Revision 72853e2991a2702ae93aaf889ac7db743a415dd3 authored by Mel Gorman on 09 September 2010, 23:38:16 UTC, committed by Linus Torvalds on 10 September 2010, 01:57:25 UTC
When allocating a page, the system uses NR_FREE_PAGES counters to determine if watermarks would remain intact after the allocation was made. This check is made without interrupts disabled or the zone lock held and so is race-prone by nature. Unfortunately, when pages are being freed in batch, the counters are updated before the pages are added on the list. During this window, the counters are misleading as the pages do not exist yet. When under significant pressure on systems with large numbers of CPUs, it's possible for processes to make progress even though they should have been stalled. This is particularly problematic if a number of the processes are using GFP_ATOMIC as the min watermark can be accidentally breached and in extreme cases, the system can livelock. This patch updates the counters after the pages have been added to the list. This makes the allocator more cautious with respect to preserving the watermarks and mitigates livelock possibilities. [akpm@linux-foundation.org: avoid modifying incoming args] Signed-off-by: Mel Gorman <mel@csn.ul.ie> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan.kim@gmail.com> Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Christoph Lameter <cl@linux.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5ee28a4
Kconfig
#
# Library configuration
#
config BINARY_PRINTF
def_bool n
menu "Library routines"
config RAID6_PQ
tristate
config BITREVERSE
tristate
config RATIONAL
boolean
config GENERIC_FIND_FIRST_BIT
bool
config GENERIC_FIND_NEXT_BIT
bool
config GENERIC_FIND_LAST_BIT
bool
default y
config CRC_CCITT
tristate "CRC-CCITT functions"
help
This option is provided for the case where no in-kernel-tree
modules require CRC-CCITT functions, but a module built outside
the kernel tree does. Such modules that use library CRC-CCITT
functions require M here.
config CRC16
tristate "CRC16 functions"
help
This option is provided for the case where no in-kernel-tree
modules require CRC16 functions, but a module built outside
the kernel tree does. Such modules that use library CRC16
functions require M here.
config CRC_T10DIF
tristate "CRC calculation for the T10 Data Integrity Field"
help
This option is only needed if a module that's not in the
kernel tree needs to calculate CRC checks for use with the
SCSI data integrity subsystem.
config CRC_ITU_T
tristate "CRC ITU-T V.41 functions"
help
This option is provided for the case where no in-kernel-tree
modules require CRC ITU-T V.41 functions, but a module built outside
the kernel tree does. Such modules that use library CRC ITU-T V.41
functions require M here.
config CRC32
tristate "CRC32 functions"
default y
select BITREVERSE
help
This option is provided for the case where no in-kernel-tree
modules require CRC32 functions, but a module built outside the
kernel tree does. Such modules that use library CRC32 functions
require M here.
config CRC7
tristate "CRC7 functions"
help
This option is provided for the case where no in-kernel-tree
modules require CRC7 functions, but a module built outside
the kernel tree does. Such modules that use library CRC7
functions require M here.
config LIBCRC32C
tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check"
select CRYPTO
select CRYPTO_CRC32C
help
This option is provided for the case where no in-kernel-tree
modules require CRC32c functions, but a module built outside the
kernel tree does. Such modules that use library CRC32c functions
require M here. See Castagnoli93.
Module will be libcrc32c.
config AUDIT_GENERIC
bool
depends on AUDIT && !AUDIT_ARCH
default y
#
# compression support is select'ed if needed
#
config ZLIB_INFLATE
tristate
config ZLIB_DEFLATE
tristate
config LZO_COMPRESS
tristate
config LZO_DECOMPRESS
tristate
#
# These all provide a common interface (hence the apparent duplication with
# ZLIB_INFLATE; DECOMPRESS_GZIP is just a wrapper.)
#
config DECOMPRESS_GZIP
select ZLIB_INFLATE
tristate
config DECOMPRESS_BZIP2
tristate
config DECOMPRESS_LZMA
tristate
config DECOMPRESS_LZO
select LZO_DECOMPRESS
tristate
#
# Generic allocator support is selected if needed
#
config GENERIC_ALLOCATOR
boolean
#
# reed solomon support is select'ed if needed
#
config REED_SOLOMON
tristate
config REED_SOLOMON_ENC8
boolean
config REED_SOLOMON_DEC8
boolean
config REED_SOLOMON_ENC16
boolean
config REED_SOLOMON_DEC16
boolean
#
# Textsearch support is select'ed if needed
#
config TEXTSEARCH
boolean
config TEXTSEARCH_KMP
tristate
config TEXTSEARCH_BM
tristate
config TEXTSEARCH_FSM
tristate
config BTREE
boolean
config HAS_IOMEM
boolean
depends on !NO_IOMEM
default y
config HAS_IOPORT
boolean
depends on HAS_IOMEM && !NO_IOPORT
default y
config HAS_DMA
boolean
depends on !NO_DMA
default y
config CHECK_SIGNATURE
bool
config CPUMASK_OFFSTACK
bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
help
Use dynamic allocation for cpumask_var_t, instead of putting
them on the stack. This is a bit more expensive, but avoids
stack overflow.
config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS
depends on EXPERIMENTAL && BROKEN
#
# Netlink attribute parsing support is select'ed if needed
#
config NLATTR
bool
#
# Generic 64-bit atomic support is selected if needed
#
config GENERIC_ATOMIC64
bool
config LRU_CACHE
tristate
endmenu
Computing file changes ...