kernel_optimize_test/mm
Minchan Kim 03ef83af52 mm: fix for infinite churning of mlocked pages
An mlocked page might lose the isolatation race.  This causes the page to
clear PG_mlocked while it remains in a VM_LOCKED vma.  This means it can
be put onto the [in]active list.  We can rescue it by using try_to_unmap()
in shrink_page_list().

But now, As Wu Fengguang pointed out, vmscan has a bug.  If the page has
PG_referenced, it can't reach try_to_unmap() in shrink_page_list() but is
put into the active list.  If the page is referenced repeatedly, it can
remain on the [in]active list without being moving to the unevictable
list.

This patch fixes it.

Reported-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: KOSAKI Motohiro <<kosaki.motohiro@jp.fujitsu.com>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Acked-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>
2009-08-26 20:06:52 -07:00
..
allocpercpu.c
backing-dev.c Fix congestion_wait() sync/async vs read/write confusion 2009-07-10 20:31:53 +02:00
bootmem.c kmemleak: Add callbacks to the bootmem allocator 2009-07-08 14:25:14 +01:00
bounce.c
debug-pagealloc.c
dmapool.c dmapools: protect page_list walk in show_pools() 2009-06-30 18:56:00 -07:00
fadvise.c
failslab.c
filemap_xip.c
filemap.c mm: mark page accessed before we write_end() 2009-07-06 13:57:03 -07:00
fremap.c
highmem.c
hugetlb.c hugetlbfs: fix i_blocks accounting 2009-07-29 19:10:35 -07:00
init-mm.c
internal.h
Kconfig Security/SELinux: seperate lsm specific mmap_min_addr 2009-08-17 15:09:11 +10:00
Kconfig.debug
kmemcheck.c
kmemleak-test.c
kmemleak.c kmemleak: Protect the seq start/next/stop sequence by rcu_read_lock() 2009-07-29 12:34:58 -07:00
maccess.c
madvise.c
Makefile
memcontrol.c cgroup avoid permanent sleep at rmdir 2009-07-29 19:10:35 -07:00
memory_hotplug.c
memory.c mm: Pass virtual address to [__]p{te,ud,md}_free_tlb() 2009-07-27 12:10:38 -07:00
mempolicy.c mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware 2009-08-07 10:39:55 -07:00
mempool.c mempool.c: clean up type-casting 2009-08-10 08:31:16 -07:00
migrate.c
mincore.c
mlock.c
mm_init.c
mmap.c Security/SELinux: seperate lsm specific mmap_min_addr 2009-08-17 15:09:11 +10:00
mmu_notifier.c
mmzone.c
mprotect.c
mremap.c
msync.c
nommu.c nommu: check fd read permission in validate_mmap_request() 2009-08-18 16:31:13 -07:00
oom_kill.c mm: revert "oom: move oom_adj value" 2009-08-18 16:31:13 -07:00
page_alloc.c mm: build_zonelists(): move clear node_load[] to __build_all_zonelists() 2009-08-18 16:31:13 -07:00
page_cgroup.c memcg: remove some redundant checks 2009-06-18 13:03:47 -07:00
page_io.c
page_isolation.c
page-writeback.c Fix congestion_wait() sync/async vs read/write confusion 2009-07-10 20:31:53 +02:00
pagewalk.c
pdflush.c
percpu.c percpu: use the right flag for get_vm_area() 2009-08-14 13:21:10 +09:00
prio_tree.c
quicklist.c
readahead.c
rmap.c mm: fix for infinite churning of mlocked pages 2009-08-26 20:06:52 -07:00
shmem_acl.c switch shmem to inode->i_acl 2009-06-24 08:17:06 -04:00
shmem.c Get "no acls for this inode" right, fix shmem breakage 2009-06-24 16:58:48 -04:00
slab.c SLAB: Fix lockdep annotations 2009-06-29 09:57:10 +03:00
slob.c fix RCU-callback-after-kmem_cache_destroy problem in sl[aou]b 2009-06-26 12:10:47 +03:00
slub.c kmemleak: Trace the kmalloc_large* functions in slub 2009-07-08 14:25:14 +01:00
sparse-vmemmap.c
sparse.c
swap_state.c
swap.c
swapfile.c PM / Hibernate: Replace bdget call with simple atomic_inc of i_count 2009-07-29 21:07:55 +02:00
thrash.c mm: pass mm to grab_swap_token 2009-06-23 12:50:05 -07:00
truncate.c
util.c
vmalloc.c
vmscan.c mm: fix for infinite churning of mlocked pages 2009-08-26 20:06:52 -07:00
vmstat.c