From 441c850857148935babe000fc2ba1455fe54a6a9 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Sat, 13 Aug 2011 11:25:18 -0400 Subject: ext4: Fix ext4_should_writeback_data() for no-journal mode ext4_should_writeback_data() had an incorrect sequence of tests to determine if it should return 0 or 1: in particular, even in no-journal mode, 0 was being returned for a non-regular-file inode. This meant that, in non-journal mode, we would use ext4_journalled_aops for directories, symlinks, and other non-regular files. However, calling journalled aop callbacks when there is no valid handle, can cause problems. This would cause a kernel crash with Jan Kara's commit 2d859db3e4 ("ext4: fix data corruption in inodes with journalled data"), because we now dereference 'handle' in ext4_journalled_write_end(). I also added BUG_ONs to check for a valid handle in the obviously journal-only aops callbacks. I tested this running xfstests with a scratch device in these modes: - no-journal - data=ordered - data=writeback - data=journal All work fine; the data=journal run has many failures and a crash in xfstests 074, but this is no different from a vanilla kernel. Signed-off-by: Curt Wohlgemuth Signed-off-by: "Theodore Ts'o" Cc: stable@kernel.org --- fs/ext4/inode.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d47264cafee0..ad3a7ca21069 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -983,6 +983,8 @@ static int ext4_journalled_write_end(struct file *file, from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; + BUG_ON(!ext4_handle_valid(handle)); + if (copied < len) { if (!PageUptodate(page)) copied = 0; @@ -1699,6 +1701,8 @@ static int __ext4_journalled_writepage(struct page *page, goto out; } + BUG_ON(!ext4_handle_valid(handle)); + ret = walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); -- cgit v1.2.3 From 2581fdc810889fdea97689cb62481201d579c796 Mon Sep 17 00:00:00 2001 From: Jiaying Zhang Date: Sat, 13 Aug 2011 12:17:13 -0400 Subject: ext4: call ext4_ioend_wait and ext4_flush_completed_IO in ext4_evict_inode Flush inode's i_completed_io_list before calling ext4_io_wait to prevent the following deadlock scenario: A page fault happens while some process is writing inode A. During page fault, shrink_icache_memory is called that in turn evicts another inode B. Inode B has some pending io_end work so it calls ext4_ioend_wait() that waits for inode B's i_ioend_count to become zero. However, inode B's ioend work was queued behind some of inode A's ioend work on the same cpu's ext4-dio-unwritten workqueue. As the ext4-dio-unwritten thread on that cpu is processing inode A's ioend work, it tries to grab inode A's i_mutex lock. Since the i_mutex lock of inode A is still hold before the page fault happened, we enter a deadlock. Also moves ext4_flush_completed_IO and ext4_ioend_wait from ext4_destroy_inode() to ext4_evict_inode(). During inode deleteion, ext4_evict_inode() is called before ext4_destroy_inode() and in ext4_evict_inode(), we may call ext4_truncate() without holding i_mutex lock. As a result, there is a race between flush_completed_IO that is called from ext4_ext_truncate() and ext4_end_io_work, which may cause corruption on an io_end structure. This change moves ext4_flush_completed_IO and ext4_ioend_wait from ext4_destroy_inode() to ext4_evict_inode() to resolve the race between ext4_truncate() and ext4_end_io_work during inode deletion. Signed-off-by: Jiaying Zhang Signed-off-by: "Theodore Ts'o" Cc: stable@kernel.org --- fs/ext4/inode.c | 6 ++++++ fs/ext4/super.c | 1 - 2 files changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ad3a7ca21069..7dd698107822 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -120,6 +120,12 @@ void ext4_evict_inode(struct inode *inode) int err; trace_ext4_evict_inode(inode); + + mutex_lock(&inode->i_mutex); + ext4_flush_completed_IO(inode); + mutex_unlock(&inode->i_mutex); + ext4_ioend_wait(inode); + if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4687fea0c00f..44d0c8db2239 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -919,7 +919,6 @@ static void ext4_i_callback(struct rcu_head *head) static void ext4_destroy_inode(struct inode *inode) { - ext4_ioend_wait(inode); if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", -- cgit v1.2.3 From 32c80b32c053dc52712dedac5e4d0aa7c93fc353 Mon Sep 17 00:00:00 2001 From: Tao Ma Date: Sat, 13 Aug 2011 12:30:59 -0400 Subject: ext4: Resolve the hang of direct i/o read in handling EXT4_IO_END_UNWRITTEN. EXT4_IO_END_UNWRITTEN flag set and the increase of i_aiodio_unwritten should be done simultaneously since ext4_end_io_nolock always clear the flag and decrease the counter in the same time. We don't increase i_aiodio_unwritten when setting EXT4_IO_END_UNWRITTEN so it will go nagative and causes some process to wait forever. Part of the patch came from Eric in his e-mail, but it doesn't fix the problem met by Michael actually. http://marc.info/?l=linux-ext4&m=131316851417460&w=2 Reported-and-Tested-by: Michael Tokarev Signed-off-by: Eric Sandeen Signed-off-by: Tao Ma Signed-off-by: "Theodore Ts'o" Cc: stable@kernel.org --- fs/ext4/inode.c | 9 ++++++++- fs/ext4/page-io.c | 6 ++++-- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7dd698107822..762e8037c888 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2678,8 +2678,15 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) goto out; } - io_end->flag = EXT4_IO_END_UNWRITTEN; + /* + * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now, + * but being more careful is always safe for the future change. + */ inode = io_end->inode; + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + io_end->flag |= EXT4_IO_END_UNWRITTEN; + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } /* Add the io_end to per-inode completed io list*/ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 430c401d0895..78839af7ce29 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -334,8 +334,10 @@ submit_and_retry: if ((io_end->num_io_pages >= MAX_IO_PAGES) && (io_end->pages[io_end->num_io_pages-1] != io_page)) goto submit_and_retry; - if (buffer_uninit(bh)) - io->io_end->flag |= EXT4_IO_END_UNWRITTEN; + if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + io_end->flag |= EXT4_IO_END_UNWRITTEN; + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } io->io_end->size += bh->b_size; io->io_next_block++; ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); -- cgit v1.2.3 From 9dd75f1f1a02d656a11a7b9b9e6c2759b9c1e946 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 13 Aug 2011 12:58:21 -0400 Subject: ext4: fix nomblk_io_submit option so it correctly converts uninit blocks Bug discovered by Jan Kara: Finally, commit 1449032be17abb69116dbc393f67ceb8bd034f92 returned back the old IO submission code but apparently it forgot to return the old handling of uninitialized buffers so we unconditionnaly call block_write_full_page() without specifying end_io function. So AFAICS we never convert unwritten extents to written in some cases. For example when I mount the fs as: mount -t ext4 -o nomblk_io_submit,dioread_nolock /dev/ubdb /mnt and do int fd = open(argv[1], O_RDWR | O_CREAT | O_TRUNC, 0600); char buf[1024]; memset(buf, 'a', sizeof(buf)); fallocate(fd, 0, 0, 16384); write(fd, buf, sizeof(buf)); I get a file full of zeros (after remounting the filesystem so that pagecache is dropped) instead of seeing the first KB contain 'a's. Signed-off-by: "Theodore Ts'o" Cc: stable@kernel.org --- fs/ext4/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 762e8037c888..c4da98a959ae 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1291,7 +1291,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT)) err = ext4_bio_write_page(&io_submit, page, len, mpd->wbc); - else + else if (buffer_uninit(page_bufs)) { + ext4_set_bh_endio(page_bufs, inode); + err = block_write_full_page_endio(page, + noalloc_get_block_write, + mpd->wbc, ext4_end_io_buffer_write); + } else err = block_write_full_page(page, noalloc_get_block_write, mpd->wbc); -- cgit v1.2.3 From 5dc06c5a70b79a323152bec7e55783e705767e63 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Aug 2011 14:49:55 +0200 Subject: block: remove READ_META and WRITE_META Replace all occurnanced of the undocumented READ_META with READ | REQ_META and remove the unused WRITE_META define. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/ext3/inode.c | 4 ++-- fs/ext3/namei.c | 2 +- fs/ext4/inode.c | 4 ++-- fs/ext4/namei.c | 2 +- fs/gfs2/quota.c | 2 +- include/linux/fs.h | 2 -- 6 files changed, 7 insertions(+), 9 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 04da6acde85d..bba7b96e0d9b 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1134,7 +1134,7 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -2807,7 +2807,7 @@ make_io: trace_ext3_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ_META, bh); + submit_bh(READ | REQ_META, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext3_error(inode->i_sb, "ext3_get_inode_loc", diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 5571708b6a58..c7d4032aa82a 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -922,7 +922,7 @@ restart: bh = ext3_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META, 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c4da98a959ae..1dfa18feeb3e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -650,7 +650,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -3301,7 +3301,7 @@ make_io: trace_ext4_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ_META, bh); + submit_bh(READ | REQ_META, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { EXT4_ERROR_INODE_BLOCK(inode, block, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f8068c7bae9f..d36315ae629e 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -922,7 +922,7 @@ restart: bh = ext4_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META, 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 42e8d23bc047..053434049dbb 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -709,7 +709,7 @@ get_a_page: set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { - ll_rw_block(READ_META, 1, &bh); + ll_rw_block(READ | REQ_META, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) goto unlock_out; diff --git a/include/linux/fs.h b/include/linux/fs.h index 178cdb4f1d4a..eae44c981173 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -162,10 +162,8 @@ struct inodes_stat_t { #define READA RWA_MASK #define READ_SYNC (READ | REQ_SYNC) -#define READ_META (READ | REQ_META) #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_FLUSH) #define WRITE_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FUA) #define WRITE_FLUSH_FUA (WRITE | REQ_SYNC | REQ_NOIDLE | REQ_FLUSH | REQ_FUA) -- cgit v1.2.3 From 65299a3b788bd274bed92f9fa3232082c9f3ea70 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 23 Aug 2011 14:50:29 +0200 Subject: block: separate priority boosting from REQ_META Add a new REQ_PRIO to let requests preempt others in the cfq I/O schedule, and lave REQ_META purely for marking requests as metadata in blktrace. All existing callers of REQ_META except for XFS are updated to also set REQ_PRIO for now. Signed-off-by: Christoph Hellwig Reviewed-by: Namhyung Kim Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 20 ++++++++++---------- drivers/mmc/card/block.c | 3 +++ fs/ext3/inode.c | 4 ++-- fs/ext3/namei.c | 3 ++- fs/ext4/inode.c | 4 ++-- fs/ext4/namei.c | 3 ++- fs/gfs2/log.c | 4 ++-- fs/gfs2/meta_io.c | 6 +++--- fs/gfs2/ops_fstype.c | 2 +- fs/gfs2/quota.c | 2 +- include/linux/blk_types.h | 6 ++++-- 11 files changed, 32 insertions(+), 25 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index a33bd4377c61..16ace89613bc 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -130,8 +130,8 @@ struct cfq_queue { unsigned long slice_end; long slice_resid; - /* pending metadata requests */ - int meta_pending; + /* pending priority requests */ + int prio_pending; /* number of requests that are on the dispatch list or inside driver */ int dispatched; @@ -684,8 +684,8 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, if (rq_is_sync(rq1) != rq_is_sync(rq2)) return rq_is_sync(rq1) ? rq1 : rq2; - if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_META) - return rq1->cmd_flags & REQ_META ? rq1 : rq2; + if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO) + return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2; s1 = blk_rq_pos(rq1); s2 = blk_rq_pos(rq2); @@ -1612,9 +1612,9 @@ static void cfq_remove_request(struct request *rq) cfqq->cfqd->rq_queued--; cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); - if (rq->cmd_flags & REQ_META) { - WARN_ON(!cfqq->meta_pending); - cfqq->meta_pending--; + if (rq->cmd_flags & REQ_PRIO) { + WARN_ON(!cfqq->prio_pending); + cfqq->prio_pending--; } } @@ -3372,7 +3372,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, * So both queues are sync. Let the new request get disk time if * it's a metadata request and the current queue is doing regular IO. */ - if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending) + if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending) return true; /* @@ -3439,8 +3439,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic = RQ_CIC(rq); cfqd->rq_queued++; - if (rq->cmd_flags & REQ_META) - cfqq->meta_pending++; + if (rq->cmd_flags & REQ_PRIO) + cfqq->prio_pending++; cfq_update_io_thinktime(cfqd, cfqq, cic); cfq_update_io_seektime(cfqd, cfqq, rq); diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 1ff5486213fb..4c1a648d00fc 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -926,6 +926,9 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, /* * Reliable writes are used to implement Forced Unit Access and * REQ_META accesses, and are supported only on MMCs. + * + * XXX: this really needs a good explanation of why REQ_META + * is treated special. */ bool do_rel_wr = ((req->cmd_flags & REQ_FUA) || (req->cmd_flags & REQ_META)) && diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index bba7b96e0d9b..12661e1deedd 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1134,7 +1134,7 @@ struct buffer_head *ext3_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -2807,7 +2807,7 @@ make_io: trace_ext3_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ | REQ_META, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { ext3_error(inode->i_sb, "ext3_get_inode_loc", diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index c7d4032aa82a..0629e09f6511 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -922,7 +922,8 @@ restart: bh = ext3_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, + 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1dfa18feeb3e..c7cbb3d85d9e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -650,7 +650,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, return bh; if (buffer_uptodate(bh)) return bh; - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; @@ -3301,7 +3301,7 @@ make_io: trace_ext4_load_inode(inode); get_bh(bh); bh->b_end_io = end_buffer_read_sync; - submit_bh(READ | REQ_META, bh); + submit_bh(READ | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { EXT4_ERROR_INODE_BLOCK(inode, block, diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d36315ae629e..1c924faeb6c8 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -922,7 +922,8 @@ restart: bh = ext4_getblk(NULL, dir, b++, 0, &err); bh_use[ra_max] = bh; if (bh) - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, + 1, &bh); } } if ((bh = bh_use[ra_ptr++]) == NULL) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 85c62923ee29..598646434362 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -624,9 +624,9 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) bh->b_end_io = end_buffer_write_sync; get_bh(bh); if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) - submit_bh(WRITE_SYNC | REQ_META, bh); + submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh); else - submit_bh(WRITE_FLUSH_FUA | REQ_META, bh); + submit_bh(WRITE_FLUSH_FUA | REQ_META | REQ_PRIO, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 747238cd9f96..be29858900f6 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 | + int write_op = REQ_META | REQ_PRIO | (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); BUG_ON(!PageLocked(page)); @@ -225,7 +225,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, } bh->b_end_io = end_buffer_read_sync; get_bh(bh); - submit_bh(READ_SYNC | REQ_META, bh); + submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh); if (!(flags & DIO_WAIT)) return 0; @@ -435,7 +435,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) if (buffer_uptodate(first_bh)) goto out; if (!buffer_locked(first_bh)) - ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh); + ll_rw_block(READ_SYNC | REQ_META | REQ_PRIO, 1, &first_bh); dblock++; extlen--; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 3bc073a4cf82..079587e53849 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -224,7 +224,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) bio->bi_end_io = end_bio_io_page; bio->bi_private = page; - submit_bio(READ_SYNC | REQ_META, bio); + submit_bio(READ_SYNC | REQ_META | REQ_PRIO, bio); wait_on_page_locked(page); bio_put(bio); if (!PageUptodate(page)) { diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 053434049dbb..0e8bb13381e4 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -709,7 +709,7 @@ get_a_page: set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { - ll_rw_block(READ | REQ_META, 1, &bh); + ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) goto unlock_out; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 32f0076e844b..71fc53bb8f1c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -124,6 +124,7 @@ enum rq_flag_bits { __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ + __REQ_PRIO, /* boost priority in cfq */ __REQ_DISCARD, /* request to discard sectors */ __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ @@ -161,14 +162,15 @@ enum rq_flag_bits { #define REQ_FAILFAST_DRIVER (1 << __REQ_FAILFAST_DRIVER) #define REQ_SYNC (1 << __REQ_SYNC) #define REQ_META (1 << __REQ_META) +#define REQ_PRIO (1 << __REQ_PRIO) #define REQ_DISCARD (1 << __REQ_DISCARD) #define REQ_NOIDLE (1 << __REQ_NOIDLE) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ - (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \ - REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) + (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \ + REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE) #define REQ_CLONE_MASK REQ_COMMON_MASK #define REQ_RAHEAD (1 << __REQ_RAHEAD) -- cgit v1.2.3 From 8c0bec2151a47906bf779c6715a10ce04453ab77 Mon Sep 17 00:00:00 2001 From: Jiaying Zhang Date: Wed, 31 Aug 2011 11:50:51 -0400 Subject: ext4: remove i_mutex lock in ext4_evict_inode to fix lockdep complaining The i_mutex lock and flush_completed_IO() added by commit 2581fdc810 in ext4_evict_inode() causes lockdep complaining about potential deadlock in several places. In most/all of these LOCKDEP complaints it looks like it's a false positive, since many of the potential circular locking cases can't take place by the time the ext4_evict_inode() is called; but since at the very least it may mask real problems, we need to address this. This change removes the flush_completed_IO() and i_mutex lock in ext4_evict_inode(). Instead, we take a different approach to resolve the software lockup that commit 2581fdc810 intends to fix. Rather than having ext4-dio-unwritten thread wait for grabing the i_mutex lock of an inode, we use mutex_trylock() instead, and simply requeue the work item if we fail to grab the inode's i_mutex lock. This should speed up work queue processing in general and also prevents the following deadlock scenario: During page fault, shrink_icache_memory is called that in turn evicts another inode B. Inode B has some pending io_end work so it calls ext4_ioend_wait() that waits for inode B's i_ioend_count to become zero. However, inode B's ioend work was queued behind some of inode A's ioend work on the same cpu's ext4-dio-unwritten workqueue. As the ext4-dio-unwritten thread on that cpu is processing inode A's ioend work, it tries to grab inode A's i_mutex lock. Since the i_mutex lock of inode A is still hold before the page fault happened, we enter a deadlock. Signed-off-by: Jiaying Zhang Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 1 + fs/ext4/inode.c | 3 --- fs/ext4/page-io.c | 18 +++++++++++++++++- 3 files changed, 18 insertions(+), 4 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e717dfd2f2b4..b7d7bd0f066e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -175,6 +175,7 @@ struct mpage_da_data { */ #define EXT4_IO_END_UNWRITTEN 0x0001 #define EXT4_IO_END_ERROR 0x0002 +#define EXT4_IO_END_QUEUED 0x0004 struct ext4_io_page { struct page *p_page; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c4da98a959ae..18d2558b7624 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -121,9 +121,6 @@ void ext4_evict_inode(struct inode *inode) trace_ext4_evict_inode(inode); - mutex_lock(&inode->i_mutex); - ext4_flush_completed_IO(inode); - mutex_unlock(&inode->i_mutex); ext4_ioend_wait(inode); if (inode->i_nlink) { diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 78839af7ce29..92f38ee13f8a 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work) unsigned long flags; int ret; - mutex_lock(&inode->i_mutex); + if (!mutex_trylock(&inode->i_mutex)) { + /* + * Requeue the work instead of waiting so that the work + * items queued after this can be processed. + */ + queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work); + /* + * To prevent the ext4-dio-unwritten thread from keeping + * requeueing end_io requests and occupying cpu for too long, + * yield the cpu if it sees an end_io request that has already + * been requeued. + */ + if (io->flag & EXT4_IO_END_QUEUED) + yield(); + io->flag |= EXT4_IO_END_QUEUED; + return; + } ret = ext4_end_io_nolock(io); if (ret < 0) { mutex_unlock(&inode->i_mutex); -- cgit v1.2.3 From 84ebd795613488992b273220c2937d575d27d2a9 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Wed, 31 Aug 2011 11:56:51 -0400 Subject: ext4: fake direct I/O mode for data=journal Currently attempts to open a file with O_DIRECT in data=journal mode causes the open to fail with -EINVAL. This makes it very hard to test data=journal mode. So we will let the open succeed, but then always fall back to O_DSYNC buffered writes. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 18d2558b7624..b84f127c085d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2854,6 +2854,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, struct inode *inode = file->f_mapping->host; ssize_t ret; + /* + * If we are doing data journalling we don't support O_DIRECT + */ + if (ext4_should_journal_data(inode)) + return 0; + trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); @@ -2923,6 +2929,7 @@ static const struct address_space_operations ext4_journalled_aops = { .bmap = ext4_bmap, .invalidatepage = ext4_invalidatepage, .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_page = generic_error_remove_page, }; -- cgit v1.2.3 From 4e96b2dbbf1d7e81f22047a50f862555a6cb87cb Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Sat, 3 Sep 2011 11:51:09 -0400 Subject: ext4: Add new ext4_discard_partial_page_buffers routines This patch adds two new routines: ext4_discard_partial_page_buffers and ext4_discard_partial_page_buffers_no_lock. The ext4_discard_partial_page_buffers routine is a wrapper function to ext4_discard_partial_page_buffers_no_lock. The wrapper function locks the page and passes it to ext4_discard_partial_page_buffers_no_lock. Calling functions that already have the page locked can call ext4_discard_partial_page_buffers_no_lock directly. The ext4_discard_partial_page_buffers_no_lock function zeros a specified range in a page, and unmaps the corresponding buffer heads. Only block aligned regions of the page will have their buffer heads unmapped. Unblock aligned regions will be mapped if needed so that they can be updated with the partial zero out. This function is meant to be used to update a page and its buffer heads to be zeroed and unmapped when the corresponding blocks have been released or will be released. This routine is used in the following scenarios: * A hole is punched and the non page aligned regions of the head and tail of the hole need to be discarded * The file is truncated and the partial page beyond EOF needs to be discarded * The end of a hole is in the same page as EOF. After the page is flushed, the partial page beyond EOF needs to be discarded. * A write operation begins or ends inside a hole and the partial page appearing before or after the write needs to be discarded * A write operation extends EOF and the partial page beyond EOF needs to be discarded This function takes a flag EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED which is used when a write operation begins or ends in a hole. When the EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED flag is used, only buffer heads that are already unmapped will have the corresponding regions of the page zeroed. Signed-off-by: Allison Henderson Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 11 +++ fs/ext4/inode.c | 224 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 235 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5c38120c389c..ccfa81f33bb0 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -528,6 +528,11 @@ struct ext4_new_group_data { #define EXT4_FREE_BLOCKS_VALIDATED 0x0004 #define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008 +/* + * Flags used by ext4_discard_partial_page_buffers + */ +#define EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED 0x0001 + /* * ioctl commands */ @@ -1838,6 +1843,12 @@ extern int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from); extern int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length); +extern int ext4_discard_partial_page_buffers(handle_t *handle, + struct address_space *mapping, loff_t from, + loff_t length, int flags); +extern int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, + struct inode *inode, struct page *page, loff_t from, + loff_t length, int flags); extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b84f127c085d..d1b1ef71e5b7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2966,6 +2966,230 @@ void ext4_set_aops(struct inode *inode) inode->i_mapping->a_ops = &ext4_journalled_aops; } + +/* + * ext4_discard_partial_page_buffers() + * Wrapper function for ext4_discard_partial_page_buffers_no_lock. + * This function finds and locks the page containing the offset + * "from" and passes it to ext4_discard_partial_page_buffers_no_lock. + * Calling functions that already have the page locked should call + * ext4_discard_partial_page_buffers_no_lock directly. + */ +int ext4_discard_partial_page_buffers(handle_t *handle, + struct address_space *mapping, loff_t from, + loff_t length, int flags) +{ + struct inode *inode = mapping->host; + struct page *page; + int err = 0; + + page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, + mapping_gfp_mask(mapping) & ~__GFP_FS); + if (!page) + return -EINVAL; + + err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page, + from, length, flags); + + unlock_page(page); + page_cache_release(page); + return err; +} + +/* + * ext4_discard_partial_page_buffers_no_lock() + * Zeros a page range of length 'length' starting from offset 'from'. + * Buffer heads that correspond to the block aligned regions of the + * zeroed range will be unmapped. Unblock aligned regions + * will have the corresponding buffer head mapped if needed so that + * that region of the page can be updated with the partial zero out. + * + * This function assumes that the page has already been locked. The + * The range to be discarded must be contained with in the given page. + * If the specified range exceeds the end of the page it will be shortened + * to the end of the page that corresponds to 'from'. This function is + * appropriate for updating a page and it buffer heads to be unmapped and + * zeroed for blocks that have been either released, or are going to be + * released. + * + * handle: The journal handle + * inode: The files inode + * page: A locked page that contains the offset "from" + * from: The starting byte offset (from the begining of the file) + * to begin discarding + * len: The length of bytes to discard + * flags: Optional flags that may be used: + * + * EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED + * Only zero the regions of the page whose buffer heads + * have already been unmapped. This flag is appropriate + * for updateing the contents of a page whose blocks may + * have already been released, and we only want to zero + * out the regions that correspond to those released blocks. + * + * Returns zero on sucess or negative on failure. + */ +int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, + struct inode *inode, struct page *page, loff_t from, + loff_t length, int flags) +{ + ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT; + unsigned int offset = from & (PAGE_CACHE_SIZE-1); + unsigned int blocksize, max, pos; + unsigned int end_of_block, range_to_discard; + ext4_lblk_t iblock; + struct buffer_head *bh; + int err = 0; + + blocksize = inode->i_sb->s_blocksize; + max = PAGE_CACHE_SIZE - offset; + + if (index != page->index) + return -EINVAL; + + /* + * correct length if it does not fall between + * 'from' and the end of the page + */ + if (length > max || length < 0) + length = max; + + iblock = index << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits); + + if (!page_has_buffers(page)) { + /* + * If the range to be discarded covers a partial block + * we need to get the page buffers. This is because + * partial blocks cannot be released and the page needs + * to be updated with the contents of the block before + * we write the zeros on top of it. + */ + if (!(from & (blocksize - 1)) || + !((from + length) & (blocksize - 1))) { + create_empty_buffers(page, blocksize, 0); + } else { + /* + * If there are no partial blocks, + * there is nothing to update, + * so we can return now + */ + return 0; + } + } + + /* Find the buffer that contains "offset" */ + bh = page_buffers(page); + pos = blocksize; + while (offset >= pos) { + bh = bh->b_this_page; + iblock++; + pos += blocksize; + } + + pos = offset; + while (pos < offset + length) { + err = 0; + + /* The length of space left to zero and unmap */ + range_to_discard = offset + length - pos; + + /* The length of space until the end of the block */ + end_of_block = blocksize - (pos & (blocksize-1)); + + /* + * Do not unmap or zero past end of block + * for this buffer head + */ + if (range_to_discard > end_of_block) + range_to_discard = end_of_block; + + + /* + * Skip this buffer head if we are only zeroing unampped + * regions of the page + */ + if (flags & EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED && + buffer_mapped(bh)) + goto next; + + /* If the range is block aligned, unmap */ + if (range_to_discard == blocksize) { + clear_buffer_dirty(bh); + bh->b_bdev = NULL; + clear_buffer_mapped(bh); + clear_buffer_req(bh); + clear_buffer_new(bh); + clear_buffer_delay(bh); + clear_buffer_unwritten(bh); + clear_buffer_uptodate(bh); + zero_user(page, pos, range_to_discard); + BUFFER_TRACE(bh, "Buffer discarded"); + goto next; + } + + /* + * If this block is not completely contained in the range + * to be discarded, then it is not going to be released. Because + * we need to keep this block, we need to make sure this part + * of the page is uptodate before we modify it by writeing + * partial zeros on it. + */ + if (!buffer_mapped(bh)) { + /* + * Buffer head must be mapped before we can read + * from the block + */ + BUFFER_TRACE(bh, "unmapped"); + ext4_get_block(inode, iblock, bh, 0); + /* unmapped? It's a hole - nothing to do */ + if (!buffer_mapped(bh)) { + BUFFER_TRACE(bh, "still unmapped"); + goto next; + } + } + + /* Ok, it's mapped. Make sure it's up-to-date */ + if (PageUptodate(page)) + set_buffer_uptodate(bh); + + if (!buffer_uptodate(bh)) { + err = -EIO; + ll_rw_block(READ, 1, &bh); + wait_on_buffer(bh); + /* Uhhuh. Read error. Complain and punt.*/ + if (!buffer_uptodate(bh)) + goto next; + } + + if (ext4_should_journal_data(inode)) { + BUFFER_TRACE(bh, "get write access"); + err = ext4_journal_get_write_access(handle, bh); + if (err) + goto next; + } + + zero_user(page, pos, range_to_discard); + + err = 0; + if (ext4_should_journal_data(inode)) { + err = ext4_handle_dirty_metadata(handle, inode, bh); + } else { + if (ext4_should_order_data(inode) && + EXT4_I(inode)->jinode) + err = ext4_jbd2_file_inode(handle, inode); + mark_buffer_dirty(bh); + } + + BUFFER_TRACE(bh, "Partial buffer zeroed"); +next: + bh = bh->b_this_page; + iblock++; + pos += range_to_discard; + } + + return err; +} + /* * ext4_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. -- cgit v1.2.3 From decbd919f4bb9cb698486880c026c4104b13d3c3 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 6 Sep 2011 02:37:06 -0400 Subject: ext4: only call ext4_jbd2_file_inode when an inode has been extended In delayed allocation mode, it's important to only call ext4_jbd2_file_inode when the file has been extended. This is necessary to avoid a race which first got introduced in commit 678aaf481, but which was made much more common with the introduction of the "punch hole" functionality. (Especially when dioread_nolock was enabled; when I could reliably reproduce this problem with xfstests #74.) The race is this: If while trying to writeback a delayed allocation inode, there is a need to map delalloc blocks, and we run out of space in the journal, *and* at the same time the inode is already on the committing transaction's t_inode_list (because for example while doing the punch hole operation, ext4_jbd2_file_inode() is called), then the commit operation will wait for the inode to finish all of its pending writebacks by calling filemap_fdatawait(), but since that inode has one or more pages with the PageWriteback flag set, the commit operation will wait forever, and the so the writeback of the inode can never take place, and the kjournald thread and the writeback thread end up waiting for each other --- forever. It's important at this point to recall why an inode is placed on the t_inode_list; it is to provide the data=ordered guarantees that we don't end up exposing stale data. In the case where we are truncating or punching a hole in the inode, there is no possibility that stale data could be exposed in the first place, so we don't need to put the inode on the t_inode_list! The right long-term fix is to get rid of data=ordered mode altogether, and only update the extent tree or indirect blocks after the data has been written. Until then, this change will also avoid some unnecessary waiting in the commit operation. Signed-off-by: "Theodore Ts'o" Cc: Allison Henderson Cc: Jan Kara --- fs/ext4/inode.c | 23 ++++++++--------------- 1 file changed, 8 insertions(+), 15 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d1b1ef71e5b7..f86b149fb8b1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1471,13 +1471,13 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) for (i = 0; i < map.m_len; i++) unmap_underlying_metadata(bdev, map.m_pblk + i); - } - if (ext4_should_order_data(mpd->inode)) { - err = ext4_jbd2_file_inode(handle, mpd->inode); - if (err) - /* This only happens if the journal is aborted */ - return; + if (ext4_should_order_data(mpd->inode)) { + err = ext4_jbd2_file_inode(handle, mpd->inode); + if (err) + /* Only if the journal is aborted */ + return; + } } /* @@ -3173,12 +3173,8 @@ int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, err = 0; if (ext4_should_journal_data(inode)) { err = ext4_handle_dirty_metadata(handle, inode, bh); - } else { - if (ext4_should_order_data(inode) && - EXT4_I(inode)->jinode) - err = ext4_jbd2_file_inode(handle, inode); + } else mark_buffer_dirty(bh); - } BUFFER_TRACE(bh, "Partial buffer zeroed"); next: @@ -3301,11 +3297,8 @@ int ext4_block_zero_page_range(handle_t *handle, err = 0; if (ext4_should_journal_data(inode)) { err = ext4_handle_dirty_metadata(handle, inode, bh); - } else { - if (ext4_should_order_data(inode) && EXT4_I(inode)->jinode) - err = ext4_jbd2_file_inode(handle, inode); + } else mark_buffer_dirty(bh); - } unlock: unlock_page(page); -- cgit v1.2.3 From 02fac1297eb3f471a27368271aadd285548297b0 Mon Sep 17 00:00:00 2001 From: Allison Henderson Date: Tue, 6 Sep 2011 21:53:01 -0400 Subject: ext4: fix partial page writes While running extended fsx tests to verify the preceeding patches, a similar bug was also found in the write operation When ever a write operation begins or ends in a hole, or extends EOF, the partial page contained in the hole or beyond EOF needs to be zeroed out. To correct this the new ext4_discard_partial_page_buffers_no_lock routine is used to zero out the partial page, but only for buffer heads that are already unmapped. Signed-off-by: Allison Henderson Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f86b149fb8b1..6ecc93979e48 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2255,6 +2255,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, pgoff_t index; struct inode *inode = mapping->host; handle_t *handle; + loff_t page_len; index = pos >> PAGE_CACHE_SHIFT; @@ -2301,6 +2302,13 @@ retry: */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode); + } else { + page_len = pos & (PAGE_CACHE_SIZE - 1); + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers_no_lock(handle, + inode, page, pos - page_len, page_len, + EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED); + } } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) @@ -2343,6 +2351,7 @@ static int ext4_da_write_end(struct file *file, loff_t new_i_size; unsigned long start, end; int write_mode = (int)(unsigned long)fsdata; + loff_t page_len; if (write_mode == FALL_BACK_TO_NONDELALLOC) { if (ext4_should_order_data(inode)) { @@ -2391,6 +2400,16 @@ static int ext4_da_write_end(struct file *file, } ret2 = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + + page_len = PAGE_CACHE_SIZE - + ((pos + copied - 1) & (PAGE_CACHE_SIZE - 1)); + + if (page_len > 0) { + ret = ext4_discard_partial_page_buffers_no_lock(handle, + inode, page, pos + copied - 1, page_len, + EXT4_DISCARD_PARTIAL_PG_ZERO_UNMAPPED); + } + copied = ret2; if (ret2 < 0) ret = ret2; -- cgit v1.2.3 From bab08ab9646288f1b0b72a7aaeecdff94bd62c18 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:36:51 -0400 Subject: ext4: enforce bigalloc restrictions (e.g., no online resizing, etc.) At least initially if the bigalloc feature is enabled, we will not support non-extent mapped inodes, online resizing, online defrag, or the FITRIM ioctl. This simplifies the initial implementation. Signed-off-by: "Theodore Ts'o" --- fs/ext4/indirect.c | 7 +++++++ fs/ext4/inode.c | 5 +++++ fs/ext4/ioctl.c | 33 +++++++++++++++++++++++++++++---- fs/ext4/super.c | 7 +++++++ 4 files changed, 48 insertions(+), 4 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index ea704dff8669..3cfc73fbca8e 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -699,6 +699,13 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, /* * Okay, we need to do block allocation. */ + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + EXT4_ERROR_INODE(inode, "Can't allocate blocks for " + "non-extent mapped inodes with bigalloc"); + return -ENOSPC; + } + goal = ext4_find_goal(inode, map->m_lblk, partial); /* the number of blocks need to allocate for [d,t]indirect blocks */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6ecc93979e48..904a9a623dab 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3358,6 +3358,11 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) return -ENOTSUPP; } + if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1) { + /* TODO: Add support for bigalloc file systems */ + return -ENOTSUPP; + } + return ext4_ext_punch_hole(file, offset, length); } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index f18bfe37aff8..2046d699b4a7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -21,6 +21,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = filp->f_dentry->d_inode; + struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); unsigned int flags; @@ -183,7 +184,6 @@ setversion_out: * Returns 1 if it slept, else zero. */ { - struct super_block *sb = inode->i_sb; DECLARE_WAITQUEUE(wait, current); int ret = 0; @@ -199,7 +199,6 @@ setversion_out: #endif case EXT4_IOC_GROUP_EXTEND: { ext4_fsblk_t n_blocks_count; - struct super_block *sb = inode->i_sb; int err, err2=0; err = ext4_resize_begin(sb); @@ -209,6 +208,13 @@ setversion_out: if (get_user(n_blocks_count, (__u32 __user *)arg)) return -EFAULT; + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + ext4_msg(sb, KERN_ERR, + "Online resizing not supported with bigalloc"); + return -EOPNOTSUPP; + } + err = mnt_want_write(filp->f_path.mnt); if (err) return err; @@ -250,6 +256,13 @@ setversion_out: goto mext_out; } + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + ext4_msg(sb, KERN_ERR, + "Online defrag not supported with bigalloc"); + return -EOPNOTSUPP; + } + err = mnt_want_write(filp->f_path.mnt); if (err) goto mext_out; @@ -270,7 +283,6 @@ mext_out: case EXT4_IOC_GROUP_ADD: { struct ext4_new_group_data input; - struct super_block *sb = inode->i_sb; int err, err2=0; err = ext4_resize_begin(sb); @@ -281,6 +293,13 @@ mext_out: sizeof(input))) return -EFAULT; + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + ext4_msg(sb, KERN_ERR, + "Online resizing not supported with bigalloc"); + return -EOPNOTSUPP; + } + err = mnt_want_write(filp->f_path.mnt); if (err) return err; @@ -337,7 +356,6 @@ mext_out: case FITRIM: { - struct super_block *sb = inode->i_sb; struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret = 0; @@ -348,6 +366,13 @@ mext_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { + ext4_msg(sb, KERN_ERR, + "FITRIM not supported with bigalloc"); + return -EOPNOTSUPP; + } + if (copy_from_user(&range, (struct fstrim_range *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 823e7d9deee2..25a4bfe3f39f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2701,6 +2701,13 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } } + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC) && + !EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) { + ext4_msg(sb, KERN_ERR, + "Can't support bigalloc feature without " + "extents feature\n"); + return 0; + } return 1; } -- cgit v1.2.3 From 5704265188ffe4290ed73b3cb685206c3ed8209d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 18:56:51 -0400 Subject: ext4: convert s_{dirty,free}blocks_counter to s_{dirty,free}clusters_counter Convert the percpu counters s_dirtyblocks_counter and s_freeblocks_counter in struct ext4_super_info to be s_dirtyclusters_counter and s_freeclusters_counter. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 10 +++++----- fs/ext4/ext4.h | 5 +++-- fs/ext4/ialloc.c | 3 ++- fs/ext4/inode.c | 18 ++++++++++-------- fs/ext4/mballoc.c | 12 +++++++----- fs/ext4/resize.c | 4 ++-- fs/ext4/super.c | 29 +++++++++++++++-------------- 7 files changed, 44 insertions(+), 37 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 89abf1f7b253..9080a857cda9 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -414,16 +414,16 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks, unsigned int flags) { s64 free_blocks, dirty_blocks, root_blocks; - struct percpu_counter *fbc = &sbi->s_freeblocks_counter; - struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter; + struct percpu_counter *fcc = &sbi->s_freeclusters_counter; + struct percpu_counter *dbc = &sbi->s_dirtyclusters_counter; - free_blocks = percpu_counter_read_positive(fbc); + free_blocks = percpu_counter_read_positive(fcc); dirty_blocks = percpu_counter_read_positive(dbc); root_blocks = ext4_r_blocks_count(sbi->s_es); if (free_blocks - (nblocks + root_blocks + dirty_blocks) < EXT4_FREEBLOCKS_WATERMARK) { - free_blocks = percpu_counter_sum_positive(fbc); + free_blocks = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc)); dirty_blocks = percpu_counter_sum_positive(dbc); } /* Check whether we have space after @@ -449,7 +449,7 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks, unsigned int flags) { if (ext4_has_free_blocks(sbi, nblocks, flags)) { - percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks); + percpu_counter_add(&sbi->s_dirtyclusters_counter, nblocks); return 0; } else return -ENOSPC; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 030bfc1cb59d..c7588366471c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -855,6 +855,7 @@ struct ext4_inode_info { ext4_group_t i_last_alloc_group; /* allocation reservation info for delalloc */ + /* In case of bigalloc, these refer to clusters rather than blocks */ unsigned int i_reserved_data_blocks; unsigned int i_reserved_meta_blocks; unsigned int i_allocated_meta_blocks; @@ -1144,10 +1145,10 @@ struct ext4_sb_info { u32 s_hash_seed[4]; int s_def_hash_version; int s_hash_unsigned; /* 3 if hash should be signed, 0 if not */ - struct percpu_counter s_freeblocks_counter; + struct percpu_counter s_freeclusters_counter; struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; - struct percpu_counter s_dirtyblocks_counter; + struct percpu_counter s_dirtyclusters_counter; struct blockgroup_lock *s_blockgroup_lock; struct proc_dir_entry *s_proc; struct kobject s_kobj; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b7a8130d0af4..58115bad163f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -490,7 +490,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent, freei = percpu_counter_read_positive(&sbi->s_freeinodes_counter); avefreei = freei / ngroups; - freeb = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + freeb = EXT4_C2B(sbi, + percpu_counter_read_positive(&sbi->s_freeclusters_counter)); avefreeb = freeb; do_div(avefreeb, ngroups); ndirs = percpu_counter_read_positive(&sbi->s_dirs_counter); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 904a9a623dab..40f51aae42fe 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -281,7 +281,7 @@ void ext4_da_update_reserve_space(struct inode *inode, /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; ei->i_reserved_meta_blocks -= ei->i_allocated_meta_blocks; - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, used + ei->i_allocated_meta_blocks); ei->i_allocated_meta_blocks = 0; @@ -291,7 +291,7 @@ void ext4_da_update_reserve_space(struct inode *inode, * only when we have written all of the delayed * allocation blocks. */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); ei->i_reserved_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; @@ -1119,14 +1119,14 @@ static void ext4_da_release_space(struct inode *inode, int to_free) * only when we have written all of the delayed * allocation blocks. */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); ei->i_reserved_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; } /* update fs dirty data blocks counter */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, to_free); + percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); @@ -1349,9 +1349,10 @@ static void ext4_print_free_blocks(struct inode *inode) ext4_count_free_blocks(inode->i_sb)); printk(KERN_CRIT "Free/Dirty block details\n"); printk(KERN_CRIT "free_blocks=%lld\n", - (long long) percpu_counter_sum(&sbi->s_freeblocks_counter)); + (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + percpu_counter_sum(&sbi->s_freeclusters_counter))); printk(KERN_CRIT "dirty_blocks=%lld\n", - (long long) percpu_counter_sum(&sbi->s_dirtyblocks_counter)); + (long long) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); printk(KERN_CRIT "Block reservation details\n"); printk(KERN_CRIT "i_reserved_data_blocks=%u\n", EXT4_I(inode)->i_reserved_data_blocks); @@ -2226,8 +2227,9 @@ static int ext4_nonda_switch(struct super_block *sb) * Delalloc need an accurate free block accounting. So switch * to non delalloc when we are near to error range. */ - free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); - dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter); + free_blocks = EXT4_C2B(sbi, + percpu_counter_read_positive(&sbi->s_freeclusters_counter)); + dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); if (2 * free_blocks < 3 * dirty_blocks || free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) { /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 57ce6960e940..4a38b65bd564 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2834,13 +2834,14 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); - percpu_counter_sub(&sbi->s_freeblocks_counter, ac->ac_b_ex.fe_len); + percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); /* * Now reduce the dirty block count also. Should not go negative */ if (!(ac->ac_flags & EXT4_MB_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, reserv_clstrs); + percpu_counter_sub(&sbi->s_dirtyclusters_counter, + reserv_clstrs); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, @@ -4384,7 +4385,7 @@ out: if (!ext4_test_inode_state(ar->inode, EXT4_STATE_DELALLOC_RESERVED)) /* release all the reserved blocks if non delalloc */ - percpu_counter_sub(&sbi->s_dirtyblocks_counter, + percpu_counter_sub(&sbi->s_dirtyclusters_counter, reserv_clstrs); } @@ -4691,7 +4692,7 @@ do_more: ext4_free_blks_set(sb, gdp, ret); gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); ext4_unlock_group(sb, block_group); - percpu_counter_add(&sbi->s_freeblocks_counter, count); + percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); @@ -4833,7 +4834,8 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_free_blks_set(sb, desc, blk_free_count); desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); ext4_unlock_group(sb, block_group); - percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed); + percpu_counter_add(&sbi->s_freeclusters_counter, + EXT4_B2C(sbi, blocks_freed)); if (sbi->s_log_groups_per_flex) { ext4_group_t flex_group = ext4_flex_group(sbi, block_group); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 707d3f16f7ce..a324a537f2dc 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -937,8 +937,8 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) input->reserved_blocks); /* Update the free space counts */ - percpu_counter_add(&sbi->s_freeblocks_counter, - input->free_blocks_count); + percpu_counter_add(&sbi->s_freeclusters_counter, + EXT4_B2C(sbi, input->free_blocks_count)); percpu_counter_add(&sbi->s_freeinodes_counter, EXT4_INODES_PER_GROUP(sb)); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 25a4bfe3f39f..f81e7e791655 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -837,10 +837,10 @@ static void ext4_put_super(struct super_block *sb) brelse(sbi->s_group_desc[i]); ext4_kvfree(sbi->s_group_desc); ext4_kvfree(sbi->s_flex_groups); - percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); - percpu_counter_destroy(&sbi->s_dirtyblocks_counter); + percpu_counter_destroy(&sbi->s_dirtyclusters_counter); brelse(sbi->s_sbh); #ifdef CONFIG_QUOTA for (i = 0; i < MAXQUOTAS; i++) @@ -2473,7 +2473,7 @@ static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a, char *buf) { return snprintf(buf, PAGE_SIZE, "%llu\n", - (s64) percpu_counter_sum(&sbi->s_dirtyblocks_counter)); + (s64) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); } static ssize_t session_write_kbytes_show(struct ext4_attr *a, @@ -3575,7 +3575,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_err_report.function = print_daily_error_info; sbi->s_err_report.data = (unsigned long) sb; - err = percpu_counter_init(&sbi->s_freeblocks_counter, + err = percpu_counter_init(&sbi->s_freeclusters_counter, ext4_count_free_blocks(sb)); if (!err) { err = percpu_counter_init(&sbi->s_freeinodes_counter, @@ -3586,7 +3586,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ext4_count_dirs(sb)); } if (!err) { - err = percpu_counter_init(&sbi->s_dirtyblocks_counter, 0); + err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0); } if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); @@ -3701,13 +3701,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * The journal may have updated the bg summary counts, so we * need to update the global counters. */ - percpu_counter_set(&sbi->s_freeblocks_counter, + percpu_counter_set(&sbi->s_freeclusters_counter, ext4_count_free_blocks(sb)); percpu_counter_set(&sbi->s_freeinodes_counter, ext4_count_free_inodes(sb)); percpu_counter_set(&sbi->s_dirs_counter, ext4_count_dirs(sb)); - percpu_counter_set(&sbi->s_dirtyblocks_counter, 0); + percpu_counter_set(&sbi->s_dirtyclusters_counter, 0); no_journal: /* @@ -3847,10 +3847,10 @@ failed_mount3: del_timer(&sbi->s_err_report); if (sbi->s_flex_groups) ext4_kvfree(sbi->s_flex_groups); - percpu_counter_destroy(&sbi->s_freeblocks_counter); + percpu_counter_destroy(&sbi->s_freeclusters_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); - percpu_counter_destroy(&sbi->s_dirtyblocks_counter); + percpu_counter_destroy(&sbi->s_dirtyclusters_counter); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: @@ -4173,8 +4173,9 @@ static int ext4_commit_super(struct super_block *sb, int sync) else es->s_kbytes_written = cpu_to_le64(EXT4_SB(sb)->s_kbytes_written); - ext4_free_blocks_count_set(es, percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeblocks_counter)); + ext4_free_blocks_count_set(es, + EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( + &EXT4_SB(sb)->s_freeclusters_counter))); es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( &EXT4_SB(sb)->s_freeinodes_counter)); @@ -4629,10 +4630,10 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_type = EXT4_SUPER_MAGIC; buf->f_bsize = sb->s_blocksize; buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last; - bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) - - percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter); + bfree = percpu_counter_sum_positive(&sbi->s_freeclusters_counter) - + percpu_counter_sum_positive(&sbi->s_dirtyclusters_counter); /* prevent underflow in case that few free space is available */ - buf->f_bfree = max_t(s64, bfree, 0); + buf->f_bfree = EXT4_C2B(sbi, max_t(s64, bfree, 0)); buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es); if (buf->f_bfree < ext4_r_blocks_count(es)) buf->f_bavail = 0; -- cgit v1.2.3 From 7b415bf60f6afb0499fd3dc0ee33444f54e28567 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 9 Sep 2011 19:04:51 -0400 Subject: ext4: Fix bigalloc quota accounting and i_blocks value With bigalloc changes, the i_blocks value was not correctly set (it was still set to number of blocks being used, but in case of bigalloc, we want i_blocks to represent the number of clusters being used). Since the quota subsystem sets the i_blocks value, this patch fixes the quota accounting and makes sure that the i_blocks value is set correctly. Signed-off-by: Aditya Kali Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 5 +- fs/ext4/ext4.h | 16 ++- fs/ext4/ext4_extents.h | 2 + fs/ext4/extents.c | 306 ++++++++++++++++++++++++++++++++++++++++++++++++- fs/ext4/inode.c | 54 ++++++--- fs/ext4/mballoc.c | 5 +- fs/ext4/super.c | 3 +- 7 files changed, 366 insertions(+), 25 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 9080a857cda9..bf42b3219e3c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -485,7 +485,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries) * @handle: handle to this transaction * @inode: file inode * @goal: given target block(filesystem wide) - * @count: pointer to total number of blocks needed + * @count: pointer to total number of clusters needed * @errp: error code * * Return 1st allocated block number on success, *count stores total account @@ -517,7 +517,8 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, spin_lock(&EXT4_I(inode)->i_block_reservation_lock); EXT4_I(inode)->i_allocated_meta_blocks += ar.len; spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); - dquot_alloc_block_nofail(inode, ar.len); + dquot_alloc_block_nofail(inode, + EXT4_C2B(EXT4_SB(inode->i_sb), ar.len)); } return ret; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index d2584224c89a..a6307f7c9807 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -144,9 +144,17 @@ struct ext4_allocation_request { #define EXT4_MAP_UNWRITTEN (1 << BH_Unwritten) #define EXT4_MAP_BOUNDARY (1 << BH_Boundary) #define EXT4_MAP_UNINIT (1 << BH_Uninit) +/* Sometimes (in the bigalloc case, from ext4_da_get_block_prep) the caller of + * ext4_map_blocks wants to know whether or not the underlying cluster has + * already been accounted for. EXT4_MAP_FROM_CLUSTER conveys to the caller that + * the requested mapping was from previously mapped (or delayed allocated) + * cluster. We use BH_AllocFromCluster only for this flag. BH_AllocFromCluster + * should never appear on buffer_head's state flags. + */ +#define EXT4_MAP_FROM_CLUSTER (1 << BH_AllocFromCluster) #define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\ - EXT4_MAP_UNINIT) + EXT4_MAP_UNINIT | EXT4_MAP_FROM_CLUSTER) struct ext4_map_blocks { ext4_fsblk_t m_pblk; @@ -1884,6 +1892,7 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); +extern int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, @@ -2284,6 +2293,11 @@ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); enum ext4_state_bits { BH_Uninit /* blocks are allocated but uninitialized on disk */ = BH_JBDPrivateStart, + BH_AllocFromCluster, /* allocated blocks were part of already + * allocated cluster. Note that this flag will + * never, ever appear in a buffer_head's state + * flag. See EXT4_MAP_FROM_CLUSTER to see where + * this is used. */ }; BUFFER_FNS(Uninit, uninit) diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 095c36f3b612..a52db3a69a30 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -290,5 +290,7 @@ extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t, struct ext4_ext_path *); extern void ext4_ext_drop_refs(struct ext4_ext_path *); extern int ext4_ext_check_inode(struct inode *inode); +extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk, + int search_hint_reverse); #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index cd4479c08031..c4e005864534 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2686,6 +2686,21 @@ again: } } + /* If we still have something in the partial cluster and we have removed + * even the first extent, then we should free the blocks in the partial + * cluster as well. */ + if (partial_cluster && path->p_hdr->eh_entries == 0) { + int flags = EXT4_FREE_BLOCKS_FORGET; + + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + flags |= EXT4_FREE_BLOCKS_METADATA; + + ext4_free_blocks(handle, inode, NULL, + EXT4_C2B(EXT4_SB(sb), partial_cluster), + EXT4_SB(sb)->s_cluster_ratio, flags); + partial_cluster = 0; + } + /* TODO: flexible tree reduction should be here */ if (path->p_hdr->eh_entries == 0) { /* @@ -3233,6 +3248,195 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode, return ext4_mark_inode_dirty(handle, inode); } +/** + * ext4_find_delalloc_range: find delayed allocated block in the given range. + * + * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns + * whether there are any buffers marked for delayed allocation. It returns '1' + * on the first delalloc'ed buffer head found. If no buffer head in the given + * range is marked for delalloc, it returns 0. + * lblk_start should always be <= lblk_end. + * search_hint_reverse is to indicate that searching in reverse from lblk_end to + * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed + * block sooner). This is useful when blocks are truncated sequentially from + * lblk_start towards lblk_end. + */ +static int ext4_find_delalloc_range(struct inode *inode, + ext4_lblk_t lblk_start, + ext4_lblk_t lblk_end, + int search_hint_reverse) +{ + struct address_space *mapping = inode->i_mapping; + struct buffer_head *head, *bh = NULL; + struct page *page; + ext4_lblk_t i, pg_lblk; + pgoff_t index; + + /* reverse search wont work if fs block size is less than page size */ + if (inode->i_blkbits < PAGE_CACHE_SHIFT) + search_hint_reverse = 0; + + if (search_hint_reverse) + i = lblk_end; + else + i = lblk_start; + + index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + + while ((i >= lblk_start) && (i <= lblk_end)) { + page = find_get_page(mapping, index); + if (!page || !PageDirty(page)) + goto nextpage; + + if (PageWriteback(page)) { + /* + * This might be a race with allocation and writeout. In + * this case we just assume that the rest of the range + * will eventually be written and there wont be any + * delalloc blocks left. + * TODO: the above assumption is troublesome, but might + * work better in practice. other option could be note + * somewhere that the cluster is getting written out and + * detect that here. + */ + page_cache_release(page); + return 0; + } + + if (!page_has_buffers(page)) + goto nextpage; + + head = page_buffers(page); + if (!head) + goto nextpage; + + bh = head; + pg_lblk = index << (PAGE_CACHE_SHIFT - + inode->i_blkbits); + do { + if (unlikely(pg_lblk < lblk_start)) { + /* + * This is possible when fs block size is less + * than page size and our cluster starts/ends in + * middle of the page. So we need to skip the + * initial few blocks till we reach the 'lblk' + */ + pg_lblk++; + continue; + } + + if (buffer_delay(bh)) { + page_cache_release(page); + return 1; + } + if (search_hint_reverse) + i--; + else + i++; + } while ((i >= lblk_start) && (i <= lblk_end) && + ((bh = bh->b_this_page) != head)); +nextpage: + if (page) + page_cache_release(page); + /* + * Move to next page. 'i' will be the first lblk in the next + * page. + */ + if (search_hint_reverse) + index--; + else + index++; + i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + } + + return 0; +} + +int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk, + int search_hint_reverse) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + ext4_lblk_t lblk_start, lblk_end; + lblk_start = lblk & (~(sbi->s_cluster_ratio - 1)); + lblk_end = lblk_start + sbi->s_cluster_ratio - 1; + + return ext4_find_delalloc_range(inode, lblk_start, lblk_end, + search_hint_reverse); +} + +/** + * Determines how many complete clusters (out of those specified by the 'map') + * are under delalloc and were reserved quota for. + * This function is called when we are writing out the blocks that were + * originally written with their allocation delayed, but then the space was + * allocated using fallocate() before the delayed allocation could be resolved. + * The cases to look for are: + * ('=' indicated delayed allocated blocks + * '-' indicates non-delayed allocated blocks) + * (a) partial clusters towards beginning and/or end outside of allocated range + * are not delalloc'ed. + * Ex: + * |----c---=|====c====|====c====|===-c----| + * |++++++ allocated ++++++| + * ==> 4 complete clusters in above example + * + * (b) partial cluster (outside of allocated range) towards either end is + * marked for delayed allocation. In this case, we will exclude that + * cluster. + * Ex: + * |----====c========|========c========| + * |++++++ allocated ++++++| + * ==> 1 complete clusters in above example + * + * Ex: + * |================c================| + * |++++++ allocated ++++++| + * ==> 0 complete clusters in above example + * + * The ext4_da_update_reserve_space will be called only if we + * determine here that there were some "entire" clusters that span + * this 'allocated' range. + * In the non-bigalloc case, this function will just end up returning num_blks + * without ever calling ext4_find_delalloc_range. + */ +static unsigned int +get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, + unsigned int num_blks) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + ext4_lblk_t alloc_cluster_start, alloc_cluster_end; + ext4_lblk_t lblk_from, lblk_to, c_offset; + unsigned int allocated_clusters = 0; + + alloc_cluster_start = EXT4_B2C(sbi, lblk_start); + alloc_cluster_end = EXT4_B2C(sbi, lblk_start + num_blks - 1); + + /* max possible clusters for this allocation */ + allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1; + + /* Check towards left side */ + c_offset = lblk_start & (sbi->s_cluster_ratio - 1); + if (c_offset) { + lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1)); + lblk_to = lblk_from + c_offset - 1; + + if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0)) + allocated_clusters--; + } + + /* Now check towards right. */ + c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1); + if (allocated_clusters && c_offset) { + lblk_from = lblk_start + num_blks; + lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1; + + if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0)) + allocated_clusters--; + } + + return allocated_clusters; +} + static int ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, @@ -3338,8 +3542,15 @@ out: * But fallocate would have already updated quota and block * count for this offset. So cancel these reservation */ - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) - ext4_da_update_reserve_space(inode, allocated, 0); + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { + unsigned int reserved_clusters; + reserved_clusters = get_reserved_cluster_alloc(inode, + map->m_lblk, map->m_len); + if (reserved_clusters) + ext4_da_update_reserve_space(inode, + reserved_clusters, + 0); + } map_out: map->m_flags |= EXT4_MAP_MAPPED; @@ -3484,6 +3695,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock = 0; int free_on_err = 0, err = 0, depth, ret; unsigned int allocated = 0, offset = 0; + unsigned int allocated_clusters = 0, reserved_clusters = 0; unsigned int punched_out = 0; unsigned int result = 0; struct ext4_allocation_request ar; @@ -3499,6 +3711,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, if (!(flags & EXT4_GET_BLOCKS_PUNCH_OUT_EXT) && ext4_ext_in_cache(inode, map->m_lblk, &newex)) { if (!newex.ee_start_lo && !newex.ee_start_hi) { + if ((sbi->s_cluster_ratio > 1) && + ext4_find_delalloc_cluster(inode, map->m_lblk, 0)) + map->m_flags |= EXT4_MAP_FROM_CLUSTER; + if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * block isn't allocated yet and @@ -3509,6 +3725,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* we should allocate requested block */ } else { /* block is already allocated */ + if (sbi->s_cluster_ratio > 1) + map->m_flags |= EXT4_MAP_FROM_CLUSTER; newblock = map->m_lblk - le32_to_cpu(newex.ee_block) + ext4_ext_pblock(&newex); @@ -3665,6 +3883,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, } } + if ((sbi->s_cluster_ratio > 1) && + ext4_find_delalloc_cluster(inode, map->m_lblk, 0)) + map->m_flags |= EXT4_MAP_FROM_CLUSTER; + /* * requested block isn't allocated yet; * we couldn't try to create block if create flag is zero @@ -3681,6 +3903,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* * Okay, we need to do block allocation. */ + map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; newex.ee_block = cpu_to_le32(map->m_lblk); cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1); @@ -3692,6 +3915,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, get_implied_cluster_alloc(sbi, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; + map->m_flags |= EXT4_MAP_FROM_CLUSTER; goto got_allocated_blocks; } @@ -3712,6 +3936,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, get_implied_cluster_alloc(sbi, map, ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; + map->m_flags |= EXT4_MAP_FROM_CLUSTER; goto got_allocated_blocks; } @@ -3765,6 +3990,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, ext_debug("allocate new block: goal %llu, found %llu/%u\n", ar.goal, newblock, allocated); free_on_err = 1; + allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; if (ar.len > allocated) ar.len = allocated; @@ -3822,8 +4048,80 @@ got_allocated_blocks: * Update reserved blocks/metadata blocks after successful * block allocation which had been deferred till now. */ - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) - ext4_da_update_reserve_space(inode, allocated, 1); + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { + /* + * Check how many clusters we had reserved this allocted range. + */ + reserved_clusters = get_reserved_cluster_alloc(inode, + map->m_lblk, allocated); + if (map->m_flags & EXT4_MAP_FROM_CLUSTER) { + if (reserved_clusters) { + /* + * We have clusters reserved for this range. + * But since we are not doing actual allocation + * and are simply using blocks from previously + * allocated cluster, we should release the + * reservation and not claim quota. + */ + ext4_da_update_reserve_space(inode, + reserved_clusters, 0); + } + } else { + BUG_ON(allocated_clusters < reserved_clusters); + /* We will claim quota for all newly allocated blocks.*/ + ext4_da_update_reserve_space(inode, allocated_clusters, + 1); + if (reserved_clusters < allocated_clusters) { + int reservation = allocated_clusters - + reserved_clusters; + /* + * It seems we claimed few clusters outside of + * the range of this allocation. We should give + * it back to the reservation pool. This can + * happen in the following case: + * + * * Suppose s_cluster_ratio is 4 (i.e., each + * cluster has 4 blocks. Thus, the clusters + * are [0-3],[4-7],[8-11]... + * * First comes delayed allocation write for + * logical blocks 10 & 11. Since there were no + * previous delayed allocated blocks in the + * range [8-11], we would reserve 1 cluster + * for this write. + * * Next comes write for logical blocks 3 to 8. + * In this case, we will reserve 2 clusters + * (for [0-3] and [4-7]; and not for [8-11] as + * that range has a delayed allocated blocks. + * Thus total reserved clusters now becomes 3. + * * Now, during the delayed allocation writeout + * time, we will first write blocks [3-8] and + * allocate 3 clusters for writing these + * blocks. Also, we would claim all these + * three clusters above. + * * Now when we come here to writeout the + * blocks [10-11], we would expect to claim + * the reservation of 1 cluster we had made + * (and we would claim it since there are no + * more delayed allocated blocks in the range + * [8-11]. But our reserved cluster count had + * already gone to 0. + * + * Thus, at the step 4 above when we determine + * that there are still some unwritten delayed + * allocated blocks outside of our current + * block range, we should increment the + * reserved clusters count so that when the + * remaining blocks finally gets written, we + * could claim them. + */ + while (reservation) { + ext4_da_reserve_space(inode, + map->m_lblk); + reservation--; + } + } + } + } /* * Cache the extent and update transaction to commit on fdatasync only diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 40f51aae42fe..d1c17e47c1c6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -300,14 +300,14 @@ void ext4_da_update_reserve_space(struct inode *inode, /* Update quota subsystem for data blocks */ if (quota_claim) - dquot_claim_block(inode, used); + dquot_claim_block(inode, EXT4_C2B(sbi, used)); else { /* * We did fallocate with an offset that is already delayed * allocated. So on delayed allocated writeback we should * not re-claim the quota for fallocated blocks. */ - dquot_release_reservation_block(inode, used); + dquot_release_reservation_block(inode, EXT4_C2B(sbi, used)); } /* @@ -1037,14 +1037,14 @@ static int ext4_journalled_write_end(struct file *file, } /* - * Reserve a single block located at lblock + * Reserve a single cluster located at lblock */ -static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) +int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) { int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long md_needed; + unsigned int md_needed; int ret; /* @@ -1054,7 +1054,8 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) */ repeat: spin_lock(&ei->i_block_reservation_lock); - md_needed = ext4_calc_metadata_amount(inode, lblock); + md_needed = EXT4_NUM_B2C(sbi, + ext4_calc_metadata_amount(inode, lblock)); trace_ext4_da_reserve_space(inode, md_needed); spin_unlock(&ei->i_block_reservation_lock); @@ -1063,7 +1064,7 @@ repeat: * us from metadata over-estimation, though we may go over by * a small amount in the end. Here we just reserve for data. */ - ret = dquot_reserve_block(inode, 1); + ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1)); if (ret) return ret; /* @@ -1071,7 +1072,7 @@ repeat: * we cannot afford to run out of free blocks. */ if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) { - dquot_release_reservation_block(inode, 1); + dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); goto repeat; @@ -1118,6 +1119,8 @@ static void ext4_da_release_space(struct inode *inode, int to_free) * We can release all of the reserved metadata blocks * only when we have written all of the delayed * allocation blocks. + * Note that in case of bigalloc, i_reserved_meta_blocks, + * i_reserved_data_blocks, etc. refer to number of clusters. */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, ei->i_reserved_meta_blocks); @@ -1130,7 +1133,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free) spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); - dquot_release_reservation_block(inode, to_free); + dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free)); } static void ext4_da_page_release_reservation(struct page *page, @@ -1139,6 +1142,9 @@ static void ext4_da_page_release_reservation(struct page *page, int to_release = 0; struct buffer_head *head, *bh; unsigned int curr_off = 0; + struct inode *inode = page->mapping->host; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int num_clusters; head = page_buffers(page); bh = head; @@ -1151,7 +1157,20 @@ static void ext4_da_page_release_reservation(struct page *page, } curr_off = next_off; } while ((bh = bh->b_this_page) != head); - ext4_da_release_space(page->mapping->host, to_release); + + /* If we have released all the blocks belonging to a cluster, then we + * need to release the reserved space for that cluster. */ + num_clusters = EXT4_NUM_B2C(sbi, to_release); + while (num_clusters > 0) { + ext4_fsblk_t lblk; + lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) + + ((num_clusters - 1) << sbi->s_cluster_bits); + if (sbi->s_cluster_ratio == 1 || + !ext4_find_delalloc_cluster(inode, lblk, 1)) + ext4_da_release_space(inode, 1); + + num_clusters--; + } } /* @@ -1352,7 +1371,8 @@ static void ext4_print_free_blocks(struct inode *inode) (long long) EXT4_C2B(EXT4_SB(inode->i_sb), percpu_counter_sum(&sbi->s_freeclusters_counter))); printk(KERN_CRIT "dirty_blocks=%lld\n", - (long long) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); + (long long) EXT4_C2B(EXT4_SB(inode->i_sb), + percpu_counter_sum(&sbi->s_dirtyclusters_counter))); printk(KERN_CRIT "Block reservation details\n"); printk(KERN_CRIT "i_reserved_data_blocks=%u\n", EXT4_I(inode)->i_reserved_data_blocks); @@ -1626,10 +1646,14 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, /* * XXX: __block_write_begin() unmaps passed block, is it OK? */ - ret = ext4_da_reserve_space(inode, iblock); - if (ret) - /* not enough space to reserve */ - return ret; + /* If the block was allocated from previously allocated cluster, + * then we dont need to reserve it again. */ + if (!(map.m_flags & EXT4_MAP_FROM_CLUSTER)) { + ret = ext4_da_reserve_space(inode, iblock); + if (ret) + /* not enough space to reserve */ + return ret; + } map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 63dd56703342..5e1215d38331 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4718,6 +4718,9 @@ do_more: freed += count; + if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) + dquot_free_block(inode, EXT4_C2B(sbi, count_clusters)); + /* We dirtied the bitmap block */ BUFFER_TRACE(bitmap_bh, "dirtied bitmap block"); err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh); @@ -4736,8 +4739,6 @@ do_more: } ext4_mark_super_dirty(sb); error_return: - if (freed && !(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE)) - dquot_free_block(inode, freed); brelse(bitmap_bh); ext4_std_error(sb, err); return; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6810957e0ac7..66b8cfa15636 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2473,7 +2473,8 @@ static ssize_t delayed_allocation_blocks_show(struct ext4_attr *a, char *buf) { return snprintf(buf, PAGE_SIZE, "%llu\n", - (s64) percpu_counter_sum(&sbi->s_dirtyclusters_counter)); + (s64) EXT4_C2B(sbi, + percpu_counter_sum(&sbi->s_dirtyclusters_counter))); } static ssize_t session_write_kbytes_show(struct ext4_attr *a, -- cgit v1.2.3 From 5dee54372c1ea15ab482b959634cda8c01b042bd Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:10:51 -0400 Subject: ext4: rename ext4_count_free_blocks() to ext4_count_free_clusters() This function really counts the free clusters reported in the block group descriptors, so rename it to reduce confusion. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 11 ++++++----- fs/ext4/ext4.h | 2 +- fs/ext4/inode.c | 6 +++--- fs/ext4/super.c | 7 ++++--- 4 files changed, 14 insertions(+), 12 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 84dc3d62b40c..4f303809e076 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -524,12 +524,12 @@ ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, } /** - * ext4_count_free_blocks() -- count filesystem free blocks + * ext4_count_free_clusters() -- count filesystem free clusters * @sb: superblock * - * Adds up the number of free blocks from each block group. + * Adds up the number of free clusters from each block group. */ -ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) +ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb) { ext4_fsblk_t desc_count; struct ext4_group_desc *gdp; @@ -562,8 +562,9 @@ ext4_fsblk_t ext4_count_free_blocks(struct super_block *sb) bitmap_count += x; } brelse(bitmap_bh); - printk(KERN_DEBUG "ext4_count_free_blocks: stored = %llu" - ", computed = %llu, %llu\n", ext4_free_blocks_count(es), + printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu" + ", computed = %llu, %llu\n", + EXT4_B2C(sbi, ext4_free_blocks_count(es)), desc_count, bitmap_count); return bitmap_count; #else diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index db279c362017..f6963cd7f709 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1775,7 +1775,7 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, int *errp); extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks, unsigned int flags); -extern ext4_fsblk_t ext4_count_free_blocks(struct super_block *); +extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *); extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, ext4_group_t block_group, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d1c17e47c1c6..f9198d7875cc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1365,7 +1365,8 @@ static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); printk(KERN_CRIT "Total free blocks count %lld\n", - ext4_count_free_blocks(inode->i_sb)); + EXT4_C2B(EXT4_SB(inode->i_sb), + ext4_count_free_clusters(inode->i_sb))); printk(KERN_CRIT "Free/Dirty block details\n"); printk(KERN_CRIT "free_blocks=%lld\n", (long long) EXT4_C2B(EXT4_SB(inode->i_sb), @@ -1451,8 +1452,7 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) if (err == -EAGAIN) goto submit_io; - if (err == -ENOSPC && - ext4_count_free_blocks(sb)) { + if (err == -ENOSPC && ext4_count_free_clusters(sb)) { mpd->retval = err; goto submit_io; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 30cf0e1bd89c..07f3de341452 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2153,7 +2153,8 @@ static int ext4_check_descriptors(struct super_block *sb, if (NULL != first_not_zeroed) *first_not_zeroed = grp; - ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb)); + ext4_free_blocks_count_set(sbi->s_es, + EXT4_C2B(sbi, ext4_count_free_clusters(sb))); sbi->s_es->s_free_inodes_count =cpu_to_le32(ext4_count_free_inodes(sb)); return 1; } @@ -3577,7 +3578,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_err_report.data = (unsigned long) sb; err = percpu_counter_init(&sbi->s_freeclusters_counter, - ext4_count_free_blocks(sb)); + ext4_count_free_clusters(sb)); if (!err) { err = percpu_counter_init(&sbi->s_freeinodes_counter, ext4_count_free_inodes(sb)); @@ -3703,7 +3704,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * need to update the global counters. */ percpu_counter_set(&sbi->s_freeclusters_counter, - ext4_count_free_blocks(sb)); + ext4_count_free_clusters(sb)); percpu_counter_set(&sbi->s_freeinodes_counter, ext4_count_free_inodes(sb)); percpu_counter_set(&sbi->s_dirs_counter, -- cgit v1.2.3 From e7d5f3156e6827970f75ab27ad7eb0155826eb0b Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:14:51 -0400 Subject: ext4: rename ext4_claim_free_blocks() to ext4_claim_free_clusters() This function really claims a number of free clusters, not blocks, so rename it so it's clearer what's going on. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 8 ++++---- fs/ext4/ext4.h | 4 ++-- fs/ext4/inode.c | 2 +- fs/ext4/mballoc.c | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 3d07c35c7089..af0c5357e35a 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -445,11 +445,11 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, return 0; } -int ext4_claim_free_blocks(struct ext4_sb_info *sbi, - s64 nblocks, unsigned int flags) +int ext4_claim_free_clusters(struct ext4_sb_info *sbi, + s64 nclusters, unsigned int flags) { - if (ext4_has_free_blocks(sbi, nblocks, flags)) { - percpu_counter_add(&sbi->s_dirtyclusters_counter, nblocks); + if (ext4_has_free_blocks(sbi, nclusters, flags)) { + percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters); return 0; } else return -ENOSPC; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1473c06e4c94..f97638634e34 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1773,8 +1773,8 @@ extern ext4_fsblk_t ext4_new_meta_blocks(handle_t *handle, struct inode *inode, unsigned int flags, unsigned long *count, int *errp); -extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, - s64 nblocks, unsigned int flags); +extern int ext4_claim_free_clusters(struct ext4_sb_info *sbi, + s64 nclusters, unsigned int flags); extern ext4_fsblk_t ext4_count_free_clusters(struct super_block *); extern void ext4_check_blocks_bitmap(struct super_block *); extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f9198d7875cc..557c34ffa05b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1071,7 +1071,7 @@ repeat: * We do still charge estimated metadata to the sb though; * we cannot afford to run out of free blocks. */ - if (ext4_claim_free_blocks(sbi, md_needed + 1, 0)) { + if (ext4_claim_free_clusters(sbi, md_needed + 1, 0)) { dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); if (ext4_should_retry_alloc(inode->i_sb, &retries)) { yield(); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 90a3ed7c565c..1c83161090f8 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4297,7 +4297,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, * and verify allocation doesn't exceed the quota limits. */ while (ar->len && - ext4_claim_free_blocks(sbi, ar->len, ar->flags)) { + ext4_claim_free_clusters(sbi, ar->len, ar->flags)) { /* let others to free the space */ yield(); -- cgit v1.2.3 From df55c99dc8ee4c3c886a5edc8a4aa6b131c95afc Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 9 Sep 2011 19:16:51 -0400 Subject: ext4: rename ext4_has_free_blocks() to ext4_has_free_clusters() Rename the function so it is more clear what is going on. Also rename the various variables so it's clearer what's happening. Also fix a missing blocks to cluster conversion when reading the number of reserved blocks for root. Signed-off-by: "Theodore Ts'o" --- fs/ext4/balloc.c | 43 ++++++++++++++++++++++--------------------- fs/ext4/ext4.h | 8 ++++---- fs/ext4/inode.c | 2 +- 3 files changed, 27 insertions(+), 26 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index af0c5357e35a..f6dba4505f1c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -403,42 +403,43 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) } /** - * ext4_has_free_blocks() + * ext4_has_free_clusters() * @sbi: in-core super block structure. - * @nblocks: number of needed blocks + * @nclusters: number of needed blocks + * @flags: flags from ext4_mb_new_blocks() * - * Check if filesystem has nblocks free & available for allocation. + * Check if filesystem has nclusters free & available for allocation. * On success return 1, return 0 on failure. */ -static int ext4_has_free_blocks(struct ext4_sb_info *sbi, - s64 nblocks, unsigned int flags) +static int ext4_has_free_clusters(struct ext4_sb_info *sbi, + s64 nclusters, unsigned int flags) { - s64 free_blocks, dirty_blocks, root_blocks; + s64 free_clusters, dirty_clusters, root_clusters; struct percpu_counter *fcc = &sbi->s_freeclusters_counter; - struct percpu_counter *dbc = &sbi->s_dirtyclusters_counter; + struct percpu_counter *dcc = &sbi->s_dirtyclusters_counter; - free_blocks = percpu_counter_read_positive(fcc); - dirty_blocks = percpu_counter_read_positive(dbc); - root_blocks = ext4_r_blocks_count(sbi->s_es); + free_clusters = percpu_counter_read_positive(fcc); + dirty_clusters = percpu_counter_read_positive(dcc); + root_clusters = EXT4_B2C(sbi, ext4_r_blocks_count(sbi->s_es)); - if (free_blocks - (nblocks + root_blocks + dirty_blocks) < - EXT4_FREEBLOCKS_WATERMARK) { - free_blocks = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc)); - dirty_blocks = percpu_counter_sum_positive(dbc); + if (free_clusters - (nclusters + root_clusters + dirty_clusters) < + EXT4_FREECLUSTERS_WATERMARK) { + free_clusters = EXT4_C2B(sbi, percpu_counter_sum_positive(fcc)); + dirty_clusters = percpu_counter_sum_positive(dcc); } - /* Check whether we have space after - * accounting for current dirty blocks & root reserved blocks. + /* Check whether we have space after accounting for current + * dirty clusters & root reserved clusters. */ - if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks)) + if (free_clusters >= ((root_clusters + nclusters) + dirty_clusters)) return 1; - /* Hm, nope. Are (enough) root reserved blocks available? */ + /* Hm, nope. Are (enough) root reserved clusters available? */ if (sbi->s_resuid == current_fsuid() || ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE) || (flags & EXT4_MB_USE_ROOT_BLOCKS)) { - if (free_blocks >= (nblocks + dirty_blocks)) + if (free_clusters >= (nclusters + dirty_clusters)) return 1; } @@ -448,7 +449,7 @@ static int ext4_has_free_blocks(struct ext4_sb_info *sbi, int ext4_claim_free_clusters(struct ext4_sb_info *sbi, s64 nclusters, unsigned int flags) { - if (ext4_has_free_blocks(sbi, nclusters, flags)) { + if (ext4_has_free_clusters(sbi, nclusters, flags)) { percpu_counter_add(&sbi->s_dirtyclusters_counter, nclusters); return 0; } else @@ -469,7 +470,7 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi, */ int ext4_should_retry_alloc(struct super_block *sb, int *retries) { - if (!ext4_has_free_blocks(EXT4_SB(sb), 1, 0) || + if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) || (*retries)++ > 3 || !EXT4_SB(sb)->s_journal) return 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index f97638634e34..21ea65d8bd46 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2103,13 +2103,13 @@ do { \ } while (0) #ifdef CONFIG_SMP -/* Each CPU can accumulate percpu_counter_batch blocks in their local - * counters. So we need to make sure we have free blocks more +/* Each CPU can accumulate percpu_counter_batch clusters in their local + * counters. So we need to make sure we have free clusters more * than percpu_counter_batch * nr_cpu_ids. Also add a window of 4 times. */ -#define EXT4_FREEBLOCKS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids)) +#define EXT4_FREECLUSTERS_WATERMARK (4 * (percpu_counter_batch * nr_cpu_ids)) #else -#define EXT4_FREEBLOCKS_WATERMARK 0 +#define EXT4_FREECLUSTERS_WATERMARK 0 #endif static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 557c34ffa05b..88dc63a01756 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2255,7 +2255,7 @@ static int ext4_nonda_switch(struct super_block *sb) percpu_counter_read_positive(&sbi->s_freeclusters_counter)); dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); if (2 * free_blocks < 3 * dirty_blocks || - free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) { + free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) { /* * free block count is less than 150% of dirty blocks * or free blocks is less than watermark -- cgit v1.2.3 From d8990240d8c911064447f8aa5a440f9345a6d692 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 9 Sep 2011 19:18:51 -0400 Subject: ext4: add some tracepoints in ext4/extents.c This patch adds some tracepoints in ext4/extents.c and updates a tracepoint in ext4/inode.c. Tested: Built and ran the kernel and verified that these tracepoints work. Also ran xfstests. Signed-off-by: Aditya Kali Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 + fs/ext4/extents.c | 44 ++++- fs/ext4/inode.c | 3 +- fs/ext4/migrate.c | 1 - fs/ext4/move_extent.c | 1 - include/trace/events/ext4.h | 398 +++++++++++++++++++++++++++++++++++++++++++- 6 files changed, 433 insertions(+), 16 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 21ea65d8bd46..751277a4890c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2339,4 +2339,6 @@ extern void ext4_resize_end(struct super_block *sb); #endif /* __KERNEL__ */ +#include "ext4_extents.h" + #endif /* _EXT4_H */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index c4e005864534..9b119308daea 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -42,7 +42,6 @@ #include #include #include "ext4_jbd2.h" -#include "ext4_extents.h" #include @@ -1969,6 +1968,7 @@ ext4_ext_put_in_cache(struct inode *inode, ext4_lblk_t block, struct ext4_ext_cache *cex; BUG_ON(len == 0); spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + trace_ext4_ext_put_in_cache(inode, block, len, start); cex = &EXT4_I(inode)->i_cached_extent; cex->ec_block = block; cex->ec_len = len; @@ -2070,6 +2070,7 @@ errout: sbi->extent_cache_misses++; else sbi->extent_cache_hits++; + trace_ext4_ext_in_cache(inode, block, ret); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); return ret; } @@ -2137,6 +2138,8 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, if (err) return err; ext_debug("index is empty, remove it, free block %llu\n", leaf); + trace_ext4_ext_rm_idx(inode, leaf); + ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); return err; @@ -2222,6 +2225,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, */ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; + trace_ext4_remove_blocks(inode, ex, from, to, *partial_cluster); /* * If we have a partial cluster, and it's different from the * cluster of the last block, we need to explicitly free the @@ -2336,6 +2340,8 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); + trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster); + while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { @@ -2591,6 +2597,8 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start) again: ext4_ext_invalidate_cache(inode); + trace_ext4_ext_remove_space(inode, start, depth); + /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. @@ -2686,6 +2694,9 @@ again: } } + trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster, + path->p_hdr->eh_entries); + /* If we still have something in the partial cluster and we have removed * even the first extent, then we should free the blocks in the partial * cluster as well. */ @@ -3300,6 +3311,10 @@ static int ext4_find_delalloc_range(struct inode *inode, * detect that here. */ page_cache_release(page); + trace_ext4_find_delalloc_range(inode, + lblk_start, lblk_end, + search_hint_reverse, + 0, i); return 0; } @@ -3327,6 +3342,10 @@ static int ext4_find_delalloc_range(struct inode *inode, if (buffer_delay(bh)) { page_cache_release(page); + trace_ext4_find_delalloc_range(inode, + lblk_start, lblk_end, + search_hint_reverse, + 1, i); return 1; } if (search_hint_reverse) @@ -3349,6 +3368,8 @@ nextpage: i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); } + trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end, + search_hint_reverse, 0, 0); return 0; } @@ -3414,6 +3435,8 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, /* max possible clusters for this allocation */ allocated_clusters = alloc_cluster_end - alloc_cluster_start + 1; + trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks); + /* Check towards left side */ c_offset = lblk_start & (sbi->s_cluster_ratio - 1); if (c_offset) { @@ -3453,6 +3476,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, flags, allocated); ext4_ext_show_leaf(inode, path); + trace_ext4_ext_handle_uninitialized_extents(inode, map, allocated, + newblock); + /* get_block() before submit the IO, split the extent */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { ret = ext4_split_unwritten_extents(handle, inode, map, @@ -3572,7 +3598,7 @@ out2: * get_implied_cluster_alloc - check to see if the requested * allocation (in the map structure) overlaps with a cluster already * allocated in an extent. - * @sbi The ext4-specific superblock structure + * @sb The filesystem superblock structure * @map The requested lblk->pblk mapping * @ex The extent structure which might contain an implied * cluster allocation @@ -3609,11 +3635,12 @@ out2: * ext4_ext_map_blocks() will then allocate one or more new clusters * by calling ext4_mb_new_blocks(). */ -static int get_implied_cluster_alloc(struct ext4_sb_info *sbi, +static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_map_blocks *map, struct ext4_extent *ex, struct ext4_ext_path *path) { + struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start, rr_cluster_end; @@ -3662,8 +3689,12 @@ static int get_implied_cluster_alloc(struct ext4_sb_info *sbi, ext4_lblk_t next = ext4_ext_next_allocated_block(path); map->m_len = min(map->m_len, next - map->m_lblk); } + + trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1); return 1; } + + trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0); return 0; } @@ -3772,6 +3803,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we split out initialized portions during a write. */ ee_len = ext4_ext_get_actual_len(ex); + + trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len); + /* if found extent covers block, simply return it */ if (in_range(map->m_lblk, ee_block, ee_len)) { ext4_fsblk_t partial_cluster = 0; @@ -3912,7 +3946,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * by ext4_ext_find_extent() implies a cluster we can use. */ if (cluster_offset && ex && - get_implied_cluster_alloc(sbi, map, ex, path)) { + get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; map->m_flags |= EXT4_MAP_FROM_CLUSTER; @@ -3933,7 +3967,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, /* Check if the extent after searching to the right implies a * cluster we can use. */ if ((sbi->s_cluster_ratio > 1) && ex2 && - get_implied_cluster_alloc(sbi, map, ex2, path)) { + get_implied_cluster_alloc(inode->i_sb, map, ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; map->m_flags |= EXT4_MAP_FROM_CLUSTER; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 88dc63a01756..2dcd4fed96ec 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -42,7 +42,6 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" -#include "ext4_extents.h" #include "truncate.h" #include @@ -268,7 +267,7 @@ void ext4_da_update_reserve_space(struct inode *inode, struct ext4_inode_info *ei = EXT4_I(inode); spin_lock(&ei->i_block_reservation_lock); - trace_ext4_da_update_reserve_space(inode, used); + trace_ext4_da_update_reserve_space(inode, used, quota_claim); if (unlikely(used > ei->i_reserved_data_blocks)) { ext4_msg(inode->i_sb, KERN_NOTICE, "%s: ino %lu, used %d " "with only %d reserved data blocks\n", diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index b57b98fb44d1..6f07a06f2437 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -15,7 +15,6 @@ #include #include #include "ext4_jbd2.h" -#include "ext4_extents.h" /* * The contiguous blocks details which can be diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index f57455a1b1b2..c5826c623e7a 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -17,7 +17,6 @@ #include #include #include "ext4_jbd2.h" -#include "ext4_extents.h" #include "ext4.h" /** diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index b50a54736242..c9a341e385a3 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -12,6 +12,8 @@ struct ext4_allocation_request; struct ext4_prealloc_space; struct ext4_inode_info; struct mpage_da_data; +struct ext4_map_blocks; +struct ext4_extent; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) @@ -1032,9 +1034,9 @@ TRACE_EVENT(ext4_forget, ); TRACE_EVENT(ext4_da_update_reserve_space, - TP_PROTO(struct inode *inode, int used_blocks), + TP_PROTO(struct inode *inode, int used_blocks, int quota_claim), - TP_ARGS(inode, used_blocks), + TP_ARGS(inode, used_blocks, quota_claim), TP_STRUCT__entry( __field( dev_t, dev ) @@ -1045,6 +1047,7 @@ TRACE_EVENT(ext4_da_update_reserve_space, __field( int, reserved_data_blocks ) __field( int, reserved_meta_blocks ) __field( int, allocated_meta_blocks ) + __field( int, quota_claim ) ), TP_fast_assign( @@ -1053,19 +1056,24 @@ TRACE_EVENT(ext4_da_update_reserve_space, __entry->mode = inode->i_mode; __entry->i_blocks = inode->i_blocks; __entry->used_blocks = used_blocks; - __entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks; - __entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks; - __entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks; + __entry->reserved_data_blocks = + EXT4_I(inode)->i_reserved_data_blocks; + __entry->reserved_meta_blocks = + EXT4_I(inode)->i_reserved_meta_blocks; + __entry->allocated_meta_blocks = + EXT4_I(inode)->i_allocated_meta_blocks; + __entry->quota_claim = quota_claim; ), TP_printk("dev %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d " "reserved_data_blocks %d reserved_meta_blocks %d " - "allocated_meta_blocks %d", + "allocated_meta_blocks %d quota_claim %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->i_blocks, __entry->used_blocks, __entry->reserved_data_blocks, - __entry->reserved_meta_blocks, __entry->allocated_meta_blocks) + __entry->reserved_meta_blocks, __entry->allocated_meta_blocks, + __entry->quota_claim) ); TRACE_EVENT(ext4_da_reserve_space, @@ -1589,6 +1597,382 @@ DEFINE_EVENT(ext4__trim, ext4_trim_all_free, TP_ARGS(sb, group, start, len) ); +TRACE_EVENT(ext4_ext_handle_uninitialized_extents, + TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, + unsigned int allocated, ext4_fsblk_t newblock), + + TP_ARGS(inode, map, allocated, newblock), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned int, len ) + __field( int, flags ) + __field( unsigned int, allocated ) + __field( ext4_fsblk_t, newblk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = map->m_lblk; + __entry->pblk = map->m_pblk; + __entry->len = map->m_len; + __entry->flags = map->m_flags; + __entry->allocated = allocated; + __entry->newblk = newblock; + ), + + TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %d" + "allocated %d newblock %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, (unsigned long long) __entry->pblk, + __entry->len, __entry->flags, + (unsigned int) __entry->allocated, + (unsigned long long) __entry->newblk) +); + +TRACE_EVENT(ext4_get_implied_cluster_alloc_exit, + TP_PROTO(struct super_block *sb, struct ext4_map_blocks *map, int ret), + + TP_ARGS(sb, map, ret), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned int, len ) + __field( unsigned int, flags ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->lblk = map->m_lblk; + __entry->pblk = map->m_pblk; + __entry->len = map->m_len; + __entry->flags = map->m_flags; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %u ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->lblk, (unsigned long long) __entry->pblk, + __entry->len, __entry->flags, __entry->ret) +); + +TRACE_EVENT(ext4_ext_put_in_cache, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len, + ext4_fsblk_t start), + + TP_ARGS(inode, lblk, len, start), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( unsigned int, len ) + __field( ext4_fsblk_t, start ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->len = len; + __entry->start = start; + ), + + TP_printk("dev %d,%d ino %lu lblk %u len %u start %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + __entry->len, + (unsigned long long) __entry->start) +); + +TRACE_EVENT(ext4_ext_in_cache, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, int ret), + + TP_ARGS(inode, lblk, ret), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->ret = ret; + ), + + TP_printk("dev %d,%d ino %lu lblk %u ret %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + __entry->ret) + +); + +TRACE_EVENT(ext4_find_delalloc_range, + TP_PROTO(struct inode *inode, ext4_lblk_t from, ext4_lblk_t to, + int reverse, int found, ext4_lblk_t found_blk), + + TP_ARGS(inode, from, to, reverse, found, found_blk), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, from ) + __field( ext4_lblk_t, to ) + __field( int, reverse ) + __field( int, found ) + __field( ext4_lblk_t, found_blk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->from = from; + __entry->to = to; + __entry->reverse = reverse; + __entry->found = found; + __entry->found_blk = found_blk; + ), + + TP_printk("dev %d,%d ino %lu from %u to %u reverse %d found %d " + "(blk = %u)", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->from, (unsigned) __entry->to, + __entry->reverse, __entry->found, + (unsigned) __entry->found_blk) +); + +TRACE_EVENT(ext4_get_reserved_cluster_alloc, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, unsigned int len), + + TP_ARGS(inode, lblk, len), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( unsigned int, len ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->len = len; + ), + + TP_printk("dev %d,%d ino %lu lblk %u len %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + __entry->len) +); + +TRACE_EVENT(ext4_ext_show_extent, + TP_PROTO(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, + unsigned short len), + + TP_ARGS(inode, lblk, pblk, len), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, lblk ) + __field( ext4_fsblk_t, pblk ) + __field( unsigned short, len ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->lblk = lblk; + __entry->pblk = pblk; + __entry->len = len; + ), + + TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->lblk, + (unsigned long long) __entry->pblk, + (unsigned short) __entry->len) +); + +TRACE_EVENT(ext4_remove_blocks, + TP_PROTO(struct inode *inode, struct ext4_extent *ex, + ext4_lblk_t from, ext4_fsblk_t to, + ext4_fsblk_t partial_cluster), + + TP_ARGS(inode, ex, from, to, partial_cluster), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, ee_lblk ) + __field( ext4_fsblk_t, ee_pblk ) + __field( unsigned short, ee_len ) + __field( ext4_lblk_t, from ) + __field( ext4_lblk_t, to ) + __field( ext4_fsblk_t, partial ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->ee_lblk = cpu_to_le32(ex->ee_block); + __entry->ee_pblk = ext4_ext_pblock(ex); + __entry->ee_len = ext4_ext_get_actual_len(ex); + __entry->from = from; + __entry->to = to; + __entry->partial = partial_cluster; + ), + + TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]" + "from %u to %u partial_cluster %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->ee_lblk, + (unsigned long long) __entry->ee_pblk, + (unsigned short) __entry->ee_len, + (unsigned) __entry->from, + (unsigned) __entry->to, + (unsigned) __entry->partial) +); + +TRACE_EVENT(ext4_ext_rm_leaf, + TP_PROTO(struct inode *inode, ext4_lblk_t start, + struct ext4_extent *ex, ext4_fsblk_t partial_cluster), + + TP_ARGS(inode, start, ex, partial_cluster), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, start ) + __field( ext4_lblk_t, ee_lblk ) + __field( ext4_fsblk_t, ee_pblk ) + __field( short, ee_len ) + __field( ext4_fsblk_t, partial ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->start = start; + __entry->ee_lblk = le32_to_cpu(ex->ee_block); + __entry->ee_pblk = ext4_ext_pblock(ex); + __entry->ee_len = ext4_ext_get_actual_len(ex); + __entry->partial = partial_cluster; + ), + + TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]" + "partial_cluster %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->start, + (unsigned) __entry->ee_lblk, + (unsigned long long) __entry->ee_pblk, + (unsigned short) __entry->ee_len, + (unsigned) __entry->partial) +); + +TRACE_EVENT(ext4_ext_rm_idx, + TP_PROTO(struct inode *inode, ext4_fsblk_t pblk), + + TP_ARGS(inode, pblk), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_fsblk_t, pblk ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->pblk = pblk; + ), + + TP_printk("dev %d,%d ino %lu index_pblk %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned long long) __entry->pblk) +); + +TRACE_EVENT(ext4_ext_remove_space, + TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth), + + TP_ARGS(inode, start, depth), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, start ) + __field( int, depth ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->start = start; + __entry->depth = depth; + ), + + TP_printk("dev %d,%d ino %lu since %u depth %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->start, + __entry->depth) +); + +TRACE_EVENT(ext4_ext_remove_space_done, + TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth, + ext4_lblk_t partial, unsigned short eh_entries), + + TP_ARGS(inode, start, depth, partial, eh_entries), + + TP_STRUCT__entry( + __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ext4_lblk_t, start ) + __field( int, depth ) + __field( ext4_lblk_t, partial ) + __field( unsigned short, eh_entries ) + ), + + TP_fast_assign( + __entry->ino = inode->i_ino; + __entry->dev = inode->i_sb->s_dev; + __entry->start = start; + __entry->depth = depth; + __entry->partial = partial; + __entry->eh_entries = eh_entries; + ), + + TP_printk("dev %d,%d ino %lu since %u depth %d partial %u " + "remaining_entries %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, + (unsigned) __entry->start, + __entry->depth, + (unsigned) __entry->partial, + (unsigned short) __entry->eh_entries) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 5356f2615cd558c57a1f7d7528d1ad4de3640d96 Mon Sep 17 00:00:00 2001 From: Aditya Kali Date: Fri, 9 Sep 2011 19:20:51 -0400 Subject: ext4: attempt to fix race in bigalloc code path Currently, there exists a race between delayed allocated writes and the writeback when bigalloc feature is in use. The race was because we wanted to determine what blocks in a cluster are under delayed allocation and we were using buffer_delayed(bh) check for it. But, the writeback codepath clears this bit without any synchronization which resulted in a race and an ext4 warning similar to: EXT4-fs (ram1): ext4_da_update_reserve_space: ino 13, used 1 with only 0 reserved data blocks The race existed in two places. (1) between ext4_find_delalloc_range() and ext4_map_blocks() when called from writeback code path. (2) between ext4_find_delalloc_range() and ext4_da_get_block_prep() (where buffer_delayed(bh) is set. To fix (1), this patch introduces a new buffer_head state bit - BH_Da_Mapped. This bit is set under the protection of EXT4_I(inode)->i_data_sem when we have actually mapped the delayed allocated blocks during the writeout time. We can now reliably check for this bit inside ext4_find_delalloc_range() to determine whether the reservation for the blocks have already been claimed or not. To fix (2), it was necessary to set buffer_delay(bh) under the protection of i_data_sem. So, I extracted the very beginning of ext4_map_blocks into a new function - ext4_da_map_blocks() - and performed the required setting of bh_delay bit and the quota reservation under the protection of i_data_sem. These two fixes makes the checking of buffer_delay(bh) and buffer_da_mapped(bh) consistent, thus removing the race. Tested: I was able to reproduce the problem by running 'dd' and 'fsync' in parallel. Also, xfstests sometimes used to reproduce this race. After the fix both my test and xfstests were successful and no race (warning message) was observed. Google-Bug-Id: 4997027 Signed-off-by: Aditya Kali Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 5 +- fs/ext4/extents.c | 38 +++++--------- fs/ext4/inode.c | 146 +++++++++++++++++++++++++++++++++++++++++++----------- 3 files changed, 134 insertions(+), 55 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 751277a4890c..1bbd2caebe7f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1893,7 +1893,6 @@ extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); extern qsize_t *ext4_get_reserved_space(struct inode *inode); extern void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim); -extern int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock); /* indirect.c */ extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, @@ -2300,10 +2299,14 @@ enum ext4_state_bits { * never, ever appear in a buffer_head's state * flag. See EXT4_MAP_FROM_CLUSTER to see where * this is used. */ + BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This + * flag is set when ext4_map_blocks is called on a + * delayed allocated block to get its real mapping. */ }; BUFFER_FNS(Uninit, uninit) TAS_BUFFER_FNS(Uninit, uninit) +BUFFER_FNS(Da_Mapped, da_mapped) /* * Add new method to test wether block and inode bitmaps are properly diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 9b119308daea..ad39627c1fbc 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3296,28 +3296,9 @@ static int ext4_find_delalloc_range(struct inode *inode, while ((i >= lblk_start) && (i <= lblk_end)) { page = find_get_page(mapping, index); - if (!page || !PageDirty(page)) + if (!page) goto nextpage; - if (PageWriteback(page)) { - /* - * This might be a race with allocation and writeout. In - * this case we just assume that the rest of the range - * will eventually be written and there wont be any - * delalloc blocks left. - * TODO: the above assumption is troublesome, but might - * work better in practice. other option could be note - * somewhere that the cluster is getting written out and - * detect that here. - */ - page_cache_release(page); - trace_ext4_find_delalloc_range(inode, - lblk_start, lblk_end, - search_hint_reverse, - 0, i); - return 0; - } - if (!page_has_buffers(page)) goto nextpage; @@ -3340,7 +3321,11 @@ static int ext4_find_delalloc_range(struct inode *inode, continue; } - if (buffer_delay(bh)) { + /* Check if the buffer is delayed allocated and that it + * is not yet mapped. (when da-buffers are mapped during + * their writeout, their da_mapped bit is set.) + */ + if (buffer_delay(bh) && !buffer_da_mapped(bh)) { page_cache_release(page); trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end, @@ -4106,6 +4091,7 @@ got_allocated_blocks: ext4_da_update_reserve_space(inode, allocated_clusters, 1); if (reserved_clusters < allocated_clusters) { + struct ext4_inode_info *ei = EXT4_I(inode); int reservation = allocated_clusters - reserved_clusters; /* @@ -4148,11 +4134,11 @@ got_allocated_blocks: * remaining blocks finally gets written, we * could claim them. */ - while (reservation) { - ext4_da_reserve_space(inode, - map->m_lblk); - reservation--; - } + dquot_reserve_block(inode, + EXT4_C2B(sbi, reservation)); + spin_lock(&ei->i_block_reservation_lock); + ei->i_reserved_data_blocks += reservation; + spin_unlock(&ei->i_block_reservation_lock); } } } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2dcd4fed96ec..1380cd29c312 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -397,6 +397,49 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx, return num; } +/* + * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map. + */ +static void set_buffers_da_mapped(struct inode *inode, + struct ext4_map_blocks *map) +{ + struct address_space *mapping = inode->i_mapping; + struct pagevec pvec; + int i, nr_pages; + pgoff_t index, end; + + index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + end = (map->m_lblk + map->m_len - 1) >> + (PAGE_CACHE_SHIFT - inode->i_blkbits); + + pagevec_init(&pvec, 0); + while (index <= end) { + nr_pages = pagevec_lookup(&pvec, mapping, index, + min(end - index + 1, + (pgoff_t)PAGEVEC_SIZE)); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + struct buffer_head *bh, *head; + + if (unlikely(page->mapping != mapping) || + !PageDirty(page)) + break; + + if (page_has_buffers(page)) { + bh = head = page_buffers(page); + do { + set_buffer_da_mapped(bh); + bh = bh->b_this_page; + } while (bh != head); + } + index++; + } + pagevec_release(&pvec); + } +} + /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -516,9 +559,17 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) ext4_da_update_reserve_space(inode, retval, 1); } - if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) { ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED); + /* If we have successfully mapped the delayed allocated blocks, + * set the BH_Da_Mapped bit on them. Its important to do this + * under the protection of i_data_sem. + */ + if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) + set_buffers_da_mapped(inode, map); + } + up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { int ret = check_block_validity(inode, map); @@ -1038,7 +1089,7 @@ static int ext4_journalled_write_end(struct file *file, /* * Reserve a single cluster located at lblock */ -int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) +static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) { int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -1153,6 +1204,7 @@ static void ext4_da_page_release_reservation(struct page *page, if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; clear_buffer_delay(bh); + clear_buffer_da_mapped(bh); } curr_off = next_off; } while ((bh = bh->b_this_page) != head); @@ -1271,6 +1323,8 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, clear_buffer_delay(bh); bh->b_blocknr = pblock; } + if (buffer_da_mapped(bh)) + clear_buffer_da_mapped(bh); if (buffer_unwritten(bh) || buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); @@ -1603,6 +1657,66 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); } +/* + * This function is grabs code from the very beginning of + * ext4_map_blocks, but assumes that the caller is from delayed write + * time. This function looks up the requested blocks and sets the + * buffer delay bit under the protection of i_data_sem. + */ +static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, + struct ext4_map_blocks *map, + struct buffer_head *bh) +{ + int retval; + sector_t invalid_block = ~((sector_t) 0xffff); + + if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) + invalid_block = ~0; + + map->m_flags = 0; + ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u," + "logical block %lu\n", inode->i_ino, map->m_len, + (unsigned long) map->m_lblk); + /* + * Try to see if we can get the block without requesting a new + * file system block. + */ + down_read((&EXT4_I(inode)->i_data_sem)); + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + retval = ext4_ext_map_blocks(NULL, inode, map, 0); + else + retval = ext4_ind_map_blocks(NULL, inode, map, 0); + + if (retval == 0) { + /* + * XXX: __block_prepare_write() unmaps passed block, + * is it OK? + */ + /* If the block was allocated from previously allocated cluster, + * then we dont need to reserve it again. */ + if (!(map->m_flags & EXT4_MAP_FROM_CLUSTER)) { + retval = ext4_da_reserve_space(inode, iblock); + if (retval) + /* not enough space to reserve */ + goto out_unlock; + } + + /* Clear EXT4_MAP_FROM_CLUSTER flag since its purpose is served + * and it should not appear on the bh->b_state. + */ + map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; + + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); + } + +out_unlock: + up_read((&EXT4_I(inode)->i_data_sem)); + + return retval; +} + /* * This is a special get_blocks_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or @@ -1620,10 +1734,6 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, { struct ext4_map_blocks map; int ret = 0; - sector_t invalid_block = ~((sector_t) 0xffff); - - if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) - invalid_block = ~0; BUG_ON(create == 0); BUG_ON(bh->b_size != inode->i_sb->s_blocksize); @@ -1636,29 +1746,9 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) + ret = ext4_da_map_blocks(inode, iblock, &map, bh); + if (ret <= 0) return ret; - if (ret == 0) { - if (buffer_delay(bh)) - return 0; /* Not sure this could or should happen */ - /* - * XXX: __block_write_begin() unmaps passed block, is it OK? - */ - /* If the block was allocated from previously allocated cluster, - * then we dont need to reserve it again. */ - if (!(map.m_flags & EXT4_MAP_FROM_CLUSTER)) { - ret = ext4_da_reserve_space(inode, iblock); - if (ret) - /* not enough space to reserve */ - return ret; - } - - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); - return 0; - } map_bh(bh, inode->i_sb, map.m_pblk); bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; -- cgit v1.2.3 From df3ab17072c31fbd394614711772682f0a956a2c Mon Sep 17 00:00:00 2001 From: Tao Ma Date: Sat, 8 Oct 2011 15:53:49 -0400 Subject: ext4: fix the comment describing ext4_ext_search_right() The comment describing what ext4_ext_search_right() does is incorrect. We return 0 in *phys when *logical is the 'largest' allocated block, not smallest. Fix a few other typos while we're at it. Cc: "Theodore Ts'o" Signed-off-by: Tao Ma --- fs/ext4/extents.c | 4 ++-- fs/ext4/inode.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ad39627c1fbc..142e3443476f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1263,7 +1263,7 @@ static int ext4_ext_search_left(struct inode *inode, /* * search the closest allocated block to the right for *logical * and returns it at @logical + it's physical address at @phys - * if *logical is the smallest allocated block, the function + * if *logical is the largest allocated block, the function * returns 0 at @phys * return value contains 0 (success) or error code */ @@ -2168,7 +2168,7 @@ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, * need to account for leaf block credit * * bitmaps and block group descriptor blocks - * and other metadat blocks still need to be + * and other metadata blocks still need to be * accounted. */ /* 1 bitmap, 1 block group descriptor */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1380cd29c312..4863238c3754 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -458,7 +458,7 @@ static void set_buffers_da_mapped(struct inode *inode, * the buffer head is mapped. * * It returns 0 if plain look up failed (blocks have not been allocated), in - * that casem, buffer head is unmapped + * that case, buffer head is unmapped * * It returns the error in case of allocation failure. */ @@ -497,7 +497,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, * Returns if the blocks have already allocated * * Note that if blocks have been preallocated - * ext4_ext_get_block() returns th create = 0 + * ext4_ext_get_block() returns the create = 0 * with buffer head unmapped. */ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) -- cgit v1.2.3 From 1bce63d1a2a2c8929442b79acd4eab2e3db10a0b Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Tue, 18 Oct 2011 10:55:51 -0400 Subject: ext4: add block plug for .writepages Add block plug for ext4 .writepages. Though ext4 .writepages already handles request merge very well, block plug is still helpful to reduce block lock contention. Signed-off-by: Shaohua Li Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 4863238c3754..081bb25a9ad3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2160,6 +2160,7 @@ static int ext4_da_writepages(struct address_space *mapping, struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); pgoff_t done_index = 0; pgoff_t end; + struct blk_plug plug; trace_ext4_da_writepages(inode, wbc); @@ -2238,6 +2239,7 @@ retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); + blk_start_plug(&plug); while (!ret && wbc->nr_to_write > 0) { /* @@ -2302,6 +2304,7 @@ retry: */ break; } + blk_finish_plug(&plug); if (!io_done && !cycled) { cycled = 1; index = 0; -- cgit v1.2.3 From 09e0834fb0ce1ea2a63885177015bd5d7d2bc22d Mon Sep 17 00:00:00 2001 From: Akira Fujita Date: Thu, 20 Oct 2011 18:56:10 -0400 Subject: ext4: fix deadlock in ext4_ordered_write_end() If ext4_jbd2_file_inode() in ext4_ordered_write_end() fails for some reasons, this function returns to caller without unlocking the page. It leads to the deadlock, and the patch fixes this issue. Signed-off-by: Akira Fujita Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 081bb25a9ad3..ecb572591924 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -959,7 +959,11 @@ static int ext4_ordered_write_end(struct file *file, ext4_orphan_add(handle, inode); if (ret2 < 0) ret = ret2; + } else { + unlock_page(page); + page_cache_release(page); } + ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; -- cgit v1.2.3 From 8de49e674a1133ab8998914a6e933ceb4b5f4b07 Mon Sep 17 00:00:00 2001 From: Kazuya Mio Date: Thu, 20 Oct 2011 19:23:08 -0400 Subject: ext4: fix the deadlock in mpage_da_map_and_submit() If ext4_jbd2_file_inode() in mpage_da_map_and_submit() fails due to journal abort, this function returns to caller without unlocking the page. It leads to the deadlock, and the patch fixes this issue by calling mpage_da_submit_io(). Signed-off-by: Kazuya Mio Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ecb572591924..ff6aace0bb3c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1552,9 +1552,11 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd) if (ext4_should_order_data(mpd->inode)) { err = ext4_jbd2_file_inode(handle, mpd->inode); - if (err) + if (err) { /* Only if the journal is aborted */ - return; + mpd->retval = err; + goto submit_io; + } } } @@ -2294,11 +2296,12 @@ retry: ret = 0; } else if (ret == MPAGE_DA_EXTENT_TAIL) { /* - * got one extent now try with - * rest of the pages + * Got one extent now try with rest of the pages. + * If mpd.retval is set -EIO, journal is aborted. + * So we don't need to write any more. */ pages_written += mpd.pages_written; - ret = 0; + ret = mpd.retval; io_done = 1; } else if (wbc->nr_to_write) /* -- cgit v1.2.3 From a4e5d88b1b24827f4f6a3cba43228936a67d81ba Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Tue, 25 Oct 2011 08:15:12 -0400 Subject: ext4: update EOFBLOCKS flag on fallocate properly EOFBLOCK_FL should be updated if called w/o FALLOCATE_FL_KEEP_SIZE Currently it happens only if new extent was allocated. TESTCASE: fallocate test_file -n -l4096 fallocate test_file -l4096 Last fallocate cmd has updated size, but keept EOFBLOCK_FL set. And fsck will complain about that. Also remove ping pong in ext4_fallocate() in case of new extents, where ext4_ext_map_blocks() clear EOFBLOCKS bit, and later ext4_falloc_update_inode() restore it again. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 2 ++ fs/ext4/extents.c | 28 +++++++++++++++++----------- fs/ext4/inode.c | 6 ++++-- 3 files changed, 23 insertions(+), 13 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4546da4f26c4..3647ae0b21ab 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -539,6 +539,8 @@ struct ext4_new_group_data { #define EXT4_GET_BLOCKS_PUNCH_OUT_EXT 0x0020 /* Don't normalize allocation size (used for fallocate) */ #define EXT4_GET_BLOCKS_NO_NORMALIZE 0x0040 + /* Request will not result in inode size update (user for fallocate) */ +#define EXT4_GET_BLOCKS_KEEP_SIZE 0x0080 /* * Flags used by ext4_free_blocks diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index d0e3f333d3f0..8686eb756b38 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3432,14 +3432,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, /* buffered write, writepage time, convert*/ ret = ext4_ext_convert_to_initialized(handle, inode, map, path); - if (ret >= 0) { + if (ret >= 0) ext4_update_inode_fsync_trans(handle, inode, 1); - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, - map->m_len); - if (err < 0) - goto out2; - } - out: if (ret <= 0) { err = ret; @@ -3480,6 +3474,12 @@ out: map_out: map->m_flags |= EXT4_MAP_MAPPED; + if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) { + err = check_eofblocks_fl(handle, inode, map->m_lblk, path, + map->m_len); + if (err < 0) + goto out2; + } out1: if (allocated > map->m_len) allocated = map->m_len; @@ -3955,7 +3955,10 @@ got_allocated_blocks: map->m_flags |= EXT4_MAP_UNINIT; } - err = check_eofblocks_fl(handle, inode, map->m_lblk, path, ar.len); + err = 0; + if ((flags & EXT4_GET_BLOCKS_KEEP_SIZE) == 0) + err = check_eofblocks_fl(handle, inode, map->m_lblk, + path, ar.len); if (!err) err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); @@ -4214,6 +4217,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) int ret = 0; int ret2 = 0; int retries = 0; + int flags; struct ext4_map_blocks map; unsigned int credits, blkbits = inode->i_blkbits; @@ -4250,6 +4254,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) trace_ext4_fallocate_exit(inode, offset, max_blocks, ret); return ret; } + flags = EXT4_GET_BLOCKS_CREATE_UNINIT_EXT | + EXT4_GET_BLOCKS_NO_NORMALIZE; + if (mode & FALLOC_FL_KEEP_SIZE) + flags |= EXT4_GET_BLOCKS_KEEP_SIZE; retry: while (ret >= 0 && ret < max_blocks) { map.m_lblk = map.m_lblk + ret; @@ -4259,9 +4267,7 @@ retry: ret = PTR_ERR(handle); break; } - ret = ext4_map_blocks(handle, inode, &map, - EXT4_GET_BLOCKS_CREATE_UNINIT_EXT | - EXT4_GET_BLOCKS_NO_NORMALIZE); + ret = ext4_map_blocks(handle, inode, &map, flags); if (ret <= 0) { #ifdef EXT4FS_DEBUG WARN_ON(ret <= 0); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index ff6aace0bb3c..87ec615f0fd6 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -477,9 +477,11 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, */ down_read((&EXT4_I(inode)->i_data_sem)); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { - retval = ext4_ext_map_blocks(handle, inode, map, 0); + retval = ext4_ext_map_blocks(handle, inode, map, flags & + EXT4_GET_BLOCKS_KEEP_SIZE); } else { - retval = ext4_ind_map_blocks(handle, inode, map, 0); + retval = ext4_ind_map_blocks(handle, inode, map, flags & + EXT4_GET_BLOCKS_KEEP_SIZE); } up_read((&EXT4_I(inode)->i_data_sem)); -- cgit v1.2.3 From fcbb5515825f1bb20b7a6f75ec48bee61416f879 Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Wed, 26 Oct 2011 05:00:19 -0400 Subject: ext4: let ext4_page_mkwrite stop started handle in failure The started journal handle should be stopped in failure case. Signed-off-by: Yongqiang Yang Signed-off-by: "Theodore Ts'o" Acked-by: Jan Kara Cc: stable@kernel.org --- fs/ext4/inode.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 87ec615f0fd6..e4b26faac5ff 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4791,6 +4791,7 @@ retry_alloc: PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) { unlock_page(page); ret = VM_FAULT_SIGBUS; + ext4_journal_stop(handle); goto out; } ext4_set_inode_state(inode, EXT4_STATE_JDATA); -- cgit v1.2.3 From 0e175a1835ffc979e55787774e58ec79e41957d7 Mon Sep 17 00:00:00 2001 From: Curt Wohlgemuth Date: Fri, 7 Oct 2011 21:54:10 -0600 Subject: writeback: Add a 'reason' to wb_writeback_work This creates a new 'reason' field in a wb_writeback_work structure, which unambiguously identifies who initiates writeback activity. A 'wb_reason' enumeration has been added to writeback.h, to enumerate the possible reasons. The 'writeback_work_class' and tracepoint event class and 'writeback_queue_io' tracepoints are updated to include the symbolic 'reason' in all trace events. And the 'writeback_inodes_sbXXX' family of routines has had a wb_stats parameter added to them, so callers can specify why writeback is being started. Acked-by: Jan Kara Signed-off-by: Curt Wohlgemuth Signed-off-by: Wu Fengguang --- fs/btrfs/extent-tree.c | 3 ++- fs/buffer.c | 2 +- fs/ext4/inode.c | 2 +- fs/fs-writeback.c | 49 +++++++++++++++++++++++++++++----------- fs/quota/quota.c | 2 +- fs/sync.c | 4 ++-- fs/ubifs/budget.c | 2 +- include/linux/backing-dev.h | 3 ++- include/linux/writeback.h | 32 +++++++++++++++++++++----- include/trace/events/writeback.h | 14 ++++++++---- mm/backing-dev.c | 3 ++- mm/page-writeback.c | 3 ++- mm/vmscan.c | 3 ++- 13 files changed, 88 insertions(+), 34 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f5be06a2462f..c9ee0e18bbdc 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3340,7 +3340,8 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans, smp_mb(); nr_pages = min_t(unsigned long, nr_pages, root->fs_info->delalloc_bytes >> PAGE_CACHE_SHIFT); - writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages); + writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages, + WB_REASON_FS_FREE_SPACE); spin_lock(&space_info->lock); if (reserved > space_info->bytes_reserved) diff --git a/fs/buffer.c b/fs/buffer.c index 1a80b048ade8..f5dcee6c4cfb 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -285,7 +285,7 @@ static void free_more_memory(void) struct zone *zone; int nid; - wakeup_flusher_threads(1024); + wakeup_flusher_threads(1024, WB_REASON_FREE_MORE_MEM); yield(); for_each_online_node(nid) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 986e2388f031..7fa73a3b2120 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2241,7 +2241,7 @@ static int ext4_nonda_switch(struct super_block *sb) * start pushing delalloc when 1/2 of free blocks are dirty. */ if (free_blocks < 2 * dirty_blocks) - writeback_inodes_sb_if_idle(sb); + writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE); return 0; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c51029693600..73c3992b2bb4 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -41,11 +41,23 @@ struct wb_writeback_work { unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; + enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct completion *done; /* set if the caller waits */ }; +const char *wb_reason_name[] = { + [WB_REASON_BACKGROUND] = "background", + [WB_REASON_TRY_TO_FREE_PAGES] = "try_to_free_pages", + [WB_REASON_SYNC] = "sync", + [WB_REASON_PERIODIC] = "periodic", + [WB_REASON_LAPTOP_TIMER] = "laptop_timer", + [WB_REASON_FREE_MORE_MEM] = "free_more_memory", + [WB_REASON_FS_FREE_SPACE] = "fs_free_space", + [WB_REASON_FORKER_THREAD] = "forker_thread" +}; + /* * Include the creation of the trace points after defining the * wb_writeback_work structure so that the definition remains local to this @@ -115,7 +127,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi, static void __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, - bool range_cyclic) + bool range_cyclic, enum wb_reason reason) { struct wb_writeback_work *work; @@ -135,6 +147,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, work->sync_mode = WB_SYNC_NONE; work->nr_pages = nr_pages; work->range_cyclic = range_cyclic; + work->reason = reason; bdi_queue_work(bdi, work); } @@ -150,9 +163,10 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, * completion. Caller need not hold sb s_umount semaphore. * */ -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages) +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, + enum wb_reason reason) { - __bdi_start_writeback(bdi, nr_pages, true); + __bdi_start_writeback(bdi, nr_pages, true, reason); } /** @@ -641,12 +655,14 @@ static long __writeback_inodes_wb(struct bdi_writeback *wb, return wrote; } -long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages) +long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, + enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, + .reason = reason, }; spin_lock(&wb->list_lock); @@ -825,6 +841,7 @@ static long wb_check_background_flush(struct bdi_writeback *wb) .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, + .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); @@ -858,6 +875,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb) .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, + .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); @@ -976,7 +994,7 @@ int bdi_writeback_thread(void *data) * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back * the whole world. */ -void wakeup_flusher_threads(long nr_pages) +void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) { struct backing_dev_info *bdi; @@ -989,7 +1007,7 @@ void wakeup_flusher_threads(long nr_pages) list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { if (!bdi_has_dirty_io(bdi)) continue; - __bdi_start_writeback(bdi, nr_pages, false); + __bdi_start_writeback(bdi, nr_pages, false, reason); } rcu_read_unlock(); } @@ -1210,7 +1228,9 @@ static void wait_sb_inodes(struct super_block *sb) * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ -void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr) +void writeback_inodes_sb_nr(struct super_block *sb, + unsigned long nr, + enum wb_reason reason) { DECLARE_COMPLETION_ONSTACK(done); struct wb_writeback_work work = { @@ -1219,6 +1239,7 @@ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr) .tagged_writepages = 1, .done = &done, .nr_pages = nr, + .reason = reason, }; WARN_ON(!rwsem_is_locked(&sb->s_umount)); @@ -1235,9 +1256,9 @@ EXPORT_SYMBOL(writeback_inodes_sb_nr); * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ -void writeback_inodes_sb(struct super_block *sb) +void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { - return writeback_inodes_sb_nr(sb, get_nr_dirty_pages()); + return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); @@ -1248,11 +1269,11 @@ EXPORT_SYMBOL(writeback_inodes_sb); * Invoke writeback_inodes_sb if no writeback is currently underway. * Returns 1 if writeback was started, 0 if not. */ -int writeback_inodes_sb_if_idle(struct super_block *sb) +int writeback_inodes_sb_if_idle(struct super_block *sb, enum wb_reason reason) { if (!writeback_in_progress(sb->s_bdi)) { down_read(&sb->s_umount); - writeback_inodes_sb(sb); + writeback_inodes_sb(sb, reason); up_read(&sb->s_umount); return 1; } else @@ -1269,11 +1290,12 @@ EXPORT_SYMBOL(writeback_inodes_sb_if_idle); * Returns 1 if writeback was started, 0 if not. */ int writeback_inodes_sb_nr_if_idle(struct super_block *sb, - unsigned long nr) + unsigned long nr, + enum wb_reason reason) { if (!writeback_in_progress(sb->s_bdi)) { down_read(&sb->s_umount); - writeback_inodes_sb_nr(sb, nr); + writeback_inodes_sb_nr(sb, nr, reason); up_read(&sb->s_umount); return 1; } else @@ -1297,6 +1319,7 @@ void sync_inodes_sb(struct super_block *sb) .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, + .reason = WB_REASON_SYNC, }; WARN_ON(!rwsem_is_locked(&sb->s_umount)); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 10b6be3ca280..4bae57fc603b 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -286,7 +286,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, /* caller already holds s_umount */ if (sb->s_flags & MS_RDONLY) return -EROFS; - writeback_inodes_sb(sb); + writeback_inodes_sb(sb, WB_REASON_SYNC); return 0; default: return -EINVAL; diff --git a/fs/sync.c b/fs/sync.c index c98a7477edfd..101b8ef901d7 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -43,7 +43,7 @@ static int __sync_filesystem(struct super_block *sb, int wait) if (wait) sync_inodes_sb(sb); else - writeback_inodes_sb(sb); + writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, wait); @@ -98,7 +98,7 @@ static void sync_filesystems(int wait) */ SYSCALL_DEFINE0(sync) { - wakeup_flusher_threads(0); + wakeup_flusher_threads(0, WB_REASON_SYNC); sync_filesystems(0); sync_filesystems(1); if (unlikely(laptop_mode)) diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 315de66e52b2..bc4f94b28706 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -63,7 +63,7 @@ static void shrink_liability(struct ubifs_info *c, int nr_to_write) { down_read(&c->vfs_sb->s_umount); - writeback_inodes_sb(c->vfs_sb); + writeback_inodes_sb(c->vfs_sb, WB_REASON_FS_FREE_SPACE); up_read(&c->vfs_sb->s_umount); } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index c3b92010d894..b1038bd686ac 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -118,7 +118,8 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev); void bdi_unregister(struct backing_dev_info *bdi); int bdi_setup_and_register(struct backing_dev_info *, char *, unsigned int); -void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages); +void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages, + enum wb_reason reason); void bdi_start_background_writeback(struct backing_dev_info *bdi); int bdi_writeback_thread(void *data); int bdi_has_dirty_io(struct backing_dev_info *bdi); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index ddb4652cb337..a378c295851f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -38,6 +38,23 @@ enum writeback_sync_modes { WB_SYNC_ALL, /* Wait on every mapping */ }; +/* + * why some writeback work was initiated + */ +enum wb_reason { + WB_REASON_BACKGROUND, + WB_REASON_TRY_TO_FREE_PAGES, + WB_REASON_SYNC, + WB_REASON_PERIODIC, + WB_REASON_LAPTOP_TIMER, + WB_REASON_FREE_MORE_MEM, + WB_REASON_FS_FREE_SPACE, + WB_REASON_FORKER_THREAD, + + WB_REASON_MAX, +}; +extern const char *wb_reason_name[]; + /* * A control structure which tells the writeback code what to do. These are * always on the stack, and hence need no locking. They are always initialised @@ -69,14 +86,17 @@ struct writeback_control { */ struct bdi_writeback; int inode_wait(void *); -void writeback_inodes_sb(struct super_block *); -void writeback_inodes_sb_nr(struct super_block *, unsigned long nr); -int writeback_inodes_sb_if_idle(struct super_block *); -int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr); +void writeback_inodes_sb(struct super_block *, enum wb_reason reason); +void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, + enum wb_reason reason); +int writeback_inodes_sb_if_idle(struct super_block *, enum wb_reason reason); +int writeback_inodes_sb_nr_if_idle(struct super_block *, unsigned long nr, + enum wb_reason reason); void sync_inodes_sb(struct super_block *); -long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages); +long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, + enum wb_reason reason); long wb_do_writeback(struct bdi_writeback *wb, int force_wait); -void wakeup_flusher_threads(long nr_pages); +void wakeup_flusher_threads(long nr_pages, enum wb_reason reason); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 1261db3916cc..b99caa8b780c 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -34,6 +34,7 @@ DECLARE_EVENT_CLASS(writeback_work_class, __field(int, for_kupdate) __field(int, range_cyclic) __field(int, for_background) + __field(int, reason) ), TP_fast_assign( strncpy(__entry->name, dev_name(bdi->dev), 32); @@ -43,16 +44,18 @@ DECLARE_EVENT_CLASS(writeback_work_class, __entry->for_kupdate = work->for_kupdate; __entry->range_cyclic = work->range_cyclic; __entry->for_background = work->for_background; + __entry->reason = work->reason; ), TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d " - "kupdate=%d range_cyclic=%d background=%d", + "kupdate=%d range_cyclic=%d background=%d reason=%s", __entry->name, MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev), __entry->nr_pages, __entry->sync_mode, __entry->for_kupdate, __entry->range_cyclic, - __entry->for_background + __entry->for_background, + wb_reason_name[__entry->reason] ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ @@ -165,6 +168,7 @@ TRACE_EVENT(writeback_queue_io, __field(unsigned long, older) __field(long, age) __field(int, moved) + __field(int, reason) ), TP_fast_assign( unsigned long *older_than_this = work->older_than_this; @@ -173,12 +177,14 @@ TRACE_EVENT(writeback_queue_io, __entry->age = older_than_this ? (jiffies - *older_than_this) * 1000 / HZ : -1; __entry->moved = moved; + __entry->reason = work->reason; ), - TP_printk("bdi %s: older=%lu age=%ld enqueue=%d", + TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s", __entry->name, __entry->older, /* older_than_this in jiffies */ __entry->age, /* older_than_this in relative milliseconds */ - __entry->moved) + __entry->moved, + wb_reason_name[__entry->reason]) ); TRACE_EVENT(global_dirty_state, diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5dcaa3c756d1..dd8916feb05e 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -476,7 +476,8 @@ static int bdi_forker_thread(void *ptr) * the bdi from the thread. Hopefully 1024 is * large enough for efficient IO. */ - writeback_inodes_wb(&bdi->wb, 1024); + writeback_inodes_wb(&bdi->wb, 1024, + WB_REASON_FORKER_THREAD); } else { /* * The spinlock makes sure we do not lose diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 45d36f7dc169..650846b61584 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1301,7 +1301,8 @@ void laptop_mode_timer_fn(unsigned long data) * threshold */ if (bdi_has_dirty_io(&q->backing_dev_info)) - bdi_start_writeback(&q->backing_dev_info, nr_pages); + bdi_start_writeback(&q->backing_dev_info, nr_pages, + WB_REASON_LAPTOP_TIMER); } /* diff --git a/mm/vmscan.c b/mm/vmscan.c index b55699cd9067..c735bd770d3d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2181,7 +2181,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2; if (total_scanned > writeback_threshold) { - wakeup_flusher_threads(laptop_mode ? 0 : total_scanned); + wakeup_flusher_threads(laptop_mode ? 0 : total_scanned, + WB_REASON_TRY_TO_FREE_PAGES); sc->may_writepage = 1; } -- cgit v1.2.3 From 0edeb71dc9133bfb505d3bf59642e07cd936613e Mon Sep 17 00:00:00 2001 From: Tao Ma Date: Mon, 31 Oct 2011 17:30:44 -0400 Subject: ext4: Create helper function for EXT4_IO_END_UNWRITTEN and i_aiodio_unwritten EXT4_IO_END_UNWRITTEN flag set and the increase of i_aiodio_unwritten should be done simultaneously since ext4_end_io_nolock always clear the flag and decrease the counter in the same time. We have found some bugs that the flag is set while leaving i_aiodio_unwritten unchanged(commit 32c80b32c053d). So this patch just tries to create a helper function to wrap them to avoid any future bug. The idea is inspired by Eric. Cc: Eric Sandeen Signed-off-by: Tao Ma Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 9 +++++++++ fs/ext4/extents.c | 18 ++++++------------ fs/ext4/inode.c | 5 +---- fs/ext4/page-io.c | 6 ++---- 4 files changed, 18 insertions(+), 20 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 657e82649fa5..604c200216c1 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1275,6 +1275,15 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)); } +static inline void ext4_set_io_unwritten_flag(struct inode *inode, + struct ext4_io_end *io_end) +{ + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + io_end->flag |= EXT4_IO_END_UNWRITTEN; + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } +} + /* * Inode dynamic state flags */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 36a0f177ecad..a5c8caaaa099 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3472,12 +3472,9 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, * that this IO needs to conversion to written when IO is * completed */ - if (io) { - if (!(io->flag & EXT4_IO_END_UNWRITTEN)) { - io->flag = EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } - } else + if (io) + ext4_set_io_unwritten_flag(inode, io); + else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); if (ext4_should_dioread_nolock(inode)) map->m_flags |= EXT4_MAP_UNINIT; @@ -4030,12 +4027,9 @@ got_allocated_blocks: * that we need to perform conversion when IO is done. */ if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { - if (io) { - if (!(io->flag & EXT4_IO_END_UNWRITTEN)) { - io->flag = EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } - } else + if (io) + ext4_set_io_unwritten_flag(inode, io); + else ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e4b26faac5ff..60af5126eb05 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2831,10 +2831,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) * but being more careful is always safe for the future change. */ inode = io_end->inode; - if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } + ext4_set_io_unwritten_flag(inode, io_end); /* Add the io_end to per-inode completed io list*/ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 9eebf44646f6..7ce1d0b19c94 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -336,10 +336,8 @@ submit_and_retry: if ((io_end->num_io_pages >= MAX_IO_PAGES) && (io_end->pages[io_end->num_io_pages-1] != io_page)) goto submit_and_retry; - if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) { - io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); - } + if (buffer_uninit(bh)) + ext4_set_io_unwritten_flag(inode, io_end); io->io_end->size += bh->b_size; io->io_next_block++; ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); -- cgit v1.2.3 From e260daf27902b2189a9198f5b64fa4567939bb5b Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Mon, 31 Oct 2011 17:54:36 -0400 Subject: ext4: move vars to local scope in ext4_discard_partial_page_buffers_no_lock() Signed-off-by: Yongqiang Yang Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 60af5126eb05..f60b459b27d7 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3179,7 +3179,6 @@ int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, ext4_fsblk_t index = from >> PAGE_CACHE_SHIFT; unsigned int offset = from & (PAGE_CACHE_SIZE-1); unsigned int blocksize, max, pos; - unsigned int end_of_block, range_to_discard; ext4_lblk_t iblock; struct buffer_head *bh; int err = 0; @@ -3231,6 +3230,8 @@ int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, pos = offset; while (pos < offset + length) { + unsigned int end_of_block, range_to_discard; + err = 0; /* The length of space left to zero and unmap */ -- cgit v1.2.3 From 5129d05fda57be13f434dbe8536de39a6c25496d Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Mon, 31 Oct 2011 17:56:10 -0400 Subject: ext4: return ENOMEM if find_or_create_pages fails Signed-off-by: Yongqiang Yang Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f60b459b27d7..5fcef98f98e5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3129,7 +3129,7 @@ int ext4_discard_partial_page_buffers(handle_t *handle, page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, mapping_gfp_mask(mapping) & ~__GFP_FS); if (!page) - return -EINVAL; + return -ENOMEM; err = ext4_discard_partial_page_buffers_no_lock(handle, inode, page, from, length, flags); @@ -3372,7 +3372,7 @@ int ext4_block_zero_page_range(handle_t *handle, page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT, mapping_gfp_mask(mapping) & ~__GFP_FS); if (!page) - return -EINVAL; + return -ENOMEM; blocksize = inode->i_sb->s_blocksize; max = blocksize - (offset & (blocksize - 1)); -- cgit v1.2.3 From edb5ac8993e25143f6af1ab143843a65c52e2a15 Mon Sep 17 00:00:00 2001 From: Yongqiang Yang Date: Mon, 31 Oct 2011 18:04:38 -0400 Subject: ext4: let ext4_discard_partial_buffers handle unaligned range correctly As comment says, we should handle unaligned range rather than aligned one. This fixes a bug found by running xfstests #91. Signed-off-by: Yongqiang Yang --- fs/ext4/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5fcef98f98e5..de05e86f1993 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3206,8 +3206,8 @@ int ext4_discard_partial_page_buffers_no_lock(handle_t *handle, * to be updated with the contents of the block before * we write the zeros on top of it. */ - if (!(from & (blocksize - 1)) || - !((from + length) & (blocksize - 1))) { + if ((from & (blocksize - 1)) || + ((from + length) & (blocksize - 1))) { create_empty_buffers(page, blocksize, 0); } else { /* -- cgit v1.2.3 From 966dbde2c208e07bab7a45a7855e1e693eabe661 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 31 Oct 2011 17:07:48 -0700 Subject: ext4: warn if direct reclaim tries to writeback pages Direct reclaim should never writeback pages. Warn if an attempt is made. Signed-off-by: Mel Gorman Cc: Dave Chinner Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Wu Fengguang Cc: Jan Kara Cc: Minchan Kim Cc: Rik van Riel Cc: Mel Gorman Cc: Alex Elder Cc: Theodore Ts'o Cc: Chris Mason Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext4/inode.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 986e2388f031..0defe0bfe019 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1811,8 +1811,12 @@ static int ext4_writepage(struct page *page, * We don't want to do block allocation, so redirty * the page and return. We may reach here when we do * a journal commit via journal_submit_inode_data_buffers. - * We can also reach here via shrink_page_list + * We can also reach here via shrink_page_list but it + * should never be for direct reclaim so warn if that + * happens */ + WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == + PF_MEMALLOC); goto redirty_page; } if (commit_write) -- cgit v1.2.3 From bfe8684869601dacfcb2cd69ef8cfd9045f62170 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 28 Oct 2011 14:13:29 +0200 Subject: filesystems: add set_nlink() Replace remaining direct i_nlink updates with a new set_nlink() updater function. Signed-off-by: Miklos Szeredi Tested-by: Toshiyuki Okajima Signed-off-by: Christoph Hellwig --- arch/s390/hypfs/inode.c | 2 +- drivers/staging/pohmelfs/inode.c | 2 +- fs/9p/vfs_inode.c | 4 ++-- fs/9p/vfs_inode_dotl.c | 4 ++-- fs/adfs/inode.c | 2 +- fs/affs/amigaffs.c | 2 +- fs/affs/inode.c | 8 ++++---- fs/afs/fsclient.c | 2 +- fs/afs/inode.c | 4 ++-- fs/autofs4/inode.c | 2 +- fs/befs/linuxvfs.c | 2 +- fs/bfs/dir.c | 2 +- fs/bfs/inode.c | 2 +- fs/btrfs/delayed-inode.c | 2 +- fs/btrfs/disk-io.c | 2 +- fs/btrfs/inode.c | 4 ++-- fs/btrfs/tree-log.c | 2 +- fs/ceph/caps.c | 2 +- fs/ceph/inode.c | 2 +- fs/cifs/inode.c | 6 +++--- fs/coda/coda_linux.c | 2 +- fs/devpts/inode.c | 2 +- fs/ecryptfs/inode.c | 12 ++++++------ fs/efs/inode.c | 2 +- fs/exofs/inode.c | 2 +- fs/ext2/inode.c | 2 +- fs/ext3/inode.c | 2 +- fs/ext3/namei.c | 4 ++-- fs/ext4/inode.c | 2 +- fs/ext4/namei.c | 6 +++--- fs/fat/inode.c | 4 ++-- fs/fat/namei_msdos.c | 2 +- fs/fat/namei_vfat.c | 2 +- fs/freevxfs/vxfs_inode.c | 2 +- fs/fuse/control.c | 2 +- fs/fuse/inode.c | 2 +- fs/gfs2/glops.c | 2 +- fs/hfs/inode.c | 4 ++-- fs/hfsplus/inode.c | 10 +++++----- fs/hostfs/hostfs_kern.c | 2 +- fs/hpfs/dir.c | 2 +- fs/hpfs/inode.c | 8 ++++---- fs/hpfs/namei.c | 8 ++++---- fs/hppfs/hppfs.c | 2 +- fs/isofs/inode.c | 4 ++-- fs/isofs/rock.c | 4 ++-- fs/jffs2/dir.c | 6 +++--- fs/jffs2/fs.c | 6 +++--- fs/jfs/jfs_imap.c | 6 +++--- fs/jfs/namei.c | 2 +- fs/libfs.c | 2 +- fs/logfs/readwrite.c | 2 +- fs/minix/inode.c | 4 ++-- fs/ncpfs/inode.c | 2 +- fs/nfs/inode.c | 4 ++-- fs/nilfs2/inode.c | 2 +- fs/nilfs2/namei.c | 2 +- fs/ntfs/inode.c | 8 ++++---- fs/ocfs2/dir.c | 4 ++-- fs/ocfs2/dlmglue.c | 2 +- fs/ocfs2/inode.c | 4 ++-- fs/ocfs2/namei.c | 8 ++++---- fs/openpromfs/inode.c | 4 ++-- fs/proc/base.c | 12 ++++++------ fs/proc/generic.c | 2 +- fs/proc/inode.c | 2 +- fs/qnx4/inode.c | 2 +- fs/reiserfs/inode.c | 6 +++--- fs/reiserfs/namei.c | 4 ++-- fs/romfs/super.c | 2 +- fs/squashfs/inode.c | 18 +++++++++--------- fs/stack.c | 2 +- fs/sysfs/inode.c | 2 +- fs/sysv/inode.c | 2 +- fs/ubifs/super.c | 2 +- fs/ubifs/xattr.c | 2 +- fs/udf/inode.c | 8 +++++--- fs/udf/namei.c | 4 ++-- fs/ufs/inode.c | 4 ++-- fs/xfs/xfs_iops.c | 2 +- include/linux/fs.h | 13 +++++++++++++ 81 files changed, 163 insertions(+), 148 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index baa82f8dd076..481f4f76f664 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -108,7 +108,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, int mode) ret->i_gid = hypfs_info->gid; ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME; if (mode & S_IFDIR) - ret->i_nlink = 2; + set_nlink(ret, 2); } return ret; } diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c index f3c6060c96b8..7a1955583b7d 100644 --- a/drivers/staging/pohmelfs/inode.c +++ b/drivers/staging/pohmelfs/inode.c @@ -1197,7 +1197,7 @@ const struct inode_operations pohmelfs_file_inode_operations = { void pohmelfs_fill_inode(struct inode *inode, struct netfs_inode_info *info) { inode->i_mode = info->mode; - inode->i_nlink = info->nlink; + set_nlink(inode, info->nlink); inode->i_uid = info->uid; inode->i_gid = info->gid; inode->i_blocks = info->blocks; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index b5a1076aaa6c..879ed8851737 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1138,7 +1138,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, struct v9fs_session_info *v9ses = sb->s_fs_info; struct v9fs_inode *v9inode = V9FS_I(inode); - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_atime.tv_sec = stat->atime; inode->i_mtime.tv_sec = stat->mtime; @@ -1164,7 +1164,7 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, /* HARDLINKCOUNT %u */ sscanf(ext, "%13s %u", tag_name, &i_nlink); if (!strncmp(tag_name, "HARDLINKCOUNT", 13)) - inode->i_nlink = i_nlink; + set_nlink(inode, i_nlink); } } mode = stat->mode & S_IALLUGO; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index aded79fcd5cf..0b5745e21946 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -606,7 +606,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) inode->i_ctime.tv_nsec = stat->st_ctime_nsec; inode->i_uid = stat->st_uid; inode->i_gid = stat->st_gid; - inode->i_nlink = stat->st_nlink; + set_nlink(inode, stat->st_nlink); mode = stat->st_mode & S_IALLUGO; mode |= inode->i_mode & ~S_IALLUGO; @@ -632,7 +632,7 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) if (stat->st_result_mask & P9_STATS_GID) inode->i_gid = stat->st_gid; if (stat->st_result_mask & P9_STATS_NLINK) - inode->i_nlink = stat->st_nlink; + set_nlink(inode, stat->st_nlink); if (stat->st_result_mask & P9_STATS_MODE) { inode->i_mode = stat->st_mode; if ((S_ISBLK(inode->i_mode)) || diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index d5250c5aae21..1dab6a174d6a 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -247,7 +247,7 @@ adfs_iget(struct super_block *sb, struct object_info *obj) inode->i_gid = ADFS_SB(sb)->s_gid; inode->i_ino = obj->file_id; inode->i_size = obj->size; - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index 8f12723bbc97..de37ec842340 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -215,7 +215,7 @@ affs_remove_link(struct dentry *dentry) break; default: if (!AFFS_TAIL(sb, bh)->link_chain) - inode->i_nlink = 1; + set_nlink(inode, 1); } affs_free_block(sb, link_ino); goto done; diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 5d828903ac69..88a4b0b50058 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -54,7 +54,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) prot = be32_to_cpu(tail->protect); inode->i_size = 0; - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_mode = 0; AFFS_I(inode)->i_extcnt = 1; AFFS_I(inode)->i_ext_last = ~1; @@ -137,7 +137,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino) sbi->s_hashsize + 1; } if (tail->link_chain) - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_mapping->a_ops = (sbi->s_flags & SF_OFS) ? &affs_aops_ofs : &affs_aops; inode->i_op = &affs_file_inode_operations; inode->i_fop = &affs_file_operations; @@ -304,7 +304,7 @@ affs_new_inode(struct inode *dir) inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_ino = block; - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; atomic_set(&AFFS_I(inode)->i_opencnt, 0); AFFS_I(inode)->i_blkcnt = 0; @@ -387,7 +387,7 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3 AFFS_TAIL(sb, inode_bh)->link_chain = cpu_to_be32(block); affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain)); mark_buffer_dirty_inode(inode_bh, inode); - inode->i_nlink = 2; + set_nlink(inode, 2); ihold(inode); } affs_fix_checksum(sb, bh); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 346e3289abd7..2f213d109c21 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -90,7 +90,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp, vnode->vfs_inode.i_uid = status->owner; vnode->vfs_inode.i_gid = status->group; vnode->vfs_inode.i_generation = vnode->fid.unique; - vnode->vfs_inode.i_nlink = status->nlink; + set_nlink(&vnode->vfs_inode, status->nlink); mode = vnode->vfs_inode.i_mode; mode &= ~S_IALLUGO; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 0fdab6e03d87..d890ae3b2ce6 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -67,7 +67,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) fscache_attr_changed(vnode->cache); #endif - inode->i_nlink = vnode->status.nlink; + set_nlink(inode, vnode->status.nlink); inode->i_uid = vnode->status.owner; inode->i_gid = 0; inode->i_size = vnode->status.size; @@ -174,7 +174,7 @@ struct inode *afs_iget_autocell(struct inode *dir, const char *dev_name, inode->i_size = 0; inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_op = &afs_autocell_inode_operations; - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_uid = 0; inode->i_gid = 0; inode->i_ctime.tv_sec = get_seconds(); diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index 180fa2425e49..8179f1ab8175 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -342,7 +342,7 @@ struct inode *autofs4_get_inode(struct super_block *sb, mode_t mode) inode->i_ino = get_next_ino(); if (S_ISDIR(mode)) { - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_op = &autofs4_dir_inode_operations; inode->i_fop = &autofs4_dir_operations; } else if (S_ISLNK(mode)) { diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 720d885e8dca..8342ca67abcd 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -357,7 +357,7 @@ static struct inode *befs_iget(struct super_block *sb, unsigned long ino) inode->i_gid = befs_sb->mount_opts.use_gid ? befs_sb->mount_opts.gid : (gid_t) fs32_to_cpu(sb, raw_inode->gid); - inode->i_nlink = 1; + set_nlink(inode, 1); /* * BEFS's time is 64 bits, but current VFS is 32 bits... diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index b14cebfd9047..9cc074019479 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -199,7 +199,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry) printf("unlinking non-existent file %s:%lu (nlink=%d)\n", inode->i_sb->s_id, inode->i_ino, inode->i_nlink); - inode->i_nlink = 1; + set_nlink(inode, 1); } de->ino = 0; mark_buffer_dirty_inode(bh, dir); diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index a8e37f81d097..697af5bf70b3 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -78,7 +78,7 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino) BFS_I(inode)->i_dsk_ino = le16_to_cpu(di->i_ino); inode->i_uid = le32_to_cpu(di->i_uid); inode->i_gid = le32_to_cpu(di->i_gid); - inode->i_nlink = le32_to_cpu(di->i_nlink); + set_nlink(inode, le32_to_cpu(di->i_nlink)); inode->i_size = BFS_FILESIZE(di); inode->i_blocks = BFS_FILEBLOCKS(di); inode->i_atime.tv_sec = le32_to_cpu(di->i_atime); diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index b52c672f4c18..ae4d9cd10961 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1641,7 +1641,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) inode->i_gid = btrfs_stack_inode_gid(inode_item); btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); inode->i_mode = btrfs_stack_inode_mode(inode_item); - inode->i_nlink = btrfs_stack_inode_nlink(inode_item); + set_nlink(inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item)); BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item); BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 07b3ac662e19..07ea91879a91 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1705,7 +1705,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, sb->s_bdi = &fs_info->bdi; fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID; - fs_info->btree_inode->i_nlink = 1; + set_nlink(fs_info->btree_inode, 1); /* * we set the i_size on the btree inode to the max possible int. * the real end of the address space is determined by all of diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b2d004ad66a0..75686a61bd45 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2534,7 +2534,7 @@ static void btrfs_read_locked_inode(struct inode *inode) inode_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item); inode->i_mode = btrfs_inode_mode(leaf, inode_item); - inode->i_nlink = btrfs_inode_nlink(leaf, inode_item); + set_nlink(inode, btrfs_inode_nlink(leaf, inode_item)); inode->i_uid = btrfs_inode_uid(leaf, inode_item); inode->i_gid = btrfs_inode_gid(leaf, inode_item); btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item)); @@ -6728,7 +6728,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, inode->i_op = &btrfs_dir_inode_operations; inode->i_fop = &btrfs_dir_file_operations; - inode->i_nlink = 1; + set_nlink(inode, 1); btrfs_i_size_write(inode, 0); err = btrfs_update_inode(trans, new_root, inode); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 786639fca067..0618aa39740b 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1030,7 +1030,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans, } btrfs_release_path(path); if (nlink != inode->i_nlink) { - inode->i_nlink = nlink; + set_nlink(inode, nlink); btrfs_update_inode(trans, root, inode); } BTRFS_I(inode)->index_cnt = (u64)-1; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index b8731bf3ef1f..15b21e35078a 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2363,7 +2363,7 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, } if ((issued & CEPH_CAP_LINK_EXCL) == 0) - inode->i_nlink = le32_to_cpu(grant->nlink); + set_nlink(inode, le32_to_cpu(grant->nlink)); if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && grant->xattr_len) { int len = le32_to_cpu(grant->xattr_len); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 5dde7d51dc11..1616a0d37cbd 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -618,7 +618,7 @@ static int fill_inode(struct inode *inode, } if ((issued & CEPH_CAP_LINK_EXCL) == 0) - inode->i_nlink = le32_to_cpu(info->nlink); + set_nlink(inode, le32_to_cpu(info->nlink)); /* be careful with mtime, atime, size */ ceph_decode_timespec(&atime, &info->atime); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 2c50bd2f65d1..e851d5b8931e 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -132,7 +132,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) inode->i_mtime = fattr->cf_mtime; inode->i_ctime = fattr->cf_ctime; inode->i_rdev = fattr->cf_rdev; - inode->i_nlink = fattr->cf_nlink; + set_nlink(inode, fattr->cf_nlink); inode->i_uid = fattr->cf_uid; inode->i_gid = fattr->cf_gid; @@ -905,7 +905,7 @@ struct inode *cifs_root_iget(struct super_block *sb) if (rc && tcon->ipc) { cFYI(1, "ipc connection - fake read inode"); inode->i_mode |= S_IFDIR; - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_op = &cifs_ipc_inode_ops; inode->i_fop = &simple_dir_operations; inode->i_uid = cifs_sb->mnt_uid; @@ -1367,7 +1367,7 @@ mkdir_get_info: /* setting nlink not necessary except in cases where we * failed to get it from the server or was set bogus */ if ((direntry->d_inode) && (direntry->d_inode->i_nlink < 2)) - direntry->d_inode->i_nlink = 2; + set_nlink(direntry->d_inode, 2); mode &= ~current_umask(); /* must turn on setgid bit if parent dir has it */ diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c index 2bdbcc11b373..854ace712685 100644 --- a/fs/coda/coda_linux.c +++ b/fs/coda/coda_linux.c @@ -104,7 +104,7 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr) if (attr->va_gid != -1) inode->i_gid = (gid_t) attr->va_gid; if (attr->va_nlink != -1) - inode->i_nlink = attr->va_nlink; + set_nlink(inode, attr->va_nlink); if (attr->va_size != -1) inode->i_size = attr->va_size; if (attr->va_size != -1) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index c196e544c64e..d5d5297efe97 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -307,7 +307,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent) inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; - inode->i_nlink = 2; + set_nlink(inode, 2); s->s_root = d_alloc_root(inode); if (s->s_root) diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 11f8582d7218..a36d327f1521 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -474,8 +474,8 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir, goto out_lock; fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode); - old_dentry->d_inode->i_nlink = - ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink; + set_nlink(old_dentry->d_inode, + ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink); i_size_write(new_dentry->d_inode, file_size_save); out_lock: unlock_dir(lower_dir_dentry); @@ -499,8 +499,8 @@ static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry) goto out_unlock; } fsstack_copy_attr_times(dir, lower_dir_inode); - dentry->d_inode->i_nlink = - ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink; + set_nlink(dentry->d_inode, + ecryptfs_inode_to_lower(dentry->d_inode)->i_nlink); dentry->d_inode->i_ctime = dir->i_ctime; d_drop(dentry); out_unlock: @@ -565,7 +565,7 @@ static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) goto out; fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode); - dir->i_nlink = lower_dir_dentry->d_inode->i_nlink; + set_nlink(dir, lower_dir_dentry->d_inode->i_nlink); out: unlock_dir(lower_dir_dentry); if (!dentry->d_inode) @@ -588,7 +588,7 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry) if (!rc && dentry->d_inode) clear_nlink(dentry->d_inode); fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode); - dir->i_nlink = lower_dir_dentry->d_inode->i_nlink; + set_nlink(dir, lower_dir_dentry->d_inode->i_nlink); unlock_dir(lower_dir_dentry); if (!rc) d_drop(dentry); diff --git a/fs/efs/inode.c b/fs/efs/inode.c index 9c13412e6c99..bc84f365d75c 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -96,7 +96,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino) efs_inode = (struct efs_dinode *) (bh->b_data + offset); inode->i_mode = be16_to_cpu(efs_inode->di_mode); - inode->i_nlink = be16_to_cpu(efs_inode->di_nlink); + set_nlink(inode, be16_to_cpu(efs_inode->di_nlink)); inode->i_uid = (uid_t)be16_to_cpu(efs_inode->di_uid); inode->i_gid = (gid_t)be16_to_cpu(efs_inode->di_gid); inode->i_size = be32_to_cpu(efs_inode->di_size); diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 3e5f3a6be90a..f6dbf7768ce6 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1165,7 +1165,7 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino) inode->i_mode = le16_to_cpu(fcb.i_mode); inode->i_uid = le32_to_cpu(fcb.i_uid); inode->i_gid = le32_to_cpu(fcb.i_gid); - inode->i_nlink = le16_to_cpu(fcb.i_links_count); + set_nlink(inode, le16_to_cpu(fcb.i_links_count)); inode->i_ctime.tv_sec = (signed)le32_to_cpu(fcb.i_ctime); inode->i_atime.tv_sec = (signed)le32_to_cpu(fcb.i_atime); inode->i_mtime.tv_sec = (signed)le32_to_cpu(fcb.i_mtime); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index a8a58f63f07c..91a6945af6d8 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1321,7 +1321,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } - inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); + set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime); diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 12661e1deedd..85fe655fe3e0 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2899,7 +2899,7 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } - inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); + set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime); diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index 8a60e3327659..642dc6d66dfd 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1821,7 +1821,7 @@ retry: de->name_len = 2; strcpy (de->name, ".."); ext3_set_de_type(dir->i_sb, de, S_IFDIR); - inode->i_nlink = 2; + set_nlink(inode, 2); BUFFER_TRACE(dir_block, "call ext3_journal_dirty_metadata"); err = ext3_journal_dirty_metadata(handle, dir_block); if (err) @@ -2170,7 +2170,7 @@ static int ext3_unlink(struct inode * dir, struct dentry *dentry) ext3_warning (inode->i_sb, "ext3_unlink", "Deleting nonexistent file (%lu), %d", inode->i_ino, inode->i_nlink); - inode->i_nlink = 1; + set_nlink(inode, 1); } retval = ext3_delete_entry(handle, dir, de, bh); if (retval) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0defe0bfe019..be6668bbc1b3 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3418,7 +3418,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } - inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); + set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ei->i_dir_start_lookup = 0; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 4623c082f3b2..5f7fb46293be 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1694,7 +1694,7 @@ static void ext4_inc_count(handle_t *handle, struct inode *inode) if (is_dx(inode) && inode->i_nlink > 1) { /* limit is 16-bit i_links_count */ if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) { - inode->i_nlink = 1; + set_nlink(inode, 1); EXT4_SET_RO_COMPAT_FEATURE(inode->i_sb, EXT4_FEATURE_RO_COMPAT_DIR_NLINK); } @@ -1861,7 +1861,7 @@ retry: de->name_len = 2; strcpy(de->name, ".."); ext4_set_de_type(dir->i_sb, de, S_IFDIR); - inode->i_nlink = 2; + set_nlink(inode, 2); BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, dir, dir_block); if (err) @@ -2214,7 +2214,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) ext4_warning(inode->i_sb, "Deleting nonexistent file (%lu), %d", inode->i_ino, inode->i_nlink); - inode->i_nlink = 1; + set_nlink(inode, 1); } retval = ext4_delete_entry(handle, dir, de, bh); if (retval) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 1726d7303047..808cac7edcfb 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -379,7 +379,7 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) return error; MSDOS_I(inode)->mmu_private = inode->i_size; - inode->i_nlink = fat_subdirs(inode); + set_nlink(inode, fat_subdirs(inode)); } else { /* not a directory */ inode->i_generation |= 1; inode->i_mode = fat_make_mode(sbi, de->attr, @@ -1233,7 +1233,7 @@ static int fat_read_root(struct inode *inode) fat_save_attrs(inode, ATTR_DIR); inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0; inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0; - inode->i_nlink = fat_subdirs(inode)+2; + set_nlink(inode, fat_subdirs(inode)+2); return 0; } diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index 66e83b845455..216b419f30e2 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -387,7 +387,7 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, int mode) /* the directory was completed, just return a error */ goto out; } - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_mtime = inode->i_atime = inode->i_ctime = ts; /* timestamp is already written, so mark_inode_dirty() is unneeded. */ diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index bb3f29c3557b..a87a65663c25 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -900,7 +900,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, int mode) goto out; } inode->i_version++; - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_mtime = inode->i_atime = inode->i_ctime = ts; /* timestamp is already written, so mark_inode_dirty() is unneeded. */ diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index 1a4311437a8b..7b2af5abe2fa 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -227,7 +227,7 @@ vxfs_iinit(struct inode *ip, struct vxfs_inode_info *vip) ip->i_uid = (uid_t)vip->vii_uid; ip->i_gid = (gid_t)vip->vii_gid; - ip->i_nlink = vip->vii_nlink; + set_nlink(ip, vip->vii_nlink); ip->i_size = vip->vii_size; ip->i_atime.tv_sec = vip->vii_atime; diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 85542a7daf40..42593c587d48 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -231,7 +231,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent, if (iop) inode->i_op = iop; inode->i_fop = fop; - inode->i_nlink = nlink; + set_nlink(inode, nlink); inode->i_private = fc; d_add(dentry, inode); return dentry; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index add96f6ffda5..3e6d72756479 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -151,7 +151,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, inode->i_ino = attr->ino; inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); - inode->i_nlink = attr->nlink; + set_nlink(inode, attr->nlink); inode->i_uid = attr->uid; inode->i_gid = attr->gid; inode->i_blocks = attr->blocks; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 78418b4fa857..1656df7aacd2 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -299,7 +299,7 @@ static void gfs2_set_nlink(struct inode *inode, u32 nlink) if (nlink == 0) clear_nlink(inode); else - inode->i_nlink = nlink; + set_nlink(inode, nlink); } } diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 96a1b625fc74..a1a9fdcd2a00 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -183,7 +183,7 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, int mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; HFS_I(inode)->flags = 0; HFS_I(inode)->rsrc_inode = NULL; @@ -313,7 +313,7 @@ static int hfs_read_inode(struct inode *inode, void *data) /* Initialize the inode */ inode->i_uid = hsb->s_uid; inode->i_gid = hsb->s_gid; - inode->i_nlink = 1; + set_nlink(inode, 1); if (idata->key) HFS_I(inode)->cat_key = *idata->key; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index 4cc1e3a36ec7..40e1413be4cf 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -391,7 +391,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, int mode) inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; hip = HFSPLUS_I(inode); @@ -512,7 +512,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_folder)); hfsplus_get_perms(inode, &folder->permissions, 1); - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_size = 2 + be32_to_cpu(folder->valence); inode->i_atime = hfsp_mt2ut(folder->access_date); inode->i_mtime = hfsp_mt2ut(folder->content_mod_date); @@ -532,11 +532,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) hfsplus_inode_read_fork(inode, HFSPLUS_IS_RSRC(inode) ? &file->rsrc_fork : &file->data_fork); hfsplus_get_perms(inode, &file->permissions, 0); - inode->i_nlink = 1; + set_nlink(inode, 1); if (S_ISREG(inode->i_mode)) { if (file->permissions.dev) - inode->i_nlink = - be32_to_cpu(file->permissions.dev); + set_nlink(inode, + be32_to_cpu(file->permissions.dev)); inode->i_op = &hfsplus_file_inode_operations; inode->i_fop = &hfsplus_file_operations; inode->i_mapping->a_ops = &hfsplus_aops; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 0d22afdd4611..2f72da5ae686 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -541,7 +541,7 @@ static int read_name(struct inode *ino, char *name) ino->i_ino = st.ino; ino->i_mode = st.mode; - ino->i_nlink = st.nlink; + set_nlink(ino, st.nlink); ino->i_uid = st.uid; ino->i_gid = st.gid; ino->i_atime = st.atime; diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index 96a8ed91cedd..2fa0089a02a8 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -247,7 +247,7 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, struct name result->i_mode &= ~0111; result->i_op = &hpfs_file_iops; result->i_fop = &hpfs_file_ops; - result->i_nlink = 1; + set_nlink(result, 1); } unlock_new_inode(result); } diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index dfe800c8ae38..3b2cec29972b 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -77,7 +77,7 @@ void hpfs_read_inode(struct inode *i) i->i_mode = S_IFLNK | 0777; i->i_op = &page_symlink_inode_operations; i->i_data.a_ops = &hpfs_symlink_aops; - i->i_nlink = 1; + set_nlink(i, 1); i->i_size = ea_size; i->i_blocks = 1; brelse(bh); @@ -101,7 +101,7 @@ void hpfs_read_inode(struct inode *i) } if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { brelse(bh); - i->i_nlink = 1; + set_nlink(i, 1); i->i_size = 0; i->i_blocks = 1; init_special_inode(i, mode, @@ -125,13 +125,13 @@ void hpfs_read_inode(struct inode *i) hpfs_count_dnodes(i->i_sb, hpfs_inode->i_dno, &n_dnodes, &n_subdirs, NULL); i->i_blocks = 4 * n_dnodes; i->i_size = 2048 * n_dnodes; - i->i_nlink = 2 + n_subdirs; + set_nlink(i, 2 + n_subdirs); } else { i->i_mode |= S_IFREG; if (!hpfs_inode->i_ea_mode) i->i_mode &= ~0111; i->i_op = &hpfs_file_iops; i->i_fop = &hpfs_file_ops; - i->i_nlink = 1; + set_nlink(i, 1); i->i_size = le32_to_cpu(fnode->file_size); i->i_blocks = ((i->i_size + 511) >> 9) + 1; i->i_data.a_ops = &hpfs_aops; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 2df69e2f07cf..ea91fcb0ef9b 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -56,7 +56,7 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) result->i_fop = &hpfs_dir_ops; result->i_blocks = 4; result->i_size = 2048; - result->i_nlink = 2; + set_nlink(result, 2); if (dee.read_only) result->i_mode &= ~0222; @@ -150,7 +150,7 @@ static int hpfs_create(struct inode *dir, struct dentry *dentry, int mode, struc result->i_mode &= ~0111; result->i_op = &hpfs_file_iops; result->i_fop = &hpfs_file_ops; - result->i_nlink = 1; + set_nlink(result, 1); hpfs_i(result)->i_parent_dir = dir->i_ino; result->i_ctime.tv_sec = result->i_mtime.tv_sec = result->i_atime.tv_sec = local_to_gmt(dir->i_sb, le32_to_cpu(dee.creation_date)); result->i_ctime.tv_nsec = 0; @@ -242,7 +242,7 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t hpfs_i(result)->i_ea_size = 0; result->i_uid = current_fsuid(); result->i_gid = current_fsgid(); - result->i_nlink = 1; + set_nlink(result, 1); result->i_size = 0; result->i_blocks = 1; init_special_inode(result, mode, rdev); @@ -318,7 +318,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy result->i_uid = current_fsuid(); result->i_gid = current_fsgid(); result->i_blocks = 1; - result->i_nlink = 1; + set_nlink(result, 1); result->i_size = strlen(symlink); result->i_op = &page_symlink_inode_operations; result->i_data.a_ops = &hpfs_symlink_aops; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 970ea987b3f6..f590b1160c6c 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -702,7 +702,7 @@ static struct inode *get_inode(struct super_block *sb, struct dentry *dentry) inode->i_ctime = proc_ino->i_ctime; inode->i_ino = proc_ino->i_ino; inode->i_mode = proc_ino->i_mode; - inode->i_nlink = proc_ino->i_nlink; + set_nlink(inode, proc_ino->i_nlink); inode->i_size = proc_ino->i_size; inode->i_blocks = proc_ino->i_blocks; diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index a5d03672d04e..562adabef985 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1319,7 +1319,7 @@ static int isofs_read_inode(struct inode *inode) inode->i_mode = S_IFDIR | sbi->s_dmode; else inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; - inode->i_nlink = 1; /* + set_nlink(inode, 1); /* * Set to 1. We know there are 2, but * the find utility tries to optimize * if it is 2, and it screws up. It is @@ -1337,7 +1337,7 @@ static int isofs_read_inode(struct inode *inode) */ inode->i_mode = S_IFREG | S_IRUGO | S_IXUGO; } - inode->i_nlink = 1; + set_nlink(inode, 1); } inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 1fbc7de88f50..70e79d0c756a 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -363,7 +363,7 @@ repeat: break; case SIG('P', 'X'): inode->i_mode = isonum_733(rr->u.PX.mode); - inode->i_nlink = isonum_733(rr->u.PX.n_links); + set_nlink(inode, isonum_733(rr->u.PX.n_links)); inode->i_uid = isonum_733(rr->u.PX.uid); inode->i_gid = isonum_733(rr->u.PX.gid); break; @@ -496,7 +496,7 @@ repeat: goto out; } inode->i_mode = reloc->i_mode; - inode->i_nlink = reloc->i_nlink; + set_nlink(inode, reloc->i_nlink); inode->i_uid = reloc->i_uid; inode->i_gid = reloc->i_gid; inode->i_rdev = reloc->i_rdev; diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index 9659b7c00468..be6169bd8acd 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -245,7 +245,7 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry) ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name, dentry->d_name.len, dead_f, now); if (dead_f->inocache) - dentry->d_inode->i_nlink = dead_f->inocache->pino_nlink; + set_nlink(dentry->d_inode, dead_f->inocache->pino_nlink); if (!ret) dir_i->i_mtime = dir_i->i_ctime = ITIME(now); return ret; @@ -278,7 +278,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de if (!ret) { mutex_lock(&f->sem); - old_dentry->d_inode->i_nlink = ++f->inocache->pino_nlink; + set_nlink(old_dentry->d_inode, ++f->inocache->pino_nlink); mutex_unlock(&f->sem); d_instantiate(dentry, old_dentry->d_inode); dir_i->i_mtime = dir_i->i_ctime = ITIME(now); @@ -497,7 +497,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode) f = JFFS2_INODE_INFO(inode); /* Directories get nlink 2 at start */ - inode->i_nlink = 2; + set_nlink(inode, 2); /* but ic->pino_nlink is the parent ino# */ f->inocache->pino_nlink = dir_i->i_ino; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index bbcb9755dd2b..7286e44ac665 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -278,7 +278,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino) inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime)); inode->i_ctime = ITIME(je32_to_cpu(latest_node.ctime)); - inode->i_nlink = f->inocache->pino_nlink; + set_nlink(inode, f->inocache->pino_nlink); inode->i_blocks = (inode->i_size + 511) >> 9; @@ -291,7 +291,7 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino) case S_IFDIR: { struct jffs2_full_dirent *fd; - inode->i_nlink = 2; /* parent and '.' */ + set_nlink(inode, 2); /* parent and '.' */ for (fd=f->dents; fd; fd = fd->next) { if (fd->type == DT_DIR && fd->ino) @@ -453,7 +453,7 @@ struct inode *jffs2_new_inode (struct inode *dir_i, umode_t mode, struct jffs2_r iput(inode); return ERR_PTR(ret); } - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_ino = je32_to_cpu(ri->ino); inode->i_mode = jemode_to_cpu(ri->mode); inode->i_gid = je16_to_cpu(ri->gid); diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index b78b2f978f04..1b6f15f191b3 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -457,7 +457,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary) /* read the page of fixed disk inode (AIT) in raw mode */ mp = read_metapage(ip, address << sbi->l2nbperpage, PSIZE, 1); if (mp == NULL) { - ip->i_nlink = 1; /* Don't want iput() deleting it */ + set_nlink(ip, 1); /* Don't want iput() deleting it */ iput(ip); return (NULL); } @@ -469,7 +469,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary) /* copy on-disk inode to in-memory inode */ if ((copy_from_dinode(dp, ip)) != 0) { /* handle bad return by returning NULL for ip */ - ip->i_nlink = 1; /* Don't want iput() deleting it */ + set_nlink(ip, 1); /* Don't want iput() deleting it */ iput(ip); /* release the page */ release_metapage(mp); @@ -3076,7 +3076,7 @@ static int copy_from_dinode(struct dinode * dip, struct inode *ip) ip->i_mode |= 0001; } } - ip->i_nlink = le32_to_cpu(dip->di_nlink); + set_nlink(ip, le32_to_cpu(dip->di_nlink)); jfs_ip->saved_uid = le32_to_cpu(dip->di_uid); if (sbi->uid == -1) diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 94b0a624b85f..a112ad96e474 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -292,7 +292,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, int mode) goto out3; } - ip->i_nlink = 2; /* for '.' */ + set_nlink(ip, 2); /* for '.' */ ip->i_op = &jfs_dir_inode_operations; ip->i_fop = &jfs_dir_operations; diff --git a/fs/libfs.c b/fs/libfs.c index a2c0029cd95f..f6d411eef1e7 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -490,7 +490,7 @@ int simple_fill_super(struct super_block *s, unsigned long magic, inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; - inode->i_nlink = 2; + set_nlink(inode, 2); root = d_alloc_root(inode); if (!root) { iput(inode); diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index d8d09380c7de..2ac4217b7901 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -126,7 +126,7 @@ static void logfs_disk_to_inode(struct logfs_disk_inode *di, struct inode*inode) inode->i_atime = be64_to_timespec(di->di_atime); inode->i_ctime = be64_to_timespec(di->di_ctime); inode->i_mtime = be64_to_timespec(di->di_mtime); - inode->i_nlink = be32_to_cpu(di->di_refcount); + set_nlink(inode, be32_to_cpu(di->di_refcount)); inode->i_generation = be32_to_cpu(di->di_generation); switch (inode->i_mode & S_IFMT) { diff --git a/fs/minix/inode.c b/fs/minix/inode.c index e7d23e25bf1d..64cdcd662ffc 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -446,7 +446,7 @@ static struct inode *V1_minix_iget(struct inode *inode) inode->i_mode = raw_inode->i_mode; inode->i_uid = (uid_t)raw_inode->i_uid; inode->i_gid = (gid_t)raw_inode->i_gid; - inode->i_nlink = raw_inode->i_nlinks; + set_nlink(inode, raw_inode->i_nlinks); inode->i_size = raw_inode->i_size; inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = raw_inode->i_time; inode->i_mtime.tv_nsec = 0; @@ -479,7 +479,7 @@ static struct inode *V2_minix_iget(struct inode *inode) inode->i_mode = raw_inode->i_mode; inode->i_uid = (uid_t)raw_inode->i_uid; inode->i_gid = (gid_t)raw_inode->i_gid; - inode->i_nlink = raw_inode->i_nlinks; + set_nlink(inode, raw_inode->i_nlinks); inode->i_size = raw_inode->i_size; inode->i_mtime.tv_sec = raw_inode->i_mtime; inode->i_atime.tv_sec = raw_inode->i_atime; diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 202f370526a7..5b5fa33b6b9d 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -228,7 +228,7 @@ static void ncp_set_attr(struct inode *inode, struct ncp_entry_info *nwinfo) DDPRINTK("ncp_read_inode: inode->i_mode = %u\n", inode->i_mode); - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_uid = server->m.uid; inode->i_gid = server->m.gid; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 1fc715acc2da..c07a55aec838 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -355,7 +355,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) | NFS_INO_INVALID_DATA | NFS_INO_REVAL_PAGECACHE; if (fattr->valid & NFS_ATTR_FATTR_NLINK) - inode->i_nlink = fattr->nlink; + set_nlink(inode, fattr->nlink); else if (nfs_server_capable(inode, NFS_CAP_NLINK)) nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_OWNER) @@ -1361,7 +1361,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_ATTR; if (S_ISDIR(inode->i_mode)) invalid |= NFS_INO_INVALID_DATA; - inode->i_nlink = fattr->nlink; + set_nlink(inode, fattr->nlink); } } else if (server->caps & NFS_CAP_NLINK) invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 08ac272b7c28..b50ffb72e5b3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -396,7 +396,7 @@ int nilfs_read_inode_common(struct inode *inode, inode->i_mode = le16_to_cpu(raw_inode->i_mode); inode->i_uid = (uid_t)le32_to_cpu(raw_inode->i_uid); inode->i_gid = (gid_t)le32_to_cpu(raw_inode->i_gid); - inode->i_nlink = le16_to_cpu(raw_inode->i_links_count); + set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le64_to_cpu(raw_inode->i_size); inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime); inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime); diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index a3141990061e..768982de10e4 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -289,7 +289,7 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) nilfs_warning(inode->i_sb, __func__, "deleting nonexistent file (%lu), %d\n", inode->i_ino, inode->i_nlink); - inode->i_nlink = 1; + set_nlink(inode, 1); } err = nilfs_delete_entry(de, page); if (err) diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 1371487da955..97e2dacbc867 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -612,7 +612,7 @@ static int ntfs_read_locked_inode(struct inode *vi) * might be tricky due to vfs interactions. Need to think about this * some more when implementing the unlink command. */ - vi->i_nlink = le16_to_cpu(m->link_count); + set_nlink(vi, le16_to_cpu(m->link_count)); /* * FIXME: Reparse points can have the directory bit set even though * they would be S_IFLNK. Need to deal with this further below when we @@ -634,7 +634,7 @@ static int ntfs_read_locked_inode(struct inode *vi) vi->i_mode &= ~vol->dmask; /* Things break without this kludge! */ if (vi->i_nlink > 1) - vi->i_nlink = 1; + set_nlink(vi, 1); } else { vi->i_mode |= S_IFREG; /* Apply the file permissions mask set in the mount options. */ @@ -1242,7 +1242,7 @@ static int ntfs_read_locked_attr_inode(struct inode *base_vi, struct inode *vi) vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; - vi->i_nlink = base_vi->i_nlink; + set_nlink(vi, base_vi->i_nlink); vi->i_mtime = base_vi->i_mtime; vi->i_ctime = base_vi->i_ctime; vi->i_atime = base_vi->i_atime; @@ -1508,7 +1508,7 @@ static int ntfs_read_locked_index_inode(struct inode *base_vi, struct inode *vi) vi->i_version = base_vi->i_version; vi->i_uid = base_vi->i_uid; vi->i_gid = base_vi->i_gid; - vi->i_nlink = base_vi->i_nlink; + set_nlink(vi, base_vi->i_nlink); vi->i_mtime = base_vi->i_mtime; vi->i_ctime = base_vi->i_ctime; vi->i_atime = base_vi->i_atime; diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 8582e3f4f120..e2878b5895fb 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -2292,7 +2292,7 @@ static int ocfs2_fill_new_dir_id(struct ocfs2_super *osb, ocfs2_journal_dirty(handle, di_bh); i_size_write(inode, size); - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_blocks = ocfs2_inode_sector_count(inode); ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); @@ -2354,7 +2354,7 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb, ocfs2_journal_dirty(handle, new_bh); i_size_write(inode, inode->i_sb->s_blocksize); - inode->i_nlink = 2; + set_nlink(inode, 2); inode->i_blocks = ocfs2_inode_sector_count(inode); status = ocfs2_mark_inode_dirty(handle, inode, fe_bh); if (status < 0) { diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 7642d7ca73e5..e1ed5e502ff2 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2092,7 +2092,7 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode) inode->i_uid = be32_to_cpu(lvb->lvb_iuid); inode->i_gid = be32_to_cpu(lvb->lvb_igid); inode->i_mode = be16_to_cpu(lvb->lvb_imode); - inode->i_nlink = be16_to_cpu(lvb->lvb_inlink); + set_nlink(inode, be16_to_cpu(lvb->lvb_inlink)); ocfs2_unpack_timespec(&inode->i_atime, be64_to_cpu(lvb->lvb_iatime_packed)); ocfs2_unpack_timespec(&inode->i_mtime, diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index b4c8bb6b8d28..a22d2c098890 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -291,7 +291,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)le64_to_cpu(fe->i_blkno)); - inode->i_nlink = ocfs2_read_links_count(fe); + set_nlink(inode, ocfs2_read_links_count(fe)); trace_ocfs2_populate_inode(OCFS2_I(inode)->ip_blkno, le32_to_cpu(fe->i_flags)); @@ -1290,7 +1290,7 @@ void ocfs2_refresh_inode(struct inode *inode, OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features); ocfs2_set_inode_flags(inode); i_size_write(inode, le64_to_cpu(fe->i_size)); - inode->i_nlink = ocfs2_read_links_count(fe); + set_nlink(inode, ocfs2_read_links_count(fe)); inode->i_uid = le32_to_cpu(fe->i_uid); inode->i_gid = le32_to_cpu(fe->i_gid); inode->i_mode = le16_to_cpu(fe->i_mode); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index ea0ecbdda58c..a8b2bfea574e 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -199,7 +199,7 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, int mode) * these are used by the support functions here and in * callers. */ if (S_ISDIR(mode)) - inode->i_nlink = 2; + set_nlink(inode, 2); inode_init_owner(inode, dir, mode); dquot_initialize(inode); return inode; @@ -2016,7 +2016,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb, orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; if (S_ISDIR(inode->i_mode)) ocfs2_add_links_count(orphan_fe, 1); - orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe); + set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe)); ocfs2_journal_dirty(handle, orphan_dir_bh); status = __ocfs2_add_entry(handle, orphan_dir_inode, name, @@ -2114,7 +2114,7 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data; if (S_ISDIR(inode->i_mode)) ocfs2_add_links_count(orphan_fe, -1); - orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe); + set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe)); ocfs2_journal_dirty(handle, orphan_dir_bh); leave: @@ -2435,7 +2435,7 @@ int ocfs2_mv_orphaned_inode_to_new(struct inode *dir, di = (struct ocfs2_dinode *)di_bh->b_data; le32_add_cpu(&di->i_flags, -OCFS2_ORPHANED_FL); di->i_orphaned_slot = 0; - inode->i_nlink = 1; + set_nlink(inode, 1); ocfs2_set_links_count(di, inode->i_nlink); ocfs2_journal_dirty(handle, di_bh); diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index a2a5bff774e3..e4e0ff7962e2 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -242,7 +242,7 @@ found: inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO; inode->i_op = &openprom_inode_operations; inode->i_fop = &openprom_operations; - inode->i_nlink = 2; + set_nlink(inode, 2); break; case op_inode_prop: if (!strcmp(dp->name, "options") && (len == 17) && @@ -251,7 +251,7 @@ found: else inode->i_mode = S_IFREG | S_IRUGO; inode->i_fop = &openpromfs_prop_ops; - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_size = ent_oi->u.prop->length; break; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 8f0087e20e16..851ba3dcdc29 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2248,7 +2248,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir, ei = PROC_I(inode); inode->i_mode = p->mode; if (S_ISDIR(inode->i_mode)) - inode->i_nlink = 2; /* Use getattr to fix if necessary */ + set_nlink(inode, 2); /* Use getattr to fix if necessary */ if (p->iop) inode->i_op = p->iop; if (p->fop) @@ -2642,7 +2642,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir, inode->i_mode = p->mode; if (S_ISDIR(inode->i_mode)) - inode->i_nlink = 2; + set_nlink(inode, 2); if (S_ISLNK(inode->i_mode)) inode->i_size = 64; if (p->iop) @@ -2981,8 +2981,8 @@ static struct dentry *proc_pid_instantiate(struct inode *dir, inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; - inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff, - ARRAY_SIZE(tgid_base_stuff)); + set_nlink(inode, 2 + pid_entry_count_dirs(tgid_base_stuff, + ARRAY_SIZE(tgid_base_stuff))); d_set_d_op(dentry, &pid_dentry_operations); @@ -3233,8 +3233,8 @@ static struct dentry *proc_task_instantiate(struct inode *dir, inode->i_fop = &proc_tid_base_operations; inode->i_flags|=S_IMMUTABLE; - inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff, - ARRAY_SIZE(tid_base_stuff)); + set_nlink(inode, 2 + pid_entry_count_dirs(tid_base_stuff, + ARRAY_SIZE(tid_base_stuff))); d_set_d_op(dentry, &pid_dentry_operations); diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 9d99131d0d65..10090d9c7ad5 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -283,7 +283,7 @@ static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry, struct inode *inode = dentry->d_inode; struct proc_dir_entry *de = PROC_I(inode)->pde; if (de && de->nlink) - inode->i_nlink = de->nlink; + set_nlink(inode, de->nlink); generic_fillattr(inode, stat); return 0; diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 7ed72d6c1c6f..7737c5468a40 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -445,7 +445,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) if (de->size) inode->i_size = de->size; if (de->nlink) - inode->i_nlink = de->nlink; + set_nlink(inode, de->nlink); if (de->proc_iops) inode->i_op = de->proc_iops; if (de->proc_fops) { diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 2b0646613f5a..3bdd21418432 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -379,7 +379,7 @@ struct inode *qnx4_iget(struct super_block *sb, unsigned long ino) inode->i_mode = le16_to_cpu(raw_inode->di_mode); inode->i_uid = (uid_t)le16_to_cpu(raw_inode->di_uid); inode->i_gid = (gid_t)le16_to_cpu(raw_inode->di_gid); - inode->i_nlink = le16_to_cpu(raw_inode->di_nlink); + set_nlink(inode, le16_to_cpu(raw_inode->di_nlink)); inode->i_size = le32_to_cpu(raw_inode->di_size); inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->di_mtime); inode->i_mtime.tv_nsec = 0; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index c425441c6942..950f13af0951 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1154,7 +1154,7 @@ static void init_inode(struct inode *inode, struct treepath *path) set_inode_item_key_version(inode, KEY_FORMAT_3_5); set_inode_sd_version(inode, STAT_DATA_V1); inode->i_mode = sd_v1_mode(sd); - inode->i_nlink = sd_v1_nlink(sd); + set_nlink(inode, sd_v1_nlink(sd)); inode->i_uid = sd_v1_uid(sd); inode->i_gid = sd_v1_gid(sd); inode->i_size = sd_v1_size(sd); @@ -1199,7 +1199,7 @@ static void init_inode(struct inode *inode, struct treepath *path) struct stat_data *sd = (struct stat_data *)B_I_PITEM(bh, ih); inode->i_mode = sd_v2_mode(sd); - inode->i_nlink = sd_v2_nlink(sd); + set_nlink(inode, sd_v2_nlink(sd)); inode->i_uid = sd_v2_uid(sd); inode->i_size = sd_v2_size(sd); inode->i_gid = sd_v2_gid(sd); @@ -1832,7 +1832,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, #endif /* fill stat data */ - inode->i_nlink = (S_ISDIR(mode) ? 2 : 1); + set_nlink(inode, (S_ISDIR(mode) ? 2 : 1)); /* uid and gid must already be set by the caller for quota init */ diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 6ce332821633..80058e8ce361 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -19,7 +19,7 @@ #include #include -#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) i->i_nlink=1; } +#define INC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) { inc_nlink(i); if (i->i_nlink >= REISERFS_LINK_MAX) set_nlink(i, 1); } #define DEC_DIR_INODE_NLINK(i) if (i->i_nlink != 1) drop_nlink(i); // directory item contains array of entry headers. This performs @@ -964,7 +964,7 @@ static int reiserfs_unlink(struct inode *dir, struct dentry *dentry) reiserfs_warning(inode->i_sb, "reiserfs-7042", "deleting nonexistent file (%lu), %d", inode->i_ino, inode->i_nlink); - inode->i_nlink = 1; + set_nlink(inode, 1); } drop_nlink(inode); diff --git a/fs/romfs/super.c b/fs/romfs/super.c index 2305e3121cb1..8b4089f30408 100644 --- a/fs/romfs/super.c +++ b/fs/romfs/super.c @@ -337,7 +337,7 @@ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) inode->i_metasize = (ROMFH_SIZE + nlen + 1 + ROMFH_PAD) & ROMFH_MASK; inode->i_dataoffset = pos + inode->i_metasize; - i->i_nlink = 1; /* Hard to decide.. */ + set_nlink(i, 1); /* Hard to decide.. */ i->i_size = be32_to_cpu(ri.size); i->i_mtime.tv_sec = i->i_atime.tv_sec = i->i_ctime.tv_sec = 0; i->i_mtime.tv_nsec = i->i_atime.tv_nsec = i->i_ctime.tv_nsec = 0; diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index 04bebcaa2373..fd7b3b3bda13 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -159,7 +159,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) frag_offset = 0; } - inode->i_nlink = 1; + set_nlink(inode, 1); inode->i_size = le32_to_cpu(sqsh_ino->file_size); inode->i_fop = &generic_ro_fops; inode->i_mode |= S_IFREG; @@ -203,7 +203,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) } xattr_id = le32_to_cpu(sqsh_ino->xattr); - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le64_to_cpu(sqsh_ino->file_size); inode->i_op = &squashfs_inode_ops; inode->i_fop = &generic_ro_fops; @@ -232,7 +232,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) if (err < 0) goto failed_read; - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le16_to_cpu(sqsh_ino->file_size); inode->i_op = &squashfs_dir_inode_ops; inode->i_fop = &squashfs_dir_ops; @@ -257,7 +257,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) goto failed_read; xattr_id = le32_to_cpu(sqsh_ino->xattr); - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->file_size); inode->i_op = &squashfs_dir_inode_ops; inode->i_fop = &squashfs_dir_ops; @@ -284,7 +284,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) if (err < 0) goto failed_read; - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); inode->i_op = &squashfs_symlink_inode_ops; inode->i_data.a_ops = &squashfs_symlink_aops; @@ -325,7 +325,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) inode->i_mode |= S_IFCHR; else inode->i_mode |= S_IFBLK; - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); rdev = le32_to_cpu(sqsh_ino->rdev); init_special_inode(inode, inode->i_mode, new_decode_dev(rdev)); @@ -349,7 +349,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) inode->i_mode |= S_IFBLK; xattr_id = le32_to_cpu(sqsh_ino->xattr); inode->i_op = &squashfs_inode_ops; - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); rdev = le32_to_cpu(sqsh_ino->rdev); init_special_inode(inode, inode->i_mode, new_decode_dev(rdev)); @@ -370,7 +370,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) inode->i_mode |= S_IFIFO; else inode->i_mode |= S_IFSOCK; - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); init_special_inode(inode, inode->i_mode, 0); break; } @@ -389,7 +389,7 @@ int squashfs_read_inode(struct inode *inode, long long ino) inode->i_mode |= S_IFSOCK; xattr_id = le32_to_cpu(sqsh_ino->xattr); inode->i_op = &squashfs_inode_ops; - inode->i_nlink = le32_to_cpu(sqsh_ino->nlink); + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); init_special_inode(inode, inode->i_mode, 0); break; } diff --git a/fs/stack.c b/fs/stack.c index b4f2ab48a61f..9c11519245a6 100644 --- a/fs/stack.c +++ b/fs/stack.c @@ -71,6 +71,6 @@ void fsstack_copy_attr_all(struct inode *dest, const struct inode *src) dest->i_ctime = src->i_ctime; dest->i_blkbits = src->i_blkbits; dest->i_flags = src->i_flags; - dest->i_nlink = src->i_nlink; + set_nlink(dest, src->i_nlink); } EXPORT_SYMBOL_GPL(fsstack_copy_attr_all); diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index e23f28894a3a..c81b22f3ace1 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -218,7 +218,7 @@ static void sysfs_refresh_inode(struct sysfs_dirent *sd, struct inode *inode) } if (sysfs_type(sd) == SYSFS_DIR) - inode->i_nlink = sd->s_dir.subdirs + 2; + set_nlink(inode, sd->s_dir.subdirs + 2); } int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 0630eb969a28..25ffb3e9a3f8 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -219,7 +219,7 @@ struct inode *sysv_iget(struct super_block *sb, unsigned int ino) inode->i_mode = fs16_to_cpu(sbi, raw_inode->i_mode); inode->i_uid = (uid_t)fs16_to_cpu(sbi, raw_inode->i_uid); inode->i_gid = (gid_t)fs16_to_cpu(sbi, raw_inode->i_gid); - inode->i_nlink = fs16_to_cpu(sbi, raw_inode->i_nlink); + set_nlink(inode, fs16_to_cpu(sbi, raw_inode->i_nlink)); inode->i_size = fs32_to_cpu(sbi, raw_inode->i_size); inode->i_atime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_atime); inode->i_mtime.tv_sec = fs32_to_cpu(sbi, raw_inode->i_mtime); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index b28121278d46..20403dc5d437 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -129,7 +129,7 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) goto out_ino; inode->i_flags |= (S_NOCMTIME | S_NOATIME); - inode->i_nlink = le32_to_cpu(ino->nlink); + set_nlink(inode, le32_to_cpu(ino->nlink)); inode->i_uid = le32_to_cpu(ino->uid); inode->i_gid = le32_to_cpu(ino->gid); inode->i_atime.tv_sec = (int64_t)le64_to_cpu(ino->atime_sec); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 993adc8f1c87..bf18f7a04544 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -561,7 +561,7 @@ int ubifs_removexattr(struct dentry *dentry, const char *name) clear_nlink(inode); err = remove_xattr(c, host, inode, &nm); if (err) - inode->i_nlink = 1; + set_nlink(inode, 1); /* If @i_nlink is 0, 'iput()' will delete the inode */ iput(inode); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 1d1358ed80c1..6e73f1d6e93c 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1236,6 +1236,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh) int offset; struct udf_sb_info *sbi = UDF_SB(inode->i_sb); struct udf_inode_info *iinfo = UDF_I(inode); + unsigned int link_count; fe = (struct fileEntry *)bh->b_data; efe = (struct extendedFileEntry *)bh->b_data; @@ -1318,9 +1319,10 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh) inode->i_mode &= ~sbi->s_umask; read_unlock(&sbi->s_cred_lock); - inode->i_nlink = le16_to_cpu(fe->fileLinkCount); - if (!inode->i_nlink) - inode->i_nlink = 1; + link_count = le16_to_cpu(fe->fileLinkCount); + if (!link_count) + link_count = 1; + set_nlink(inode, link_count); inode->i_size = le64_to_cpu(fe->informationLength); iinfo->i_lenExtents = inode->i_size; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index e8d61b114c1b..f1c64c6a4532 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -667,7 +667,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, int mode) iput(inode); goto out; } - inode->i_nlink = 2; + set_nlink(inode, 2); cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); cfi.icb.extLocation = cpu_to_lelb(dinfo->i_location); *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = @@ -837,7 +837,7 @@ static int udf_unlink(struct inode *dir, struct dentry *dentry) if (!inode->i_nlink) { udf_debug("Deleting nonexistent file (%lu), %d\n", inode->i_ino, inode->i_nlink); - inode->i_nlink = 1; + set_nlink(inode, 1); } retval = udf_delete_entry(dir, fi, &fibh, &cfi); if (retval) diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index b4d791a83207..879b13436fa4 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -589,7 +589,7 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode) * Copy data to the in-core inode. */ inode->i_mode = mode = fs16_to_cpu(sb, ufs_inode->ui_mode); - inode->i_nlink = fs16_to_cpu(sb, ufs_inode->ui_nlink); + set_nlink(inode, fs16_to_cpu(sb, ufs_inode->ui_nlink)); if (inode->i_nlink == 0) { ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino); return -1; @@ -637,7 +637,7 @@ static int ufs2_read_inode(struct inode *inode, struct ufs2_inode *ufs2_inode) * Copy data to the in-core inode. */ inode->i_mode = mode = fs16_to_cpu(sb, ufs2_inode->ui_mode); - inode->i_nlink = fs16_to_cpu(sb, ufs2_inode->ui_nlink); + set_nlink(inode, fs16_to_cpu(sb, ufs2_inode->ui_nlink)); if (inode->i_nlink == 0) { ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino); return -1; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 9ba2a07b7343..23ce927973a4 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1153,7 +1153,7 @@ xfs_setup_inode( hlist_add_fake(&inode->i_hash); inode->i_mode = ip->i_d.di_mode; - inode->i_nlink = ip->i_d.di_nlink; + set_nlink(inode, ip->i_d.di_nlink); inode->i_uid = ip->i_d.di_uid; inode->i_gid = ip->i_d.di_gid; diff --git a/include/linux/fs.h b/include/linux/fs.h index 7a049fd2aa4c..48c1f5fc7411 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1754,6 +1754,19 @@ static inline void mark_inode_dirty_sync(struct inode *inode) __mark_inode_dirty(inode, I_DIRTY_SYNC); } +/** + * set_nlink - directly set an inode's link count + * @inode: inode + * @nlink: new nlink (should be non-zero) + * + * This is a low-level filesystem helper to replace any + * direct filesystem manipulation of i_nlink. + */ +static inline void set_nlink(struct inode *inode, unsigned int nlink) +{ + inode->i_nlink = nlink; +} + /** * inc_nlink - directly increment an inode's link count * @inode: inode -- cgit v1.2.3