From 7eaceaccab5f40bbfda044629a6298616aeaed50 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 10 Mar 2011 08:52:07 +0100 Subject: block: remove per-queue plugging Code has been converted over to the new explicit on-stack plugging, and delay users have been converted to use the new API for that. So lets kill off the old plugging along with aops->sync_page(). Signed-off-by: Jens Axboe --- drivers/md/md.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 0cc30ecda4c..ca0d79c264b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -4812,7 +4812,6 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) __md_stop_writes(mddev); md_stop(mddev); mddev->queue->merge_bvec_fn = NULL; - mddev->queue->unplug_fn = NULL; mddev->queue->backing_dev_info.congested_fn = NULL; /* tell userspace to handle 'inactive' */ @@ -6669,8 +6668,6 @@ EXPORT_SYMBOL_GPL(md_allow_write); void md_unplug(mddev_t *mddev) { - if (mddev->queue) - blk_unplug(mddev->queue); if (mddev->plug) mddev->plug->unplug_fn(mddev->plug); } @@ -6853,7 +6850,6 @@ void md_do_sync(mddev_t *mddev) >= mddev->resync_max - mddev->curr_resync_completed )) { /* time to update curr_resync_completed */ - md_unplug(mddev); wait_event(mddev->recovery_wait, atomic_read(&mddev->recovery_active) == 0); mddev->curr_resync_completed = j; @@ -6929,7 +6925,6 @@ void md_do_sync(mddev_t *mddev) * about not overloading the IO subsystem. (things like an * e2fsck being done on the RAID array should execute fast) */ - md_unplug(mddev); cond_resched(); currspeed = ((unsigned long)(io_sectors-mddev->resync_mark_cnt))/2 @@ -6948,8 +6943,6 @@ void md_do_sync(mddev_t *mddev) * this also signals 'finished resyncing' to md_stop */ out: - md_unplug(mddev); - wait_event(mddev->recovery_wait, !atomic_read(&mddev->recovery_active)); /* tell personality that we are finished */ -- cgit v1.2.3-70-g09d2 From 721a9602e6607417c6bc15b18e97a2f35266c690 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Mar 2011 11:56:30 +0100 Subject: block: kill off REQ_UNPLUG With the plugging now being explicitly controlled by the submitter, callers need not pass down unplugging hints to the block layer. If they want to unplug, it's because they manually plugged on their own - in which case, they should just unplug at will. Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- drivers/block/drbd/drbd_actlog.c | 2 +- drivers/block/drbd/drbd_int.h | 2 +- drivers/block/drbd/drbd_main.c | 3 +-- drivers/block/drbd/drbd_receiver.c | 9 +-------- drivers/md/bitmap.c | 2 +- drivers/md/dm-io.c | 2 +- drivers/md/dm-kcopyd.c | 5 +---- drivers/md/md.c | 5 ++--- fs/btrfs/extent_io.c | 2 +- fs/buffer.c | 14 ++++---------- fs/direct-io.c | 2 +- fs/ext4/page-io.c | 3 +-- fs/gfs2/log.c | 4 ++-- fs/gfs2/lops.c | 12 ++++++------ fs/gfs2/meta_io.c | 2 +- fs/jbd/commit.c | 2 +- fs/jbd2/commit.c | 6 +++--- fs/nilfs2/segbuf.c | 2 +- fs/xfs/linux-2.6/xfs_aops.c | 3 +-- include/linux/blk_types.h | 2 -- include/linux/fs.h | 28 +++++++++------------------- kernel/power/block_io.c | 2 +- mm/page_io.c | 2 +- 24 files changed, 43 insertions(+), 75 deletions(-) (limited to 'drivers/md/md.c') diff --git a/block/blk-core.c b/block/blk-core.c index 82a45898ba7..7e9715ae18c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1290,7 +1290,7 @@ get_rq: } plug = current->plug; - if (plug && !sync) { + if (plug) { if (!plug->should_sort && !list_empty(&plug->list)) { struct request *__rq; diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index 2096628d6e6..aca302492ff 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -80,7 +80,7 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev, if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags)) rw |= REQ_FUA; - rw |= REQ_UNPLUG | REQ_SYNC; + rw |= REQ_SYNC; bio = bio_alloc(GFP_NOIO, 1); bio->bi_bdev = bdev->md_bdev; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 0b5718e1958..b0bd27dfc1e 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -377,7 +377,7 @@ union p_header { #define DP_HARDBARRIER 1 /* depricated */ #define DP_RW_SYNC 2 /* equals REQ_SYNC */ #define DP_MAY_SET_IN_SYNC 4 -#define DP_UNPLUG 8 /* equals REQ_UNPLUG */ +#define DP_UNPLUG 8 /* not used anymore */ #define DP_FUA 16 /* equals REQ_FUA */ #define DP_FLUSH 32 /* equals REQ_FLUSH */ #define DP_DISCARD 64 /* equals REQ_DISCARD */ diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 6049cb85310..8a43ce0edee 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2477,12 +2477,11 @@ static u32 bio_flags_to_wire(struct drbd_conf *mdev, unsigned long bi_rw) { if (mdev->agreed_pro_version >= 95) return (bi_rw & REQ_SYNC ? DP_RW_SYNC : 0) | - (bi_rw & REQ_UNPLUG ? DP_UNPLUG : 0) | (bi_rw & REQ_FUA ? DP_FUA : 0) | (bi_rw & REQ_FLUSH ? DP_FLUSH : 0) | (bi_rw & REQ_DISCARD ? DP_DISCARD : 0); else - return bi_rw & (REQ_SYNC | REQ_UNPLUG) ? DP_RW_SYNC : 0; + return bi_rw & REQ_SYNC ? DP_RW_SYNC : 0; } /* Used to send write requests diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 84132f8bf8a..8e68be939de 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -1100,8 +1100,6 @@ next_bio: /* > e->sector, unless this is the first bio */ bio->bi_sector = sector; bio->bi_bdev = mdev->ldev->backing_bdev; - /* we special case some flags in the multi-bio case, see below - * (REQ_UNPLUG) */ bio->bi_rw = rw; bio->bi_private = e; bio->bi_end_io = drbd_endio_sec; @@ -1130,10 +1128,6 @@ next_bio: bios = bios->bi_next; bio->bi_next = NULL; - /* strip off REQ_UNPLUG unless it is the last bio */ - if (bios) - bio->bi_rw &= ~REQ_UNPLUG; - drbd_generic_make_request(mdev, fault_type, bio); } while (bios); return 0; @@ -1621,12 +1615,11 @@ static unsigned long write_flags_to_bio(struct drbd_conf *mdev, u32 dpf) { if (mdev->agreed_pro_version >= 95) return (dpf & DP_RW_SYNC ? REQ_SYNC : 0) | - (dpf & DP_UNPLUG ? REQ_UNPLUG : 0) | (dpf & DP_FUA ? REQ_FUA : 0) | (dpf & DP_FLUSH ? REQ_FUA : 0) | (dpf & DP_DISCARD ? REQ_DISCARD : 0); else - return dpf & DP_RW_SYNC ? (REQ_SYNC | REQ_UNPLUG) : 0; + return dpf & DP_RW_SYNC ? REQ_SYNC : 0; } /* mirrored write */ diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 54bfc274b39..ca203cb23f3 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -347,7 +347,7 @@ static void write_page(struct bitmap *bitmap, struct page *page, int wait) atomic_inc(&bitmap->pending_writes); set_buffer_locked(bh); set_buffer_mapped(bh); - submit_bh(WRITE | REQ_UNPLUG | REQ_SYNC, bh); + submit_bh(WRITE | REQ_SYNC, bh); bh = bh->b_this_page; } diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c index 136d4f71a11..76a5af00a26 100644 --- a/drivers/md/dm-io.c +++ b/drivers/md/dm-io.c @@ -352,7 +352,7 @@ static void dispatch_io(int rw, unsigned int num_regions, BUG_ON(num_regions > DM_IO_MAX_REGIONS); if (sync) - rw |= REQ_SYNC | REQ_UNPLUG; + rw |= REQ_SYNC; /* * For multiple regions we need to be careful to rewind diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c index 400cf35094a..1bb73a13ca4 100644 --- a/drivers/md/dm-kcopyd.c +++ b/drivers/md/dm-kcopyd.c @@ -356,11 +356,8 @@ static int run_io_job(struct kcopyd_job *job) if (job->rw == READ) r = dm_io(&io_req, 1, &job->source, NULL); - else { - if (job->num_dests > 1) - io_req.bi_rw |= REQ_UNPLUG; + else r = dm_io(&io_req, job->num_dests, job->dests, NULL); - } return r; } diff --git a/drivers/md/md.c b/drivers/md/md.c index ca0d79c264b..28f9c1ee4e3 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -777,8 +777,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, bio->bi_end_io = super_written; atomic_inc(&mddev->pending_writes); - submit_bio(REQ_WRITE | REQ_SYNC | REQ_UNPLUG | REQ_FLUSH | REQ_FUA, - bio); + submit_bio(REQ_WRITE | REQ_SYNC | REQ_FLUSH | REQ_FUA, bio); } void md_super_wait(mddev_t *mddev) @@ -806,7 +805,7 @@ int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size, struct completion event; int ret; - rw |= REQ_SYNC | REQ_UNPLUG; + rw |= REQ_SYNC; bio->bi_bdev = (metadata_op && rdev->meta_bdev) ? rdev->meta_bdev : rdev->bdev; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 92ac5192c51..b76f7cd4740 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2182,7 +2182,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, unsigned long nr_written = 0; if (wbc->sync_mode == WB_SYNC_ALL) - write_flags = WRITE_SYNC_PLUG; + write_flags = WRITE_SYNC; else write_flags = WRITE; diff --git a/fs/buffer.c b/fs/buffer.c index f903f2e5b4f..42534f67d71 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -767,7 +767,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * still in flight on potentially older * contents. */ - write_dirty_buffer(bh, WRITE_SYNC_PLUG); + write_dirty_buffer(bh, WRITE_SYNC); /* * Kick off IO for the previous mapping. Note @@ -1602,14 +1602,8 @@ EXPORT_SYMBOL(unmap_underlying_metadata); * prevents this contention from occurring. * * If block_write_full_page() is called with wbc->sync_mode == - * WB_SYNC_ALL, the writes are posted using WRITE_SYNC_PLUG; this - * causes the writes to be flagged as synchronous writes, but the - * block device queue will NOT be unplugged, since usually many pages - * will be pushed to the out before the higher-level caller actually - * waits for the writes to be completed. The various wait functions, - * such as wait_on_writeback_range() will ultimately call sync_page() - * which will ultimately call blk_run_backing_dev(), which will end up - * unplugging the device queue. + * WB_SYNC_ALL, the writes are posted using WRITE_SYNC; this + * causes the writes to be flagged as synchronous writes. */ static int __block_write_full_page(struct inode *inode, struct page *page, get_block_t *get_block, struct writeback_control *wbc, @@ -1622,7 +1616,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, const unsigned blocksize = 1 << inode->i_blkbits; int nr_underway = 0; int write_op = (wbc->sync_mode == WB_SYNC_ALL ? - WRITE_SYNC_PLUG : WRITE); + WRITE_SYNC : WRITE); BUG_ON(!PageLocked(page)); diff --git a/fs/direct-io.c b/fs/direct-io.c index df709b3b860..42608313609 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1173,7 +1173,7 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct dio *dio; if (rw & WRITE) - rw = WRITE_ODIRECT_PLUG; + rw = WRITE_ODIRECT; if (bdev) bdev_blkbits = blksize_bits(bdev_logical_block_size(bdev)); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 955cc309142..e2cd90e4bb7 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -310,8 +310,7 @@ static int io_submit_init(struct ext4_io_submit *io, io_end->offset = (page->index << PAGE_CACHE_SHIFT) + bh_offset(bh); io->io_bio = bio; - io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? - WRITE_SYNC_PLUG : WRITE); + io->io_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); io->io_next_block = bh->b_blocknr; return 0; } diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index eb01f3575e1..7f1c1120234 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -121,7 +121,7 @@ __acquires(&sdp->sd_log_lock) lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; - submit_bh(WRITE_SYNC_PLUG, bh); + submit_bh(WRITE_SYNC, bh); } else { unlock_buffer(bh); brelse(bh); @@ -647,7 +647,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) lock_buffer(bh); if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; - submit_bh(WRITE_SYNC_PLUG, bh); + submit_bh(WRITE_SYNC, bh); } else { unlock_buffer(bh); brelse(bh); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index bf33f822058..48b545a1979 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -200,7 +200,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) } gfs2_log_unlock(sdp); - submit_bh(WRITE_SYNC_PLUG, bh); + submit_bh(WRITE_SYNC, bh); gfs2_log_lock(sdp); n = 0; @@ -210,7 +210,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) gfs2_log_unlock(sdp); lock_buffer(bd2->bd_bh); bh = gfs2_log_fake_buf(sdp, bd2->bd_bh); - submit_bh(WRITE_SYNC_PLUG, bh); + submit_bh(WRITE_SYNC, bh); gfs2_log_lock(sdp); if (++n >= num) break; @@ -352,7 +352,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) sdp->sd_log_num_revoke--; if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) { - submit_bh(WRITE_SYNC_PLUG, bh); + submit_bh(WRITE_SYNC, bh); bh = gfs2_log_get_buf(sdp); mh = (struct gfs2_meta_header *)bh->b_data; @@ -369,7 +369,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) } gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); - submit_bh(WRITE_SYNC_PLUG, bh); + submit_bh(WRITE_SYNC, bh); } static void revoke_lo_before_scan(struct gfs2_jdesc *jd, @@ -571,7 +571,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, ptr = bh_log_ptr(bh); get_bh(bh); - submit_bh(WRITE_SYNC_PLUG, bh); + submit_bh(WRITE_SYNC, bh); gfs2_log_lock(sdp); while(!list_empty(list)) { bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list); @@ -597,7 +597,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, } else { bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh); } - submit_bh(WRITE_SYNC_PLUG, bh1); + submit_bh(WRITE_SYNC, bh1); gfs2_log_lock(sdp); ptr += 2; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index a566331db4e..867b713cba9 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -37,7 +37,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb struct buffer_head *bh, *head; int nr_underway = 0; int write_op = REQ_META | - (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC_PLUG : WRITE); + (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); BUG_ON(!PageLocked(page)); BUG_ON(!page_has_buffers(page)); diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index 34a4861c14b..66be299acb1 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -333,7 +333,7 @@ void journal_commit_transaction(journal_t *journal) * instead we rely on sync_buffer() doing the unplug for us. */ if (commit_transaction->t_synchronous_commit) - write_op = WRITE_SYNC_PLUG; + write_op = WRITE_SYNC; spin_lock(&commit_transaction->t_handle_lock); while (commit_transaction->t_updates) { DEFINE_WAIT(wait); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index f3ad1598b20..3da1cc4346d 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -137,9 +137,9 @@ static int journal_submit_commit_record(journal_t *journal, if (journal->j_flags & JBD2_BARRIER && !JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) - ret = submit_bh(WRITE_SYNC_PLUG | WRITE_FLUSH_FUA, bh); + ret = submit_bh(WRITE_SYNC | WRITE_FLUSH_FUA, bh); else - ret = submit_bh(WRITE_SYNC_PLUG, bh); + ret = submit_bh(WRITE_SYNC, bh); *cbh = bh; return ret; @@ -369,7 +369,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) * instead we rely on sync_buffer() doing the unplug for us. */ if (commit_transaction->t_synchronous_commit) - write_op = WRITE_SYNC_PLUG; + write_op = WRITE_SYNC; trace_jbd2_commit_locking(journal, commit_transaction); stats.run.rs_wait = commit_transaction->t_max_wait; stats.run.rs_locked = jiffies; diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 0f83e93935b..2853ff20f85 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -509,7 +509,7 @@ static int nilfs_segbuf_write(struct nilfs_segment_buffer *segbuf, * Last BIO is always sent through the following * submission. */ - rw |= REQ_SYNC | REQ_UNPLUG; + rw |= REQ_SYNC; res = nilfs_segbuf_submit_bio(segbuf, &wi, rw); } diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 83c1c20d145..6bbb0ee3325 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -413,8 +413,7 @@ xfs_submit_ioend_bio( if (xfs_ioend_new_eof(ioend)) xfs_mark_inode_dirty(XFS_I(ioend->io_inode)); - submit_bio(wbc->sync_mode == WB_SYNC_ALL ? - WRITE_SYNC_PLUG : WRITE, bio); + submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE, bio); } STATIC struct bio * diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 16b28647304..be50d9e70a7 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -128,7 +128,6 @@ enum rq_flag_bits { __REQ_NOIDLE, /* don't anticipate more IO after this one */ /* bio only flags */ - __REQ_UNPLUG, /* unplug the immediately after submission */ __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ @@ -172,7 +171,6 @@ enum rq_flag_bits { REQ_NOIDLE | REQ_FLUSH | REQ_FUA) #define REQ_CLONE_MASK REQ_COMMON_MASK -#define REQ_UNPLUG (1 << __REQ_UNPLUG) #define REQ_RAHEAD (1 << __REQ_RAHEAD) #define REQ_THROTTLED (1 << __REQ_THROTTLED) diff --git a/include/linux/fs.h b/include/linux/fs.h index 9f2cf69911b..543e226ea6a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -135,16 +135,10 @@ struct inodes_stat_t { * block layer could (in theory) choose to ignore this * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. - * WRITE_SYNC_PLUG Synchronous write. Identical to WRITE, but passes down + * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down * the hint that someone will be waiting on this IO - * shortly. The device must still be unplugged explicitly, - * WRITE_SYNC_PLUG does not do this as we could be - * submitting more writes before we actually wait on any - * of them. - * WRITE_SYNC Like WRITE_SYNC_PLUG, but also unplugs the device - * immediately after submission. The write equivalent - * of READ_SYNC. - * WRITE_ODIRECT_PLUG Special case write for O_DIRECT only. + * shortly. The write equivalent of READ_SYNC. + * WRITE_ODIRECT Special case write for O_DIRECT only. * WRITE_FLUSH Like WRITE_SYNC but with preceding cache flush. * WRITE_FUA Like WRITE_SYNC but data is guaranteed to be on * non-volatile media on completion. @@ -160,18 +154,14 @@ struct inodes_stat_t { #define WRITE RW_MASK #define READA RWA_MASK -#define READ_SYNC (READ | REQ_SYNC | REQ_UNPLUG) +#define READ_SYNC (READ | REQ_SYNC) #define READ_META (READ | REQ_META) -#define WRITE_SYNC_PLUG (WRITE | REQ_SYNC | REQ_NOIDLE) -#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG) -#define WRITE_ODIRECT_PLUG (WRITE | REQ_SYNC) +#define WRITE_SYNC (WRITE | REQ_SYNC | REQ_NOIDLE) +#define WRITE_ODIRECT (WRITE | REQ_SYNC) #define WRITE_META (WRITE | REQ_META) -#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ - REQ_FLUSH) -#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ - REQ_FUA) -#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \ - REQ_FLUSH | REQ_FUA) +#define WRITE_FLUSH (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH) +#define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) +#define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) #define SEL_IN 1 #define SEL_OUT 2 diff --git a/kernel/power/block_io.c b/kernel/power/block_io.c index 83bbc7c02df..d09dd10c5a5 100644 --- a/kernel/power/block_io.c +++ b/kernel/power/block_io.c @@ -28,7 +28,7 @@ static int submit(int rw, struct block_device *bdev, sector_t sector, struct page *page, struct bio **bio_chain) { - const int bio_rw = rw | REQ_SYNC | REQ_UNPLUG; + const int bio_rw = rw | REQ_SYNC; struct bio *bio; bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1); diff --git a/mm/page_io.c b/mm/page_io.c index 2dee975bf46..dc76b4d0611 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -106,7 +106,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) goto out; } if (wbc->sync_mode == WB_SYNC_ALL) - rw |= REQ_SYNC | REQ_UNPLUG; + rw |= REQ_SYNC; count_vm_event(PSWPOUT); set_page_writeback(page); unlock_page(page); -- cgit v1.2.3-70-g09d2 From a91a2785b200864aef2270ed6a3babac7a253a20 Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Thu, 17 Mar 2011 11:11:05 +0100 Subject: block: Require subsystems to explicitly allocate bio_set integrity mempool MD and DM create a new bio_set for every metadevice. Each bio_set has an integrity mempool attached regardless of whether the metadevice is capable of passing integrity metadata. This is a waste of memory. Instead we defer the allocation decision to MD and DM since we know at metadevice creation time whether integrity passthrough is needed or not. Automatic integrity mempool allocation can then be removed from bioset_create() and we make an explicit integrity allocation for the fs_bio_set. Signed-off-by: Martin K. Petersen Reported-by: Zdenek Kabelac Acked-by: Mike Snitzer Signed-off-by: Jens Axboe --- drivers/md/dm-table.c | 7 +++++-- drivers/md/dm.c | 12 +++++++++--- drivers/md/dm.h | 2 +- drivers/md/linear.c | 3 +-- drivers/md/md.c | 8 ++++++-- drivers/md/multipath.c | 7 +++++-- drivers/md/raid0.c | 3 +-- drivers/md/raid1.c | 5 ++--- drivers/md/raid10.c | 7 +++++-- fs/bio-integrity.c | 3 +++ fs/bio.c | 6 +++--- 11 files changed, 41 insertions(+), 22 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index f50a7b95225..416d4e258df 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -55,6 +55,7 @@ struct dm_table { struct dm_target *targets; unsigned discards_supported:1; + unsigned integrity_supported:1; /* * Indicates the rw permissions for the new logical @@ -859,7 +860,7 @@ int dm_table_alloc_md_mempools(struct dm_table *t) return -EINVAL; } - t->mempools = dm_alloc_md_mempools(type); + t->mempools = dm_alloc_md_mempools(type, t->integrity_supported); if (!t->mempools) return -ENOMEM; @@ -935,8 +936,10 @@ static int dm_table_prealloc_integrity(struct dm_table *t, struct mapped_device struct dm_dev_internal *dd; list_for_each_entry(dd, devices, list) - if (bdev_get_integrity(dd->dm_dev.bdev)) + if (bdev_get_integrity(dd->dm_dev.bdev)) { + t->integrity_supported = 1; return blk_integrity_register(dm_disk(md), NULL); + } return 0; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index d22b9905c16..88820704a19 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2620,9 +2620,10 @@ int dm_noflush_suspending(struct dm_target *ti) } EXPORT_SYMBOL_GPL(dm_noflush_suspending); -struct dm_md_mempools *dm_alloc_md_mempools(unsigned type) +struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity) { struct dm_md_mempools *pools = kmalloc(sizeof(*pools), GFP_KERNEL); + unsigned int pool_size = (type == DM_TYPE_BIO_BASED) ? 16 : MIN_IOS; if (!pools) return NULL; @@ -2639,13 +2640,18 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type) if (!pools->tio_pool) goto free_io_pool_and_out; - pools->bs = (type == DM_TYPE_BIO_BASED) ? - bioset_create(16, 0) : bioset_create(MIN_IOS, 0); + pools->bs = bioset_create(pool_size, 0); if (!pools->bs) goto free_tio_pool_and_out; + if (integrity && bioset_integrity_create(pools->bs, pool_size)) + goto free_bioset_and_out; + return pools; +free_bioset_and_out: + bioset_free(pools->bs); + free_tio_pool_and_out: mempool_destroy(pools->tio_pool); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 0c2dd5f4af7..1aaf16746da 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -149,7 +149,7 @@ void dm_kcopyd_exit(void); /* * Mempool operations */ -struct dm_md_mempools *dm_alloc_md_mempools(unsigned type); +struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity); void dm_free_md_mempools(struct dm_md_mempools *pools); #endif diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 338804f8fb3..abfb59a61ed 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -210,8 +210,7 @@ static int linear_run (mddev_t *mddev) blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec); mddev->queue->backing_dev_info.congested_fn = linear_congested; mddev->queue->backing_dev_info.congested_data = mddev; - md_integrity_register(mddev); - return 0; + return md_integrity_register(mddev); } static void free_conf(struct rcu_head *head) diff --git a/drivers/md/md.c b/drivers/md/md.c index 86ba66c0b28..1876761f182 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1803,8 +1803,12 @@ int md_integrity_register(mddev_t *mddev) mdname(mddev)); return -EINVAL; } - printk(KERN_NOTICE "md: data integrity on %s enabled\n", - mdname(mddev)); + printk(KERN_NOTICE "md: data integrity enabled on %s\n", mdname(mddev)); + if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) { + printk(KERN_ERR "md: failed to create integrity pool for %s\n", + mdname(mddev)); + return -EINVAL; + } return 0; } EXPORT_SYMBOL(md_integrity_register); diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index 5e694b151c3..c3589099098 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -315,7 +315,7 @@ static int multipath_remove_disk(mddev_t *mddev, int number) p->rdev = rdev; goto abort; } - md_integrity_register(mddev); + err = md_integrity_register(mddev); } abort: @@ -489,7 +489,10 @@ static int multipath_run (mddev_t *mddev) mddev->queue->backing_dev_info.congested_fn = multipath_congested; mddev->queue->backing_dev_info.congested_data = mddev; - md_integrity_register(mddev); + + if (md_integrity_register(mddev)) + goto out_free_conf; + return 0; out_free_conf: diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 95916fd6394..e86bf3682e1 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -379,8 +379,7 @@ static int raid0_run(mddev_t *mddev) blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec); dump_zones(mddev); - md_integrity_register(mddev); - return 0; + return md_integrity_register(mddev); } static int raid0_stop(mddev_t *mddev) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 8f34ad5c478..c2a21ae56d9 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1132,7 +1132,7 @@ static int raid1_remove_disk(mddev_t *mddev, int number) p->rdev = rdev; goto abort; } - md_integrity_register(mddev); + err = md_integrity_register(mddev); } abort: @@ -2017,8 +2017,7 @@ static int run(mddev_t *mddev) mddev->queue->backing_dev_info.congested_fn = raid1_congested; mddev->queue->backing_dev_info.congested_data = mddev; - md_integrity_register(mddev); - return 0; + return md_integrity_register(mddev); } static int stop(mddev_t *mddev) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index c0d0f5f7e40..f7b62370b37 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1188,7 +1188,7 @@ static int raid10_remove_disk(mddev_t *mddev, int number) p->rdev = rdev; goto abort; } - md_integrity_register(mddev); + err = md_integrity_register(mddev); } abort: @@ -2343,7 +2343,10 @@ static int run(mddev_t *mddev) if (conf->near_copies < conf->raid_disks) blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec); - md_integrity_register(mddev); + + if (md_integrity_register(mddev)) + goto out_free_conf; + return 0; out_free_conf: diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c index e49cce234c6..9c5e6b2cd11 100644 --- a/fs/bio-integrity.c +++ b/fs/bio-integrity.c @@ -761,6 +761,9 @@ int bioset_integrity_create(struct bio_set *bs, int pool_size) { unsigned int max_slab = vecs_to_idx(BIO_MAX_PAGES); + if (bs->bio_integrity_pool) + return 0; + bs->bio_integrity_pool = mempool_create_slab_pool(pool_size, bip_slab[max_slab].slab); diff --git a/fs/bio.c b/fs/bio.c index 5694b756ed0..85e2eabb1f8 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1636,9 +1636,6 @@ struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad) if (!bs->bio_pool) goto bad; - if (bioset_integrity_create(bs, pool_size)) - goto bad; - if (!biovec_create_pools(bs, pool_size)) return bs; @@ -1682,6 +1679,9 @@ static int __init init_bio(void) if (!fs_bio_set) panic("bio: can't allocate bios\n"); + if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE)) + panic("bio: can't create integrity pool\n"); + bio_split_pool = mempool_create_kmalloc_pool(BIO_SPLIT_ENTRIES, sizeof(struct bio_pair)); if (!bio_split_pool) -- cgit v1.2.3-70-g09d2 From 89078d572eb9ce8d4c04264b8b0ba86de0d74c8f Mon Sep 17 00:00:00 2001 From: "Martin K. Petersen" Date: Mon, 28 Mar 2011 20:09:12 -0400 Subject: md: Fix integrity registration error when no devices are capable We incorrectly returned -EINVAL when none of the devices in the array had an integrity profile. This in turn prevented mdadm from starting the metadevice. Fix this so we only return errors on mismatched profiles and memory allocation failures. Reported-by: Giacomo Catenazzi Reported-by: Thomas Gleixner Signed-off-by: Martin K. Petersen Signed-off-by: Linus Torvalds --- drivers/md/md.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 06ecea751a3..8b66e04c2ea 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1777,12 +1777,6 @@ int md_integrity_register(mddev_t *mddev) continue; if (rdev->raid_disk < 0) continue; - /* - * If at least one rdev is not integrity capable, we can not - * enable data integrity for the md device. - */ - if (!bdev_get_integrity(rdev->bdev)) - return -EINVAL; if (!reference) { /* Use the first rdev as the reference */ reference = rdev; @@ -1793,6 +1787,8 @@ int md_integrity_register(mddev_t *mddev) rdev->bdev->bd_disk) < 0) return -EINVAL; } + if (!reference || !bdev_get_integrity(reference->bdev)) + return 0; /* * All component devices are integrity capable and have matching * profiles, register the common profile for the md device. -- cgit v1.2.3-70-g09d2