summaryrefslogtreecommitdiffstats
path: root/mm/bounce.c
diff options
context:
space:
mode:
authorDarrick J. Wong <darrick.wong@oracle.com>2013-02-21 16:42:55 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2013-02-21 17:22:20 -0800
commitffecfd1a72fccfcee3dabb99b9ecba9735318f90 (patch)
treea5c3caf67249ec811a2c2c95678d9349fd8e2412 /mm/bounce.c
parent13575ca14fcdacd1ad914d00bc63eb4d96280986 (diff)
downloadop-kernel-dev-ffecfd1a72fccfcee3dabb99b9ecba9735318f90.zip
op-kernel-dev-ffecfd1a72fccfcee3dabb99b9ecba9735318f90.tar.gz
block: optionally snapshot page contents to provide stable pages during write
This provides a band-aid to provide stable page writes on jbd without needing to backport the fixed locking and page writeback bit handling schemes of jbd2. The band-aid works by using bounce buffers to snapshot page contents instead of waiting. For those wondering about the ext3 bandage -- fixing the jbd locking (which was done as part of ext4dev years ago) is a lot of surgery, and setting PG_writeback on data pages when we actually hold the page lock dropped ext3 performance by nearly an order of magnitude. If we're going to migrate iscsi and raid to use stable page writes, the complaints about high latency will likely return. We might as well centralize their page snapshotting thing to one place. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Tested-by: Andy Lutomirski <luto@amacapital.net> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Artem Bityutskiy <dedekind1@gmail.com> Reviewed-by: Jan Kara <jack@suse.cz> Cc: Joel Becker <jlbec@evilplan.org> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Latchesar Ionkov <lucho@ionkov.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/bounce.c')
-rw-r--r--mm/bounce.c48
1 files changed, 44 insertions, 4 deletions
diff --git a/mm/bounce.c b/mm/bounce.c
index 0420867..5f89017 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -178,8 +178,45 @@ static void bounce_end_io_read_isa(struct bio *bio, int err)
__bounce_end_io_read(bio, isa_page_pool, err);
}
+#ifdef CONFIG_NEED_BOUNCE_POOL
+static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
+{
+ struct page *page;
+ struct backing_dev_info *bdi;
+ struct address_space *mapping;
+ struct bio_vec *from;
+ int i;
+
+ if (bio_data_dir(bio) != WRITE)
+ return 0;
+
+ if (!bdi_cap_stable_pages_required(&q->backing_dev_info))
+ return 0;
+
+ /*
+ * Based on the first page that has a valid mapping, decide whether or
+ * not we have to employ bounce buffering to guarantee stable pages.
+ */
+ bio_for_each_segment(from, bio, i) {
+ page = from->bv_page;
+ mapping = page_mapping(page);
+ if (!mapping)
+ continue;
+ bdi = mapping->backing_dev_info;
+ return mapping->host->i_sb->s_flags & MS_SNAP_STABLE;
+ }
+
+ return 0;
+}
+#else
+static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio)
+{
+ return 0;
+}
+#endif /* CONFIG_NEED_BOUNCE_POOL */
+
static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
- mempool_t *pool)
+ mempool_t *pool, int force)
{
struct page *page;
struct bio *bio = NULL;
@@ -192,7 +229,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
/*
* is destination page below bounce pfn?
*/
- if (page_to_pfn(page) <= queue_bounce_pfn(q))
+ if (page_to_pfn(page) <= queue_bounce_pfn(q) && !force)
continue;
/*
@@ -270,6 +307,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
{
+ int must_bounce;
mempool_t *pool;
/*
@@ -278,13 +316,15 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
if (!bio_has_data(*bio_orig))
return;
+ must_bounce = must_snapshot_stable_pages(q, *bio_orig);
+
/*
* for non-isa bounce case, just check if the bounce pfn is equal
* to or bigger than the highest pfn in the system -- in that case,
* don't waste time iterating over bio segments
*/
if (!(q->bounce_gfp & GFP_DMA)) {
- if (queue_bounce_pfn(q) >= blk_max_pfn)
+ if (queue_bounce_pfn(q) >= blk_max_pfn && !must_bounce)
return;
pool = page_pool;
} else {
@@ -295,7 +335,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
/*
* slow path
*/
- __blk_queue_bounce(q, bio_orig, pool);
+ __blk_queue_bounce(q, bio_orig, pool, must_bounce);
}
EXPORT_SYMBOL(blk_queue_bounce);
OpenPOWER on IntegriCloud