[PATCH 08/17] mm: page_alloc: Use word-based accesses for get/set pageblock bitmaps

From: Mel Gorman
Date: Thu May 01 2014 - 04:49:23 EST


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%.

Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
---
include/linux/mmzone.h | 7 +++++-
include/linux/pageblock-flags.h | 39 +++++++++++++++++++++++++++-----
mm/page_alloc.c | 49 +++++++++++++++++++++++++----------------
3 files changed, 69 insertions(+), 26 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index fac5509..c84703d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -75,9 +75,14 @@ enum {

extern int page_group_by_mobility_disabled;

+#define NR_MIGRATETYPE_BITS (PB_migrate_end - PB_migrate + 1)
+#define MIGRATETYPE_MASK ((1UL << NR_MIGRATETYPE_BITS) - 1)
+
static inline int get_pageblock_migratetype(struct page *page)
{
- return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end);
+ BUILD_BUG_ON(PB_migrate_end - PB_migrate != 2);
+ return get_pageblock_flags_mask(page, PB_migrate_end,
+ NR_MIGRATETYPE_BITS, MIGRATETYPE_MASK);
}

struct free_area {
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 2ee8cd2..bc37036 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -30,9 +30,12 @@ enum pageblock_bits {
PB_migrate,
PB_migrate_end = PB_migrate + 3 - 1,
/* 3 bits required for migrate types */
-#ifdef CONFIG_COMPACTION
PB_migrate_skip,/* If set the block is skipped by compaction */
-#endif /* CONFIG_COMPACTION */
+
+ /*
+ * Assume the bits will always align on a word. If this assumption
+ * changes then get/set pageblock needs updating.
+ */
NR_PAGEBLOCK_BITS
};

@@ -62,11 +65,35 @@ extern int pageblock_order;
/* Forward declaration */
struct page;

+unsigned long get_pageblock_flags_mask(struct page *page,
+ unsigned long end_bitidx,
+ unsigned long nr_flag_bits,
+ unsigned long mask);
+void set_pageblock_flags_mask(struct page *page,
+ unsigned long flags,
+ unsigned long end_bitidx,
+ unsigned long nr_flag_bits,
+ unsigned long mask);
+
/* Declarations for getting and setting flags. See mm/page_alloc.c */
-unsigned long get_pageblock_flags_group(struct page *page,
- int start_bitidx, int end_bitidx);
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
- int start_bitidx, int end_bitidx);
+static inline unsigned long get_pageblock_flags_group(struct page *page,
+ int start_bitidx, int end_bitidx)
+{
+ unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
+ unsigned long mask = (1 << nr_flag_bits) - 1;
+
+ return get_pageblock_flags_mask(page, end_bitidx, nr_flag_bits, mask);
+}
+
+static inline void set_pageblock_flags_group(struct page *page,
+ unsigned long flags,
+ int start_bitidx, int end_bitidx)
+{
+ unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
+ unsigned long mask = (1 << nr_flag_bits) - 1;
+
+ set_pageblock_flags_mask(page, flags, end_bitidx, nr_flag_bits, mask);
+}

#ifdef CONFIG_COMPACTION
#define get_pageblock_skip(page) \
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index dc123ff..2cf1558 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6032,25 +6032,26 @@ 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 nr_flag_bits,
+ 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;
}

/**
@@ -6060,25 +6061,35 @@ unsigned long get_pageblock_flags_group(struct page *page,
* @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_pfnblock_flags_group(struct page *page, unsigned long flags,
+ unsigned long end_bitidx,
+ unsigned long nr_flag_bits,
+ 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, new_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);
+
+ do {
+ old_word = ACCESS_ONCE(bitmap[word_bitidx]);
+ new_word = (old_word & ~mask) | flags;
+ } while (cmpxchg(&bitmap[word_bitidx], old_word, new_word) != old_word);
}

/*
--
1.8.4.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/