aboutsummaryrefslogtreecommitdiff
path: root/mm/mlock.c
diff options
context:
space:
mode:
authorKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>2008-11-12 13:26:53 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2008-11-12 17:17:16 -0800
commit8891d6da17db0f9bb507d3a017f130b9970c3087 (patch)
treefd0fa107c4b85649722b9921a4bcdb35776eb36f /mm/mlock.c
parenta189d0350f387786b1fb5a5d19e3a5ab0bc0cceb (diff)
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>
Diffstat (limited to 'mm/mlock.c')
-rw-r--r--mm/mlock.c16
1 files changed, 6 insertions, 10 deletions
diff --git a/mm/mlock.c b/mm/mlock.c
index 008ea70b7af..a6da2aee940 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -66,14 +66,10 @@ void __clear_page_mlock(struct page *page)
putback_lru_page(page);
} else {
/*
- * Page not on the LRU yet. Flush all pagevecs and retry.
+ * We lost the race. the page already moved to evictable list.
*/
- lru_add_drain_all();
- if (!isolate_lru_page(page))
- putback_lru_page(page);
- else if (PageUnevictable(page))
+ if (PageUnevictable(page))
count_vm_event(UNEVICTABLE_PGSTRANDED);
-
}
}
@@ -187,8 +183,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
if (vma->vm_flags & VM_WRITE)
gup_flags |= GUP_FLAGS_WRITE;
- lru_add_drain_all(); /* push cached pages to LRU */
-
while (nr_pages > 0) {
int i;
@@ -251,8 +245,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
ret = 0;
}
- lru_add_drain_all(); /* to update stats */
-
return ret; /* count entire vma as locked_vm */
}
@@ -546,6 +538,8 @@ asmlinkage long sys_mlock(unsigned long start, size_t len)
if (!can_do_mlock())
return -EPERM;
+ lru_add_drain_all(); /* flush pagevec */
+
down_write(&current->mm->mmap_sem);
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
@@ -612,6 +606,8 @@ asmlinkage long sys_mlockall(int flags)
if (!can_do_mlock())
goto out;
+ lru_add_drain_all(); /* flush pagevec */
+
down_write(&current->mm->mmap_sem);
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;