
enough to serialize. Follow that example with anon_vma: add new vmas to the
tail instead of the head.
(There's no corresponding problem when inserting migration entries,
because a missed pte will leave the page count and mapcount high, which is
allowed for. And there's no corresponding problem when migrating via swap,
because a leftover swap entry will be correctly faulted. But the swapless
method has no refcounting of its entries.)
From: Ingo Molnar <mingo@elte.hu>
pte_unmap_unlock() takes the pte pointer as an argument.
From: Hugh Dickins <hugh@veritas.com>
Several times while testing swapless page migration, gcc has tried to exec
a pointer instead of a string: smells like COW mappings are not being
properly write-protected on fork.
The protection in copy_one_pte looks very convincing, until at last you
realize that the second arg to make_migration_entry is a boolean "write",
and SWP_MIGRATION_READ is 30.
Anyway, it's better done like in change_pte_range, using
is_write_migration_entry and make_migration_entry_read.
From: Hugh Dickins <hugh@veritas.com>
Remove unnecessary obfuscation from sys_swapon's range check on swap type,
which blew up causing memory corruption once swapless migration made
MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Christoph Lameter <clameter@engr.sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:35 +00:00
|
|
|
#endif
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2009-09-16 09:50:05 +00:00
|
|
|
/*
|
|
|
|
|
* Handling of hardware poisoned pages with memory corruption.
|
|
|
|
|
*/
|
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
|
|
|
#define SWP_HWPOISON_NUM 1
|
|
|
|
|
#define SWP_HWPOISON MAX_SWAPFILES
|
|
|
|
|
#else
|
|
|
|
|
#define SWP_HWPOISON_NUM 0
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#define MAX_SWAPFILES \
|
2017-09-08 23:11:43 +00:00
|
|
|
((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \
|
2022-05-19 12:50:26 +00:00
|
|
|
SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \
|
2022-10-30 21:41:51 +00:00
|
|
|
SWP_PTE_MARKER_NUM)
|
2009-09-16 09:50:05 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
|
* Magic header for a swap area. The first part of the union is
|
|
|
|
|
* what the swap magic looks like for the old (limited to 128MB)
|
|
|
|
|
* swap area format, the second part of the union adds - in the
|
|
|
|
|
* old reserved area - some extra information. Note that the first
|
|
|
|
|
* kilobyte is reserved for boot loader or disk label stuff...
|
|
|
|
|
*
|
|
|
|
|
* Having the magic at the end of the PAGE_SIZE makes detecting swap
|
|
|
|
|
* areas somewhat tricky on machines that support multiple page sizes.
|
|
|
|
|
* For 2.5 we'll probably want to move the magic to just beyond the
|
|
|
|
|
* bootbits...
|
|
|
|
|
*/
|
|
|
|
|
union swap_header {
|
|
|
|
|
struct {
|
|
|
|
|
char reserved[PAGE_SIZE - 10];
|
|
|
|
|
char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */
|
|
|
|
|
} magic;
|
|
|
|
|
struct {
|
2006-06-23 09:03:14 +00:00
|
|
|
char bootbits[1024]; /* Space for disklabel etc. */
|
|
|
|
|
__u32 version;
|
|
|
|
|
__u32 last_page;
|
|
|
|
|
__u32 nr_badpages;
|
|
|
|
|
unsigned char sws_uuid[16];
|
|
|
|
|
unsigned char sws_volume[16];
|
|
|
|
|
__u32 padding[117];
|
|
|
|
|
__u32 badpages[1];
|
2005-04-16 22:20:36 +00:00
|
|
|
} info;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* current->reclaim_state points to one of these when a task is running
|
|
|
|
|
* memory reclaim
|
|
|
|
|
*/
|
|
|
|
|
struct reclaim_state {
|
2023-04-13 10:40:34 +00:00
|
|
|
/* pages reclaimed outside of LRU-based reclaim */
|
|
|
|
|
unsigned long reclaimed;
|
mm: multi-gen LRU: support page table walks
To further exploit spatial locality, the aging prefers to walk page tables
to search for young PTEs and promote hot pages. A kill switch will be
added in the next patch to disable this behavior. When disabled, the
aging relies on the rmap only.
NB: this behavior has nothing similar with the page table scanning in the
2.4 kernel [1], which searches page tables for old PTEs, adds cold pages
to swapcache and unmaps them.
To avoid confusion, the term "iteration" specifically means the traversal
of an entire mm_struct list; the term "walk" will be applied to page
tables and the rmap, as usual.
An mm_struct list is maintained for each memcg, and an mm_struct follows
its owner task to the new memcg when this task is migrated. Given an
lruvec, the aging iterates lruvec_memcg()->mm_list and calls
walk_page_range() with each mm_struct on this list to promote hot pages
before it increments max_seq.
When multiple page table walkers iterate the same list, each of them gets
a unique mm_struct; therefore they can run concurrently. Page table
walkers ignore any misplaced pages, e.g., if an mm_struct was migrated,
pages it left in the previous memcg will not be promoted when its current
memcg is under reclaim. Similarly, page table walkers will not promote
pages from nodes other than the one under reclaim.
This patch uses the following optimizations when walking page tables:
1. It tracks the usage of mm_struct's between context switches so that
page table walkers can skip processes that have been sleeping since
the last iteration.
2. It uses generational Bloom filters to record populated branches so
that page table walkers can reduce their search space based on the
query results, e.g., to skip page tables containing mostly holes or
misplaced pages.
3. It takes advantage of the accessed bit in non-leaf PMD entries when
CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y.
4. It does not zigzag between a PGD table and the same PMD table
spanning multiple VMAs. IOW, it finishes all the VMAs within the
range of the same PMD table before it returns to a PGD table. This
improves the cache performance for workloads that have large
numbers of tiny VMAs [2], especially when CONFIG_PGTABLE_LEVELS=5.
Server benchmark results:
Single workload:
fio (buffered I/O): no change
Single workload:
memcached (anon): +[8, 10]%
Ops/sec KB/sec
patch1-7: 1147696.57 44640.29
patch1-8: 1245274.91 48435.66
Configurations:
no change
Client benchmark results:
kswapd profiles:
patch1-7
48.16% lzo1x_1_do_compress (real work)
8.20% page_vma_mapped_walk (overhead)
7.06% _raw_spin_unlock_irq
2.92% ptep_clear_flush
2.53% __zram_bvec_write
2.11% do_raw_spin_lock
2.02% memmove
1.93% lru_gen_look_around
1.56% free_unref_page_list
1.40% memset
patch1-8
49.44% lzo1x_1_do_compress (real work)
6.19% page_vma_mapped_walk (overhead)
5.97% _raw_spin_unlock_irq
3.13% get_pfn_folio
2.85% ptep_clear_flush
2.42% __zram_bvec_write
2.08% do_raw_spin_lock
1.92% memmove
1.44% alloc_zspage
1.36% memset
Configurations:
no change
Thanks to the following developers for their efforts [3].
kernel test robot <lkp@intel.com>
[1] https://lwn.net/Articles/23732/
[2] https://llvm.org/docs/ScudoHardenedAllocator.html
[3] https://lore.kernel.org/r/202204160827.ekEARWQo-lkp@intel.com/
Link: https://lkml.kernel.org/r/20220918080010.2920238-9-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-18 08:00:05 +00:00
|
|
|
#ifdef CONFIG_LRU_GEN
|
|
|
|
|
/* per-thread mm walk data */
|
|
|
|
|
struct lru_gen_mm_walk *mm_walk;
|
|
|
|
|
#endif
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
|
|
|
|
|
2023-04-13 10:40:34 +00:00
|
|
|
/*
|
|
|
|
|
* mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based
|
|
|
|
|
* reclaim
|
|
|
|
|
* @pages: number of pages reclaimed
|
|
|
|
|
*
|
|
|
|
|
* If the current process is undergoing a reclaim operation, increment the
|
|
|
|
|
* number of reclaimed pages by @pages.
|
|
|
|
|
*/
|
|
|
|
|
static inline void mm_account_reclaimed_pages(unsigned long pages)
|
|
|
|
|
{
|
|
|
|
|
if (current->reclaim_state)
|
|
|
|
|
current->reclaim_state->reclaimed += pages;
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
#ifdef __KERNEL__
|
|
|
|
|
|
|
|
|
|
struct address_space;
|
|
|
|
|
struct sysinfo;
|
|
|
|
|
struct writeback_control;
|
|
|
|
|
struct zone;
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of
|
2022-05-19 21:08:52 +00:00
|
|
|
* disk blocks. A rbtree of swap extents maps the entire swapfile (Where the
|
|
|
|
|
* term `swapfile' refers to either a blockdevice or an IS_REG file). Apart
|
2005-04-16 22:20:36 +00:00
|
|
|
* from setup, they're handled identically.
|
|
|
|
|
*
|
|
|
|
|
* We always assume that blocks are of size PAGE_SIZE.
|
|
|
|
|
*/
|
|
|
|
|
struct swap_extent {
|
mm, swap: use rbtree for swap_extent
swap_extent is used to map swap page offset to backing device's block
offset. For a continuous block range, one swap_extent is used and all
these swap_extents are managed in a linked list.
These swap_extents are used by map_swap_entry() during swap's read and
write path. To find out the backing device's block offset for a page
offset, the swap_extent list will be traversed linearly, with
curr_swap_extent being used as a cache to speed up the search.
This works well as long as swap_extents are not huge or when the number
of processes that access swap device are few, but when the swap device
has many extents and there are a number of processes accessing the swap
device concurrently, it can be a problem. On one of our servers, the
disk's remaining size is tight:
$df -h
Filesystem Size Used Avail Use% Mounted on
... ...
/dev/nvme0n1p1 1.8T 1.3T 504G 72% /home/t4
When creating a 80G swapfile there, there are as many as 84656 swap
extents. The end result is, kernel spends abou 30% time in
map_swap_entry() and swap throughput is only 70MB/s.
As a comparison, when I used smaller sized swapfile, like 4G whose
swap_extent dropped to 2000, swap throughput is back to 400-500MB/s and
map_swap_entry() is about 3%.
One downside of using rbtree for swap_extent is, 'struct rbtree' takes
24 bytes while 'struct list_head' takes 16 bytes, that's 8 bytes more
for each swap_extent. For a swapfile that has 80k swap_extents, that
means 625KiB more memory consumed.
Test:
Since it's not possible to reboot that server, I can not test this patch
diretly there. Instead, I tested it on another server with NVMe disk.
I created a 20G swapfile on an NVMe backed XFS fs. By default, the
filesystem is quite clean and the created swapfile has only 2 extents.
Testing vanilla and this patch shows no obvious performance difference
when swapfile is not fragmented.
To see the patch's effects, I used some tweaks to manually fragment the
swapfile by breaking the extent at 1M boundary. This made the swapfile
have 20K extents.
nr_task=4
kernel swapout(KB/s) map_swap_entry(perf) swapin(KB/s) map_swap_entry(perf)
vanilla 165191 90.77% 171798 90.21%
patched 858993 +420% 2.16% 715827 +317% 0.77%
nr_task=8
kernel swapout(KB/s) map_swap_entry(perf) swapin(KB/s) map_swap_entry(perf)
vanilla 306783 92.19% 318145 87.76%
patched 954437 +211% 2.35% 1073741 +237% 1.57%
swapout: the throughput of swap out, in KB/s, higher is better 1st
map_swap_entry: cpu cycles percent sampled by perf swapin: the
throughput of swap in, in KB/s, higher is better. 2nd map_swap_entry:
cpu cycles percent sampled by perf
nr_task=1 doesn't show any difference, this is due to the curr_swap_extent
can be effectively used to cache the correct swap extent for single task
workload.
[akpm@linux-foundation.org: s/BUG_ON(1)/BUG()/]
Link: http://lkml.kernel.org/r/20190523142404.GA181@aaronlu
Signed-off-by: Aaron Lu <ziqian.lzq@antfin.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:41 +00:00
|
|
|
struct rb_node rb_node;
|
2005-04-16 22:20:36 +00:00
|
|
|
pgoff_t start_page;
|
|
|
|
|
pgoff_t nr_pages;
|
|
|
|
|
sector_t start_block;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* Max bad pages in the new format..
|
|
|
|
|
*/
|
|
|
|
|
#define MAX_SWAP_BADPAGES \
|
2019-03-13 18:44:33 +00:00
|
|
|
((offsetof(union swap_header, magic.magic) - \
|
|
|
|
|
offsetof(union swap_header, info.badpages)) / sizeof(int))
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
enum {
|
|
|
|
|
SWP_USED = (1 << 0), /* is slot in swap_info[] used? */
|
|
|
|
|
SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */
|
swap: discard while swapping only if SWAP_FLAG_DISCARD_PAGES
Considering the use cases where the swap device supports discard:
a) and can do it quickly;
b) but it's slow to do in small granularities (or concurrent with other
I/O);
c) but the implementation is so horrendous that you don't even want to
send one down;
And assuming that the sysadmin considers it useful to send the discards down
at all, we would (probably) want the following solutions:
i. do the fine-grained discards for freed swap pages, if device is
capable of doing so optimally;
ii. do single-time (batched) swap area discards, either at swapon
or via something like fstrim (not implemented yet);
iii. allow doing both single-time and fine-grained discards; or
iv. turn it off completely (default behavior)
As implemented today, one can only enable/disable discards for swap, but
one cannot select, for instance, solution (ii) on a swap device like (b)
even though the single-time discard is regarded to be interesting, or
necessary to the workload because it would imply (1), and the device is
not capable of performing it optimally.
This patch addresses the scenario depicted above by introducing a way to
ensure the (probably) wanted solutions (i, ii, iii and iv) can be flexibly
flagged through swapon(8) to allow a sysadmin to select the best suitable
swap discard policy accordingly to system constraints.
This patch introduces SWAP_FLAG_DISCARD_PAGES and SWAP_FLAG_DISCARD_ONCE
new flags to allow more flexibe swap discard policies being flagged
through swapon(8). The default behavior is to keep both single-time, or
batched, area discards (SWAP_FLAG_DISCARD_ONCE) and fine-grained discards
for page-clusters (SWAP_FLAG_DISCARD_PAGES) enabled, in order to keep
consistentcy with older kernel behavior, as well as maintain compatibility
with older swapon(8). However, through the new introduced flags the best
suitable discard policy can be selected accordingly to any given swap
device constraint.
[akpm@linux-foundation.org: tweak comments]
Signed-off-by: Rafael Aquini <aquini@redhat.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Karel Zak <kzak@redhat.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-03 22:02:46 +00:00
|
|
|
SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */
|
2009-01-06 22:39:53 +00:00
|
|
|
SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */
|
2009-01-06 22:39:54 +00:00
|
|
|
SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */
|
swap_info: swap count continuations
Swap is duplicated (reference count incremented by one) whenever the same
swap page is inserted into another mm (when forking finds a swap entry in
place of a pte, or when reclaim unmaps a pte to insert the swap entry).
swap_info_struct's vmalloc'ed swap_map is the array of these reference
counts: but what happens when the unsigned short (or unsigned char since
the preceding patch) is full? (and its high bit is kept for a cache flag)
We then lose track of it, never freeing, leaving it in use until swapoff:
at which point we _hope_ that a single pass will have found all instances,
assume there are no more, and will lose user data if we're wrong.
Swapping of KSM pages has not yet been enabled; but it is implemented,
and makes it very easy for a user to overflow the maximum swap count:
possible with ordinary process pages, but unlikely, even when pid_max
has been raised from PID_MAX_DEFAULT.
This patch implements swap count continuations: when the count overflows,
a continuation page is allocated and linked to the original vmalloc'ed
map page, and this used to hold the continuation counts for that entry
and its neighbours. These continuation pages are seldom referenced:
the common paths all work on the original swap_map, only referring to
a continuation page when the low "digit" of a count is incremented or
decremented through SWAP_MAP_MAX.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:46 +00:00
|
|
|
SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */
|
2010-05-17 05:32:42 +00:00
|
|
|
SWP_BLKDEV = (1 << 6), /* its a block device */
|
2018-10-26 22:10:51 +00:00
|
|
|
SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */
|
2020-10-13 23:52:04 +00:00
|
|
|
SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */
|
2018-10-26 22:10:51 +00:00
|
|
|
SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */
|
|
|
|
|
SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */
|
|
|
|
|
SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */
|
|
|
|
|
SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */
|
[PATCH] swap: scan_swap_map drop swap_device_lock
get_swap_page has often shown up on latency traces, doing lengthy scans while
holding two spinlocks. swap_list_lock is already dropped, now scan_swap_map
drop swap_device_lock before scanning the swap_map.
While scanning for an empty cluster, don't worry that racing tasks may
allocate what was free and free what was allocated; but when allocating an
entry, check it's still free after retaking the lock. Avoid dropping the lock
in the expected common path. No barriers beyond the locks, just let the
cookie crumble; highest_bit limit is volatile, but benign.
Guard against swapoff: must check SWP_WRITEOK before allocating, must raise
SWP_SCANNING reference count while in scan_swap_map, swapoff wait for that to
fall - just use schedule_timeout, we don't want to burden scan_swap_map
itself, and it's very unlikely that anyone can really still be in
scan_swap_map once swapoff gets this far.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-03 22:54:39 +00:00
|
|
|
/* add others here before... */
|
mm, swap: fix race between swapoff and some swap operations
When swapin is performed, after getting the swap entry information from
the page table, system will swap in the swap entry, without any lock held
to prevent the swap device from being swapoff. This may cause the race
like below,
CPU 1 CPU 2
----- -----
do_swap_page
swapin_readahead
__read_swap_cache_async
swapoff swapcache_prepare
p->swap_map = NULL __swap_duplicate
p->swap_map[?] /* !!! NULL pointer access */
Because swapoff is usually done when system shutdown only, the race may
not hit many people in practice. But it is still a race need to be fixed.
To fix the race, get_swap_device() is added to check whether the specified
swap entry is valid in its swap device. If so, it will keep the swap
entry valid via preventing the swap device from being swapoff, until
put_swap_device() is called.
Because swapoff() is very rare code path, to make the normal path runs as
fast as possible, rcu_read_lock/unlock() and synchronize_rcu() instead of
reference count is used to implement get/put_swap_device(). >From
get_swap_device() to put_swap_device(), RCU reader side is locked, so
synchronize_rcu() in swapoff() will wait until put_swap_device() is
called.
In addition to swap_map, cluster_info, etc. data structure in the struct
swap_info_struct, the swap cache radix tree will be freed after swapoff,
so this patch fixes the race between swap cache looking up and swapoff
too.
Races between some other swap cache usages and swapoff are fixed too via
calling synchronize_rcu() between clearing PageSwapCache() and freeing
swap cache data structure.
Another possible method to fix this is to use preempt_off() +
stop_machine() to prevent the swap device from being swapoff when its data
structure is being accessed. The overhead in hot-path of both methods is
similar. The advantages of RCU based method are,
1. stop_machine() may disturb the normal execution code path on other
CPUs.
2. File cache uses RCU to protect its radix tree. If the similar
mechanism is used for swap cache too, it is easier to share code
between them.
3. RCU is used to protect swap cache in total_swapcache_pages() and
exit_swap_address_space() already. The two mechanisms can be
merged to simplify the logic.
Link: http://lkml.kernel.org/r/20190522015423.14418-1-ying.huang@intel.com
Fixes: 235b62176712 ("mm/swap: add cluster lock")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Not-nacked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:33 +00:00
|
|
|
SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
|
|
|
|
|
2013-02-23 00:32:12 +00:00
|
|
|
#define SWAP_CLUSTER_MAX 32UL
|
2010-05-24 21:32:27 +00:00
|
|
|
#define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2020-06-02 04:49:13 +00:00
|
|
|
/* Bit flag in swap_map */
|
swap_info: swap count continuations
Swap is duplicated (reference count incremented by one) whenever the same
swap page is inserted into another mm (when forking finds a swap entry in
place of a pte, or when reclaim unmaps a pte to insert the swap entry).
swap_info_struct's vmalloc'ed swap_map is the array of these reference
counts: but what happens when the unsigned short (or unsigned char since
the preceding patch) is full? (and its high bit is kept for a cache flag)
We then lose track of it, never freeing, leaving it in use until swapoff:
at which point we _hope_ that a single pass will have found all instances,
assume there are no more, and will lose user data if we're wrong.
Swapping of KSM pages has not yet been enabled; but it is implemented,
and makes it very easy for a user to overflow the maximum swap count:
possible with ordinary process pages, but unlikely, even when pid_max
has been raised from PID_MAX_DEFAULT.
This patch implements swap count continuations: when the count overflows,
a continuation page is allocated and linked to the original vmalloc'ed
map page, and this used to hold the continuation counts for that entry
and its neighbours. These continuation pages are seldom referenced:
the common paths all work on the original swap_map, only referring to
a continuation page when the low "digit" of a count is incremented or
decremented through SWAP_MAP_MAX.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:46 +00:00
|
|
|
#define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */
|
2020-06-02 04:49:13 +00:00
|
|
|
#define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */
|
|
|
|
|
|
|
|
|
|
/* Special value in first swap_map */
|
|
|
|
|
#define SWAP_MAP_MAX 0x3e /* Max count */
|
|
|
|
|
#define SWAP_MAP_BAD 0x3f /* Note page is bad */
|
|
|
|
|
#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */
|
|
|
|
|
|
|
|
|
|
/* Special value in each swap_map continuation */
|
|
|
|
|
#define SWAP_CONT_MAX 0x7f /* Max count */
|
2009-12-15 01:58:44 +00:00
|
|
|
|
swap: change block allocation algorithm for SSD
I'm using a fast SSD to do swap. scan_swap_map() sometimes uses up to
20~30% CPU time (when cluster is hard to find, the CPU time can be up to
80%), which becomes a bottleneck. scan_swap_map() scans a byte array to
search a 256 page cluster, which is very slow.
Here I introduced a simple algorithm to search cluster. Since we only
care about 256 pages cluster, we can just use a counter to track if a
cluster is free. Every 256 pages use one int to store the counter. If
the counter of a cluster is 0, the cluster is free. All free clusters
will be added to a list, so searching cluster is very efficient. With
this, scap_swap_map() overhead disappears.
This might help low end SD card swap too. Because if the cluster is
aligned, SD firmware can do flash erase more efficiently.
We only enable the algorithm for SSD. Hard disk swap isn't fast enough
and has downside with the algorithm which might introduce regression (see
below).
The patch slightly changes which cluster is choosen. It always adds free
cluster to list tail. This can help wear leveling for low end SSD too.
And if no cluster found, the scan_swap_map() will do search from the end
of last cluster. So if no cluster found, the scan_swap_map() will do
search from the end of last free cluster, which is random. For SSD, this
isn't a problem at all.
Another downside is the cluster must be aligned to 256 pages, which will
reduce the chance to find a cluster. I would expect this isn't a big
problem for SSD because of the non-seek penality. (And this is the reason
I only enable the algorithm for SSD).
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:28 +00:00
|
|
|
/*
|
|
|
|
|
* We use this to track usage of a cluster. A cluster is a block of swap disk
|
|
|
|
|
* space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All
|
|
|
|
|
* free clusters are organized into a list. We fetch an entry from the list to
|
|
|
|
|
* get a free cluster.
|
|
|
|
|
*
|
|
|
|
|
* The data field stores next cluster if the cluster is free or cluster usage
|
|
|
|
|
* counter otherwise. The flags field determines if a cluster is free. This is
|
|
|
|
|
* protected by swap_info_struct.lock.
|
|
|
|
|
*/
|
|
|
|
|
struct swap_cluster_info {
|
mm/swap: add cluster lock
This patch is to reduce the lock contention of swap_info_struct->lock
via using a more fine grained lock in swap_cluster_info for some swap
operations. swap_info_struct->lock is heavily contended if multiple
processes reclaim pages simultaneously. Because there is only one lock
for each swap device. While in common configuration, there is only one
or several swap devices in the system. The lock protects almost all
swap related operations.
In fact, many swap operations only access one element of
swap_info_struct->swap_map array. And there is no dependency between
different elements of swap_info_struct->swap_map. So a fine grained
lock can be used to allow parallel access to the different elements of
swap_info_struct->swap_map.
In this patch, a spinlock is added to swap_cluster_info to protect the
elements of swap_info_struct->swap_map in the swap cluster and the
fields of swap_cluster_info. This reduced locking contention for
swap_info_struct->swap_map access greatly.
Because of the added spinlock, the size of swap_cluster_info increases
from 4 bytes to 8 bytes on the 64 bit and 32 bit system. This will use
additional 4k RAM for every 1G swap space.
Because the size of swap_cluster_info is much smaller than the size of
the cache line (8 vs 64 on x86_64 architecture), there may be false
cache line sharing between spinlocks in swap_cluster_info. To avoid the
false sharing in the first round of the swap cluster allocation, the
order of the swap clusters in the free clusters list is changed. So
that, the swap_cluster_info sharing the same cache line will be placed
as far as possible. After the first round of allocation, the order of
the clusters in free clusters list is expected to be random. So the
false sharing should be not serious.
Compared with a previous implementation using bit_spin_lock, the
sequential swap out throughput improved about 3.2%. Test was done on a
Xeon E5 v3 system. The swap device used is a RAM simulated PMEM
(persistent memory) device. To test the sequential swapping out, the
test case created 32 processes, which sequentially allocate and write to
the anonymous pages until the RAM and part of the swap device is used.
[ying.huang@intel.com: v5]
Link: http://lkml.kernel.org/r/878tqeuuic.fsf_-_@yhuang-dev.intel.com
[minchan@kernel.org: initialize spinlock for swap_cluster_info]
Link: http://lkml.kernel.org/r/1486434945-29753-1-git-send-email-minchan@kernel.org
[hughd@google.com: annotate nested locking for cluster lock]
Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1702161050540.21773@eggly.anvils
Link: http://lkml.kernel.org/r/dbb860bbd825b1aaba18988015e8963f263c3f0d.1484082593.git.tim.c.chen@linux.intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net> escreveu:
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-22 23:45:22 +00:00
|
|
|
spinlock_t lock; /*
|
|
|
|
|
* Protect swap_cluster_info fields
|
|
|
|
|
* and swap_info_struct->swap_map
|
|
|
|
|
* elements correspond to the swap
|
|
|
|
|
* cluster
|
|
|
|
|
*/
|
swap: change block allocation algorithm for SSD
I'm using a fast SSD to do swap. scan_swap_map() sometimes uses up to
20~30% CPU time (when cluster is hard to find, the CPU time can be up to
80%), which becomes a bottleneck. scan_swap_map() scans a byte array to
search a 256 page cluster, which is very slow.
Here I introduced a simple algorithm to search cluster. Since we only
care about 256 pages cluster, we can just use a counter to track if a
cluster is free. Every 256 pages use one int to store the counter. If
the counter of a cluster is 0, the cluster is free. All free clusters
will be added to a list, so searching cluster is very efficient. With
this, scap_swap_map() overhead disappears.
This might help low end SD card swap too. Because if the cluster is
aligned, SD firmware can do flash erase more efficiently.
We only enable the algorithm for SSD. Hard disk swap isn't fast enough
and has downside with the algorithm which might introduce regression (see
below).
The patch slightly changes which cluster is choosen. It always adds free
cluster to list tail. This can help wear leveling for low end SSD too.
And if no cluster found, the scan_swap_map() will do search from the end
of last cluster. So if no cluster found, the scan_swap_map() will do
search from the end of last free cluster, which is random. For SSD, this
isn't a problem at all.
Another downside is the cluster must be aligned to 256 pages, which will
reduce the chance to find a cluster. I would expect this isn't a big
problem for SSD because of the non-seek penality. (And this is the reason
I only enable the algorithm for SSD).
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:28 +00:00
|
|
|
unsigned int data:24;
|
|
|
|
|
unsigned int flags:8;
|
|
|
|
|
};
|
|
|
|
|
#define CLUSTER_FLAG_FREE 1 /* This cluster is free */
|
|
|
|
|
#define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */
|
mm, THP, swap: support to reclaim swap space for THP swapped out
The normal swap slot reclaiming can be done when the swap count reaches
SWAP_HAS_CACHE. But for the swap slot which is backing a THP, all swap
slots backing one THP must be reclaimed together, because the swap slot
may be used again when the THP is swapped out again later. So the swap
slots backing one THP can be reclaimed together when the swap count for
all swap slots for the THP reached SWAP_HAS_CACHE. In the patch, the
functions to check whether the swap count for all swap slots backing one
THP reached SWAP_HAS_CACHE are implemented and used when checking
whether a swap slot can be reclaimed.
To make it easier to determine whether a swap slot is backing a THP, a
new swap cluster flag named CLUSTER_FLAG_HUGE is added to mark a swap
cluster which is backing a THP (Transparent Huge Page). Because THP
swap in as a whole isn't supported now. After deleting the THP from the
swap cache (for example, swapping out finished), the CLUSTER_FLAG_HUGE
flag will be cleared. So that, the normal pages inside THP can be
swapped in individually.
[ying.huang@intel.com: fix swap_page_trans_huge_swapped on HDD]
Link: http://lkml.kernel.org/r/874ltsm0bi.fsf@yhuang-dev.intel.com
Link: http://lkml.kernel.org/r/20170724051840.2309-3-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Ross Zwisler <ross.zwisler@intel.com> [for brd.c, zram_drv.c, pmem.c]
Cc: Vishal L Verma <vishal.l.verma@intel.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-06 23:22:16 +00:00
|
|
|
#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */
|
swap: change block allocation algorithm for SSD
I'm using a fast SSD to do swap. scan_swap_map() sometimes uses up to
20~30% CPU time (when cluster is hard to find, the CPU time can be up to
80%), which becomes a bottleneck. scan_swap_map() scans a byte array to
search a 256 page cluster, which is very slow.
Here I introduced a simple algorithm to search cluster. Since we only
care about 256 pages cluster, we can just use a counter to track if a
cluster is free. Every 256 pages use one int to store the counter. If
the counter of a cluster is 0, the cluster is free. All free clusters
will be added to a list, so searching cluster is very efficient. With
this, scap_swap_map() overhead disappears.
This might help low end SD card swap too. Because if the cluster is
aligned, SD firmware can do flash erase more efficiently.
We only enable the algorithm for SSD. Hard disk swap isn't fast enough
and has downside with the algorithm which might introduce regression (see
below).
The patch slightly changes which cluster is choosen. It always adds free
cluster to list tail. This can help wear leveling for low end SSD too.
And if no cluster found, the scan_swap_map() will do search from the end
of last cluster. So if no cluster found, the scan_swap_map() will do
search from the end of last free cluster, which is random. For SSD, this
isn't a problem at all.
Another downside is the cluster must be aligned to 256 pages, which will
reduce the chance to find a cluster. I would expect this isn't a big
problem for SSD because of the non-seek penality. (And this is the reason
I only enable the algorithm for SSD).
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:28 +00:00
|
|
|
|
swap: make cluster allocation per-cpu
swap cluster allocation is to get better request merge to improve
performance. But the cluster is shared globally, if multiple tasks are
doing swap, this will cause interleave disk access. While multiple tasks
swap is quite common, for example, each numa node has a kswapd thread
doing swap and multiple threads/processes doing direct page reclaim.
ioscheduler can't help too much here, because tasks don't send swapout IO
down to block layer in the meantime. Block layer does merge some IOs, but
a lot not, depending on how many tasks are doing swapout concurrently. In
practice, I've seen a lot of small size IO in swapout workloads.
We makes the cluster allocation per-cpu here. The interleave disk access
issue goes away. All tasks swapout to their own cluster, so swapout will
become sequential, which can be easily merged to big size IO. If one CPU
can't get its per-cpu cluster (for example, there is no free cluster
anymore in the swap), it will fallback to scan swap_map. The CPU can
still continue swap. We don't need recycle free swap entries of other
CPUs.
In my test (swap to a 2-disk raid0 partition), this improves around 10%
swapout throughput, and request size is increased significantly.
How does this impact swap readahead is uncertain though. On one side,
page reclaim always isolates and swaps several adjancent pages, this will
make page reclaim write the pages sequentially and benefit readahead. On
the other side, several CPU write pages interleave means the pages don't
live _sequentially_ but relatively _near_. In the per-cpu allocation
case, if adjancent pages are written by different cpus, they will live
relatively _far_. So how this impacts swap readahead depends on how many
pages page reclaim isolates and swaps one time. If the number is big,
this patch will benefit swap readahead. Of course, this is about
sequential access pattern. The patch has no impact for random access
pattern, because the new cluster allocation algorithm is just for SSD.
Alternative solution is organizing swap layout to be per-mm instead of
this per-cpu approach. In the per-mm layout, we allocate a disk range for
each mm, so pages of one mm live in swap disk adjacently. per-mm layout
has potential issues of lock contention if multiple reclaimers are swap
pages from one mm. For a sequential workload, per-mm layout is better to
implement swap readahead, because pages from the mm are adjacent in disk.
But per-cpu layout isn't very bad in this workload, as page reclaim always
isolates and swaps several pages one time, such pages will still live in
disk sequentially and readahead can utilize this. For a random workload,
per-mm layout isn't beneficial of request merge, because it's quite
possible pages from different mm are swapout in the meantime and IO can't
be merged in per-mm layout. while with per-cpu layout we can merge
requests from any mm. Considering random workload is more popular in
workloads with swap (and per-cpu approach isn't too bad for sequential
workload too), I'm choosing per-cpu layout.
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:32 +00:00
|
|
|
/*
|
|
|
|
|
* We assign a cluster to each CPU, so each CPU can allocate swap entry from
|
|
|
|
|
* its own cluster and swapout sequentially. The purpose is to optimize swapout
|
|
|
|
|
* throughput.
|
|
|
|
|
*/
|
|
|
|
|
struct percpu_cluster {
|
|
|
|
|
struct swap_cluster_info index; /* Current cluster index */
|
|
|
|
|
unsigned int next; /* Likely next allocation offset */
|
|
|
|
|
};
|
|
|
|
|
|
2016-10-07 23:58:42 +00:00
|
|
|
struct swap_cluster_list {
|
|
|
|
|
struct swap_cluster_info head;
|
|
|
|
|
struct swap_cluster_info tail;
|
|
|
|
|
};
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/*
|
|
|
|
|
* The in-memory structure used to track swap areas.
|
|
|
|
|
*/
|
|
|
|
|
struct swap_info_struct {
|
2021-06-29 02:36:46 +00:00
|
|
|
struct percpu_ref users; /* indicate and keep swap device valid. */
|
2009-12-15 01:58:41 +00:00
|
|
|
unsigned long flags; /* SWP_USED etc: see above */
|
|
|
|
|
signed short prio; /* swap priority of this type */
|
swap: change swap_list_head to plist, add swap_avail_head
Originally get_swap_page() started iterating through the singly-linked
list of swap_info_structs using swap_list.next or highest_priority_index,
which both were intended to point to the highest priority active swap
target that was not full. The first patch in this series changed the
singly-linked list to a doubly-linked list, and removed the logic to start
at the highest priority non-full entry; it starts scanning at the highest
priority entry each time, even if the entry is full.
Replace the manually ordered swap_list_head with a plist, swap_active_head.
Add a new plist, swap_avail_head. The original swap_active_head plist
contains all active swap_info_structs, as before, while the new
swap_avail_head plist contains only swap_info_structs that are active and
available, i.e. not full. Add a new spinlock, swap_avail_lock, to protect
the swap_avail_head list.
Mel Gorman suggested using plists since they internally handle ordering
the list entries based on priority, which is exactly what swap was doing
manually. All the ordering code is now removed, and swap_info_struct
entries and simply added to their corresponding plist and automatically
ordered correctly.
Using a new plist for available swap_info_structs simplifies and
optimizes get_swap_page(), which no longer has to iterate over full
swap_info_structs. Using a new spinlock for swap_avail_head plist
allows each swap_info_struct to add or remove themselves from the
plist when they become full or not-full; previously they could not
do so because the swap_info_struct->lock is held when they change
from full<->not-full, and the swap_lock protecting the main
swap_active_head must be ordered before any swap_info_struct->lock.
Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Cc: Weijie Yang <weijieut@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-06-04 23:09:59 +00:00
|
|
|
struct plist_node list; /* entry in swap_active_head */
|
2009-12-15 01:58:41 +00:00
|
|
|
signed char type; /* strange name for an index */
|
2009-12-15 01:58:48 +00:00
|
|
|
unsigned int max; /* extent of the swap_map */
|
|
|
|
|
unsigned char *swap_map; /* vmalloc'ed array of usage counts */
|
swap: change block allocation algorithm for SSD
I'm using a fast SSD to do swap. scan_swap_map() sometimes uses up to
20~30% CPU time (when cluster is hard to find, the CPU time can be up to
80%), which becomes a bottleneck. scan_swap_map() scans a byte array to
search a 256 page cluster, which is very slow.
Here I introduced a simple algorithm to search cluster. Since we only
care about 256 pages cluster, we can just use a counter to track if a
cluster is free. Every 256 pages use one int to store the counter. If
the counter of a cluster is 0, the cluster is free. All free clusters
will be added to a list, so searching cluster is very efficient. With
this, scap_swap_map() overhead disappears.
This might help low end SD card swap too. Because if the cluster is
aligned, SD firmware can do flash erase more efficiently.
We only enable the algorithm for SSD. Hard disk swap isn't fast enough
and has downside with the algorithm which might introduce regression (see
below).
The patch slightly changes which cluster is choosen. It always adds free
cluster to list tail. This can help wear leveling for low end SSD too.
And if no cluster found, the scan_swap_map() will do search from the end
of last cluster. So if no cluster found, the scan_swap_map() will do
search from the end of last free cluster, which is random. For SSD, this
isn't a problem at all.
Another downside is the cluster must be aligned to 256 pages, which will
reduce the chance to find a cluster. I would expect this isn't a big
problem for SSD because of the non-seek penality. (And this is the reason
I only enable the algorithm for SSD).
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:28 +00:00
|
|
|
struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
|
2016-10-07 23:58:42 +00:00
|
|
|
struct swap_cluster_list free_clusters; /* free clusters list */
|
2009-12-15 01:58:48 +00:00
|
|
|
unsigned int lowest_bit; /* index of first free in swap_map */
|
|
|
|
|
unsigned int highest_bit; /* index of last free in swap_map */
|
|
|
|
|
unsigned int pages; /* total of usable pages of swap */
|
|
|
|
|
unsigned int inuse_pages; /* number of those currently in use */
|
|
|
|
|
unsigned int cluster_next; /* likely index for next allocation */
|
|
|
|
|
unsigned int cluster_nr; /* countdown to next cluster search */
|
swap: reduce lock contention on swap cache from swap slots allocation
In some swap scalability test, it is found that there are heavy lock
contention on swap cache even if we have split one swap cache radix tree
per swap device to one swap cache radix tree every 64 MB trunk in commit
4b3ef9daa4fc ("mm/swap: split swap cache into 64MB trunks").
The reason is as follow. After the swap device becomes fragmented so
that there's no free swap cluster, the swap device will be scanned
linearly to find the free swap slots. swap_info_struct->cluster_next is
the next scanning base that is shared by all CPUs. So nearby free swap
slots will be allocated for different CPUs. The probability for
multiple CPUs to operate on the same 64 MB trunk is high. This causes
the lock contention on the swap cache.
To solve the issue, in this patch, for SSD swap device, a percpu version
next scanning base (cluster_next_cpu) is added. Every CPU will use its
own per-cpu next scanning base. And after finishing scanning a 64MB
trunk, the per-cpu scanning base will be changed to the beginning of
another randomly selected 64MB trunk. In this way, the probability for
multiple CPUs to operate on the same 64 MB trunk is reduced greatly.
Thus the lock contention is reduced too. For HDD, because sequential
access is more important for IO performance, the original shared next
scanning base is used.
To test the patch, we have run 16-process pmbench memory benchmark on a
2-socket server machine with 48 cores. One ram disk is configured as the
swap device per socket. The pmbench working-set size is much larger than
the available memory so that swapping is triggered. The memory read/write
ratio is 80/20 and the accessing pattern is random. In the original
implementation, the lock contention on the swap cache is heavy. The perf
profiling data of the lock contention code path is as following,
_raw_spin_lock_irq.add_to_swap_cache.add_to_swap.shrink_page_list: 7.91
_raw_spin_lock_irqsave.__remove_mapping.shrink_page_list: 7.11
_raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 2.51
_raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 1.66
_raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 1.29
_raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.03
_raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 0.93
After applying this patch, it becomes,
_raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 3.58
_raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 2.3
_raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 2.26
_raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 1.8
_raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.19
The lock contention on the swap cache is almost eliminated.
And the pmbench score increases 18.5%. The swapin throughput increases
18.7% from 2.96 GB/s to 3.51 GB/s. While the swapout throughput increases
18.5% from 2.99 GB/s to 3.54 GB/s.
We need really fast disk to show the benefit. I have tried this on 2
Intel P3600 NVMe disks. The performance improvement is only about 1%.
The improvement should be better on the faster disks, such as Intel Optane
disk.
[ying.huang@intel.com: fix cluster_next_cpu allocation and freeing, per Daniel]
Link: http://lkml.kernel.org/r/20200525002648.336325-1-ying.huang@intel.com
[ying.huang@intel.com: v4]
Link: http://lkml.kernel.org/r/20200529010840.928819-1-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Link: http://lkml.kernel.org/r/20200520031502.175659-1-ying.huang@intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-02 04:49:22 +00:00
|
|
|
unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */
|
swap: make cluster allocation per-cpu
swap cluster allocation is to get better request merge to improve
performance. But the cluster is shared globally, if multiple tasks are
doing swap, this will cause interleave disk access. While multiple tasks
swap is quite common, for example, each numa node has a kswapd thread
doing swap and multiple threads/processes doing direct page reclaim.
ioscheduler can't help too much here, because tasks don't send swapout IO
down to block layer in the meantime. Block layer does merge some IOs, but
a lot not, depending on how many tasks are doing swapout concurrently. In
practice, I've seen a lot of small size IO in swapout workloads.
We makes the cluster allocation per-cpu here. The interleave disk access
issue goes away. All tasks swapout to their own cluster, so swapout will
become sequential, which can be easily merged to big size IO. If one CPU
can't get its per-cpu cluster (for example, there is no free cluster
anymore in the swap), it will fallback to scan swap_map. The CPU can
still continue swap. We don't need recycle free swap entries of other
CPUs.
In my test (swap to a 2-disk raid0 partition), this improves around 10%
swapout throughput, and request size is increased significantly.
How does this impact swap readahead is uncertain though. On one side,
page reclaim always isolates and swaps several adjancent pages, this will
make page reclaim write the pages sequentially and benefit readahead. On
the other side, several CPU write pages interleave means the pages don't
live _sequentially_ but relatively _near_. In the per-cpu allocation
case, if adjancent pages are written by different cpus, they will live
relatively _far_. So how this impacts swap readahead depends on how many
pages page reclaim isolates and swaps one time. If the number is big,
this patch will benefit swap readahead. Of course, this is about
sequential access pattern. The patch has no impact for random access
pattern, because the new cluster allocation algorithm is just for SSD.
Alternative solution is organizing swap layout to be per-mm instead of
this per-cpu approach. In the per-mm layout, we allocate a disk range for
each mm, so pages of one mm live in swap disk adjacently. per-mm layout
has potential issues of lock contention if multiple reclaimers are swap
pages from one mm. For a sequential workload, per-mm layout is better to
implement swap readahead, because pages from the mm are adjacent in disk.
But per-cpu layout isn't very bad in this workload, as page reclaim always
isolates and swaps several pages one time, such pages will still live in
disk sequentially and readahead can utilize this. For a random workload,
per-mm layout isn't beneficial of request merge, because it's quite
possible pages from different mm are swapout in the meantime and IO can't
be merged in per-mm layout. while with per-cpu layout we can merge
requests from any mm. Considering random workload is more popular in
workloads with swap (and per-cpu approach isn't too bad for sequential
workload too), I'm choosing per-cpu layout.
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:32 +00:00
|
|
|
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
|
mm, swap: use rbtree for swap_extent
swap_extent is used to map swap page offset to backing device's block
offset. For a continuous block range, one swap_extent is used and all
these swap_extents are managed in a linked list.
These swap_extents are used by map_swap_entry() during swap's read and
write path. To find out the backing device's block offset for a page
offset, the swap_extent list will be traversed linearly, with
curr_swap_extent being used as a cache to speed up the search.
This works well as long as swap_extents are not huge or when the number
of processes that access swap device are few, but when the swap device
has many extents and there are a number of processes accessing the swap
device concurrently, it can be a problem. On one of our servers, the
disk's remaining size is tight:
$df -h
Filesystem Size Used Avail Use% Mounted on
... ...
/dev/nvme0n1p1 1.8T 1.3T 504G 72% /home/t4
When creating a 80G swapfile there, there are as many as 84656 swap
extents. The end result is, kernel spends abou 30% time in
map_swap_entry() and swap throughput is only 70MB/s.
As a comparison, when I used smaller sized swapfile, like 4G whose
swap_extent dropped to 2000, swap throughput is back to 400-500MB/s and
map_swap_entry() is about 3%.
One downside of using rbtree for swap_extent is, 'struct rbtree' takes
24 bytes while 'struct list_head' takes 16 bytes, that's 8 bytes more
for each swap_extent. For a swapfile that has 80k swap_extents, that
means 625KiB more memory consumed.
Test:
Since it's not possible to reboot that server, I can not test this patch
diretly there. Instead, I tested it on another server with NVMe disk.
I created a 20G swapfile on an NVMe backed XFS fs. By default, the
filesystem is quite clean and the created swapfile has only 2 extents.
Testing vanilla and this patch shows no obvious performance difference
when swapfile is not fragmented.
To see the patch's effects, I used some tweaks to manually fragment the
swapfile by breaking the extent at 1M boundary. This made the swapfile
have 20K extents.
nr_task=4
kernel swapout(KB/s) map_swap_entry(perf) swapin(KB/s) map_swap_entry(perf)
vanilla 165191 90.77% 171798 90.21%
patched 858993 +420% 2.16% 715827 +317% 0.77%
nr_task=8
kernel swapout(KB/s) map_swap_entry(perf) swapin(KB/s) map_swap_entry(perf)
vanilla 306783 92.19% 318145 87.76%
patched 954437 +211% 2.35% 1073741 +237% 1.57%
swapout: the throughput of swap out, in KB/s, higher is better 1st
map_swap_entry: cpu cycles percent sampled by perf swapin: the
throughput of swap in, in KB/s, higher is better. 2nd map_swap_entry:
cpu cycles percent sampled by perf
nr_task=1 doesn't show any difference, this is due to the curr_swap_extent
can be effectively used to cache the correct swap extent for single task
workload.
[akpm@linux-foundation.org: s/BUG_ON(1)/BUG()/]
Link: http://lkml.kernel.org/r/20190523142404.GA181@aaronlu
Signed-off-by: Aaron Lu <ziqian.lzq@antfin.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:41 +00:00
|
|
|
struct rb_root swap_extent_root;/* root of the swap extent rbtree */
|
2023-09-27 09:34:24 +00:00
|
|
|
struct bdev_handle *bdev_handle;/* open handle of the bdev */
|
2009-12-15 01:58:48 +00:00
|
|
|
struct block_device *bdev; /* swap device or bdev of swap file */
|
|
|
|
|
struct file *swap_file; /* seldom referenced */
|
|
|
|
|
unsigned int old_block_size; /* seldom referenced */
|
2021-06-29 02:36:46 +00:00
|
|
|
struct completion comp; /* seldom referenced */
|
swap: add per-partition lock for swapfile
swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD). The main contention comes
from swap_info_get(). This patch tries to fix the gap with adding a new
per-partition lock.
Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.
nr_swap_pages is an atomic now, it can be changed without swap_lock. In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages. But sounds not a big problem.
Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.
Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it. read the
flags is ok with either the locks hold.
If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.
swap_entry_free() can change swap_list. To delete that code, we add a
new highest_priority_index. Whenever get_swap_page() is called, we
check it. If it's valid, we use it.
It's a pity get_swap_page() still holds swap_lock(). But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush). And
BTW, looks get_swap_page() doesn't really need the lock. We never free
swap_info[] and we check SWAP_WRITEOK flag. The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.
"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s. This patch further improves the
speed to 2.3G/s, so around 15% improvement. It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.
[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 00:34:38 +00:00
|
|
|
spinlock_t lock; /*
|
|
|
|
|
* protect map scan related fields like
|
|
|
|
|
* swap_map, lowest_bit, highest_bit,
|
|
|
|
|
* inuse_pages, cluster_next,
|
swap: make swap discard async
swap can do cluster discard for SSD, which is good, but there are some
problems here:
1. swap do the discard just before page reclaim gets a swap entry and
writes the disk sectors. This is useless for high end SSD, because an
overwrite to a sector implies a discard to original sector too. A
discard + overwrite == overwrite.
2. the purpose of doing discard is to improve SSD firmware garbage
collection. Idealy we should send discard as early as possible, so
firmware can do something smart. Sending discard just after swap entry
is freed is considered early compared to sending discard before write.
Of course, if workload is already bound to gc speed, sending discard
earlier or later doesn't make
3. block discard is a sync API, which will delay scan_swap_map()
significantly.
4. Write and discard command can be executed parallel in PCIe SSD.
Making swap discard async can make execution more efficiently.
This patch makes swap discard async and moves discard to where swap entry
is freed. Discard and write have no dependence now, so above issues can
be avoided. Idealy we should do discard for any freed sectors, but some
SSD discard is very slow. This patch still does discard for a whole
cluster.
My test does a several round of 'mmap, write, unmap', which will trigger a
lot of swap discard. In a fusionio card, with this patch, the test
runtime is reduced to 18% of the time without it, so around 5.5x faster.
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:30 +00:00
|
|
|
* cluster_nr, lowest_alloc,
|
|
|
|
|
* highest_alloc, free/discard cluster
|
|
|
|
|
* list. other fields are only changed
|
|
|
|
|
* at swapon/swapoff, so are protected
|
|
|
|
|
* by swap_lock. changing flags need
|
|
|
|
|
* hold this lock and swap_lock. If
|
|
|
|
|
* both locks need hold, hold swap_lock
|
|
|
|
|
* first.
|
swap: add per-partition lock for swapfile
swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD). The main contention comes
from swap_info_get(). This patch tries to fix the gap with adding a new
per-partition lock.
Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.
nr_swap_pages is an atomic now, it can be changed without swap_lock. In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages. But sounds not a big problem.
Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.
Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it. read the
flags is ok with either the locks hold.
If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.
swap_entry_free() can change swap_list. To delete that code, we add a
new highest_priority_index. Whenever get_swap_page() is called, we
check it. If it's valid, we use it.
It's a pity get_swap_page() still holds swap_lock(). But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush). And
BTW, looks get_swap_page() doesn't really need the lock. We never free
swap_info[] and we check SWAP_WRITEOK flag. The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.
"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s. This patch further improves the
speed to 2.3G/s, so around 15% improvement. It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.
[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 00:34:38 +00:00
|
|
|
*/
|
mm, swap: fix race between swap count continuation operations
One page may store a set of entries of the sis->swap_map
(swap_info_struct->swap_map) in multiple swap clusters.
If some of the entries has sis->swap_map[offset] > SWAP_MAP_MAX,
multiple pages will be used to store the set of entries of the
sis->swap_map. And the pages are linked with page->lru. This is called
swap count continuation. To access the pages which store the set of
entries of the sis->swap_map simultaneously, previously, sis->lock is
used. But to improve the scalability of __swap_duplicate(), swap
cluster lock may be used in swap_count_continued() now. This may race
with add_swap_count_continuation() which operates on a nearby swap
cluster, in which the sis->swap_map entries are stored in the same page.
The race can cause wrong swap count in practice, thus cause unfreeable
swap entries or software lockup, etc.
To fix the race, a new spin lock called cont_lock is added to struct
swap_info_struct to protect the swap count continuation page list. This
is a lock at the swap device level, so the scalability isn't very well.
But it is still much better than the original sis->lock, because it is
only acquired/released when swap count continuation is used. Which is
considered rare in practice. If it turns out that the scalability
becomes an issue for some workloads, we can split the lock into some
more fine grained locks.
Link: http://lkml.kernel.org/r/20171017081320.28133-1-ying.huang@intel.com
Fixes: 235b62176712 ("mm/swap: add cluster lock")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Shaohua Li <shli@kernel.org>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org> [4.11+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-02 22:59:50 +00:00
|
|
|
spinlock_t cont_lock; /*
|
|
|
|
|
* protect swap count continuation page
|
|
|
|
|
* list.
|
|
|
|
|
*/
|
swap: make swap discard async
swap can do cluster discard for SSD, which is good, but there are some
problems here:
1. swap do the discard just before page reclaim gets a swap entry and
writes the disk sectors. This is useless for high end SSD, because an
overwrite to a sector implies a discard to original sector too. A
discard + overwrite == overwrite.
2. the purpose of doing discard is to improve SSD firmware garbage
collection. Idealy we should send discard as early as possible, so
firmware can do something smart. Sending discard just after swap entry
is freed is considered early compared to sending discard before write.
Of course, if workload is already bound to gc speed, sending discard
earlier or later doesn't make
3. block discard is a sync API, which will delay scan_swap_map()
significantly.
4. Write and discard command can be executed parallel in PCIe SSD.
Making swap discard async can make execution more efficiently.
This patch makes swap discard async and moves discard to where swap entry
is freed. Discard and write have no dependence now, so above issues can
be avoided. Idealy we should do discard for any freed sectors, but some
SSD discard is very slow. This patch still does discard for a whole
cluster.
My test does a several round of 'mmap, write, unmap', which will trigger a
lot of swap discard. In a fusionio card, with this patch, the test
runtime is reduced to 18% of the time without it, so around 5.5x faster.
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Kyungmin Park <kmpark@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rafael Aquini <aquini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-09-11 21:20:30 +00:00
|
|
|
struct work_struct discard_work; /* discard worker */
|
2016-10-07 23:58:42 +00:00
|
|
|
struct swap_cluster_list discard_clusters; /* discard clusters list */
|
2020-03-24 00:23:10 +00:00
|
|
|
struct plist_node avail_lists[]; /*
|
2018-12-28 08:34:39 +00:00
|
|
|
* entries in swap_avail_heads, one
|
|
|
|
|
* entry per node.
|
|
|
|
|
* Must be last as the number of the
|
|
|
|
|
* array is nr_node_ids, which is not
|
|
|
|
|
* a fixed value so have to allocate
|
|
|
|
|
* dynamically.
|
|
|
|
|
* And it has to be an array so that
|
|
|
|
|
* plist_for_each_* can work.
|
|
|
|
|
*/
|
2005-04-16 22:20:36 +00:00
|
|
|
};
|
|
|
|
|
|
2023-08-21 16:08:46 +00:00
|
|
|
static inline swp_entry_t page_swap_entry(struct page *page)
|
|
|
|
|
{
|
|
|
|
|
struct folio *folio = page_folio(page);
|
2023-08-21 16:08:48 +00:00
|
|
|
swp_entry_t entry = folio->swap;
|
2023-08-21 16:08:46 +00:00
|
|
|
|
|
|
|
|
entry.val += folio_page_idx(folio, page);
|
|
|
|
|
return entry;
|
|
|
|
|
}
|
|
|
|
|
|
2014-04-03 21:47:51 +00:00
|
|
|
/* linux/mm/workingset.c */
|
workingset: refactor LRU refault to expose refault recency check
Patch series "cachestat: a new syscall for page cache state of files",
v13.
There is currently no good way to query the page cache statistics of large
files and directory trees. There is mincore(), but it scales poorly: the
kernel writes out a lot of bitmap data that userspace has to aggregate,
when the user really does not care about per-page information in that
case. The user also needs to mmap and unmap each file as it goes along,
which can be quite slow as well.
Some use cases where this information could come in handy:
* Allowing database to decide whether to perform an index scan or direct
table queries based on the in-memory cache state of the index.
* Visibility into the writeback algorithm, for performance issues
diagnostic.
* Workload-aware writeback pacing: estimating IO fulfilled by page cache
(and IO to be done) within a range of a file, allowing for more
frequent syncing when and where there is IO capacity, and batching
when there is not.
* Computing memory usage of large files/directory trees, analogous to
the du tool for disk usage.
More information about these use cases could be found in this thread:
https://lore.kernel.org/lkml/20230315170934.GA97793@cmpxchg.org/
This series of patches introduces a new system call, cachestat, that
summarizes the page cache statistics (number of cached pages, dirty pages,
pages marked for writeback, evicted pages etc.) of a file, in a specified
range of bytes. It also include a selftest suite that tests some typical
usage. Currently, the syscall is only wired in for x86 architecture.
This interface is inspired by past discussion and concerns with fincore,
which has a similar design (and as a result, issues) as mincore. Relevant
links:
https://lkml.indiana.edu/hypermail/linux/kernel/1302.1/04207.html
https://lkml.indiana.edu/hypermail/linux/kernel/1302.1/04209.html
I have also developed a small tool that computes the memory usage of files
and directories, analogous to the du utility. User can choose between
mincore or cachestat (with cachestat exporting more information than
mincore). To compare the performance of these two options, I benchmarked
the tool on the root directory of a Meta's server machine, each for five
runs:
Using cachestat
real -- Median: 33.377s, Average: 33.475s, Standard Deviation: 0.3602
user -- Median: 4.08s, Average: 4.1078s, Standard Deviation: 0.0742
sys -- Median: 28.823s, Average: 28.8866s, Standard Deviation: 0.2689
Using mincore:
real -- Median: 102.352s, Average: 102.3442s, Standard Deviation: 0.2059
user -- Median: 10.149s, Average: 10.1482s, Standard Deviation: 0.0162
sys -- Median: 91.186s, Average: 91.2084s, Standard Deviation: 0.2046
I also ran both syscalls on a 2TB sparse file:
Using cachestat:
real 0m0.009s
user 0m0.000s
sys 0m0.009s
Using mincore:
real 0m37.510s
user 0m2.934s
sys 0m34.558s
Very large files like this are the pathological case for mincore. In
fact, to compute the stats for a single 2TB file, mincore takes as long as
cachestat takes to compute the stats for the entire tree! This could
easily happen inadvertently when we run it on subdirectories. Mincore is
clearly not suitable for a general-purpose command line tool.
Regarding security concerns, cachestat() should not pose any additional
issues. The caller already has read permission to the file itself (since
they need an fd to that file to call cachestat). This means that the
caller can access the underlying data in its entirety, which is a much
greater source of information (and as a result, a much greater security
risk) than the cache status itself.
The latest API change (in v13 of the patch series) is suggested by Jens
Axboe. It allows for 64-bit length argument, even on 32-bit architecture
(which is previously not possible due to the limit on the number of
syscall arguments). Furthermore, it eliminates the need for compatibility
handling - every user can use the same ABI.
This patch (of 4):
In preparation for computing recently evicted pages in cachestat, refactor
workingset_refault and lru_gen_refault to expose a helper function that
would test if an evicted page is recently evicted.
[penguin-kernel@I-love.SAKURA.ne.jp: add missing rcu_read_unlock() in lru_gen_refault()]
Link: https://lkml.kernel.org/r/610781bc-cf11-fc89-a46f-87cb8235d439@I-love.SAKURA.ne.jp
Link: https://lkml.kernel.org/r/20230503013608.2431726-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20230503013608.2431726-2-nphamcs@gmail.com
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Brian Foster <bfoster@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-03 01:36:06 +00:00
|
|
|
bool workingset_test_recent(void *shadow, bool file, bool *workingset);
|
2020-06-26 03:30:31 +00:00
|
|
|
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
|
2021-12-23 21:39:05 +00:00
|
|
|
void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg);
|
2021-04-29 14:27:16 +00:00
|
|
|
void workingset_refault(struct folio *folio, void *shadow);
|
2021-05-04 21:19:13 +00:00
|
|
|
void workingset_activation(struct folio *folio);
|
2017-11-16 01:37:41 +00:00
|
|
|
|
2017-11-17 15:01:45 +00:00
|
|
|
/* Only track the nodes of mappings with shadow entries */
|
|
|
|
|
void workingset_update_node(struct xa_node *node);
|
2022-03-22 21:41:12 +00:00
|
|
|
extern struct list_lru shadow_nodes;
|
2017-11-17 15:01:45 +00:00
|
|
|
#define mapping_set_update(xas, mapping) do { \
|
2022-03-22 21:41:12 +00:00
|
|
|
if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \
|
2017-11-17 15:01:45 +00:00
|
|
|
xas_set_update(xas, workingset_update_node); \
|
2022-03-22 21:41:12 +00:00
|
|
|
xas_set_lru(xas, &shadow_nodes); \
|
|
|
|
|
} \
|
2017-11-17 15:01:45 +00:00
|
|
|
} while (0)
|
2014-04-03 21:47:51 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/* linux/mm/page_alloc.c */
|
2006-04-11 05:52:59 +00:00
|
|
|
extern unsigned long totalreserve_pages;
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2017-09-06 23:23:36 +00:00
|
|
|
/* Definition of global_zone_page_state not available yet */
|
|
|
|
|
#define nr_free_pages() global_zone_page_state(NR_FREE_PAGES)
|
2007-02-10 09:43:03 +00:00
|
|
|
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
/* linux/mm/swap.c */
|
mm: vmscan: make rotations a secondary factor in balancing anon vs file
We noticed a 2% webserver throughput regression after upgrading from 5.6.
This could be tracked down to a shift in the anon/file reclaim balance
(confirmed with swappiness) that resulted in worse reclaim efficiency and
thus more kswapd activity for the same outcome.
The change that exposed the problem is aae466b0052e ("mm/swap: implement
workingset detection for anonymous LRU"). By qualifying swapins based on
their refault distance, it lowered the cost of anon reclaim in this
workload, in turn causing (much) more anon scanning than before. Scanning
the anon list is more expensive due to the higher ratio of mmapped pages
that may rotate during reclaim, and so the result was an increase in %sys
time.
Right now, rotations aren't considered a cost when balancing scan pressure
between LRUs. We can end up with very few file refaults putting all the
scan pressure on hot anon pages that are rotated en masse, don't get
reclaimed, and never push back on the file LRU again. We still only
reclaim file cache in that case, but we burn a lot CPU rotating anon
pages. It's "fair" from an LRU age POV, but doesn't reflect the real cost
it imposes on the system.
Consider rotations as a secondary factor in balancing the LRUs. This
doesn't attempt to make a precise comparison between IO cost and CPU cost,
it just says: if reloads are about comparable between the lists, or
rotations are overwhelmingly different, adjust for CPU work.
This fixed the regression on our webservers. It has since been deployed
to the entire Meta fleet and hasn't caused any problems.
Link: https://lkml.kernel.org/r/20221013193113.726425-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-10-13 19:31:13 +00:00
|
|
|
void lru_note_cost(struct lruvec *lruvec, bool file,
|
|
|
|
|
unsigned int nr_io, unsigned int nr_rotated);
|
|
|
|
|
void lru_note_cost_refault(struct folio *);
|
2022-09-02 19:46:01 +00:00
|
|
|
void folio_add_lru(struct folio *);
|
|
|
|
|
void folio_add_lru_vma(struct folio *, struct vm_area_struct *);
|
2021-04-27 14:47:39 +00:00
|
|
|
void mark_page_accessed(struct page *);
|
|
|
|
|
void folio_mark_accessed(struct folio *);
|
mm: disable LRU pagevec during the migration temporarily
LRU pagevec holds refcount of pages until the pagevec are drained. It
could prevent migration since the refcount of the page is greater than
the expection in migration logic. To mitigate the issue, callers of
migrate_pages drains LRU pagevec via migrate_prep or lru_add_drain_all
before migrate_pages call.
However, it's not enough because pages coming into pagevec after the
draining call still could stay at the pagevec so it could keep
preventing page migration. Since some callers of migrate_pages have
retrial logic with LRU draining, the page would migrate at next trail
but it is still fragile in that it doesn't close the fundamental race
between upcoming LRU pages into pagvec and migration so the migration
failure could cause contiguous memory allocation failure in the end.
To close the race, this patch disables lru caches(i.e, pagevec) during
ongoing migration until migrate is done.
Since it's really hard to reproduce, I measured how many times
migrate_pages retried with force mode(it is about a fallback to a sync
migration) with below debug code.
int migrate_pages(struct list_head *from, new_page_t get_new_page,
..
..
if (rc && reason == MR_CONTIG_RANGE && pass > 2) {
printk(KERN_ERR, "pfn 0x%lx reason %d", page_to_pfn(page), rc);
dump_page(page, "fail to migrate");
}
The test was repeating android apps launching with cma allocation in
background every five seconds. Total cma allocation count was about 500
during the testing. With this patch, the dump_page count was reduced
from 400 to 30.
The new interface is also useful for memory hotplug which currently
drains lru pcp caches after each migration failure. This is rather
suboptimal as it has to disrupt others running during the operation.
With the new interface the operation happens only once. This is also in
line with pcp allocator cache which are disabled for the offlining as
well.
Link: https://lkml.kernel.org/r/20210319175127.886124-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Chris Goldsworthy <cgoldswo@codeaurora.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: John Dias <joaodias@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Oliver Sang <oliver.sang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-05 01:36:54 +00:00
|
|
|
|
|
|
|
|
extern atomic_t lru_disable_count;
|
|
|
|
|
|
|
|
|
|
static inline bool lru_cache_disabled(void)
|
|
|
|
|
{
|
|
|
|
|
return atomic_read(&lru_disable_count);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void lru_cache_enable(void)
|
|
|
|
|
{
|
|
|
|
|
atomic_dec(&lru_disable_count);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
extern void lru_cache_disable(void);
|
2005-04-16 22:20:36 +00:00
|
|
|
extern void lru_add_drain(void);
|
2012-03-21 23:34:06 +00:00
|
|
|
extern void lru_add_drain_cpu(int cpu);
|
2020-05-27 20:11:15 +00:00
|
|
|
extern void lru_add_drain_cpu_zone(struct zone *zone);
|
2013-09-12 22:13:55 +00:00
|
|
|
extern void lru_add_drain_all(void);
|
2022-12-21 18:08:48 +00:00
|
|
|
void folio_deactivate(struct folio *folio);
|
2022-12-09 02:06:18 +00:00
|
|
|
void folio_mark_lazyfree(struct folio *folio);
|
2005-04-16 22:20:36 +00:00
|
|
|
extern void swap_setup(void);
|
|
|
|
|
|
|
|
|
|
/* linux/mm/vmscan.c */
|
2016-07-28 22:47:31 +00:00
|
|
|
extern unsigned long zone_reclaimable_pages(struct zone *zone);
|
2008-04-28 09:12:12 +00:00
|
|
|
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
|
2009-03-31 22:23:31 +00:00
|
|
|
gfp_t gfp_mask, nodemask_t *mask);
|
2022-07-14 06:49:18 +00:00
|
|
|
|
|
|
|
|
#define MEMCG_RECLAIM_MAY_SWAP (1 << 1)
|
|
|
|
|
#define MEMCG_RECLAIM_PROACTIVE (1 << 2)
|
2014-10-09 22:28:56 +00:00
|
|
|
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
|
|
|
|
|
unsigned long nr_pages,
|
|
|
|
|
gfp_t gfp_mask,
|
2022-12-16 09:46:33 +00:00
|
|
|
unsigned int reclaim_options);
|
2016-07-28 22:46:02 +00:00
|
|
|
extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
|
2011-09-14 23:21:58 +00:00
|
|
|
gfp_t gfp_mask, bool noswap,
|
2016-07-28 22:46:05 +00:00
|
|
|
pg_data_t *pgdat,
|
2011-09-14 23:21:58 +00:00
|
|
|
unsigned long *nr_scanned);
|
2006-03-22 08:08:19 +00:00
|
|
|
extern unsigned long shrink_all_memory(unsigned long nr_pages);
|
2005-04-16 22:20:36 +00:00
|
|
|
extern int vm_swappiness;
|
2022-02-13 03:48:55 +00:00
|
|
|
long remove_mapping(struct address_space *mapping, struct folio *folio);
|
2006-03-22 08:09:12 +00:00
|
|
|
|
2006-01-19 01:42:31 +00:00
|
|
|
#ifdef CONFIG_NUMA
|
2016-07-28 22:46:32 +00:00
|
|
|
extern int node_reclaim_mode;
|
2006-07-03 07:24:13 +00:00
|
|
|
extern int sysctl_min_unmapped_ratio;
|
2006-09-26 06:31:52 +00:00
|
|
|
extern int sysctl_min_slab_ratio;
|
2006-01-19 01:42:31 +00:00
|
|
|
#else
|
2016-07-28 22:46:32 +00:00
|
|
|
#define node_reclaim_mode 0
|
2006-01-19 01:42:31 +00:00
|
|
|
#endif
|
|
|
|
|
|
2021-05-05 01:36:04 +00:00
|
|
|
static inline bool node_reclaim_enabled(void)
|
|
|
|
|
{
|
|
|
|
|
/* Is any node_reclaim_mode bit set? */
|
|
|
|
|
return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP);
|
|
|
|
|
}
|
|
|
|
|
|
2022-06-04 21:39:09 +00:00
|
|
|
void check_move_unevictable_folios(struct folio_batch *fbatch);
|
2008-10-19 03:26:53 +00:00
|
|
|
|
2023-06-06 12:18:13 +00:00
|
|
|
extern void __meminit kswapd_run(int nid);
|
|
|
|
|
extern void __meminit kswapd_stop(int nid);
|
2015-09-08 22:01:02 +00:00
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
#ifdef CONFIG_SWAP
|
2016-11-01 13:40:16 +00:00
|
|
|
|
2012-07-31 23:44:57 +00:00
|
|
|
int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
|
|
|
|
|
unsigned long nr_pages, sector_t start_block);
|
|
|
|
|
int generic_swapfile_activate(struct swap_info_struct *, struct file *,
|
|
|
|
|
sector_t *);
|
|
|
|
|
|
2021-02-24 20:03:55 +00:00
|
|
|
static inline unsigned long total_swapcache_pages(void)
|
|
|
|
|
{
|
|
|
|
|
return global_node_page_state(NR_SWAPCACHE);
|
|
|
|
|
}
|
|
|
|
|
|
2022-06-25 09:28:16 +00:00
|
|
|
extern void free_swap_cache(struct page *page);
|
2005-04-16 22:20:36 +00:00
|
|
|
extern void free_page_and_swap_cache(struct page *);
|
2022-11-09 20:30:50 +00:00
|
|
|
extern void free_pages_and_swap_cache(struct encoded_page **, int);
|
2005-04-16 22:20:36 +00:00
|
|
|
/* linux/mm/swapfile.c */
|
swap: add per-partition lock for swapfile
swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD). The main contention comes
from swap_info_get(). This patch tries to fix the gap with adding a new
per-partition lock.
Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.
nr_swap_pages is an atomic now, it can be changed without swap_lock. In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages. But sounds not a big problem.
Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.
Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it. read the
flags is ok with either the locks hold.
If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.
swap_entry_free() can change swap_list. To delete that code, we add a
new highest_priority_index. Whenever get_swap_page() is called, we
check it. If it's valid, we use it.
It's a pity get_swap_page() still holds swap_lock(). But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush). And
BTW, looks get_swap_page() doesn't really need the lock. We never free
swap_info[] and we check SWAP_WRITEOK flag. The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.
"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s. This patch further improves the
speed to 2.3G/s, so around 15% improvement. It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.
[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 00:34:38 +00:00
|
|
|
extern atomic_long_t nr_swap_pages;
|
2005-04-16 22:20:36 +00:00
|
|
|
extern long total_swap_pages;
|
2017-09-06 23:24:43 +00:00
|
|
|
extern atomic_t nr_rotate_swap;
|
2017-02-22 23:45:39 +00:00
|
|
|
extern bool has_usable_swap(void);
|
swap: add per-partition lock for swapfile
swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD). The main contention comes
from swap_info_get(). This patch tries to fix the gap with adding a new
per-partition lock.
Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.
nr_swap_pages is an atomic now, it can be changed without swap_lock. In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages. But sounds not a big problem.
Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.
Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it. read the
flags is ok with either the locks hold.
If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.
swap_entry_free() can change swap_list. To delete that code, we add a
new highest_priority_index. Whenever get_swap_page() is called, we
check it. If it's valid, we use it.
It's a pity get_swap_page() still holds swap_lock(). But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush). And
BTW, looks get_swap_page() doesn't really need the lock. We never free
swap_info[] and we check SWAP_WRITEOK flag. The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.
"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s. This patch further improves the
speed to 2.3G/s, so around 15% improvement. It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.
[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 00:34:38 +00:00
|
|
|
|
|
|
|
|
/* Swap 50% full? Release swapcache more aggressively.. */
|
|
|
|
|
static inline bool vm_swap_full(void)
|
|
|
|
|
{
|
|
|
|
|
return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline long get_nr_swap_pages(void)
|
|
|
|
|
{
|
|
|
|
|
return atomic_long_read(&nr_swap_pages);
|
|
|
|
|
}
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
extern void si_swapinfo(struct sysinfo *);
|
2022-05-13 03:23:02 +00:00
|
|
|
swp_entry_t folio_alloc_swap(struct folio *folio);
|
2022-09-02 19:46:06 +00:00
|
|
|
bool folio_free_swap(struct folio *folio);
|
2022-09-02 19:46:09 +00:00
|
|
|
void put_swap_folio(struct folio *folio, swp_entry_t entry);
|
2010-09-09 23:38:07 +00:00
|
|
|
extern swp_entry_t get_swap_page_of_type(int);
|
2018-08-22 04:52:20 +00:00
|
|
|
extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size);
|
swap_info: swap count continuations
Swap is duplicated (reference count incremented by one) whenever the same
swap page is inserted into another mm (when forking finds a swap entry in
place of a pte, or when reclaim unmaps a pte to insert the swap entry).
swap_info_struct's vmalloc'ed swap_map is the array of these reference
counts: but what happens when the unsigned short (or unsigned char since
the preceding patch) is full? (and its high bit is kept for a cache flag)
We then lose track of it, never freeing, leaving it in use until swapoff:
at which point we _hope_ that a single pass will have found all instances,
assume there are no more, and will lose user data if we're wrong.
Swapping of KSM pages has not yet been enabled; but it is implemented,
and makes it very easy for a user to overflow the maximum swap count:
possible with ordinary process pages, but unlikely, even when pid_max
has been raised from PID_MAX_DEFAULT.
This patch implements swap count continuations: when the count overflows,
a continuation page is allocated and linked to the original vmalloc'ed
map page, and this used to hold the continuation counts for that entry
and its neighbours. These continuation pages are seldom referenced:
the common paths all work on the original swap_map, only referring to
a continuation page when the low "digit" of a count is incremented or
decremented through SWAP_MAP_MAX.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:46 +00:00
|
|
|
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
|
2009-12-15 01:58:47 +00:00
|
|
|
extern void swap_shmem_alloc(swp_entry_t);
|
swap_info: swap count continuations
Swap is duplicated (reference count incremented by one) whenever the same
swap page is inserted into another mm (when forking finds a swap entry in
place of a pte, or when reclaim unmaps a pte to insert the swap entry).
swap_info_struct's vmalloc'ed swap_map is the array of these reference
counts: but what happens when the unsigned short (or unsigned char since
the preceding patch) is full? (and its high bit is kept for a cache flag)
We then lose track of it, never freeing, leaving it in use until swapoff:
at which point we _hope_ that a single pass will have found all instances,
assume there are no more, and will lose user data if we're wrong.
Swapping of KSM pages has not yet been enabled; but it is implemented,
and makes it very easy for a user to overflow the maximum swap count:
possible with ordinary process pages, but unlikely, even when pid_max
has been raised from PID_MAX_DEFAULT.
This patch implements swap count continuations: when the count overflows,
a continuation page is allocated and linked to the original vmalloc'ed
map page, and this used to hold the continuation counts for that entry
and its neighbours. These continuation pages are seldom referenced:
the common paths all work on the original swap_map, only referring to
a continuation page when the low "digit" of a count is incremented or
decremented through SWAP_MAP_MAX.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:46 +00:00
|
|
|
extern int swap_duplicate(swp_entry_t);
|
|
|
|
|
extern int swapcache_prepare(swp_entry_t);
|
2005-04-16 22:20:36 +00:00
|
|
|
extern void swap_free(swp_entry_t);
|
2017-02-22 23:45:36 +00:00
|
|
|
extern void swapcache_free_entries(swp_entry_t *entries, int n);
|
2009-01-06 22:40:10 +00:00
|
|
|
extern int free_swap_and_cache(swp_entry_t);
|
2020-09-21 07:19:56 +00:00
|
|
|
int swap_type_of(dev_t device, sector_t offset);
|
|
|
|
|
int find_first_swap(dev_t *device);
|
2006-03-23 10:59:59 +00:00
|
|
|
extern unsigned int count_swap_pages(int, int);
|
2006-12-07 04:34:10 +00:00
|
|
|
extern sector_t swapdev_block(int, pgoff_t);
|
mm, swap: fix race between swapoff and some swap operations
When swapin is performed, after getting the swap entry information from
the page table, system will swap in the swap entry, without any lock held
to prevent the swap device from being swapoff. This may cause the race
like below,
CPU 1 CPU 2
----- -----
do_swap_page
swapin_readahead
__read_swap_cache_async
swapoff swapcache_prepare
p->swap_map = NULL __swap_duplicate
p->swap_map[?] /* !!! NULL pointer access */
Because swapoff is usually done when system shutdown only, the race may
not hit many people in practice. But it is still a race need to be fixed.
To fix the race, get_swap_device() is added to check whether the specified
swap entry is valid in its swap device. If so, it will keep the swap
entry valid via preventing the swap device from being swapoff, until
put_swap_device() is called.
Because swapoff() is very rare code path, to make the normal path runs as
fast as possible, rcu_read_lock/unlock() and synchronize_rcu() instead of
reference count is used to implement get/put_swap_device(). >From
get_swap_device() to put_swap_device(), RCU reader side is locked, so
synchronize_rcu() in swapoff() will wait until put_swap_device() is
called.
In addition to swap_map, cluster_info, etc. data structure in the struct
swap_info_struct, the swap cache radix tree will be freed after swapoff,
so this patch fixes the race between swap cache looking up and swapoff
too.
Races between some other swap cache usages and swapoff are fixed too via
calling synchronize_rcu() between clearing PageSwapCache() and freeing
swap cache data structure.
Another possible method to fix this is to use preempt_off() +
stop_machine() to prevent the swap device from being swapoff when its data
structure is being accessed. The overhead in hot-path of both methods is
similar. The advantages of RCU based method are,
1. stop_machine() may disturb the normal execution code path on other
CPUs.
2. File cache uses RCU to protect its radix tree. If the similar
mechanism is used for swap cache too, it is easier to share code
between them.
3. RCU is used to protect swap cache in total_swapcache_pages() and
exit_swap_address_space() already. The two mechanisms can be
merged to simplify the logic.
Link: http://lkml.kernel.org/r/20190522015423.14418-1-ying.huang@intel.com
Fixes: 235b62176712 ("mm/swap: add cluster lock")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Not-nacked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:33 +00:00
|
|
|
extern int __swap_count(swp_entry_t entry);
|
2023-05-29 06:13:53 +00:00
|
|
|
extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry);
|
2015-09-08 22:00:24 +00:00
|
|
|
extern int swp_swapcount(swp_entry_t entry);
|
2023-12-13 21:58:40 +00:00
|
|
|
struct swap_info_struct *swp_swap_info(swp_entry_t entry);
|
2005-04-16 22:20:36 +00:00
|
|
|
struct backing_dev_info;
|
mm/swap: split swap cache into 64MB trunks
The patch is to improve the scalability of the swap out/in via using
fine grained locks for the swap cache. In current kernel, one address
space will be used for each swap device. And in the common
configuration, the number of the swap device is very small (one is
typical). This causes the heavy lock contention on the radix tree of
the address space if multiple tasks swap out/in concurrently.
But in fact, there is no dependency between pages in the swap cache. So
that, we can split the one shared address space for each swap device
into several address spaces to reduce the lock contention. In the
patch, the shared address space is split into 64MB trunks. 64MB is
chosen to balance the memory space usage and effect of lock contention
reduction.
The size of struct address_space on x86_64 architecture is 408B, so with
the patch, 6528B more memory will be used for every 1GB swap space on
x86_64 architecture.
One address space is still shared for the swap entries in the same 64M
trunks. To avoid lock contention for the first round of swap space
allocation, the order of the swap clusters in the initial free clusters
list is changed. The swap space distance between the consecutive swap
clusters in the free cluster list is at least 64M. After the first
round of allocation, the swap clusters are expected to be freed
randomly, so the lock contention should be reduced effectively.
Link: http://lkml.kernel.org/r/735bab895e64c930581ffb0a05b661e01da82bc5.1484082593.git.tim.c.chen@linux.intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net> escreveu:
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-22 23:45:26 +00:00
|
|
|
extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
|
|
|
|
|
extern void exit_swap_address_space(unsigned int type);
|
mm, swap: fix race between swapoff and some swap operations
When swapin is performed, after getting the swap entry information from
the page table, system will swap in the swap entry, without any lock held
to prevent the swap device from being swapoff. This may cause the race
like below,
CPU 1 CPU 2
----- -----
do_swap_page
swapin_readahead
__read_swap_cache_async
swapoff swapcache_prepare
p->swap_map = NULL __swap_duplicate
p->swap_map[?] /* !!! NULL pointer access */
Because swapoff is usually done when system shutdown only, the race may
not hit many people in practice. But it is still a race need to be fixed.
To fix the race, get_swap_device() is added to check whether the specified
swap entry is valid in its swap device. If so, it will keep the swap
entry valid via preventing the swap device from being swapoff, until
put_swap_device() is called.
Because swapoff() is very rare code path, to make the normal path runs as
fast as possible, rcu_read_lock/unlock() and synchronize_rcu() instead of
reference count is used to implement get/put_swap_device(). >From
get_swap_device() to put_swap_device(), RCU reader side is locked, so
synchronize_rcu() in swapoff() will wait until put_swap_device() is
called.
In addition to swap_map, cluster_info, etc. data structure in the struct
swap_info_struct, the swap cache radix tree will be freed after swapoff,
so this patch fixes the race between swap cache looking up and swapoff
too.
Races between some other swap cache usages and swapoff are fixed too via
calling synchronize_rcu() between clearing PageSwapCache() and freeing
swap cache data structure.
Another possible method to fix this is to use preempt_off() +
stop_machine() to prevent the swap device from being swapoff when its data
structure is being accessed. The overhead in hot-path of both methods is
similar. The advantages of RCU based method are,
1. stop_machine() may disturb the normal execution code path on other
CPUs.
2. File cache uses RCU to protect its radix tree. If the similar
mechanism is used for swap cache too, it is easier to share code
between them.
3. RCU is used to protect swap cache in total_swapcache_pages() and
exit_swap_address_space() already. The two mechanisms can be
merged to simplify the logic.
Link: http://lkml.kernel.org/r/20190522015423.14418-1-ying.huang@intel.com
Fixes: 235b62176712 ("mm/swap: add cluster lock")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Not-nacked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:33 +00:00
|
|
|
extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
|
2023-12-13 21:58:38 +00:00
|
|
|
sector_t swap_folio_sector(struct folio *folio);
|
mm, swap: fix race between swapoff and some swap operations
When swapin is performed, after getting the swap entry information from
the page table, system will swap in the swap entry, without any lock held
to prevent the swap device from being swapoff. This may cause the race
like below,
CPU 1 CPU 2
----- -----
do_swap_page
swapin_readahead
__read_swap_cache_async
swapoff swapcache_prepare
p->swap_map = NULL __swap_duplicate
p->swap_map[?] /* !!! NULL pointer access */
Because swapoff is usually done when system shutdown only, the race may
not hit many people in practice. But it is still a race need to be fixed.
To fix the race, get_swap_device() is added to check whether the specified
swap entry is valid in its swap device. If so, it will keep the swap
entry valid via preventing the swap device from being swapoff, until
put_swap_device() is called.
Because swapoff() is very rare code path, to make the normal path runs as
fast as possible, rcu_read_lock/unlock() and synchronize_rcu() instead of
reference count is used to implement get/put_swap_device(). >From
get_swap_device() to put_swap_device(), RCU reader side is locked, so
synchronize_rcu() in swapoff() will wait until put_swap_device() is
called.
In addition to swap_map, cluster_info, etc. data structure in the struct
swap_info_struct, the swap cache radix tree will be freed after swapoff,
so this patch fixes the race between swap cache looking up and swapoff
too.
Races between some other swap cache usages and swapoff are fixed too via
calling synchronize_rcu() between clearing PageSwapCache() and freeing
swap cache data structure.
Another possible method to fix this is to use preempt_off() +
stop_machine() to prevent the swap device from being swapoff when its data
structure is being accessed. The overhead in hot-path of both methods is
similar. The advantages of RCU based method are,
1. stop_machine() may disturb the normal execution code path on other
CPUs.
2. File cache uses RCU to protect its radix tree. If the similar
mechanism is used for swap cache too, it is easier to share code
between them.
3. RCU is used to protect swap cache in total_swapcache_pages() and
exit_swap_address_space() already. The two mechanisms can be
merged to simplify the logic.
Link: http://lkml.kernel.org/r/20190522015423.14418-1-ying.huang@intel.com
Fixes: 235b62176712 ("mm/swap: add cluster lock")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Not-nacked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:33 +00:00
|
|
|
|
|
|
|
|
static inline void put_swap_device(struct swap_info_struct *si)
|
|
|
|
|
{
|
2021-06-29 02:36:46 +00:00
|
|
|
percpu_ref_put(&si->users);
|
mm, swap: fix race between swapoff and some swap operations
When swapin is performed, after getting the swap entry information from
the page table, system will swap in the swap entry, without any lock held
to prevent the swap device from being swapoff. This may cause the race
like below,
CPU 1 CPU 2
----- -----
do_swap_page
swapin_readahead
__read_swap_cache_async
swapoff swapcache_prepare
p->swap_map = NULL __swap_duplicate
p->swap_map[?] /* !!! NULL pointer access */
Because swapoff is usually done when system shutdown only, the race may
not hit many people in practice. But it is still a race need to be fixed.
To fix the race, get_swap_device() is added to check whether the specified
swap entry is valid in its swap device. If so, it will keep the swap
entry valid via preventing the swap device from being swapoff, until
put_swap_device() is called.
Because swapoff() is very rare code path, to make the normal path runs as
fast as possible, rcu_read_lock/unlock() and synchronize_rcu() instead of
reference count is used to implement get/put_swap_device(). >From
get_swap_device() to put_swap_device(), RCU reader side is locked, so
synchronize_rcu() in swapoff() will wait until put_swap_device() is
called.
In addition to swap_map, cluster_info, etc. data structure in the struct
swap_info_struct, the swap cache radix tree will be freed after swapoff,
so this patch fixes the race between swap cache looking up and swapoff
too.
Races between some other swap cache usages and swapoff are fixed too via
calling synchronize_rcu() between clearing PageSwapCache() and freeing
swap cache data structure.
Another possible method to fix this is to use preempt_off() +
stop_machine() to prevent the swap device from being swapoff when its data
structure is being accessed. The overhead in hot-path of both methods is
similar. The advantages of RCU based method are,
1. stop_machine() may disturb the normal execution code path on other
CPUs.
2. File cache uses RCU to protect its radix tree. If the similar
mechanism is used for swap cache too, it is easier to share code
between them.
3. RCU is used to protect swap cache in total_swapcache_pages() and
exit_swap_address_space() already. The two mechanisms can be
merged to simplify the logic.
Link: http://lkml.kernel.org/r/20190522015423.14418-1-ying.huang@intel.com
Fixes: 235b62176712 ("mm/swap: add cluster lock")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Not-nacked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:33 +00:00
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
#else /* CONFIG_SWAP */
|
2017-11-16 01:33:07 +00:00
|
|
|
static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry)
|
|
|
|
|
{
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
2021-06-29 02:36:50 +00:00
|
|
|
static inline struct swap_info_struct *get_swap_device(swp_entry_t entry)
|
|
|
|
|
{
|
|
|
|
|
return NULL;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline void put_swap_device(struct swap_info_struct *si)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
swap: add per-partition lock for swapfile
swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD). The main contention comes
from swap_info_get(). This patch tries to fix the gap with adding a new
per-partition lock.
Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.
nr_swap_pages is an atomic now, it can be changed without swap_lock. In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages. But sounds not a big problem.
Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.
Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it. read the
flags is ok with either the locks hold.
If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.
swap_entry_free() can change swap_list. To delete that code, we add a
new highest_priority_index. Whenever get_swap_page() is called, we
check it. If it's valid, we use it.
It's a pity get_swap_page() still holds swap_lock(). But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush). And
BTW, looks get_swap_page() doesn't really need the lock. We never free
swap_info[] and we check SWAP_WRITEOK flag. The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.
"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s. This patch further improves the
speed to 2.3G/s, so around 15% improvement. It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.
[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 00:34:38 +00:00
|
|
|
#define get_nr_swap_pages() 0L
|
2009-01-06 22:39:41 +00:00
|
|
|
#define total_swap_pages 0L
|
2013-02-23 00:34:37 +00:00
|
|
|
#define total_swapcache_pages() 0UL
|
swap: add per-partition lock for swapfile
swap_lock is heavily contended when I test swap to 3 fast SSD (even
slightly slower than swap to 2 such SSD). The main contention comes
from swap_info_get(). This patch tries to fix the gap with adding a new
per-partition lock.
Global data like nr_swapfiles, total_swap_pages, least_priority and
swap_list are still protected by swap_lock.
nr_swap_pages is an atomic now, it can be changed without swap_lock. In
theory, it's possible get_swap_page() finds no swap pages but actually
there are free swap pages. But sounds not a big problem.
Accessing partition specific data (like scan_swap_map and so on) is only
protected by swap_info_struct.lock.
Changing swap_info_struct.flags need hold swap_lock and
swap_info_struct.lock, because scan_scan_map() will check it. read the
flags is ok with either the locks hold.
If both swap_lock and swap_info_struct.lock must be hold, we always hold
the former first to avoid deadlock.
swap_entry_free() can change swap_list. To delete that code, we add a
new highest_priority_index. Whenever get_swap_page() is called, we
check it. If it's valid, we use it.
It's a pity get_swap_page() still holds swap_lock(). But in practice,
swap_lock() isn't heavily contended in my test with this patch (or I can
say there are other much more heavier bottlenecks like TLB flush). And
BTW, looks get_swap_page() doesn't really need the lock. We never free
swap_info[] and we check SWAP_WRITEOK flag. The only risk without the
lock is we could swapout to some low priority swap, but we can quickly
recover after several rounds of swap, so sounds not a big deal to me.
But I'd prefer to fix this if it's a real problem.
"swap: make each swap partition have one address_space" improved the
swapout speed from 1.7G/s to 2G/s. This patch further improves the
speed to 2.3G/s, so around 15% improvement. It's a multi-process test,
so TLB flush isn't the biggest bottleneck before the patches.
[arnd@arndb.de: fix it for nommu]
[hughd@google.com: add missing unlock]
[minchan@kernel.org: get rid of lockdep whinge on sys_swapon]
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-23 00:34:38 +00:00
|
|
|
#define vm_swap_full() 0
|
2005-04-16 22:20:36 +00:00
|
|
|
|
|
|
|
|
#define si_swapinfo(val) \
|
|
|
|
|
do { (val)->freeswap = (val)->totalswap = 0; } while (0)
|
2005-08-07 16:42:24 +00:00
|
|
|
/* only sparc can not include linux/pagemap.h in this file
|
2016-04-01 12:29:48 +00:00
|
|
|
* so leave put_page and release_pages undeclared... */
|
2005-04-16 22:20:36 +00:00
|
|
|
#define free_page_and_swap_cache(page) \
|
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros
PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.
This promise never materialized. And unlikely will.
We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE. And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.
Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.
Let's stop pretending that pages in page cache are special. They are
not.
The changes are pretty straight-forward:
- <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;
- PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};
- page_cache_get() -> get_page();
- page_cache_release() -> put_page();
This patch contains automated changes generated with coccinelle using
script below. For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.
The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.
There are few places in the code where coccinelle didn't reach. I'll
fix them manually in a separate patch. Comments and documentation also
will be addressed with the separate patch.
virtual patch
@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E
@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT
@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE
@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK
@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)
@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)
@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 12:29:47 +00:00
|
|
|
put_page(page)
|
2005-04-16 22:20:36 +00:00
|
|
|
#define free_pages_and_swap_cache(pages, nr) \
|
2017-11-16 01:37:55 +00:00
|
|
|
release_pages((pages), (nr));
|
2005-04-16 22:20:36 +00:00
|
|
|
|
2021-07-01 01:54:06 +00:00
|
|
|
/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */
|
|
|
|
|
#define free_swap_and_cache(e) is_pfn_swap_entry(e)
|
2006-06-23 09:03:42 +00:00
|
|
|
|
2022-06-25 09:28:16 +00:00
|
|
|
static inline void free_swap_cache(struct page *page)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
swap_info: swap count continuations
Swap is duplicated (reference count incremented by one) whenever the same
swap page is inserted into another mm (when forking finds a swap entry in
place of a pte, or when reclaim unmaps a pte to insert the swap entry).
swap_info_struct's vmalloc'ed swap_map is the array of these reference
counts: but what happens when the unsigned short (or unsigned char since
the preceding patch) is full? (and its high bit is kept for a cache flag)
We then lose track of it, never freeing, leaving it in use until swapoff:
at which point we _hope_ that a single pass will have found all instances,
assume there are no more, and will lose user data if we're wrong.
Swapping of KSM pages has not yet been enabled; but it is implemented,
and makes it very easy for a user to overflow the maximum swap count:
possible with ordinary process pages, but unlikely, even when pid_max
has been raised from PID_MAX_DEFAULT.
This patch implements swap count continuations: when the count overflows,
a continuation page is allocated and linked to the original vmalloc'ed
map page, and this used to hold the continuation counts for that entry
and its neighbours. These continuation pages are seldom referenced:
the common paths all work on the original swap_map, only referring to
a continuation page when the low "digit" of a count is incremented or
decremented through SWAP_MAP_MAX.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:46 +00:00
|
|
|
static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
|
2009-06-16 22:32:53 +00:00
|
|
|
{
|
swap_info: swap count continuations
Swap is duplicated (reference count incremented by one) whenever the same
swap page is inserted into another mm (when forking finds a swap entry in
place of a pte, or when reclaim unmaps a pte to insert the swap entry).
swap_info_struct's vmalloc'ed swap_map is the array of these reference
counts: but what happens when the unsigned short (or unsigned char since
the preceding patch) is full? (and its high bit is kept for a cache flag)
We then lose track of it, never freeing, leaving it in use until swapoff:
at which point we _hope_ that a single pass will have found all instances,
assume there are no more, and will lose user data if we're wrong.
Swapping of KSM pages has not yet been enabled; but it is implemented,
and makes it very easy for a user to overflow the maximum swap count:
possible with ordinary process pages, but unlikely, even when pid_max
has been raised from PID_MAX_DEFAULT.
This patch implements swap count continuations: when the count overflows,
a continuation page is allocated and linked to the original vmalloc'ed
map page, and this used to hold the continuation counts for that entry
and its neighbours. These continuation pages are seldom referenced:
the common paths all work on the original swap_map, only referring to
a continuation page when the low "digit" of a count is incremented or
decremented through SWAP_MAP_MAX.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:46 +00:00
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2009-12-15 01:58:47 +00:00
|
|
|
static inline void swap_shmem_alloc(swp_entry_t swp)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
swap_info: swap count continuations
Swap is duplicated (reference count incremented by one) whenever the same
swap page is inserted into another mm (when forking finds a swap entry in
place of a pte, or when reclaim unmaps a pte to insert the swap entry).
swap_info_struct's vmalloc'ed swap_map is the array of these reference
counts: but what happens when the unsigned short (or unsigned char since
the preceding patch) is full? (and its high bit is kept for a cache flag)
We then lose track of it, never freeing, leaving it in use until swapoff:
at which point we _hope_ that a single pass will have found all instances,
assume there are no more, and will lose user data if we're wrong.
Swapping of KSM pages has not yet been enabled; but it is implemented,
and makes it very easy for a user to overflow the maximum swap count:
possible with ordinary process pages, but unlikely, even when pid_max
has been raised from PID_MAX_DEFAULT.
This patch implements swap count continuations: when the count overflows,
a continuation page is allocated and linked to the original vmalloc'ed
map page, and this used to hold the continuation counts for that entry
and its neighbours. These continuation pages are seldom referenced:
the common paths all work on the original swap_map, only referring to
a continuation page when the low "digit" of a count is incremented or
decremented through SWAP_MAP_MAX.
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 01:58:46 +00:00
|
|
|
static inline int swap_duplicate(swp_entry_t swp)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
2009-06-16 22:32:53 +00:00
|
|
|
}
|
|
|
|
|
|
mm/swap: fix race when skipping swapcache
When skipping swapcache for SWP_SYNCHRONOUS_IO, if two or more threads
swapin the same entry at the same time, they get different pages (A, B).
Before one thread (T0) finishes the swapin and installs page (A) to the
PTE, another thread (T1) could finish swapin of page (B), swap_free the
entry, then swap out the possibly modified page reusing the same entry.
It breaks the pte_same check in (T0) because PTE value is unchanged,
causing ABA problem. Thread (T0) will install a stalled page (A) into the
PTE and cause data corruption.
One possible callstack is like this:
CPU0 CPU1
---- ----
do_swap_page() do_swap_page() with same entry
<direct swapin path> <direct swapin path>
<alloc page A> <alloc page B>
swap_read_folio() <- read to page A swap_read_folio() <- read to page B
<slow on later locks or interrupt> <finished swapin first>
... set_pte_at()
swap_free() <- entry is free
<write to page B, now page A stalled>
<swap out page B to same swap entry>
pte_same() <- Check pass, PTE seems
unchanged, but page A
is stalled!
swap_free() <- page B content lost!
set_pte_at() <- staled page A installed!
And besides, for ZRAM, swap_free() allows the swap device to discard the
entry content, so even if page (B) is not modified, if swap_read_folio()
on CPU0 happens later than swap_free() on CPU1, it may also cause data
loss.
To fix this, reuse swapcache_prepare which will pin the swap entry using
the cache flag, and allow only one thread to swap it in, also prevent any
parallel code from putting the entry in the cache. Release the pin after
PT unlocked.
Racers just loop and wait since it's a rare and very short event. A
schedule_timeout_uninterruptible(1) call is added to avoid repeated page
faults wasting too much CPU, causing livelock or adding too much noise to
perf statistics. A similar livelock issue was described in commit
029c4628b2eb ("mm: swap: get rid of livelock in swapin readahead")
Reproducer:
This race issue can be triggered easily using a well constructed
reproducer and patched brd (with a delay in read path) [1]:
With latest 6.8 mainline, race caused data loss can be observed easily:
$ gcc -g -lpthread test-thread-swap-race.c && ./a.out
Polulating 32MB of memory region...
Keep swapping out...
Starting round 0...
Spawning 65536 workers...
32746 workers spawned, wait for done...
Round 0: Error on 0x5aa00, expected 32746, got 32743, 3 data loss!
Round 0: Error on 0x395200, expected 32746, got 32743, 3 data loss!
Round 0: Error on 0x3fd000, expected 32746, got 32737, 9 data loss!
Round 0 Failed, 15 data loss!
This reproducer spawns multiple threads sharing the same memory region
using a small swap device. Every two threads updates mapped pages one by
one in opposite direction trying to create a race, with one dedicated
thread keep swapping out the data out using madvise.
The reproducer created a reproduce rate of about once every 5 minutes, so
the race should be totally possible in production.
After this patch, I ran the reproducer for over a few hundred rounds and
no data loss observed.
Performance overhead is minimal, microbenchmark swapin 10G from 32G
zram:
Before: 10934698 us
After: 11157121 us
Cached: 13155355 us (Dropping SWP_SYNCHRONOUS_IO flag)
[kasong@tencent.com: v4]
Link: https://lkml.kernel.org/r/20240219082040.7495-1-ryncsn@gmail.com
Link: https://lkml.kernel.org/r/20240206182559.32264-1-ryncsn@gmail.com
Fixes: 0bcac06f27d7 ("mm, swap: skip swapcache for swapin of synchronous device")
Reported-by: "Huang, Ying" <ying.huang@intel.com>
Closes: https://lore.kernel.org/lkml/87bk92gqpx.fsf_-_@yhuang6-desk2.ccr.corp.intel.com/
Link: https://github.com/ryncsn/emm-test-project/tree/master/swap-stress-race [1]
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Yu Zhao <yuzhao@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Chris Li <chrisl@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-02-06 18:25:59 +00:00
|
|
|
static inline int swapcache_prepare(swp_entry_t swp)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2006-06-23 09:03:42 +00:00
|
|
|
static inline void swap_free(swp_entry_t swp)
|
|
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
2022-09-02 19:46:09 +00:00
|
|
|
static inline void put_swap_folio(struct folio *folio, swp_entry_t swp)
|
2009-06-16 22:32:52 +00:00
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
mm, swap: fix race between swapoff and some swap operations
When swapin is performed, after getting the swap entry information from
the page table, system will swap in the swap entry, without any lock held
to prevent the swap device from being swapoff. This may cause the race
like below,
CPU 1 CPU 2
----- -----
do_swap_page
swapin_readahead
__read_swap_cache_async
swapoff swapcache_prepare
p->swap_map = NULL __swap_duplicate
p->swap_map[?] /* !!! NULL pointer access */
Because swapoff is usually done when system shutdown only, the race may
not hit many people in practice. But it is still a race need to be fixed.
To fix the race, get_swap_device() is added to check whether the specified
swap entry is valid in its swap device. If so, it will keep the swap
entry valid via preventing the swap device from being swapoff, until
put_swap_device() is called.
Because swapoff() is very rare code path, to make the normal path runs as
fast as possible, rcu_read_lock/unlock() and synchronize_rcu() instead of
reference count is used to implement get/put_swap_device(). >From
get_swap_device() to put_swap_device(), RCU reader side is locked, so
synchronize_rcu() in swapoff() will wait until put_swap_device() is
called.
In addition to swap_map, cluster_info, etc. data structure in the struct
swap_info_struct, the swap cache radix tree will be freed after swapoff,
so this patch fixes the race between swap cache looking up and swapoff
too.
Races between some other swap cache usages and swapoff are fixed too via
calling synchronize_rcu() between clearing PageSwapCache() and freeing
swap cache data structure.
Another possible method to fix this is to use preempt_off() +
stop_machine() to prevent the swap device from being swapoff when its data
structure is being accessed. The overhead in hot-path of both methods is
similar. The advantages of RCU based method are,
1. stop_machine() may disturb the normal execution code path on other
CPUs.
2. File cache uses RCU to protect its radix tree. If the similar
mechanism is used for swap cache too, it is easier to share code
between them.
3. RCU is used to protect swap cache in total_swapcache_pages() and
exit_swap_address_space() already. The two mechanisms can be
merged to simplify the logic.
Link: http://lkml.kernel.org/r/20190522015423.14418-1-ying.huang@intel.com
Fixes: 235b62176712 ("mm/swap: add cluster lock")
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Not-nacked-by: Hugh Dickins <hughd@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-12 03:55:33 +00:00
|
|
|
static inline int __swap_count(swp_entry_t entry)
|
2017-11-16 01:33:11 +00:00
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2023-05-29 06:13:53 +00:00
|
|
|
static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
|
2017-02-22 23:45:29 +00:00
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2015-09-08 22:00:24 +00:00
|
|
|
static inline int swp_swapcount(swp_entry_t entry)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2022-05-13 03:23:02 +00:00
|
|
|
static inline swp_entry_t folio_alloc_swap(struct folio *folio)
|
2005-04-16 22:20:36 +00:00
|
|
|
{
|
|
|
|
|
swp_entry_t entry;
|
|
|
|
|
entry.val = 0;
|
|
|
|
|
return entry;
|
|
|
|
|
}
|
|
|
|
|
|
2022-09-02 19:46:06 +00:00
|
|
|
static inline bool folio_free_swap(struct folio *folio)
|
|
|
|
|
{
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
|
2022-05-10 01:20:48 +00:00
|
|
|
static inline int add_swap_extent(struct swap_info_struct *sis,
|
|
|
|
|
unsigned long start_page,
|
|
|
|
|
unsigned long nr_pages, sector_t start_block)
|
|
|
|
|
{
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
}
|
2005-04-16 22:20:36 +00:00
|
|
|
#endif /* CONFIG_SWAP */
|
2016-01-20 23:03:05 +00:00
|
|
|
|
2017-09-06 23:22:34 +00:00
|
|
|
#ifdef CONFIG_THP_SWAP
|
|
|
|
|
extern int split_swap_cluster(swp_entry_t entry);
|
|
|
|
|
#else
|
|
|
|
|
static inline int split_swap_cluster(swp_entry_t entry)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
2016-01-20 23:03:05 +00:00
|
|
|
#ifdef CONFIG_MEMCG
|
|
|
|
|
static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
|
|
|
|
|
{
|
2016-05-05 23:22:03 +00:00
|
|
|
/* Cgroup2 doesn't have per-cgroup swappiness */
|
|
|
|
|
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
|
2023-03-06 15:41:36 +00:00
|
|
|
return READ_ONCE(vm_swappiness);
|
2016-05-05 23:22:03 +00:00
|
|
|
|
2016-01-20 23:03:05 +00:00
|
|
|
/* root ? */
|
2019-03-05 23:48:02 +00:00
|
|
|
if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg))
|
2023-03-06 15:41:36 +00:00
|
|
|
return READ_ONCE(vm_swappiness);
|
2016-01-20 23:03:05 +00:00
|
|
|
|
2023-03-06 15:41:36 +00:00
|
|
|
return READ_ONCE(memcg->swappiness);
|
2016-01-20 23:03:05 +00:00
|
|
|
}
|
|
|
|
|
#else
|
|
|
|
|
static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
|
|
|
|
|
{
|
2023-03-06 15:41:36 +00:00
|
|
|
return READ_ONCE(vm_swappiness);
|
2016-01-20 23:03:05 +00:00
|
|
|
}
|
|
|
|
|
#endif
|
|
|
|
|
|
2018-07-03 15:14:56 +00:00
|
|
|
#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
|
2023-03-02 11:58:35 +00:00
|
|
|
void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp);
|
|
|
|
|
static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
|
2021-09-02 21:54:54 +00:00
|
|
|
{
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
|
return;
|
2023-03-02 11:58:35 +00:00
|
|
|
__folio_throttle_swaprate(folio, gfp);
|
2021-09-02 21:54:54 +00:00
|
|
|
}
|
2018-07-03 15:14:56 +00:00
|
|
|
#else
|
2022-05-13 03:23:04 +00:00
|
|
|
static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp)
|
|
|
|
|
{
|
|
|
|
|
}
|
2023-03-02 11:58:35 +00:00
|
|
|
#endif
|
2018-07-03 15:14:56 +00:00
|
|
|
|
2022-09-26 13:57:04 +00:00
|
|
|
#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP)
|
2021-12-28 02:11:34 +00:00
|
|
|
void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry);
|
2022-05-13 03:23:02 +00:00
|
|
|
int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry);
|
|
|
|
|
static inline int mem_cgroup_try_charge_swap(struct folio *folio,
|
|
|
|
|
swp_entry_t entry)
|
2021-09-02 21:54:54 +00:00
|
|
|
{
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
|
return 0;
|
2022-05-13 03:23:02 +00:00
|
|
|
return __mem_cgroup_try_charge_swap(folio, entry);
|
2021-09-02 21:54:54 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
|
|
|
|
|
static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages)
|
|
|
|
|
{
|
|
|
|
|
if (mem_cgroup_disabled())
|
|
|
|
|
return;
|
|
|
|
|
__mem_cgroup_uncharge_swap(entry, nr_pages);
|
|
|
|
|
}
|
|
|
|
|
|
2016-01-20 23:03:07 +00:00
|
|
|
extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
|
2022-09-02 19:46:43 +00:00
|
|
|
extern bool mem_cgroup_swap_full(struct folio *folio);
|
2016-01-20 23:03:05 +00:00
|
|
|
#else
|
2021-12-28 02:11:34 +00:00
|
|
|
static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
|
2016-01-20 23:03:05 +00:00
|
|
|
{
|
|
|
|
|
}
|
|
|
|
|
|
2022-05-13 03:23:02 +00:00
|
|
|
static inline int mem_cgroup_try_charge_swap(struct folio *folio,
|
2016-01-20 23:03:05 +00:00
|
|
|
swp_entry_t entry)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
mm, THP, swap: delay splitting THP during swap out
Patch series "THP swap: Delay splitting THP during swapping out", v11.
This patchset is to optimize the performance of Transparent Huge Page
(THP) swap.
Recently, the performance of the storage devices improved so fast that
we cannot saturate the disk bandwidth with single logical CPU when do
page swap out even on a high-end server machine. Because the
performance of the storage device improved faster than that of single
logical CPU. And it seems that the trend will not change in the near
future. On the other hand, the THP becomes more and more popular
because of increased memory size. So it becomes necessary to optimize
THP swap performance.
The advantages of the THP swap support include:
- Batch the swap operations for the THP to reduce lock
acquiring/releasing, including allocating/freeing the swap space,
adding/deleting to/from the swap cache, and writing/reading the swap
space, etc. This will help improve the performance of the THP swap.
- The THP swap space read/write will be 2M sequential IO. It is
particularly helpful for the swap read, which are usually 4k random
IO. This will improve the performance of the THP swap too.
- It will help the memory fragmentation, especially when the THP is
heavily used by the applications. The 2M continuous pages will be
free up after THP swapping out.
- It will improve the THP utilization on the system with the swap
turned on. Because the speed for khugepaged to collapse the normal
pages into the THP is quite slow. After the THP is split during the
swapping out, it will take quite long time for the normal pages to
collapse back into the THP after being swapped in. The high THP
utilization helps the efficiency of the page based memory management
too.
There are some concerns regarding THP swap in, mainly because possible
enlarged read/write IO size (for swap in/out) may put more overhead on
the storage device. To deal with that, the THP swap in should be turned
on only when necessary. For example, it can be selected via
"always/never/madvise" logic, to be turned on globally, turned off
globally, or turned on only for VMA with MADV_HUGEPAGE, etc.
This patchset is the first step for the THP swap support. The plan is
to delay splitting THP step by step, finally avoid splitting THP during
the THP swapping out and swap out/in the THP as a whole.
As the first step, in this patchset, the splitting huge page is delayed
from almost the first step of swapping out to after allocating the swap
space for the THP and adding the THP into the swap cache. This will
reduce lock acquiring/releasing for the locks used for the swap cache
management.
With the patchset, the swap out throughput improves 15.5% (from about
3.73GB/s to about 4.31GB/s) in the vm-scalability swap-w-seq test case
with 8 processes. The test is done on a Xeon E5 v3 system. The swap
device used is a RAM simulated PMEM (persistent memory) device. To test
the sequential swapping out, the test case creates 8 processes, which
sequentially allocate and write to the anonymous pages until the RAM and
part of the swap device is used up.
This patch (of 5):
In this patch, splitting huge page is delayed from almost the first step
of swapping out to after allocating the swap space for the THP
(Transparent Huge Page) and adding the THP into the swap cache. This
will batch the corresponding operation, thus improve THP swap out
throughput.
This is the first step for the THP swap optimization. The plan is to
delay splitting the THP step by step and avoid splitting the THP
finally.
In this patch, one swap cluster is used to hold the contents of each THP
swapped out. So, the size of the swap cluster is changed to that of the
THP (Transparent Huge Page) on x86_64 architecture (512). For other
architectures which want such THP swap optimization,
ARCH_USES_THP_SWAP_CLUSTER needs to be selected in the Kconfig file for
the architecture. In effect, this will enlarge swap cluster size by 2
times on x86_64. Which may make it harder to find a free cluster when
the swap space becomes fragmented. So that, this may reduce the
continuous swap space allocation and sequential write in theory. The
performance test in 0day shows no regressions caused by this.
In the future of THP swap optimization, some information of the swapped
out THP (such as compound map count) will be recorded in the
swap_cluster_info data structure.
The mem cgroup swap accounting functions are enhanced to support charge
or uncharge a swap cluster backing a THP as a whole.
The swap cluster allocate/free functions are added to allocate/free a
swap cluster for a THP. A fair simple algorithm is used for swap
cluster allocation, that is, only the first swap device in priority list
will be tried to allocate the swap cluster. The function will fail if
the trying is not successful, and the caller will fallback to allocate a
single swap slot instead. This works good enough for normal cases. If
the difference of the number of the free swap clusters among multiple
swap devices is significant, it is possible that some THPs are split
earlier than necessary. For example, this could be caused by big size
difference among multiple swap devices.
The swap cache functions is enhanced to support add/delete THP to/from
the swap cache as a set of (HPAGE_PMD_NR) sub-pages. This may be
enhanced in the future with multi-order radix tree. But because we will
split the THP soon during swapping out, that optimization doesn't make
much sense for this first step.
The THP splitting functions are enhanced to support to split THP in swap
cache during swapping out. The page lock will be held during allocating
the swap cluster, adding the THP into the swap cache and splitting the
THP. So in the code path other than swapping out, if the THP need to be
split, the PageSwapCache(THP) will be always false.
The swap cluster is only available for SSD, so the THP swap optimization
in this patchset has no effect for HDD.
[ying.huang@intel.com: fix two issues in THP optimize patch]
Link: http://lkml.kernel.org/r/87k25ed8zo.fsf@yhuang-dev.intel.com
[hannes@cmpxchg.org: extensive cleanups and simplifications, reduce code size]
Link: http://lkml.kernel.org/r/20170515112522.32457-2-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Suggested-by: Andrew Morton <akpm@linux-foundation.org> [for config option]
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> [for changes in huge_memory.c and huge_mm.h]
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-06 22:37:18 +00:00
|
|
|
static inline void mem_cgroup_uncharge_swap(swp_entry_t entry,
|
|
|
|
|
unsigned int nr_pages)
|
2016-01-20 23:03:05 +00:00
|
|
|
{
|
|
|
|
|
}
|
2016-01-20 23:03:07 +00:00
|
|
|
|
|
|
|
|
static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
|
|
|
|
|
{
|
|
|
|
|
return get_nr_swap_pages();
|
|
|
|
|
}
|
2016-01-20 23:03:10 +00:00
|
|
|
|
2022-09-02 19:46:43 +00:00
|
|
|
static inline bool mem_cgroup_swap_full(struct folio *folio)
|
2016-01-20 23:03:10 +00:00
|
|
|
{
|
|
|
|
|
return vm_swap_full();
|
|
|
|
|
}
|
2016-01-20 23:03:05 +00:00
|
|
|
#endif
|
|
|
|
|
|
2005-04-16 22:20:36 +00:00
|
|
|
#endif /* __KERNEL__*/
|
|
|
|
|
#endif /* _LINUX_SWAP_H */
|