linux/mm/mlock.c

865 lines
22 KiB
C
Raw Normal View History

/*
* linux/mm/mlock.c
*
* (C) Copyright 1995 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*/
#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
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
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
2013-09-12 05:22:29 +08:00
#include <linux/pagevec.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
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
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
2013-09-12 05:22:29 +08:00
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
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
#include "internal.h"
int can_do_mlock(void)
{
if (capable(CAP_IPC_LOCK))
return 1;
if (rlimit(RLIMIT_MEMLOCK) != 0)
return 1;
return 0;
}
EXPORT_SYMBOL(can_do_mlock);
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
/*
* Mlocked pages are marked with PageMlocked() flag for efficient testing
* in vmscan and, possibly, the fault path; and to support semi-accurate
* statistics.
*
* An mlocked page [PageMlocked(page)] is unevictable. As such, it will
* be placed on the LRU "unevictable" list, rather than the [in]active lists.
* The unevictable list is an LRU sibling list to the [in]active lists.
* PageUnevictable is set to indicate the unevictable state.
*
* When lazy mlocking via vmscan, it is important to ensure that the
* vma's VM_LOCKED status is not concurrently being modified, otherwise we
* may have mlocked a page that is being munlocked. So lazy mlock must take
* the mmap_sem for read, and verify that the vma really is locked
* (see mm/rmap.c).
*/
/*
* LRU accounting for clear_page_mlock()
*/
mm: use clear_page_mlock() in page_remove_rmap() We had thought that pages could no longer get freed while still marked as mlocked; but Johannes Weiner posted this program to demonstrate that truncating an mlocked private file mapping containing COWed pages is still mishandled: #include <sys/types.h> #include <sys/mman.h> #include <sys/stat.h> #include <stdlib.h> #include <unistd.h> #include <fcntl.h> #include <stdio.h> int main(void) { char *map; int fd; system("grep mlockfreed /proc/vmstat"); fd = open("chigurh", O_CREAT|O_EXCL|O_RDWR); unlink("chigurh"); ftruncate(fd, 4096); map = mmap(NULL, 4096, PROT_WRITE, MAP_PRIVATE, fd, 0); map[0] = 11; mlock(map, sizeof(fd)); ftruncate(fd, 0); close(fd); munlock(map, sizeof(fd)); munmap(map, 4096); system("grep mlockfreed /proc/vmstat"); return 0; } The anon COWed pages are not caught by truncation's clear_page_mlock() of the pagecache pages; but unmap_mapping_range() unmaps them, so we ought to look out for them there in page_remove_rmap(). Indeed, why should truncation or invalidation be doing the clear_page_mlock() when removing from pagecache? mlock is a property of mapping in userspace, not a property of pagecache: an mlocked unmapped page is nonsensical. Reported-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ying Han <yinghan@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:33:19 +08:00
void clear_page_mlock(struct page *page)
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
{
mm: use clear_page_mlock() in page_remove_rmap() We had thought that pages could no longer get freed while still marked as mlocked; but Johannes Weiner posted this program to demonstrate that truncating an mlocked private file mapping containing COWed pages is still mishandled: #include <sys/types.h> #include <sys/mman.h> #include <sys/stat.h> #include <stdlib.h> #include <unistd.h> #include <fcntl.h> #include <stdio.h> int main(void) { char *map; int fd; system("grep mlockfreed /proc/vmstat"); fd = open("chigurh", O_CREAT|O_EXCL|O_RDWR); unlink("chigurh"); ftruncate(fd, 4096); map = mmap(NULL, 4096, PROT_WRITE, MAP_PRIVATE, fd, 0); map[0] = 11; mlock(map, sizeof(fd)); ftruncate(fd, 0); close(fd); munlock(map, sizeof(fd)); munmap(map, 4096); system("grep mlockfreed /proc/vmstat"); return 0; } The anon COWed pages are not caught by truncation's clear_page_mlock() of the pagecache pages; but unmap_mapping_range() unmaps them, so we ought to look out for them there in page_remove_rmap(). Indeed, why should truncation or invalidation be doing the clear_page_mlock() when removing from pagecache? mlock is a property of mapping in userspace, not a property of pagecache: an mlocked unmapped page is nonsensical. Reported-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik van Riel <riel@redhat.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ying Han <yinghan@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-09 07:33:19 +08:00
if (!TestClearPageMlocked(page))
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
return;
mod_zone_page_state(page_zone(page), NR_MLOCK,
-hpage_nr_pages(page));
count_vm_event(UNEVICTABLE_PGCLEARED);
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
if (!isolate_lru_page(page)) {
putback_lru_page(page);
} else {
/*
mm: remove lru_add_drain_all() from the munlock path lockdep warns about following message at boot time on one of my test machine. Then, schedule_on_each_cpu() sholdn't be called when the task have mmap_sem. Actually, lru_add_drain_all() exist to prevent the unevictalble pages stay on reclaimable lru list. but currenct unevictable code can rescue unevictable pages although it stay on reclaimable list. So removing is better. In addition, this patch add lru_add_drain_all() to sys_mlock() and sys_mlockall(). it isn't must. but it reduce the failure of moving to unevictable list. its failure can rescue in vmscan later. but reducing is better. Note, if above rescuing happend, the Mlocked and the Unevictable field mismatching happend in /proc/meminfo. but it doesn't cause any real trouble. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.28-rc2-mm1 #2 ------------------------------------------------------- lvm/1103 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<c0130789>] get_online_cpus+0x29/0x50 but task is already holding lock: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){----}: [<c0153da2>] check_noncircular+0x82/0x110 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156161>] validate_chain+0xb11/0x1070 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab mmap_sem [<c0185e6a>] might_fault+0x4a/0xa0 [<c0185e9b>] might_fault+0x7b/0xa0 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0294dd0>] copy_to_user+0x30/0x60 [<c01ae3ec>] filldir+0x7c/0xd0 [<c01e3a6a>] sysfs_readdir+0x11a/0x1f0 (*) grab sysfs_mutex [<c01ae370>] filldir+0x0/0xd0 [<c01ae370>] filldir+0x0/0xd0 [<c01ae4c6>] vfs_readdir+0x86/0xa0 (*) grab i_mutex [<c01ae75b>] sys_getdents+0x6b/0xc0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff -> #2 (sysfs_mutex){--..}: [<c0153da2>] check_noncircular+0x82/0x110 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156161>] validate_chain+0xb11/0x1070 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab sysfs_mutex [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e422f>] create_dir+0x3f/0x90 [<c01e42a9>] sysfs_create_dir+0x29/0x50 [<c04faaf5>] _spin_unlock+0x25/0x40 [<c028f21d>] kobject_add_internal+0xcd/0x1a0 [<c028f37a>] kobject_set_name_vargs+0x3a/0x50 [<c028f41d>] kobject_init_and_add+0x2d/0x40 [<c019d4d2>] sysfs_slab_add+0xd2/0x180 [<c019d580>] sysfs_add_func+0x0/0x70 [<c019d5dc>] sysfs_add_func+0x5c/0x70 (*) grab slub_lock [<c01400f2>] run_workqueue+0x172/0x200 [<c014008f>] run_workqueue+0x10f/0x200 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0140c6c>] worker_thread+0x9c/0xf0 [<c0143c80>] autoremove_wake_function+0x0/0x50 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0143972>] kthread+0x42/0x70 [<c0143930>] kthread+0x0/0x70 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #1 (slub_lock){----}: [<c0153d2d>] check_noncircular+0xd/0x110 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c0156161>] validate_chain+0xb11/0x1070 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c015433d>] mark_lock+0x35d/0xd00 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04f93a3>] down_read+0x43/0x80 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 (*) grab slub_lock [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04fd9ac>] notifier_call_chain+0x3c/0x70 [<c04f5454>] _cpu_up+0x84/0x110 [<c04f552b>] cpu_up+0x4b/0x70 (*) grab cpu_hotplug.lock [<c06d1530>] kernel_init+0x0/0x170 [<c06d15e5>] kernel_init+0xb5/0x170 [<c06d1530>] kernel_init+0x0/0x170 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #0 (&cpu_hotplug.lock){--..}: [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 (*) grab cpu_hotplug.lock [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 (*) grab mmap_sem [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by lvm/1103: #0: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 stack backtrace: Pid: 1103, comm: lvm Not tainted 2.6.28-rc2-mm1 #2 Call Trace: [<c01555fc>] print_circular_bug_tail+0x7c/0xd0 [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-13 05:26:53 +08:00
* We lost the race. the page already moved to evictable list.
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
*/
mm: remove lru_add_drain_all() from the munlock path lockdep warns about following message at boot time on one of my test machine. Then, schedule_on_each_cpu() sholdn't be called when the task have mmap_sem. Actually, lru_add_drain_all() exist to prevent the unevictalble pages stay on reclaimable lru list. but currenct unevictable code can rescue unevictable pages although it stay on reclaimable list. So removing is better. In addition, this patch add lru_add_drain_all() to sys_mlock() and sys_mlockall(). it isn't must. but it reduce the failure of moving to unevictable list. its failure can rescue in vmscan later. but reducing is better. Note, if above rescuing happend, the Mlocked and the Unevictable field mismatching happend in /proc/meminfo. but it doesn't cause any real trouble. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.28-rc2-mm1 #2 ------------------------------------------------------- lvm/1103 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<c0130789>] get_online_cpus+0x29/0x50 but task is already holding lock: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){----}: [<c0153da2>] check_noncircular+0x82/0x110 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156161>] validate_chain+0xb11/0x1070 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab mmap_sem [<c0185e6a>] might_fault+0x4a/0xa0 [<c0185e9b>] might_fault+0x7b/0xa0 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0294dd0>] copy_to_user+0x30/0x60 [<c01ae3ec>] filldir+0x7c/0xd0 [<c01e3a6a>] sysfs_readdir+0x11a/0x1f0 (*) grab sysfs_mutex [<c01ae370>] filldir+0x0/0xd0 [<c01ae370>] filldir+0x0/0xd0 [<c01ae4c6>] vfs_readdir+0x86/0xa0 (*) grab i_mutex [<c01ae75b>] sys_getdents+0x6b/0xc0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff -> #2 (sysfs_mutex){--..}: [<c0153da2>] check_noncircular+0x82/0x110 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156161>] validate_chain+0xb11/0x1070 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab sysfs_mutex [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e422f>] create_dir+0x3f/0x90 [<c01e42a9>] sysfs_create_dir+0x29/0x50 [<c04faaf5>] _spin_unlock+0x25/0x40 [<c028f21d>] kobject_add_internal+0xcd/0x1a0 [<c028f37a>] kobject_set_name_vargs+0x3a/0x50 [<c028f41d>] kobject_init_and_add+0x2d/0x40 [<c019d4d2>] sysfs_slab_add+0xd2/0x180 [<c019d580>] sysfs_add_func+0x0/0x70 [<c019d5dc>] sysfs_add_func+0x5c/0x70 (*) grab slub_lock [<c01400f2>] run_workqueue+0x172/0x200 [<c014008f>] run_workqueue+0x10f/0x200 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0140c6c>] worker_thread+0x9c/0xf0 [<c0143c80>] autoremove_wake_function+0x0/0x50 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0143972>] kthread+0x42/0x70 [<c0143930>] kthread+0x0/0x70 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #1 (slub_lock){----}: [<c0153d2d>] check_noncircular+0xd/0x110 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c0156161>] validate_chain+0xb11/0x1070 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c015433d>] mark_lock+0x35d/0xd00 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04f93a3>] down_read+0x43/0x80 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 (*) grab slub_lock [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04fd9ac>] notifier_call_chain+0x3c/0x70 [<c04f5454>] _cpu_up+0x84/0x110 [<c04f552b>] cpu_up+0x4b/0x70 (*) grab cpu_hotplug.lock [<c06d1530>] kernel_init+0x0/0x170 [<c06d15e5>] kernel_init+0xb5/0x170 [<c06d1530>] kernel_init+0x0/0x170 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #0 (&cpu_hotplug.lock){--..}: [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 (*) grab cpu_hotplug.lock [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 (*) grab mmap_sem [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by lvm/1103: #0: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 stack backtrace: Pid: 1103, comm: lvm Not tainted 2.6.28-rc2-mm1 #2 Call Trace: [<c01555fc>] print_circular_bug_tail+0x7c/0xd0 [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-13 05:26:53 +08:00
if (PageUnevictable(page))
count_vm_event(UNEVICTABLE_PGSTRANDED);
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
}
}
/*
* Mark page as mlocked if not already.
* If page on LRU, isolate and putback to move to unevictable list.
*/
void mlock_vma_page(struct page *page)
{
BUG_ON(!PageLocked(page));
if (!TestSetPageMlocked(page)) {
mod_zone_page_state(page_zone(page), NR_MLOCK,
hpage_nr_pages(page));
count_vm_event(UNEVICTABLE_PGMLOCKED);
if (!isolate_lru_page(page))
putback_lru_page(page);
}
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
}
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
/*
* Isolate a page from LRU with optional get_page() pin.
* Assumes lru_lock already held and page already pinned.
*/
static bool __munlock_isolate_lru_page(struct page *page, bool getpage)
{
if (PageLRU(page)) {
struct lruvec *lruvec;
lruvec = mem_cgroup_page_lruvec(page, page_zone(page));
if (getpage)
get_page(page);
ClearPageLRU(page);
del_page_from_lru_list(page, lruvec, page_lru(page));
return true;
}
return false;
}
2013-09-12 05:22:29 +08:00
/*
* Finish munlock after successful page isolation
*
* Page must be locked. This is a wrapper for try_to_munlock()
* and putback_lru_page() with munlock accounting.
*/
static void __munlock_isolated_page(struct page *page)
{
int ret = SWAP_AGAIN;
/*
* Optimization: if the page was mapped just once, that's our mapping
* and we don't need to check all the other vmas.
*/
if (page_mapcount(page) > 1)
ret = try_to_munlock(page);
/* Did try_to_unlock() succeed or punt? */
if (ret != SWAP_MLOCK)
count_vm_event(UNEVICTABLE_PGMUNLOCKED);
putback_lru_page(page);
}
/*
* Accounting for page isolation fail during munlock
*
* Performs accounting when page isolation fails in munlock. There is nothing
* else to do because it means some other task has already removed the page
* from the LRU. putback_lru_page() will take care of removing the page from
* the unevictable list, if necessary. vmscan [page_referenced()] will move
* the page back to the unevictable list if some other vma has it mlocked.
*/
static void __munlock_isolation_failed(struct page *page)
{
if (PageUnevictable(page))
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
__count_vm_event(UNEVICTABLE_PGSTRANDED);
2013-09-12 05:22:29 +08:00
else
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
__count_vm_event(UNEVICTABLE_PGMUNLOCKED);
2013-09-12 05:22:29 +08:00
}
/**
* munlock_vma_page - munlock a vma page
mm: munlock: fix a bug where THP tail page is encountered Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. However, when the head page already has PageMlocked unset, it will not skip the tail pages. Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") has added a PageTransHuge() check which contains VM_BUG_ON(PageTail(page)). Sasha Levin found this triggered using trinity, on the first tail page of a THP page without PageMlocked flag. This patch fixes the issue by skipping tail pages also in the case when PageMlocked flag is unset. There is still a possibility of race with THP page split between clearing PageMlocked and determining how many pages to skip. The race might result in former tail pages not being skipped, which is however no longer a bug, as during the skip the PageTail flags are cleared. However this race also affects correctness of NR_MLOCK accounting, which is to be fixed in a separate patch. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-03 04:58:43 +08:00
* @page - page to be unlocked, either a normal page or THP page head
*
* returns the size of the page as a page mask (0 for normal page,
* HPAGE_PMD_NR - 1 for THP head page)
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
*
* called from munlock()/munmap() path with page supposedly on the LRU.
* When we munlock a page, because the vma where we found the page is being
* munlock()ed or munmap()ed, we want to check whether other vmas hold the
* page locked so that we can leave it on the unevictable lru list and not
* bother vmscan with it. However, to walk the page's rmap list in
* try_to_munlock() we must isolate the page from the LRU. If some other
* task has removed the page from the LRU, we won't be able to do that.
* So we clear the PageMlocked as we might not get another chance. If we
* can't isolate the page, we leave it for putback_lru_page() and vmscan
* [page_referenced()/try_to_unmap()] to deal with.
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
*/
unsigned int munlock_vma_page(struct page *page)
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
{
mm: munlock: fix a bug where THP tail page is encountered Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. However, when the head page already has PageMlocked unset, it will not skip the tail pages. Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") has added a PageTransHuge() check which contains VM_BUG_ON(PageTail(page)). Sasha Levin found this triggered using trinity, on the first tail page of a THP page without PageMlocked flag. This patch fixes the issue by skipping tail pages also in the case when PageMlocked flag is unset. There is still a possibility of race with THP page split between clearing PageMlocked and determining how many pages to skip. The race might result in former tail pages not being skipped, which is however no longer a bug, as during the skip the PageTail flags are cleared. However this race also affects correctness of NR_MLOCK accounting, which is to be fixed in a separate patch. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-03 04:58:43 +08:00
unsigned int nr_pages;
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
struct zone *zone = page_zone(page);
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
BUG_ON(!PageLocked(page));
mm: munlock: fix a bug where THP tail page is encountered Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. However, when the head page already has PageMlocked unset, it will not skip the tail pages. Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") has added a PageTransHuge() check which contains VM_BUG_ON(PageTail(page)). Sasha Levin found this triggered using trinity, on the first tail page of a THP page without PageMlocked flag. This patch fixes the issue by skipping tail pages also in the case when PageMlocked flag is unset. There is still a possibility of race with THP page split between clearing PageMlocked and determining how many pages to skip. The race might result in former tail pages not being skipped, which is however no longer a bug, as during the skip the PageTail flags are cleared. However this race also affects correctness of NR_MLOCK accounting, which is to be fixed in a separate patch. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-03 04:58:43 +08:00
/*
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
* Serialize with any parallel __split_huge_page_refcount() which
* might otherwise copy PageMlocked to part of the tail pages before
* we clear it in the head page. It also stabilizes hpage_nr_pages().
mm: munlock: fix a bug where THP tail page is encountered Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. However, when the head page already has PageMlocked unset, it will not skip the tail pages. Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") has added a PageTransHuge() check which contains VM_BUG_ON(PageTail(page)). Sasha Levin found this triggered using trinity, on the first tail page of a THP page without PageMlocked flag. This patch fixes the issue by skipping tail pages also in the case when PageMlocked flag is unset. There is still a possibility of race with THP page split between clearing PageMlocked and determining how many pages to skip. The race might result in former tail pages not being skipped, which is however no longer a bug, as during the skip the PageTail flags are cleared. However this race also affects correctness of NR_MLOCK accounting, which is to be fixed in a separate patch. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-03 04:58:43 +08:00
*/
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
spin_lock_irq(&zone->lru_lock);
nr_pages = hpage_nr_pages(page);
if (!TestClearPageMlocked(page))
goto unlock_out;
__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
if (__munlock_isolate_lru_page(page, true)) {
spin_unlock_irq(&zone->lru_lock);
__munlock_isolated_page(page);
goto out;
}
__munlock_isolation_failed(page);
unlock_out:
spin_unlock_irq(&zone->lru_lock);
out:
mm: munlock: fix a bug where THP tail page is encountered Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. However, when the head page already has PageMlocked unset, it will not skip the tail pages. Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") has added a PageTransHuge() check which contains VM_BUG_ON(PageTail(page)). Sasha Levin found this triggered using trinity, on the first tail page of a THP page without PageMlocked flag. This patch fixes the issue by skipping tail pages also in the case when PageMlocked flag is unset. There is still a possibility of race with THP page split between clearing PageMlocked and determining how many pages to skip. The race might result in former tail pages not being skipped, which is however no longer a bug, as during the skip the PageTail flags are cleared. However this race also affects correctness of NR_MLOCK accounting, which is to be fixed in a separate patch. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-03 04:58:43 +08:00
return nr_pages - 1;
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
}
/**
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
* __mlock_vma_pages_range() - mlock a range of pages in the vma.
* @vma: target vma
* @start: start address
* @end: end address
*
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
* This takes care of making the pages present too.
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
*
* return 0 on success, negative error code on error.
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
*
* vma->vm_mm->mmap_sem must be held for at least read.
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
*/
long __mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, int *nonblocking)
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
{
struct mm_struct *mm = vma->vm_mm;
unsigned long nr_pages = (end - start) / PAGE_SIZE;
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
int gup_flags;
VM_BUG_ON(start & ~PAGE_MASK);
VM_BUG_ON(end & ~PAGE_MASK);
VM_BUG_ON(start < vma->vm_start);
VM_BUG_ON(end > vma->vm_end);
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
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
gup_flags = FOLL_TOUCH | FOLL_MLOCK;
/*
* We want to touch writable mappings with a write fault in order
* to break COW, except for shared mappings because these don't COW
* and we would not want to dirty them for nothing.
*/
if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
gup_flags |= FOLL_WRITE;
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
/*
* We want mlock to succeed for regions that have any permissions
* other than PROT_NONE.
*/
if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
gup_flags |= FOLL_FORCE;
/*
* We made sure addr is within a VMA, so the following will
* not result in a stack expansion that recurses back here.
*/
return __get_user_pages(current, mm, start, nr_pages, gup_flags,
NULL, NULL, nonblocking);
}
/*
* convert get_user_pages() return value to posix mlock() error
*/
static int __mlock_posix_error_return(long retval)
{
if (retval == -EFAULT)
retval = -ENOMEM;
else if (retval == -ENOMEM)
retval = -EAGAIN;
return retval;
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
}
/*
* Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec()
*
* The fast path is available only for evictable pages with single mapping.
* Then we can bypass the per-cpu pvec and get better performance.
* when mapcount > 1 we need try_to_munlock() which can fail.
* when !page_evictable(), we need the full redo logic of putback_lru_page to
* avoid leaving evictable page in unevictable list.
*
* In case of success, @page is added to @pvec and @pgrescued is incremented
* in case that the page was previously unevictable. @page is also unlocked.
*/
static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec,
int *pgrescued)
{
VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
if (page_mapcount(page) <= 1 && page_evictable(page)) {
pagevec_add(pvec, page);
if (TestClearPageUnevictable(page))
(*pgrescued)++;
unlock_page(page);
return true;
}
return false;
}
/*
* Putback multiple evictable pages to the LRU
*
* Batched putback of evictable pages that bypasses the per-cpu pvec. Some of
* the pages might have meanwhile become unevictable but that is OK.
*/
static void __putback_lru_fast(struct pagevec *pvec, int pgrescued)
{
count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec));
/*
*__pagevec_lru_add() calls release_pages() so we don't call
* put_page() explicitly
*/
__pagevec_lru_add(pvec);
count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
}
2013-09-12 05:22:29 +08:00
/*
* Munlock a batch of pages from the same zone
*
* The work is split to two main phases. First phase clears the Mlocked flag
* and attempts to isolate the pages, all under a single zone lru lock.
* The second phase finishes the munlock only for pages where isolation
* succeeded.
*
* Note that the pagevec may be modified during the process.
2013-09-12 05:22:29 +08:00
*/
static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
{
int i;
int nr = pagevec_count(pvec);
int delta_munlocked;
struct pagevec pvec_putback;
int pgrescued = 0;
2013-09-12 05:22:29 +08:00
pagevec_init(&pvec_putback, 0);
2013-09-12 05:22:29 +08:00
/* Phase 1: page isolation */
spin_lock_irq(&zone->lru_lock);
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
if (TestClearPageMlocked(page)) {
/*
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
* We already have pin from follow_page_mask()
* so we can spare the get_page() here.
2013-09-12 05:22:29 +08:00
*/
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
if (__munlock_isolate_lru_page(page, false))
continue;
else
__munlock_isolation_failed(page);
2013-09-12 05:22:29 +08:00
}
mm: munlock: fix potential race with THP page split Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. There is some attempt to prevent bad consequences of racing with a THP page split, but code inspection indicates that there are two problems that may lead to a non-fatal, yet wrong outcome. First, __split_huge_page_refcount() copies flags including PageMlocked from the head page to the tail pages. Clearing PageMlocked by munlock_vma_page() in the middle of this operation might result in part of tail pages left with PageMlocked flag. As the head page still appears to be a THP page until all tail pages are processed, munlock_vma_page() might think it munlocked the whole THP page and skip all the former tail pages. Before ff6a6da60, those pages would be cleared in further iterations of munlock_vma_pages_range(), but NR_MLOCK would still become undercounted (related the next point). Second, NR_MLOCK accounting is based on call to hpage_nr_pages() after the PageMlocked is cleared. The accounting might also become inconsistent due to race with __split_huge_page_refcount() - undercount when HUGE_PMD_NR is subtracted, but some tail pages are left with PageMlocked set and counted again (only possible before ff6a6da60) - overcount when hpage_nr_pages() sees a normal page (split has already finished), but the parallel split has meanwhile cleared PageMlocked from additional tail pages This patch prevents both problems via extending the scope of lru_lock in munlock_vma_page(). This is convenient because: - __split_huge_page_refcount() takes lru_lock for its whole operation - munlock_vma_page() typically takes lru_lock anyway for page isolation As this becomes a second function where page isolation is done with lru_lock already held, factor this out to a new __munlock_isolate_lru_page() function and clean up the code around. [akpm@linux-foundation.org: avoid a coding-style ugly] Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-24 07:52:50 +08:00
/*
* We won't be munlocking this page in the next phase
* but we still need to release the follow_page_mask()
* pin. We cannot do it under lru_lock however. If it's
* the last pin, __page_cache_release() would deadlock.
*/
pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
2013-09-12 05:22:29 +08:00
}
delta_munlocked = -nr + pagevec_count(&pvec_putback);
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
2013-09-12 05:22:29 +08:00
spin_unlock_irq(&zone->lru_lock);
/* Now we can release pins of pages that we are not munlocking */
pagevec_release(&pvec_putback);
/* Phase 2: page munlock */
2013-09-12 05:22:29 +08:00
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
if (page) {
lock_page(page);
if (!__putback_lru_fast_prepare(page, &pvec_putback,
&pgrescued)) {
/*
* Slow path. We don't want to lose the last
* pin before unlock_page()
*/
get_page(page); /* for putback_lru_page() */
__munlock_isolated_page(page);
unlock_page(page);
put_page(page); /* from follow_page_mask() */
}
2013-09-12 05:22:29 +08:00
}
}
/*
* Phase 3: page putback for pages that qualified for the fast path
* This will also call put_page() to return pin from follow_page_mask()
*/
if (pagevec_count(&pvec_putback))
__putback_lru_fast(&pvec_putback, pgrescued);
}
/*
* Fill up pagevec for __munlock_pagevec using pte walk
*
* The function expects that the struct page corresponding to @start address is
* a non-TPH page already pinned and in the @pvec, and that it belongs to @zone.
*
* The rest of @pvec is filled by subsequent pages within the same pmd and same
* zone, as long as the pte's are present and vm_normal_page() succeeds. These
* pages also get pinned.
*
* Returns the address of the next page that should be scanned. This equals
* @start + PAGE_SIZE when no page could be added by the pte walk.
*/
static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
struct vm_area_struct *vma, int zoneid, unsigned long start,
unsigned long end)
{
pte_t *pte;
spinlock_t *ptl;
/*
* Initialize pte walk starting at the already pinned page where we
* are sure that there is a pte, as it was pinned under the same
* mmap_sem write op.
*/
pte = get_locked_pte(vma->vm_mm, start, &ptl);
/* Make sure we do not cross the page table boundary */
end = pgd_addr_end(start, end);
end = pud_addr_end(start, end);
end = pmd_addr_end(start, end);
/* The page next to the pinned page is the first we will try to get */
start += PAGE_SIZE;
while (start < end) {
struct page *page = NULL;
pte++;
if (pte_present(*pte))
page = vm_normal_page(vma, start, *pte);
/*
* Break if page could not be obtained or the page's node+zone does not
* match
*/
if (!page || page_zone_id(page) != zoneid)
break;
get_page(page);
/*
* Increase the address that will be returned *before* the
* eventual break due to pvec becoming full by adding the page
*/
start += PAGE_SIZE;
if (pagevec_add(pvec, page) == 0)
break;
}
pte_unmap_unlock(pte, ptl);
return start;
2013-09-12 05:22:29 +08:00
}
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
/*
* munlock_vma_pages_range() - munlock all pages in the vma range.'
* @vma - vma containing range to be munlock()ed.
* @start - start address in @vma of the range
* @end - end of range in @vma.
*
* For mremap(), munmap() and exit().
*
* Called with @vma VM_LOCKED.
*
* Returns with VM_LOCKED cleared. Callers must be prepared to
* deal with this.
*
* We don't save and restore VM_LOCKED here because pages are
* still on lru. In unmap path, pages might be scanned by reclaim
* and re-mlocked by try_to_{munlock|unmap} before we unmap and
* free them. This will result in freeing mlocked pages.
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
*/
void munlock_vma_pages_range(struct vm_area_struct *vma,
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
unsigned long start, unsigned long end)
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
{
vma->vm_flags &= ~VM_LOCKED;
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
while (start < end) {
struct page *page = NULL;
mm: munlock: fix a bug where THP tail page is encountered Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. However, when the head page already has PageMlocked unset, it will not skip the tail pages. Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") has added a PageTransHuge() check which contains VM_BUG_ON(PageTail(page)). Sasha Levin found this triggered using trinity, on the first tail page of a THP page without PageMlocked flag. This patch fixes the issue by skipping tail pages also in the case when PageMlocked flag is unset. There is still a possibility of race with THP page split between clearing PageMlocked and determining how many pages to skip. The race might result in former tail pages not being skipped, which is however no longer a bug, as during the skip the PageTail flags are cleared. However this race also affects correctness of NR_MLOCK accounting, which is to be fixed in a separate patch. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-03 04:58:43 +08:00
unsigned int page_mask;
unsigned long page_increm;
struct pagevec pvec;
struct zone *zone;
int zoneid;
pagevec_init(&pvec, 0);
/*
* Although FOLL_DUMP is intended for get_dump_page(),
* it just so happens that its special treatment of the
* ZERO_PAGE (returning an error instead of doing get_page)
* suits munlock very well (and if somehow an abnormal page
* has sneaked into the range, we won't oops here: great).
*/
page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
&page_mask);
if (page && !IS_ERR(page)) {
2013-09-12 05:22:29 +08:00
if (PageTransHuge(page)) {
lock_page(page);
/*
* Any THP page found by follow_page_mask() may
* have gotten split before reaching
* munlock_vma_page(), so we need to recompute
* the page_mask here.
*/
page_mask = munlock_vma_page(page);
unlock_page(page);
put_page(page); /* follow_page_mask() */
} else {
/*
* Non-huge pages are handled in batches via
* pagevec. The pin from follow_page_mask()
* prevents them from collapsing by THP.
*/
pagevec_add(&pvec, page);
zone = page_zone(page);
zoneid = page_zone_id(page);
/*
* Try to fill the rest of pagevec using fast
* pte walk. This will also update start to
* the next page to process. Then munlock the
* pagevec.
2013-09-12 05:22:29 +08:00
*/
start = __munlock_pagevec_fill(&pvec, vma,
zoneid, start, end);
__munlock_pagevec(&pvec, zone);
goto next;
2013-09-12 05:22:29 +08:00
}
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
}
mm: munlock: fix a bug where THP tail page is encountered Since commit ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") munlock skips tail pages of a munlocked THP page. However, when the head page already has PageMlocked unset, it will not skip the tail pages. Commit 7225522bb429 ("mm: munlock: batch non-THP page isolation and munlock+putback using pagevec") has added a PageTransHuge() check which contains VM_BUG_ON(PageTail(page)). Sasha Levin found this triggered using trinity, on the first tail page of a THP page without PageMlocked flag. This patch fixes the issue by skipping tail pages also in the case when PageMlocked flag is unset. There is still a possibility of race with THP page split between clearing PageMlocked and determining how many pages to skip. The race might result in former tail pages not being skipped, which is however no longer a bug, as during the skip the PageTail flags are cleared. However this race also affects correctness of NR_MLOCK accounting, which is to be fixed in a separate patch. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Hugh Dickins <hughd@google.com> Cc: Bob Liu <bob.liu@oracle.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-03 04:58:43 +08:00
/* It's a bug to munlock in the middle of a THP page */
VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
page_increm = 1 + page_mask;
start += page_increm * PAGE_SIZE;
next:
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
cond_resched();
}
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
}
/*
* mlock_fixup - handle mlock[all]/munlock[all] requests.
*
* Filters out "special" vmas -- VM_LOCKED never gets set for these, and
* munlock is a no-op. However, for some special vmas, we go ahead and
* populate the ptes.
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
*
* For vmas that pass the filters, merge/split as appropriate.
*/
static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
unsigned long start, unsigned long end, vm_flags_t newflags)
{
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
struct mm_struct *mm = vma->vm_mm;
pgoff_t pgoff;
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
int nr_pages;
int ret = 0;
int lock = !!(newflags & VM_LOCKED);
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm))
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
goto out; /* don't set VM_LOCKED, don't count */
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma));
if (*prev) {
vma = *prev;
goto success;
}
if (start != vma->vm_start) {
ret = split_vma(mm, vma, start, 1);
if (ret)
goto out;
}
if (end != vma->vm_end) {
ret = split_vma(mm, vma, end, 0);
if (ret)
goto out;
}
success:
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
/*
* Keep track of amount of locked VM.
*/
nr_pages = (end - start) >> PAGE_SHIFT;
if (!lock)
nr_pages = -nr_pages;
mm->locked_vm += nr_pages;
/*
* vm_flags is protected by the mmap_sem held in write mode.
* It's okay if try_to_unmap_one unmaps a page just after we
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
* set VM_LOCKED, __mlock_vma_pages_range will bring it back.
*/
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
if (lock)
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
vma->vm_flags = newflags;
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
else
mm: munlock use follow_page Hiroaki Wakabayashi points out that when mlock() has been interrupted by SIGKILL, the subsequent munlock() takes unnecessarily long because its use of __get_user_pages() insists on faulting in all the pages which mlock() never reached. It's worse than slowness if mlock() is terminated by Out Of Memory kill: the munlock_vma_pages_all() in exit_mmap() insists on faulting in all the pages which mlock() could not find memory for; so innocent bystanders are killed too, and perhaps the system hangs. __get_user_pages() does a lot that's silly for munlock(): so remove the munlock option from __mlock_vma_pages_range(), and use a simple loop of follow_page()s in munlock_vma_pages_range() instead; ignoring absent pages, and not marking present pages as accessed or dirty. (Change munlock() to only go so far as mlock() reached? That does not work out, given the convention that mlock() claims complete success even when it has to give up early - in part so that an underlying file can be extended later, and those pages locked which earlier would give SIGBUS.) Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: <stable@kernel.org> Acked-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Hiroaki Wakabayashi <primulaelatior@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-09-22 08:03:23 +08:00
munlock_vma_pages_range(vma, start, end);
out:
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
*prev = vma;
return ret;
}
static int do_mlock(unsigned long start, size_t len, int on)
{
unsigned long nstart, end, tmp;
struct vm_area_struct * vma, * prev;
int error;
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
VM_BUG_ON(start & ~PAGE_MASK);
VM_BUG_ON(len != PAGE_ALIGN(len));
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
vma = find_vma(current->mm, start);
if (!vma || vma->vm_start > start)
return -ENOMEM;
prev = vma->vm_prev;
if (start > vma->vm_start)
prev = vma;
for (nstart = start ; ; ) {
vm_flags_t newflags;
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
newflags = vma->vm_flags & ~VM_LOCKED;
if (on)
newflags |= VM_LOCKED;
tmp = vma->vm_end;
if (tmp > end)
tmp = end;
error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
if (error)
break;
nstart = tmp;
if (nstart < prev->vm_end)
nstart = prev->vm_end;
if (nstart >= end)
break;
vma = prev->vm_next;
if (!vma || vma->vm_start != nstart) {
error = -ENOMEM;
break;
}
}
return error;
}
/*
* __mm_populate - populate and/or mlock pages within a range of address space.
*
* This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
* flags. VMAs must be already marked with the desired vm_flags, and
* mmap_sem must not be held.
*/
int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
{
struct mm_struct *mm = current->mm;
unsigned long end, nstart, nend;
struct vm_area_struct *vma = NULL;
int locked = 0;
long ret = 0;
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
VM_BUG_ON(start & ~PAGE_MASK);
VM_BUG_ON(len != PAGE_ALIGN(len));
end = start + len;
for (nstart = start; nstart < end; nstart = nend) {
/*
* We want to fault in pages for [nstart; end) address range.
* Find first corresponding VMA.
*/
if (!locked) {
locked = 1;
down_read(&mm->mmap_sem);
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
vma = find_vma(mm, nstart);
} else if (nstart >= vma->vm_end)
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
vma = vma->vm_next;
if (!vma || vma->vm_start >= end)
break;
/*
* Set [nstart; nend) to intersection of desired address
* range with the first VMA. Also, skip undesirable VMA types.
*/
nend = min(end, vma->vm_end);
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
continue;
if (nstart < vma->vm_start)
nstart = vma->vm_start;
/*
* Now fault in a range of pages. __mlock_vma_pages_range()
* double checks the vma flags, so that it won't mlock pages
* if the vma was already munlocked.
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
*/
ret = __mlock_vma_pages_range(vma, nstart, nend, &locked);
if (ret < 0) {
if (ignore_errors) {
ret = 0;
continue; /* continue at next VMA */
}
ret = __mlock_posix_error_return(ret);
break;
}
nend = nstart + ret * PAGE_SIZE;
ret = 0;
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
}
if (locked)
up_read(&mm->mmap_sem);
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
return ret; /* 0 or negative error code */
}
SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
unsigned long locked;
unsigned long lock_limit;
int error = -ENOMEM;
if (!can_do_mlock())
return -EPERM;
mm: remove lru_add_drain_all() from the munlock path lockdep warns about following message at boot time on one of my test machine. Then, schedule_on_each_cpu() sholdn't be called when the task have mmap_sem. Actually, lru_add_drain_all() exist to prevent the unevictalble pages stay on reclaimable lru list. but currenct unevictable code can rescue unevictable pages although it stay on reclaimable list. So removing is better. In addition, this patch add lru_add_drain_all() to sys_mlock() and sys_mlockall(). it isn't must. but it reduce the failure of moving to unevictable list. its failure can rescue in vmscan later. but reducing is better. Note, if above rescuing happend, the Mlocked and the Unevictable field mismatching happend in /proc/meminfo. but it doesn't cause any real trouble. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.28-rc2-mm1 #2 ------------------------------------------------------- lvm/1103 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<c0130789>] get_online_cpus+0x29/0x50 but task is already holding lock: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){----}: [<c0153da2>] check_noncircular+0x82/0x110 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156161>] validate_chain+0xb11/0x1070 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab mmap_sem [<c0185e6a>] might_fault+0x4a/0xa0 [<c0185e9b>] might_fault+0x7b/0xa0 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0294dd0>] copy_to_user+0x30/0x60 [<c01ae3ec>] filldir+0x7c/0xd0 [<c01e3a6a>] sysfs_readdir+0x11a/0x1f0 (*) grab sysfs_mutex [<c01ae370>] filldir+0x0/0xd0 [<c01ae370>] filldir+0x0/0xd0 [<c01ae4c6>] vfs_readdir+0x86/0xa0 (*) grab i_mutex [<c01ae75b>] sys_getdents+0x6b/0xc0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff -> #2 (sysfs_mutex){--..}: [<c0153da2>] check_noncircular+0x82/0x110 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156161>] validate_chain+0xb11/0x1070 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab sysfs_mutex [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e422f>] create_dir+0x3f/0x90 [<c01e42a9>] sysfs_create_dir+0x29/0x50 [<c04faaf5>] _spin_unlock+0x25/0x40 [<c028f21d>] kobject_add_internal+0xcd/0x1a0 [<c028f37a>] kobject_set_name_vargs+0x3a/0x50 [<c028f41d>] kobject_init_and_add+0x2d/0x40 [<c019d4d2>] sysfs_slab_add+0xd2/0x180 [<c019d580>] sysfs_add_func+0x0/0x70 [<c019d5dc>] sysfs_add_func+0x5c/0x70 (*) grab slub_lock [<c01400f2>] run_workqueue+0x172/0x200 [<c014008f>] run_workqueue+0x10f/0x200 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0140c6c>] worker_thread+0x9c/0xf0 [<c0143c80>] autoremove_wake_function+0x0/0x50 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0143972>] kthread+0x42/0x70 [<c0143930>] kthread+0x0/0x70 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #1 (slub_lock){----}: [<c0153d2d>] check_noncircular+0xd/0x110 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c0156161>] validate_chain+0xb11/0x1070 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c015433d>] mark_lock+0x35d/0xd00 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04f93a3>] down_read+0x43/0x80 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 (*) grab slub_lock [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04fd9ac>] notifier_call_chain+0x3c/0x70 [<c04f5454>] _cpu_up+0x84/0x110 [<c04f552b>] cpu_up+0x4b/0x70 (*) grab cpu_hotplug.lock [<c06d1530>] kernel_init+0x0/0x170 [<c06d15e5>] kernel_init+0xb5/0x170 [<c06d1530>] kernel_init+0x0/0x170 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #0 (&cpu_hotplug.lock){--..}: [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 (*) grab cpu_hotplug.lock [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 (*) grab mmap_sem [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by lvm/1103: #0: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 stack backtrace: Pid: 1103, comm: lvm Not tainted 2.6.28-rc2-mm1 #2 Call Trace: [<c01555fc>] print_circular_bug_tail+0x7c/0xd0 [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-13 05:26:53 +08:00
lru_add_drain_all(); /* flush pagevec */
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
locked = len >> PAGE_SHIFT;
down_write(&current->mm->mmap_sem);
locked += current->mm->locked_vm;
/* check against resource limits */
if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
error = do_mlock(start, len, 1);
up_write(&current->mm->mmap_sem);
mlock: only hold mmap_sem in shared mode when faulting in pages Currently mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time, during which various commands such as 'ps auxw' will block. This makes sysadmins unhappy: real 14m36.232s user 0m0.003s sys 0m0.015s (output from 'time ps auxw' while a 20GB file was being mlocked without being previously preloaded into page cache) I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages, in small batches, releasing mmap_sem when we block on disk access or when we detect some contention. This patch: Before this change, mlock() holds mmap_sem in exclusive mode while the pages get faulted in. In the case of a large mlock, this can potentially take a very long time. Various things will block while mmap_sem is held, including 'ps auxw'. This can make sysadmins angry. I propose that mlock() could release mmap_sem after the VM_LOCKED bits have been set in all appropriate VMAs. Then a second pass could be done to actually mlock the pages with mmap_sem held for reads only. We need to recheck the vma flags after we re-acquire mmap_sem, but this is easy. In the case where a vma has been munlocked before mlock completes, pages that were already marked as PageMlocked() are handled by the munlock() call, and mlock() is careful to not mark new page batches as PageMlocked() after the munlock() call has cleared the VM_LOCKED vma flags. So, the end result will be identical to what'd happen if munlock() had executed after the mlock() call. In a later change, I will allow the second pass to release mmap_sem when blocking on disk accesses or when it is otherwise contended, so that it won't be held for long periods of time even in shared mode. Signed-off-by: Michel Lespinasse <walken@google.com> Tested-by: Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Nick Piggin <npiggin@kernel.dk> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-01-14 07:46:10 +08:00
if (!error)
error = __mm_populate(start, len, 0);
return error;
}
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
down_write(&current->mm->mmap_sem);
ret = do_mlock(start, len, 0);
up_write(&current->mm->mmap_sem);
return ret;
}
static int do_mlockall(int flags)
{
struct vm_area_struct * vma, * prev = NULL;
if (flags & MCL_FUTURE)
current->mm->def_flags |= VM_LOCKED;
else
current->mm->def_flags &= ~VM_LOCKED;
if (flags == MCL_FUTURE)
goto out;
for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
vm_flags_t newflags;
newflags = vma->vm_flags & ~VM_LOCKED;
if (flags & MCL_CURRENT)
newflags |= VM_LOCKED;
/* Ignore errors */
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
cond_resched();
}
out:
return 0;
}
SYSCALL_DEFINE1(mlockall, int, flags)
{
unsigned long lock_limit;
int ret = -EINVAL;
if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
goto out;
ret = -EPERM;
if (!can_do_mlock())
goto out;
if (flags & MCL_CURRENT)
lru_add_drain_all(); /* flush pagevec */
mm: remove lru_add_drain_all() from the munlock path lockdep warns about following message at boot time on one of my test machine. Then, schedule_on_each_cpu() sholdn't be called when the task have mmap_sem. Actually, lru_add_drain_all() exist to prevent the unevictalble pages stay on reclaimable lru list. but currenct unevictable code can rescue unevictable pages although it stay on reclaimable list. So removing is better. In addition, this patch add lru_add_drain_all() to sys_mlock() and sys_mlockall(). it isn't must. but it reduce the failure of moving to unevictable list. its failure can rescue in vmscan later. but reducing is better. Note, if above rescuing happend, the Mlocked and the Unevictable field mismatching happend in /proc/meminfo. but it doesn't cause any real trouble. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.28-rc2-mm1 #2 ------------------------------------------------------- lvm/1103 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<c0130789>] get_online_cpus+0x29/0x50 but task is already holding lock: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){----}: [<c0153da2>] check_noncircular+0x82/0x110 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156161>] validate_chain+0xb11/0x1070 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab mmap_sem [<c0185e6a>] might_fault+0x4a/0xa0 [<c0185e9b>] might_fault+0x7b/0xa0 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0294dd0>] copy_to_user+0x30/0x60 [<c01ae3ec>] filldir+0x7c/0xd0 [<c01e3a6a>] sysfs_readdir+0x11a/0x1f0 (*) grab sysfs_mutex [<c01ae370>] filldir+0x0/0xd0 [<c01ae370>] filldir+0x0/0xd0 [<c01ae4c6>] vfs_readdir+0x86/0xa0 (*) grab i_mutex [<c01ae75b>] sys_getdents+0x6b/0xc0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff -> #2 (sysfs_mutex){--..}: [<c0153da2>] check_noncircular+0x82/0x110 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156161>] validate_chain+0xb11/0x1070 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab sysfs_mutex [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e422f>] create_dir+0x3f/0x90 [<c01e42a9>] sysfs_create_dir+0x29/0x50 [<c04faaf5>] _spin_unlock+0x25/0x40 [<c028f21d>] kobject_add_internal+0xcd/0x1a0 [<c028f37a>] kobject_set_name_vargs+0x3a/0x50 [<c028f41d>] kobject_init_and_add+0x2d/0x40 [<c019d4d2>] sysfs_slab_add+0xd2/0x180 [<c019d580>] sysfs_add_func+0x0/0x70 [<c019d5dc>] sysfs_add_func+0x5c/0x70 (*) grab slub_lock [<c01400f2>] run_workqueue+0x172/0x200 [<c014008f>] run_workqueue+0x10f/0x200 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0140c6c>] worker_thread+0x9c/0xf0 [<c0143c80>] autoremove_wake_function+0x0/0x50 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0143972>] kthread+0x42/0x70 [<c0143930>] kthread+0x0/0x70 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #1 (slub_lock){----}: [<c0153d2d>] check_noncircular+0xd/0x110 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c0156161>] validate_chain+0xb11/0x1070 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c015433d>] mark_lock+0x35d/0xd00 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04f93a3>] down_read+0x43/0x80 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 (*) grab slub_lock [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04fd9ac>] notifier_call_chain+0x3c/0x70 [<c04f5454>] _cpu_up+0x84/0x110 [<c04f552b>] cpu_up+0x4b/0x70 (*) grab cpu_hotplug.lock [<c06d1530>] kernel_init+0x0/0x170 [<c06d15e5>] kernel_init+0xb5/0x170 [<c06d1530>] kernel_init+0x0/0x170 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #0 (&cpu_hotplug.lock){--..}: [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 (*) grab cpu_hotplug.lock [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 (*) grab mmap_sem [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by lvm/1103: #0: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 stack backtrace: Pid: 1103, comm: lvm Not tainted 2.6.28-rc2-mm1 #2 Call Trace: [<c01555fc>] print_circular_bug_tail+0x7c/0xd0 [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-13 05:26:53 +08:00
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
ret = -ENOMEM;
down_write(&current->mm->mmap_sem);
if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
capable(CAP_IPC_LOCK))
ret = do_mlockall(flags);
up_write(&current->mm->mmap_sem);
if (!ret && (flags & MCL_CURRENT))
mm_populate(0, TASK_SIZE);
out:
return ret;
}
SYSCALL_DEFINE0(munlockall)
{
int ret;
down_write(&current->mm->mmap_sem);
ret = do_mlockall(0);
up_write(&current->mm->mmap_sem);
return ret;
}
/*
* Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
* shm segments) get accounted against the user_struct instead.
*/
static DEFINE_SPINLOCK(shmlock_user_lock);
int user_shm_lock(size_t size, struct user_struct *user)
{
unsigned long lock_limit, locked;
int allowed = 0;
locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
lock_limit = rlimit(RLIMIT_MEMLOCK);
if (lock_limit == RLIM_INFINITY)
allowed = 1;
lock_limit >>= PAGE_SHIFT;
spin_lock(&shmlock_user_lock);
if (!allowed &&
locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
goto out;
get_uid(user);
user->locked_shm += locked;
allowed = 1;
out:
spin_unlock(&shmlock_user_lock);
return allowed;
}
void user_shm_unlock(size_t size, struct user_struct *user)
{
spin_lock(&shmlock_user_lock);
user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
spin_unlock(&shmlock_user_lock);
free_uid(user);
}