From: NeilBrown <neilb@suse.com>
To: Shaohua Li <shli@kernel.org>
Cc: linux-raid@vger.kernel.org, hch@lst.de
Subject: [md PATCH 05/15] md/raid5: use bio_inc_remaining() instead of repurposing bi_phys_segments as a counter
Date: Wed, 15 Mar 2017 14:05:13 +1100 [thread overview]
Message-ID: <148954711289.18641.14871758568324640221.stgit@noble> (raw)
In-Reply-To: <148954692173.18641.1294690639716682540.stgit@noble>
md/raid5 needs to keep track of how many stripe_heads are processing a
bio so that it can delay calling bio_endio() until all stripe_heads
have completed. It currently uses 16 bits of ->bi_phys_segments for
this purpose.
16 bits is only enough for 256M requests, and it is possible for a
single bio to be larger than this, which causes problems. Also, the
bio struct contains a larger counter, __bi_remaining, which has a
purpose very similar to the purpose of our counter. So stop using
->bi_phys_segments, and instead use __bi_remaining.
This means we don't need to initialize the counter, as our caller
initializes it to '1'. It also means we can call bio_endio() directly
as it tests this counter internally.
Signed-off-by: NeilBrown <neilb@suse.com>
---
drivers/md/raid5-cache.c | 3 +--
drivers/md/raid5.c | 50 +++++++++++-----------------------------------
drivers/md/raid5.h | 17 +---------------
3 files changed, 14 insertions(+), 56 deletions(-)
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 5be8dbc5d91b..25eb048298fe 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -318,8 +318,7 @@ r5c_return_dev_pending_writes(struct r5conf *conf, struct r5dev *dev)
dev->sector + STRIPE_SECTORS) {
wbi2 = r5_next_bio(wbi, dev->sector);
md_write_end(conf->mddev);
- if (!raid5_dec_bi_active_stripes(wbi))
- bio_endio(wbi);
+ bio_endio(wbi);
wbi = wbi2;
}
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7a45045ab358..7824c2509905 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1322,8 +1322,7 @@ static void ops_complete_biofill(void *stripe_head_ref)
while (rbi && rbi->bi_iter.bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
- if (!raid5_dec_bi_active_stripes(rbi))
- bio_endio(rbi);
+ bio_endio(rbi);
rbi = rbi2;
}
}
@@ -3195,14 +3194,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
(unsigned long long)bi->bi_iter.bi_sector,
(unsigned long long)sh->sector);
- /*
- * If several bio share a stripe. The bio bi_phys_segments acts as a
- * reference count to avoid race. The reference count should already be
- * increased before this function is called (for example, in
- * raid5_make_request()), so other bio sharing this stripe will not free the
- * stripe. If a stripe is owned by one stripe, the stripe lock will
- * protect it.
- */
spin_lock_irq(&sh->stripe_lock);
/* Don't allow new IO added to stripes in batch list */
if (sh->batch_head)
@@ -3258,7 +3249,7 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
if (*bip)
bi->bi_next = *bip;
*bip = bi;
- raid5_inc_bi_active_stripes(bi);
+ bio_inc_remaining(bi);
md_write_inc(conf->mddev, bi);
if (forwrite) {
@@ -3383,8 +3374,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
bi->bi_error = -EIO;
md_write_end(conf->mddev);
- if (!raid5_dec_bi_active_stripes(bi))
- bio_endio(bi);
+ bio_endio(bi);
bi = nextbi;
}
if (bitmap_end)
@@ -3406,8 +3396,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
bi->bi_error = -EIO;
md_write_end(conf->mddev);
- if (!raid5_dec_bi_active_stripes(bi))
- bio_endio(bi);
+ bio_endio(bi);
bi = bi2;
}
@@ -3432,8 +3421,7 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
r5_next_bio(bi, sh->dev[i].sector);
bi->bi_error = -EIO;
- if (!raid5_dec_bi_active_stripes(bi))
- bio_endio(bi);
+ bio_endio(bi);
bi = nextbi;
}
}
@@ -3765,8 +3753,7 @@ static void handle_stripe_clean_event(struct r5conf *conf,
dev->sector + STRIPE_SECTORS) {
wbi2 = r5_next_bio(wbi, dev->sector);
md_write_end(conf->mddev);
- if (!raid5_dec_bi_active_stripes(wbi))
- bio_endio(wbi);
+ bio_endio(wbi);
wbi = wbi2;
}
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
@@ -5111,7 +5098,7 @@ static struct bio *remove_bio_from_retry(struct r5conf *conf)
* this sets the active strip count to 1 and the processed
* strip count to zero (upper 8 bits)
*/
- raid5_set_bi_stripes(bi, 1); /* biased count of active stripes */
+ raid5_set_bi_processed_stripes(bi, 0);
}
return bi;
@@ -5446,7 +5433,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
struct r5conf *conf = mddev->private;
sector_t logical_sector, last_sector;
struct stripe_head *sh;
- int remaining;
int stripe_sectors;
if (mddev->reshape_position != MaxSector)
@@ -5457,7 +5443,6 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
last_sector = bi->bi_iter.bi_sector + (bi->bi_iter.bi_size>>9);
bi->bi_next = NULL;
- bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
md_write_start(mddev, bi);
stripe_sectors = conf->chunk_sectors *
@@ -5504,7 +5489,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
continue;
sh->dev[d].towrite = bi;
set_bit(R5_OVERWRITE, &sh->dev[d].flags);
- raid5_inc_bi_active_stripes(bi);
+ bio_inc_remaining(bi);
md_write_inc(mddev, bi);
sh->overwrite_disks++;
}
@@ -5529,10 +5514,7 @@ static void make_discard_request(struct mddev *mddev, struct bio *bi)
}
md_write_end(mddev);
- remaining = raid5_dec_bi_active_stripes(bi);
- if (remaining == 0) {
- bio_endio(bi);
- }
+ bio_endio(bi);
}
static void raid5_make_request(struct mddev *mddev, struct bio * bi)
@@ -5543,7 +5525,6 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
sector_t logical_sector, last_sector;
struct stripe_head *sh;
const int rw = bio_data_dir(bi);
- int remaining;
DEFINE_WAIT(w);
bool do_prepare;
bool do_flush = false;
@@ -5585,7 +5566,6 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
logical_sector = bi->bi_iter.bi_sector & ~((sector_t)STRIPE_SECTORS-1);
last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
- bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
md_write_start(mddev, bi);
prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
@@ -5723,10 +5703,7 @@ static void raid5_make_request(struct mddev *mddev, struct bio * bi)
if (rw == WRITE)
md_write_end(mddev);
- remaining = raid5_dec_bi_active_stripes(bi);
- if (remaining == 0) {
- bio_endio(bi);
- }
+ bio_endio(bi);
}
static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks);
@@ -6091,7 +6068,6 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
int dd_idx;
sector_t sector, logical_sector, last_sector;
int scnt = 0;
- int remaining;
int handled = 0;
logical_sector = raid_bio->bi_iter.bi_sector &
@@ -6130,10 +6106,8 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
raid5_release_stripe(sh);
handled++;
}
- remaining = raid5_dec_bi_active_stripes(raid_bio);
- if (remaining == 0) {
- bio_endio(raid_bio);
- }
+ bio_endio(raid_bio);
+
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent);
return handled;
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index fd5c21cde77f..7d74fb3f2ec6 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -488,8 +488,7 @@ static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
}
/*
- * We maintain a biased count of active stripes in the bottom 16 bits of
- * bi_phys_segments, and a count of processed stripes in the upper 16 bits
+ * We maintain a count of processed stripes in the upper 16 bits
*/
static inline int raid5_bi_processed_stripes(struct bio *bio)
{
@@ -498,20 +497,6 @@ static inline int raid5_bi_processed_stripes(struct bio *bio)
return (atomic_read(segments) >> 16) & 0xffff;
}
-static inline int raid5_dec_bi_active_stripes(struct bio *bio)
-{
- atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
-
- return atomic_sub_return(1, segments) & 0xffff;
-}
-
-static inline void raid5_inc_bi_active_stripes(struct bio *bio)
-{
- atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
-
- atomic_inc(segments);
-}
-
static inline void raid5_set_bi_processed_stripes(struct bio *bio,
unsigned int cnt)
{
next prev parent reply other threads:[~2017-03-15 3:05 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-15 3:05 [md PATCH 00/15 v2] remove all abuse of bi_phys_segments NeilBrown
2017-03-15 3:05 ` [md PATCH 04/15] block: trace completion of all bios NeilBrown
2017-03-15 3:05 ` [md PATCH 02/15] md/raid5: simplfy delaying of writes while metadata is updated NeilBrown
2017-03-15 23:03 ` Shaohua Li
2017-03-16 2:45 ` NeilBrown
2017-03-22 1:40 ` Fix bug in " NeilBrown
2017-03-22 2:29 ` REALLY " NeilBrown
2017-03-22 2:35 ` NeilBrown
2017-03-23 2:22 ` Shaohua Li
2017-03-15 3:05 ` [md PATCH 01/15] md/raid5: use md_write_start to count stripes, not bios NeilBrown
2017-03-15 3:05 ` [md PATCH 03/15] md/raid5: call bio_endio() directly rather than queueing for later NeilBrown
2017-03-15 3:05 ` [md PATCH 09/15] md/raid10: stop using bi_phys_segments NeilBrown
2017-03-15 3:05 ` [md PATCH 08/15] md/raid1, raid10: move rXbio accounting closer to allocation NeilBrown
2017-03-15 3:05 ` [md PATCH 06/15] md/raid5: remove over-loading of ->bi_phys_segments NeilBrown
2017-03-15 3:05 ` [md PATCH 07/15] Revert "md/raid5: limit request size according to implementation limits" NeilBrown
2017-03-15 3:05 ` NeilBrown [this message]
2017-03-15 3:05 ` [md PATCH 14/15] percpu-refcount: support synchronous switch to atomic mode NeilBrown
2017-03-15 3:05 ` [md PATCH 11/15] md/raid5: don't test ->writes_pending in raid5_remove_disk NeilBrown
2017-03-15 3:05 ` [md PATCH 13/15] md: close a race with setting mddev->in_sync NeilBrown
2017-03-15 3:05 ` [md PATCH 15/15] MD: use per-cpu counter for writes_pending NeilBrown
2017-03-16 1:05 ` Shaohua Li
2017-03-16 2:57 ` NeilBrown
2017-03-22 1:55 ` Improvement for " NeilBrown
2017-03-22 2:34 ` IMPROVEMENT for " NeilBrown
2017-03-15 3:05 ` [md PATCH 10/15] md/raid1: stop using bi_phys_segment NeilBrown
2017-03-16 0:13 ` Shaohua Li
2017-03-16 2:49 ` NeilBrown
2017-03-16 3:36 ` Shaohua Li
2017-03-22 1:41 ` Fix bugs in " NeilBrown
2017-03-15 3:05 ` [md PATCH 12/15] md: factor out set_in_sync() NeilBrown
2017-03-16 1:12 ` [md PATCH 00/15 v2] remove all abuse of bi_phys_segments Shaohua Li
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=148954711289.18641.14871758568324640221.stgit@noble \
--to=neilb@suse.com \
--cc=hch@lst.de \
--cc=linux-raid@vger.kernel.org \
--cc=shli@kernel.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