3.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Rientjes <rientjes@xxxxxxxxxx>
commit 4b59e6c4730978679b414a8da61514a2518da512 upstream.
On large systems with a lot of memory, walking all RAM to determine page
types may take a half second or even more.
In non-blockable contexts, the page allocator will emit a page allocation
failure warning unless __GFP_NOWARN is specified. In such contexts, irqs
are typically disabled and such a lengthy delay may even result in NMI
watchdog timeouts.
To fix this, suppress the page walk in such contexts when printing the
page allocation failure warning.
Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxx>
Cc: Dave Hansen <dave@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Xishi Qiu <qiuxishi@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/arm/mm/init.c | 3 +++
arch/ia64/mm/contig.c | 2 ++
arch/ia64/mm/discontig.c | 2 ++
arch/parisc/mm/init.c | 2 ++
arch/unicore32/mm/init.c | 3 +++
include/linux/mm.h | 3 ++-
lib/show_mem.c | 3 +++
mm/page_alloc.c | 7 +++++++
8 files changed, 24 insertions(+), 1 deletion(-)
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -98,6 +98,9 @@ void show_mem(unsigned int filter)
printk("Mem-info:\n");
show_free_areas(filter);
+ if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+ return;
+
for_each_bank (i, mi) {
struct membank *bank = &mi->bank[i];
unsigned int pfn1, pfn2;
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -47,6 +47,8 @@ void show_mem(unsigned int filter)
printk(KERN_INFO "Mem-info:\n");
show_free_areas(filter);
printk(KERN_INFO "Node memory in pages:\n");
+ if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+ return;
for_each_online_pgdat(pgdat) {
unsigned long present;
unsigned long flags;
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -623,6 +623,8 @@ void show_mem(unsigned int filter)
printk(KERN_INFO "Mem-info:\n");
show_free_areas(filter);
+ if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+ return;
printk(KERN_INFO "Node memory in pages:\n");
for_each_online_pgdat(pgdat) {
unsigned long present;
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -685,6 +685,8 @@ void show_mem(unsigned int filter)
printk(KERN_INFO "Mem-info:\n");
show_free_areas(filter);
+ if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+ return;
#ifndef CONFIG_DISCONTIGMEM
i = max_mapnr;
while (i-- > 0) {
--- a/arch/unicore32/mm/init.c
+++ b/arch/unicore32/mm/init.c
@@ -66,6 +66,9 @@ void show_mem(unsigned int filter)
printk(KERN_DEFAULT "Mem-info:\n");
show_free_areas(filter);
+ if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+ return;
+
for_each_bank(i, mi) {
struct membank *bank = &mi->bank[i];
unsigned int pfn1, pfn2;
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -866,7 +866,8 @@ extern void pagefault_out_of_memory(void
* Flags passed to show_mem() and show_free_areas() to suppress output in
* various contexts.
*/
-#define SHOW_MEM_FILTER_NODES (0x0001u) /* filter disallowed nodes */
+#define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */
+#define SHOW_MEM_FILTER_PAGE_COUNT (0x0002u) /* page type count */
extern void show_free_areas(unsigned int flags);
extern bool skip_free_areas_node(unsigned int flags, int nid);
--- a/lib/show_mem.c
+++ b/lib/show_mem.c
@@ -18,6 +18,9 @@ void show_mem(unsigned int filter)
printk("Mem-Info:\n");
show_free_areas(filter);
+ if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
+ return;
+
for_each_online_pgdat(pgdat) {
unsigned long i, flags;
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1885,6 +1885,13 @@ void warn_alloc_failed(gfp_t gfp_mask, i
return;
/*
+ * Walking all memory to count page types is very expensive and should
+ * be inhibited in non-blockable contexts.
+ */
+ if (!(gfp_mask & __GFP_WAIT))
+ filter |= SHOW_MEM_FILTER_PAGE_COUNT;
+
+ /*
* This documents exceptions given to allocations in certain
* contexts that are allowed to allocate outside current's set
* of allowed nodes.
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html