From 25985edcedea6396277003854657b5f3cb31a628 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@profusion.mobi>
Date: Wed, 30 Mar 2011 22:57:33 -0300
Subject: Fix common misspellings

Fixes generated by 'codespell' and manually reviewed.

Signed-off-by: Lucas De Marchi <lucas.demarchi@profusion.mobi>
---
 mm/page_alloc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d6e7ba7373be..2747f5e5abc1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -942,7 +942,7 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
 			 * If breaking a large block of pages, move all free
 			 * pages to the preferred allocation list. If falling
 			 * back for a reclaimable kernel allocation, be more
-			 * agressive about taking ownership of free pages
+			 * aggressive about taking ownership of free pages
 			 */
 			if (unlikely(current_order >= (pageblock_order >> 1)) ||
 					start_migratetype == MIGRATE_RECLAIMABLE ||
@@ -3926,7 +3926,7 @@ static void __init find_usable_zone_for_movable(void)
 
 /*
  * The zone ranges provided by the architecture do not include ZONE_MOVABLE
- * because it is sized independant of architecture. Unlike the other zones,
+ * because it is sized independent of architecture. Unlike the other zones,
  * the starting point for ZONE_MOVABLE is not fixed. It may be different
  * in each node depending on the size of each node and how evenly kernelcore
  * is distributed. This helper function adjusts the zone ranges
-- 
cgit v1.2.3


From 58c2ee4007bea04cc37041fcbd380fadb7b7be82 Mon Sep 17 00:00:00 2001
From: Nikanth Karthikesan <knikanth@suse.de>
Date: Tue, 15 Mar 2011 10:59:02 +0530
Subject: mm: Fix section mismatch for setup_zone_pageset()

build_all_zonelists() which is not __meminit, calls setup_zone_pageset().

Signed-off-by: Nikanth Karthikesan <knikanth@suse.de>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7945247b1e53..48c9737ad49a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3448,7 +3448,7 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
 		pcp->batch = PAGE_SHIFT * 8;
 }
 
-static __meminit void setup_zone_pageset(struct zone *zone)
+static void setup_zone_pageset(struct zone *zone)
 {
 	int cpu;
 
-- 
cgit v1.2.3


From 9f6ae448bfc6cdf40279f43bb0b4fd159edc4e0a Mon Sep 17 00:00:00 2001
From: Paul Mundt <lethal@linux-sh.org>
Date: Thu, 14 Apr 2011 15:21:57 -0700
Subject: mm/page_alloc.c: silence build_all_zonelists() section mismatch

The memory hotplug case involves calling to build_all_zonelists() which
in turns calls in to setup_zone_pageset().  The latter is marked
__meminit while build_all_zonelists() itself has no particular
annotation.  build_all_zonelists() is only handed a non-NULL pointer in
the case of memory hotplug through an existing __meminit path, so the
setup_zone_pageset() reference is always safe.

The options as such are either to flag build_all_zonelists() as __ref (as
per __build_all_zonelists()), or to simply discard the __meminit
annotation from setup_zone_pageset().

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2747f5e5abc1..9f8a97b9a350 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3176,7 +3176,7 @@ static __init_refok int __build_all_zonelists(void *data)
  * Called with zonelists_mutex held always
  * unless system_state == SYSTEM_BOOTING.
  */
-void build_all_zonelists(void *data)
+void __ref build_all_zonelists(void *data)
 {
 	set_zonelist_order();
 
-- 
cgit v1.2.3


From 8f389a99b652aab5b42297280bd94d95933ad12f Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Wed, 11 May 2011 15:13:32 -0700
Subject: mm: use alloc_bootmem_node_nopanic() on really needed path

Stefan found nobootmem does not work on his system that has only 8M of
RAM.  This causes an early panic:

  BIOS-provided physical RAM map:
   BIOS-88: 0000000000000000 - 000000000009f000 (usable)
   BIOS-88: 0000000000100000 - 0000000000840000 (usable)
  bootconsole [earlyser0] enabled
  Notice: NX (Execute Disable) protection missing in CPU or disabled in BIOS!
  DMI not present or invalid.
  last_pfn = 0x840 max_arch_pfn = 0x100000
  init_memory_mapping: 0000000000000000-0000000000840000
  8MB LOWMEM available.
    mapped low ram: 0 - 00840000
    low ram: 0 - 00840000
  Zone PFN ranges:
    DMA      0x00000001 -> 0x00001000
    Normal   empty
  Movable zone start PFN for each node
  early_node_map[2] active PFN ranges
      0: 0x00000001 -> 0x0000009f
      0: 0x00000100 -> 0x00000840
  BUG: Int 6: CR2 (null)
       EDI c034663c  ESI (null)  EBP c0329f38  ESP c0329ef4
       EBX c0346380  EDX 00000006  ECX ffffffff  EAX fffffff4
       err (null)  EIP c0353191   CS c0320060  flg 00010082
  Stack: (null) c030c533 000007cd (null) c030c533 00000001 (null) (null)
         00000003 0000083f 00000018 00000002 00000002 c0329f6c c03534d6 (null)
         (null) 00000100 00000840 (null) c0329f64 00000001 00001000 (null)
  Pid: 0, comm: swapper Not tainted 2.6.36 #5
  Call Trace:
   [<c02e3707>] ? 0xc02e3707
   [<c035e6e5>] 0xc035e6e5
   [<c0353191>] ? 0xc0353191
   [<c03534d6>] 0xc03534d6
   [<c034f1cd>] 0xc034f1cd
   [<c034a824>] 0xc034a824
   [<c03513cb>] ? 0xc03513cb
   [<c0349432>] 0xc0349432
   [<c0349066>] 0xc0349066

It turns out that we should ignore the low limit of 16M.

Use alloc_bootmem_node_nopanic() in this case.

[akpm@linux-foundation.org: less mess]
Signed-off-by: Yinghai LU <yinghai@kernel.org>
Reported-by: Stefan Hellermann <stefan@the2masters.de>
Tested-by: Stefan Hellermann <stefan@the2masters.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@kernel.org>		[2.6.34+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bootmem.h | 2 ++
 mm/page_alloc.c         | 7 ++++---
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index b8613e806aa9..01eca1794e14 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -111,6 +111,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 	__alloc_bootmem_nopanic(x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_node(pgdat, x) \
 	__alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_node_nopanic(pgdat, x) \
+	__alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_node(pgdat, x) \
 	__alloc_bootmem_node(pgdat, x, PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages_node_nopanic(pgdat, x) \
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9f8a97b9a350..454191a25173 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3564,7 +3564,7 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
 
 	if (!slab_is_available()) {
 		zone->wait_table = (wait_queue_head_t *)
-			alloc_bootmem_node(pgdat, alloc_size);
+			alloc_bootmem_node_nopanic(pgdat, alloc_size);
 	} else {
 		/*
 		 * This case means that a zone whose size was 0 gets new memory
@@ -4141,7 +4141,8 @@ static void __init setup_usemap(struct pglist_data *pgdat,
 	unsigned long usemapsize = usemap_size(zonesize);
 	zone->pageblock_flags = NULL;
 	if (usemapsize)
-		zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
+		zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
+								   usemapsize);
 }
 #else
 static inline void setup_usemap(struct pglist_data *pgdat,
@@ -4307,7 +4308,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
 		size =  (end - start) * sizeof(struct page);
 		map = alloc_remap(pgdat->node_id, size);
 		if (!map)
-			map = alloc_bootmem_node(pgdat, size);
+			map = alloc_bootmem_node_nopanic(pgdat, size);
 		pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
 	}
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-- 
cgit v1.2.3


From ee85c2e1454603ebb9f8d87223ac79dcdc87fa32 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 11 May 2011 15:13:34 -0700
Subject: mm: add alloc_pages_exact_nid()

Add a alloc_pages_exact_nid() that allocates on a specific node.

The naming is quite broken, but fixing that would need a larger renaming
action.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: tweak comment]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: David Rientjes <rientjes@google.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>
---
 include/linux/gfp.h |  2 ++
 mm/page_alloc.c     | 49 +++++++++++++++++++++++++++++++++++++------------
 2 files changed, 39 insertions(+), 12 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index bfb8f934521e..56d8fc87fbbc 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -353,6 +353,8 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
 void free_pages_exact(void *virt, size_t size);
+/* This is different from alloc_pages_exact_node !!! */
+void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 #define __get_free_page(gfp_mask) \
 		__get_free_pages((gfp_mask), 0)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 454191a25173..570d944daeb5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2317,6 +2317,21 @@ void free_pages(unsigned long addr, unsigned int order)
 
 EXPORT_SYMBOL(free_pages);
 
+static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
+{
+	if (addr) {
+		unsigned long alloc_end = addr + (PAGE_SIZE << order);
+		unsigned long used = addr + PAGE_ALIGN(size);
+
+		split_page(virt_to_page((void *)addr), order);
+		while (used < alloc_end) {
+			free_page(used);
+			used += PAGE_SIZE;
+		}
+	}
+	return (void *)addr;
+}
+
 /**
  * alloc_pages_exact - allocate an exact number physically-contiguous pages.
  * @size: the number of bytes to allocate
@@ -2336,21 +2351,31 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
 	unsigned long addr;
 
 	addr = __get_free_pages(gfp_mask, order);
-	if (addr) {
-		unsigned long alloc_end = addr + (PAGE_SIZE << order);
-		unsigned long used = addr + PAGE_ALIGN(size);
-
-		split_page(virt_to_page((void *)addr), order);
-		while (used < alloc_end) {
-			free_page(used);
-			used += PAGE_SIZE;
-		}
-	}
-
-	return (void *)addr;
+	return make_alloc_exact(addr, order, size);
 }
 EXPORT_SYMBOL(alloc_pages_exact);
 
+/**
+ * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
+ *			   pages on a node.
+ * @size: the number of bytes to allocate
+ * @gfp_mask: GFP flags for the allocation
+ *
+ * Like alloc_pages_exact(), but try to allocate on node nid first before falling
+ * back.
+ * Note this is not alloc_pages_exact_node() which allocates on a specific node,
+ * but is not exact.
+ */
+void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
+{
+	unsigned order = get_order(size);
+	struct page *p = alloc_pages_node(nid, gfp_mask, order);
+	if (!p)
+		return NULL;
+	return make_alloc_exact((unsigned long)page_address(p), order, size);
+}
+EXPORT_SYMBOL(alloc_pages_exact_nid);
+
 /**
  * free_pages_exact - release memory allocated via alloc_pages_exact()
  * @virt: the value returned by alloc_pages_exact.
-- 
cgit v1.2.3


From b5e6ab589d570ac79cc939517fab05c87a23c262 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <randy.dunlap@oracle.com>
Date: Mon, 16 May 2011 13:16:54 -0700
Subject: mm: fix kernel-doc warning in page_alloc.c

Fix new kernel-doc warning in mm/page_alloc.c:

  Warning(mm/page_alloc.c:2370): No description found for parameter 'nid'

Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 570d944daeb5..3f8bce264df6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2358,6 +2358,7 @@ EXPORT_SYMBOL(alloc_pages_exact);
 /**
  * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
  *			   pages on a node.
+ * @nid: the preferred node ID where memory should be allocated
  * @size: the number of bytes to allocate
  * @gfp_mask: GFP flags for the allocation
  *
-- 
cgit v1.2.3


From 268bb0ce3e87872cb9290c322b0d35bce230d88f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 20 May 2011 12:50:29 -0700
Subject: sanitize <linux/prefetch.h> usage

Commit e66eed651fd1 ("list: remove prefetching from regular list
iterators") removed the include of prefetch.h from list.h, which
uncovered several cases that had apparently relied on that rather
obscure header file dependency.

So this fixes things up a bit, using

   grep -L linux/prefetch.h $(git grep -l '[^a-z_]prefetchw*(' -- '*.[ch]')
   grep -L 'prefetchw*(' $(git grep -l 'linux/prefetch.h' -- '*.[ch]')

to guide us in finding files that either need <linux/prefetch.h>
inclusion, or have it despite not needing it.

There are more of them around (mostly network drivers), but this gets
many core ones.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/hp/common/sba_iommu.c      | 1 +
 arch/ia64/mm/fault.c                 | 1 +
 arch/powerpc/lib/sstep.c             | 1 +
 arch/sh/kernel/cpu/sh4/sq.c          | 1 +
 arch/x86/include/asm/uaccess.h       | 1 -
 arch/x86/include/asm/uaccess_32.h    | 1 -
 arch/x86/include/asm/uaccess_64.h    | 1 -
 arch/x86/mm/fault.c                  | 1 +
 drivers/misc/sgi-gru/grufault.c      | 1 +
 drivers/misc/sgi-gru/grumain.c       | 1 +
 drivers/net/acenic.c                 | 1 +
 drivers/net/ehea/ehea_main.c         | 1 +
 drivers/staging/pohmelfs/inode.c     | 1 +
 drivers/usb/gadget/goku_udc.c        | 1 +
 drivers/usb/gadget/imx_udc.c         | 1 +
 drivers/usb/gadget/omap_udc.c        | 1 +
 drivers/usb/gadget/pxa25x_udc.c      | 1 +
 drivers/usb/gadget/pxa27x_udc.c      | 1 +
 drivers/usb/host/isp1362-hcd.c       | 1 +
 drivers/usb/host/sl811-hcd.c         | 1 +
 drivers/video/udlfb.c                | 1 +
 fs/btrfs/extent_io.c                 | 1 +
 fs/dcache.c                          | 1 +
 fs/logfs/dev_bdev.c                  | 1 +
 include/asm-generic/xor.h            | 2 +-
 kernel/rcutiny.c                     | 1 +
 kernel/rcutree.c                     | 1 +
 mm/page_alloc.c                      | 1 +
 mm/prio_tree.c                       | 1 +
 mm/slab.c                            | 1 +
 mm/vmscan.c                          | 1 +
 net/core/dst.c                       | 1 +
 net/core/pktgen.c                    | 1 +
 net/core/skbuff.c                    | 1 +
 tools/perf/util/include/linux/list.h | 2 +-
 35 files changed, 32 insertions(+), 5 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 4ce8d1358fee..c04dd576f333 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -37,6 +37,7 @@
 #include <linux/crash_dump.h>
 #include <linux/iommu-helper.h>
 #include <linux/dma-mapping.h>
+#include <linux/prefetch.h>
 
 #include <asm/delay.h>		/* ia64_get_itc() */
 #include <asm/io.h>
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 0799fea4c588..20b359376128 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
+#include <linux/prefetch.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index ae5189ab0049..f73daa6f3970 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/ptrace.h>
+#include <linux/prefetch.h>
 #include <asm/sstep.h>
 #include <asm/processor.h>
 #include <asm/uaccess.h>
diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c
index 14726eef1ce0..f0907995b4c9 100644
--- a/arch/sh/kernel/cpu/sh4/sq.c
+++ b/arch/sh/kernel/cpu/sh4/sq.c
@@ -20,6 +20,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/io.h>
+#include <linux/prefetch.h>
 #include <asm/page.h>
 #include <asm/cacheflush.h>
 #include <cpu/sq.h>
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 99f0ad753f32..99ddd148a760 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -6,7 +6,6 @@
 #include <linux/errno.h>
 #include <linux/compiler.h>
 #include <linux/thread_info.h>
-#include <linux/prefetch.h>
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 088d09fb1615..566e803cc602 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -6,7 +6,6 @@
  */
 #include <linux/errno.h>
 #include <linux/thread_info.h>
-#include <linux/prefetch.h>
 #include <linux/string.h>
 #include <asm/asm.h>
 #include <asm/page.h>
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 316708d5af92..1c66d30971ad 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -6,7 +6,6 @@
  */
 #include <linux/compiler.h>
 #include <linux/errno.h>
-#include <linux/prefetch.h>
 #include <linux/lockdep.h>
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 20e3f8702d1e..bcb394dfbb35 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -12,6 +12,7 @@
 #include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
 #include <linux/perf_event.h>		/* perf_sw_event		*/
 #include <linux/hugetlb.h>		/* hstate_index_to_shift	*/
+#include <linux/prefetch.h>		/* prefetchw			*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index 38657cdaf54d..c4acac74725c 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -33,6 +33,7 @@
 #include <linux/io.h>
 #include <linux/uaccess.h>
 #include <linux/security.h>
+#include <linux/prefetch.h>
 #include <asm/pgtable.h>
 #include "gru.h"
 #include "grutables.h"
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index f8538bbd0bfa..ae16c8cb4f3e 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -28,6 +28,7 @@
 #include <linux/device.h>
 #include <linux/list.h>
 #include <linux/err.h>
+#include <linux/prefetch.h>
 #include <asm/uv/uv_hub.h>
 #include "gru.h"
 #include "grutables.h"
diff --git a/drivers/net/acenic.c b/drivers/net/acenic.c
index ee648fe5d96f..01560bb67a7a 100644
--- a/drivers/net/acenic.c
+++ b/drivers/net/acenic.c
@@ -68,6 +68,7 @@
 #include <linux/sockios.h>
 #include <linux/firmware.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
 
 #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
 #include <linux/if_vlan.h>
diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c
index cf79cf759e13..2c60435f2beb 100644
--- a/drivers/net/ehea/ehea_main.c
+++ b/drivers/net/ehea/ehea_main.c
@@ -41,6 +41,7 @@
 #include <linux/memory.h>
 #include <asm/kexec.h>
 #include <linux/mutex.h>
+#include <linux/prefetch.h>
 
 #include <net/ip.h>
 
diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c
index c93ef207b0b4..c0f0ac7c1cdb 100644
--- a/drivers/staging/pohmelfs/inode.c
+++ b/drivers/staging/pohmelfs/inode.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/statfs.h>
 #include <linux/writeback.h>
+#include <linux/prefetch.h>
 
 #include "netfs.h"
 
diff --git a/drivers/usb/gadget/goku_udc.c b/drivers/usb/gadget/goku_udc.c
index 48a760220baf..bf6e11c758d5 100644
--- a/drivers/usb/gadget/goku_udc.c
+++ b/drivers/usb/gadget/goku_udc.c
@@ -38,6 +38,7 @@
 #include <linux/device.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
+#include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
diff --git a/drivers/usb/gadget/imx_udc.c b/drivers/usb/gadget/imx_udc.c
index 5408186afc35..ade40066decf 100644
--- a/drivers/usb/gadget/imx_udc.c
+++ b/drivers/usb/gadget/imx_udc.c
@@ -30,6 +30,7 @@
 #include <linux/delay.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
 
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
diff --git a/drivers/usb/gadget/omap_udc.c b/drivers/usb/gadget/omap_udc.c
index cb5cd422f3f5..82fd24935332 100644
--- a/drivers/usb/gadget/omap_udc.c
+++ b/drivers/usb/gadget/omap_udc.c
@@ -44,6 +44,7 @@
 #include <linux/usb/otg.h>
 #include <linux/dma-mapping.h>
 #include <linux/clk.h>
+#include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
 #include <asm/io.h>
diff --git a/drivers/usb/gadget/pxa25x_udc.c b/drivers/usb/gadget/pxa25x_udc.c
index 444b60aa15e9..365c02fc25fc 100644
--- a/drivers/usb/gadget/pxa25x_udc.c
+++ b/drivers/usb/gadget/pxa25x_udc.c
@@ -46,6 +46,7 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/io.h>
+#include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
 #include <asm/dma.h>
diff --git a/drivers/usb/gadget/pxa27x_udc.c b/drivers/usb/gadget/pxa27x_udc.c
index 78a39a41547d..57607696735c 100644
--- a/drivers/usb/gadget/pxa27x_udc.c
+++ b/drivers/usb/gadget/pxa27x_udc.c
@@ -32,6 +32,7 @@
 #include <linux/irq.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
 
 #include <asm/byteorder.h>
 #include <mach/hardware.h>
diff --git a/drivers/usb/host/isp1362-hcd.c b/drivers/usb/host/isp1362-hcd.c
index f97570a847ca..9c37dad3e816 100644
--- a/drivers/usb/host/isp1362-hcd.c
+++ b/drivers/usb/host/isp1362-hcd.c
@@ -81,6 +81,7 @@
 #include <linux/pm.h>
 #include <linux/io.h>
 #include <linux/bitmap.h>
+#include <linux/prefetch.h>
 
 #include <asm/irq.h>
 #include <asm/system.h>
diff --git a/drivers/usb/host/sl811-hcd.c b/drivers/usb/host/sl811-hcd.c
index 18b7099a8125..fafccc2fd331 100644
--- a/drivers/usb/host/sl811-hcd.c
+++ b/drivers/usb/host/sl811-hcd.c
@@ -47,6 +47,7 @@
 #include <linux/usb/sl811.h>
 #include <linux/usb/hcd.h>
 #include <linux/platform_device.h>
+#include <linux/prefetch.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
diff --git a/drivers/video/udlfb.c b/drivers/video/udlfb.c
index 68041d9dc260..695066b5b2e6 100644
--- a/drivers/video/udlfb.c
+++ b/drivers/video/udlfb.c
@@ -27,6 +27,7 @@
 #include <linux/fb.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
 #include <linux/delay.h>
 #include <video/udlfb.h>
 #include "edid.h"
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ba41da59e31b..96fcfa522dab 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -10,6 +10,7 @@
 #include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
+#include <linux/prefetch.h>
 #include "extent_io.h"
 #include "extent_map.h"
 #include "compat.h"
diff --git a/fs/dcache.c b/fs/dcache.c
index 22a0ef41bad1..18b2a1f10ed8 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -35,6 +35,7 @@
 #include <linux/hardirq.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rculist_bl.h>
+#include <linux/prefetch.h>
 #include "internal.h"
 
 /*
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 1adc8d455f0e..df0de27c2733 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -10,6 +10,7 @@
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
 #include <linux/gfp.h>
+#include <linux/prefetch.h>
 
 #define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))
 
diff --git a/include/asm-generic/xor.h b/include/asm-generic/xor.h
index aaab875e1a35..6028fb862254 100644
--- a/include/asm-generic/xor.h
+++ b/include/asm-generic/xor.h
@@ -13,7 +13,7 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <asm/processor.h>
+#include <linux/prefetch.h>
 
 static void
 xor_8regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 421abfd3641d..7bbac7d0f5ab 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -35,6 +35,7 @@
 #include <linux/init.h>
 #include <linux/time.h>
 #include <linux/cpu.h>
+#include <linux/prefetch.h>
 
 /* Controls for rcu_kthread() kthread, replacing RCU_SOFTIRQ used previously. */
 static struct task_struct *rcu_kthread_task;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index e486f7c3ffb8..f07d2f03181a 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -49,6 +49,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/wait.h>
 #include <linux/kthread.h>
+#include <linux/prefetch.h>
 
 #include "rcutree.h"
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3f8bce264df6..d49df7840541 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -54,6 +54,7 @@
 #include <trace/events/kmem.h>
 #include <linux/ftrace_event.h>
 #include <linux/memcontrol.h>
+#include <linux/prefetch.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
diff --git a/mm/prio_tree.c b/mm/prio_tree.c
index 603ae98d9694..799dcfd7cd8c 100644
--- a/mm/prio_tree.c
+++ b/mm/prio_tree.c
@@ -13,6 +13,7 @@
 
 #include <linux/mm.h>
 #include <linux/prio_tree.h>
+#include <linux/prefetch.h>
 
 /*
  * See lib/prio_tree.c for details on the general radix priority search tree
diff --git a/mm/slab.c b/mm/slab.c
index 46a9c163a92f..bcfa4987c8ae 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -115,6 +115,7 @@
 #include	<linux/debugobjects.h>
 #include	<linux/kmemcheck.h>
 #include	<linux/memory.h>
+#include	<linux/prefetch.h>
 
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8bfd45050a61..c9177202c8ce 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -42,6 +42,7 @@
 #include <linux/delayacct.h>
 #include <linux/sysctl.h>
 #include <linux/oom.h>
+#include <linux/prefetch.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
diff --git a/net/core/dst.c b/net/core/dst.c
index 91104d35de7d..0a3920bf3613 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <net/net_namespace.h>
 #include <linux/sched.h>
+#include <linux/prefetch.h>
 
 #include <net/dst.h>
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index aeeece72b72f..6ed9e27d8202 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -156,6 +156,7 @@
 #include <linux/wait.h>
 #include <linux/etherdevice.h>
 #include <linux/kthread.h>
+#include <linux/prefetch.h>
 #include <net/net_namespace.h>
 #include <net/checksum.h>
 #include <net/ipv6.h>
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7ebeed0a877c..960ea899c864 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -57,6 +57,7 @@
 #include <linux/init.h>
 #include <linux/scatterlist.h>
 #include <linux/errqueue.h>
+#include <linux/prefetch.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index 356c7e467b83..99358d61e9a5 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -23,5 +23,5 @@ static inline void list_del_range(struct list_head *begin,
  * @head: the head for your list.
  */
 #define list_for_each_from(pos, head) \
-	for (; prefetch(pos->next), pos != (head); pos = pos->next)
+	for (; pos != (head); pos = pos->next)
 #endif
-- 
cgit v1.2.3


From 7bf02ea22c6cdd09e2d3f1d3c3fe366b834ae9af Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Tue, 24 May 2011 17:11:16 -0700
Subject: arch, mm: filter disallowed nodes from arch specific show_mem
 functions

Architectures that implement their own show_mem() function did not pass
the filter argument to show_free_areas() to appropriately avoid emitting
the state of nodes that are disallowed in the current context.  This patch
now passes the filter argument to show_free_areas() so those nodes are now
avoided.

This patch also removes the show_free_areas() wrapper around
__show_free_areas() and converts existing callers to pass an empty filter.

ia64 emits additional information for each node, so skip_free_areas_zone()
must be made global to filter disallowed nodes and it is converted to use
a nid argument rather than a zone for this use case.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Helge Deller <deller@gmx.de>
Cc: James Bottomley <jejb@parisc-linux.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arm/mm/init.c               |  2 +-
 arch/ia64/mm/contig.c            | 10 ++++++----
 arch/ia64/mm/discontig.c         | 10 ++++++----
 arch/parisc/mm/init.c            |  2 +-
 arch/sparc/kernel/setup_32.c     |  2 +-
 arch/sparc/mm/init_32.c          |  2 +-
 arch/unicore32/mm/init.c         |  2 +-
 drivers/net/ioc3-eth.c           |  2 +-
 drivers/tty/serial/68328serial.c |  2 +-
 include/linux/mm.h               |  6 +++---
 lib/show_mem.c                   |  2 +-
 mm/nommu.c                       |  6 +++---
 mm/page_alloc.c                  | 22 ++++++++--------------
 13 files changed, 34 insertions(+), 36 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 76f82ae44efb..3f17ea146f0e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -85,7 +85,7 @@ void show_mem(unsigned int filter)
 	struct meminfo * mi = &meminfo;
 
 	printk("Mem-info:\n");
-	show_free_areas();
+	show_free_areas(filter);
 
 	for_each_bank (i, mi) {
 		struct membank *bank = &mi->bank[i];
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 9a018cde5d84..f114a3b14c6a 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -44,13 +44,16 @@ void show_mem(unsigned int filter)
 	pg_data_t *pgdat;
 
 	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
+	show_free_areas(filter);
 	printk(KERN_INFO "Node memory in pages:\n");
 	for_each_online_pgdat(pgdat) {
 		unsigned long present;
 		unsigned long flags;
 		int shared = 0, cached = 0, reserved = 0;
+		int nid = pgdat->node_id;
 
+		if (skip_free_areas_node(filter, nid))
+			continue;
 		pgdat_resize_lock(pgdat, &flags);
 		present = pgdat->node_present_pages;
 		for(i = 0; i < pgdat->node_spanned_pages; i++) {
@@ -64,8 +67,7 @@ void show_mem(unsigned int filter)
 				if (max_gap < LARGE_GAP)
 					continue;
 #endif
-				i = vmemmap_find_next_valid_pfn(pgdat->node_id,
-					 i) - 1;
+				i = vmemmap_find_next_valid_pfn(nid, i) - 1;
 				continue;
 			}
 			if (PageReserved(page))
@@ -81,7 +83,7 @@ void show_mem(unsigned int filter)
 		total_cached += cached;
 		total_shared += shared;
 		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-		       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+		       "shrd: %10d, swpd: %10d\n", nid,
 		       present, reserved, shared, cached);
 	}
 	printk(KERN_INFO "%ld pages of RAM\n", total_present);
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 82ab1bc6afb1..c641333cd997 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -622,13 +622,16 @@ void show_mem(unsigned int filter)
 	pg_data_t *pgdat;
 
 	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
+	show_free_areas(filter);
 	printk(KERN_INFO "Node memory in pages:\n");
 	for_each_online_pgdat(pgdat) {
 		unsigned long present;
 		unsigned long flags;
 		int shared = 0, cached = 0, reserved = 0;
+		int nid = pgdat->node_id;
 
+		if (skip_free_areas_node(filter, nid))
+			continue;
 		pgdat_resize_lock(pgdat, &flags);
 		present = pgdat->node_present_pages;
 		for(i = 0; i < pgdat->node_spanned_pages; i++) {
@@ -638,8 +641,7 @@ void show_mem(unsigned int filter)
 			if (pfn_valid(pgdat->node_start_pfn + i))
 				page = pfn_to_page(pgdat->node_start_pfn + i);
 			else {
-				i = vmemmap_find_next_valid_pfn(pgdat->node_id,
-					 i) - 1;
+				i = vmemmap_find_next_valid_pfn(nid, i) - 1;
 				continue;
 			}
 			if (PageReserved(page))
@@ -655,7 +657,7 @@ void show_mem(unsigned int filter)
 		total_cached += cached;
 		total_shared += shared;
 		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-		       "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+		       "shrd: %10d, swpd: %10d\n", nid,
 		       present, reserved, shared, cached);
 	}
 	printk(KERN_INFO "%ld pages of RAM\n", total_present);
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 5fa1e273006e..c5c9c65e502d 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -686,7 +686,7 @@ void show_mem(unsigned int filter)
 	int shared = 0, cached = 0;
 
 	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
+	show_free_areas(filter);
 #ifndef CONFIG_DISCONTIGMEM
 	i = max_mapnr;
 	while (i-- > 0) {
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 3609bdee9ed2..3249d3f3234d 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -82,7 +82,7 @@ static void prom_sync_me(void)
 			     "nop\n\t" : : "r" (&trapbase));
 
 	prom_printf("PROM SYNC COMMAND...\n");
-	show_free_areas();
+	show_free_areas(0);
 	if(current->pid != 0) {
 		local_irq_enable();
 		sys_sync();
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index 4c31e2b6e71b..28c2cc81c9a9 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -78,7 +78,7 @@ void __init kmap_init(void)
 void show_mem(unsigned int filter)
 {
 	printk("Mem-info:\n");
-	show_free_areas();
+	show_free_areas(filter);
 	printk("Free swap:       %6ldkB\n",
 	       nr_swap_pages << (PAGE_SHIFT-10));
 	printk("%ld pages of RAM\n", totalram_pages);
diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c
index 1fc02633f700..2d3e7112d2a3 100644
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -62,7 +62,7 @@ void show_mem(unsigned int filter)
 	struct meminfo *mi = &meminfo;
 
 	printk(KERN_DEFAULT "Mem-info:\n");
-	show_free_areas();
+	show_free_areas(filter);
 
 	for_each_bank(i, mi) {
 		struct membank *bank = &mi->bank[i];
diff --git a/drivers/net/ioc3-eth.c b/drivers/net/ioc3-eth.c
index 96c95617195f..32f07f868d89 100644
--- a/drivers/net/ioc3-eth.c
+++ b/drivers/net/ioc3-eth.c
@@ -915,7 +915,7 @@ static void ioc3_alloc_rings(struct net_device *dev)
 
 			skb = ioc3_alloc_skb(RX_BUF_ALLOC_SIZE, GFP_ATOMIC);
 			if (!skb) {
-				show_free_areas();
+				show_free_areas(0);
 				continue;
 			}
 
diff --git a/drivers/tty/serial/68328serial.c b/drivers/tty/serial/68328serial.c
index d5bfd41707e7..e0a77540b8ca 100644
--- a/drivers/tty/serial/68328serial.c
+++ b/drivers/tty/serial/68328serial.c
@@ -281,7 +281,7 @@ static void receive_chars(struct m68k_serial *info, unsigned short rx)
 #ifdef CONFIG_MAGIC_SYSRQ
 			} else if (ch == 0x10) { /* ^P */
 				show_state();
-				show_free_areas();
+				show_free_areas(0);
 				show_buffers();
 /*				show_net_buffers(); */
 				return;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6507dde38b16..1746f67c33de 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -862,13 +862,13 @@ extern void pagefault_out_of_memory(void);
 #define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)
 
 /*
- * Flags passed to show_mem() and __show_free_areas() to suppress output in
+ * Flags passed to show_mem() and show_free_areas() to suppress output in
  * various contexts.
  */
 #define SHOW_MEM_FILTER_NODES	(0x0001u)	/* filter disallowed nodes */
 
-extern void show_free_areas(void);
-extern void __show_free_areas(unsigned int flags);
+extern void show_free_areas(unsigned int flags);
+extern bool skip_free_areas_node(unsigned int flags, int nid);
 
 int shmem_lock(struct file *file, int lock, struct user_struct *user);
 struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
diff --git a/lib/show_mem.c b/lib/show_mem.c
index 90cbe4bb5960..4407f8c9b1f7 100644
--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -16,7 +16,7 @@ void show_mem(unsigned int filter)
 		nonshared = 0, highmem = 0;
 
 	printk("Mem-Info:\n");
-	__show_free_areas(filter);
+	show_free_areas(filter);
 
 	for_each_online_pgdat(pgdat) {
 		unsigned long i, flags;
diff --git a/mm/nommu.c b/mm/nommu.c
index c4c542c736a9..5afce48ce339 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1235,7 +1235,7 @@ error_free:
 enomem:
 	printk("Allocation of length %lu from process %d (%s) failed\n",
 	       len, current->pid, current->comm);
-	show_free_areas();
+	show_free_areas(0);
 	return -ENOMEM;
 }
 
@@ -1468,14 +1468,14 @@ error_getting_vma:
 	printk(KERN_WARNING "Allocation of vma for %lu byte allocation"
 	       " from process %d failed\n",
 	       len, current->pid);
-	show_free_areas();
+	show_free_areas(0);
 	return -ENOMEM;
 
 error_getting_region:
 	printk(KERN_WARNING "Allocation of vm region for %lu byte allocation"
 	       " from process %d failed\n",
 	       len, current->pid);
-	show_free_areas();
+	show_free_areas(0);
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(do_mmap_pgoff);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9d5498e2d0f5..b1447522d346 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2473,10 +2473,10 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 #endif
 
 /*
- * Determine whether the zone's node should be displayed or not, depending on
- * whether SHOW_MEM_FILTER_NODES was passed to __show_free_areas().
+ * Determine whether the node should be displayed or not, depending on whether
+ * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
  */
-static bool skip_free_areas_zone(unsigned int flags, const struct zone *zone)
+bool skip_free_areas_node(unsigned int flags, int nid)
 {
 	bool ret = false;
 
@@ -2484,8 +2484,7 @@ static bool skip_free_areas_zone(unsigned int flags, const struct zone *zone)
 		goto out;
 
 	get_mems_allowed();
-	ret = !node_isset(zone->zone_pgdat->node_id,
-				cpuset_current_mems_allowed);
+	ret = !node_isset(nid, cpuset_current_mems_allowed);
 	put_mems_allowed();
 out:
 	return ret;
@@ -2500,13 +2499,13 @@ out:
  * Suppresses nodes that are not allowed by current's cpuset if
  * SHOW_MEM_FILTER_NODES is passed.
  */
-void __show_free_areas(unsigned int filter)
+void show_free_areas(unsigned int filter)
 {
 	int cpu;
 	struct zone *zone;
 
 	for_each_populated_zone(zone) {
-		if (skip_free_areas_zone(filter, zone))
+		if (skip_free_areas_node(filter, zone_to_nid(zone)))
 			continue;
 		show_node(zone);
 		printk("%s per-cpu:\n", zone->name);
@@ -2549,7 +2548,7 @@ void __show_free_areas(unsigned int filter)
 	for_each_populated_zone(zone) {
 		int i;
 
-		if (skip_free_areas_zone(filter, zone))
+		if (skip_free_areas_node(filter, zone_to_nid(zone)))
 			continue;
 		show_node(zone);
 		printk("%s"
@@ -2618,7 +2617,7 @@ void __show_free_areas(unsigned int filter)
 	for_each_populated_zone(zone) {
  		unsigned long nr[MAX_ORDER], flags, order, total = 0;
 
-		if (skip_free_areas_zone(filter, zone))
+		if (skip_free_areas_node(filter, zone_to_nid(zone)))
 			continue;
 		show_node(zone);
 		printk("%s: ", zone->name);
@@ -2639,11 +2638,6 @@ void __show_free_areas(unsigned int filter)
 	show_swap_cache_info();
 }
 
-void show_free_areas(void)
-{
-	__show_free_areas(0);
-}
-
 static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
 {
 	zoneref->zone = zone;
-- 
cgit v1.2.3


From ac3bbec5ec69b973317677e038de2d1a0c90c18c Mon Sep 17 00:00:00 2001
From: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Date: Tue, 24 May 2011 17:11:21 -0700
Subject: mm: remove unused zone_idx variable from set_migratetype_isolate

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b1447522d346..eb19ba8396c3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5502,10 +5502,8 @@ int set_migratetype_isolate(struct page *page)
 	struct memory_isolate_notify arg;
 	int notifier_ret;
 	int ret = -EBUSY;
-	int zone_idx;
 
 	zone = page_zone(page);
-	zone_idx = zone_idx(zone);
 
 	spin_lock_irqsave(&zone->lock, flags);
 
-- 
cgit v1.2.3


From 839a4fcc8af7412be2efd11f0bd0504757f79f08 Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Tue, 24 May 2011 17:11:31 -0700
Subject: mm, mem-hotplug: fix section mismatch.
 setup_per_zone_inactive_ratio() should be __meminit.

Commit bce7394a3e ("page-allocator: reset wmark_min and inactive ratio of
zone when hotplug happens") introduced invalid section references.  Now,
setup_per_zone_inactive_ratio() is marked __init and then it can't be
referenced from memory hotplug code.

This patch marks it as __meminit and also marks caller as __ref.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/memory_hotplug.c | 4 ++--
 mm/page_alloc.c     | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9ca1d604f7cd..2c4edc459fb0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -400,7 +400,7 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 }
 
 
-int online_pages(unsigned long pfn, unsigned long nr_pages)
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 {
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
@@ -795,7 +795,7 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	return offlined;
 }
 
-static int offline_pages(unsigned long start_pfn,
+static int __ref offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn, unsigned long timeout)
 {
 	unsigned long pfn, nr_pages, expire;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eb19ba8396c3..56d0be36be9d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5094,7 +5094,7 @@ void setup_per_zone_wmarks(void)
  *    1TB     101        10GB
  *   10TB     320        32GB
  */
-void calculate_zone_inactive_ratio(struct zone *zone)
+void __meminit calculate_zone_inactive_ratio(struct zone *zone)
 {
 	unsigned int gb, ratio;
 
@@ -5108,7 +5108,7 @@ void calculate_zone_inactive_ratio(struct zone *zone)
 	zone->inactive_ratio = ratio;
 }
 
-static void __init setup_per_zone_inactive_ratio(void)
+static void __meminit setup_per_zone_inactive_ratio(void)
 {
 	struct zone *zone;
 
-- 
cgit v1.2.3


From 1b79acc91115ba47e744b70bb166b77bd94f5855 Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Tue, 24 May 2011 17:11:32 -0700
Subject: mm, mem-hotplug: recalculate lowmem_reserve when memory hotplug
 occurs

Currently, memory hotplug calls setup_per_zone_wmarks() and
calculate_zone_inactive_ratio(), but doesn't call
setup_per_zone_lowmem_reserve().

It means the number of reserved pages aren't updated even if memory hot
plug occur.  This patch fixes it.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h  | 2 +-
 mm/memory_hotplug.c | 9 +++++----
 mm/page_alloc.c     | 4 ++--
 3 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 57d3d5fade16..e173cd297d88 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1381,7 +1381,7 @@ extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_zone(unsigned long, int, unsigned long,
 				unsigned long, enum memmap_context);
 extern void setup_per_zone_wmarks(void);
-extern void calculate_zone_inactive_ratio(struct zone *zone);
+extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
 extern void __init mmap_init(void);
 extern void show_mem(unsigned int flags);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 2c4edc459fb0..59ac18fefd65 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -459,8 +459,9 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 		zone_pcp_update(zone);
 
 	mutex_unlock(&zonelists_mutex);
-	setup_per_zone_wmarks();
-	calculate_zone_inactive_ratio(zone);
+
+	init_per_zone_wmark_min();
+
 	if (onlined_pages) {
 		kswapd_run(zone_to_nid(zone));
 		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
@@ -893,8 +894,8 @@ repeat:
 	zone->zone_pgdat->node_present_pages -= offlined_pages;
 	totalram_pages -= offlined_pages;
 
-	setup_per_zone_wmarks();
-	calculate_zone_inactive_ratio(zone);
+	init_per_zone_wmark_min();
+
 	if (!node_present_pages(node)) {
 		node_clear_state(node, N_HIGH_MEMORY);
 		kswapd_stop(node);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 56d0be36be9d..e133cea36932 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5094,7 +5094,7 @@ void setup_per_zone_wmarks(void)
  *    1TB     101        10GB
  *   10TB     320        32GB
  */
-void __meminit calculate_zone_inactive_ratio(struct zone *zone)
+static void __meminit calculate_zone_inactive_ratio(struct zone *zone)
 {
 	unsigned int gb, ratio;
 
@@ -5140,7 +5140,7 @@ static void __meminit setup_per_zone_inactive_ratio(void)
  * 8192MB:	11584k
  * 16384MB:	16384k
  */
-static int __init init_per_zone_wmark_min(void)
+int __meminit init_per_zone_wmark_min(void)
 {
 	unsigned long lowmem_kbytes;
 
-- 
cgit v1.2.3


From a6cccdc36c966e51fd969560d870cfd37afbfa9c Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Tue, 24 May 2011 17:11:33 -0700
Subject: mm, mem-hotplug: update pcp->stat_threshold when memory hotplug occur

Currently, cpu hotplug updates pcp->stat_threshold, but memory hotplug
doesn't.  There is no reason for this.

[akpm@linux-foundation.org: fix CONFIG_SMP=n build]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmstat.h | 3 +++
 mm/page_alloc.c        | 2 ++
 mm/vmstat.c            | 3 +--
 3 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index e73d1030f2f7..51359837511a 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -261,6 +261,7 @@ extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
 void refresh_cpu_vm_stats(int);
+void refresh_zone_stat_thresholds(void);
 
 int calculate_pressure_threshold(struct zone *zone);
 int calculate_normal_threshold(struct zone *zone);
@@ -313,6 +314,8 @@ static inline void __dec_zone_page_state(struct page *page,
 #define set_pgdat_percpu_threshold(pgdat, callback) { }
 
 static inline void refresh_cpu_vm_stats(int cpu) { }
+static inline void refresh_zone_stat_thresholds(void) { }
+
 #endif		/* CONFIG_SMP */
 
 extern const char * const vmstat_text[];
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e133cea36932..77773329aa72 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -39,6 +39,7 @@
 #include <linux/memory_hotplug.h>
 #include <linux/nodemask.h>
 #include <linux/vmalloc.h>
+#include <linux/vmstat.h>
 #include <linux/mempolicy.h>
 #include <linux/stop_machine.h>
 #include <linux/sort.h>
@@ -5152,6 +5153,7 @@ int __meminit init_per_zone_wmark_min(void)
 	if (min_free_kbytes > 65536)
 		min_free_kbytes = 65536;
 	setup_per_zone_wmarks();
+	refresh_zone_stat_thresholds();
 	setup_per_zone_lowmem_reserve();
 	setup_per_zone_inactive_ratio();
 	return 0;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 209546a8bdd5..20c18b7694b2 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -157,7 +157,7 @@ int calculate_normal_threshold(struct zone *zone)
 /*
  * Refresh the thresholds for each zone.
  */
-static void refresh_zone_stat_thresholds(void)
+void refresh_zone_stat_thresholds(void)
 {
 	struct zone *zone;
 	int cpu;
@@ -1201,7 +1201,6 @@ static int __init setup_vmstat(void)
 #ifdef CONFIG_SMP
 	int cpu;
 
-	refresh_zone_stat_thresholds();
 	register_cpu_notifier(&vmstat_notifier);
 
 	for_each_online_cpu(cpu)
-- 
cgit v1.2.3


From c6a140bf164829769499b5e50d380893da39b29e Mon Sep 17 00:00:00 2001
From: Andrea Arcangeli <aarcange@redhat.com>
Date: Tue, 24 May 2011 17:11:38 -0700
Subject: mm/compaction: reverse the change that forbade sync migraton with
 __GFP_NO_KSWAPD

It's uncertain this has been beneficial, so it's safer to undo it.  All
other compaction users would still go in synchronous mode if a first
attempt at async compaction failed.  Hopefully we don't need to force
special behavior for THP (which is the only __GFP_NO_KSWAPD user so far
and it's the easier to exercise and to be noticeable).  This also make
__GFP_NO_KSWAPD return to its original strict semantics specific to bypass
kswapd, as THP allocations have khugepaged for the async THP
allocations/compactions.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Alex Villacis Lasso <avillaci@fiec.espol.edu.ec>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 77773329aa72..83eaa2eb72f8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2107,7 +2107,7 @@ rebalance:
 					sync_migration);
 	if (page)
 		goto got_pg;
-	sync_migration = !(gfp_mask & __GFP_NO_KSWAPD);
+	sync_migration = true;
 
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
-- 
cgit v1.2.3


From a238ab5b0239575c179f4976064192c3f7409dad Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave@linux.vnet.ibm.com>
Date: Tue, 24 May 2011 17:12:16 -0700
Subject: mm: break out page allocation warning code

This originally started as a simple patch to give vmalloc() some more
verbose output on failure on top of the plain page allocator messages.
Johannes suggested that it might be nicer to lead with the vmalloc() info
_before_ the page allocator messages.

But, I do think there's a lot of value in what __alloc_pages_slowpath()
does with its filtering and so forth.

This patch creates a new function which other allocators can call instead
of relying on the internal page allocator warnings.  It also gives this
function private rate-limiting which separates it from other
printk_ratelimit() users.

Signed-off-by: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h |  2 ++
 mm/page_alloc.c    | 62 ++++++++++++++++++++++++++++++++++++------------------
 2 files changed, 43 insertions(+), 21 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2ad0ac8c3f32..8e2f2cd821f7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1387,6 +1387,8 @@ extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 extern int after_bootmem;
 
+extern void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
+
 extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 83eaa2eb72f8..44019da9632e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -30,6 +30,7 @@
 #include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
+#include <linux/ratelimit.h>
 #include <linux/oom.h>
 #include <linux/notifier.h>
 #include <linux/topology.h>
@@ -1736,6 +1737,45 @@ static inline bool should_suppress_show_mem(void)
 	return ret;
 }
 
+static DEFINE_RATELIMIT_STATE(nopage_rs,
+		DEFAULT_RATELIMIT_INTERVAL,
+		DEFAULT_RATELIMIT_BURST);
+
+void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
+{
+	va_list args;
+	unsigned int filter = SHOW_MEM_FILTER_NODES;
+
+	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+		return;
+
+	/*
+	 * This documents exceptions given to allocations in certain
+	 * contexts that are allowed to allocate outside current's set
+	 * of allowed nodes.
+	 */
+	if (!(gfp_mask & __GFP_NOMEMALLOC))
+		if (test_thread_flag(TIF_MEMDIE) ||
+		    (current->flags & (PF_MEMALLOC | PF_EXITING)))
+			filter &= ~SHOW_MEM_FILTER_NODES;
+	if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
+		filter &= ~SHOW_MEM_FILTER_NODES;
+
+	if (fmt) {
+		printk(KERN_WARNING);
+		va_start(args, fmt);
+		vprintk(fmt, args);
+		va_end(args);
+	}
+
+	pr_warning("%s: page allocation failure: order:%d, mode:0x%x\n",
+		   current->comm, order, gfp_mask);
+
+	dump_stack();
+	if (!should_suppress_show_mem())
+		show_mem(filter);
+}
+
 static inline int
 should_alloc_retry(gfp_t gfp_mask, unsigned int order,
 				unsigned long pages_reclaimed)
@@ -2178,27 +2218,7 @@ rebalance:
 	}
 
 nopage:
-	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
-		unsigned int filter = SHOW_MEM_FILTER_NODES;
-
-		/*
-		 * This documents exceptions given to allocations in certain
-		 * contexts that are allowed to allocate outside current's set
-		 * of allowed nodes.
-		 */
-		if (!(gfp_mask & __GFP_NOMEMALLOC))
-			if (test_thread_flag(TIF_MEMDIE) ||
-			    (current->flags & (PF_MEMALLOC | PF_EXITING)))
-				filter &= ~SHOW_MEM_FILTER_NODES;
-		if (in_interrupt() || !wait)
-			filter &= ~SHOW_MEM_FILTER_NODES;
-
-		pr_warning("%s: page allocation failure. order:%d, mode:0x%x\n",
-			current->comm, order, gfp_mask);
-		dump_stack();
-		if (!should_suppress_show_mem())
-			show_mem(filter);
-	}
+	warn_alloc_failed(gfp_mask, order, NULL);
 	return page;
 got_pg:
 	if (kmemcheck_enabled)
-- 
cgit v1.2.3


From 6d3163ce86dd386b4f7bda80241d7fea2bc0bb1d Mon Sep 17 00:00:00 2001
From: Arve Hjønnevåg <arve@android.com>
Date: Tue, 24 May 2011 17:12:24 -0700
Subject: mm: check if any page in a pageblock is reserved before marking it
 MIGRATE_RESERVE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes a problem where the first pageblock got marked MIGRATE_RESERVE
even though it only had a few free pages.  eg, On current ARM port, The
kernel starts at offset 0x8000 to leave room for boot parameters, and the
memory is freed later.

This in turn caused no contiguous memory to be reserved and frequent
kswapd wakeups that emptied the caches to get more contiguous memory.

Unfortunatelly, ARM needs order-2 allocation for pgd (see
arm/mm/pgd.c#pgd_alloc()).  Therefore the issue is not minor nor easy
avoidable.

[kosaki.motohiro@jp.fujitsu.com: added some explanation]
[kosaki.motohiro@jp.fujitsu.com: add !pfn_valid_within() to check]
[minchan.kim@gmail.com: check end_pfn in pageblock_is_reserved]
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Arve Hjønnevåg <arve@android.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Dave Hansen <dave@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 44019da9632e..01e6b614839d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3328,6 +3328,20 @@ static inline unsigned long wait_table_bits(unsigned long size)
 
 #define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
 
+/*
+ * Check if a pageblock contains reserved pages
+ */
+static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+		if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn)))
+			return 1;
+	}
+	return 0;
+}
+
 /*
  * Mark a number of pageblocks as MIGRATE_RESERVE. The number
  * of blocks reserved is based on min_wmark_pages(zone). The memory within
@@ -3337,7 +3351,7 @@ static inline unsigned long wait_table_bits(unsigned long size)
  */
 static void setup_zone_migrate_reserve(struct zone *zone)
 {
-	unsigned long start_pfn, pfn, end_pfn;
+	unsigned long start_pfn, pfn, end_pfn, block_end_pfn;
 	struct page *page;
 	unsigned long block_migratetype;
 	int reserve;
@@ -3367,7 +3381,8 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 			continue;
 
 		/* Blocks with reserved pages will never free, skip them. */
-		if (PageReserved(page))
+		block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+		if (pageblock_is_reserved(pfn, block_end_pfn))
 			continue;
 
 		block_migratetype = get_pageblock_migratetype(page);
-- 
cgit v1.2.3


From a197b59ae6e8bee56fcef37ea2482dc08414e2ac Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Tue, 24 May 2011 17:12:35 -0700
Subject: mm: fail GFP_DMA allocations when ZONE_DMA is not configured

The page allocator will improperly return a page from ZONE_NORMAL even
when __GFP_DMA is passed if CONFIG_ZONE_DMA is disabled.  The caller
expects DMA memory, perhaps for ISA devices with 16-bit address registers,
and may get higher memory resulting in undefined behavior.

This patch causes the page allocator to return NULL in such circumstances
with a warning emitted to the kernel log on the first occurrence.

Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 01e6b614839d..10a8c6da385f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2247,6 +2247,10 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
 	if (should_fail_alloc_page(gfp_mask, order))
 		return NULL;
+#ifndef CONFIG_ZONE_DMA
+	if (WARN_ON_ONCE(gfp_mask & __GFP_DMA))
+		return NULL;
+#endif
 
 	/*
 	 * Check the zones suitable for the gfp_mask contain at least one
-- 
cgit v1.2.3


From cfa54a0fcfc1017c6f122b6f21aaba36daa07f71 Mon Sep 17 00:00:00 2001
From: Andrew Barry <abarry@cray.com>
Date: Tue, 24 May 2011 17:12:52 -0700
Subject: mm/page_alloc.c: prevent unending loop in __alloc_pages_slowpath()

I believe I found a problem in __alloc_pages_slowpath, which allows a
process to get stuck endlessly looping, even when lots of memory is
available.

Running an I/O and memory intensive stress-test I see a 0-order page
allocation with __GFP_IO and __GFP_WAIT, running on a system with very
little free memory.  Right about the same time that the stress-test gets
killed by the OOM-killer, the utility trying to allocate memory gets stuck
in __alloc_pages_slowpath even though most of the systems memory was freed
by the oom-kill of the stress-test.

The utility ends up looping from the rebalance label down through the
wait_iff_congested continiously.  Because order=0,
__alloc_pages_direct_compact skips the call to get_page_from_freelist.
Because all of the reclaimable memory on the system has already been
reclaimed, __alloc_pages_direct_reclaim skips the call to
get_page_from_freelist.  Since there is no __GFP_FS flag, the block with
__alloc_pages_may_oom is skipped.  The loop hits the wait_iff_congested,
then jumps back to rebalance without ever trying to
get_page_from_freelist.  This loop repeats infinitely.

The test case is pretty pathological.  Running a mix of I/O stress-tests
that do a lot of fork() and consume all of the system memory, I can pretty
reliably hit this on 600 nodes, in about 12 hours.  32GB/node.

Signed-off-by: Andrew Barry <abarry@cray.com>
Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Reviewed-by: Rik van Riel<riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'mm/page_alloc.c')

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 10a8c6da385f..2a00f17c3bf4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2106,6 +2106,7 @@ restart:
 		first_zones_zonelist(zonelist, high_zoneidx, NULL,
 					&preferred_zone);
 
+rebalance:
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2113,7 +2114,6 @@ restart:
 	if (page)
 		goto got_pg;
 
-rebalance:
 	/* Allocate without watermarks if the context allows */
 	if (alloc_flags & ALLOC_NO_WATERMARKS) {
 		page = __alloc_pages_high_priority(gfp_mask, order,
-- 
cgit v1.2.3


From 246e87a9393448c20873bc5dee64be68ed559e24 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Thu, 26 May 2011 16:25:34 -0700
Subject: memcg: fix get_scan_count() for small targets

During memory reclaim we determine the number of pages to be scanned per
zone as

	(anon + file) >> priority.
Assume
	scan = (anon + file) >> priority.

If scan < SWAP_CLUSTER_MAX, the scan will be skipped for this time and
priority gets higher.  This has some problems.

  1. This increases priority as 1 without any scan.
     To do scan in this priority, amount of pages should be larger than 512M.
     If pages>>priority < SWAP_CLUSTER_MAX, it's recorded and scan will be
     batched, later. (But we lose 1 priority.)
     If memory size is below 16M, pages >> priority is 0 and no scan in
     DEF_PRIORITY forever.

  2. If zone->all_unreclaimabe==true, it's scanned only when priority==0.
     So, x86's ZONE_DMA will never be recoverred until the user of pages
     frees memory by itself.

  3. With memcg, the limit of memory can be small. When using small memcg,
     it gets priority < DEF_PRIORITY-2 very easily and need to call
     wait_iff_congested().
     For doing scan before priorty=9, 64MB of memory should be used.

Then, this patch tries to scan SWAP_CLUSTER_MAX of pages in force...when

  1. the target is enough small.
  2. it's kswapd or memcg reclaim.

Then we can avoid rapid priority drop and may be able to recover
all_unreclaimable in a small zones.  And this patch removes nr_saved_scan.
 This will allow scanning in this priority even when pages >> priority is
very small.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Ying Han <yinghan@google.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mmzone.h |  5 -----
 mm/page_alloc.c        |  4 +---
 mm/vmscan.c            | 60 +++++++++++++++++++++++++++-----------------------
 3 files changed, 34 insertions(+), 35 deletions(-)

(limited to 'mm/page_alloc.c')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 217bcf6bca77..29312bdf119f 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -273,11 +273,6 @@ struct zone_reclaim_stat {
 	 */
 	unsigned long		recent_rotated[2];
 	unsigned long		recent_scanned[2];
-
-	/*
-	 * accumulated for batching
-	 */
-	unsigned long		nr_saved_scan[NR_LRU_LISTS];
 };
 
 struct zone {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2a00f17c3bf4..a4e1db3f1981 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4323,10 +4323,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		zone->zone_pgdat = pgdat;
 
 		zone_pcp_init(zone);
-		for_each_lru(l) {
+		for_each_lru(l)
 			INIT_LIST_HEAD(&zone->lru[l].list);
-			zone->reclaim_stat.nr_saved_scan[l] = 0;
-		}
 		zone->reclaim_stat.recent_rotated[0] = 0;
 		zone->reclaim_stat.recent_rotated[1] = 0;
 		zone->reclaim_stat.recent_scanned[0] = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b0875871820d..2e8fbacd8744 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1717,26 +1717,6 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 	return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
 }
 
-/*
- * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
- * until we collected @swap_cluster_max pages to scan.
- */
-static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
-				       unsigned long *nr_saved_scan)
-{
-	unsigned long nr;
-
-	*nr_saved_scan += nr_to_scan;
-	nr = *nr_saved_scan;
-
-	if (nr >= SWAP_CLUSTER_MAX)
-		*nr_saved_scan = 0;
-	else
-		nr = 0;
-
-	return nr;
-}
-
 /*
  * Determine how aggressively the anon and file LRU lists should be
  * scanned.  The relative value of each set of LRU lists is determined
@@ -1755,6 +1735,22 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	u64 fraction[2], denominator;
 	enum lru_list l;
 	int noswap = 0;
+	int force_scan = 0;
+
+
+	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+
+	if (((anon + file) >> priority) < SWAP_CLUSTER_MAX) {
+		/* kswapd does zone balancing and need to scan this zone */
+		if (scanning_global_lru(sc) && current_is_kswapd())
+			force_scan = 1;
+		/* memcg may have small limit and need to avoid priority drop */
+		if (!scanning_global_lru(sc))
+			force_scan = 1;
+	}
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (!sc->may_swap || (nr_swap_pages <= 0)) {
@@ -1765,11 +1761,6 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 		goto out;
 	}
 
-	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
-	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
-
 	if (scanning_global_lru(sc)) {
 		free  = zone_page_state(zone, NR_FREE_PAGES);
 		/* If we have very few page cache pages,
@@ -1836,8 +1827,23 @@ out:
 			scan >>= priority;
 			scan = div64_u64(scan * fraction[file], denominator);
 		}
-		nr[l] = nr_scan_try_batch(scan,
-					  &reclaim_stat->nr_saved_scan[l]);
+
+		/*
+		 * If zone is small or memcg is small, nr[l] can be 0.
+		 * This results no-scan on this priority and priority drop down.
+		 * For global direct reclaim, it can visit next zone and tend
+		 * not to have problems. For global kswapd, it's for zone
+		 * balancing and it need to scan a small amounts. When using
+		 * memcg, priority drop can cause big latency. So, it's better
+		 * to scan small amount. See may_noscan above.
+		 */
+		if (!scan && force_scan) {
+			if (file)
+				scan = SWAP_CLUSTER_MAX;
+			else if (!noswap)
+				scan = SWAP_CLUSTER_MAX;
+		}
+		nr[l] = scan;
 	}
 }
 
-- 
cgit v1.2.3