linux-sg2042/mm/mlock.c

650 lines
16 KiB
C
Raw Normal View History

/*
* linux/mm/mlock.c
*
* (C) Copyright 1995 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*/
#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#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 11:26:44 +08:00
#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 11:26:44 +08:00
/*
* Mlocked pages are marked with PageMlocked() flag for efficient testing
* in vmscan and, possibly, the fault path; and to support semi-accurate
* statistics.
*
* An mlocked page [PageMlocked(page)] is unevictable. As such, it will
* be placed on the LRU "unevictable" list, rather than the [in]active lists.
* The unevictable list is an LRU sibling list to the [in]active lists.
* PageUnevictable is set to indicate the unevictable state.
*
* When lazy mlocking via vmscan, it is important to ensure that the
* vma's VM_LOCKED status is not concurrently being modified, otherwise we
* may have mlocked a page that is being munlocked. So lazy mlock must take
* the mmap_sem for read, and verify that the vma really is locked
* (see mm/rmap.c).
*/
/*
* LRU accounting for clear_page_mlock()
*/
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 11:26:44 +08:00
if (!isolate_lru_page(page)) {
putback_lru_page(page);
} else {
/*
mm: remove lru_add_drain_all() from the munlock path lockdep warns about following message at boot time on one of my test machine. Then, schedule_on_each_cpu() sholdn't be called when the task have mmap_sem. Actually, lru_add_drain_all() exist to prevent the unevictalble pages stay on reclaimable lru list. but currenct unevictable code can rescue unevictable pages although it stay on reclaimable list. So removing is better. In addition, this patch add lru_add_drain_all() to sys_mlock() and sys_mlockall(). it isn't must. but it reduce the failure of moving to unevictable list. its failure can rescue in vmscan later. but reducing is better. Note, if above rescuing happend, the Mlocked and the Unevictable field mismatching happend in /proc/meminfo. but it doesn't cause any real trouble. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.28-rc2-mm1 #2 ------------------------------------------------------- lvm/1103 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<c0130789>] get_online_cpus+0x29/0x50 but task is already holding lock: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){----}: [<c0153da2>] check_noncircular+0x82/0x110 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156161>] validate_chain+0xb11/0x1070 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab mmap_sem [<c0185e6a>] might_fault+0x4a/0xa0 [<c0185e9b>] might_fault+0x7b/0xa0 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0294dd0>] copy_to_user+0x30/0x60 [<c01ae3ec>] filldir+0x7c/0xd0 [<c01e3a6a>] sysfs_readdir+0x11a/0x1f0 (*) grab sysfs_mutex [<c01ae370>] filldir+0x0/0xd0 [<c01ae370>] filldir+0x0/0xd0 [<c01ae4c6>] vfs_readdir+0x86/0xa0 (*) grab i_mutex [<c01ae75b>] sys_getdents+0x6b/0xc0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff -> #2 (sysfs_mutex){--..}: [<c0153da2>] check_noncircular+0x82/0x110 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156161>] validate_chain+0xb11/0x1070 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab sysfs_mutex [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e422f>] create_dir+0x3f/0x90 [<c01e42a9>] sysfs_create_dir+0x29/0x50 [<c04faaf5>] _spin_unlock+0x25/0x40 [<c028f21d>] kobject_add_internal+0xcd/0x1a0 [<c028f37a>] kobject_set_name_vargs+0x3a/0x50 [<c028f41d>] kobject_init_and_add+0x2d/0x40 [<c019d4d2>] sysfs_slab_add+0xd2/0x180 [<c019d580>] sysfs_add_func+0x0/0x70 [<c019d5dc>] sysfs_add_func+0x5c/0x70 (*) grab slub_lock [<c01400f2>] run_workqueue+0x172/0x200 [<c014008f>] run_workqueue+0x10f/0x200 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0140c6c>] worker_thread+0x9c/0xf0 [<c0143c80>] autoremove_wake_function+0x0/0x50 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0143972>] kthread+0x42/0x70 [<c0143930>] kthread+0x0/0x70 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #1 (slub_lock){----}: [<c0153d2d>] check_noncircular+0xd/0x110 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c0156161>] validate_chain+0xb11/0x1070 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c015433d>] mark_lock+0x35d/0xd00 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04f93a3>] down_read+0x43/0x80 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 (*) grab slub_lock [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04fd9ac>] notifier_call_chain+0x3c/0x70 [<c04f5454>] _cpu_up+0x84/0x110 [<c04f552b>] cpu_up+0x4b/0x70 (*) grab cpu_hotplug.lock [<c06d1530>] kernel_init+0x0/0x170 [<c06d15e5>] kernel_init+0xb5/0x170 [<c06d1530>] kernel_init+0x0/0x170 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #0 (&cpu_hotplug.lock){--..}: [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 (*) grab cpu_hotplug.lock [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 (*) grab mmap_sem [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by lvm/1103: #0: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 stack backtrace: Pid: 1103, comm: lvm Not tainted 2.6.28-rc2-mm1 #2 Call Trace: [<c01555fc>] print_circular_bug_tail+0x7c/0xd0 [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-13 05:26:53 +08:00
* We lost the race. the page already moved to evictable list.
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
*/
mm: remove lru_add_drain_all() from the munlock path lockdep warns about following message at boot time on one of my test machine. Then, schedule_on_each_cpu() sholdn't be called when the task have mmap_sem. Actually, lru_add_drain_all() exist to prevent the unevictalble pages stay on reclaimable lru list. but currenct unevictable code can rescue unevictable pages although it stay on reclaimable list. So removing is better. In addition, this patch add lru_add_drain_all() to sys_mlock() and sys_mlockall(). it isn't must. but it reduce the failure of moving to unevictable list. its failure can rescue in vmscan later. but reducing is better. Note, if above rescuing happend, the Mlocked and the Unevictable field mismatching happend in /proc/meminfo. but it doesn't cause any real trouble. ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.28-rc2-mm1 #2 ------------------------------------------------------- lvm/1103 is trying to acquire lock: (&cpu_hotplug.lock){--..}, at: [<c0130789>] get_online_cpus+0x29/0x50 but task is already holding lock: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&mm->mmap_sem){----}: [<c0153da2>] check_noncircular+0x82/0x110 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156161>] validate_chain+0xb11/0x1070 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab mmap_sem [<c0185e6a>] might_fault+0x4a/0xa0 [<c0185e9b>] might_fault+0x7b/0xa0 [<c0185e6a>] might_fault+0x4a/0xa0 [<c0294dd0>] copy_to_user+0x30/0x60 [<c01ae3ec>] filldir+0x7c/0xd0 [<c01e3a6a>] sysfs_readdir+0x11a/0x1f0 (*) grab sysfs_mutex [<c01ae370>] filldir+0x0/0xd0 [<c01ae370>] filldir+0x0/0xd0 [<c01ae4c6>] vfs_readdir+0x86/0xa0 (*) grab i_mutex [<c01ae75b>] sys_getdents+0x6b/0xc0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff -> #2 (sysfs_mutex){--..}: [<c0153da2>] check_noncircular+0x82/0x110 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156161>] validate_chain+0xb11/0x1070 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 (*) grab sysfs_mutex [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0 [<c01e422f>] create_dir+0x3f/0x90 [<c01e42a9>] sysfs_create_dir+0x29/0x50 [<c04faaf5>] _spin_unlock+0x25/0x40 [<c028f21d>] kobject_add_internal+0xcd/0x1a0 [<c028f37a>] kobject_set_name_vargs+0x3a/0x50 [<c028f41d>] kobject_init_and_add+0x2d/0x40 [<c019d4d2>] sysfs_slab_add+0xd2/0x180 [<c019d580>] sysfs_add_func+0x0/0x70 [<c019d5dc>] sysfs_add_func+0x5c/0x70 (*) grab slub_lock [<c01400f2>] run_workqueue+0x172/0x200 [<c014008f>] run_workqueue+0x10f/0x200 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0140c6c>] worker_thread+0x9c/0xf0 [<c0143c80>] autoremove_wake_function+0x0/0x50 [<c0140bd0>] worker_thread+0x0/0xf0 [<c0143972>] kthread+0x42/0x70 [<c0143930>] kthread+0x0/0x70 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #1 (slub_lock){----}: [<c0153d2d>] check_noncircular+0xd/0x110 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c0156161>] validate_chain+0xb11/0x1070 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c015433d>] mark_lock+0x35d/0xd00 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04f93a3>] down_read+0x43/0x80 [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 (*) grab slub_lock [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0 [<c04fd9ac>] notifier_call_chain+0x3c/0x70 [<c04f5454>] _cpu_up+0x84/0x110 [<c04f552b>] cpu_up+0x4b/0x70 (*) grab cpu_hotplug.lock [<c06d1530>] kernel_init+0x0/0x170 [<c06d15e5>] kernel_init+0xb5/0x170 [<c06d1530>] kernel_init+0x0/0x170 [<c01042db>] kernel_thread_helper+0x7/0x1c [<ffffffff>] 0xffffffff -> #0 (&cpu_hotplug.lock){--..}: [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 (*) grab cpu_hotplug.lock [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 (*) grab mmap_sem [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb [<ffffffff>] 0xffffffff other info that might help us debug this: 1 lock held by lvm/1103: #0: (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0 stack backtrace: Pid: 1103, comm: lvm Not tainted 2.6.28-rc2-mm1 #2 Call Trace: [<c01555fc>] print_circular_bug_tail+0x7c/0xd0 [<c0155bff>] validate_chain+0x5af/0x1070 [<c040f7e0>] dev_status+0x0/0x50 [<c0156923>] __lock_acquire+0x263/0xa10 [<c015714c>] lock_acquire+0x7c/0xb0 [<c0130789>] get_online_cpus+0x29/0x50 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0 [<c0130789>] get_online_cpus+0x29/0x50 [<c0130789>] get_online_cpus+0x29/0x50 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10 [<c0130789>] get_online_cpus+0x29/0x50 [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0 [<c0156945>] __lock_acquire+0x285/0xa10 [<c0188f09>] vma_merge+0xa9/0x1d0 [<c0187450>] mlock_fixup+0x180/0x200 [<c0187548>] do_mlockall+0x78/0x90 [<c01878e1>] sys_mlockall+0x81/0xb0 [<c010355a>] syscall_call+0x7/0xb Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-13 05:26:53 +08:00
if (PageUnevictable(page))
count_vm_event(UNEVICTABLE_PGSTRANDED);
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
}
}
/*
* Mark page as mlocked if not already.
* If page on LRU, isolate and putback to move to unevictable list.
*/
void mlock_vma_page(struct page *page)
{
BUG_ON(!PageLocked(page));
if (!TestSetPageMlocked(page)) {
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 11:26:44 +08:00
}
/*
* called from munlock()/munmap() path with page supposedly on the LRU.
*
* Note: unlike mlock_vma_page(), we can't just clear the PageMlocked
* [in try_to_munlock()] and then attempt to isolate the page. We must
* isolate the page to keep others from messing with its unevictable
* and mlocked state while trying to munlock. However, we pre-clear the
* mlocked state anyway as we might lose the isolation race and we might
* not get another chance to clear PageMlocked. If we successfully
* isolate the page and try_to_munlock() detects other VM_LOCKED vmas
* mapping the page, it will restore the PageMlocked state, unless the page
* is mapped in a non-linear vma. So, we go ahead and SetPageMlocked(),
* perhaps redundantly.
* If we lose the isolation race, and the page is mapped by other VM_LOCKED
* vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
* either of which will restore the PageMlocked state by calling
* mlock_vma_page() above, if it can grab the vma's mmap sem.
*/
static void munlock_vma_page(struct page *page)
{
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?
*/
if (ret == SWAP_SUCCESS || ret == SWAP_AGAIN)
count_vm_event(UNEVICTABLE_PGMUNLOCKED);
putback_lru_page(page);
} else {
/*
* We lost the race. let try_to_unmap() deal
* with it. At least we get the page state and
* mlock stats right. However, page is still on
* the noreclaim list. We'll fix that up when
* the page is eventually freed or we scan the
* noreclaim list.
*/
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 11:26:44 +08:00
}
}
/**
* __mlock_vma_pages_range() - mlock/munlock a range of pages in the vma.
* @vma: target vma
* @start: start address
* @end: end address
* @mlock: 0 indicate munlock, otherwise mlock.
*
* If @mlock == 0, unlock an mlocked range;
* else mlock the range of pages. This takes care of making the pages present ,
* too.
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
*
* return 0 on success, negative error code on error.
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
*
* vma->vm_mm->mmap_sem must be held for at least read.
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
*/
static long __mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
int mlock)
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
{
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;
int gup_flags = 0;
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);
VM_BUG_ON((!rwsem_is_locked(&mm->mmap_sem)) &&
(atomic_read(&mm->mm_users) != 0));
/*
mm: make get_user_pages() interruptible The initial implementation of checking TIF_MEMDIE covers the cases of OOM killing. If the process has been OOM killed, the TIF_MEMDIE is set and it return immediately. This patch includes: 1. add the case that the SIGKILL is sent by user processes. The process can try to get_user_pages() unlimited memory even if a user process has sent a SIGKILL to it(maybe a monitor find the process exceed its memory limit and try to kill it). In the old implementation, the SIGKILL won't be handled until the get_user_pages() returns. 2. change the return value to be ERESTARTSYS. It makes no sense to return ENOMEM if the get_user_pages returned by getting a SIGKILL signal. Considering the general convention for a system call interrupted by a signal is ERESTARTNOSYS, so the current return value is consistant to that. Lee: An unfortunate side effect of "make-get_user_pages-interruptible" is that it prevents a SIGKILL'd task from munlock-ing pages that it had mlocked, resulting in freeing of mlocked pages. Freeing of mlocked pages, in itself, is not so bad. We just count them now--altho' I had hoped to remove this stat and add PG_MLOCKED to the free pages flags check. However, consider pages in shared libraries mapped by more than one task that a task mlocked--e.g., via mlockall(). If the task that mlocked the pages exits via SIGKILL, these pages would be left mlocked and unevictable. Proposed fix: Add another GUP flag to ignore sigkill when calling get_user_pages from munlock()--similar to Kosaki Motohiro's 'IGNORE_VMA_PERMISSIONS flag for the same purpose. We are not actually allocating memory in this case, which "make-get_user_pages-interruptible" intends to avoid. We're just munlocking pages that are already resident and mapped, and we're reusing get_user_pages() to access those pages. ?? Maybe we should combine 'IGNORE_VMA_PERMISSIONS and '_IGNORE_SIGKILL into a single flag: GUP_FLAGS_MUNLOCK ??? [Lee.Schermerhorn@hp.com: ignore sigkill in get_user_pages during munlock] Signed-off-by: Paul Menage <menage@google.com> Signed-off-by: Ying Han <yinghan@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rohit Seth <rohitseth@google.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:18 +08:00
* mlock: don't page populate if vma has PROT_NONE permission.
* munlock: always do munlock although the vma has PROT_NONE
* permission, or SIGKILL is pending.
*/
if (!mlock)
mm: make get_user_pages() interruptible The initial implementation of checking TIF_MEMDIE covers the cases of OOM killing. If the process has been OOM killed, the TIF_MEMDIE is set and it return immediately. This patch includes: 1. add the case that the SIGKILL is sent by user processes. The process can try to get_user_pages() unlimited memory even if a user process has sent a SIGKILL to it(maybe a monitor find the process exceed its memory limit and try to kill it). In the old implementation, the SIGKILL won't be handled until the get_user_pages() returns. 2. change the return value to be ERESTARTSYS. It makes no sense to return ENOMEM if the get_user_pages returned by getting a SIGKILL signal. Considering the general convention for a system call interrupted by a signal is ERESTARTNOSYS, so the current return value is consistant to that. Lee: An unfortunate side effect of "make-get_user_pages-interruptible" is that it prevents a SIGKILL'd task from munlock-ing pages that it had mlocked, resulting in freeing of mlocked pages. Freeing of mlocked pages, in itself, is not so bad. We just count them now--altho' I had hoped to remove this stat and add PG_MLOCKED to the free pages flags check. However, consider pages in shared libraries mapped by more than one task that a task mlocked--e.g., via mlockall(). If the task that mlocked the pages exits via SIGKILL, these pages would be left mlocked and unevictable. Proposed fix: Add another GUP flag to ignore sigkill when calling get_user_pages from munlock()--similar to Kosaki Motohiro's 'IGNORE_VMA_PERMISSIONS flag for the same purpose. We are not actually allocating memory in this case, which "make-get_user_pages-interruptible" intends to avoid. We're just munlocking pages that are already resident and mapped, and we're reusing get_user_pages() to access those pages. ?? Maybe we should combine 'IGNORE_VMA_PERMISSIONS and '_IGNORE_SIGKILL into a single flag: GUP_FLAGS_MUNLOCK ??? [Lee.Schermerhorn@hp.com: ignore sigkill in get_user_pages during munlock] Signed-off-by: Paul Menage <menage@google.com> Signed-off-by: Ying Han <yinghan@google.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Hugh Dickins <hugh@veritas.com> Cc: Oleg Nesterov <oleg@tv-sign.ru> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rohit Seth <rohitseth@google.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 06:40:18 +08:00
gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS |
GUP_FLAGS_IGNORE_SIGKILL;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
if (vma->vm_flags & VM_WRITE)
gup_flags |= GUP_FLAGS_WRITE;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
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 11:26:44 +08:00
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 11:26:44 +08:00
/*
* 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.
* We'll mlock the the pages if/when they get faulted in.
*/
if (ret < 0)
break;
if (ret == 0) {
/*
* We know the vma is there, so the only time
* we cannot get a single page should be an
* error (ret < 0) case.
*/
WARN_ON(1);
break;
}
lru_add_drain(); /* push cached pages to LRU */
for (i = 0; i < ret; i++) {
struct page *page = pages[i];
lock_page(page);
/*
* Because we lock page here and migration is blocked
* by the elevated reference, we need only check for
* page truncation (file-cache only).
*/
if (page->mapping) {
if (mlock)
mlock_vma_page(page);
else
munlock_vma_page(page);
}
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
unlock_page(page);
put_page(page); /* ref from get_user_pages() */
/*
* here we assume that get_user_pages() has given us
* a list of virtually contiguous pages.
*/
addr += PAGE_SIZE; /* for next get_user_pages() */
nr_pages--;
}
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 11:26:44 +08:00
}
return ret; /* count entire vma as locked_vm */
}
/*
* convert get_user_pages() return value to posix mlock() error
*/
static int __mlock_posix_error_return(long retval)
{
if (retval == -EFAULT)
retval = -ENOMEM;
else if (retval == -ENOMEM)
retval = -EAGAIN;
return retval;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
}
/**
* 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 11:26:44 +08:00
*/
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 11:26:44 +08:00
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 11:26:49 +08:00
vma == get_gate_vma(current))) {
__mlock_vma_pages_range(vma, start, end, 1);
/* 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 11:26:49 +08:00
}
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
/*
* 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 11:26:44 +08:00
}
/*
* munlock_vma_pages_range() - munlock all pages in the vma range.'
* @vma - vma containing range to be munlock()ed.
* @start - start address in @vma of the range
* @end - end of range in @vma.
*
* For mremap(), munmap() and exit().
*
* Called with @vma VM_LOCKED.
*
* Returns with VM_LOCKED cleared. Callers must be prepared to
* deal with this.
*
* We don't save and restore VM_LOCKED here because pages are
* still on lru. In unmap path, pages might be scanned by reclaim
* and re-mlocked by try_to_{munlock|unmap} before we unmap and
* free them. This will result in freeing mlocked pages.
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
*/
void munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
{
vma->vm_flags &= ~VM_LOCKED;
__mlock_vma_pages_range(vma, start, end, 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 11:26:44 +08:00
}
/*
* mlock_fixup - handle mlock[all]/munlock[all] requests.
*
* Filters out "special" vmas -- VM_LOCKED never gets set for these, and
* munlock is a no-op. However, for some special vmas, we go ahead and
* populate the ptes 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 11:26:44 +08:00
struct mm_struct *mm = vma->vm_mm;
pgoff_t pgoff;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
int nr_pages;
int ret = 0;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
int 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 11:26:44 +08:00
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 11:26:44 +08:00
/*
* Keep track of amount of locked VM.
*/
nr_pages = (end - start) >> PAGE_SHIFT;
if (!lock)
nr_pages = -nr_pages;
mm->locked_vm += nr_pages;
/*
* vm_flags is protected by the mmap_sem held in write mode.
* It's okay if try_to_unmap_one unmaps a page just after we
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
* set VM_LOCKED, __mlock_vma_pages_range will bring it back.
*/
vma->vm_flags = newflags;
mlock: mlocked pages are unevictable Make sure that mlocked pages also live on the unevictable LRU, so kswapd will not scan them over and over again. This is achieved through various strategies: 1) add yet another page flag--PG_mlocked--to indicate that the page is locked for efficient testing in vmscan and, optionally, fault path. This allows early culling of unevictable pages, preventing them from getting to page_referenced()/try_to_unmap(). Also allows separate accounting of mlock'd pages, as Nick's original patch did. Note: Nick's original mlock patch used a PG_mlocked flag. I had removed this in favor of the PG_unevictable flag + an mlock_count [new page struct member]. I restored the PG_mlocked flag to eliminate the new count field. 2) add the mlock/unevictable infrastructure to mm/mlock.c, with internal APIs in mm/internal.h. This is a rework of Nick's original patch to these files, taking into account that mlocked pages are now kept on unevictable LRU list. 3) update vmscan.c:page_evictable() to check PageMlocked() and, if vma passed in, the vm_flags. Note that the vma will only be passed in for new pages in the fault path; and then only if the "cull unevictable pages in fault path" patch is included. 4) add try_to_unlock() to rmap.c to walk a page's rmap and ClearPageMlocked() if no other vmas have it mlocked. Reuses as much of try_to_unmap() as possible. This effectively replaces the use of one of the lru list links as an mlock count. If this mechanism let's pages in mlocked vmas leak through w/o PG_mlocked set [I don't know that it does], we should catch them later in try_to_unmap(). One hopes this will be rare, as it will be relatively expensive. Original mm/internal.h, mm/rmap.c and mm/mlock.c changes: Signed-off-by: Nick Piggin <npiggin@suse.de> splitlru: introduce __get_user_pages(): New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS. because current get_user_pages() can't grab PROT_NONE pages theresore it cause PROT_NONE pages can't munlock. [akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch] [akpm@linux-foundation.org: untangle patch interdependencies] [akpm@linux-foundation.org: fix things after out-of-order merging] [hugh@veritas.com: fix page-flags mess] [lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm'] [kosaki.motohiro@jp.fujitsu.com: build fix] [kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments] [kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()] Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Dave Hansen <dave@linux.vnet.ibm.com> Cc: Matt Mackall <mpm@selenic.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:26:44 +08:00
if (lock) {
ret = __mlock_vma_pages_range(vma, start, end, 1);
Manually revert "mlock: downgrade mmap sem while populating mlocked regions" This essentially reverts commit 8edb08caf68184fb170f4f69c7445929e199eaea. It downgraded our mmap semaphore to a read-lock while mlocking pages, in order to allow other threads (and external accesses like "ps" et al) to walk the vma lists and take page faults etc. Which is a nice idea, but the implementation does not work. Because we cannot upgrade the lock back to a write lock without releasing the mmap semaphore, the code had to release the lock entirely and then re-take it as a writelock. However, that meant that the caller possibly lost the vma chain that it was following, since now another thread could come in and mmap/munmap the range. The code tried to work around that by just looking up the vma again and erroring out if that happened, but quite frankly, that was just a buggy hack that doesn't actually protect against anything (the other thread could just have replaced the vma with another one instead of totally unmapping it). The only way to downgrade to a read map _reliably_ is to do it at the end, which is likely the right thing to do: do all the 'vma' operations with the write-lock held, then downgrade to a read after completing them all, and then do the "populate the newly mlocked regions" while holding just the read lock. And then just drop the read-lock and return to user space. The (perhaps somewhat simpler) alternative is to just make all the callers of mlock_vma_pages_range() know that the mmap lock got dropped, and just re-grab the mmap semaphore if it needs to mlock more than one vma region. So we can do this "downgrade mmap sem while populating mlocked regions" thing right, but the way it was done here was absolutely not correct. Thus the revert, in the expectation that we will do it all correctly some day. Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: stable@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-02 03:00:16 +08:00
if (ret > 0) {
mm->locked_vm -= ret;
ret = 0;
} else
ret = __mlock_posix_error_return(ret); /* translate if needed */
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 11:26:49 +08:00
} else {
__mlock_vma_pages_range(vma, start, end, 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 11:26:49 +08:00
}
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 11:26:44 +08:00
*prev = vma;
return ret;
}
static int do_mlock(unsigned long start, size_t len, int on)
{
unsigned long nstart, end, tmp;
struct vm_area_struct * vma, * prev;
int error;
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 05:26:53 +08:00
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 05:26:53 +08:00
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);
}