summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2014-06-04 16:10:16 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-06-04 16:54:09 -0700
commite58469bafd0524e848c3733bc3918d854595e20f (patch)
tree5881b188eb2c179576773aedf5b11983047350aa /mm
parent5dab29113ca56335c78be3f98bf5ddf2ef8eb6a6 (diff)
mm: page_alloc: use word-based accesses for get/set pageblock bitmaps
The test_bit operations in get/set pageblock flags are expensive. This patch reads the bitmap on a word basis and use shifts and masks to isolate the bits of interest. Similarly masks are used to set a local copy of the bitmap and then use cmpxchg to update the bitmap if there have been no other changes made in parallel. In a test running dd onto tmpfs the overhead of the pageblock-related functions went from 1.27% in profiles to 0.5%. In addition to the performance benefits, this patch closes races that are possible between: a) get_ and set_pageblock_migratetype(), where get_pageblock_migratetype() reads part of the bits before and other part of the bits after set_pageblock_migratetype() has updated them. b) set_pageblock_migratetype() and set_pageblock_skip(), where the non-atomic read-modify-update set bit operation in set_pageblock_skip() will cause lost updates to some bits changed in the set_pageblock_migratetype(). Joonsoo Kim first reported the case a) via code inspection. Vlastimil Babka's testing with a debug patch showed that either a) or b) occurs roughly once per mmtests' stress-highalloc benchmark (although not necessarily in the same pageblock). Furthermore during development of unrelated compaction patches, it was observed that frequent calls to {start,undo}_isolate_page_range() the race occurs several thousands of times and has resulted in NULL pointer dereferences in move_freepages() and free_one_page() in places where free_list[migratetype] is manipulated by e.g. list_move(). Further debugging confirmed that migratetype had invalid value of 6, causing out of bounds access to the free_list array. That confirmed that the race exist, although it may be extremely rare, and currently only fatal where page isolation is performed due to memory hot remove. Races on pageblocks being updated by set_pageblock_migratetype(), where both old and new migratetype are lower MIGRATE_RESERVE, currently cannot result in an invalid value being observed, although theoretically they may still lead to unexpected creation or destruction of MIGRATE_RESERVE pageblocks. Furthermore, things could get suddenly worse when memory isolation is used more, or when new migratetypes are added. After this patch, the race has no longer been observed in testing. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reported-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Reported-and-tested-by: Vlastimil Babka <vbabka@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jan Kara <jack@suse.cz> Cc: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Theodore Ts'o <tytso@mit.edu> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/page_alloc.c52
1 files changed, 32 insertions, 20 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 485932c577e7..6e937809c87a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6028,53 +6028,65 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
* @end_bitidx: The last bit of interest
* returns pageblock_bits flags
*/
-unsigned long get_pageblock_flags_group(struct page *page,
- int start_bitidx, int end_bitidx)
+unsigned long get_pageblock_flags_mask(struct page *page,
+ unsigned long end_bitidx,
+ unsigned long mask)
{
struct zone *zone;
unsigned long *bitmap;
- unsigned long pfn, bitidx;
- unsigned long flags = 0;
- unsigned long value = 1;
+ unsigned long pfn, bitidx, word_bitidx;
+ unsigned long word;
zone = page_zone(page);
pfn = page_to_pfn(page);
bitmap = get_pageblock_bitmap(zone, pfn);
bitidx = pfn_to_bitidx(zone, pfn);
+ word_bitidx = bitidx / BITS_PER_LONG;
+ bitidx &= (BITS_PER_LONG-1);
- for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
- if (test_bit(bitidx + start_bitidx, bitmap))
- flags |= value;
-
- return flags;
+ word = bitmap[word_bitidx];
+ bitidx += end_bitidx;
+ return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
}
/**
- * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * set_pageblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
* @page: The page within the block of interest
* @start_bitidx: The first bit of interest
* @end_bitidx: The last bit of interest
* @flags: The flags to set
*/
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
- int start_bitidx, int end_bitidx)
+void set_pageblock_flags_mask(struct page *page, unsigned long flags,
+ unsigned long end_bitidx,
+ unsigned long mask)
{
struct zone *zone;
unsigned long *bitmap;
- unsigned long pfn, bitidx;
- unsigned long value = 1;
+ unsigned long pfn, bitidx, word_bitidx;
+ unsigned long old_word, word;
+
+ BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
zone = page_zone(page);
pfn = page_to_pfn(page);
bitmap = get_pageblock_bitmap(zone, pfn);
bitidx = pfn_to_bitidx(zone, pfn);
+ word_bitidx = bitidx / BITS_PER_LONG;
+ bitidx &= (BITS_PER_LONG-1);
+
VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page);
- for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
- if (flags & value)
- __set_bit(bitidx + start_bitidx, bitmap);
- else
- __clear_bit(bitidx + start_bitidx, bitmap);
+ bitidx += end_bitidx;
+ mask <<= (BITS_PER_LONG - bitidx - 1);
+ flags <<= (BITS_PER_LONG - bitidx - 1);
+
+ word = ACCESS_ONCE(bitmap[word_bitidx]);
+ for (;;) {
+ old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
+ if (word == old_word)
+ break;
+ word = old_word;
+ }
}
/*