From: Mel Gorman <mgorman@suse.de>
To: Linux-MM <linux-mm@kvack.org>
Cc: Linux-FSDevel <linux-fsdevel@vger.kernel.org>
Subject: [PATCH 10/16] mm: page_alloc: Use word-based accesses for get/set pageblock bitmaps
Date: Fri, 18 Apr 2014 15:50:37 +0100 [thread overview]
Message-ID: <1397832643-14275-11-git-send-email-mgorman@suse.de> (raw)
In-Reply-To: <1397832643-14275-1-git-send-email-mgorman@suse.de>
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@suse.de>
---
include/linux/mmzone.h | 6 +++++-
include/linux/pageblock-flags.h | 21 ++++++++++++++++----
mm/page_alloc.c | 43 +++++++++++++++++++++++++----------------
3 files changed, 48 insertions(+), 22 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index c1dbe0b..c97b4bc 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -75,9 +75,13 @@ enum {
extern int page_group_by_mobility_disabled;
+#define NR_MIGRATETYPE_BITS 3
+#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, NR_MIGRATETYPE_BITS, MIGRATETYPE_MASK);
}
struct free_area {
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 2ee8cd2..c89ac75 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
};
@@ -62,9 +65,19 @@ extern int pageblock_order;
/* Forward declaration */
struct page;
+unsigned long get_pageblock_flags_mask(struct page *page,
+ 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);
+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, nr_flag_bits, mask);
+}
void set_pageblock_flags_group(struct page *page, unsigned long flags,
int start_bitidx, int end_bitidx);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 737577c..6047866 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6012,25 +6012,24 @@ 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 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];
+ return (word >> (BITS_PER_LONG - (bitidx + nr_flag_bits))) & mask;
}
/**
@@ -6045,20 +6044,30 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
{
struct zone *zone;
unsigned long *bitmap;
- unsigned long pfn, bitidx;
- unsigned long value = 1;
+ unsigned long pfn, bitidx, word_bitidx;
+ unsigned long nr_flag_bits = end_bitidx - start_bitidx + 1;
+ unsigned long mask = (1 << nr_flag_bits) - 1;
+ 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);
+ end_bitidx = bitidx + (end_bitidx - start_bitidx);
+ mask <<= (BITS_PER_LONG - end_bitidx - 1);
+ flags <<= (BITS_PER_LONG - end_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, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2014-04-18 14:50 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-18 14:50 [PATCH 00/16] Misc page alloc, shmem and mark_page_accessed optimisations Mel Gorman
2014-04-18 14:50 ` [PATCH 01/16] mm: Disable zone_reclaim_mode by default Mel Gorman
2014-04-18 17:26 ` Andi Kleen
2014-04-18 21:15 ` Dave Hansen
2014-04-18 14:50 ` [PATCH 02/16] mm: page_alloc: Do not cache reclaim distances Mel Gorman
2014-04-18 14:50 ` [PATCH 03/16] mm: page_alloc: Do not update zlc unless the zlc is active Mel Gorman
2014-04-18 17:52 ` Johannes Weiner
2014-04-18 14:50 ` [PATCH 04/16] mm: page_alloc: Do not treat a zone that cannot be used for dirty pages as "full" Mel Gorman
2014-04-18 17:52 ` Johannes Weiner
2014-04-18 14:50 ` [PATCH 05/16] mm: page_alloc: Use jump labels to avoid checking number_of_cpusets Mel Gorman
2014-04-18 14:50 ` [PATCH 06/16] mm: page_alloc: Calculate classzone_idx once from the zonelist ref Mel Gorman
2014-04-18 18:03 ` Johannes Weiner
2014-04-19 11:18 ` Mel Gorman
2014-04-18 14:50 ` [PATCH 07/16] mm: page_alloc: Only check the zone id check if pages are buddies Mel Gorman
2014-04-18 18:05 ` Johannes Weiner
2014-04-18 14:50 ` [PATCH 08/16] mm: page_alloc: Only check the alloc flags and gfp_mask for dirty once Mel Gorman
2014-04-18 18:08 ` Johannes Weiner
2014-04-19 11:19 ` Mel Gorman
2014-04-18 14:50 ` [PATCH 09/16] mm: page_alloc: Take the ALLOC_NO_WATERMARK check out of the fast path Mel Gorman
2014-04-18 18:10 ` Johannes Weiner
2014-04-18 14:50 ` Mel Gorman [this message]
2014-04-18 17:16 ` [PATCH 10/16] mm: page_alloc: Use word-based accesses for get/set pageblock bitmaps Vlastimil Babka
2014-04-18 14:50 ` [PATCH 11/16] mm: page_alloc: Reduce number of times page_to_pfn is called Mel Gorman
2014-04-18 14:50 ` [PATCH 12/16] mm: shmem: Avoid atomic operation during shmem_getpage_gfp Mel Gorman
2014-04-18 18:13 ` Johannes Weiner
2014-04-18 14:50 ` [PATCH 13/16] mm: Do not use atomic operations when releasing pages Mel Gorman
2014-04-18 14:50 ` [PATCH 14/16] mm: Do not use unnecessary atomic operations when adding pages to the LRU Mel Gorman
2014-04-18 14:50 ` [PATCH 15/16] mm: Non-atomically mark page accessed in write_begin where possible Mel Gorman
2014-04-18 14:50 ` [PATCH 16/16] mm: filemap: Prefetch page->flags if !PageUptodate Mel Gorman
2014-04-18 19:16 ` Hugh Dickins
2014-04-19 11:23 ` Mel Gorman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1397832643-14275-11-git-send-email-mgorman@suse.de \
--to=mgorman@suse.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox