WSL2-Linux-Kernel/mm/mlock.c

651 строка
16 KiB
C
Исходник Обычный вид История

/*
* 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 07:26:44 +04:00
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/module.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 07:26:44 +04:00
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include "internal.h"
int can_do_mlock(void)
{
if (capable(CAP_IPC_LOCK))
return 1;
if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 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 07:26:44 +04:00
/*
* 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()
*/
void __clear_page_mlock(struct page *page)
{
VM_BUG_ON(!PageLocked(page));
if (!page->mapping) { /* truncated ? */
return;
}
dec_zone_page_state(page, NR_MLOCK);
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 07:26:44 +04:00
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 00:26:53 +03:00
* 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 07:26:44 +04:00
*/
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 00:26:53 +03:00
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 07:26:44 +04:00
}
}
/*
* 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)) {
inc_zone_page_state(page, NR_MLOCK);
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 07:26:44 +04:00
}
/**
* munlock_vma_page - munlock a vma page
* @page - page to be unlocked
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 07:26:44 +04:00
*
* 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 07:26:44 +04:00
*/
void 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 07:26:44 +04:00
{
BUG_ON(!PageLocked(page));
if (TestClearPageMlocked(page)) {
dec_zone_page_state(page, NR_MLOCK);
if (!isolate_lru_page(page)) {
int ret = try_to_munlock(page);
/*
* did try_to_unlock() succeed or punt?
*/
mm: mlocking in try_to_unmap_one There's contorted mlock/munlock handling in try_to_unmap_anon() and try_to_unmap_file(), which we'd prefer not to repeat for KSM swapping. Simplify it by moving it all down into try_to_unmap_one(). One thing is then lost, try_to_munlock()'s distinction between when no vma holds the page mlocked, and when a vma does mlock it, but we could not get mmap_sem to set the page flag. But its only caller takes no interest in that distinction (and is better testing SWAP_MLOCK anyway), so let's keep the code simple and return SWAP_AGAIN for both cases. try_to_unmap_file()'s TTU_MUNLOCK nonlinear handling was particularly amusing: once unravelled, it turns out to have been choosing between two different ways of doing the same nothing. Ah, no, one way was actually returning SWAP_FAIL when it meant to return SWAP_SUCCESS. [kosaki.motohiro@jp.fujitsu.com: comment adding to mlocking in try_to_unmap_one] [akpm@linux-foundation.org: remove test of MLOCK_PAGES] Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk> Cc: Izik Eidus <ieidus@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Rik van Riel <riel@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Minchan Kim <minchan.kim@gmail.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Andi Kleen <andi@firstfloor.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-15 04:58:58 +03:00
if (ret != SWAP_MLOCK)
count_vm_event(UNEVICTABLE_PGMUNLOCKED);
putback_lru_page(page);
} else {
/*
* Some other task has 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.
*/
if (PageUnevictable(page))
count_vm_event(UNEVICTABLE_PGSTRANDED);
else
count_vm_event(UNEVICTABLE_PGMUNLOCKED);
}
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 07:26:44 +04:00
}
}
/**
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 04:03:23 +04:00
* __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 04:03:23 +04:00
* 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 07:26:44 +04:00
*
* 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 07:26:44 +04:00
*
* 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 07:26:44 +04:00
*/
static long __mlock_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 04:03:23 +04:00
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 07:26:44 +04:00
{
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = start;
struct page *pages[16]; /* 16 gives a reasonable batch */
int nr_pages = (end - start) / PAGE_SIZE;
int ret = 0;
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 04:03:23 +04:00
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 04:03:23 +04:00
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 07:26:44 +04:00
gup_flags = FOLL_TOUCH | FOLL_GET;
if (vma->vm_flags & 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 07:26:44 +04:00
while (nr_pages > 0) {
int i;
cond_resched();
/*
* get_user_pages makes pages present if we are
* setting mlock. and this extra reference count will
* disable migration of this page. However, page may
* still be truncated out from under us.
*/
ret = __get_user_pages(current, mm, addr,
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 07:26:44 +04:00
min_t(int, nr_pages, ARRAY_SIZE(pages)),
gup_flags, pages, NULL);
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 07:26:44 +04:00
/*
* This can happen for, e.g., VM_NONLINEAR regions before
* a page has been allocated and mapped at a given offset,
* or for addresses that map beyond end of a file.
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 04:03:23 +04:00
* We'll mlock the pages if/when they get faulted in.
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 07:26:44 +04:00
*/
if (ret < 0)
break;
lru_add_drain(); /* push cached pages to LRU */
for (i = 0; i < ret; i++) {
struct page *page = pages[i];
if (page->mapping) {
/*
* That preliminary check is mainly to avoid
* the pointless overhead of lock_page on the
* ZERO_PAGE: which might bounce very badly if
* there is contention. However, we're still
* dirtying its cacheline with get/put_page:
* we'll add another __get_user_pages flag to
* avoid it if that case turns out to matter.
*/
lock_page(page);
/*
* Because we lock page here and migration is
* blocked by the elevated reference, we need
* only check for file-cache page truncation.
*/
if (page->mapping)
mlock_vma_page(page);
unlock_page(page);
}
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 04:03:23 +04:00
put_page(page); /* ref from get_user_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 07:26:44 +04:00
}
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 04:03:23 +04:00
addr += ret * PAGE_SIZE;
nr_pages -= ret;
ret = 0;
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 07:26:44 +04:00
}
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 04:03:23 +04:00
return ret; /* 0 or negative error code */
}
/*
* 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 07:26:44 +04:00
}
/**
* mlock_vma_pages_range() - mlock pages in specified vma range.
* @vma - the vma containing the specfied address range
* @start - starting address in @vma to mlock
* @end - end address [+1] in @vma to mlock
*
* For mmap()/mremap()/expansion of mlocked vma.
*
* return 0 on success for "normal" vmas.
*
* return number of pages [> 0] to be removed from locked_vm on success
* of "special" vmas.
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 07:26:44 +04:00
*/
long mlock_vma_pages_range(struct vm_area_struct *vma,
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 07:26:44 +04:00
unsigned long start, unsigned long end)
{
int nr_pages = (end - start) / PAGE_SIZE;
BUG_ON(!(vma->vm_flags & VM_LOCKED));
/*
* filter unlockable vmas
*/
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
goto no_mlock;
if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
is_vm_hugetlb_page(vma) ||
mlock: downgrade mmap sem while populating mlocked regions We need to hold the mmap_sem for write to initiatate mlock()/munlock() because we may need to merge/split vmas. However, this can lead to very long lock hold times attempting to fault in a large memory region to mlock it into memory. This can hold off other faults against the mm [multithreaded tasks] and other scans of the mm, such as via /proc. To alleviate this, downgrade the mmap_sem to read mode during the population of the region for locking. This is especially the case if we need to reclaim memory to lock down the region. We [probably?] don't need to do this for unlocking as all of the pages should be resident--they're already mlocked. Now, the caller's of the mlock functions [mlock_fixup() and mlock_vma_pages_range()] expect the mmap_sem to be returned in write mode. Changing all callers appears to be way too much effort at this point. So, restore write mode before returning. Note that this opens a window where the mmap list could change in a multithreaded process. So, at least for mlock_fixup(), where we could be called in a loop over multiple vmas, we check that a vma still exists at the start address and that vma still covers the page range [start,end). If not, we return an error, -EAGAIN, and let the caller deal with it. Return -EAGAIN from mlock_vma_pages_range() function and mlock_fixup() if the vma at 'start' disappears or changes so that the page range [start,end) is no longer contained in the vma. Again, let the caller deal with it. Looks like only sys_remap_file_pages() [via mmap_region()] should actually care. With this patch, I no longer see processes like ps(1) blocked for seconds or minutes at a time waiting for a large [multiple gigabyte] region to be locked down. However, I occassionally see delays while unlocking or unmapping a large mlocked region. Should we also downgrade the mmap_sem for the unlock path? Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:49 +04:00
vma == get_gate_vma(current))) {
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 04:03:23 +04:00
__mlock_vma_pages_range(vma, start, end);
/* Hide errors from mmap() and other callers */
return 0;
mlock: downgrade mmap sem while populating mlocked regions We need to hold the mmap_sem for write to initiatate mlock()/munlock() because we may need to merge/split vmas. However, this can lead to very long lock hold times attempting to fault in a large memory region to mlock it into memory. This can hold off other faults against the mm [multithreaded tasks] and other scans of the mm, such as via /proc. To alleviate this, downgrade the mmap_sem to read mode during the population of the region for locking. This is especially the case if we need to reclaim memory to lock down the region. We [probably?] don't need to do this for unlocking as all of the pages should be resident--they're already mlocked. Now, the caller's of the mlock functions [mlock_fixup() and mlock_vma_pages_range()] expect the mmap_sem to be returned in write mode. Changing all callers appears to be way too much effort at this point. So, restore write mode before returning. Note that this opens a window where the mmap list could change in a multithreaded process. So, at least for mlock_fixup(), where we could be called in a loop over multiple vmas, we check that a vma still exists at the start address and that vma still covers the page range [start,end). If not, we return an error, -EAGAIN, and let the caller deal with it. Return -EAGAIN from mlock_vma_pages_range() function and mlock_fixup() if the vma at 'start' disappears or changes so that the page range [start,end) is no longer contained in the vma. Again, let the caller deal with it. Looks like only sys_remap_file_pages() [via mmap_region()] should actually care. With this patch, I no longer see processes like ps(1) blocked for seconds or minutes at a time waiting for a large [multiple gigabyte] region to be locked down. However, I occassionally see delays while unlocking or unmapping a large mlocked region. Should we also downgrade the mmap_sem for the unlock path? Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:49 +04:00
}
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 07:26:44 +04:00
/*
* User mapped kernel pages or huge pages:
* make these pages present to populate the ptes, but
* fall thru' to reset VM_LOCKED--no need to unlock, and
* return nr_pages so these don't get counted against task's
* locked limit. huge pages are already counted against
* locked vm limit.
*/
make_pages_present(start, end);
no_mlock:
vma->vm_flags &= ~VM_LOCKED; /* and don't come back! */
return nr_pages; /* error or pages NOT mlocked */
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 07:26:44 +04:00
}
/*
* 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 07:26:44 +04:00
*/
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 04:03:23 +04:00
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 07:26:44 +04:00
{
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 04:03:23 +04:00
unsigned long addr;
lru_add_drain();
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 07:26:44 +04:00
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 04:03:23 +04:00
for (addr = start; addr < end; addr += PAGE_SIZE) {
struct page *page;
/*
* 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(vma, addr, FOLL_GET | FOLL_DUMP);
if (page && !IS_ERR(page)) {
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 04:03:23 +04:00
lock_page(page);
/*
* Like in __mlock_vma_pages_range(),
* because we lock page here and migration is
* blocked by the elevated reference, we need
* only check for file-cache page truncation.
*/
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 04:03:23 +04:00
if (page->mapping)
munlock_vma_page(page);
unlock_page(page);
put_page(page);
}
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 07:26:44 +04:00
}
/*
* 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 via make_pages_present().
*
* 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, unsigned int 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 07:26:44 +04:00
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 07:26:44 +04:00
int nr_pages;
int ret = 0;
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 07:26:44 +04:00
int lock = newflags & VM_LOCKED;
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 07:26:44 +04:00
if (newflags == vma->vm_flags ||
(vma->vm_flags & (VM_IO | VM_PFNMAP)))
goto out; /* don't set VM_LOCKED, don't count */
if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
is_vm_hugetlb_page(vma) ||
vma == get_gate_vma(current)) {
if (lock)
make_pages_present(start, end);
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 07:26:44 +04:00
/*
* 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 07:26:44 +04:00
* set VM_LOCKED, __mlock_vma_pages_range will bring it back.
*/
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 07:26:44 +04:00
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 04:03:23 +04:00
vma->vm_flags = newflags;
ret = __mlock_vma_pages_range(vma, start, end);
if (ret < 0)
ret = __mlock_posix_error_return(ret);
mlock: downgrade mmap sem while populating mlocked regions We need to hold the mmap_sem for write to initiatate mlock()/munlock() because we may need to merge/split vmas. However, this can lead to very long lock hold times attempting to fault in a large memory region to mlock it into memory. This can hold off other faults against the mm [multithreaded tasks] and other scans of the mm, such as via /proc. To alleviate this, downgrade the mmap_sem to read mode during the population of the region for locking. This is especially the case if we need to reclaim memory to lock down the region. We [probably?] don't need to do this for unlocking as all of the pages should be resident--they're already mlocked. Now, the caller's of the mlock functions [mlock_fixup() and mlock_vma_pages_range()] expect the mmap_sem to be returned in write mode. Changing all callers appears to be way too much effort at this point. So, restore write mode before returning. Note that this opens a window where the mmap list could change in a multithreaded process. So, at least for mlock_fixup(), where we could be called in a loop over multiple vmas, we check that a vma still exists at the start address and that vma still covers the page range [start,end). If not, we return an error, -EAGAIN, and let the caller deal with it. Return -EAGAIN from mlock_vma_pages_range() function and mlock_fixup() if the vma at 'start' disappears or changes so that the page range [start,end) is no longer contained in the vma. Again, let the caller deal with it. Looks like only sys_remap_file_pages() [via mmap_region()] should actually care. With this patch, I no longer see processes like ps(1) blocked for seconds or minutes at a time waiting for a large [multiple gigabyte] region to be locked down. However, I occassionally see delays while unlocking or unmapping a large mlocked region. Should we also downgrade the mmap_sem for the unlock path? Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:49 +04:00
} 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 04:03:23 +04:00
munlock_vma_pages_range(vma, start, end);
mlock: downgrade mmap sem while populating mlocked regions We need to hold the mmap_sem for write to initiatate mlock()/munlock() because we may need to merge/split vmas. However, this can lead to very long lock hold times attempting to fault in a large memory region to mlock it into memory. This can hold off other faults against the mm [multithreaded tasks] and other scans of the mm, such as via /proc. To alleviate this, downgrade the mmap_sem to read mode during the population of the region for locking. This is especially the case if we need to reclaim memory to lock down the region. We [probably?] don't need to do this for unlocking as all of the pages should be resident--they're already mlocked. Now, the caller's of the mlock functions [mlock_fixup() and mlock_vma_pages_range()] expect the mmap_sem to be returned in write mode. Changing all callers appears to be way too much effort at this point. So, restore write mode before returning. Note that this opens a window where the mmap list could change in a multithreaded process. So, at least for mlock_fixup(), where we could be called in a loop over multiple vmas, we check that a vma still exists at the start address and that vma still covers the page range [start,end). If not, we return an error, -EAGAIN, and let the caller deal with it. Return -EAGAIN from mlock_vma_pages_range() function and mlock_fixup() if the vma at 'start' disappears or changes so that the page range [start,end) is no longer contained in the vma. Again, let the caller deal with it. Looks like only sys_remap_file_pages() [via mmap_region()] should actually care. With this patch, I no longer see processes like ps(1) blocked for seconds or minutes at a time waiting for a large [multiple gigabyte] region to be locked down. However, I occassionally see delays while unlocking or unmapping a large mlocked region. Should we also downgrade the mmap_sem for the unlock path? Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 07:26:49 +04:00
}
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 07:26:44 +04:00
*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;
len = PAGE_ALIGN(len);
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
vma = find_vma_prev(current->mm, start, &prev);
if (!vma || vma->vm_start > start)
return -ENOMEM;
if (start > vma->vm_start)
prev = vma;
for (nstart = start ; ; ) {
unsigned int 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;
}
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 00:26:53 +03:00
lru_add_drain_all(); /* flush pagevec */
down_write(&current->mm->mmap_sem);
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
locked = len >> PAGE_SHIFT;
locked += current->mm->locked_vm;
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
lock_limit >>= PAGE_SHIFT;
/* check against resource limits */
if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
error = do_mlock(start, len, 1);
up_write(&current->mm->mmap_sem);
return error;
}
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
down_write(&current->mm->mmap_sem);
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
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;
unsigned int def_flags = 0;
if (flags & MCL_FUTURE)
def_flags = VM_LOCKED;
current->mm->def_flags = def_flags;
if (flags == MCL_FUTURE)
goto out;
for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
unsigned int 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);
}
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;
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 00:26:53 +03:00
lru_add_drain_all(); /* flush pagevec */
down_write(&current->mm->mmap_sem);
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
lock_limit >>= PAGE_SHIFT;
ret = -ENOMEM;
if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
capable(CAP_IPC_LOCK))
ret = do_mlockall(flags);
up_write(&current->mm->mmap_sem);
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 = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
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);
}
int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
size_t size)
{
unsigned long lim, vm, pgsz;
int error = -ENOMEM;
pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
down_write(&mm->mmap_sem);
lim = rlim[RLIMIT_AS].rlim_cur >> PAGE_SHIFT;
vm = mm->total_vm + pgsz;
if (lim < vm)
goto out;
lim = rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;
vm = mm->locked_vm + pgsz;
if (lim < vm)
goto out;
mm->total_vm += pgsz;
mm->locked_vm += pgsz;
error = 0;
out:
up_write(&mm->mmap_sem);
return error;
}
void refund_locked_memory(struct mm_struct *mm, size_t size)
{
unsigned long pgsz = PAGE_ALIGN(size) >> PAGE_SHIFT;
down_write(&mm->mmap_sem);
mm->total_vm -= pgsz;
mm->locked_vm -= pgsz;
up_write(&mm->mmap_sem);
}