From d50bdd5aa55127635fd8a5c74bd2abb256bd34e3 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Mon, 7 Feb 2011 12:46:14 -0500 Subject: ext4: Fix data corruption with multi-block writepages support This fixes a corruption problem with the multi-block writepages submittal change for ext4, from commit bd2d0210cf22f2bd0cef72eb97cf94fc7d31d8cc ("ext4: use bio layer instead of buffer layer in mpage_da_submit_io"). (Note that this corruption is not present in 2.6.37 on ext4, because the corruption was detected after the feature was merged in 2.6.37-rc1, and so it was turned off by adding a non-default mount option, mblk_io_submit. With this commit, which hopefully fixes the last of the bugs with this feature, we'll be able to turn on this performance feature by default in 2.6.38, and remove the mblk_io_submit option.) The ext4 code path to bundle multiple pages for writeback in ext4_bio_write_page() had a bug: we should be clearing buffer head dirty flags *before* we submit the bio, not in the completion routine. The patch below was tested on 2.6.37 under KVM with the postgresql script which was submitted by Jon Nelson as documented in commit 1449032be1. Without the patch, I'd hit the corruption problem about 50-70% of the time. With the patch, I executed the script > 100 times with no corruption seen. I also fixed a bug to make sure ext4_end_bio() doesn't dereference the bio after the bio_put() call. Reported-by: Jon Nelson Reported-by: Matthias Bayer Signed-off-by: Curt Wohlgemuth Signed-off-by: "Theodore Ts'o" Cc: stable@kernel.org --- fs/ext4/page-io.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'fs/ext4/page-io.c') diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 7270dcfca92..4e9b0a242f4 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -190,6 +190,7 @@ static void ext4_end_bio(struct bio *bio, int error) struct inode *inode; unsigned long flags; int i; + sector_t bi_sector = bio->bi_sector; BUG_ON(!io_end); bio->bi_private = NULL; @@ -207,9 +208,7 @@ static void ext4_end_bio(struct bio *bio, int error) if (error) SetPageError(page); BUG_ON(!head); - if (head->b_size == PAGE_CACHE_SIZE) - clear_buffer_dirty(head); - else { + if (head->b_size != PAGE_CACHE_SIZE) { loff_t offset; loff_t io_end_offset = io_end->offset + io_end->size; @@ -221,7 +220,6 @@ static void ext4_end_bio(struct bio *bio, int error) if (error) buffer_io_error(bh); - clear_buffer_dirty(bh); } if (buffer_delay(bh)) partial_write = 1; @@ -257,7 +255,7 @@ static void ext4_end_bio(struct bio *bio, int error) (unsigned long long) io_end->offset, (long) io_end->size, (unsigned long long) - bio->bi_sector >> (inode->i_blkbits - 9)); + bi_sector >> (inode->i_blkbits - 9)); } /* Add the io_end to per-inode completed io list*/ @@ -380,6 +378,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, blocksize = 1 << inode->i_blkbits; + BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); set_page_writeback(page); ClearPageError(page); @@ -397,12 +396,14 @@ int ext4_bio_write_page(struct ext4_io_submit *io, for (bh = head = page_buffers(page), block_start = 0; bh != head || !block_start; block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; if (block_start >= len) { clear_buffer_dirty(bh); set_buffer_uptodate(bh); continue; } + clear_buffer_dirty(bh); ret = io_submit_add_bh(io, io_page, inode, wbc, bh); if (ret) { /* -- cgit v1.2.3-70-g09d2 From e9e3bcecf44c04b9e6b505fd8e2eb9cea58fb94d Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Sat, 12 Feb 2011 08:17:34 -0500 Subject: ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 10 ++++++++++ fs/ext4/extents.c | 10 ++++++---- fs/ext4/file.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++++- fs/ext4/page-io.c | 25 ++++++++++++----------- fs/ext4/super.c | 13 +++++++++++- 5 files changed, 100 insertions(+), 18 deletions(-) (limited to 'fs/ext4/page-io.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0c8d97b56f3..3aa0b72b3b9 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -848,6 +848,7 @@ struct ext4_inode_info { atomic_t i_ioend_count; /* Number of outstanding io_end structs */ /* current io_end structure for async DIO write*/ ext4_io_end_t *cur_aio_dio; + atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */ spinlock_t i_block_reservation_lock; @@ -2119,6 +2120,15 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) #define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) +/* For ioend & aio unwritten conversion wait queues */ +#define EXT4_WQ_HASH_SZ 37 +#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\ + EXT4_WQ_HASH_SZ]) +#define ext4_aio_mutex(v) (&ext4__aio_mutex[((unsigned long)(v)) %\ + EXT4_WQ_HASH_SZ]) +extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; +extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; + #endif /* __KERNEL__ */ #endif /* _EXT4_H */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 63a75810b7c..ccce8a7e94e 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3174,9 +3174,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, * that this IO needs to convertion to written when IO is * completed */ - if (io) + if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) { io->flag = EXT4_IO_END_UNWRITTEN; - else + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); if (ext4_should_dioread_nolock(inode)) map->m_flags |= EXT4_MAP_UNINIT; @@ -3463,9 +3464,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * that we need to perform convertion when IO is done. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { - if (io) + if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) { io->flag = EXT4_IO_END_UNWRITTEN; - else + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 2e8322c8aa8..7b80d543b89 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -55,11 +55,47 @@ static int ext4_release_file(struct inode *inode, struct file *filp) return 0; } +static void ext4_aiodio_wait(struct inode *inode) +{ + wait_queue_head_t *wq = ext4_ioend_wq(inode); + + wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0)); +} + +/* + * This tests whether the IO in question is block-aligned or not. + * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they + * are converted to written only after the IO is complete. Until they are + * mapped, these blocks appear as holes, so dio_zero_block() will assume that + * it needs to zero out portions of the start and/or end block. If 2 AIO + * threads are at work on the same unwritten block, they must be synchronized + * or one thread will zero the other's data, causing corruption. + */ +static int +ext4_unaligned_aio(struct inode *inode, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + struct super_block *sb = inode->i_sb; + int blockmask = sb->s_blocksize - 1; + size_t count = iov_length(iov, nr_segs); + loff_t final_size = pos + count; + + if (pos >= inode->i_size) + return 0; + + if ((pos & blockmask) || (final_size & blockmask)) + return 1; + + return 0; +} + static ssize_t ext4_file_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; + int unaligned_aio = 0; + int ret; /* * If we have encountered a bitmap-format file, the size limit @@ -78,9 +114,31 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, nr_segs = iov_shorten((struct iovec *)iov, nr_segs, sbi->s_bitmap_maxbytes - pos); } + } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) && + !is_sync_kiocb(iocb))) { + unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos); } - return generic_file_aio_write(iocb, iov, nr_segs, pos); + /* Unaligned direct AIO must be serialized; see comment above */ + if (unaligned_aio) { + static unsigned long unaligned_warn_time; + + /* Warn about this once per day */ + if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ)) + ext4_msg(inode->i_sb, KERN_WARNING, + "Unaligned AIO/DIO on inode %ld by %s; " + "performance will be poor.", + inode->i_ino, current->comm); + mutex_lock(ext4_aio_mutex(inode)); + ext4_aiodio_wait(inode); + } + + ret = generic_file_aio_write(iocb, iov, nr_segs, pos); + + if (unaligned_aio) + mutex_unlock(ext4_aio_mutex(inode)); + + return ret; } static const struct vm_operations_struct ext4_file_vm_ops = { diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 4e9b0a242f4..955cc309142 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -32,14 +32,8 @@ static struct kmem_cache *io_page_cachep, *io_end_cachep; -#define WQ_HASH_SZ 37 -#define to_ioend_wq(v) (&ioend_wq[((unsigned long)v) % WQ_HASH_SZ]) -static wait_queue_head_t ioend_wq[WQ_HASH_SZ]; - int __init ext4_init_pageio(void) { - int i; - io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT); if (io_page_cachep == NULL) return -ENOMEM; @@ -48,9 +42,6 @@ int __init ext4_init_pageio(void) kmem_cache_destroy(io_page_cachep); return -ENOMEM; } - for (i = 0; i < WQ_HASH_SZ; i++) - init_waitqueue_head(&ioend_wq[i]); - return 0; } @@ -62,7 +53,7 @@ void ext4_exit_pageio(void) void ext4_ioend_wait(struct inode *inode) { - wait_queue_head_t *wq = to_ioend_wq(inode); + wait_queue_head_t *wq = ext4_ioend_wq(inode); wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0)); } @@ -87,7 +78,7 @@ void ext4_free_io_end(ext4_io_end_t *io) for (i = 0; i < io->num_io_pages; i++) put_io_page(io->pages[i]); io->num_io_pages = 0; - wq = to_ioend_wq(io->inode); + wq = ext4_ioend_wq(io->inode); if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) && waitqueue_active(wq)) wake_up_all(wq); @@ -102,6 +93,7 @@ int ext4_end_io_nolock(ext4_io_end_t *io) struct inode *inode = io->inode; loff_t offset = io->offset; ssize_t size = io->size; + wait_queue_head_t *wq; int ret = 0; ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p," @@ -126,7 +118,16 @@ int ext4_end_io_nolock(ext4_io_end_t *io) if (io->iocb) aio_complete(io->iocb, io->result, 0); /* clear the DIO AIO unwritten flag */ - io->flag &= ~EXT4_IO_END_UNWRITTEN; + if (io->flag & EXT4_IO_END_UNWRITTEN) { + io->flag &= ~EXT4_IO_END_UNWRITTEN; + /* Wake up anyone waiting on unwritten extent conversion */ + wq = ext4_ioend_wq(io->inode); + if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) && + waitqueue_active(wq)) { + wake_up_all(wq); + } + } + return ret; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 86b05486dc6..f6a318f836b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -833,6 +833,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); + atomic_set(&ei->i_aiodio_unwritten, 0); return &ei->vfs_inode; } @@ -4800,11 +4801,21 @@ static void ext4_exit_feat_adverts(void) kfree(ext4_feat); } +/* Shared across all ext4 file systems */ +wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ]; +struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ]; + static int __init ext4_init_fs(void) { - int err; + int i, err; ext4_check_flag_values(); + + for (i = 0; i < EXT4_WQ_HASH_SZ; i++) { + mutex_init(&ext4__aio_mutex[i]); + init_waitqueue_head(&ext4__ioend_wq[i]); + } + err = ext4_init_pageio(); if (err) return err; -- 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 'fs/ext4/page-io.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