2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Macros for manipulating and testing page->flags
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef PAGE_FLAGS_H
|
|
|
|
#define PAGE_FLAGS_H
|
|
|
|
|
2006-06-23 17:03:06 +08:00
|
|
|
#include <linux/types.h>
|
2011-11-24 09:12:59 +08:00
|
|
|
#include <linux/bug.h>
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:43:58 +08:00
|
|
|
#include <linux/mmdebug.h>
|
2008-04-28 17:12:48 +08:00
|
|
|
#ifndef __GENERATING_BOUNDS_H
|
2007-05-07 05:49:40 +08:00
|
|
|
#include <linux/mm_types.h>
|
2009-04-20 03:57:19 +08:00
|
|
|
#include <generated/bounds.h>
|
2008-04-28 17:12:48 +08:00
|
|
|
#endif /* !__GENERATING_BOUNDS_H */
|
2006-06-23 17:03:06 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* Various page->flags bits:
|
|
|
|
*
|
|
|
|
* PG_reserved is set for special pages, which can never be swapped out. Some
|
|
|
|
* of them might not even exist (eg empty_bad_page)...
|
|
|
|
*
|
2006-09-26 14:31:35 +08:00
|
|
|
* The PG_private bitflag is set on pagecache pages if they contain filesystem
|
|
|
|
* specific data (which is normally at page->private). It can be used by
|
|
|
|
* private allocations for its own usage.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
2006-09-26 14:31:35 +08:00
|
|
|
* During initiation of disk I/O, PG_locked is set. This bit is set before I/O
|
|
|
|
* and cleared when writeback _starts_ or when read _completes_. PG_writeback
|
|
|
|
* is set before writeback starts and cleared when it finishes.
|
|
|
|
*
|
|
|
|
* PG_locked also pins a page in pagecache, and blocks truncation of the file
|
|
|
|
* while it is held.
|
|
|
|
*
|
|
|
|
* page_waitqueue(page) is a wait queue of all tasks waiting for the page
|
|
|
|
* to become unlocked.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* PG_uptodate tells whether the page's contents is valid. When a read
|
|
|
|
* completes, the page becomes uptodate, unless a disk I/O error happened.
|
|
|
|
*
|
2006-09-26 14:31:35 +08:00
|
|
|
* PG_referenced, PG_reclaim are used for page reclaim for anonymous and
|
|
|
|
* file-backed pagecache (see mm/vmscan.c).
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* PG_error is set to indicate that an I/O error occurred on this page.
|
|
|
|
*
|
|
|
|
* PG_arch_1 is an architecture specific page state bit. The generic code
|
|
|
|
* guarantees that this bit is cleared for a page when it first is entered into
|
|
|
|
* the page cache.
|
|
|
|
*
|
|
|
|
* PG_highmem pages are not permanently mapped into the kernel virtual address
|
|
|
|
* space, they need to be kmapped separately for doing IO on the pages. The
|
|
|
|
* struct page (these bits with information) are always mapped into kernel
|
|
|
|
* address space...
|
2006-09-26 14:31:35 +08:00
|
|
|
*
|
2009-09-16 17:50:03 +08:00
|
|
|
* PG_hwpoison indicates that a page got corrupted in hardware and contains
|
|
|
|
* data with incorrect ECC bits that triggered a machine check. Accessing is
|
|
|
|
* not safe since it may cause another machine check. Don't touch!
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Don't use the *_dontuse flags. Use the macros. Otherwise you'll break
|
2006-04-11 13:53:01 +08:00
|
|
|
* locked- and dirty-page accounting.
|
|
|
|
*
|
|
|
|
* The page flags field is split into two parts, the main flags area
|
|
|
|
* which extends from the low bits upwards, and the fields area which
|
|
|
|
* extends from the high bits downwards.
|
|
|
|
*
|
|
|
|
* | FIELD | ... | FLAGS |
|
2008-04-28 17:12:48 +08:00
|
|
|
* N-1 ^ 0
|
|
|
|
* (NR_PAGEFLAGS)
|
2006-04-11 13:53:01 +08:00
|
|
|
*
|
2008-04-28 17:12:48 +08:00
|
|
|
* The fields area is reserved for fields mapping zone, node (for NUMA) and
|
|
|
|
* SPARSEMEM section (for variants of SPARSEMEM that require section ids like
|
|
|
|
* SPARSEMEM_EXTREME with !SPARSEMEM_VMEMMAP).
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
2008-04-28 17:12:47 +08:00
|
|
|
enum pageflags {
|
|
|
|
PG_locked, /* Page is locked. Don't touch. */
|
|
|
|
PG_error,
|
|
|
|
PG_referenced,
|
|
|
|
PG_uptodate,
|
|
|
|
PG_dirty,
|
|
|
|
PG_lru,
|
|
|
|
PG_active,
|
|
|
|
PG_slab,
|
|
|
|
PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/
|
|
|
|
PG_arch_1,
|
|
|
|
PG_reserved,
|
|
|
|
PG_private, /* If pagecache, has fs-private data */
|
2009-04-03 23:42:36 +08:00
|
|
|
PG_private_2, /* If pagecache, has fs aux data */
|
2008-04-28 17:12:47 +08:00
|
|
|
PG_writeback, /* Page is under writeback */
|
2008-04-28 17:12:55 +08:00
|
|
|
PG_head, /* A head page */
|
2008-04-28 17:12:47 +08:00
|
|
|
PG_swapcache, /* Swap page: swp_entry_t in private */
|
|
|
|
PG_mappedtodisk, /* Has blocks allocated on-disk */
|
|
|
|
PG_reclaim, /* To be reclaimed asap */
|
2008-10-19 11:26:30 +08:00
|
|
|
PG_swapbacked, /* Page is backed by RAM/swap */
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
|
|
|
PG_unevictable, /* Page is "unevictable" */
|
2009-12-15 09:58:59 +08:00
|
|
|
#ifdef CONFIG_MMU
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
|
|
|
PG_mlocked, /* Page is vma mlocked */
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
|
|
|
#endif
|
2009-07-11 00:57:37 +08:00
|
|
|
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
|
2008-04-28 17:12:52 +08:00
|
|
|
PG_uncached, /* Page has been mapped as uncached */
|
2009-09-16 17:50:03 +08:00
|
|
|
#endif
|
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
|
|
|
PG_hwpoison, /* hardware poisoned page. Don't touch */
|
2011-01-14 07:46:32 +08:00
|
|
|
#endif
|
mm: introduce idle page tracking
Knowing the portion of memory that is not used by a certain application or
memory cgroup (idle memory) can be useful for partitioning the system
efficiently, e.g. by setting memory cgroup limits appropriately.
Currently, the only means to estimate the amount of idle memory provided
by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the
access bit for all pages mapped to a particular process by writing 1 to
clear_refs, wait for some time, and then count smaps:Referenced. However,
this method has two serious shortcomings:
- it does not count unmapped file pages
- it affects the reclaimer logic
To overcome these drawbacks, this patch introduces two new page flags,
Idle and Young, and a new sysfs file, /sys/kernel/mm/page_idle/bitmap.
A page's Idle flag can only be set from userspace by setting bit in
/sys/kernel/mm/page_idle/bitmap at the offset corresponding to the page,
and it is cleared whenever the page is accessed either through page tables
(it is cleared in page_referenced() in this case) or using the read(2)
system call (mark_page_accessed()). Thus by setting the Idle flag for
pages of a particular workload, which can be found e.g. by reading
/proc/PID/pagemap, waiting for some time to let the workload access its
working set, and then reading the bitmap file, one can estimate the amount
of pages that are not used by the workload.
The Young page flag is used to avoid interference with the memory
reclaimer. A page's Young flag is set whenever the Access bit of a page
table entry pointing to the page is cleared by writing to the bitmap file.
If page_referenced() is called on a Young page, it will add 1 to its
return value, therefore concealing the fact that the Access bit was
cleared.
Note, since there is no room for extra page flags on 32 bit, this feature
uses extended page flags when compiled on 32 bit.
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: kpageidle requires an MMU]
[akpm@linux-foundation.org: decouple from page-flags rework]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-10 06:35:45 +08:00
|
|
|
#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
|
|
|
|
PG_young,
|
|
|
|
PG_idle,
|
2006-06-23 17:03:06 +08:00
|
|
|
#endif
|
2008-07-24 12:27:16 +08:00
|
|
|
__NR_PAGEFLAGS,
|
|
|
|
|
|
|
|
/* Filesystems */
|
|
|
|
PG_checked = PG_owner_priv_1,
|
|
|
|
|
2009-04-03 23:42:36 +08:00
|
|
|
/* Two page bits are conscripted by FS-Cache to maintain local caching
|
|
|
|
* state. These bits are set on pages belonging to the netfs's inodes
|
|
|
|
* when those inodes are being locally cached.
|
|
|
|
*/
|
|
|
|
PG_fscache = PG_private_2, /* page backed by cache */
|
|
|
|
|
2008-07-24 12:27:16 +08:00
|
|
|
/* XEN */
|
2015-01-05 21:24:09 +08:00
|
|
|
/* Pinned in Xen as a read-only pagetable page. */
|
2008-07-24 12:27:16 +08:00
|
|
|
PG_pinned = PG_owner_priv_1,
|
2015-01-05 21:24:09 +08:00
|
|
|
/* Pinned as part of domain save (see xen_mm_pin_all()). */
|
2008-07-24 12:27:16 +08:00
|
|
|
PG_savepinned = PG_dirty,
|
2015-01-05 21:24:09 +08:00
|
|
|
/* Has a grant mapping of another (foreign) domain's page. */
|
|
|
|
PG_foreign = PG_owner_priv_1,
|
2008-07-24 12:27:18 +08:00
|
|
|
|
2008-07-24 12:27:19 +08:00
|
|
|
/* SLOB */
|
|
|
|
PG_slob_free = PG_private,
|
2016-01-16 08:53:42 +08:00
|
|
|
|
|
|
|
/* Compound pages. Stored in first tail page's flags */
|
|
|
|
PG_double_map = PG_private_2,
|
2008-04-28 17:12:47 +08:00
|
|
|
};
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-04-28 17:12:48 +08:00
|
|
|
#ifndef __GENERATING_BOUNDS_H
|
|
|
|
|
2016-01-16 08:51:17 +08:00
|
|
|
struct page; /* forward declaration */
|
|
|
|
|
|
|
|
static inline struct page *compound_head(struct page *page)
|
|
|
|
{
|
|
|
|
unsigned long head = READ_ONCE(page->compound_head);
|
|
|
|
|
|
|
|
if (unlikely(head & 1))
|
|
|
|
return (struct page *) (head - 1);
|
|
|
|
return page;
|
|
|
|
}
|
|
|
|
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline int PageTail(struct page *page)
|
2016-01-16 08:51:17 +08:00
|
|
|
{
|
|
|
|
return READ_ONCE(page->compound_head) & 1;
|
|
|
|
}
|
|
|
|
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline int PageCompound(struct page *page)
|
2016-01-16 08:51:17 +08:00
|
|
|
{
|
|
|
|
return test_bit(PG_head, &page->flags) || PageTail(page);
|
|
|
|
}
|
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
/*
|
|
|
|
* Page flags policies wrt compound pages
|
|
|
|
*
|
|
|
|
* PF_ANY:
|
|
|
|
* the page flag is relevant for small, head and tail pages.
|
|
|
|
*
|
|
|
|
* PF_HEAD:
|
|
|
|
* for compound page all operations related to the page flag applied to
|
|
|
|
* head page.
|
|
|
|
*
|
|
|
|
* PF_NO_TAIL:
|
|
|
|
* modifications of the page flag must be done on small or head pages,
|
|
|
|
* checks can be done on tail pages too.
|
|
|
|
*
|
|
|
|
* PF_NO_COMPOUND:
|
|
|
|
* the page flag is not relevant for compound pages.
|
|
|
|
*/
|
|
|
|
#define PF_ANY(page, enforce) page
|
|
|
|
#define PF_HEAD(page, enforce) compound_head(page)
|
|
|
|
#define PF_NO_TAIL(page, enforce) ({ \
|
|
|
|
VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page); \
|
|
|
|
compound_head(page);})
|
2016-01-16 08:52:03 +08:00
|
|
|
#define PF_NO_COMPOUND(page, enforce) ({ \
|
2016-01-16 08:51:21 +08:00
|
|
|
VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page); \
|
|
|
|
page;})
|
|
|
|
|
2008-04-28 17:12:49 +08:00
|
|
|
/*
|
|
|
|
* Macros to create function definitions for page flags
|
|
|
|
*/
|
2016-01-16 08:51:21 +08:00
|
|
|
#define TESTPAGEFLAG(uname, lname, policy) \
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline int Page##uname(struct page *page) \
|
2016-01-16 08:51:21 +08:00
|
|
|
{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define SETPAGEFLAG(uname, lname, policy) \
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void SetPage##uname(struct page *page) \
|
2016-01-16 08:51:21 +08:00
|
|
|
{ set_bit(PG_##lname, &policy(page, 1)->flags); }
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define CLEARPAGEFLAG(uname, lname, policy) \
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void ClearPage##uname(struct page *page) \
|
2016-01-16 08:51:21 +08:00
|
|
|
{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define __SETPAGEFLAG(uname, lname, policy) \
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void __SetPage##uname(struct page *page) \
|
2016-01-16 08:51:21 +08:00
|
|
|
{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define __CLEARPAGEFLAG(uname, lname, policy) \
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void __ClearPage##uname(struct page *page) \
|
2016-01-16 08:51:21 +08:00
|
|
|
{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define TESTSETFLAG(uname, lname, policy) \
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline int TestSetPage##uname(struct page *page) \
|
2016-01-16 08:51:21 +08:00
|
|
|
{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define TESTCLEARFLAG(uname, lname, policy) \
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline int TestClearPage##uname(struct page *page) \
|
2016-01-16 08:51:21 +08:00
|
|
|
{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define PAGEFLAG(uname, lname, policy) \
|
|
|
|
TESTPAGEFLAG(uname, lname, policy) \
|
|
|
|
SETPAGEFLAG(uname, lname, policy) \
|
|
|
|
CLEARPAGEFLAG(uname, lname, policy)
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define __PAGEFLAG(uname, lname, policy) \
|
|
|
|
TESTPAGEFLAG(uname, lname, policy) \
|
|
|
|
__SETPAGEFLAG(uname, lname, policy) \
|
|
|
|
__CLEARPAGEFLAG(uname, lname, policy)
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#define TESTSCFLAG(uname, lname, policy) \
|
|
|
|
TESTSETFLAG(uname, lname, policy) \
|
|
|
|
TESTCLEARFLAG(uname, lname, policy)
|
2008-04-28 17:12:49 +08:00
|
|
|
|
2014-08-07 07:05:40 +08:00
|
|
|
#define TESTPAGEFLAG_FALSE(uname) \
|
|
|
|
static inline int Page##uname(const struct page *page) { return 0; }
|
|
|
|
|
2008-10-19 11:26:37 +08:00
|
|
|
#define SETPAGEFLAG_NOOP(uname) \
|
|
|
|
static inline void SetPage##uname(struct page *page) { }
|
|
|
|
|
|
|
|
#define CLEARPAGEFLAG_NOOP(uname) \
|
|
|
|
static inline void ClearPage##uname(struct page *page) { }
|
|
|
|
|
|
|
|
#define __CLEARPAGEFLAG_NOOP(uname) \
|
|
|
|
static inline void __ClearPage##uname(struct page *page) { }
|
|
|
|
|
2014-08-07 07:05:40 +08:00
|
|
|
#define TESTSETFLAG_FALSE(uname) \
|
|
|
|
static inline int TestSetPage##uname(struct page *page) { return 0; }
|
|
|
|
|
2008-10-19 11:26:37 +08:00
|
|
|
#define TESTCLEARFLAG_FALSE(uname) \
|
|
|
|
static inline int TestClearPage##uname(struct page *page) { return 0; }
|
|
|
|
|
2014-08-07 07:05:40 +08:00
|
|
|
#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \
|
|
|
|
SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname)
|
|
|
|
|
|
|
|
#define TESTSCFLAG_FALSE(uname) \
|
|
|
|
TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
|
|
|
|
|
2016-01-16 08:51:24 +08:00
|
|
|
__PAGEFLAG(Locked, locked, PF_NO_TAIL)
|
2016-01-16 08:51:28 +08:00
|
|
|
PAGEFLAG(Error, error, PF_NO_COMPOUND) TESTCLEARFLAG(Error, error, PF_NO_COMPOUND)
|
2016-01-16 08:51:32 +08:00
|
|
|
PAGEFLAG(Referenced, referenced, PF_HEAD)
|
|
|
|
TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
|
|
|
|
__SETPAGEFLAG(Referenced, referenced, PF_HEAD)
|
2016-01-16 08:51:28 +08:00
|
|
|
PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
|
|
|
|
__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
|
2016-01-16 08:51:32 +08:00
|
|
|
PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
|
|
|
|
PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
|
|
|
|
TESTCLEARFLAG(Active, active, PF_HEAD)
|
2016-01-16 08:51:35 +08:00
|
|
|
__PAGEFLAG(Slab, slab, PF_NO_TAIL)
|
|
|
|
__PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL)
|
2016-01-16 08:51:28 +08:00
|
|
|
PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */
|
2016-01-16 08:51:39 +08:00
|
|
|
|
|
|
|
/* Xen */
|
|
|
|
PAGEFLAG(Pinned, pinned, PF_NO_COMPOUND)
|
|
|
|
TESTSCFLAG(Pinned, pinned, PF_NO_COMPOUND)
|
|
|
|
PAGEFLAG(SavePinned, savepinned, PF_NO_COMPOUND);
|
|
|
|
PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND);
|
|
|
|
|
2016-01-16 08:51:42 +08:00
|
|
|
PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
|
|
|
|
__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
|
2016-01-16 08:51:46 +08:00
|
|
|
PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
|
|
|
|
__CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
|
|
|
|
__SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
|
2016-01-16 08:51:21 +08:00
|
|
|
|
2009-04-03 23:42:36 +08:00
|
|
|
/*
|
|
|
|
* Private page markings that may be used by the filesystem that owns the page
|
|
|
|
* for its own purposes.
|
|
|
|
* - PG_private and PG_private_2 cause releasepage() and co to be invoked
|
|
|
|
*/
|
2016-01-16 08:51:21 +08:00
|
|
|
PAGEFLAG(Private, private, PF_ANY) __SETPAGEFLAG(Private, private, PF_ANY)
|
|
|
|
__CLEARPAGEFLAG(Private, private, PF_ANY)
|
|
|
|
PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
|
|
|
|
PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
|
|
|
|
TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
|
2009-04-03 23:42:36 +08:00
|
|
|
|
2008-04-28 17:12:50 +08:00
|
|
|
/*
|
|
|
|
* Only test-and-set exist for PG_writeback. The unconditional operators are
|
|
|
|
* risky: they bypass page accounting.
|
|
|
|
*/
|
2016-01-16 08:51:28 +08:00
|
|
|
TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND)
|
|
|
|
TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND)
|
|
|
|
PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_COMPOUND)
|
2008-04-28 17:12:50 +08:00
|
|
|
|
swap: add a simple detector for inappropriate swapin readahead
This is a patch to improve swap readahead algorithm. It's from Hugh and
I slightly changed it.
Hugh's original changelog:
swapin readahead does a blind readahead, whether or not the swapin is
sequential. This may be ok on harddisk, because large reads have
relatively small costs, and if the readahead pages are unneeded they can
be reclaimed easily - though, what if their allocation forced reclaim of
useful pages? But on SSD devices large reads are more expensive than
small ones: if the readahead pages are unneeded, reading them in caused
significant overhead.
This patch adds very simplistic random read detection. Stealing the
PageReadahead technique from Konstantin Khlebnikov's patch, avoiding the
vma/anon_vma sophistications of Shaohua Li's patch, swapin_nr_pages()
simply looks at readahead's current success rate, and narrows or widens
its readahead window accordingly. There is little science to its
heuristic: it's about as stupid as can be whilst remaining effective.
The table below shows elapsed times (in centiseconds) when running a
single repetitive swapping load across a 1000MB mapping in 900MB ram
with 1GB swap (the harddisk tests had taken painfully too long when I
used mem=500M, but SSD shows similar results for that).
Vanilla is the 3.6-rc7 kernel on which I started; Shaohua denotes his
Sep 3 patch in mmotm and linux-next; HughOld denotes my Oct 1 patch
which Shaohua showed to be defective; HughNew this Nov 14 patch, with
page_cluster as usual at default of 3 (8-page reads); HughPC4 this same
patch with page_cluster 4 (16-page reads); HughPC0 with page_cluster 0
(1-page reads: no readahead).
HDD for swapping to harddisk, SSD for swapping to VertexII SSD. Seq for
sequential access to the mapping, cycling five times around; Rand for
the same number of random touches. Anon for a MAP_PRIVATE anon mapping;
Shmem for a MAP_SHARED anon mapping, equivalent to tmpfs.
One weakness of Shaohua's vma/anon_vma approach was that it did not
optimize Shmem: seen below. Konstantin's approach was perhaps mistuned,
50% slower on Seq: did not compete and is not shown below.
HDD Vanilla Shaohua HughOld HughNew HughPC4 HughPC0
Seq Anon 73921 76210 75611 76904 78191 121542
Seq Shmem 73601 73176 73855 72947 74543 118322
Rand Anon 895392 831243 871569 845197 846496 841680
Rand Shmem 1058375 1053486 827935 764955 764376 756489
SSD Vanilla Shaohua HughOld HughNew HughPC4 HughPC0
Seq Anon 24634 24198 24673 25107 21614 70018
Seq Shmem 24959 24932 25052 25703 22030 69678
Rand Anon 43014 26146 28075 25989 26935 25901
Rand Shmem 45349 45215 28249 24268 24138 24332
These tests are, of course, two extremes of a very simple case: under
heavier mixed loads I've not yet observed any consistent improvement or
degradation, and wider testing would be welcome.
Shaohua Li:
Test shows Vanilla is slightly better in sequential workload than Hugh's
patch. I observed with Hugh's patch sometimes the readahead size is
shrinked too fast (from 8 to 1 immediately) in sequential workload if
there is no hit. And in such case, continuing doing readahead is good
actually.
I don't prepare a sophisticated algorithm for the sequential workload
because so far we can't guarantee sequential accessed pages are swap out
sequentially. So I slightly change Hugh's heuristic - don't shrink
readahead size too fast.
Here is my test result (unit second, 3 runs average):
Vanilla Hugh New
Seq 356 370 360
Random 4525 2447 2444
Attached graph is the swapin/swapout throughput I collected with 'vmstat
2'. The first part is running a random workload (till around 1200 of
the x-axis) and the second part is running a sequential workload.
swapin and swapout throughput are almost identical in steady state in
both workloads. These are expected behavior. while in Vanilla, swapin
is much bigger than swapout especially in random workload (because wrong
readahead).
Original patches by: Shaohua Li and Konstantin Khlebnikov.
[fengguang.wu@intel.com: swapin_nr_pages() can be static]
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-02-07 04:04:21 +08:00
|
|
|
/* PG_readahead is only used for reads; PG_reclaim is only for writes */
|
2016-01-16 08:51:28 +08:00
|
|
|
PAGEFLAG(Reclaim, reclaim, PF_NO_COMPOUND)
|
|
|
|
TESTCLEARFLAG(Reclaim, reclaim, PF_NO_COMPOUND)
|
|
|
|
PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
|
|
|
|
TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND)
|
2008-04-28 17:12:50 +08:00
|
|
|
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2008-04-28 17:12:50 +08:00
|
|
|
* Must use a macro here due to header dependency issues. page_zone() is not
|
|
|
|
* available at this point.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
mm: optimize PageHighMem() check
This came up when implementing HIHGMEM/PAE40 for ARC. The kmap() /
kmap_atomic() generated code seemed needlessly bloated due to the way
PageHighMem() macro is implemented. It derives the exact zone for page
and then does pointer subtraction with first zone to infer the zone_type.
The pointer arithmatic in turn generates the code bloat.
PageHighMem(page)
is_highmem(page_zone(page))
zone_off = (char *)zone - (char *)zone->zone_pgdat->node_zones
Instead use is_highmem_idx() to work on zone_type available in page flags
----- Before -----
80756348: mov_s r13,r0
8075634a: ld_s r2,[r13,0]
8075634c: lsr_s r2,r2,30
8075634e: mpy r2,r2,0x2a4
80756352: add_s r2,r2,0x80aef880
80756358: ld_s r3,[r2,28]
8075635a: sub_s r2,r2,r3
8075635c: breq r2,0x2a4,80756378 <kmap+0x48>
80756364: breq r2,0x548,80756378 <kmap+0x48>
----- After -----
80756330: mov_s r13,r0
80756332: ld_s r2,[r13,0]
80756334: lsr_s r2,r2,30
80756336: sub_s r2,r2,1
80756338: brlo r2,2,80756348 <kmap+0x30>
For x86 defconfig build (32 bit only) it saves around 900 bytes.
For ARC defconfig with HIGHMEM, it saved around 2K bytes.
---->8-------
./scripts/bloat-o-meter x86/vmlinux-defconfig-pre x86/vmlinux-defconfig-post
add/remove: 0/0 grow/shrink: 0/36 up/down: 0/-934 (-934)
function old new delta
saveable_page 162 154 -8
saveable_highmem_page 154 146 -8
skb_gro_reset_offset 147 131 -16
...
...
__change_page_attr_set_clr 1715 1678 -37
setup_data_read 434 394 -40
mon_bin_event 1967 1927 -40
swsusp_save 1148 1105 -43
_set_pages_array 549 493 -56
---->8-------
e.g. For ARC kmap()
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Jennifer Herbert <jennifer.herbert@citrix.com>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-11-06 10:48:29 +08:00
|
|
|
#define PageHighMem(__p) is_highmem_idx(page_zonenum(__p))
|
2008-04-28 17:12:50 +08:00
|
|
|
#else
|
2008-04-28 17:12:53 +08:00
|
|
|
PAGEFLAG_FALSE(HighMem)
|
2008-04-28 17:12:50 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef CONFIG_SWAP
|
2016-01-16 08:51:49 +08:00
|
|
|
PAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
|
2008-04-28 17:12:50 +08:00
|
|
|
#else
|
2008-04-28 17:12:53 +08:00
|
|
|
PAGEFLAG_FALSE(SwapCache)
|
2008-04-28 17:12:50 +08:00
|
|
|
#endif
|
|
|
|
|
2016-01-16 08:51:32 +08:00
|
|
|
PAGEFLAG(Unevictable, unevictable, PF_HEAD)
|
|
|
|
__CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD)
|
|
|
|
TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD)
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
|
|
|
|
2009-12-15 09:58:59 +08:00
|
|
|
#ifdef CONFIG_MMU
|
2016-01-16 08:51:53 +08:00
|
|
|
PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
|
|
|
|
__CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
|
|
|
|
TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL)
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
|
|
|
#else
|
2014-08-07 07:05:40 +08:00
|
|
|
PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
|
2016-01-16 08:52:10 +08:00
|
|
|
TESTSCFLAG_FALSE(Mlocked)
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
|
|
|
#endif
|
|
|
|
|
2009-07-11 00:57:37 +08:00
|
|
|
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
|
2016-01-16 08:51:56 +08:00
|
|
|
PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND)
|
2008-04-28 17:12:52 +08:00
|
|
|
#else
|
2008-04-28 17:12:53 +08:00
|
|
|
PAGEFLAG_FALSE(Uncached)
|
2008-04-28 17:12:50 +08:00
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-09-16 17:50:03 +08:00
|
|
|
#ifdef CONFIG_MEMORY_FAILURE
|
2016-01-16 08:51:21 +08:00
|
|
|
PAGEFLAG(HWPoison, hwpoison, PF_ANY)
|
|
|
|
TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
|
2009-09-16 17:50:03 +08:00
|
|
|
#define __PG_HWPOISON (1UL << PG_hwpoison)
|
|
|
|
#else
|
|
|
|
PAGEFLAG_FALSE(HWPoison)
|
|
|
|
#define __PG_HWPOISON 0
|
|
|
|
#endif
|
|
|
|
|
mm: introduce idle page tracking
Knowing the portion of memory that is not used by a certain application or
memory cgroup (idle memory) can be useful for partitioning the system
efficiently, e.g. by setting memory cgroup limits appropriately.
Currently, the only means to estimate the amount of idle memory provided
by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the
access bit for all pages mapped to a particular process by writing 1 to
clear_refs, wait for some time, and then count smaps:Referenced. However,
this method has two serious shortcomings:
- it does not count unmapped file pages
- it affects the reclaimer logic
To overcome these drawbacks, this patch introduces two new page flags,
Idle and Young, and a new sysfs file, /sys/kernel/mm/page_idle/bitmap.
A page's Idle flag can only be set from userspace by setting bit in
/sys/kernel/mm/page_idle/bitmap at the offset corresponding to the page,
and it is cleared whenever the page is accessed either through page tables
(it is cleared in page_referenced() in this case) or using the read(2)
system call (mark_page_accessed()). Thus by setting the Idle flag for
pages of a particular workload, which can be found e.g. by reading
/proc/PID/pagemap, waiting for some time to let the workload access its
working set, and then reading the bitmap file, one can estimate the amount
of pages that are not used by the workload.
The Young page flag is used to avoid interference with the memory
reclaimer. A page's Young flag is set whenever the Access bit of a page
table entry pointing to the page is cleared by writing to the bitmap file.
If page_referenced() is called on a Young page, it will add 1 to its
return value, therefore concealing the fact that the Access bit was
cleared.
Note, since there is no room for extra page flags on 32 bit, this feature
uses extended page flags when compiled on 32 bit.
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: kpageidle requires an MMU]
[akpm@linux-foundation.org: decouple from page-flags rework]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-10 06:35:45 +08:00
|
|
|
#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
|
2016-01-16 08:51:21 +08:00
|
|
|
TESTPAGEFLAG(Young, young, PF_ANY)
|
|
|
|
SETPAGEFLAG(Young, young, PF_ANY)
|
|
|
|
TESTCLEARFLAG(Young, young, PF_ANY)
|
|
|
|
PAGEFLAG(Idle, idle, PF_ANY)
|
mm: introduce idle page tracking
Knowing the portion of memory that is not used by a certain application or
memory cgroup (idle memory) can be useful for partitioning the system
efficiently, e.g. by setting memory cgroup limits appropriately.
Currently, the only means to estimate the amount of idle memory provided
by the kernel is /proc/PID/{clear_refs,smaps}: the user can clear the
access bit for all pages mapped to a particular process by writing 1 to
clear_refs, wait for some time, and then count smaps:Referenced. However,
this method has two serious shortcomings:
- it does not count unmapped file pages
- it affects the reclaimer logic
To overcome these drawbacks, this patch introduces two new page flags,
Idle and Young, and a new sysfs file, /sys/kernel/mm/page_idle/bitmap.
A page's Idle flag can only be set from userspace by setting bit in
/sys/kernel/mm/page_idle/bitmap at the offset corresponding to the page,
and it is cleared whenever the page is accessed either through page tables
(it is cleared in page_referenced() in this case) or using the read(2)
system call (mark_page_accessed()). Thus by setting the Idle flag for
pages of a particular workload, which can be found e.g. by reading
/proc/PID/pagemap, waiting for some time to let the workload access its
working set, and then reading the bitmap file, one can estimate the amount
of pages that are not used by the workload.
The Young page flag is used to avoid interference with the memory
reclaimer. A page's Young flag is set whenever the Access bit of a page
table entry pointing to the page is cleared by writing to the bitmap file.
If page_referenced() is called on a Young page, it will add 1 to its
return value, therefore concealing the fact that the Access bit was
cleared.
Note, since there is no room for extra page flags on 32 bit, this feature
uses extended page flags when compiled on 32 bit.
[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: kpageidle requires an MMU]
[akpm@linux-foundation.org: decouple from page-flags rework]
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Reviewed-by: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Greg Thelen <gthelen@google.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-10 06:35:45 +08:00
|
|
|
#endif
|
|
|
|
|
2015-04-16 07:13:08 +08:00
|
|
|
/*
|
|
|
|
* On an anonymous page mapped into a user virtual memory area,
|
|
|
|
* page->mapping points to its anon_vma, not to a struct address_space;
|
|
|
|
* with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h.
|
|
|
|
*
|
|
|
|
* On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
|
|
|
|
* the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
|
|
|
|
* and then page->mapping points, not to an anon_vma, but to a private
|
|
|
|
* structure which KSM associates with that merged page. See ksm.h.
|
|
|
|
*
|
|
|
|
* PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
|
|
|
|
*
|
|
|
|
* Please note that, confusingly, "page_mapping" refers to the inode
|
|
|
|
* address_space which maps the page from disk; whereas "page_mapped"
|
|
|
|
* refers to user virtual address space into which the page is mapped.
|
|
|
|
*/
|
|
|
|
#define PAGE_MAPPING_ANON 1
|
|
|
|
#define PAGE_MAPPING_KSM 2
|
|
|
|
#define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
|
|
|
|
|
2016-05-20 08:13:21 +08:00
|
|
|
static __always_inline int PageAnonHead(struct page *page)
|
|
|
|
{
|
|
|
|
return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
|
|
|
|
}
|
|
|
|
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline int PageAnon(struct page *page)
|
2015-04-16 07:13:08 +08:00
|
|
|
{
|
2016-01-16 08:52:03 +08:00
|
|
|
page = compound_head(page);
|
2016-05-20 08:13:21 +08:00
|
|
|
return PageAnonHead(page);
|
2015-04-16 07:13:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_KSM
|
|
|
|
/*
|
|
|
|
* A KSM page is one of those write-protected "shared pages" or "merged pages"
|
|
|
|
* which KSM maps into multiple mms, wherever identical anonymous page content
|
|
|
|
* is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any
|
|
|
|
* anon_vma, but to that page's node of the stable tree.
|
|
|
|
*/
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline int PageKsm(struct page *page)
|
2015-04-16 07:13:08 +08:00
|
|
|
{
|
2016-01-16 08:52:03 +08:00
|
|
|
page = compound_head(page);
|
2015-04-16 07:13:08 +08:00
|
|
|
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
|
|
|
|
(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM);
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
TESTPAGEFLAG_FALSE(Ksm)
|
|
|
|
#endif
|
|
|
|
|
2009-12-16 19:19:59 +08:00
|
|
|
u64 stable_page_flags(struct page *page);
|
|
|
|
|
mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.
Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked. Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.
Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such. Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem. Both file and anonymous pages are
handled with the same barriers.
FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.
Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.
Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:34 +08:00
|
|
|
static inline int PageUptodate(struct page *page)
|
|
|
|
{
|
2016-01-16 08:52:00 +08:00
|
|
|
int ret;
|
|
|
|
page = compound_head(page);
|
|
|
|
ret = test_bit(PG_uptodate, &(page)->flags);
|
mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.
Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked. Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.
Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such. Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem. Both file and anonymous pages are
handled with the same barriers.
FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.
Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.
Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:34 +08:00
|
|
|
/*
|
|
|
|
* Must ensure that the data we read out of the page is loaded
|
|
|
|
* _after_ we've loaded page->flags to check for PageUptodate.
|
|
|
|
* We can skip the barrier if the page is not uptodate, because
|
|
|
|
* we wouldn't be reading anything from it.
|
|
|
|
*
|
|
|
|
* See SetPageUptodate() for the other side of the story.
|
|
|
|
*/
|
|
|
|
if (ret)
|
|
|
|
smp_rmb();
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void __SetPageUptodate(struct page *page)
|
mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.
Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked. Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.
Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such. Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem. Both file and anonymous pages are
handled with the same barriers.
FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.
Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.
Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:34 +08:00
|
|
|
{
|
2016-01-16 08:52:00 +08:00
|
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.
Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked. Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.
Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such. Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem. Both file and anonymous pages are
handled with the same barriers.
FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.
Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.
Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:34 +08:00
|
|
|
smp_wmb();
|
2016-01-16 08:51:28 +08:00
|
|
|
__set_bit(PG_uptodate, &page->flags);
|
mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.
Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked. Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.
Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such. Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem. Both file and anonymous pages are
handled with the same barriers.
FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.
Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.
Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:34 +08:00
|
|
|
}
|
|
|
|
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void SetPageUptodate(struct page *page)
|
2006-09-29 16:58:41 +08:00
|
|
|
{
|
2016-01-16 08:52:00 +08:00
|
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.
Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked. Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.
Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such. Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem. Both file and anonymous pages are
handled with the same barriers.
FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.
Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.
Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:34 +08:00
|
|
|
/*
|
|
|
|
* Memory barrier must be issued before setting the PG_uptodate bit,
|
|
|
|
* so that all previous stores issued in order to bring the page
|
|
|
|
* uptodate are actually visible before PageUptodate becomes true.
|
|
|
|
*/
|
|
|
|
smp_wmb();
|
2016-01-16 08:51:28 +08:00
|
|
|
set_bit(PG_uptodate, &page->flags);
|
mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.
Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked. Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.
Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such. Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem. Both file and anonymous pages are
handled with the same barriers.
FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.
Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.
Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:29:34 +08:00
|
|
|
}
|
|
|
|
|
2016-01-16 08:52:00 +08:00
|
|
|
CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-04-28 17:12:50 +08:00
|
|
|
int test_clear_page_writeback(struct page *page);
|
2014-05-12 20:12:25 +08:00
|
|
|
int __test_set_page_writeback(struct page *page, bool keep_write);
|
|
|
|
|
|
|
|
#define test_set_page_writeback(page) \
|
|
|
|
__test_set_page_writeback(page, false)
|
|
|
|
#define test_set_page_writeback_keepwrite(page) \
|
|
|
|
__test_set_page_writeback(page, true)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-04-28 17:12:50 +08:00
|
|
|
static inline void set_page_writeback(struct page *page)
|
|
|
|
{
|
|
|
|
test_set_page_writeback(page);
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2014-05-12 20:12:25 +08:00
|
|
|
static inline void set_page_writeback_keepwrite(struct page *page)
|
|
|
|
{
|
|
|
|
test_set_page_writeback_keepwrite(page);
|
|
|
|
}
|
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
|
2008-04-28 17:12:55 +08:00
|
|
|
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void set_compound_head(struct page *page, struct page *head)
|
2012-12-22 02:03:50 +08:00
|
|
|
{
|
2015-11-07 08:29:54 +08:00
|
|
|
WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
|
2012-12-22 02:03:50 +08:00
|
|
|
}
|
|
|
|
|
2016-03-18 05:18:24 +08:00
|
|
|
static __always_inline void clear_compound_head(struct page *page)
|
2008-04-28 17:12:50 +08:00
|
|
|
{
|
2015-11-07 08:29:54 +08:00
|
|
|
WRITE_ONCE(page->compound_head, 0);
|
2008-04-28 17:12:50 +08:00
|
|
|
}
|
2007-05-07 05:49:40 +08:00
|
|
|
|
2011-01-14 07:46:44 +08:00
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
|
|
static inline void ClearPageCompound(struct page *page)
|
|
|
|
{
|
2015-11-07 08:29:54 +08:00
|
|
|
BUG_ON(!PageHead(page));
|
|
|
|
ClearPageHead(page);
|
2011-01-14 07:46:44 +08:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2016-05-21 07:58:16 +08:00
|
|
|
#define PG_head_mask ((1UL << PG_head))
|
2008-06-10 00:18:45 +08:00
|
|
|
|
2015-04-16 07:13:08 +08:00
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
|
|
int PageHuge(struct page *page);
|
|
|
|
int PageHeadHuge(struct page *page);
|
2015-04-16 07:14:41 +08:00
|
|
|
bool page_huge_active(struct page *page);
|
2015-04-16 07:13:08 +08:00
|
|
|
#else
|
|
|
|
TESTPAGEFLAG_FALSE(Huge)
|
|
|
|
TESTPAGEFLAG_FALSE(HeadHuge)
|
2015-04-16 07:14:41 +08:00
|
|
|
|
|
|
|
static inline bool page_huge_active(struct page *page)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2015-04-16 07:13:08 +08:00
|
|
|
#endif
|
|
|
|
|
2015-04-16 07:14:41 +08:00
|
|
|
|
2011-01-14 07:46:48 +08:00
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
thp: transparent hugepage core
Lately I've been working to make KVM use hugepages transparently without
the usual restrictions of hugetlbfs. Some of the restrictions I'd like to
see removed:
1) hugepages have to be swappable or the guest physical memory remains
locked in RAM and can't be paged out to swap
2) if a hugepage allocation fails, regular pages should be allocated
instead and mixed in the same vma without any failure and without
userland noticing
3) if some task quits and more hugepages become available in the
buddy, guest physical memory backed by regular pages should be
relocated on hugepages automatically in regions under
madvise(MADV_HUGEPAGE) (ideally event driven by waking up the
kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes
not null)
4) avoidance of reservation and maximization of use of hugepages whenever
possible. Reservation (needed to avoid runtime fatal faliures) may be ok for
1 machine with 1 database with 1 database cache with 1 database cache size
known at boot time. It's definitely not feasible with a virtualization
hypervisor usage like RHEV-H that runs an unknown number of virtual machines
with an unknown size of each virtual machine with an unknown amount of
pagecache that could be potentially useful in the host for guest not using
O_DIRECT (aka cache=off).
hugepages in the virtualization hypervisor (and also in the guest!) are
much more important than in a regular host not using virtualization,
becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24
to 19 in case only the hypervisor uses transparent hugepages, and they
decrease the tlb-miss cacheline accesses from 19 to 15 in case both the
linux hypervisor and the linux guest both uses this patch (though the
guest will limit the addition speedup to anonymous regions only for
now...). Even more important is that the tlb miss handler is much slower
on a NPT/EPT guest than for a regular shadow paging or no-virtualization
scenario. So maximizing the amount of virtual memory cached by the TLB
pays off significantly more with NPT/EPT than without (even if there would
be no significant speedup in the tlb-miss runtime).
The first (and more tedious) part of this work requires allowing the VM to
handle anonymous hugepages mixed with regular pages transparently on
regular anonymous vmas. This is what this patch tries to achieve in the
least intrusive possible way. We want hugepages and hugetlb to be used in
a way so that all applications can benefit without changes (as usual we
leverage the KVM virtualization design: by improving the Linux VM at
large, KVM gets the performance boost too).
The most important design choice is: always fallback to 4k allocation if
the hugepage allocation fails! This is the _very_ opposite of some large
pagecache patches that failed with -EIO back then if a 64k (or similar)
allocation failed...
Second important decision (to reduce the impact of the feature on the
existing pagetable handling code) is that at any time we can split an
hugepage into 512 regular pages and it has to be done with an operation
that can't fail. This way the reliability of the swapping isn't decreased
(no need to allocate memory when we are short on memory to swap) and it's
trivial to plug a split_huge_page* one-liner where needed without
polluting the VM. Over time we can teach mprotect, mremap and friends to
handle pmd_trans_huge natively without calling split_huge_page*. The fact
it can't fail isn't just for swap: if split_huge_page would return -ENOMEM
(instead of the current void) we'd need to rollback the mprotect from the
middle of it (ideally including undoing the split_vma) which would be a
big change and in the very wrong direction (it'd likely be simpler not to
call split_huge_page at all and to teach mprotect and friends to handle
hugepages instead of rolling them back from the middle). In short the
very value of split_huge_page is that it can't fail.
The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and
incremental and it'll just be an "harmless" addition later if this initial
part is agreed upon. It also should be noted that locking-wise replacing
regular pages with hugepages is going to be very easy if compared to what
I'm doing below in split_huge_page, as it will only happen when
page_count(page) matches page_mapcount(page) if we can take the PG_lock
and mmap_sem in write mode. collapse_huge_page will be a "best effort"
that (unlike split_huge_page) can fail at the minimal sign of trouble and
we can try again later. collapse_huge_page will be similar to how KSM
works and the madvise(MADV_HUGEPAGE) will work similar to
madvise(MADV_MERGEABLE).
The default I like is that transparent hugepages are used at page fault
time. This can be changed with
/sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set
to three values "always", "madvise", "never" which mean respectively that
hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions,
or never used. /sys/kernel/mm/transparent_hugepage/defrag instead
controls if the hugepage allocation should defrag memory aggressively
"always", only inside "madvise" regions, or "never".
The pmd_trans_splitting/pmd_trans_huge locking is very solid. The
put_page (from get_user_page users that can't use mmu notifier like
O_DIRECT) that runs against a __split_huge_page_refcount instead was a
pain to serialize in a way that would result always in a coherent page
count for both tail and head. I think my locking solution with a
compound_lock taken only after the page_first is valid and is still a
PageHead should be safe but it surely needs review from SMP race point of
view. In short there is no current existing way to serialize the O_DIRECT
final put_page against split_huge_page_refcount so I had to invent a new
one (O_DIRECT loses knowledge on the mapping status by the time gup_fast
returns so...). And I didn't want to impact all gup/gup_fast users for
now, maybe if we change the gup interface substantially we can avoid this
locking, I admit I didn't think too much about it because changing the gup
unpinning interface would be invasive.
If we ignored O_DIRECT we could stick to the existing compound refcounting
code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM
(and any other mmu notifier user) would call it without FOLL_GET (and if
FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the
current task mmu notifier list yet). But O_DIRECT is fundamental for
decent performance of virtualized I/O on fast storage so we can't avoid it
to solve the race of put_page against split_huge_page_refcount to achieve
a complete hugepage feature for KVM.
Swap and oom works fine (well just like with regular pages ;). MMU
notifier is handled transparently too, with the exception of the young bit
on the pmd, that didn't have a range check but I think KVM will be fine
because the whole point of hugepages is that EPT/NPT will also use a huge
pmd when they notice gup returns pages with PageCompound set, so they
won't care of a range and there's just the pmd young bit to check in that
case.
NOTE: in some cases if the L2 cache is small, this may slowdown and waste
memory during COWs because 4M of memory are accessed in a single fault
instead of 8k (the payoff is that after COW the program can run faster).
So we might want to switch the copy_huge_page (and clear_huge_page too) to
not temporal stores. I also extensively researched ways to avoid this
cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k
up to 1M (I can send those patches that fully implemented prefault) but I
concluded they're not worth it and they add an huge additional complexity
and they remove all tlb benefits until the full hugepage has been faulted
in, to save a little bit of memory and some cache during app startup, but
they still don't improve substantially the cache-trashing during startup
if the prefault happens in >4k chunks. One reason is that those 4k pte
entries copied are still mapped on a perfectly cache-colored hugepage, so
the trashing is the worst one can generate in those copies (cow of 4k page
copies aren't so well colored so they trashes less, but again this results
in software running faster after the page fault). Those prefault patches
allowed things like a pte where post-cow pages were local 4k regular anon
pages and the not-yet-cowed pte entries were pointing in the middle of
some hugepage mapped read-only. If it doesn't payoff substantially with
todays hardware it will payoff even less in the future with larger l2
caches, and the prefault logic would blot the VM a lot. If one is
emebdded transparent_hugepage can be disabled during boot with sysfs or
with the boot commandline parameter transparent_hugepage=0 (or
transparent_hugepage=2 to restrict hugepages inside madvise regions) that
will ensure not a single hugepage is allocated at boot time. It is simple
enough to just disable transparent hugepage globally and let transparent
hugepages be allocated selectively by applications in the MADV_HUGEPAGE
region (both at page fault time, and if enabled with the
collapse_huge_page too through the kernel daemon).
This patch supports only hugepages mapped in the pmd, archs that have
smaller hugepages will not fit in this patch alone. Also some archs like
power have certain tlb limits that prevents mixing different page size in
the same regions so they will not fit in this framework that requires
"graceful fallback" to basic PAGE_SIZE in case of physical memory
fragmentation. hugetlbfs remains a perfect fit for those because its
software limits happen to match the hardware limits. hugetlbfs also
remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped
to be found not fragmented after a certain system uptime and that would be
very expensive to defragment with relocation, so requiring reservation.
hugetlbfs is the "reservation way", the point of transparent hugepages is
not to have any reservation at all and maximizing the use of cache and
hugepages at all times automatically.
Some performance result:
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep
ages3
memset page fault 1566023
memset tlb miss 453854
memset second tlb miss 453321
random access tlb miss 41635
random access second tlb miss 41658
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3
memset page fault 1566471
memset tlb miss 453375
memset second tlb miss 453320
random access tlb miss 41636
random access second tlb miss 41637
vmx andrea # ./largepages3
memset page fault 1566642
memset tlb miss 453417
memset second tlb miss 453313
random access tlb miss 41630
random access second tlb miss 41647
vmx andrea # ./largepages3
memset page fault 1566872
memset tlb miss 453418
memset second tlb miss 453315
random access tlb miss 41618
random access second tlb miss 41659
vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage
vmx andrea # ./largepages3
memset page fault 2182476
memset tlb miss 460305
memset second tlb miss 460179
random access tlb miss 44483
random access second tlb miss 44186
vmx andrea # ./largepages3
memset page fault 2182791
memset tlb miss 460742
memset second tlb miss 459962
random access tlb miss 43981
random access second tlb miss 43988
============
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#define SIZE (3UL*1024*1024*1024)
int main()
{
char *p = malloc(SIZE), *p2;
struct timeval before, after;
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset page fault %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
return 0;
}
============
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:52 +08:00
|
|
|
/*
|
|
|
|
* PageHuge() only returns true for hugetlbfs pages, but not for
|
|
|
|
* normal or transparent huge pages.
|
|
|
|
*
|
|
|
|
* PageTransHuge() returns true for both transparent huge and
|
|
|
|
* hugetlbfs pages, but not normal pages. PageTransHuge() can only be
|
|
|
|
* called only in the core VM paths where hugetlbfs pages can't exist.
|
|
|
|
*/
|
|
|
|
static inline int PageTransHuge(struct page *page)
|
|
|
|
{
|
2014-01-24 07:52:54 +08:00
|
|
|
VM_BUG_ON_PAGE(PageTail(page), page);
|
thp: transparent hugepage core
Lately I've been working to make KVM use hugepages transparently without
the usual restrictions of hugetlbfs. Some of the restrictions I'd like to
see removed:
1) hugepages have to be swappable or the guest physical memory remains
locked in RAM and can't be paged out to swap
2) if a hugepage allocation fails, regular pages should be allocated
instead and mixed in the same vma without any failure and without
userland noticing
3) if some task quits and more hugepages become available in the
buddy, guest physical memory backed by regular pages should be
relocated on hugepages automatically in regions under
madvise(MADV_HUGEPAGE) (ideally event driven by waking up the
kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes
not null)
4) avoidance of reservation and maximization of use of hugepages whenever
possible. Reservation (needed to avoid runtime fatal faliures) may be ok for
1 machine with 1 database with 1 database cache with 1 database cache size
known at boot time. It's definitely not feasible with a virtualization
hypervisor usage like RHEV-H that runs an unknown number of virtual machines
with an unknown size of each virtual machine with an unknown amount of
pagecache that could be potentially useful in the host for guest not using
O_DIRECT (aka cache=off).
hugepages in the virtualization hypervisor (and also in the guest!) are
much more important than in a regular host not using virtualization,
becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24
to 19 in case only the hypervisor uses transparent hugepages, and they
decrease the tlb-miss cacheline accesses from 19 to 15 in case both the
linux hypervisor and the linux guest both uses this patch (though the
guest will limit the addition speedup to anonymous regions only for
now...). Even more important is that the tlb miss handler is much slower
on a NPT/EPT guest than for a regular shadow paging or no-virtualization
scenario. So maximizing the amount of virtual memory cached by the TLB
pays off significantly more with NPT/EPT than without (even if there would
be no significant speedup in the tlb-miss runtime).
The first (and more tedious) part of this work requires allowing the VM to
handle anonymous hugepages mixed with regular pages transparently on
regular anonymous vmas. This is what this patch tries to achieve in the
least intrusive possible way. We want hugepages and hugetlb to be used in
a way so that all applications can benefit without changes (as usual we
leverage the KVM virtualization design: by improving the Linux VM at
large, KVM gets the performance boost too).
The most important design choice is: always fallback to 4k allocation if
the hugepage allocation fails! This is the _very_ opposite of some large
pagecache patches that failed with -EIO back then if a 64k (or similar)
allocation failed...
Second important decision (to reduce the impact of the feature on the
existing pagetable handling code) is that at any time we can split an
hugepage into 512 regular pages and it has to be done with an operation
that can't fail. This way the reliability of the swapping isn't decreased
(no need to allocate memory when we are short on memory to swap) and it's
trivial to plug a split_huge_page* one-liner where needed without
polluting the VM. Over time we can teach mprotect, mremap and friends to
handle pmd_trans_huge natively without calling split_huge_page*. The fact
it can't fail isn't just for swap: if split_huge_page would return -ENOMEM
(instead of the current void) we'd need to rollback the mprotect from the
middle of it (ideally including undoing the split_vma) which would be a
big change and in the very wrong direction (it'd likely be simpler not to
call split_huge_page at all and to teach mprotect and friends to handle
hugepages instead of rolling them back from the middle). In short the
very value of split_huge_page is that it can't fail.
The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and
incremental and it'll just be an "harmless" addition later if this initial
part is agreed upon. It also should be noted that locking-wise replacing
regular pages with hugepages is going to be very easy if compared to what
I'm doing below in split_huge_page, as it will only happen when
page_count(page) matches page_mapcount(page) if we can take the PG_lock
and mmap_sem in write mode. collapse_huge_page will be a "best effort"
that (unlike split_huge_page) can fail at the minimal sign of trouble and
we can try again later. collapse_huge_page will be similar to how KSM
works and the madvise(MADV_HUGEPAGE) will work similar to
madvise(MADV_MERGEABLE).
The default I like is that transparent hugepages are used at page fault
time. This can be changed with
/sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set
to three values "always", "madvise", "never" which mean respectively that
hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions,
or never used. /sys/kernel/mm/transparent_hugepage/defrag instead
controls if the hugepage allocation should defrag memory aggressively
"always", only inside "madvise" regions, or "never".
The pmd_trans_splitting/pmd_trans_huge locking is very solid. The
put_page (from get_user_page users that can't use mmu notifier like
O_DIRECT) that runs against a __split_huge_page_refcount instead was a
pain to serialize in a way that would result always in a coherent page
count for both tail and head. I think my locking solution with a
compound_lock taken only after the page_first is valid and is still a
PageHead should be safe but it surely needs review from SMP race point of
view. In short there is no current existing way to serialize the O_DIRECT
final put_page against split_huge_page_refcount so I had to invent a new
one (O_DIRECT loses knowledge on the mapping status by the time gup_fast
returns so...). And I didn't want to impact all gup/gup_fast users for
now, maybe if we change the gup interface substantially we can avoid this
locking, I admit I didn't think too much about it because changing the gup
unpinning interface would be invasive.
If we ignored O_DIRECT we could stick to the existing compound refcounting
code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM
(and any other mmu notifier user) would call it without FOLL_GET (and if
FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the
current task mmu notifier list yet). But O_DIRECT is fundamental for
decent performance of virtualized I/O on fast storage so we can't avoid it
to solve the race of put_page against split_huge_page_refcount to achieve
a complete hugepage feature for KVM.
Swap and oom works fine (well just like with regular pages ;). MMU
notifier is handled transparently too, with the exception of the young bit
on the pmd, that didn't have a range check but I think KVM will be fine
because the whole point of hugepages is that EPT/NPT will also use a huge
pmd when they notice gup returns pages with PageCompound set, so they
won't care of a range and there's just the pmd young bit to check in that
case.
NOTE: in some cases if the L2 cache is small, this may slowdown and waste
memory during COWs because 4M of memory are accessed in a single fault
instead of 8k (the payoff is that after COW the program can run faster).
So we might want to switch the copy_huge_page (and clear_huge_page too) to
not temporal stores. I also extensively researched ways to avoid this
cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k
up to 1M (I can send those patches that fully implemented prefault) but I
concluded they're not worth it and they add an huge additional complexity
and they remove all tlb benefits until the full hugepage has been faulted
in, to save a little bit of memory and some cache during app startup, but
they still don't improve substantially the cache-trashing during startup
if the prefault happens in >4k chunks. One reason is that those 4k pte
entries copied are still mapped on a perfectly cache-colored hugepage, so
the trashing is the worst one can generate in those copies (cow of 4k page
copies aren't so well colored so they trashes less, but again this results
in software running faster after the page fault). Those prefault patches
allowed things like a pte where post-cow pages were local 4k regular anon
pages and the not-yet-cowed pte entries were pointing in the middle of
some hugepage mapped read-only. If it doesn't payoff substantially with
todays hardware it will payoff even less in the future with larger l2
caches, and the prefault logic would blot the VM a lot. If one is
emebdded transparent_hugepage can be disabled during boot with sysfs or
with the boot commandline parameter transparent_hugepage=0 (or
transparent_hugepage=2 to restrict hugepages inside madvise regions) that
will ensure not a single hugepage is allocated at boot time. It is simple
enough to just disable transparent hugepage globally and let transparent
hugepages be allocated selectively by applications in the MADV_HUGEPAGE
region (both at page fault time, and if enabled with the
collapse_huge_page too through the kernel daemon).
This patch supports only hugepages mapped in the pmd, archs that have
smaller hugepages will not fit in this patch alone. Also some archs like
power have certain tlb limits that prevents mixing different page size in
the same regions so they will not fit in this framework that requires
"graceful fallback" to basic PAGE_SIZE in case of physical memory
fragmentation. hugetlbfs remains a perfect fit for those because its
software limits happen to match the hardware limits. hugetlbfs also
remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped
to be found not fragmented after a certain system uptime and that would be
very expensive to defragment with relocation, so requiring reservation.
hugetlbfs is the "reservation way", the point of transparent hugepages is
not to have any reservation at all and maximizing the use of cache and
hugepages at all times automatically.
Some performance result:
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep
ages3
memset page fault 1566023
memset tlb miss 453854
memset second tlb miss 453321
random access tlb miss 41635
random access second tlb miss 41658
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3
memset page fault 1566471
memset tlb miss 453375
memset second tlb miss 453320
random access tlb miss 41636
random access second tlb miss 41637
vmx andrea # ./largepages3
memset page fault 1566642
memset tlb miss 453417
memset second tlb miss 453313
random access tlb miss 41630
random access second tlb miss 41647
vmx andrea # ./largepages3
memset page fault 1566872
memset tlb miss 453418
memset second tlb miss 453315
random access tlb miss 41618
random access second tlb miss 41659
vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage
vmx andrea # ./largepages3
memset page fault 2182476
memset tlb miss 460305
memset second tlb miss 460179
random access tlb miss 44483
random access second tlb miss 44186
vmx andrea # ./largepages3
memset page fault 2182791
memset tlb miss 460742
memset second tlb miss 459962
random access tlb miss 43981
random access second tlb miss 43988
============
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#define SIZE (3UL*1024*1024*1024)
int main()
{
char *p = malloc(SIZE), *p2;
struct timeval before, after;
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset page fault %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
return 0;
}
============
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:52 +08:00
|
|
|
return PageHead(page);
|
|
|
|
}
|
|
|
|
|
2012-03-22 07:34:05 +08:00
|
|
|
/*
|
|
|
|
* PageTransCompound returns true for both transparent huge pages
|
|
|
|
* and hugetlbfs pages, so it should only be called when it's known
|
|
|
|
* that hugetlbfs pages aren't involved.
|
|
|
|
*/
|
2011-01-14 07:46:48 +08:00
|
|
|
static inline int PageTransCompound(struct page *page)
|
|
|
|
{
|
|
|
|
return PageCompound(page);
|
|
|
|
}
|
thp: transparent hugepage core
Lately I've been working to make KVM use hugepages transparently without
the usual restrictions of hugetlbfs. Some of the restrictions I'd like to
see removed:
1) hugepages have to be swappable or the guest physical memory remains
locked in RAM and can't be paged out to swap
2) if a hugepage allocation fails, regular pages should be allocated
instead and mixed in the same vma without any failure and without
userland noticing
3) if some task quits and more hugepages become available in the
buddy, guest physical memory backed by regular pages should be
relocated on hugepages automatically in regions under
madvise(MADV_HUGEPAGE) (ideally event driven by waking up the
kernel deamon if the order=HPAGE_PMD_SHIFT-PAGE_SHIFT list becomes
not null)
4) avoidance of reservation and maximization of use of hugepages whenever
possible. Reservation (needed to avoid runtime fatal faliures) may be ok for
1 machine with 1 database with 1 database cache with 1 database cache size
known at boot time. It's definitely not feasible with a virtualization
hypervisor usage like RHEV-H that runs an unknown number of virtual machines
with an unknown size of each virtual machine with an unknown amount of
pagecache that could be potentially useful in the host for guest not using
O_DIRECT (aka cache=off).
hugepages in the virtualization hypervisor (and also in the guest!) are
much more important than in a regular host not using virtualization,
becasue with NPT/EPT they decrease the tlb-miss cacheline accesses from 24
to 19 in case only the hypervisor uses transparent hugepages, and they
decrease the tlb-miss cacheline accesses from 19 to 15 in case both the
linux hypervisor and the linux guest both uses this patch (though the
guest will limit the addition speedup to anonymous regions only for
now...). Even more important is that the tlb miss handler is much slower
on a NPT/EPT guest than for a regular shadow paging or no-virtualization
scenario. So maximizing the amount of virtual memory cached by the TLB
pays off significantly more with NPT/EPT than without (even if there would
be no significant speedup in the tlb-miss runtime).
The first (and more tedious) part of this work requires allowing the VM to
handle anonymous hugepages mixed with regular pages transparently on
regular anonymous vmas. This is what this patch tries to achieve in the
least intrusive possible way. We want hugepages and hugetlb to be used in
a way so that all applications can benefit without changes (as usual we
leverage the KVM virtualization design: by improving the Linux VM at
large, KVM gets the performance boost too).
The most important design choice is: always fallback to 4k allocation if
the hugepage allocation fails! This is the _very_ opposite of some large
pagecache patches that failed with -EIO back then if a 64k (or similar)
allocation failed...
Second important decision (to reduce the impact of the feature on the
existing pagetable handling code) is that at any time we can split an
hugepage into 512 regular pages and it has to be done with an operation
that can't fail. This way the reliability of the swapping isn't decreased
(no need to allocate memory when we are short on memory to swap) and it's
trivial to plug a split_huge_page* one-liner where needed without
polluting the VM. Over time we can teach mprotect, mremap and friends to
handle pmd_trans_huge natively without calling split_huge_page*. The fact
it can't fail isn't just for swap: if split_huge_page would return -ENOMEM
(instead of the current void) we'd need to rollback the mprotect from the
middle of it (ideally including undoing the split_vma) which would be a
big change and in the very wrong direction (it'd likely be simpler not to
call split_huge_page at all and to teach mprotect and friends to handle
hugepages instead of rolling them back from the middle). In short the
very value of split_huge_page is that it can't fail.
The collapsing and madvise(MADV_HUGEPAGE) part will remain separated and
incremental and it'll just be an "harmless" addition later if this initial
part is agreed upon. It also should be noted that locking-wise replacing
regular pages with hugepages is going to be very easy if compared to what
I'm doing below in split_huge_page, as it will only happen when
page_count(page) matches page_mapcount(page) if we can take the PG_lock
and mmap_sem in write mode. collapse_huge_page will be a "best effort"
that (unlike split_huge_page) can fail at the minimal sign of trouble and
we can try again later. collapse_huge_page will be similar to how KSM
works and the madvise(MADV_HUGEPAGE) will work similar to
madvise(MADV_MERGEABLE).
The default I like is that transparent hugepages are used at page fault
time. This can be changed with
/sys/kernel/mm/transparent_hugepage/enabled. The control knob can be set
to three values "always", "madvise", "never" which mean respectively that
hugepages are always used, or only inside madvise(MADV_HUGEPAGE) regions,
or never used. /sys/kernel/mm/transparent_hugepage/defrag instead
controls if the hugepage allocation should defrag memory aggressively
"always", only inside "madvise" regions, or "never".
The pmd_trans_splitting/pmd_trans_huge locking is very solid. The
put_page (from get_user_page users that can't use mmu notifier like
O_DIRECT) that runs against a __split_huge_page_refcount instead was a
pain to serialize in a way that would result always in a coherent page
count for both tail and head. I think my locking solution with a
compound_lock taken only after the page_first is valid and is still a
PageHead should be safe but it surely needs review from SMP race point of
view. In short there is no current existing way to serialize the O_DIRECT
final put_page against split_huge_page_refcount so I had to invent a new
one (O_DIRECT loses knowledge on the mapping status by the time gup_fast
returns so...). And I didn't want to impact all gup/gup_fast users for
now, maybe if we change the gup interface substantially we can avoid this
locking, I admit I didn't think too much about it because changing the gup
unpinning interface would be invasive.
If we ignored O_DIRECT we could stick to the existing compound refcounting
code, by simply adding a get_user_pages_fast_flags(foll_flags) where KVM
(and any other mmu notifier user) would call it without FOLL_GET (and if
FOLL_GET isn't set we'd just BUG_ON if nobody registered itself in the
current task mmu notifier list yet). But O_DIRECT is fundamental for
decent performance of virtualized I/O on fast storage so we can't avoid it
to solve the race of put_page against split_huge_page_refcount to achieve
a complete hugepage feature for KVM.
Swap and oom works fine (well just like with regular pages ;). MMU
notifier is handled transparently too, with the exception of the young bit
on the pmd, that didn't have a range check but I think KVM will be fine
because the whole point of hugepages is that EPT/NPT will also use a huge
pmd when they notice gup returns pages with PageCompound set, so they
won't care of a range and there's just the pmd young bit to check in that
case.
NOTE: in some cases if the L2 cache is small, this may slowdown and waste
memory during COWs because 4M of memory are accessed in a single fault
instead of 8k (the payoff is that after COW the program can run faster).
So we might want to switch the copy_huge_page (and clear_huge_page too) to
not temporal stores. I also extensively researched ways to avoid this
cache trashing with a full prefault logic that would cow in 8k/16k/32k/64k
up to 1M (I can send those patches that fully implemented prefault) but I
concluded they're not worth it and they add an huge additional complexity
and they remove all tlb benefits until the full hugepage has been faulted
in, to save a little bit of memory and some cache during app startup, but
they still don't improve substantially the cache-trashing during startup
if the prefault happens in >4k chunks. One reason is that those 4k pte
entries copied are still mapped on a perfectly cache-colored hugepage, so
the trashing is the worst one can generate in those copies (cow of 4k page
copies aren't so well colored so they trashes less, but again this results
in software running faster after the page fault). Those prefault patches
allowed things like a pte where post-cow pages were local 4k regular anon
pages and the not-yet-cowed pte entries were pointing in the middle of
some hugepage mapped read-only. If it doesn't payoff substantially with
todays hardware it will payoff even less in the future with larger l2
caches, and the prefault logic would blot the VM a lot. If one is
emebdded transparent_hugepage can be disabled during boot with sysfs or
with the boot commandline parameter transparent_hugepage=0 (or
transparent_hugepage=2 to restrict hugepages inside madvise regions) that
will ensure not a single hugepage is allocated at boot time. It is simple
enough to just disable transparent hugepage globally and let transparent
hugepages be allocated selectively by applications in the MADV_HUGEPAGE
region (both at page fault time, and if enabled with the
collapse_huge_page too through the kernel daemon).
This patch supports only hugepages mapped in the pmd, archs that have
smaller hugepages will not fit in this patch alone. Also some archs like
power have certain tlb limits that prevents mixing different page size in
the same regions so they will not fit in this framework that requires
"graceful fallback" to basic PAGE_SIZE in case of physical memory
fragmentation. hugetlbfs remains a perfect fit for those because its
software limits happen to match the hardware limits. hugetlbfs also
remains a perfect fit for hugepage sizes like 1GByte that cannot be hoped
to be found not fragmented after a certain system uptime and that would be
very expensive to defragment with relocation, so requiring reservation.
hugetlbfs is the "reservation way", the point of transparent hugepages is
not to have any reservation at all and maximizing the use of cache and
hugepages at all times automatically.
Some performance result:
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largep
ages3
memset page fault 1566023
memset tlb miss 453854
memset second tlb miss 453321
random access tlb miss 41635
random access second tlb miss 41658
vmx andrea # LD_PRELOAD=/usr/lib64/libhugetlbfs.so HUGETLB_MORECORE=yes HUGETLB_PATH=/mnt/huge/ ./largepages3
memset page fault 1566471
memset tlb miss 453375
memset second tlb miss 453320
random access tlb miss 41636
random access second tlb miss 41637
vmx andrea # ./largepages3
memset page fault 1566642
memset tlb miss 453417
memset second tlb miss 453313
random access tlb miss 41630
random access second tlb miss 41647
vmx andrea # ./largepages3
memset page fault 1566872
memset tlb miss 453418
memset second tlb miss 453315
random access tlb miss 41618
random access second tlb miss 41659
vmx andrea # echo 0 > /proc/sys/vm/transparent_hugepage
vmx andrea # ./largepages3
memset page fault 2182476
memset tlb miss 460305
memset second tlb miss 460179
random access tlb miss 44483
random access second tlb miss 44186
vmx andrea # ./largepages3
memset page fault 2182791
memset tlb miss 460742
memset second tlb miss 459962
random access tlb miss 43981
random access second tlb miss 43988
============
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/time.h>
#define SIZE (3UL*1024*1024*1024)
int main()
{
char *p = malloc(SIZE), *p2;
struct timeval before, after;
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset page fault %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
memset(p, 0, SIZE);
gettimeofday(&after, NULL);
printf("memset second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
gettimeofday(&before, NULL);
for (p2 = p; p2 < p+SIZE; p2 += 4096)
*p2 = 0;
gettimeofday(&after, NULL);
printf("random access second tlb miss %Lu\n",
(after.tv_sec-before.tv_sec)*1000000UL +
after.tv_usec-before.tv_usec);
return 0;
}
============
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:52 +08:00
|
|
|
|
mm: thp: kvm: fix memory corruption in KVM with THP enabled
After the THP refcounting change, obtaining a compound pages from
get_user_pages() no longer allows us to assume the entire compound page
is immediately mappable from a secondary MMU.
A secondary MMU doesn't want to call get_user_pages() more than once for
each compound page, in order to know if it can map the whole compound
page. So a secondary MMU needs to know from a single get_user_pages()
invocation when it can map immediately the entire compound page to avoid
a flood of unnecessary secondary MMU faults and spurious
atomic_inc()/atomic_dec() (pages don't have to be pinned by MMU notifier
users).
Ideally instead of the page->_mapcount < 1 check, get_user_pages()
should return the granularity of the "page" mapping in the "mm" passed
to get_user_pages(). However it's non trivial change to pass the "pmd"
status belonging to the "mm" walked by get_user_pages up the stack (up
to the caller of get_user_pages). So the fix just checks if there is
not a single pte mapping on the page returned by get_user_pages, and in
turn if the caller can assume that the whole compound page is mapped in
the current "mm" (in a pmd_trans_huge()). In such case the entire
compound page is safe to map into the secondary MMU without additional
get_user_pages() calls on the surrounding tail/head pages. In addition
of being faster, not having to run other get_user_pages() calls also
reduces the memory footprint of the secondary MMU fault in case the pmd
split happened as result of memory pressure.
Without this fix after a MADV_DONTNEED (like invoked by QEMU during
postcopy live migration or balloning) or after generic swapping (with a
failure in split_huge_page() that would only result in pmd splitting and
not a physical page split), KVM would map the whole compound page into
the shadow pagetables, despite regular faults or userfaults (like
UFFDIO_COPY) may map regular pages into the primary MMU as result of the
pte faults, leading to the guest mode and userland mode going out of
sync and not working on the same memory at all times.
Any other secondary MMU notifier manager (KVM is just one of the many
MMU notifier users) will need the same information if it doesn't want to
run a flood of get_user_pages_fast and it can support multiple
granularity in the secondary MMU mappings, so I think it is justified to
be exposed not just to KVM.
The other option would be to move transparent_hugepage_adjust to
mm/huge_memory.c but that currently has all kind of KVM data structures
in it, so it's definitely not a cut-and-paste work, so I couldn't do a
fix as cleaner as this one for 4.6.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: "Li, Liang Z" <liang.z.li@intel.com>
Cc: Amit Shah <amit.shah@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-06 07:22:20 +08:00
|
|
|
/*
|
|
|
|
* PageTransCompoundMap is the same as PageTransCompound, but it also
|
|
|
|
* guarantees the primary MMU has the entire compound page mapped
|
|
|
|
* through pmd_trans_huge, which in turn guarantees the secondary MMUs
|
|
|
|
* can also map the entire compound page. This allows the secondary
|
|
|
|
* MMUs to call get_user_pages() only once for each compound page and
|
|
|
|
* to immediately map the entire compound page with a single secondary
|
|
|
|
* MMU fault. If there will be a pmd split later, the secondary MMUs
|
|
|
|
* will get an update through the MMU notifier invalidation through
|
|
|
|
* split_huge_pmd().
|
|
|
|
*
|
|
|
|
* Unlike PageTransCompound, this is safe to be called only while
|
|
|
|
* split_huge_pmd() cannot run from under us, like if protected by the
|
|
|
|
* MMU notifier, otherwise it may result in page->_mapcount < 0 false
|
|
|
|
* positives.
|
|
|
|
*/
|
|
|
|
static inline int PageTransCompoundMap(struct page *page)
|
|
|
|
{
|
|
|
|
return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0;
|
|
|
|
}
|
|
|
|
|
2012-03-22 07:34:05 +08:00
|
|
|
/*
|
|
|
|
* PageTransTail returns true for both transparent huge pages
|
|
|
|
* and hugetlbfs pages, so it should only be called when it's known
|
|
|
|
* that hugetlbfs pages aren't involved.
|
|
|
|
*/
|
|
|
|
static inline int PageTransTail(struct page *page)
|
|
|
|
{
|
|
|
|
return PageTail(page);
|
|
|
|
}
|
|
|
|
|
2016-01-16 08:53:42 +08:00
|
|
|
/*
|
|
|
|
* PageDoubleMap indicates that the compound page is mapped with PTEs as well
|
|
|
|
* as PMDs.
|
|
|
|
*
|
|
|
|
* This is required for optimization of rmap operations for THP: we can postpone
|
|
|
|
* per small page mapcount accounting (and its overhead from atomic operations)
|
|
|
|
* until the first PMD split.
|
|
|
|
*
|
|
|
|
* For the page PageDoubleMap means ->_mapcount in all sub-pages is offset up
|
|
|
|
* by one. This reference will go away with last compound_mapcount.
|
|
|
|
*
|
|
|
|
* See also __split_huge_pmd_locked() and page_remove_anon_compound_rmap().
|
|
|
|
*/
|
|
|
|
static inline int PageDoubleMap(struct page *page)
|
|
|
|
{
|
|
|
|
return PageHead(page) && test_bit(PG_double_map, &page[1].flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int TestSetPageDoubleMap(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(!PageHead(page), page);
|
|
|
|
return test_and_set_bit(PG_double_map, &page[1].flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int TestClearPageDoubleMap(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(!PageHead(page), page);
|
|
|
|
return test_and_clear_bit(PG_double_map, &page[1].flags);
|
|
|
|
}
|
|
|
|
|
2011-01-14 07:46:48 +08:00
|
|
|
#else
|
2016-01-16 08:51:13 +08:00
|
|
|
TESTPAGEFLAG_FALSE(TransHuge)
|
|
|
|
TESTPAGEFLAG_FALSE(TransCompound)
|
mm: thp: kvm: fix memory corruption in KVM with THP enabled
After the THP refcounting change, obtaining a compound pages from
get_user_pages() no longer allows us to assume the entire compound page
is immediately mappable from a secondary MMU.
A secondary MMU doesn't want to call get_user_pages() more than once for
each compound page, in order to know if it can map the whole compound
page. So a secondary MMU needs to know from a single get_user_pages()
invocation when it can map immediately the entire compound page to avoid
a flood of unnecessary secondary MMU faults and spurious
atomic_inc()/atomic_dec() (pages don't have to be pinned by MMU notifier
users).
Ideally instead of the page->_mapcount < 1 check, get_user_pages()
should return the granularity of the "page" mapping in the "mm" passed
to get_user_pages(). However it's non trivial change to pass the "pmd"
status belonging to the "mm" walked by get_user_pages up the stack (up
to the caller of get_user_pages). So the fix just checks if there is
not a single pte mapping on the page returned by get_user_pages, and in
turn if the caller can assume that the whole compound page is mapped in
the current "mm" (in a pmd_trans_huge()). In such case the entire
compound page is safe to map into the secondary MMU without additional
get_user_pages() calls on the surrounding tail/head pages. In addition
of being faster, not having to run other get_user_pages() calls also
reduces the memory footprint of the secondary MMU fault in case the pmd
split happened as result of memory pressure.
Without this fix after a MADV_DONTNEED (like invoked by QEMU during
postcopy live migration or balloning) or after generic swapping (with a
failure in split_huge_page() that would only result in pmd splitting and
not a physical page split), KVM would map the whole compound page into
the shadow pagetables, despite regular faults or userfaults (like
UFFDIO_COPY) may map regular pages into the primary MMU as result of the
pte faults, leading to the guest mode and userland mode going out of
sync and not working on the same memory at all times.
Any other secondary MMU notifier manager (KVM is just one of the many
MMU notifier users) will need the same information if it doesn't want to
run a flood of get_user_pages_fast and it can support multiple
granularity in the secondary MMU mappings, so I think it is justified to
be exposed not just to KVM.
The other option would be to move transparent_hugepage_adjust to
mm/huge_memory.c but that currently has all kind of KVM data structures
in it, so it's definitely not a cut-and-paste work, so I couldn't do a
fix as cleaner as this one for 4.6.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: "Li, Liang Z" <liang.z.li@intel.com>
Cc: Amit Shah <amit.shah@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-05-06 07:22:20 +08:00
|
|
|
TESTPAGEFLAG_FALSE(TransCompoundMap)
|
2016-01-16 08:51:13 +08:00
|
|
|
TESTPAGEFLAG_FALSE(TransTail)
|
2016-01-16 08:53:42 +08:00
|
|
|
TESTPAGEFLAG_FALSE(DoubleMap)
|
|
|
|
TESTSETFLAG_FALSE(DoubleMap)
|
|
|
|
TESTCLEARFLAG_FALSE(DoubleMap)
|
2011-01-14 07:46:48 +08:00
|
|
|
#endif
|
|
|
|
|
2015-04-16 07:13:08 +08:00
|
|
|
/*
|
|
|
|
* PageBuddy() indicate that the page is free and in the buddy system
|
|
|
|
* (see mm/page_alloc.c).
|
|
|
|
*
|
|
|
|
* PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to
|
|
|
|
* -2 so that an underflow of the page_mapcount() won't be mistaken
|
|
|
|
* for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very
|
|
|
|
* efficiently by most CPU architectures.
|
|
|
|
*/
|
|
|
|
#define PAGE_BUDDY_MAPCOUNT_VALUE (-128)
|
|
|
|
|
|
|
|
static inline int PageBuddy(struct page *page)
|
|
|
|
{
|
|
|
|
return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __SetPageBuddy(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
|
|
|
|
atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __ClearPageBuddy(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(!PageBuddy(page), page);
|
|
|
|
atomic_set(&page->_mapcount, -1);
|
|
|
|
}
|
|
|
|
|
2016-03-18 05:17:41 +08:00
|
|
|
extern bool is_free_buddy_page(struct page *page);
|
|
|
|
|
2015-04-16 07:13:08 +08:00
|
|
|
#define PAGE_BALLOON_MAPCOUNT_VALUE (-256)
|
|
|
|
|
|
|
|
static inline int PageBalloon(struct page *page)
|
|
|
|
{
|
|
|
|
return atomic_read(&page->_mapcount) == PAGE_BALLOON_MAPCOUNT_VALUE;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __SetPageBalloon(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(atomic_read(&page->_mapcount) != -1, page);
|
|
|
|
atomic_set(&page->_mapcount, PAGE_BALLOON_MAPCOUNT_VALUE);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __ClearPageBalloon(struct page *page)
|
|
|
|
{
|
|
|
|
VM_BUG_ON_PAGE(!PageBalloon(page), page);
|
|
|
|
atomic_set(&page->_mapcount, -1);
|
|
|
|
}
|
|
|
|
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:43:58 +08:00
|
|
|
/*
|
|
|
|
* If network-based swap is enabled, sl*b must keep track of whether pages
|
|
|
|
* were allocated from pfmemalloc reserves.
|
|
|
|
*/
|
|
|
|
static inline int PageSlabPfmemalloc(struct page *page)
|
|
|
|
{
|
2014-01-24 07:52:54 +08:00
|
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:43:58 +08:00
|
|
|
return PageActive(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void SetPageSlabPfmemalloc(struct page *page)
|
|
|
|
{
|
2014-01-24 07:52:54 +08:00
|
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:43:58 +08:00
|
|
|
SetPageActive(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __ClearPageSlabPfmemalloc(struct page *page)
|
|
|
|
{
|
2014-01-24 07:52:54 +08:00
|
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:43:58 +08:00
|
|
|
__ClearPageActive(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void ClearPageSlabPfmemalloc(struct page *page)
|
|
|
|
{
|
2014-01-24 07:52:54 +08:00
|
|
|
VM_BUG_ON_PAGE(!PageSlab(page), page);
|
mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
When a user or administrator requires swap for their application, they
create a swap partition and file, format it with mkswap and activate it
with swapon. Swap over the network is considered as an option in diskless
systems. The two likely scenarios are when blade servers are used as part
of a cluster where the form factor or maintenance costs do not allow the
use of disks and thin clients.
The Linux Terminal Server Project recommends the use of the Network Block
Device (NBD) for swap according to the manual at
https://sourceforge.net/projects/ltsp/files/Docs-Admin-Guide/LTSPManual.pdf/download
There is also documentation and tutorials on how to setup swap over NBD at
places like https://help.ubuntu.com/community/UbuntuLTSP/EnableNBDSWAP The
nbd-client also documents the use of NBD as swap. Despite this, the fact
is that a machine using NBD for swap can deadlock within minutes if swap
is used intensively. This patch series addresses the problem.
The core issue is that network block devices do not use mempools like
normal block devices do. As the host cannot control where they receive
packets from, they cannot reliably work out in advance how much memory
they might need. Some years ago, Peter Zijlstra developed a series of
patches that supported swap over an NFS that at least one distribution is
carrying within their kernels. This patch series borrows very heavily
from Peter's work to support swapping over NBD as a pre-requisite to
supporting swap-over-NFS. The bulk of the complexity is concerned with
preserving memory that is allocated from the PFMEMALLOC reserves for use
by the network layer which is needed for both NBD and NFS.
Patch 1 adds knowledge of the PFMEMALLOC reserves to SLAB and SLUB to
preserve access to pages allocated under low memory situations
to callers that are freeing memory.
Patch 2 optimises the SLUB fast path to avoid pfmemalloc checks
Patch 3 introduces __GFP_MEMALLOC to allow access to the PFMEMALLOC
reserves without setting PFMEMALLOC.
Patch 4 opens the possibility for softirqs to use PFMEMALLOC reserves
for later use by network packet processing.
Patch 5 only sets page->pfmemalloc when ALLOC_NO_WATERMARKS was required
Patch 6 ignores memory policies when ALLOC_NO_WATERMARKS is set.
Patches 7-12 allows network processing to use PFMEMALLOC reserves when
the socket has been marked as being used by the VM to clean pages. If
packets are received and stored in pages that were allocated under
low-memory situations and are unrelated to the VM, the packets
are dropped.
Patch 11 reintroduces __skb_alloc_page which the networking
folk may object to but is needed in some cases to propogate
pfmemalloc from a newly allocated page to an skb. If there is a
strong objection, this patch can be dropped with the impact being
that swap-over-network will be slower in some cases but it should
not fail.
Patch 13 is a micro-optimisation to avoid a function call in the
common case.
Patch 14 tags NBD sockets as being SOCK_MEMALLOC so they can use
PFMEMALLOC if necessary.
Patch 15 notes that it is still possible for the PFMEMALLOC reserve
to be depleted. To prevent this, direct reclaimers get throttled on
a waitqueue if 50% of the PFMEMALLOC reserves are depleted. It is
expected that kswapd and the direct reclaimers already running
will clean enough pages for the low watermark to be reached and
the throttled processes are woken up.
Patch 16 adds a statistic to track how often processes get throttled
Some basic performance testing was run using kernel builds, netperf on
loopback for UDP and TCP, hackbench (pipes and sockets), iozone and
sysbench. Each of them were expected to use the sl*b allocators
reasonably heavily but there did not appear to be significant performance
variances.
For testing swap-over-NBD, a machine was booted with 2G of RAM with a
swapfile backed by NBD. 8*NUM_CPU processes were started that create
anonymous memory mappings and read them linearly in a loop. The total
size of the mappings were 4*PHYSICAL_MEMORY to use swap heavily under
memory pressure.
Without the patches and using SLUB, the machine locks up within minutes
and runs to completion with them applied. With SLAB, the story is
different as an unpatched kernel run to completion. However, the patched
kernel completed the test 45% faster.
MICRO
3.5.0-rc2 3.5.0-rc2
vanilla swapnbd
Unrecognised test vmscan-anon-mmap-write
MMTests Statistics: duration
Sys Time Running Test (seconds) 197.80 173.07
User+Sys Time Running Test (seconds) 206.96 182.03
Total Elapsed Time (seconds) 3240.70 1762.09
This patch: mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages
Allocations of pages below the min watermark run a risk of the machine
hanging due to a lack of memory. To prevent this, only callers who have
PF_MEMALLOC or TIF_MEMDIE set and are not processing an interrupt are
allowed to allocate with ALLOC_NO_WATERMARKS. Once they are allocated to
a slab though, nothing prevents other callers consuming free objects
within those slabs. This patch limits access to slab pages that were
alloced from the PFMEMALLOC reserves.
When this patch is applied, pages allocated from below the low watermark
are returned with page->pfmemalloc set and it is up to the caller to
determine how the page should be protected. SLAB restricts access to any
page with page->pfmemalloc set to callers which are known to able to
access the PFMEMALLOC reserve. If one is not available, an attempt is
made to allocate a new page rather than use a reserve. SLUB is a bit more
relaxed in that it only records if the current per-CPU page was allocated
from PFMEMALLOC reserve and uses another partial slab if the caller does
not have the necessary GFP or process flags. This was found to be
sufficient in tests to avoid hangs due to SLUB generally maintaining
smaller lists than SLAB.
In low-memory conditions it does mean that !PFMEMALLOC allocators can fail
a slab allocation even though free objects are available because they are
being preserved for callers that are freeing pages.
[a.p.zijlstra@chello.nl: Original implementation]
[sebastian@breakpoint.cc: Correct order of page flag clearing]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-08-01 07:43:58 +08:00
|
|
|
ClearPageActive(page);
|
|
|
|
}
|
|
|
|
|
2009-12-15 09:58:59 +08:00
|
|
|
#ifdef CONFIG_MMU
|
2016-05-21 07:58:16 +08:00
|
|
|
#define __PG_MLOCKED (1UL << PG_mlocked)
|
2009-04-01 06:23:26 +08:00
|
|
|
#else
|
mlock: mlocked pages are unevictable
Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.
This is achieved through various strategies:
1) add yet another page flag--PG_mlocked--to indicate that
the page is locked for efficient testing in vmscan and,
optionally, fault path. This allows early culling of
unevictable pages, preventing them from getting to
page_referenced()/try_to_unmap(). Also allows separate
accounting of mlock'd pages, as Nick's original patch
did.
Note: Nick's original mlock patch used a PG_mlocked
flag. I had removed this in favor of the PG_unevictable
flag + an mlock_count [new page struct member]. I
restored the PG_mlocked flag to eliminate the new
count field.
2) add the mlock/unevictable infrastructure to mm/mlock.c,
with internal APIs in mm/internal.h. This is a rework
of Nick's original patch to these files, taking into
account that mlocked pages are now kept on unevictable
LRU list.
3) update vmscan.c:page_evictable() to check PageMlocked()
and, if vma passed in, the vm_flags. Note that the vma
will only be passed in for new pages in the fault path;
and then only if the "cull unevictable pages in fault
path" patch is included.
4) add try_to_unlock() to rmap.c to walk a page's rmap and
ClearPageMlocked() if no other vmas have it mlocked.
Reuses as much of try_to_unmap() as possible. This
effectively replaces the use of one of the lru list links
as an mlock count. If this mechanism let's pages in mlocked
vmas leak through w/o PG_mlocked set [I don't know that it
does], we should catch them later in try_to_unmap(). One
hopes this will be rare, as it will be relatively expensive.
Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>
splitlru: introduce __get_user_pages():
New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
because current get_user_pages() can't grab PROT_NONE pages theresore it
cause PROT_NONE pages can't munlock.
[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
|
|
|
#define __PG_MLOCKED 0
|
Unevictable LRU Infrastructure
When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages. Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.
Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.
Kosaki Motohiro added the support for the memory controller unevictable
lru list.
Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.
The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.
A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable. Subsequent patches will add the various
!evictable tests. We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.
To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference. If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list. This way, we avoid "stranding" evictable pages on the
unevictable list.
[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:39 +08:00
|
|
|
#endif
|
|
|
|
|
2008-06-10 00:18:45 +08:00
|
|
|
/*
|
|
|
|
* Flags checked when a page is freed. Pages being freed should not have
|
|
|
|
* these flags set. It they are, there is a problem.
|
|
|
|
*/
|
2009-01-07 06:40:05 +08:00
|
|
|
#define PAGE_FLAGS_CHECK_AT_FREE \
|
2016-05-21 07:58:16 +08:00
|
|
|
(1UL << PG_lru | 1UL << PG_locked | \
|
|
|
|
1UL << PG_private | 1UL << PG_private_2 | \
|
|
|
|
1UL << PG_writeback | 1UL << PG_reserved | \
|
|
|
|
1UL << PG_slab | 1UL << PG_swapcache | 1UL << PG_active | \
|
|
|
|
1UL << PG_unevictable | __PG_MLOCKED)
|
2008-06-10 00:18:45 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Flags checked when a page is prepped for return by the page allocator.
|
mm: check __PG_HWPOISON separately from PAGE_FLAGS_CHECK_AT_*
The race condition addressed in commit add05cecef80 ("mm: soft-offline:
don't free target page in successful page migration") was not closed
completely, because that can happen not only for soft-offline, but also
for hard-offline. Consider that a slab page is about to be freed into
buddy pool, and then an uncorrected memory error hits the page just
after entering __free_one_page(), then VM_BUG_ON_PAGE(page->flags &
PAGE_FLAGS_CHECK_AT_PREP) is triggered, despite the fact that it's not
necessary because the data on the affected page is not consumed.
To solve it, this patch drops __PG_HWPOISON from page flag checks at
allocation/free time. I think it's justified because __PG_HWPOISON
flags is defined to prevent the page from being reused, and setting it
outside the page's alloc-free cycle is a designed behavior (not a bug.)
For recent months, I was annoyed about BUG_ON when soft-offlined page
remains on lru cache list for a while, which is avoided by calling
put_page() instead of putback_lru_page() in page migration's success
path. This means that this patch reverts a major change from commit
add05cecef80 about the new refcounting rule of soft-offlined pages, so
"reuse window" revives. This will be closed by a subsequent patch.
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Dean Nelson <dnelson@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-08-07 06:47:08 +08:00
|
|
|
* Pages being prepped should not have these flags set. It they are set,
|
2009-01-07 06:40:05 +08:00
|
|
|
* there has been a kernel bug or struct page corruption.
|
mm: check __PG_HWPOISON separately from PAGE_FLAGS_CHECK_AT_*
The race condition addressed in commit add05cecef80 ("mm: soft-offline:
don't free target page in successful page migration") was not closed
completely, because that can happen not only for soft-offline, but also
for hard-offline. Consider that a slab page is about to be freed into
buddy pool, and then an uncorrected memory error hits the page just
after entering __free_one_page(), then VM_BUG_ON_PAGE(page->flags &
PAGE_FLAGS_CHECK_AT_PREP) is triggered, despite the fact that it's not
necessary because the data on the affected page is not consumed.
To solve it, this patch drops __PG_HWPOISON from page flag checks at
allocation/free time. I think it's justified because __PG_HWPOISON
flags is defined to prevent the page from being reused, and setting it
outside the page's alloc-free cycle is a designed behavior (not a bug.)
For recent months, I was annoyed about BUG_ON when soft-offlined page
remains on lru cache list for a while, which is avoided by calling
put_page() instead of putback_lru_page() in page migration's success
path. This means that this patch reverts a major change from commit
add05cecef80 about the new refcounting rule of soft-offlined pages, so
"reuse window" revives. This will be closed by a subsequent patch.
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Dean Nelson <dnelson@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-08-07 06:47:08 +08:00
|
|
|
*
|
|
|
|
* __PG_HWPOISON is exceptional because it needs to be kept beyond page's
|
|
|
|
* alloc-free cycle to prevent from reusing the page.
|
2008-06-10 00:18:45 +08:00
|
|
|
*/
|
mm: check __PG_HWPOISON separately from PAGE_FLAGS_CHECK_AT_*
The race condition addressed in commit add05cecef80 ("mm: soft-offline:
don't free target page in successful page migration") was not closed
completely, because that can happen not only for soft-offline, but also
for hard-offline. Consider that a slab page is about to be freed into
buddy pool, and then an uncorrected memory error hits the page just
after entering __free_one_page(), then VM_BUG_ON_PAGE(page->flags &
PAGE_FLAGS_CHECK_AT_PREP) is triggered, despite the fact that it's not
necessary because the data on the affected page is not consumed.
To solve it, this patch drops __PG_HWPOISON from page flag checks at
allocation/free time. I think it's justified because __PG_HWPOISON
flags is defined to prevent the page from being reused, and setting it
outside the page's alloc-free cycle is a designed behavior (not a bug.)
For recent months, I was annoyed about BUG_ON when soft-offlined page
remains on lru cache list for a while, which is avoided by calling
put_page() instead of putback_lru_page() in page migration's success
path. This means that this patch reverts a major change from commit
add05cecef80 about the new refcounting rule of soft-offlined pages, so
"reuse window" revives. This will be closed by a subsequent patch.
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Dean Nelson <dnelson@redhat.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-08-07 06:47:08 +08:00
|
|
|
#define PAGE_FLAGS_CHECK_AT_PREP \
|
2016-05-21 07:58:16 +08:00
|
|
|
(((1UL << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
|
2008-06-10 00:18:45 +08:00
|
|
|
|
2009-09-22 08:02:59 +08:00
|
|
|
#define PAGE_FLAGS_PRIVATE \
|
2016-05-21 07:58:16 +08:00
|
|
|
(1UL << PG_private | 1UL << PG_private_2)
|
2009-04-03 23:42:36 +08:00
|
|
|
/**
|
|
|
|
* page_has_private - Determine if page has private stuff
|
|
|
|
* @page: The page to be checked
|
|
|
|
*
|
|
|
|
* Determine if a page has private stuff, indicating that release routines
|
|
|
|
* should be invoked upon it.
|
|
|
|
*/
|
2009-09-22 08:02:59 +08:00
|
|
|
static inline int page_has_private(struct page *page)
|
|
|
|
{
|
|
|
|
return !!(page->flags & PAGE_FLAGS_PRIVATE);
|
|
|
|
}
|
|
|
|
|
2016-01-16 08:51:21 +08:00
|
|
|
#undef PF_ANY
|
|
|
|
#undef PF_HEAD
|
|
|
|
#undef PF_NO_TAIL
|
|
|
|
#undef PF_NO_COMPOUND
|
2009-09-22 08:02:59 +08:00
|
|
|
#endif /* !__GENERATING_BOUNDS_H */
|
2009-04-03 23:42:36 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* PAGE_FLAGS_H */
|