From d47992f86b307985b3215bcf141d56d1849d71df Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 21 May 2013 23:17:23 -0400 Subject: mm: change invalidatepage prototype to accept length Currently there is no way to truncate partial page where the end truncate point is not at the end of the page. This is because it was not needed and the functionality was enough for file system truncate operation to work properly. However more file systems now support punch hole feature and it can benefit from mm supporting truncating page just up to the certain point. Specifically, with this functionality truncate_inode_pages_range() can be changed so it supports truncating partial page at the end of the range (currently it will BUG_ON() if 'end' is not at the end of the page). This commit changes the invalidatepage() address space operation prototype to accept range to be invalidated and update all the instances for it. We also change the block_invalidatepage() in the same way and actually make a use of the new length argument implementing range invalidation. Actual file system implementations will follow except the file systems where the changes are really simple and should not change the behaviour in any way .Implementation for truncate_page_range() which will be able to accept page unaligned ranges will follow as well. Signed-off-by: Lukas Czerner Cc: Andrew Morton Cc: Hugh Dickins --- include/linux/buffer_head.h | 3 ++- include/linux/fs.h | 2 +- include/linux/mm.h | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 9e52b0626b39..f5a3b838ddb0 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -198,7 +198,8 @@ extern int buffer_heads_over_limit; * Generic address_space_operations implementations for buffer_head-backed * address_spaces. */ -void block_invalidatepage(struct page *page, unsigned long offset); +void block_invalidatepage(struct page *page, unsigned int offset, + unsigned int length); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int block_write_full_page_endio(struct page *page, get_block_t *get_block, diff --git a/include/linux/fs.h b/include/linux/fs.h index 43db02e9c9fa..9f696014988d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -364,7 +364,7 @@ struct address_space_operations { /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); - void (*invalidatepage) (struct page *, unsigned long); + void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, diff --git a/include/linux/mm.h b/include/linux/mm.h index e0c8528a41a4..66d881f1d576 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1041,7 +1041,8 @@ int get_kernel_page(unsigned long start, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); -extern void do_invalidatepage(struct page *page, unsigned long offset); +extern void do_invalidatepage(struct page *page, unsigned int offset, + unsigned int length); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); -- cgit v1.2.3-58-ga151 From 259709b07da103edc40b8c5bdb2d5c0e77374f94 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 21 May 2013 23:20:03 -0400 Subject: jbd2: change jbd2_journal_invalidatepage to accept length invalidatepage now accepts range to invalidate and there are two file system using jbd2 also implementing punch hole feature which can benefit from this. We need to implement the same thing for jbd2 layer in order to allow those file system take benefit of this functionality. This commit adds length argument to the jbd2_journal_invalidatepage() and updates all instances in ext4 and ocfs2. Signed-off-by: Lukas Czerner Reviewed-by: Jan Kara --- fs/ext4/inode.c | 3 ++- fs/jbd2/transaction.c | 24 +++++++++++++++++------- fs/ocfs2/aops.c | 3 ++- include/linux/jbd2.h | 2 +- 4 files changed, 22 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 19d6ca27c879..694645e51fe0 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3015,7 +3015,8 @@ static int __ext4_journalled_invalidatepage(struct page *page, if (offset == 0) ClearPageChecked(page); - return jbd2_journal_invalidatepage(journal, page, offset); + return jbd2_journal_invalidatepage(journal, page, offset, + PAGE_CACHE_SIZE - offset); } /* Wrapper for aops... */ diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 10f524c59ea8..5d8268ad364a 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2034,18 +2034,23 @@ zap_buffer_unlocked: * void jbd2_journal_invalidatepage() * @journal: journal to use for flush... * @page: page to flush - * @offset: length of page to invalidate. + * @offset: start of the range to invalidate + * @length: length of the range to invalidate * - * Reap page buffers containing data after offset in page. Can return -EBUSY - * if buffers are part of the committing transaction and the page is straddling - * i_size. Caller then has to wait for current commit and try again. + * Reap page buffers containing data after in the specified range in page. + * Can return -EBUSY if buffers are part of the committing transaction and + * the page is straddling i_size. Caller then has to wait for current commit + * and try again. */ int jbd2_journal_invalidatepage(journal_t *journal, struct page *page, - unsigned long offset) + unsigned int offset, + unsigned int length) { struct buffer_head *head, *bh, *next; + unsigned int stop = offset + length; unsigned int curr_off = 0; + int partial_page = (offset || length < PAGE_CACHE_SIZE); int may_free = 1; int ret = 0; @@ -2054,6 +2059,8 @@ int jbd2_journal_invalidatepage(journal_t *journal, if (!page_has_buffers(page)) return 0; + BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + /* We will potentially be playing with lists other than just the * data lists (especially for journaled data mode), so be * cautious in our locking. */ @@ -2063,10 +2070,13 @@ int jbd2_journal_invalidatepage(journal_t *journal, unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; + if (next_off > stop) + return 0; + if (offset <= curr_off) { /* This block is wholly outside the truncation point */ lock_buffer(bh); - ret = journal_unmap_buffer(journal, bh, offset > 0); + ret = journal_unmap_buffer(journal, bh, partial_page); unlock_buffer(bh); if (ret < 0) return ret; @@ -2077,7 +2087,7 @@ int jbd2_journal_invalidatepage(journal_t *journal, } while (bh != head); - if (!offset) { + if (!partial_page) { if (may_free && try_to_free_buffers(page)) J_ASSERT(!page_has_buffers(page)); } diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index ecb86ca8b1f1..7c477559f38e 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -608,7 +608,8 @@ static void ocfs2_invalidatepage(struct page *page, unsigned int offset, { journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal; - jbd2_journal_invalidatepage(journal, page, offset); + jbd2_journal_invalidatepage(journal, page, offset, + PAGE_CACHE_SIZE - offset); } static int ocfs2_releasepage(struct page *page, gfp_t wait) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 6e051f472edb..682a63c34d26 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1090,7 +1090,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern void journal_sync_buffer (struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, - struct page *, unsigned long); + struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush (journal_t *); -- cgit v1.2.3-58-ga151 From ca99fdd26b450cfc1dbcb6b01e1753ee5e6c88e0 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 21 May 2013 23:25:01 -0400 Subject: ext4: use ->invalidatepage() length argument ->invalidatepage() aop now accepts range to invalidate so we can make use of it in all ext4 invalidatepage routines. Signed-off-by: Lukas Czerner Reviewed-by: Jan Kara --- fs/ext4/inode.c | 30 +++++++++++++++++++----------- include/trace/events/ext4.h | 22 ++++++++++++---------- 2 files changed, 31 insertions(+), 21 deletions(-) (limited to 'include') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 694645e51fe0..11638d7982c9 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1416,21 +1416,28 @@ static void ext4_da_release_space(struct inode *inode, int to_free) } static void ext4_da_page_release_reservation(struct page *page, - unsigned long offset) + unsigned int offset, + unsigned int length) { 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); + unsigned int stop = offset + length; int num_clusters; ext4_fsblk_t lblk; + BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + head = page_buffers(page); bh = head; do { unsigned int next_off = curr_off + bh->b_size; + if (next_off > stop) + break; + if ((offset <= curr_off) && (buffer_delay(bh))) { to_release++; clear_buffer_delay(bh); @@ -2840,7 +2847,7 @@ static void ext4_da_invalidatepage(struct page *page, unsigned int offset, if (!page_has_buffers(page)) goto out; - ext4_da_page_release_reservation(page, offset); + ext4_da_page_release_reservation(page, offset, length); out: ext4_invalidatepage(page, offset, length); @@ -2994,29 +3001,29 @@ ext4_readpages(struct file *file, struct address_space *mapping, static void ext4_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { - trace_ext4_invalidatepage(page, offset); + trace_ext4_invalidatepage(page, offset, length); /* No journalling happens on data buffers when this function is used */ WARN_ON(page_has_buffers(page) && buffer_jbd(page_buffers(page))); - block_invalidatepage(page, offset, PAGE_CACHE_SIZE - offset); + block_invalidatepage(page, offset, length); } static int __ext4_journalled_invalidatepage(struct page *page, - unsigned long offset) + unsigned int offset, + unsigned int length) { journal_t *journal = EXT4_JOURNAL(page->mapping->host); - trace_ext4_journalled_invalidatepage(page, offset); + trace_ext4_journalled_invalidatepage(page, offset, length); /* * If it's a full truncate we just forget about the pending dirtying */ - if (offset == 0) + if (offset == 0 && length == PAGE_CACHE_SIZE) ClearPageChecked(page); - return jbd2_journal_invalidatepage(journal, page, offset, - PAGE_CACHE_SIZE - offset); + return jbd2_journal_invalidatepage(journal, page, offset, length); } /* Wrapper for aops... */ @@ -3024,7 +3031,7 @@ static void ext4_journalled_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { - WARN_ON(__ext4_journalled_invalidatepage(page, offset) < 0); + WARN_ON(__ext4_journalled_invalidatepage(page, offset, length) < 0); } static int ext4_releasepage(struct page *page, gfp_t wait) @@ -4628,7 +4635,8 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) inode->i_size >> PAGE_CACHE_SHIFT); if (!page) return; - ret = __ext4_journalled_invalidatepage(page, offset); + ret = __ext4_journalled_invalidatepage(page, offset, + PAGE_CACHE_SIZE - offset); unlock_page(page); page_cache_release(page); if (ret != -EBUSY) diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 8ee15b97cd38..dcfce96c08a8 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -444,16 +444,16 @@ DEFINE_EVENT(ext4__page_op, ext4_releasepage, ); DECLARE_EVENT_CLASS(ext4_invalidatepage_op, - TP_PROTO(struct page *page, unsigned long offset), + TP_PROTO(struct page *page, unsigned int offset, unsigned int length), - TP_ARGS(page, offset), + TP_ARGS(page, offset, length), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( pgoff_t, index ) - __field( unsigned long, offset ) - + __field( unsigned int, offset ) + __field( unsigned int, length ) ), TP_fast_assign( @@ -461,24 +461,26 @@ DECLARE_EVENT_CLASS(ext4_invalidatepage_op, __entry->ino = page->mapping->host->i_ino; __entry->index = page->index; __entry->offset = offset; + __entry->length = length; ), - TP_printk("dev %d,%d ino %lu page_index %lu offset %lu", + TP_printk("dev %d,%d ino %lu page_index %lu offset %u length %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - (unsigned long) __entry->index, __entry->offset) + (unsigned long) __entry->index, + __entry->offset, __entry->length) ); DEFINE_EVENT(ext4_invalidatepage_op, ext4_invalidatepage, - TP_PROTO(struct page *page, unsigned long offset), + TP_PROTO(struct page *page, unsigned int offset, unsigned int length), - TP_ARGS(page, offset) + TP_ARGS(page, offset, length) ); DEFINE_EVENT(ext4_invalidatepage_op, ext4_journalled_invalidatepage, - TP_PROTO(struct page *page, unsigned long offset), + TP_PROTO(struct page *page, unsigned int offset, unsigned int length), - TP_ARGS(page, offset) + TP_ARGS(page, offset, length) ); TRACE_EVENT(ext4_discard_blocks, -- cgit v1.2.3-58-ga151 From d8c8900ac113d2b2b3d382acda198b4ae29b1b51 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Tue, 21 May 2013 23:26:36 -0400 Subject: jbd: change journal_invalidatepage() to accept length ->invalidatepage() aop now accepts range to invalidate so we can make use of it in journal_invalidatepage() and all the users in ext3 file system. Also update ext3 trace point to print out length argument. Signed-off-by: Lukas Czerner Reviewed-by: Jan Kara --- fs/ext3/inode.c | 6 +++--- fs/jbd/transaction.c | 19 ++++++++++++++----- include/linux/jbd.h | 2 +- include/trace/events/ext3.h | 12 +++++++----- 4 files changed, 25 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index b6e5934f5dd6..f67668f724ba 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1830,15 +1830,15 @@ static void ext3_invalidatepage(struct page *page, unsigned int offset, { journal_t *journal = EXT3_JOURNAL(page->mapping->host); - trace_ext3_invalidatepage(page, offset); + trace_ext3_invalidatepage(page, offset, length); /* * If it's a full truncate we just forget about the pending dirtying */ - if (offset == 0) + if (offset == 0 && length == PAGE_CACHE_SIZE) ClearPageChecked(page); - journal_invalidatepage(journal, page, offset); + journal_invalidatepage(journal, page, offset, length); } static int ext3_releasepage(struct page *page, gfp_t wait) diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index e3e255c0a509..be0c39b66fe0 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -2019,16 +2019,20 @@ zap_buffer_unlocked: * void journal_invalidatepage() - invalidate a journal page * @journal: journal to use for flush * @page: page to flush - * @offset: length of page to invalidate. + * @offset: offset of the range to invalidate + * @length: length of the range to invalidate * - * Reap page buffers containing data after offset in page. + * Reap page buffers containing data in specified range in page. */ void journal_invalidatepage(journal_t *journal, struct page *page, - unsigned long offset) + unsigned int offset, + unsigned int length) { struct buffer_head *head, *bh, *next; + unsigned int stop = offset + length; unsigned int curr_off = 0; + int partial_page = (offset || length < PAGE_CACHE_SIZE); int may_free = 1; if (!PageLocked(page)) @@ -2036,6 +2040,8 @@ void journal_invalidatepage(journal_t *journal, if (!page_has_buffers(page)) return; + BUG_ON(stop > PAGE_CACHE_SIZE || stop < length); + /* We will potentially be playing with lists other than just the * data lists (especially for journaled data mode), so be * cautious in our locking. */ @@ -2045,11 +2051,14 @@ void journal_invalidatepage(journal_t *journal, unsigned int next_off = curr_off + bh->b_size; next = bh->b_this_page; + if (next_off > stop) + return; + if (offset <= curr_off) { /* This block is wholly outside the truncation point */ lock_buffer(bh); may_free &= journal_unmap_buffer(journal, bh, - offset > 0); + partial_page); unlock_buffer(bh); } curr_off = next_off; @@ -2057,7 +2066,7 @@ void journal_invalidatepage(journal_t *journal, } while (bh != head); - if (!offset) { + if (!partial_page) { if (may_free && try_to_free_buffers(page)) J_ASSERT(!page_has_buffers(page)); } diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 7e0b622503c4..9c505f1aa1fd 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -840,7 +840,7 @@ extern void journal_release_buffer (handle_t *, struct buffer_head *); extern int journal_forget (handle_t *, struct buffer_head *); extern void journal_sync_buffer (struct buffer_head *); extern void journal_invalidatepage(journal_t *, - struct page *, unsigned long); + struct page *, unsigned int, unsigned int); extern int journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); extern int journal_stop(handle_t *); extern int journal_flush (journal_t *); diff --git a/include/trace/events/ext3.h b/include/trace/events/ext3.h index 15d11a39be47..6797b9de90ed 100644 --- a/include/trace/events/ext3.h +++ b/include/trace/events/ext3.h @@ -290,13 +290,14 @@ DEFINE_EVENT(ext3__page_op, ext3_releasepage, ); TRACE_EVENT(ext3_invalidatepage, - TP_PROTO(struct page *page, unsigned long offset), + TP_PROTO(struct page *page, unsigned int offset, unsigned int length), - TP_ARGS(page, offset), + TP_ARGS(page, offset, length), TP_STRUCT__entry( __field( pgoff_t, index ) - __field( unsigned long, offset ) + __field( unsigned int, offset ) + __field( unsigned int, length ) __field( ino_t, ino ) __field( dev_t, dev ) @@ -305,14 +306,15 @@ TRACE_EVENT(ext3_invalidatepage, TP_fast_assign( __entry->index = page->index; __entry->offset = offset; + __entry->length = length; __entry->ino = page->mapping->host->i_ino; __entry->dev = page->mapping->host->i_sb->s_dev; ), - TP_printk("dev %d,%d ino %lu page_index %lu offset %lu", + TP_printk("dev %d,%d ino %lu page_index %lu offset %u length %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->index, __entry->offset) + __entry->index, __entry->offset, __entry->length) ); TRACE_EVENT(ext3_discard_blocks, -- cgit v1.2.3-58-ga151 From 61801325f790ea15ba0630a7a26bd80a0741813f Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Mon, 27 May 2013 23:32:35 -0400 Subject: ext4: update ext4_ext_remove_space trace point Add "end" variable. Signed-off-by: Lukas Czerner Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 6 +++--- include/trace/events/ext4.h | 21 ++++++++++++++------- 2 files changed, 17 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 18c3f1a131b3..fb9b41483c86 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2663,7 +2663,7 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, return PTR_ERR(handle); again: - trace_ext4_ext_remove_space(inode, start, depth); + trace_ext4_ext_remove_space(inode, start, end, depth); /* * Check if we are removing extents inside the extent tree. If that @@ -2831,8 +2831,8 @@ again: } } - trace_ext4_ext_remove_space_done(inode, start, depth, partial_cluster, - path->p_hdr->eh_entries); + trace_ext4_ext_remove_space_done(inode, start, end, 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 diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index dcfce96c08a8..bcb5a021945c 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -2027,14 +2027,16 @@ TRACE_EVENT(ext4_ext_rm_idx, ); TRACE_EVENT(ext4_ext_remove_space, - TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth), + TP_PROTO(struct inode *inode, ext4_lblk_t start, + ext4_lblk_t end, int depth), - TP_ARGS(inode, start, depth), + TP_ARGS(inode, start, end, depth), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) + __field( ext4_lblk_t, end ) __field( int, depth ) ), @@ -2042,26 +2044,29 @@ TRACE_EVENT(ext4_ext_remove_space, __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; + __entry->end = end; __entry->depth = depth; ), - TP_printk("dev %d,%d ino %lu since %u depth %d", + TP_printk("dev %d,%d ino %lu since %u end %u depth %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, + (unsigned) __entry->end, __entry->depth) ); TRACE_EVENT(ext4_ext_remove_space_done, - TP_PROTO(struct inode *inode, ext4_lblk_t start, int depth, - ext4_lblk_t partial, __le16 eh_entries), + TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, + int depth, ext4_lblk_t partial, __le16 eh_entries), - TP_ARGS(inode, start, depth, partial, eh_entries), + TP_ARGS(inode, start, end, depth, partial, eh_entries), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) __field( ext4_lblk_t, start ) + __field( ext4_lblk_t, end ) __field( int, depth ) __field( ext4_lblk_t, partial ) __field( unsigned short, eh_entries ) @@ -2071,16 +2076,18 @@ TRACE_EVENT(ext4_ext_remove_space_done, __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->start = start; + __entry->end = end; __entry->depth = depth; __entry->partial = partial; __entry->eh_entries = le16_to_cpu(eh_entries); ), - TP_printk("dev %d,%d ino %lu since %u depth %d partial %u " + TP_printk("dev %d,%d ino %lu since %u end %u depth %d partial %u " "remaining_entries %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, + (unsigned) __entry->end, __entry->depth, (unsigned) __entry->partial, (unsigned short) __entry->eh_entries) -- cgit v1.2.3-58-ga151 From d23142c6271c499d913d0d5e668b5a4eb6dafcb0 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Mon, 27 May 2013 23:33:35 -0400 Subject: ext4: make punch hole code path work with bigalloc Currently punch hole is disabled in file systems with bigalloc feature enabled. However the recent changes in punch hole patch should make it easier to support punching holes on bigalloc enabled file systems. This commit changes partial_cluster handling in ext4_remove_blocks(), ext4_ext_rm_leaf() and ext4_ext_remove_space(). Currently partial_cluster is unsigned long long type and it makes sure that we will free the partial cluster if all extents has been released from that cluster. However it has been specifically designed only for truncate. With punch hole we can be freeing just some extents in the cluster leaving the rest untouched. So we have to make sure that we will notice cluster which still has some extents. To do this I've changed partial_cluster to be signed long long type. The only scenario where this could be a problem is when cluster_size == block size, however in that case there would not be any partial clusters so we're safe. For bigger clusters the signed type is enough. Now we use the negative value in partial_cluster to mark such cluster used, hence we know that we must not free it even if all other extents has been freed from such cluster. This scenario can be described in simple diagram: |FFF...FF..FF.UUU| ^----------^ punch hole . - free space | - cluster boundary F - freed extent U - used extent Also update respective tracepoints to use signed long long type for partial_cluster. Signed-off-by: Lukas Czerner Reviewed-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 69 +++++++++++++++++++++++++++++++++------------ include/trace/events/ext4.h | 25 ++++++++-------- 2 files changed, 64 insertions(+), 30 deletions(-) (limited to 'include') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index fb9b41483c86..214e68a5e79f 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2359,7 +2359,7 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_extent *ex, - ext4_fsblk_t *partial_cluster, + long long *partial_cluster, ext4_lblk_t from, ext4_lblk_t to) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -2388,7 +2388,8 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, * partial cluster here. */ pblk = ext4_ext_pblock(ex) + ee_len - 1; - if (*partial_cluster && (EXT4_B2C(sbi, pblk) != *partial_cluster)) { + if ((*partial_cluster > 0) && + (EXT4_B2C(sbi, pblk) != *partial_cluster)) { ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, *partial_cluster), sbi->s_cluster_ratio, flags); @@ -2414,23 +2415,41 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, && to == le32_to_cpu(ex->ee_block) + ee_len - 1) { /* tail removal */ ext4_lblk_t num; + unsigned int unaligned; num = le32_to_cpu(ex->ee_block) + ee_len - from; pblk = ext4_ext_pblock(ex) + ee_len - num; - ext_debug("free last %u blocks starting %llu\n", num, pblk); + /* + * Usually we want to free partial cluster at the end of the + * extent, except for the situation when the cluster is still + * used by any other extent (partial_cluster is negative). + */ + if (*partial_cluster < 0 && + -(*partial_cluster) == EXT4_B2C(sbi, pblk + num - 1)) + flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER; + + ext_debug("free last %u blocks starting %llu partial %lld\n", + num, pblk, *partial_cluster); ext4_free_blocks(handle, inode, NULL, pblk, num, flags); /* * If the block range to be freed didn't start at the * beginning of a cluster, and we removed the entire - * extent, save the partial cluster here, since we - * might need to delete if we determine that the - * truncate operation has removed all of the blocks in - * the cluster. + * extent and the cluster is not used by any other extent, + * save the partial cluster here, since we might need to + * delete if we determine that the truncate operation has + * removed all of the blocks in the cluster. + * + * On the other hand, if we did not manage to free the whole + * extent, we have to mark the cluster as used (store negative + * cluster number in partial_cluster). */ - if (pblk & (sbi->s_cluster_ratio - 1) && - (ee_len == num)) + unaligned = pblk & (sbi->s_cluster_ratio - 1); + if (unaligned && (ee_len == num) && + (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk)))) *partial_cluster = EXT4_B2C(sbi, pblk); - else + else if (unaligned) + *partial_cluster = -((long long)EXT4_B2C(sbi, pblk)); + else if (*partial_cluster > 0) *partial_cluster = 0; } else ext4_error(sbi->s_sb, "strange request: removal(2) " @@ -2448,12 +2467,16 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, * @handle: The journal handle * @inode: The files inode * @path: The path to the leaf + * @partial_cluster: The cluster which we'll have to free if all extents + * has been released from it. It gets negative in case + * that the cluster is still used. * @start: The first block to remove * @end: The last block to remove */ static int ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, - struct ext4_ext_path *path, ext4_fsblk_t *partial_cluster, + struct ext4_ext_path *path, + long long *partial_cluster, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -2466,6 +2489,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, unsigned short ex_ee_len; unsigned uninitialized = 0; struct ext4_extent *ex; + ext4_fsblk_t pblk; /* the header must be checked already in ext4_ext_remove_space() */ ext_debug("truncate since %u in leaf to %u\n", start, end); @@ -2504,6 +2528,16 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, /* If this extent is beyond the end of the hole, skip it */ if (end < ex_ee_block) { + /* + * We're going to skip this extent and move to another, + * so if this extent is not cluster aligned we have + * to mark the current cluster as used to avoid + * accidentally freeing it later on + */ + pblk = ext4_ext_pblock(ex); + if (pblk & (sbi->s_cluster_ratio - 1)) + *partial_cluster = + -((long long)EXT4_B2C(sbi, pblk)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); @@ -2579,7 +2613,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, sizeof(struct ext4_extent)); } le16_add_cpu(&eh->eh_entries, -1); - } else + } else if (*partial_cluster > 0) *partial_cluster = 0; err = ext4_ext_dirty(handle, inode, path + depth); @@ -2597,11 +2631,10 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, err = ext4_ext_correct_indexes(handle, inode, path); /* - * If there is still a entry in the leaf node, check to see if - * it references the partial cluster. This is the only place - * where it could; if it doesn't, we can free the cluster. + * Free the partial cluster only if the current extent does not + * reference it. Otherwise we might free used cluster. */ - if (*partial_cluster && ex >= EXT_FIRST_EXTENT(eh) && + if (*partial_cluster > 0 && (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) != *partial_cluster)) { int flags = EXT4_FREE_BLOCKS_FORGET; @@ -2651,7 +2684,7 @@ int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, struct super_block *sb = inode->i_sb; int depth = ext_depth(inode); struct ext4_ext_path *path = NULL; - ext4_fsblk_t partial_cluster = 0; + long long partial_cluster = 0; handle_t *handle; int i = 0, err = 0; @@ -2837,7 +2870,7 @@ 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) { + if (partial_cluster > 0 && path->p_hdr->eh_entries == 0) { int flags = EXT4_FREE_BLOCKS_FORGET; if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index bcb5a021945c..e23b2188110a 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -1928,7 +1928,7 @@ TRACE_EVENT(ext4_ext_show_extent, 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), + long long partial_cluster), TP_ARGS(inode, ex, from, to, partial_cluster), @@ -1937,7 +1937,7 @@ TRACE_EVENT(ext4_remove_blocks, __field( ino_t, ino ) __field( ext4_lblk_t, from ) __field( ext4_lblk_t, to ) - __field( ext4_fsblk_t, partial ) + __field( long long, partial ) __field( ext4_fsblk_t, ee_pblk ) __field( ext4_lblk_t, ee_lblk ) __field( unsigned short, ee_len ) @@ -1955,7 +1955,7 @@ TRACE_EVENT(ext4_remove_blocks, ), TP_printk("dev %d,%d ino %lu extent [%u(%llu), %u]" - "from %u to %u partial_cluster %u", + "from %u to %u partial_cluster %lld", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->ee_lblk, @@ -1963,19 +1963,20 @@ TRACE_EVENT(ext4_remove_blocks, (unsigned short) __entry->ee_len, (unsigned) __entry->from, (unsigned) __entry->to, - (unsigned) __entry->partial) + (long long) __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), + struct ext4_extent *ex, + long long partial_cluster), TP_ARGS(inode, start, ex, partial_cluster), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) - __field( ext4_fsblk_t, partial ) + __field( long long, partial ) __field( ext4_lblk_t, start ) __field( ext4_lblk_t, ee_lblk ) __field( ext4_fsblk_t, ee_pblk ) @@ -1993,14 +1994,14 @@ TRACE_EVENT(ext4_ext_rm_leaf, ), TP_printk("dev %d,%d ino %lu start_lblk %u last_extent [%u(%llu), %u]" - "partial_cluster %u", + "partial_cluster %lld", 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) + (long long) __entry->partial) ); TRACE_EVENT(ext4_ext_rm_idx, @@ -2058,7 +2059,7 @@ TRACE_EVENT(ext4_ext_remove_space, TRACE_EVENT(ext4_ext_remove_space_done, TP_PROTO(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end, - int depth, ext4_lblk_t partial, __le16 eh_entries), + int depth, long long partial, __le16 eh_entries), TP_ARGS(inode, start, end, depth, partial, eh_entries), @@ -2068,7 +2069,7 @@ TRACE_EVENT(ext4_ext_remove_space_done, __field( ext4_lblk_t, start ) __field( ext4_lblk_t, end ) __field( int, depth ) - __field( ext4_lblk_t, partial ) + __field( long long, partial ) __field( unsigned short, eh_entries ) ), @@ -2082,14 +2083,14 @@ TRACE_EVENT(ext4_ext_remove_space_done, __entry->eh_entries = le16_to_cpu(eh_entries); ), - TP_printk("dev %d,%d ino %lu since %u end %u depth %d partial %u " + TP_printk("dev %d,%d ino %lu since %u end %u depth %d partial %lld " "remaining_entries %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, (unsigned) __entry->start, (unsigned) __entry->end, __entry->depth, - (unsigned) __entry->partial, + (long long) __entry->partial, (unsigned short) __entry->eh_entries) ); -- cgit v1.2.3-58-ga151 From f5113effc2a2ee6b86a4b345ce557353dcbcfffe Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:01:45 -0400 Subject: jbd2: don't create journal_head for temporary journal buffers When writing metadata to the journal, we create temporary buffer heads for that task. We also attach journal heads to these buffer heads but the only purpose of the journal heads is to keep buffers linked in transaction's BJ_IO list. We remove the need for journal heads by reusing buffer_head's b_assoc_buffers list for that purpose. Also since BJ_IO list is just a temporary list for transaction commit, we use a private list in jbd2_journal_commit_transaction() for that thus removing BJ_IO list from transaction completely. Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/checkpoint.c | 1 - fs/jbd2/commit.c | 65 +++++++++++++++++---------------------------------- fs/jbd2/journal.c | 36 +++++++++++----------------- fs/jbd2/transaction.c | 14 ++++------- include/linux/jbd2.h | 32 ++++++++++++------------- 5 files changed, 56 insertions(+), 92 deletions(-) (limited to 'include') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index c78841ee81cf..2735fef6e55e 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -690,7 +690,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact J_ASSERT(transaction->t_state == T_FINISHED); J_ASSERT(transaction->t_buffers == NULL); J_ASSERT(transaction->t_forget == NULL); - J_ASSERT(transaction->t_iobuf_list == NULL); J_ASSERT(transaction->t_shadow_list == NULL); J_ASSERT(transaction->t_log_list == NULL); J_ASSERT(transaction->t_checkpoint_list == NULL); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index e61d7224a729..57bd2ff97888 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -369,7 +369,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) { struct transaction_stats_s stats; transaction_t *commit_transaction; - struct journal_head *jh, *new_jh, *descriptor; + struct journal_head *jh, *descriptor; struct buffer_head **wbuf = journal->j_wbuf; int bufs; int flags; @@ -393,6 +393,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) tid_t first_tid; int update_tail; int csum_size = 0; + LIST_HEAD(io_bufs); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) csum_size = sizeof(struct jbd2_journal_block_tail); @@ -659,29 +660,22 @@ void jbd2_journal_commit_transaction(journal_t *journal) /* Bump b_count to prevent truncate from stumbling over the shadowed buffer! @@@ This can go if we ever get - rid of the BJ_IO/BJ_Shadow pairing of buffers. */ + rid of the shadow pairing of buffers. */ atomic_inc(&jh2bh(jh)->b_count); - /* Make a temporary IO buffer with which to write it out - (this will requeue both the metadata buffer and the - temporary IO buffer). new_bh goes on BJ_IO*/ - - set_bit(BH_JWrite, &jh2bh(jh)->b_state); /* - * akpm: jbd2_journal_write_metadata_buffer() sets - * new_bh->b_transaction to commit_transaction. - * We need to clean this up before we release new_bh - * (which is of type BJ_IO) + * Make a temporary IO buffer with which to write it out + * (this will requeue the metadata buffer to BJ_Shadow). */ + set_bit(BH_JWrite, &jh2bh(jh)->b_state); JBUFFER_TRACE(jh, "ph3: write metadata"); flags = jbd2_journal_write_metadata_buffer(commit_transaction, - jh, &new_jh, blocknr); + jh, &wbuf[bufs], blocknr); if (flags < 0) { jbd2_journal_abort(journal, flags); continue; } - set_bit(BH_JWrite, &jh2bh(new_jh)->b_state); - wbuf[bufs++] = jh2bh(new_jh); + jbd2_file_log_bh(&io_bufs, wbuf[bufs]); /* Record the new block's tag in the current descriptor buffer */ @@ -695,10 +689,11 @@ void jbd2_journal_commit_transaction(journal_t *journal) tag = (journal_block_tag_t *) tagp; write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr); tag->t_flags = cpu_to_be16(tag_flag); - jbd2_block_tag_csum_set(journal, tag, jh2bh(new_jh), + jbd2_block_tag_csum_set(journal, tag, wbuf[bufs], commit_transaction->t_tid); tagp += tag_bytes; space_left -= tag_bytes; + bufs++; if (first_tag) { memcpy (tagp, journal->j_uuid, 16); @@ -810,7 +805,7 @@ start_journal_io: the log. Before we can commit it, wait for the IO so far to complete. Control buffers being written are on the transaction's t_log_list queue, and metadata buffers are on - the t_iobuf_list queue. + the io_bufs list. Wait for the buffers in reverse order. That way we are less likely to be woken up until all IOs have completed, and @@ -819,46 +814,31 @@ start_journal_io: jbd_debug(3, "JBD2: commit phase 3\n"); - /* - * akpm: these are BJ_IO, and j_list_lock is not needed. - * See __journal_try_to_free_buffer. - */ -wait_for_iobuf: - while (commit_transaction->t_iobuf_list != NULL) { - struct buffer_head *bh; + while (!list_empty(&io_bufs)) { + struct buffer_head *bh = list_entry(io_bufs.prev, + struct buffer_head, + b_assoc_buffers); - jh = commit_transaction->t_iobuf_list->b_tprev; - bh = jh2bh(jh); - if (buffer_locked(bh)) { - wait_on_buffer(bh); - goto wait_for_iobuf; - } - if (cond_resched()) - goto wait_for_iobuf; + wait_on_buffer(bh); + cond_resched(); if (unlikely(!buffer_uptodate(bh))) err = -EIO; - - clear_buffer_jwrite(bh); - - JBUFFER_TRACE(jh, "ph4: unfile after journal write"); - jbd2_journal_unfile_buffer(journal, jh); + jbd2_unfile_log_bh(bh); /* - * ->t_iobuf_list should contain only dummy buffer_heads - * which were created by jbd2_journal_write_metadata_buffer(). + * The list contains temporary buffer heads created by + * jbd2_journal_write_metadata_buffer(). */ BUFFER_TRACE(bh, "dumping temporary bh"); - jbd2_journal_put_journal_head(jh); __brelse(bh); J_ASSERT_BH(bh, atomic_read(&bh->b_count) == 0); free_buffer_head(bh); - /* We also have to unlock and free the corresponding - shadowed buffer */ + /* We also have to refile the corresponding shadowed buffer */ jh = commit_transaction->t_shadow_list->b_tprev; bh = jh2bh(jh); - clear_bit(BH_JWrite, &bh->b_state); + clear_buffer_jwrite(bh); J_ASSERT_BH(bh, buffer_jbddirty(bh)); /* The metadata is now released for reuse, but we need @@ -953,7 +933,6 @@ wait_for_iobuf: J_ASSERT(list_empty(&commit_transaction->t_inode_list)); J_ASSERT(commit_transaction->t_buffers == NULL); J_ASSERT(commit_transaction->t_checkpoint_list == NULL); - J_ASSERT(commit_transaction->t_iobuf_list == NULL); J_ASSERT(commit_transaction->t_shadow_list == NULL); J_ASSERT(commit_transaction->t_log_list == NULL); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 3cdd285df204..45cdc080e466 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -310,14 +310,12 @@ static void journal_kill_thread(journal_t *journal) * * If the source buffer has already been modified by a new transaction * since we took the last commit snapshot, we use the frozen copy of - * that data for IO. If we end up using the existing buffer_head's data - * for the write, then we *have* to lock the buffer to prevent anyone - * else from using and possibly modifying it while the IO is in - * progress. + * that data for IO. If we end up using the existing buffer_head's data + * for the write, then we have to make sure nobody modifies it while the + * IO is in progress. do_get_write_access() handles this. * - * The function returns a pointer to the buffer_heads to be used for IO. - * - * We assume that the journal has already been locked in this function. + * The function returns a pointer to the buffer_head to be used for IO. + * * * Return value: * <0: Error @@ -330,15 +328,14 @@ static void journal_kill_thread(journal_t *journal) int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, - struct journal_head **jh_out, - unsigned long long blocknr) + struct buffer_head **bh_out, + sector_t blocknr) { int need_copy_out = 0; int done_copy_out = 0; int do_escape = 0; char *mapped_data; struct buffer_head *new_bh; - struct journal_head *new_jh; struct page *new_page; unsigned int new_offset; struct buffer_head *bh_in = jh2bh(jh_in); @@ -368,14 +365,13 @@ retry_alloc: /* keep subsequent assertions sane */ atomic_set(&new_bh->b_count, 1); - new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */ + jbd_lock_bh_state(bh_in); +repeat: /* * If a new transaction has already done a buffer copy-out, then * we use that version of the data for the commit. */ - jbd_lock_bh_state(bh_in); -repeat: if (jh_in->b_frozen_data) { done_copy_out = 1; new_page = virt_to_page(jh_in->b_frozen_data); @@ -415,7 +411,7 @@ repeat: jbd_unlock_bh_state(bh_in); tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); if (!tmp) { - jbd2_journal_put_journal_head(new_jh); + brelse(new_bh); return -ENOMEM; } jbd_lock_bh_state(bh_in); @@ -426,7 +422,7 @@ repeat: jh_in->b_frozen_data = tmp; mapped_data = kmap_atomic(new_page); - memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size); + memcpy(tmp, mapped_data + new_offset, bh_in->b_size); kunmap_atomic(mapped_data); new_page = virt_to_page(tmp); @@ -452,14 +448,13 @@ repeat: } set_bh_page(new_bh, new_page, new_offset); - new_jh->b_transaction = NULL; - new_bh->b_size = jh2bh(jh_in)->b_size; - new_bh->b_bdev = transaction->t_journal->j_dev; + new_bh->b_size = bh_in->b_size; + new_bh->b_bdev = journal->j_dev; new_bh->b_blocknr = blocknr; set_buffer_mapped(new_bh); set_buffer_dirty(new_bh); - *jh_out = new_jh; + *bh_out = new_bh; /* * The to-be-written buffer needs to get moved to the io queue, @@ -472,9 +467,6 @@ repeat: spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh_in); - JBUFFER_TRACE(new_jh, "file as BJ_IO"); - jbd2_journal_file_buffer(new_jh, transaction, BJ_IO); - return do_escape | (done_copy_out << 1); } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 5d8268ad364a..983010900258 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1601,10 +1601,10 @@ __blist_del_buffer(struct journal_head **list, struct journal_head *jh) * Remove a buffer from the appropriate transaction list. * * Note that this function can *change* the value of - * bh->b_transaction->t_buffers, t_forget, t_iobuf_list, t_shadow_list, - * t_log_list or t_reserved_list. If the caller is holding onto a copy of one - * of these pointers, it could go bad. Generally the caller needs to re-read - * the pointer from the transaction_t. + * bh->b_transaction->t_buffers, t_forget, t_shadow_list, t_log_list or + * t_reserved_list. If the caller is holding onto a copy of one of these + * pointers, it could go bad. Generally the caller needs to re-read the + * pointer from the transaction_t. * * Called under j_list_lock. */ @@ -1634,9 +1634,6 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) case BJ_Forget: list = &transaction->t_forget; break; - case BJ_IO: - list = &transaction->t_iobuf_list; - break; case BJ_Shadow: list = &transaction->t_shadow_list; break; @@ -2148,9 +2145,6 @@ void __jbd2_journal_file_buffer(struct journal_head *jh, case BJ_Forget: list = &transaction->t_forget; break; - case BJ_IO: - list = &transaction->t_iobuf_list; - break; case BJ_Shadow: list = &transaction->t_shadow_list; break; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 682a63c34d26..57210844b228 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -523,12 +523,6 @@ struct transaction_s */ struct journal_head *t_checkpoint_io_list; - /* - * Doubly-linked circular list of temporary buffers currently undergoing - * IO in the log [j_list_lock] - */ - struct journal_head *t_iobuf_list; - /* * Doubly-linked circular list of metadata buffers being shadowed by log * IO. The IO buffers on the iobuf list and the shadow buffers on this @@ -991,6 +985,14 @@ extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, i extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); extern void __journal_clean_data_list(transaction_t *transaction); +static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) +{ + list_add_tail(&bh->b_assoc_buffers, head); +} +static inline void jbd2_unfile_log_bh(struct buffer_head *bh) +{ + list_del_init(&bh->b_assoc_buffers); +} /* Log buffer allocation */ extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *); @@ -1039,11 +1041,10 @@ extern void jbd2_buffer_abort_trigger(struct journal_head *jh, struct jbd2_buffer_trigger_type *triggers); /* Buffer IO */ -extern int -jbd2_journal_write_metadata_buffer(transaction_t *transaction, - struct journal_head *jh_in, - struct journal_head **jh_out, - unsigned long long blocknr); +extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, + struct journal_head *jh_in, + struct buffer_head **bh_out, + sector_t blocknr); /* Transaction locking */ extern void __wait_on_journal (journal_t *); @@ -1286,11 +1287,10 @@ static inline int jbd_space_needed(journal_t *journal) #define BJ_None 0 /* Not journaled */ #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ -#define BJ_IO 3 /* Buffer is for temporary IO use */ -#define BJ_Shadow 4 /* Buffer contents being shadowed to the log */ -#define BJ_LogCtl 5 /* Buffer contains log descriptors */ -#define BJ_Reserved 6 /* Buffer is reserved for access by journal */ -#define BJ_Types 7 +#define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ +#define BJ_LogCtl 4 /* Buffer contains log descriptors */ +#define BJ_Reserved 5 /* Buffer is reserved for access by journal */ +#define BJ_Types 6 extern int jbd_blocks_per_page(struct inode *inode); -- cgit v1.2.3-58-ga151 From e5a120aeb57f40ae568a5ca1dd6ace53d0213582 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:06:01 -0400 Subject: jbd2: remove journal_head from descriptor buffers Similarly as for metadata buffers, also log descriptor buffers don't really need the journal head. So strip it and remove BJ_LogCtl list. Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/checkpoint.c | 1 - fs/jbd2/commit.c | 78 ++++++++++++++++++++------------------------------- fs/jbd2/journal.c | 4 +-- fs/jbd2/revoke.c | 49 ++++++++++++++++---------------- fs/jbd2/transaction.c | 6 ---- include/linux/jbd2.h | 19 +++++-------- 6 files changed, 64 insertions(+), 93 deletions(-) (limited to 'include') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 2735fef6e55e..65ec076e41f2 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -691,7 +691,6 @@ void __jbd2_journal_drop_transaction(journal_t *journal, transaction_t *transact J_ASSERT(transaction->t_buffers == NULL); J_ASSERT(transaction->t_forget == NULL); J_ASSERT(transaction->t_shadow_list == NULL); - J_ASSERT(transaction->t_log_list == NULL); J_ASSERT(transaction->t_checkpoint_list == NULL); J_ASSERT(transaction->t_checkpoint_io_list == NULL); J_ASSERT(atomic_read(&transaction->t_updates) == 0); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 57bd2ff97888..7c6f7eea2316 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -85,8 +85,7 @@ nope: __brelse(bh); } -static void jbd2_commit_block_csum_set(journal_t *j, - struct journal_head *descriptor) +static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh) { struct commit_header *h; __u32 csum; @@ -94,12 +93,11 @@ static void jbd2_commit_block_csum_set(journal_t *j, if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return; - h = (struct commit_header *)(jh2bh(descriptor)->b_data); + h = (struct commit_header *)(bh->b_data); h->h_chksum_type = 0; h->h_chksum_size = 0; h->h_chksum[0] = 0; - csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, - j->j_blocksize); + csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize); h->h_chksum[0] = cpu_to_be32(csum); } @@ -116,7 +114,6 @@ static int journal_submit_commit_record(journal_t *journal, struct buffer_head **cbh, __u32 crc32_sum) { - struct journal_head *descriptor; struct commit_header *tmp; struct buffer_head *bh; int ret; @@ -127,12 +124,10 @@ static int journal_submit_commit_record(journal_t *journal, if (is_journal_aborted(journal)) return 0; - descriptor = jbd2_journal_get_descriptor_buffer(journal); - if (!descriptor) + bh = jbd2_journal_get_descriptor_buffer(journal); + if (!bh) return 1; - bh = jh2bh(descriptor); - tmp = (struct commit_header *)bh->b_data; tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK); @@ -146,9 +141,9 @@ static int journal_submit_commit_record(journal_t *journal, tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE; tmp->h_chksum[0] = cpu_to_be32(crc32_sum); } - jbd2_commit_block_csum_set(journal, descriptor); + jbd2_commit_block_csum_set(journal, bh); - JBUFFER_TRACE(descriptor, "submit commit block"); + BUFFER_TRACE(bh, "submit commit block"); lock_buffer(bh); clear_buffer_dirty(bh); set_buffer_uptodate(bh); @@ -180,7 +175,6 @@ static int journal_wait_on_commit_record(journal_t *journal, if (unlikely(!buffer_uptodate(bh))) ret = -EIO; put_bh(bh); /* One for getblk() */ - jbd2_journal_put_journal_head(bh2jh(bh)); return ret; } @@ -321,7 +315,7 @@ static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, } static void jbd2_descr_block_csum_set(journal_t *j, - struct journal_head *descriptor) + struct buffer_head *bh) { struct jbd2_journal_block_tail *tail; __u32 csum; @@ -329,12 +323,10 @@ static void jbd2_descr_block_csum_set(journal_t *j, if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return; - tail = (struct jbd2_journal_block_tail *) - (jh2bh(descriptor)->b_data + j->j_blocksize - + tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - sizeof(struct jbd2_journal_block_tail)); tail->t_checksum = 0; - csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, - j->j_blocksize); + csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize); tail->t_checksum = cpu_to_be32(csum); } @@ -369,7 +361,8 @@ void jbd2_journal_commit_transaction(journal_t *journal) { struct transaction_stats_s stats; transaction_t *commit_transaction; - struct journal_head *jh, *descriptor; + struct journal_head *jh; + struct buffer_head *descriptor; struct buffer_head **wbuf = journal->j_wbuf; int bufs; int flags; @@ -394,6 +387,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) int update_tail; int csum_size = 0; LIST_HEAD(io_bufs); + LIST_HEAD(log_bufs); if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) csum_size = sizeof(struct jbd2_journal_block_tail); @@ -547,7 +541,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) blk_start_plug(&plug); jbd2_journal_write_revoke_records(journal, commit_transaction, - WRITE_SYNC); + &log_bufs, WRITE_SYNC); blk_finish_plug(&plug); jbd_debug(3, "JBD2: commit phase 2\n"); @@ -573,8 +567,8 @@ void jbd2_journal_commit_transaction(journal_t *journal) atomic_read(&commit_transaction->t_outstanding_credits)); err = 0; - descriptor = NULL; bufs = 0; + descriptor = NULL; blk_start_plug(&plug); while (commit_transaction->t_buffers) { @@ -606,8 +600,6 @@ void jbd2_journal_commit_transaction(journal_t *journal) record the metadata buffer. */ if (!descriptor) { - struct buffer_head *bh; - J_ASSERT (bufs == 0); jbd_debug(4, "JBD2: get descriptor\n"); @@ -618,26 +610,26 @@ void jbd2_journal_commit_transaction(journal_t *journal) continue; } - bh = jh2bh(descriptor); jbd_debug(4, "JBD2: got buffer %llu (%p)\n", - (unsigned long long)bh->b_blocknr, bh->b_data); - header = (journal_header_t *)&bh->b_data[0]; + (unsigned long long)descriptor->b_blocknr, + descriptor->b_data); + header = (journal_header_t *)descriptor->b_data; header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); header->h_blocktype = cpu_to_be32(JBD2_DESCRIPTOR_BLOCK); header->h_sequence = cpu_to_be32(commit_transaction->t_tid); - tagp = &bh->b_data[sizeof(journal_header_t)]; - space_left = bh->b_size - sizeof(journal_header_t); + tagp = &descriptor->b_data[sizeof(journal_header_t)]; + space_left = descriptor->b_size - + sizeof(journal_header_t); first_tag = 1; - set_buffer_jwrite(bh); - set_buffer_dirty(bh); - wbuf[bufs++] = bh; + set_buffer_jwrite(descriptor); + set_buffer_dirty(descriptor); + wbuf[bufs++] = descriptor; /* Record it so that we can wait for IO completion later */ - BUFFER_TRACE(bh, "ph3: file as descriptor"); - jbd2_journal_file_buffer(descriptor, commit_transaction, - BJ_LogCtl); + BUFFER_TRACE(descriptor, "ph3: file as descriptor"); + jbd2_file_log_bh(&log_bufs, descriptor); } /* Where is the buffer to be written? */ @@ -864,26 +856,19 @@ start_journal_io: jbd_debug(3, "JBD2: commit phase 4\n"); /* Here we wait for the revoke record and descriptor record buffers */ - wait_for_ctlbuf: - while (commit_transaction->t_log_list != NULL) { + while (!list_empty(&log_bufs)) { struct buffer_head *bh; - jh = commit_transaction->t_log_list->b_tprev; - bh = jh2bh(jh); - if (buffer_locked(bh)) { - wait_on_buffer(bh); - goto wait_for_ctlbuf; - } - if (cond_resched()) - goto wait_for_ctlbuf; + bh = list_entry(log_bufs.prev, struct buffer_head, b_assoc_buffers); + wait_on_buffer(bh); + cond_resched(); if (unlikely(!buffer_uptodate(bh))) err = -EIO; BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile"); clear_buffer_jwrite(bh); - jbd2_journal_unfile_buffer(journal, jh); - jbd2_journal_put_journal_head(jh); + jbd2_unfile_log_bh(bh); __brelse(bh); /* One for getblk */ /* AKPM: bforget here */ } @@ -934,7 +919,6 @@ start_journal_io: J_ASSERT(commit_transaction->t_buffers == NULL); J_ASSERT(commit_transaction->t_checkpoint_list == NULL); J_ASSERT(commit_transaction->t_shadow_list == NULL); - J_ASSERT(commit_transaction->t_log_list == NULL); restart_loop: /* diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 45cdc080e466..b0a8d1e4703e 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -790,7 +790,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, * But we don't bother doing that, so there will be coherency problems with * mmaps of blockdevs which hold live JBD-controlled filesystems. */ -struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal) +struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal) { struct buffer_head *bh; unsigned long long blocknr; @@ -809,7 +809,7 @@ struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal) set_buffer_uptodate(bh); unlock_buffer(bh); BUFFER_TRACE(bh, "return this buffer"); - return jbd2_journal_add_journal_head(bh); + return bh; } /* diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index f30b80b4ce8b..198c9c10276d 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -122,9 +122,10 @@ struct jbd2_revoke_table_s #ifdef __KERNEL__ static void write_one_revoke_record(journal_t *, transaction_t *, - struct journal_head **, int *, + struct list_head *, + struct buffer_head **, int *, struct jbd2_revoke_record_s *, int); -static void flush_descriptor(journal_t *, struct journal_head *, int, int); +static void flush_descriptor(journal_t *, struct buffer_head *, int, int); #endif /* Utility functions to maintain the revoke table */ @@ -531,9 +532,10 @@ void jbd2_journal_switch_revoke_table(journal_t *journal) */ void jbd2_journal_write_revoke_records(journal_t *journal, transaction_t *transaction, + struct list_head *log_bufs, int write_op) { - struct journal_head *descriptor; + struct buffer_head *descriptor; struct jbd2_revoke_record_s *record; struct jbd2_revoke_table_s *revoke; struct list_head *hash_list; @@ -553,7 +555,7 @@ void jbd2_journal_write_revoke_records(journal_t *journal, while (!list_empty(hash_list)) { record = (struct jbd2_revoke_record_s *) hash_list->next; - write_one_revoke_record(journal, transaction, + write_one_revoke_record(journal, transaction, log_bufs, &descriptor, &offset, record, write_op); count++; @@ -573,13 +575,14 @@ void jbd2_journal_write_revoke_records(journal_t *journal, static void write_one_revoke_record(journal_t *journal, transaction_t *transaction, - struct journal_head **descriptorp, + struct list_head *log_bufs, + struct buffer_head **descriptorp, int *offsetp, struct jbd2_revoke_record_s *record, int write_op) { int csum_size = 0; - struct journal_head *descriptor; + struct buffer_head *descriptor; int offset; journal_header_t *header; @@ -609,26 +612,26 @@ static void write_one_revoke_record(journal_t *journal, descriptor = jbd2_journal_get_descriptor_buffer(journal); if (!descriptor) return; - header = (journal_header_t *) &jh2bh(descriptor)->b_data[0]; + header = (journal_header_t *)descriptor->b_data; header->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); header->h_blocktype = cpu_to_be32(JBD2_REVOKE_BLOCK); header->h_sequence = cpu_to_be32(transaction->t_tid); /* Record it so that we can wait for IO completion later */ - JBUFFER_TRACE(descriptor, "file as BJ_LogCtl"); - jbd2_journal_file_buffer(descriptor, transaction, BJ_LogCtl); + BUFFER_TRACE(descriptor, "file in log_bufs"); + jbd2_file_log_bh(log_bufs, descriptor); offset = sizeof(jbd2_journal_revoke_header_t); *descriptorp = descriptor; } if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) { - * ((__be64 *)(&jh2bh(descriptor)->b_data[offset])) = + * ((__be64 *)(&descriptor->b_data[offset])) = cpu_to_be64(record->blocknr); offset += 8; } else { - * ((__be32 *)(&jh2bh(descriptor)->b_data[offset])) = + * ((__be32 *)(&descriptor->b_data[offset])) = cpu_to_be32(record->blocknr); offset += 4; } @@ -636,8 +639,7 @@ static void write_one_revoke_record(journal_t *journal, *offsetp = offset; } -static void jbd2_revoke_csum_set(journal_t *j, - struct journal_head *descriptor) +static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh) { struct jbd2_journal_revoke_tail *tail; __u32 csum; @@ -645,12 +647,10 @@ static void jbd2_revoke_csum_set(journal_t *j, if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) return; - tail = (struct jbd2_journal_revoke_tail *) - (jh2bh(descriptor)->b_data + j->j_blocksize - + tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize - sizeof(struct jbd2_journal_revoke_tail)); tail->r_checksum = 0; - csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, - j->j_blocksize); + csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize); tail->r_checksum = cpu_to_be32(csum); } @@ -662,25 +662,24 @@ static void jbd2_revoke_csum_set(journal_t *j, */ static void flush_descriptor(journal_t *journal, - struct journal_head *descriptor, + struct buffer_head *descriptor, int offset, int write_op) { jbd2_journal_revoke_header_t *header; - struct buffer_head *bh = jh2bh(descriptor); if (is_journal_aborted(journal)) { - put_bh(bh); + put_bh(descriptor); return; } - header = (jbd2_journal_revoke_header_t *) jh2bh(descriptor)->b_data; + header = (jbd2_journal_revoke_header_t *)descriptor->b_data; header->r_count = cpu_to_be32(offset); jbd2_revoke_csum_set(journal, descriptor); - set_buffer_jwrite(bh); - BUFFER_TRACE(bh, "write"); - set_buffer_dirty(bh); - write_dirty_buffer(bh, write_op); + set_buffer_jwrite(descriptor); + BUFFER_TRACE(descriptor, "write"); + set_buffer_dirty(descriptor); + write_dirty_buffer(descriptor, write_op); } #endif diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 983010900258..f1c5392e62b6 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1637,9 +1637,6 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) case BJ_Shadow: list = &transaction->t_shadow_list; break; - case BJ_LogCtl: - list = &transaction->t_log_list; - break; case BJ_Reserved: list = &transaction->t_reserved_list; break; @@ -2148,9 +2145,6 @@ void __jbd2_journal_file_buffer(struct journal_head *jh, case BJ_Shadow: list = &transaction->t_shadow_list; break; - case BJ_LogCtl: - list = &transaction->t_log_list; - break; case BJ_Reserved: list = &transaction->t_reserved_list; break; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 57210844b228..b7dc40da99e0 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -530,12 +530,6 @@ struct transaction_s */ struct journal_head *t_shadow_list; - /* - * Doubly-linked circular list of control buffers being written to the - * log. [j_list_lock] - */ - struct journal_head *t_log_list; - /* * List of inodes whose data we've modified in data=ordered mode. * [j_list_lock] @@ -995,7 +989,7 @@ static inline void jbd2_unfile_log_bh(struct buffer_head *bh) } /* Log buffer allocation */ -extern struct journal_head * jbd2_journal_get_descriptor_buffer(journal_t *); +struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); @@ -1179,8 +1173,10 @@ extern int jbd2_journal_init_revoke_caches(void); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); -extern void jbd2_journal_write_revoke_records(journal_t *, - transaction_t *, int); +extern void jbd2_journal_write_revoke_records(journal_t *journal, + transaction_t *transaction, + struct list_head *log_bufs, + int write_op); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); @@ -1288,9 +1284,8 @@ static inline int jbd_space_needed(journal_t *journal) #define BJ_Metadata 1 /* Normal journaled metadata */ #define BJ_Forget 2 /* Buffer superseded by this transaction */ #define BJ_Shadow 3 /* Buffer contents being shadowed to the log */ -#define BJ_LogCtl 4 /* Buffer contains log descriptors */ -#define BJ_Reserved 5 /* Buffer is reserved for access by journal */ -#define BJ_Types 6 +#define BJ_Reserved 4 /* Buffer is reserved for access by journal */ +#define BJ_Types 5 extern int jbd_blocks_per_page(struct inode *inode); -- cgit v1.2.3-58-ga151 From b34090e5e22a02fba0e4473056cce9420ad9dd0b Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:08:56 -0400 Subject: jbd2: refine waiting for shadow buffers Currently when we add a buffer to a transaction, we wait until the buffer is removed from BJ_Shadow list (so that we prevent any changes to the buffer that is just written to the journal). This can take unnecessarily long as a lot happens between the time the buffer is submitted to the journal and the time when we remove the buffer from BJ_Shadow list. (e.g. We wait for all data buffers in the transaction, we issue a cache flush, etc.) Also this creates a dependency of do_get_write_access() on transaction commit (namely waiting for data IO to complete) which we want to avoid when implementing transaction reservation. So we modify commit code to set new BH_Shadow flag when temporary shadowing buffer is created and we clear that flag once IO on that buffer is complete. This allows do_get_write_access() to wait only for BH_Shadow bit and thus removes the dependency on data IO completion. Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/commit.c | 18 +++++++++--------- fs/jbd2/journal.c | 2 ++ fs/jbd2/transaction.c | 44 +++++++++++++++++++------------------------- include/linux/jbd.h | 25 +++++++++++++++++++++++++ include/linux/jbd2.h | 28 ++++++++++++++++++++++++++++ include/linux/jbd_common.h | 26 -------------------------- 6 files changed, 83 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 7c6f7eea2316..d73a0d808ec1 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -30,15 +30,22 @@ #include /* - * Default IO end handler for temporary BJ_IO buffer_heads. + * IO end handler for temporary buffer_heads handling writes to the journal. */ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate) { + struct buffer_head *orig_bh = bh->b_private; + BUFFER_TRACE(bh, ""); if (uptodate) set_buffer_uptodate(bh); else clear_buffer_uptodate(bh); + if (orig_bh) { + clear_bit_unlock(BH_Shadow, &orig_bh->b_state); + smp_mb__after_clear_bit(); + wake_up_bit(&orig_bh->b_state, BH_Shadow); + } unlock_buffer(bh); } @@ -832,6 +839,7 @@ start_journal_io: bh = jh2bh(jh); clear_buffer_jwrite(bh); J_ASSERT_BH(bh, buffer_jbddirty(bh)); + J_ASSERT_BH(bh, !buffer_shadow(bh)); /* The metadata is now released for reuse, but we need to remember it against this transaction so that when @@ -839,14 +847,6 @@ start_journal_io: required. */ JBUFFER_TRACE(jh, "file as BJ_Forget"); jbd2_journal_file_buffer(jh, commit_transaction, BJ_Forget); - /* - * Wake up any transactions which were waiting for this IO to - * complete. The barrier must be here so that changes by - * jbd2_journal_file_buffer() take effect before wake_up_bit() - * does the waitqueue check. - */ - smp_mb(); - wake_up_bit(&bh->b_state, BH_Unshadow); JBUFFER_TRACE(jh, "brelse shadowed buffer"); __brelse(bh); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index b0a8d1e4703e..5ef0712e2f7a 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -451,6 +451,7 @@ repeat: new_bh->b_size = bh_in->b_size; new_bh->b_bdev = journal->j_dev; new_bh->b_blocknr = blocknr; + new_bh->b_private = bh_in; set_buffer_mapped(new_bh); set_buffer_dirty(new_bh); @@ -465,6 +466,7 @@ repeat: spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow); spin_unlock(&journal->j_list_lock); + set_buffer_shadow(bh_in); jbd_unlock_bh_state(bh_in); return do_escape | (done_copy_out << 1); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f1c5392e62b6..6f4248dd8759 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -619,6 +619,12 @@ static void warn_dirty_buffer(struct buffer_head *bh) bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr); } +static int sleep_on_shadow_bh(void *word) +{ + io_schedule(); + return 0; +} + /* * If the buffer is already part of the current transaction, then there * is nothing we need to do. If it is already part of a prior @@ -754,41 +760,29 @@ repeat: * journaled. If the primary copy is already going to * disk then we cannot do copy-out here. */ - if (jh->b_jlist == BJ_Shadow) { - DEFINE_WAIT_BIT(wait, &bh->b_state, BH_Unshadow); - wait_queue_head_t *wqh; - - wqh = bit_waitqueue(&bh->b_state, BH_Unshadow); - + if (buffer_shadow(bh)) { JBUFFER_TRACE(jh, "on shadow: sleep"); jbd_unlock_bh_state(bh); - /* commit wakes up all shadow buffers after IO */ - for ( ; ; ) { - prepare_to_wait(wqh, &wait.wait, - TASK_UNINTERRUPTIBLE); - if (jh->b_jlist != BJ_Shadow) - break; - schedule(); - } - finish_wait(wqh, &wait.wait); + wait_on_bit(&bh->b_state, BH_Shadow, + sleep_on_shadow_bh, TASK_UNINTERRUPTIBLE); goto repeat; } - /* Only do the copy if the currently-owning transaction - * still needs it. If it is on the Forget list, the - * committing transaction is past that stage. The - * buffer had better remain locked during the kmalloc, - * but that should be true --- we hold the journal lock - * still and the buffer is already on the BUF_JOURNAL - * list so won't be flushed. + /* + * Only do the copy if the currently-owning transaction still + * needs it. If buffer isn't on BJ_Metadata list, the + * committing transaction is past that stage (here we use the + * fact that BH_Shadow is set under bh_state lock together with + * refiling to BJ_Shadow list and at this point we know the + * buffer doesn't have BH_Shadow set). * * Subtle point, though: if this is a get_undo_access, * then we will be relying on the frozen_data to contain * the new value of the committed_data record after the * transaction, so we HAVE to force the frozen_data copy - * in that case. */ - - if (jh->b_jlist != BJ_Forget || force_copy) { + * in that case. + */ + if (jh->b_jlist == BJ_Metadata || force_copy) { JBUFFER_TRACE(jh, "generate frozen data"); if (!frozen_buffer) { JBUFFER_TRACE(jh, "allocate memory for buffer"); diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 9c505f1aa1fd..2439054a6c9a 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -244,6 +244,31 @@ typedef struct journal_superblock_s #include #include + +enum jbd_state_bits { + BH_JBD /* Has an attached ext3 journal_head */ + = BH_PrivateStart, + BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ + BH_Freed, /* Has been freed (truncated) */ + BH_Revoked, /* Has been revoked from the log */ + BH_RevokeValid, /* Revoked flag is valid */ + BH_JBDDirty, /* Is dirty but journaled */ + BH_State, /* Pins most journal_head state */ + BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ + BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */ + BH_JBDPrivateStart, /* First bit available for private use by FS */ +}; + +BUFFER_FNS(JBD, jbd) +BUFFER_FNS(JWrite, jwrite) +BUFFER_FNS(JBDDirty, jbddirty) +TAS_BUFFER_FNS(JBDDirty, jbddirty) +BUFFER_FNS(Revoked, revoked) +TAS_BUFFER_FNS(Revoked, revoked) +BUFFER_FNS(RevokeValid, revokevalid) +TAS_BUFFER_FNS(RevokeValid, revokevalid) +BUFFER_FNS(Freed, freed) + #include #define J_ASSERT(assert) BUG_ON(!(assert)) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index b7dc40da99e0..e33e84b3d5c8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -302,6 +302,34 @@ typedef struct journal_superblock_s #include #include + +enum jbd_state_bits { + BH_JBD /* Has an attached ext3 journal_head */ + = BH_PrivateStart, + BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ + BH_Freed, /* Has been freed (truncated) */ + BH_Revoked, /* Has been revoked from the log */ + BH_RevokeValid, /* Revoked flag is valid */ + BH_JBDDirty, /* Is dirty but journaled */ + BH_State, /* Pins most journal_head state */ + BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ + BH_Shadow, /* IO on shadow buffer is running */ + BH_Verified, /* Metadata block has been verified ok */ + BH_JBDPrivateStart, /* First bit available for private use by FS */ +}; + +BUFFER_FNS(JBD, jbd) +BUFFER_FNS(JWrite, jwrite) +BUFFER_FNS(JBDDirty, jbddirty) +TAS_BUFFER_FNS(JBDDirty, jbddirty) +BUFFER_FNS(Revoked, revoked) +TAS_BUFFER_FNS(Revoked, revoked) +BUFFER_FNS(RevokeValid, revokevalid) +TAS_BUFFER_FNS(RevokeValid, revokevalid) +BUFFER_FNS(Freed, freed) +BUFFER_FNS(Shadow, shadow) +BUFFER_FNS(Verified, verified) + #include #define J_ASSERT(assert) BUG_ON(!(assert)) diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h index 6133679bc4c0..b1f708976ffd 100644 --- a/include/linux/jbd_common.h +++ b/include/linux/jbd_common.h @@ -1,32 +1,6 @@ #ifndef _LINUX_JBD_STATE_H #define _LINUX_JBD_STATE_H -enum jbd_state_bits { - BH_JBD /* Has an attached ext3 journal_head */ - = BH_PrivateStart, - BH_JWrite, /* Being written to log (@@@ DEBUGGING) */ - BH_Freed, /* Has been freed (truncated) */ - BH_Revoked, /* Has been revoked from the log */ - BH_RevokeValid, /* Revoked flag is valid */ - BH_JBDDirty, /* Is dirty but journaled */ - BH_State, /* Pins most journal_head state */ - BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ - BH_Unshadow, /* Dummy bit, for BJ_Shadow wakeup filtering */ - BH_Verified, /* Metadata block has been verified ok */ - BH_JBDPrivateStart, /* First bit available for private use by FS */ -}; - -BUFFER_FNS(JBD, jbd) -BUFFER_FNS(JWrite, jwrite) -BUFFER_FNS(JBDDirty, jbddirty) -TAS_BUFFER_FNS(JBDDirty, jbddirty) -BUFFER_FNS(Revoked, revoked) -TAS_BUFFER_FNS(Revoked, revoked) -BUFFER_FNS(RevokeValid, revokevalid) -TAS_BUFFER_FNS(RevokeValid, revokevalid) -BUFFER_FNS(Freed, freed) -BUFFER_FNS(Verified, verified) - static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; -- cgit v1.2.3-58-ga151 From 76c39904561004ac8675f858a290129e439d5168 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:12:57 -0400 Subject: jbd2: cleanup needed free block estimates when starting a transaction __jbd2_log_space_left() and jbd_space_needed() were kind of odd. jbd_space_needed() accounted also credits needed for currently committing transaction while it didn't account for credits needed for control blocks. __jbd2_log_space_left() then accounted for control blocks as a fraction of free space. Since results of these two functions are always only compared against each other, this works correct but is somewhat strange. Move the estimates so that jbd_space_needed() returns number of blocks needed for a transaction including control blocks and __jbd2_log_space_left() returns free space in the journal (with the committing transaction already subtracted). Rename functions to jbd2_log_space_left() and jbd2_space_needed() while we are changing them. Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/checkpoint.c | 8 ++++---- fs/jbd2/journal.c | 29 ----------------------------- fs/jbd2/transaction.c | 9 +++++---- include/linux/jbd2.h | 32 ++++++++++++++++++++++++++------ 4 files changed, 35 insertions(+), 43 deletions(-) (limited to 'include') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 65ec076e41f2..a572383bcf99 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -120,8 +120,8 @@ void __jbd2_log_wait_for_space(journal_t *journal) int nblocks, space_left; /* assert_spin_locked(&journal->j_state_lock); */ - nblocks = jbd_space_needed(journal); - while (__jbd2_log_space_left(journal) < nblocks) { + nblocks = jbd2_space_needed(journal); + while (jbd2_log_space_left(journal) < nblocks) { if (journal->j_flags & JBD2_ABORT) return; write_unlock(&journal->j_state_lock); @@ -140,8 +140,8 @@ void __jbd2_log_wait_for_space(journal_t *journal) */ write_lock(&journal->j_state_lock); spin_lock(&journal->j_list_lock); - nblocks = jbd_space_needed(journal); - space_left = __jbd2_log_space_left(journal); + nblocks = jbd2_space_needed(journal); + space_left = jbd2_log_space_left(journal); if (space_left < nblocks) { int chkpt = journal->j_checkpoint_transactions != NULL; tid_t tid = 0; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 5ef0712e2f7a..8e5486d62e89 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -477,35 +477,6 @@ repeat: * journal, so that we can begin checkpointing when appropriate. */ -/* - * __jbd2_log_space_left: Return the number of free blocks left in the journal. - * - * Called with the journal already locked. - * - * Called under j_state_lock - */ - -int __jbd2_log_space_left(journal_t *journal) -{ - int left = journal->j_free; - - /* assert_spin_locked(&journal->j_state_lock); */ - - /* - * Be pessimistic here about the number of those free blocks which - * might be required for log descriptor control blocks. - */ - -#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */ - - left -= MIN_LOG_RESERVED_BLOCKS; - - if (left <= 0) - return 0; - left -= (left >> 3); - return left; -} - /* * Called with j_state_lock locked for writing. * Returns true if a transaction commit was started. diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 60361c634b5d..f9cd43190b43 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -283,12 +283,12 @@ repeat: * reduce the free space arbitrarily. Be careful to account for * those buffers when checkpointing. */ - if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) { + if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) { jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle); atomic_sub(nblocks, &transaction->t_outstanding_credits); read_unlock(&journal->j_state_lock); write_lock(&journal->j_state_lock); - if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) + if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) __jbd2_log_wait_for_space(journal); write_unlock(&journal->j_state_lock); goto repeat; @@ -306,7 +306,7 @@ repeat: jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n", handle, nblocks, atomic_read(&transaction->t_outstanding_credits), - __jbd2_log_space_left(journal)); + jbd2_log_space_left(journal)); read_unlock(&journal->j_state_lock); lock_map_acquire(&handle->h_lockdep_map); @@ -441,7 +441,8 @@ int jbd2_journal_extend(handle_t *handle, int nblocks) goto unlock; } - if (wanted > __jbd2_log_space_left(journal)) { + if (wanted + (wanted >> JBD2_CONTROL_BLOCKS_SHIFT) > + jbd2_log_space_left(journal)) { jbd_debug(3, "denied handle %p %d blocks: " "insufficient log space\n", handle, nblocks); goto unlock; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index e33e84b3d5c8..7a1f6cd864c8 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1220,7 +1220,6 @@ extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); * transitions on demand. */ -int __jbd2_log_space_left(journal_t *); /* Called with journal locked */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); @@ -1290,17 +1289,38 @@ static inline int tid_geq(tid_t x, tid_t y) extern int jbd2_journal_blocks_per_page(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); +/* + * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for + * transaction control blocks. + */ +#define JBD2_CONTROL_BLOCKS_SHIFT 5 + /* * Return the minimum number of blocks which must be free in the journal * before a new transaction may be started. Must be called under j_state_lock. */ -static inline int jbd_space_needed(journal_t *journal) +static inline int jbd2_space_needed(journal_t *journal) { int nblocks = journal->j_max_transaction_buffers; - if (journal->j_committing_transaction) - nblocks += atomic_read(&journal->j_committing_transaction-> - t_outstanding_credits); - return nblocks; + return nblocks + (nblocks >> JBD2_CONTROL_BLOCKS_SHIFT); +} + +/* + * Return number of free blocks in the log. Must be called under j_state_lock. + */ +static inline unsigned long jbd2_log_space_left(journal_t *journal) +{ + /* Allow for rounding errors */ + unsigned long free = journal->j_free - 32; + + if (journal->j_committing_transaction) { + unsigned long committing = atomic_read(&journal-> + j_committing_transaction->t_outstanding_credits); + + /* Transaction + control blocks */ + free -= committing + (committing >> JBD2_CONTROL_BLOCKS_SHIFT); + } + return free; } /* -- cgit v1.2.3-58-ga151 From f29fad72105287e6899d9128a9d494514f220e77 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:24:11 -0400 Subject: jbd2: remove unused waitqueues j_wait_logspace and j_wait_checkpoint are unused. Remove them. Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/jbd2/checkpoint.c | 4 ---- fs/jbd2/journal.c | 2 -- include/linux/jbd2.h | 8 -------- 3 files changed, 14 deletions(-) (limited to 'include') diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index a572383bcf99..75a15f371b00 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -625,10 +625,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh) __jbd2_journal_drop_transaction(journal, transaction); jbd2_journal_free_transaction(transaction); - - /* Just in case anybody was waiting for more transactions to be - checkpointed... */ - wake_up(&journal->j_wait_logspace); ret = 1; out: return ret; diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 8e5486d62e89..f43f97ba002e 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1027,9 +1027,7 @@ static journal_t * journal_init_common (void) return NULL; init_waitqueue_head(&journal->j_wait_transaction_locked); - init_waitqueue_head(&journal->j_wait_logspace); init_waitqueue_head(&journal->j_wait_done_commit); - init_waitqueue_head(&journal->j_wait_checkpoint); init_waitqueue_head(&journal->j_wait_commit); init_waitqueue_head(&journal->j_wait_updates); mutex_init(&journal->j_barrier); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 7a1f6cd864c8..8028dd581cb0 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -687,9 +687,7 @@ jbd2_time_diff(unsigned long start, unsigned long end) * waiting for checkpointing * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction * to start committing, or for a barrier lock to be released - * @j_wait_logspace: Wait queue for waiting for checkpointing to complete * @j_wait_done_commit: Wait queue for waiting for commit to complete - * @j_wait_checkpoint: Wait queue to trigger checkpointing * @j_wait_commit: Wait queue to trigger commit * @j_wait_updates: Wait queue to wait for updates to complete * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints @@ -794,15 +792,9 @@ struct journal_s */ wait_queue_head_t j_wait_transaction_locked; - /* Wait queue for waiting for checkpointing to complete */ - wait_queue_head_t j_wait_logspace; - /* Wait queue for waiting for commit to complete */ wait_queue_head_t j_wait_done_commit; - /* Wait queue to trigger checkpointing */ - wait_queue_head_t j_wait_checkpoint; - /* Wait queue to trigger commit */ wait_queue_head_t j_wait_commit; -- cgit v1.2.3-58-ga151 From 8f7d89f36829b9061a14f9040cda1372f264c4fe Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:35:11 -0400 Subject: jbd2: transaction reservation support In some cases we cannot start a transaction because of locking constraints and passing started transaction into those places is not handy either because we could block transaction commit for too long. Transaction reservation is designed to solve these issues. It reserves a handle with given number of credits in the journal and the handle can be later attached to the running transaction without blocking on commit or checkpointing. Reserved handles do not block transaction commit in any way, they only reduce maximum size of the running transaction (because we have to always be prepared to accomodate request for attaching reserved handle). Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_jbd2.c | 2 +- fs/jbd2/commit.c | 6 + fs/jbd2/journal.c | 2 + fs/jbd2/transaction.c | 328 ++++++++++++++++++++++++++++++++++++-------------- include/linux/jbd2.h | 28 ++++- 5 files changed, 273 insertions(+), 93 deletions(-) (limited to 'include') diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 451eb4045330..bd25e782ec6b 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -62,7 +62,7 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, ext4_abort(sb, "Detected aborted journal"); return ERR_PTR(-EROFS); } - return jbd2__journal_start(journal, nblocks, GFP_NOFS, type, line); + return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, type, line); } int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index d73a0d808ec1..cfbce48adc0b 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -523,6 +523,12 @@ void jbd2_journal_commit_transaction(journal_t *journal) */ jbd2_journal_switch_revoke_table(journal); + /* + * Reserved credits cannot be claimed anymore, free them + */ + atomic_sub(atomic_read(&journal->j_reserved_credits), + &commit_transaction->t_outstanding_credits); + trace_jbd2_commit_flushing(journal, commit_transaction); stats.run.rs_flushing = jiffies; stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked, diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index f43f97ba002e..70990d682a0c 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1030,6 +1030,7 @@ static journal_t * journal_init_common (void) init_waitqueue_head(&journal->j_wait_done_commit); init_waitqueue_head(&journal->j_wait_commit); init_waitqueue_head(&journal->j_wait_updates); + init_waitqueue_head(&journal->j_wait_reserved); mutex_init(&journal->j_barrier); mutex_init(&journal->j_checkpoint_mutex); spin_lock_init(&journal->j_revoke_lock); @@ -1039,6 +1040,7 @@ static journal_t * journal_init_common (void) journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE); journal->j_min_batch_time = 0; journal->j_max_batch_time = 15000; /* 15ms */ + atomic_set(&journal->j_reserved_credits, 0); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f14288b04042..f33342a2a95e 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -89,7 +89,8 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction) transaction->t_expires = jiffies + journal->j_commit_interval; spin_lock_init(&transaction->t_handle_lock); atomic_set(&transaction->t_updates, 0); - atomic_set(&transaction->t_outstanding_credits, 0); + atomic_set(&transaction->t_outstanding_credits, + atomic_read(&journal->j_reserved_credits)); atomic_set(&transaction->t_handle_count, 0); INIT_LIST_HEAD(&transaction->t_inode_list); INIT_LIST_HEAD(&transaction->t_private_list); @@ -140,6 +141,112 @@ static inline void update_t_max_wait(transaction_t *transaction, #endif } +/* + * Wait until running transaction passes T_LOCKED state. Also starts the commit + * if needed. The function expects running transaction to exist and releases + * j_state_lock. + */ +static void wait_transaction_locked(journal_t *journal) + __releases(journal->j_state_lock) +{ + DEFINE_WAIT(wait); + int need_to_start; + tid_t tid = journal->j_running_transaction->t_tid; + + prepare_to_wait(&journal->j_wait_transaction_locked, &wait, + TASK_UNINTERRUPTIBLE); + need_to_start = !tid_geq(journal->j_commit_request, tid); + read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); + schedule(); + finish_wait(&journal->j_wait_transaction_locked, &wait); +} + +static void sub_reserved_credits(journal_t *journal, int blocks) +{ + atomic_sub(blocks, &journal->j_reserved_credits); + wake_up(&journal->j_wait_reserved); +} + +/* + * Wait until we can add credits for handle to the running transaction. Called + * with j_state_lock held for reading. Returns 0 if handle joined the running + * transaction. Returns 1 if we had to wait, j_state_lock is dropped, and + * caller must retry. + */ +static int add_transaction_credits(journal_t *journal, int blocks, + int rsv_blocks) +{ + transaction_t *t = journal->j_running_transaction; + int needed; + int total = blocks + rsv_blocks; + + /* + * If the current transaction is locked down for commit, wait + * for the lock to be released. + */ + if (t->t_state == T_LOCKED) { + wait_transaction_locked(journal); + return 1; + } + + /* + * If there is not enough space left in the log to write all + * potential buffers requested by this operation, we need to + * stall pending a log checkpoint to free some more log space. + */ + needed = atomic_add_return(total, &t->t_outstanding_credits); + if (needed > journal->j_max_transaction_buffers) { + /* + * If the current transaction is already too large, + * then start to commit it: we can then go back and + * attach this handle to a new transaction. + */ + atomic_sub(total, &t->t_outstanding_credits); + wait_transaction_locked(journal); + return 1; + } + + /* + * The commit code assumes that it can get enough log space + * without forcing a checkpoint. This is *critical* for + * correctness: a checkpoint of a buffer which is also + * associated with a committing transaction creates a deadlock, + * so commit simply cannot force through checkpoints. + * + * We must therefore ensure the necessary space in the journal + * *before* starting to dirty potentially checkpointed buffers + * in the new transaction. + */ + if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) { + atomic_sub(total, &t->t_outstanding_credits); + read_unlock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); + if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) + __jbd2_log_wait_for_space(journal); + write_unlock(&journal->j_state_lock); + return 1; + } + + /* No reservation? We are done... */ + if (!rsv_blocks) + return 0; + + needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits); + /* We allow at most half of a transaction to be reserved */ + if (needed > journal->j_max_transaction_buffers / 2) { + sub_reserved_credits(journal, rsv_blocks); + atomic_sub(total, &t->t_outstanding_credits); + read_unlock(&journal->j_state_lock); + wait_event(journal->j_wait_reserved, + atomic_read(&journal->j_reserved_credits) + rsv_blocks + <= journal->j_max_transaction_buffers / 2); + return 1; + } + return 0; +} + /* * start_this_handle: Given a handle, deal with any locking or stalling * needed to make sure that there is enough journal space for the handle @@ -151,18 +258,24 @@ static int start_this_handle(journal_t *journal, handle_t *handle, gfp_t gfp_mask) { transaction_t *transaction, *new_transaction = NULL; - tid_t tid; - int needed, need_to_start; - int nblocks = handle->h_buffer_credits; + int blocks = handle->h_buffer_credits; + int rsv_blocks = 0; unsigned long ts = jiffies; - if (nblocks > journal->j_max_transaction_buffers) { + /* + * 1/2 of transaction can be reserved so we can practically handle + * only 1/2 of maximum transaction size per operation + */ + if (WARN_ON(blocks > journal->j_max_transaction_buffers / 2)) { printk(KERN_ERR "JBD2: %s wants too many credits (%d > %d)\n", - current->comm, nblocks, - journal->j_max_transaction_buffers); + current->comm, blocks, + journal->j_max_transaction_buffers / 2); return -ENOSPC; } + if (handle->h_rsv_handle) + rsv_blocks = handle->h_rsv_handle->h_buffer_credits; + alloc_transaction: if (!journal->j_running_transaction) { new_transaction = kmem_cache_zalloc(transaction_cache, @@ -199,8 +312,12 @@ repeat: return -EROFS; } - /* Wait on the journal's transaction barrier if necessary */ - if (journal->j_barrier_count) { + /* + * Wait on the journal's transaction barrier if necessary. Specifically + * we allow reserved handles to proceed because otherwise commit could + * deadlock on page writeback not being able to complete. + */ + if (!handle->h_reserved && journal->j_barrier_count) { read_unlock(&journal->j_state_lock); wait_event(journal->j_wait_transaction_locked, journal->j_barrier_count == 0); @@ -213,7 +330,7 @@ repeat: goto alloc_transaction; write_lock(&journal->j_state_lock); if (!journal->j_running_transaction && - !journal->j_barrier_count) { + (handle->h_reserved || !journal->j_barrier_count)) { jbd2_get_transaction(journal, new_transaction); new_transaction = NULL; } @@ -223,75 +340,18 @@ repeat: transaction = journal->j_running_transaction; - /* - * If the current transaction is locked down for commit, wait for the - * lock to be released. - */ - if (transaction->t_state == T_LOCKED) { - DEFINE_WAIT(wait); - - prepare_to_wait(&journal->j_wait_transaction_locked, - &wait, TASK_UNINTERRUPTIBLE); - read_unlock(&journal->j_state_lock); - schedule(); - finish_wait(&journal->j_wait_transaction_locked, &wait); - goto repeat; - } - - /* - * If there is not enough space left in the log to write all potential - * buffers requested by this operation, we need to stall pending a log - * checkpoint to free some more log space. - */ - needed = atomic_add_return(nblocks, - &transaction->t_outstanding_credits); - - if (needed > journal->j_max_transaction_buffers) { + if (!handle->h_reserved) { + /* We may have dropped j_state_lock - restart in that case */ + if (add_transaction_credits(journal, blocks, rsv_blocks)) + goto repeat; + } else { /* - * If the current transaction is already too large, then start - * to commit it: we can then go back and attach this handle to - * a new transaction. + * We have handle reserved so we are allowed to join T_LOCKED + * transaction and we don't have to check for transaction size + * and journal space. */ - DEFINE_WAIT(wait); - - jbd_debug(2, "Handle %p starting new commit...\n", handle); - atomic_sub(nblocks, &transaction->t_outstanding_credits); - prepare_to_wait(&journal->j_wait_transaction_locked, &wait, - TASK_UNINTERRUPTIBLE); - tid = transaction->t_tid; - need_to_start = !tid_geq(journal->j_commit_request, tid); - read_unlock(&journal->j_state_lock); - if (need_to_start) - jbd2_log_start_commit(journal, tid); - schedule(); - finish_wait(&journal->j_wait_transaction_locked, &wait); - goto repeat; - } - - /* - * The commit code assumes that it can get enough log space - * without forcing a checkpoint. This is *critical* for - * correctness: a checkpoint of a buffer which is also - * associated with a committing transaction creates a deadlock, - * so commit simply cannot force through checkpoints. - * - * We must therefore ensure the necessary space in the journal - * *before* starting to dirty potentially checkpointed buffers - * in the new transaction. - * - * The worst part is, any transaction currently committing can - * reduce the free space arbitrarily. Be careful to account for - * those buffers when checkpointing. - */ - if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) { - jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle); - atomic_sub(nblocks, &transaction->t_outstanding_credits); - read_unlock(&journal->j_state_lock); - write_lock(&journal->j_state_lock); - if (jbd2_log_space_left(journal) < jbd2_space_needed(journal)) - __jbd2_log_wait_for_space(journal); - write_unlock(&journal->j_state_lock); - goto repeat; + sub_reserved_credits(journal, blocks); + handle->h_reserved = 0; } /* OK, account for the buffers that this operation expects to @@ -299,12 +359,12 @@ repeat: */ update_t_max_wait(transaction, ts); handle->h_transaction = transaction; - handle->h_requested_credits = nblocks; + handle->h_requested_credits = blocks; handle->h_start_jiffies = jiffies; atomic_inc(&transaction->t_updates); atomic_inc(&transaction->t_handle_count); - jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n", - handle, nblocks, + jbd_debug(4, "Handle %p given %d credits (total %d, free %lu)\n", + handle, blocks, atomic_read(&transaction->t_outstanding_credits), jbd2_log_space_left(journal)); read_unlock(&journal->j_state_lock); @@ -338,16 +398,21 @@ static handle_t *new_handle(int nblocks) * * We make sure that the transaction can guarantee at least nblocks of * modified buffers in the log. We block until the log can guarantee - * that much space. - * - * This function is visible to journal users (like ext3fs), so is not - * called with the journal already locked. + * that much space. Additionally, if rsv_blocks > 0, we also create another + * handle with rsv_blocks reserved blocks in the journal. This handle is + * is stored in h_rsv_handle. It is not attached to any particular transaction + * and thus doesn't block transaction commit. If the caller uses this reserved + * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() + * on the parent handle will dispose the reserved one. Reserved handle has to + * be converted to a normal handle using jbd2_journal_start_reserved() before + * it can be used. * * Return a pointer to a newly allocated handle, or an ERR_PTR() value * on failure. */ -handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask, - unsigned int type, unsigned int line_no) +handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, + gfp_t gfp_mask, unsigned int type, + unsigned int line_no) { handle_t *handle = journal_current_handle(); int err; @@ -364,11 +429,25 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask, handle = new_handle(nblocks); if (!handle) return ERR_PTR(-ENOMEM); + if (rsv_blocks) { + handle_t *rsv_handle; + + rsv_handle = new_handle(rsv_blocks); + if (!rsv_handle) { + jbd2_free_handle(handle); + return ERR_PTR(-ENOMEM); + } + rsv_handle->h_reserved = 1; + rsv_handle->h_journal = journal; + handle->h_rsv_handle = rsv_handle; + } current->journal_info = handle; err = start_this_handle(journal, handle, gfp_mask); if (err < 0) { + if (handle->h_rsv_handle) + jbd2_free_handle(handle->h_rsv_handle); jbd2_free_handle(handle); current->journal_info = NULL; return ERR_PTR(err); @@ -385,10 +464,68 @@ EXPORT_SYMBOL(jbd2__journal_start); handle_t *jbd2_journal_start(journal_t *journal, int nblocks) { - return jbd2__journal_start(journal, nblocks, GFP_NOFS, 0, 0); + return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, 0, 0); } EXPORT_SYMBOL(jbd2_journal_start); +void jbd2_journal_free_reserved(handle_t *handle) +{ + journal_t *journal = handle->h_journal; + + WARN_ON(!handle->h_reserved); + sub_reserved_credits(journal, handle->h_buffer_credits); + jbd2_free_handle(handle); +} +EXPORT_SYMBOL(jbd2_journal_free_reserved); + +/** + * int jbd2_journal_start_reserved(handle_t *handle) - start reserved handle + * @handle: handle to start + * + * Start handle that has been previously reserved with jbd2_journal_reserve(). + * This attaches @handle to the running transaction (or creates one if there's + * not transaction running). Unlike jbd2_journal_start() this function cannot + * block on journal commit, checkpointing, or similar stuff. It can block on + * memory allocation or frozen journal though. + * + * Return 0 on success, non-zero on error - handle is freed in that case. + */ +int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, + unsigned int line_no) +{ + journal_t *journal = handle->h_journal; + int ret = -EIO; + + if (WARN_ON(!handle->h_reserved)) { + /* Someone passed in normal handle? Just stop it. */ + jbd2_journal_stop(handle); + return ret; + } + /* + * Usefulness of mixing of reserved and unreserved handles is + * questionable. So far nobody seems to need it so just error out. + */ + if (WARN_ON(current->journal_info)) { + jbd2_journal_free_reserved(handle); + return ret; + } + + handle->h_journal = NULL; + current->journal_info = handle; + /* + * GFP_NOFS is here because callers are likely from writeback or + * similarly constrained call sites + */ + ret = start_this_handle(journal, handle, GFP_NOFS); + if (ret < 0) { + current->journal_info = NULL; + jbd2_journal_free_reserved(handle); + } + handle->h_type = type; + handle->h_line_no = line_no; + return ret; +} +EXPORT_SYMBOL(jbd2_journal_start_reserved); /** * int jbd2_journal_extend() - extend buffer credits. @@ -483,7 +620,8 @@ out: * to a running handle, a call to jbd2_journal_restart will commit the * handle's transaction so far and reattach the handle to a new * transaction capabable of guaranteeing the requested number of - * credits. + * credits. We preserve reserved handle if there's any attached to the + * passed in handle. */ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) { @@ -508,6 +646,10 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) spin_lock(&transaction->t_handle_lock); atomic_sub(handle->h_buffer_credits, &transaction->t_outstanding_credits); + if (handle->h_rsv_handle) { + sub_reserved_credits(journal, + handle->h_rsv_handle->h_buffer_credits); + } if (atomic_dec_and_test(&transaction->t_updates)) wake_up(&journal->j_wait_updates); spin_unlock(&transaction->t_handle_lock); @@ -550,6 +692,14 @@ void jbd2_journal_lock_updates(journal_t *journal) write_lock(&journal->j_state_lock); ++journal->j_barrier_count; + /* Wait until there are no reserved handles */ + if (atomic_read(&journal->j_reserved_credits)) { + write_unlock(&journal->j_state_lock); + wait_event(journal->j_wait_reserved, + atomic_read(&journal->j_reserved_credits) == 0); + write_lock(&journal->j_state_lock); + } + /* Wait until there are no running updates */ while (1) { transaction_t *transaction = journal->j_running_transaction; @@ -1505,6 +1655,8 @@ int jbd2_journal_stop(handle_t *handle) lock_map_release(&handle->h_lockdep_map); + if (handle->h_rsv_handle) + jbd2_journal_free_reserved(handle->h_rsv_handle); jbd2_free_handle(handle); return err; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 8028dd581cb0..fb91c8debe6a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -410,8 +410,15 @@ struct jbd2_revoke_table_s; struct jbd2_journal_handle { - /* Which compound transaction is this update a part of? */ - transaction_t *h_transaction; + union { + /* Which compound transaction is this update a part of? */ + transaction_t *h_transaction; + /* Which journal handle belongs to - used iff h_reserved set */ + journal_t *h_journal; + }; + + /* Handle reserved for finishing the logical operation */ + handle_t *h_rsv_handle; /* Number of remaining buffers we are allowed to dirty: */ int h_buffer_credits; @@ -426,6 +433,7 @@ struct jbd2_journal_handle /* Flags [no locking] */ unsigned int h_sync: 1; /* sync-on-close */ unsigned int h_jdata: 1; /* force data journaling */ + unsigned int h_reserved: 1; /* handle with reserved credits */ unsigned int h_aborted: 1; /* fatal error on handle */ unsigned int h_type: 8; /* for handle statistics */ unsigned int h_line_no: 16; /* for handle statistics */ @@ -690,6 +698,7 @@ jbd2_time_diff(unsigned long start, unsigned long end) * @j_wait_done_commit: Wait queue for waiting for commit to complete * @j_wait_commit: Wait queue to trigger commit * @j_wait_updates: Wait queue to wait for updates to complete + * @j_wait_reserved: Wait queue to wait for reserved buffer credits to drop * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints * @j_head: Journal head - identifies the first unused block in the journal * @j_tail: Journal tail - identifies the oldest still-used block in the @@ -703,6 +712,7 @@ jbd2_time_diff(unsigned long start, unsigned long end) * journal * @j_fs_dev: Device which holds the client fs. For internal journal this will * be equal to j_dev + * @j_reserved_credits: Number of buffers reserved from the running transaction * @j_maxlen: Total maximum capacity of the journal region on disk. * @j_list_lock: Protects the buffer lists and internal buffer state. * @j_inode: Optional inode where we store the journal. If present, all journal @@ -801,6 +811,9 @@ struct journal_s /* Wait queue to wait for updates to complete */ wait_queue_head_t j_wait_updates; + /* Wait queue to wait for reserved buffer credits to drop */ + wait_queue_head_t j_wait_reserved; + /* Semaphore for locking against concurrent checkpoints */ struct mutex j_checkpoint_mutex; @@ -855,6 +868,9 @@ struct journal_s /* Total maximum capacity of the journal region on disk. */ unsigned int j_maxlen; + /* Number of buffers reserved from the running transaction */ + atomic_t j_reserved_credits; + /* * Protects the buffer lists and internal buffer state. */ @@ -1091,10 +1107,14 @@ static inline handle_t *journal_current_handle(void) */ extern handle_t *jbd2_journal_start(journal_t *, int nblocks); -extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask, - unsigned int type, unsigned int line_no); +extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, + gfp_t gfp_mask, unsigned int type, + unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); extern int jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask); +extern int jbd2_journal_start_reserved(handle_t *handle, + unsigned int type, unsigned int line_no); +extern void jbd2_journal_free_reserved(handle_t *handle); extern int jbd2_journal_extend (handle_t *, int nblocks); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); -- cgit v1.2.3-58-ga151 From 5fe2fe895a9a6b857e2f3a7fc5b8f080b03fd55f Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:37:50 -0400 Subject: ext4: provide wrappers for transaction reservation calls Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4_jbd2.c | 58 ++++++++++++++++++++++++++++++++++++--------- fs/ext4/ext4_jbd2.h | 26 ++++++++++++++++---- fs/ext4/ialloc.c | 3 ++- include/trace/events/ext4.h | 41 +++++++++++++++++++++++++------- 4 files changed, 103 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index bd25e782ec6b..72a3600aedbd 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -38,31 +38,43 @@ static void ext4_put_nojournal(handle_t *handle) /* * Wrappers for jbd2_journal_start/end. */ -handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, - int type, int nblocks) +static int ext4_journal_check_start(struct super_block *sb) { journal_t *journal; might_sleep(); - - trace_ext4_journal_start(sb, nblocks, _RET_IP_); if (sb->s_flags & MS_RDONLY) - return ERR_PTR(-EROFS); - + return -EROFS; WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; - if (!journal) - return ext4_get_nojournal(); /* * Special case here: if the journal has aborted behind our * backs (eg. EIO in the commit thread), then we still need to * take the FS itself readonly cleanly. */ - if (is_journal_aborted(journal)) { + if (journal && is_journal_aborted(journal)) { ext4_abort(sb, "Detected aborted journal"); - return ERR_PTR(-EROFS); + return -EROFS; } - return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, type, line); + return 0; +} + +handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, + int type, int blocks, int rsv_blocks) +{ + journal_t *journal; + int err; + + trace_ext4_journal_start(sb, blocks, rsv_blocks, _RET_IP_); + err = ext4_journal_check_start(sb); + if (err < 0) + return ERR_PTR(err); + + journal = EXT4_SB(sb)->s_journal; + if (!journal) + return ext4_get_nojournal(); + return jbd2__journal_start(journal, blocks, rsv_blocks, GFP_NOFS, + type, line); } int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) @@ -86,6 +98,30 @@ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) return err; } +handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, + int type) +{ + struct super_block *sb; + int err; + + if (!ext4_handle_valid(handle)) + return ext4_get_nojournal(); + + sb = handle->h_journal->j_private; + trace_ext4_journal_start_reserved(sb, handle->h_buffer_credits, + _RET_IP_); + err = ext4_journal_check_start(sb); + if (err < 0) { + jbd2_journal_free_reserved(handle); + return ERR_PTR(err); + } + + err = jbd2_journal_start_reserved(handle, type, line); + if (err < 0) + return ERR_PTR(err); + return handle; +} + void ext4_journal_abort_handle(const char *caller, unsigned int line, const char *err_fn, struct buffer_head *bh, handle_t *handle, int err) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index c8c6885406db..fdd865eb1879 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -265,7 +265,7 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, - int type, int nblocks); + int type, int blocks, int rsv_blocks); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096) @@ -300,21 +300,37 @@ static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed) } #define ext4_journal_start_sb(sb, type, nblocks) \ - __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks)) + __ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0) #define ext4_journal_start(inode, type, nblocks) \ - __ext4_journal_start((inode), __LINE__, (type), (nblocks)) + __ext4_journal_start((inode), __LINE__, (type), (nblocks), 0) + +#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks) \ + __ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks)) static inline handle_t *__ext4_journal_start(struct inode *inode, unsigned int line, int type, - int nblocks) + int blocks, int rsv_blocks) { - return __ext4_journal_start_sb(inode->i_sb, line, type, nblocks); + return __ext4_journal_start_sb(inode->i_sb, line, type, blocks, + rsv_blocks); } #define ext4_journal_stop(handle) \ __ext4_journal_stop(__func__, __LINE__, (handle)) +#define ext4_journal_start_reserve(handle, type) \ + __ext4_journal_start_reserved((handle), __LINE__, (type)) + +handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, + int type); + +static inline void ext4_journal_free_reserved(handle_t *handle) +{ + if (ext4_handle_valid(handle)) + jbd2_journal_free_reserved(handle); +} + static inline handle_t *ext4_journal_current_handle(void) { return journal_current_handle(); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 00a818d67b54..f03598c6ffd3 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -747,7 +747,8 @@ repeat_in_this_group: if (!handle) { BUG_ON(nblocks <= 0); handle = __ext4_journal_start_sb(dir->i_sb, line_no, - handle_type, nblocks); + handle_type, nblocks, + 0); if (IS_ERR(handle)) { err = PTR_ERR(handle); ext4_std_error(sb, err); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index e23b2188110a..1f2ea7140d56 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -1640,25 +1640,50 @@ TRACE_EVENT(ext4_load_inode, ); TRACE_EVENT(ext4_journal_start, - TP_PROTO(struct super_block *sb, int nblocks, unsigned long IP), + TP_PROTO(struct super_block *sb, int blocks, int rsv_blocks, + unsigned long IP), - TP_ARGS(sb, nblocks, IP), + TP_ARGS(sb, blocks, rsv_blocks, IP), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, ip ) - __field( int, nblocks ) + __field( int, blocks ) + __field( int, rsv_blocks ) ), TP_fast_assign( - __entry->dev = sb->s_dev; - __entry->ip = IP; - __entry->nblocks = nblocks; + __entry->dev = sb->s_dev; + __entry->ip = IP; + __entry->blocks = blocks; + __entry->rsv_blocks = rsv_blocks; ), - TP_printk("dev %d,%d nblocks %d caller %pF", + TP_printk("dev %d,%d blocks, %d rsv_blocks, %d caller %pF", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->nblocks, (void *)__entry->ip) + __entry->blocks, __entry->rsv_blocks, (void *)__entry->ip) +); + +TRACE_EVENT(ext4_journal_start_reserved, + TP_PROTO(struct super_block *sb, int blocks, unsigned long IP), + + TP_ARGS(sb, blocks, IP), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field(unsigned long, ip ) + __field( int, blocks ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->ip = IP; + __entry->blocks = blocks; + ), + + TP_printk("dev %d,%d blocks, %d caller %pF", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->blocks, (void *)__entry->ip) ); DECLARE_EVENT_CLASS(ext4__trim, -- cgit v1.2.3-58-ga151 From 4e7ea81db53465ddd753678bc4cebf95369d0984 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 13:17:40 -0400 Subject: ext4: restructure writeback path There are two issues with current writeback path in ext4. For one we don't necessarily map complete pages when blocksize < pagesize and thus needn't do any writeback in one iteration. We always map some blocks though so we will eventually finish mapping the page. Just if writeback races with other operations on the file, forward progress is not really guaranteed. The second problem is that current code structure makes it hard to associate all the bios to some range of pages with one io_end structure so that unwritten extents can be converted after all the bios are finished. This will be especially difficult later when io_end will be associated with reserved transaction handle. We restructure the writeback path to a relatively simple loop which first prepares extent of pages, then maps one or more extents so that no page is partially mapped, and once page is fully mapped it is submitted for IO. We keep all the mapping and IO submission information in mpage_da_data structure to somewhat reduce stack usage. Resulting code is somewhat shorter than the old one and hopefully also easier to read. Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/ext4.h | 15 - fs/ext4/inode.c | 1011 +++++++++++++++++++++---------------------- fs/ext4/page-io.c | 4 - include/trace/events/ext4.h | 64 ++- 4 files changed, 527 insertions(+), 567 deletions(-) (limited to 'include') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2ebfcde5a156..90a164f365c4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -176,21 +176,6 @@ struct ext4_map_blocks { unsigned int m_flags; }; -/* - * For delayed allocation tracking - */ -struct mpage_da_data { - struct inode *inode; - sector_t b_blocknr; /* start block number of extent */ - size_t b_size; /* size of extent */ - unsigned long b_state; /* state of the extent */ - unsigned long first_page, next_page; /* extent of pages */ - struct writeback_control *wbc; - int io_done; - int pages_written; - int retval; -}; - /* * Flags for ext4_io_end->flags */ diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2b777e51b677..5939a4742def 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1407,149 +1407,42 @@ static void ext4_da_page_release_reservation(struct page *page, * Delayed allocation stuff */ -static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd); - -/* - * mpage_da_submit_io - walks through extent of pages and try to write - * them with writepage() call back - * - * @mpd->inode: inode - * @mpd->first_page: first page of the extent - * @mpd->next_page: page after the last page of the extent - * - * By the time mpage_da_submit_io() is called we expect all blocks - * to be allocated. this may be wrong if allocation failed. - * - * As pages are already locked by write_cache_pages(), we can't use it - */ -static int mpage_da_submit_io(struct mpage_da_data *mpd, - struct ext4_map_blocks *map) -{ - struct pagevec pvec; - unsigned long index, end; - int ret = 0, err, nr_pages, i; - struct inode *inode = mpd->inode; - struct address_space *mapping = inode->i_mapping; - loff_t size = i_size_read(inode); - unsigned int len, block_start; - struct buffer_head *bh, *page_bufs = NULL; - sector_t pblock = 0, cur_logical = 0; - struct ext4_io_submit io_submit; - - BUG_ON(mpd->next_page <= mpd->first_page); - ext4_io_submit_init(&io_submit, mpd->wbc); - io_submit.io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_submit.io_end) { - ext4_da_block_invalidatepages(mpd); - return -ENOMEM; - } +struct mpage_da_data { + struct inode *inode; + struct writeback_control *wbc; + pgoff_t first_page; /* The first page to write */ + pgoff_t next_page; /* Current page to examine */ + pgoff_t last_page; /* Last page to examine */ /* - * We need to start from the first_page to the next_page - 1 - * to make sure we also write the mapped dirty buffer_heads. - * If we look at mpd->b_blocknr we would only be looking - * at the currently mapped buffer_heads. + * Extent to map - this can be after first_page because that can be + * fully mapped. We somewhat abuse m_flags to store whether the extent + * is delalloc or unwritten. */ - index = mpd->first_page; - end = mpd->next_page - 1; - - pagevec_init(&pvec, 0); - while (index <= end) { - nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); - if (nr_pages == 0) - break; - for (i = 0; i < nr_pages; i++) { - int skip_page = 0; - struct page *page = pvec.pages[i]; - - index = page->index; - if (index > end) - break; - - if (index == size >> PAGE_CACHE_SHIFT) - len = size & ~PAGE_CACHE_MASK; - else - len = PAGE_CACHE_SIZE; - if (map) { - cur_logical = index << (PAGE_CACHE_SHIFT - - inode->i_blkbits); - pblock = map->m_pblk + (cur_logical - - map->m_lblk); - } - index++; - - BUG_ON(!PageLocked(page)); - BUG_ON(PageWriteback(page)); - - bh = page_bufs = page_buffers(page); - block_start = 0; - do { - if (map && (cur_logical >= map->m_lblk) && - (cur_logical <= (map->m_lblk + - (map->m_len - 1)))) { - if (buffer_delay(bh)) { - clear_buffer_delay(bh); - bh->b_blocknr = pblock; - } - if (buffer_unwritten(bh) || - buffer_mapped(bh)) - BUG_ON(bh->b_blocknr != pblock); - if (map->m_flags & EXT4_MAP_UNINIT) - set_buffer_uninit(bh); - clear_buffer_unwritten(bh); - } - - /* - * skip page if block allocation undone and - * block is dirty - */ - if (ext4_bh_delay_or_unwritten(NULL, bh)) - skip_page = 1; - bh = bh->b_this_page; - block_start += bh->b_size; - cur_logical++; - pblock++; - } while (bh != page_bufs); - - if (skip_page) { - unlock_page(page); - continue; - } - - clear_page_dirty_for_io(page); - err = ext4_bio_write_page(&io_submit, page, len, - mpd->wbc); - if (!err) - mpd->pages_written++; - /* - * In error case, we have to continue because - * remaining pages are still locked - */ - if (ret == 0) - ret = err; - } - pagevec_release(&pvec); - } - ext4_io_submit(&io_submit); - /* Drop io_end reference we got from init */ - ext4_put_io_end_defer(io_submit.io_end); - return ret; -} + struct ext4_map_blocks map; + struct ext4_io_submit io_submit; /* IO submission data */ +}; -static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd) +static void mpage_release_unused_pages(struct mpage_da_data *mpd, + bool invalidate) { int nr_pages, i; pgoff_t index, end; struct pagevec pvec; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; - ext4_lblk_t start, last; + + /* This is necessary when next_page == 0. */ + if (mpd->first_page >= mpd->next_page) + return; index = mpd->first_page; end = mpd->next_page - 1; - - start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits); - ext4_es_remove_extent(inode, start, last - start + 1); + if (invalidate) { + ext4_lblk_t start, last; + start = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + last = end << (PAGE_CACHE_SHIFT - inode->i_blkbits); + ext4_es_remove_extent(inode, start, last - start + 1); + } pagevec_init(&pvec, 0); while (index <= end) { @@ -1562,14 +1455,15 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd) break; BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); - block_invalidatepage(page, 0, PAGE_CACHE_SIZE); - ClearPageUptodate(page); + if (invalidate) { + block_invalidatepage(page, 0, PAGE_CACHE_SIZE); + ClearPageUptodate(page); + } unlock_page(page); } index = pvec.pages[nr_pages - 1]->index + 1; pagevec_release(&pvec); } - return; } static void ext4_print_free_blocks(struct inode *inode) @@ -1598,215 +1492,6 @@ static void ext4_print_free_blocks(struct inode *inode) return; } -/* - * mpage_da_map_and_submit - go through given space, map them - * if necessary, and then submit them for I/O - * - * @mpd - bh describing space - * - * The function skips space we know is already mapped to disk blocks. - * - */ -static void mpage_da_map_and_submit(struct mpage_da_data *mpd) -{ - int err, blks, get_blocks_flags; - struct ext4_map_blocks map, *mapp = NULL; - sector_t next = mpd->b_blocknr; - unsigned max_blocks = mpd->b_size >> mpd->inode->i_blkbits; - loff_t disksize = EXT4_I(mpd->inode)->i_disksize; - handle_t *handle = NULL; - - /* - * If the blocks are mapped already, or we couldn't accumulate - * any blocks, then proceed immediately to the submission stage. - */ - if ((mpd->b_size == 0) || - ((mpd->b_state & (1 << BH_Mapped)) && - !(mpd->b_state & (1 << BH_Delay)) && - !(mpd->b_state & (1 << BH_Unwritten)))) - goto submit_io; - - handle = ext4_journal_current_handle(); - BUG_ON(!handle); - - /* - * Call ext4_map_blocks() to allocate any delayed allocation - * blocks, or to convert an uninitialized extent to be - * initialized (in the case where we have written into - * one or more preallocated blocks). - * - * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE to - * indicate that we are on the delayed allocation path. This - * affects functions in many different parts of the allocation - * call path. This flag exists primarily because we don't - * want to change *many* call functions, so ext4_map_blocks() - * will set the EXT4_STATE_DELALLOC_RESERVED flag once the - * inode's allocation semaphore is taken. - * - * If the blocks in questions were delalloc blocks, set - * EXT4_GET_BLOCKS_DELALLOC_RESERVE so the delalloc accounting - * variables are updated after the blocks have been allocated. - */ - map.m_lblk = next; - map.m_len = max_blocks; - /* - * We're in delalloc path and it is possible that we're going to - * need more metadata blocks than previously reserved. However - * we must not fail because we're in writeback and there is - * nothing we can do about it so it might result in data loss. - * So use reserved blocks to allocate metadata if possible. - */ - get_blocks_flags = EXT4_GET_BLOCKS_CREATE | - EXT4_GET_BLOCKS_METADATA_NOFAIL; - if (ext4_should_dioread_nolock(mpd->inode)) - get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; - if (mpd->b_state & (1 << BH_Delay)) - get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; - - - blks = ext4_map_blocks(handle, mpd->inode, &map, get_blocks_flags); - if (blks < 0) { - struct super_block *sb = mpd->inode->i_sb; - - err = blks; - /* - * If get block returns EAGAIN or ENOSPC and there - * appears to be free blocks we will just let - * mpage_da_submit_io() unlock all of the pages. - */ - if (err == -EAGAIN) - goto submit_io; - - if (err == -ENOSPC && ext4_count_free_clusters(sb)) { - mpd->retval = err; - goto submit_io; - } - - /* - * get block failure will cause us to loop in - * writepages, because a_ops->writepage won't be able - * to make progress. The page will be redirtied by - * writepage and writepages will again try to write - * the same. - */ - if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) { - ext4_msg(sb, KERN_CRIT, - "delayed block allocation failed for inode %lu " - "at logical offset %llu with max blocks %zd " - "with error %d", mpd->inode->i_ino, - (unsigned long long) next, - mpd->b_size >> mpd->inode->i_blkbits, err); - ext4_msg(sb, KERN_CRIT, - "This should not happen!! Data will be lost"); - if (err == -ENOSPC) - ext4_print_free_blocks(mpd->inode); - } - /* invalidate all the pages */ - ext4_da_block_invalidatepages(mpd); - - /* Mark this page range as having been completed */ - mpd->io_done = 1; - return; - } - BUG_ON(blks == 0); - - mapp = ↦ - if (map.m_flags & EXT4_MAP_NEW) { - struct block_device *bdev = mpd->inode->i_sb->s_bdev; - int i; - - for (i = 0; i < map.m_len; i++) - unmap_underlying_metadata(bdev, map.m_pblk + i); - } - - /* - * Update on-disk size along with block allocation. - */ - disksize = ((loff_t) next + blks) << mpd->inode->i_blkbits; - if (disksize > i_size_read(mpd->inode)) - disksize = i_size_read(mpd->inode); - if (disksize > EXT4_I(mpd->inode)->i_disksize) { - ext4_update_i_disksize(mpd->inode, disksize); - err = ext4_mark_inode_dirty(handle, mpd->inode); - if (err) - ext4_error(mpd->inode->i_sb, - "Failed to mark inode %lu dirty", - mpd->inode->i_ino); - } - -submit_io: - mpage_da_submit_io(mpd, mapp); - mpd->io_done = 1; -} - -#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \ - (1 << BH_Delay) | (1 << BH_Unwritten)) - -/* - * mpage_add_bh_to_extent - try to add one more block to extent of blocks - * - * @mpd->lbh - extent of blocks - * @logical - logical number of the block in the file - * @b_state - b_state of the buffer head added - * - * the function is used to collect contig. blocks in same state - */ -static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, sector_t logical, - unsigned long b_state) -{ - sector_t next; - int blkbits = mpd->inode->i_blkbits; - int nrblocks = mpd->b_size >> blkbits; - - /* - * XXX Don't go larger than mballoc is willing to allocate - * This is a stopgap solution. We eventually need to fold - * mpage_da_submit_io() into this function and then call - * ext4_map_blocks() multiple times in a loop - */ - if (nrblocks >= (8*1024*1024 >> blkbits)) - goto flush_it; - - /* check if the reserved journal credits might overflow */ - if (!ext4_test_inode_flag(mpd->inode, EXT4_INODE_EXTENTS)) { - if (nrblocks >= EXT4_MAX_TRANS_DATA) { - /* - * With non-extent format we are limited by the journal - * credit available. Total credit needed to insert - * nrblocks contiguous blocks is dependent on the - * nrblocks. So limit nrblocks. - */ - goto flush_it; - } - } - /* - * First block in the extent - */ - if (mpd->b_size == 0) { - mpd->b_blocknr = logical; - mpd->b_size = 1 << blkbits; - mpd->b_state = b_state & BH_FLAGS; - return; - } - - next = mpd->b_blocknr + nrblocks; - /* - * Can we merge the block to our big extent? - */ - if (logical == next && (b_state & BH_FLAGS) == mpd->b_state) { - mpd->b_size += 1 << blkbits; - return; - } - -flush_it: - /* - * We couldn't merge the block to our extent, so we - * need to flush current extent and start new one - */ - mpage_da_map_and_submit(mpd); - return; -} - static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh) { return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh); @@ -2204,6 +1889,8 @@ static int ext4_writepage(struct page *page, return ret; } +#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay)) + /* * mballoc gives us at most this number of blocks... * XXX: That seems to be only a limitation of ext4_mb_normalize_request(). @@ -2211,6 +1898,315 @@ static int ext4_writepage(struct page *page, */ #define MAX_WRITEPAGES_EXTENT_LEN 2048 +/* + * mpage_add_bh_to_extent - try to add bh to extent of blocks to map + * + * @mpd - extent of blocks + * @lblk - logical number of the block in the file + * @b_state - b_state of the buffer head added + * + * the function is used to collect contig. blocks in same state + */ +static int mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, + unsigned long b_state) +{ + struct ext4_map_blocks *map = &mpd->map; + + /* Don't go larger than mballoc is willing to allocate */ + if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN) + return 0; + + /* First block in the extent? */ + if (map->m_len == 0) { + map->m_lblk = lblk; + map->m_len = 1; + map->m_flags = b_state & BH_FLAGS; + return 1; + } + + /* Can we merge the block to our big extent? */ + if (lblk == map->m_lblk + map->m_len && + (b_state & BH_FLAGS) == map->m_flags) { + map->m_len++; + return 1; + } + return 0; +} + +static bool add_page_bufs_to_extent(struct mpage_da_data *mpd, + struct buffer_head *head, + struct buffer_head *bh, + ext4_lblk_t lblk) +{ + struct inode *inode = mpd->inode; + ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) + >> inode->i_blkbits; + + do { + BUG_ON(buffer_locked(bh)); + + if (!buffer_dirty(bh) || !buffer_mapped(bh) || + (!buffer_delay(bh) && !buffer_unwritten(bh)) || + lblk >= blocks) { + /* Found extent to map? */ + if (mpd->map.m_len) + return false; + if (lblk >= blocks) + return true; + continue; + } + if (!mpage_add_bh_to_extent(mpd, lblk, bh->b_state)) + return false; + } while (lblk++, (bh = bh->b_this_page) != head); + return true; +} + +static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) +{ + int len; + loff_t size = i_size_read(mpd->inode); + int err; + + BUG_ON(page->index != mpd->first_page); + if (page->index == size >> PAGE_CACHE_SHIFT) + len = size & ~PAGE_CACHE_MASK; + else + len = PAGE_CACHE_SIZE; + clear_page_dirty_for_io(page); + err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc); + if (!err) + mpd->wbc->nr_to_write--; + mpd->first_page++; + + return err; +} + +/* + * mpage_map_buffers - update buffers corresponding to changed extent and + * submit fully mapped pages for IO + * + * @mpd - description of extent to map, on return next extent to map + * + * Scan buffers corresponding to changed extent (we expect corresponding pages + * to be already locked) and update buffer state according to new extent state. + * We map delalloc buffers to their physical location, clear unwritten bits, + * and mark buffers as uninit when we perform writes to uninitialized extents + * and do extent conversion after IO is finished. If the last page is not fully + * mapped, we update @map to the next extent in the last page that needs + * mapping. Otherwise we submit the page for IO. + */ +static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) +{ + struct pagevec pvec; + int nr_pages, i; + struct inode *inode = mpd->inode; + struct buffer_head *head, *bh; + int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits; + ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1) + >> inode->i_blkbits; + pgoff_t start, end; + ext4_lblk_t lblk; + sector_t pblock; + int err; + + start = mpd->map.m_lblk >> bpp_bits; + end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits; + lblk = start << bpp_bits; + pblock = mpd->map.m_pblk; + + pagevec_init(&pvec, 0); + while (start <= end) { + nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start, + PAGEVEC_SIZE); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + if (page->index > end) + break; + /* Upto 'end' pages must be contiguous */ + BUG_ON(page->index != start); + bh = head = page_buffers(page); + do { + if (lblk < mpd->map.m_lblk) + continue; + if (lblk >= mpd->map.m_lblk + mpd->map.m_len) { + /* + * Buffer after end of mapped extent. + * Find next buffer in the page to map. + */ + mpd->map.m_len = 0; + mpd->map.m_flags = 0; + add_page_bufs_to_extent(mpd, head, bh, + lblk); + pagevec_release(&pvec); + return 0; + } + if (buffer_delay(bh)) { + clear_buffer_delay(bh); + bh->b_blocknr = pblock++; + } + if (mpd->map.m_flags & EXT4_MAP_UNINIT) + set_buffer_uninit(bh); + clear_buffer_unwritten(bh); + } while (++lblk < blocks && + (bh = bh->b_this_page) != head); + + /* + * FIXME: This is going to break if dioread_nolock + * supports blocksize < pagesize as we will try to + * convert potentially unmapped parts of inode. + */ + mpd->io_submit.io_end->size += PAGE_CACHE_SIZE; + /* Page fully mapped - let IO run! */ + err = mpage_submit_page(mpd, page); + if (err < 0) { + pagevec_release(&pvec); + return err; + } + start++; + } + pagevec_release(&pvec); + } + /* Extent fully mapped and matches with page boundary. We are done. */ + mpd->map.m_len = 0; + mpd->map.m_flags = 0; + return 0; +} + +static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) +{ + struct inode *inode = mpd->inode; + struct ext4_map_blocks *map = &mpd->map; + int get_blocks_flags; + int err; + + trace_ext4_da_write_pages_extent(inode, map); + /* + * Call ext4_map_blocks() to allocate any delayed allocation blocks, or + * to convert an uninitialized extent to be initialized (in the case + * where we have written into one or more preallocated blocks). It is + * possible that we're going to need more metadata blocks than + * previously reserved. However we must not fail because we're in + * writeback and there is nothing we can do about it so it might result + * in data loss. So use reserved blocks to allocate metadata if + * possible. + * + * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE if the blocks + * in question are delalloc blocks. This affects functions in many + * different parts of the allocation call path. This flag exists + * primarily because we don't want to change *many* call functions, so + * ext4_map_blocks() will set the EXT4_STATE_DELALLOC_RESERVED flag + * once the inode's allocation semaphore is taken. + */ + get_blocks_flags = EXT4_GET_BLOCKS_CREATE | + EXT4_GET_BLOCKS_METADATA_NOFAIL; + if (ext4_should_dioread_nolock(inode)) + get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; + if (map->m_flags & (1 << BH_Delay)) + get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; + + err = ext4_map_blocks(handle, inode, map, get_blocks_flags); + if (err < 0) + return err; + + BUG_ON(map->m_len == 0); + if (map->m_flags & EXT4_MAP_NEW) { + struct block_device *bdev = inode->i_sb->s_bdev; + int i; + + for (i = 0; i < map->m_len; i++) + unmap_underlying_metadata(bdev, map->m_pblk + i); + } + return 0; +} + +/* + * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length + * mpd->len and submit pages underlying it for IO + * + * @handle - handle for journal operations + * @mpd - extent to map + * + * The function maps extent starting at mpd->lblk of length mpd->len. If it is + * delayed, blocks are allocated, if it is unwritten, we may need to convert + * them to initialized or split the described range from larger unwritten + * extent. Note that we need not map all the described range since allocation + * can return less blocks or the range is covered by more unwritten extents. We + * cannot map more because we are limited by reserved transaction credits. On + * the other hand we always make sure that the last touched page is fully + * mapped so that it can be written out (and thus forward progress is + * guaranteed). After mapping we submit all mapped pages for IO. + */ +static int mpage_map_and_submit_extent(handle_t *handle, + struct mpage_da_data *mpd) +{ + struct inode *inode = mpd->inode; + struct ext4_map_blocks *map = &mpd->map; + int err; + loff_t disksize; + + mpd->io_submit.io_end->offset = + ((loff_t)map->m_lblk) << inode->i_blkbits; + while (map->m_len) { + err = mpage_map_one_extent(handle, mpd); + if (err < 0) { + struct super_block *sb = inode->i_sb; + + /* + * Need to commit transaction to free blocks. Let upper + * layers sort it out. + */ + if (err == -ENOSPC && ext4_count_free_clusters(sb)) + return -ENOSPC; + + if (!(EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)) { + ext4_msg(sb, KERN_CRIT, + "Delayed block allocation failed for " + "inode %lu at logical offset %llu with" + " max blocks %u with error %d", + inode->i_ino, + (unsigned long long)map->m_lblk, + (unsigned)map->m_len, err); + ext4_msg(sb, KERN_CRIT, + "This should not happen!! Data will " + "be lost\n"); + if (err == -ENOSPC) + ext4_print_free_blocks(inode); + } + /* invalidate all the pages */ + mpage_release_unused_pages(mpd, true); + return err; + } + /* + * Update buffer state, submit mapped pages, and get us new + * extent to map + */ + err = mpage_map_and_submit_buffers(mpd); + if (err < 0) + return err; + } + + /* Update on-disk size after IO is submitted */ + disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT; + if (disksize > i_size_read(inode)) + disksize = i_size_read(inode); + if (disksize > EXT4_I(inode)->i_disksize) { + int err2; + + ext4_update_i_disksize(inode, disksize); + err2 = ext4_mark_inode_dirty(handle, inode); + if (err2) + ext4_error(inode->i_sb, + "Failed to mark inode %lu dirty", + inode->i_ino); + if (!err) + err = err2; + } + return err; +} + /* * Calculate the total number of credits to reserve for one writepages * iteration. This is called from ext4_da_writepages(). We map an extent of @@ -2227,44 +2223,49 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode) } /* - * write_cache_pages_da - walk the list of dirty pages of the given - * address space and accumulate pages that need writing, and call - * mpage_da_map_and_submit to map a single contiguous memory region - * and then write them. + * mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages + * and underlying extent to map + * + * @mpd - where to look for pages + * + * Walk dirty pages in the mapping. If they are fully mapped, submit them for + * IO immediately. When we find a page which isn't mapped we start accumulating + * extent of buffers underlying these pages that needs mapping (formed by + * either delayed or unwritten buffers). We also lock the pages containing + * these buffers. The extent found is returned in @mpd structure (starting at + * mpd->lblk with length mpd->len blocks). + * + * Note that this function can attach bios to one io_end structure which are + * neither logically nor physically contiguous. Although it may seem as an + * unnecessary complication, it is actually inevitable in blocksize < pagesize + * case as we need to track IO to all buffers underlying a page in one io_end. */ -static int write_cache_pages_da(handle_t *handle, - struct address_space *mapping, - struct writeback_control *wbc, - struct mpage_da_data *mpd, - pgoff_t *done_index) +static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) { - struct buffer_head *bh, *head; - struct inode *inode = mapping->host; - struct pagevec pvec; - unsigned int nr_pages; - sector_t logical; - pgoff_t index, end; - long nr_to_write = wbc->nr_to_write; - int i, tag, ret = 0; - - memset(mpd, 0, sizeof(struct mpage_da_data)); - mpd->wbc = wbc; - mpd->inode = inode; - pagevec_init(&pvec, 0); - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + struct address_space *mapping = mpd->inode->i_mapping; + struct pagevec pvec; + unsigned int nr_pages; + pgoff_t index = mpd->first_page; + pgoff_t end = mpd->last_page; + int tag; + int i, err = 0; + int blkbits = mpd->inode->i_blkbits; + ext4_lblk_t lblk; + struct buffer_head *head; - if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; - *done_index = index; + pagevec_init(&pvec, 0); + mpd->map.m_len = 0; + mpd->next_page = index; while (index <= end) { nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) - return 0; + goto out; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -2279,31 +2280,21 @@ static int write_cache_pages_da(handle_t *handle, if (page->index > end) goto out; - *done_index = page->index + 1; - - /* - * If we can't merge this page, and we have - * accumulated an contiguous region, write it - */ - if ((mpd->next_page != page->index) && - (mpd->next_page != mpd->first_page)) { - mpage_da_map_and_submit(mpd); - goto ret_extent_tail; - } + /* If we can't merge this page, we are done. */ + if (mpd->map.m_len > 0 && mpd->next_page != page->index) + goto out; lock_page(page); - /* - * If the page is no longer dirty, or its - * mapping no longer corresponds to inode we - * are writing (which means it has been - * truncated or invalidated), or the page is - * already under writeback and we are not - * doing a data integrity writeback, skip the page + * If the page is no longer dirty, or its mapping no + * longer corresponds to inode we are writing (which + * means it has been truncated or invalidated), or the + * page is already under writeback and we are not doing + * a data integrity writeback, skip the page */ if (!PageDirty(page) || (PageWriteback(page) && - (wbc->sync_mode == WB_SYNC_NONE)) || + (mpd->wbc->sync_mode == WB_SYNC_NONE)) || unlikely(page->mapping != mapping)) { unlock_page(page); continue; @@ -2312,101 +2303,57 @@ static int write_cache_pages_da(handle_t *handle, wait_on_page_writeback(page); BUG_ON(PageWriteback(page)); - /* - * If we have inline data and arrive here, it means that - * we will soon create the block for the 1st page, so - * we'd better clear the inline data here. - */ - if (ext4_has_inline_data(inode)) { - BUG_ON(ext4_test_inode_state(inode, - EXT4_STATE_MAY_INLINE_DATA)); - ext4_destroy_inline_data(handle, inode); - } - - if (mpd->next_page != page->index) + if (mpd->map.m_len == 0) mpd->first_page = page->index; mpd->next_page = page->index + 1; - logical = (sector_t) page->index << - (PAGE_CACHE_SHIFT - inode->i_blkbits); - /* Add all dirty buffers to mpd */ + lblk = ((ext4_lblk_t)page->index) << + (PAGE_CACHE_SHIFT - blkbits); head = page_buffers(page); - bh = head; - do { - BUG_ON(buffer_locked(bh)); - /* - * We need to try to allocate unmapped blocks - * in the same page. Otherwise we won't make - * progress with the page in ext4_writepage - */ - if (ext4_bh_delay_or_unwritten(NULL, bh)) { - mpage_add_bh_to_extent(mpd, logical, - bh->b_state); - if (mpd->io_done) - goto ret_extent_tail; - } else if (buffer_dirty(bh) && - buffer_mapped(bh)) { - /* - * mapped dirty buffer. We need to - * update the b_state because we look - * at b_state in mpage_da_map_blocks. - * We don't update b_size because if we - * find an unmapped buffer_head later - * we need to use the b_state flag of - * that buffer_head. - */ - if (mpd->b_size == 0) - mpd->b_state = - bh->b_state & BH_FLAGS; - } - logical++; - } while ((bh = bh->b_this_page) != head); - - if (nr_to_write > 0) { - nr_to_write--; - if (nr_to_write == 0 && - wbc->sync_mode == WB_SYNC_NONE) - /* - * We stop writing back only if we are - * not doing integrity sync. In case of - * integrity sync we have to keep going - * because someone may be concurrently - * dirtying pages, and we might have - * synced a lot of newly appeared dirty - * pages, but have not synced all of the - * old dirty pages. - */ + if (!add_page_bufs_to_extent(mpd, head, head, lblk)) + goto out; + /* So far everything mapped? Submit the page for IO. */ + if (mpd->map.m_len == 0) { + err = mpage_submit_page(mpd, page); + if (err < 0) goto out; } + + /* + * Accumulated enough dirty pages? This doesn't apply + * to WB_SYNC_ALL mode. For integrity sync we have to + * keep going because someone may be concurrently + * dirtying pages, and we might have synced a lot of + * newly appeared dirty pages, but have not synced all + * of the old dirty pages. + */ + if (mpd->wbc->sync_mode == WB_SYNC_NONE && + mpd->next_page - mpd->first_page >= + mpd->wbc->nr_to_write) + goto out; } pagevec_release(&pvec); cond_resched(); } return 0; -ret_extent_tail: - ret = MPAGE_DA_EXTENT_TAIL; out: pagevec_release(&pvec); - cond_resched(); - return ret; + return err; } - static int ext4_da_writepages(struct address_space *mapping, struct writeback_control *wbc) { - pgoff_t index; + pgoff_t writeback_index = 0; + long nr_to_write = wbc->nr_to_write; int range_whole = 0; + int cycled = 1; handle_t *handle = NULL; struct mpage_da_data mpd; struct inode *inode = mapping->host; - int pages_written = 0; - int range_cyclic, cycled = 1, io_done = 0; int needed_blocks, ret = 0; - loff_t range_start = wbc->range_start; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); - pgoff_t done_index = 0; - pgoff_t end; + bool done; struct blk_plug plug; trace_ext4_da_writepages(inode, wbc); @@ -2432,40 +2379,65 @@ static int ext4_da_writepages(struct address_space *mapping, if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) return -EROFS; + /* + * If we have inline data and arrive here, it means that + * we will soon create the block for the 1st page, so + * we'd better clear the inline data here. + */ + if (ext4_has_inline_data(inode)) { + /* Just inode will be modified... */ + handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out_writepages; + } + BUG_ON(ext4_test_inode_state(inode, + EXT4_STATE_MAY_INLINE_DATA)); + ext4_destroy_inline_data(handle, inode); + ext4_journal_stop(handle); + } + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; - range_cyclic = wbc->range_cyclic; if (wbc->range_cyclic) { - index = mapping->writeback_index; - if (index) + writeback_index = mapping->writeback_index; + if (writeback_index) cycled = 0; - wbc->range_start = index << PAGE_CACHE_SHIFT; - wbc->range_end = LLONG_MAX; - wbc->range_cyclic = 0; - end = -1; + mpd.first_page = writeback_index; + mpd.last_page = -1; } else { - index = wbc->range_start >> PAGE_CACHE_SHIFT; - end = wbc->range_end >> PAGE_CACHE_SHIFT; + mpd.first_page = wbc->range_start >> PAGE_CACHE_SHIFT; + mpd.last_page = wbc->range_end >> PAGE_CACHE_SHIFT; } + mpd.inode = inode; + mpd.wbc = wbc; + ext4_io_submit_init(&mpd.io_submit, wbc); retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) - tag_pages_for_writeback(mapping, index, end); - + tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page); + done = false; blk_start_plug(&plug); - while (!ret && wbc->nr_to_write > 0) { + while (!done && mpd.first_page <= mpd.last_page) { + /* For each extent of pages we use new io_end */ + mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); + if (!mpd.io_submit.io_end) { + ret = -ENOMEM; + break; + } /* - * we insert one extent at a time. So we need - * credit needed for single extent allocation. - * journalled mode is currently not supported - * by delalloc + * We have two constraints: We find one extent to map and we + * must always write out whole page (makes a difference when + * blocksize < pagesize) so that we don't block on IO when we + * try to write out the rest of the page. Journalled mode is + * not supported by delalloc. */ BUG_ON(ext4_should_journal_data(inode)); needed_blocks = ext4_da_writepages_trans_blocks(inode); - /* start a new transaction*/ + /* start a new transaction */ handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { @@ -2473,76 +2445,67 @@ retry: ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: " "%ld pages, ino %lu; err %d", __func__, wbc->nr_to_write, inode->i_ino, ret); - blk_finish_plug(&plug); - goto out_writepages; + /* Release allocated io_end */ + ext4_put_io_end(mpd.io_submit.io_end); + break; } - /* - * Now call write_cache_pages_da() to find the next - * contiguous region of logical blocks that need - * blocks to be allocated by ext4 and submit them. - */ - ret = write_cache_pages_da(handle, mapping, - wbc, &mpd, &done_index); - /* - * If we have a contiguous extent of pages and we - * haven't done the I/O yet, map the blocks and submit - * them for I/O. - */ - if (!mpd.io_done && mpd.next_page != mpd.first_page) { - mpage_da_map_and_submit(&mpd); - ret = MPAGE_DA_EXTENT_TAIL; + trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc); + ret = mpage_prepare_extent_to_map(&mpd); + if (!ret) { + if (mpd.map.m_len) + ret = mpage_map_and_submit_extent(handle, &mpd); + else { + /* + * We scanned the whole range (or exhausted + * nr_to_write), submitted what was mapped and + * didn't find anything needing mapping. We are + * done. + */ + done = true; + } } - trace_ext4_da_write_pages(inode, &mpd); - wbc->nr_to_write -= mpd.pages_written; - ext4_journal_stop(handle); - - if ((mpd.retval == -ENOSPC) && sbi->s_journal) { - /* commit the transaction which would + /* Submit prepared bio */ + ext4_io_submit(&mpd.io_submit); + /* Unlock pages we didn't use */ + mpage_release_unused_pages(&mpd, false); + /* Drop our io_end reference we got from init */ + ext4_put_io_end(mpd.io_submit.io_end); + + if (ret == -ENOSPC && sbi->s_journal) { + /* + * Commit the transaction which would * free blocks released in the transaction * and try again */ jbd2_journal_force_commit_nested(sbi->s_journal); ret = 0; - } else if (ret == MPAGE_DA_EXTENT_TAIL) { - /* - * 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 = mpd.retval; - io_done = 1; - } else if (wbc->nr_to_write) - /* - * There is no more writeout needed - * or we requested for a noblocking writeout - * and we found the device congested - */ + continue; + } + /* Fatal error - ENOMEM, EIO... */ + if (ret) break; } blk_finish_plug(&plug); - if (!io_done && !cycled) { + if (!ret && !cycled) { cycled = 1; - index = 0; - wbc->range_start = index << PAGE_CACHE_SHIFT; - wbc->range_end = mapping->writeback_index - 1; + mpd.last_page = writeback_index - 1; + mpd.first_page = 0; goto retry; } /* Update index */ - wbc->range_cyclic = range_cyclic; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) /* - * set the writeback_index so that range_cyclic + * Set the writeback_index so that range_cyclic * mode will write it back later */ - mapping->writeback_index = done_index; + mapping->writeback_index = mpd.first_page; out_writepages: - wbc->range_start = range_start; - trace_ext4_da_writepages_result(inode, wbc, ret, pages_written); + trace_ext4_da_writepages_result(inode, wbc, ret, + nr_to_write - wbc->nr_to_write); return ret; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 19599bded62a..3e5854625126 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -360,9 +360,6 @@ static int io_submit_init_bio(struct ext4_io_submit *io, bio->bi_bdev = bh->b_bdev; bio->bi_end_io = ext4_end_bio; bio->bi_private = ext4_get_io_end(io->io_end); - if (!io->io_end->size) - io->io_end->offset = (bh->b_page->index << PAGE_CACHE_SHIFT) - + bh_offset(bh); io->io_bio = bio; io->io_next_block = bh->b_blocknr; return 0; @@ -390,7 +387,6 @@ submit_and_retry: io_end = io->io_end; if (test_clear_buffer_uninit(bh)) ext4_set_io_unwritten_flag(inode, io_end); - io_end->size += bh->b_size; io->io_next_block++; return 0; } diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 1f2ea7140d56..832a412e6515 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -324,43 +324,59 @@ TRACE_EVENT(ext4_da_writepages, ); TRACE_EVENT(ext4_da_write_pages, - TP_PROTO(struct inode *inode, struct mpage_da_data *mpd), + TP_PROTO(struct inode *inode, pgoff_t first_page, + struct writeback_control *wbc), - TP_ARGS(inode, mpd), + TP_ARGS(inode, first_page, wbc), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) - __field( __u64, b_blocknr ) - __field( __u32, b_size ) - __field( __u32, b_state ) - __field( unsigned long, first_page ) - __field( int, io_done ) - __field( int, pages_written ) - __field( int, sync_mode ) + __field( pgoff_t, first_page ) + __field( long, nr_to_write ) + __field( int, sync_mode ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->b_blocknr = mpd->b_blocknr; - __entry->b_size = mpd->b_size; - __entry->b_state = mpd->b_state; - __entry->first_page = mpd->first_page; - __entry->io_done = mpd->io_done; - __entry->pages_written = mpd->pages_written; - __entry->sync_mode = mpd->wbc->sync_mode; + __entry->first_page = first_page; + __entry->nr_to_write = wbc->nr_to_write; + __entry->sync_mode = wbc->sync_mode; ), - TP_printk("dev %d,%d ino %lu b_blocknr %llu b_size %u b_state 0x%04x " - "first_page %lu io_done %d pages_written %d sync_mode %d", + TP_printk("dev %d,%d ino %lu first_page %lu nr_to_write %ld " + "sync_mode %d", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, - __entry->b_blocknr, __entry->b_size, - __entry->b_state, __entry->first_page, - __entry->io_done, __entry->pages_written, - __entry->sync_mode - ) + (unsigned long) __entry->ino, __entry->first_page, + __entry->nr_to_write, __entry->sync_mode) +); + +TRACE_EVENT(ext4_da_write_pages_extent, + TP_PROTO(struct inode *inode, struct ext4_map_blocks *map), + + TP_ARGS(inode, map), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( __u64, lblk ) + __field( __u32, len ) + __field( __u32, flags ) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = inode->i_ino; + __entry->lblk = map->m_lblk; + __entry->len = map->m_len; + __entry->flags = map->m_flags; + ), + + TP_printk("dev %d,%d ino %lu lblk %llu len %u flags 0x%04x", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long) __entry->ino, __entry->lblk, __entry->len, + __entry->flags) ); TRACE_EVENT(ext4_da_writepages_result, -- cgit v1.2.3-58-ga151 From 20970ba65d5a22f2e4efbfa100377722fde56935 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 6 Jun 2013 14:00:46 -0400 Subject: ext4: use ext4_da_writepages() for all modes Rename ext4_da_writepages() to ext4_writepages() and use it for all modes. We still need to iterate over all the pages in the case of data=journalling, but in the case of nodelalloc/data=ordered (which is what file systems mounted using ext3 backwards compatibility will use) this will allow us to use a much more efficient I/O submission path. Signed-off-by: "Theodore Ts'o" --- fs/ext4/inode.c | 41 +++++++++++++++++++++++++++++++---------- include/trace/events/ext4.h | 4 ++-- 2 files changed, 33 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 442c5d2e0978..0db830d541ec 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1799,7 +1799,7 @@ out: * lock so we have to do some magic. * * This function can get called via... - * - ext4_da_writepages after taking page lock (have journal handle) + * - ext4_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) @@ -2217,7 +2217,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, /* * Calculate the total number of credits to reserve for one writepages - * iteration. This is called from ext4_da_writepages(). We map an extent of + * iteration. This is called from ext4_writepages(). We map an extent of * upto MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN + * bpp - 1 blocks in bpp different extents. @@ -2349,8 +2349,17 @@ out: return err; } -static int ext4_da_writepages(struct address_space *mapping, - struct writeback_control *wbc) +static int __writepage(struct page *page, struct writeback_control *wbc, + void *data) +{ + struct address_space *mapping = data; + int ret = ext4_writepage(page, wbc); + mapping_set_error(mapping, ret); + return ret; +} + +static int ext4_writepages(struct address_space *mapping, + struct writeback_control *wbc) { pgoff_t writeback_index = 0; long nr_to_write = wbc->nr_to_write; @@ -2364,7 +2373,7 @@ static int ext4_da_writepages(struct address_space *mapping, bool done; struct blk_plug plug; - trace_ext4_da_writepages(inode, wbc); + trace_ext4_writepages(inode, wbc); /* * No pages to write? This is mainly a kludge to avoid starting @@ -2374,13 +2383,23 @@ static int ext4_da_writepages(struct address_space *mapping, if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; + if (ext4_should_journal_data(inode)) { + struct blk_plug plug; + int ret; + + blk_start_plug(&plug); + ret = write_cache_pages(mapping, wbc, __writepage, mapping); + blk_finish_plug(&plug); + return ret; + } + /* * If the filesystem has aborted, it is read-only, so return * right away instead of dumping stack traces later on that * will obscure the real source of the problem. We test * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because * the latter could be true if the filesystem is mounted - * read-only, and in that case, ext4_da_writepages should + * read-only, and in that case, ext4_writepages should * *never* be called, so if that ever happens, we would want * the stack trace. */ @@ -2520,8 +2539,8 @@ retry: mapping->writeback_index = mpd.first_page; out_writepages: - trace_ext4_da_writepages_result(inode, wbc, ret, - nr_to_write - wbc->nr_to_write); + trace_ext4_writepages_result(inode, wbc, ret, + nr_to_write - wbc->nr_to_write); return ret; } @@ -2769,7 +2788,7 @@ int ext4_alloc_da_blocks(struct inode *inode) * laptop_mode, not even desirable). However, to do otherwise * would require replicating code paths in: * - * ext4_da_writepages() -> + * ext4_writepages() -> * write_cache_pages() ---> (via passed in callback function) * __mpage_da_writepage() --> * mpage_add_bh_to_extent() @@ -3213,6 +3232,7 @@ static const struct address_space_operations ext4_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, + .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_write_end, .bmap = ext4_bmap, @@ -3228,6 +3248,7 @@ static const struct address_space_operations ext4_journalled_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, + .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, .set_page_dirty = ext4_journalled_set_page_dirty, @@ -3243,7 +3264,7 @@ static const struct address_space_operations ext4_da_aops = { .readpage = ext4_readpage, .readpages = ext4_readpages, .writepage = ext4_writepage, - .writepages = ext4_da_writepages, + .writepages = ext4_writepages, .write_begin = ext4_da_write_begin, .write_end = ext4_da_write_end, .bmap = ext4_bmap, diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 832a412e6515..72f523eb82e0 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -281,7 +281,7 @@ DEFINE_EVENT(ext4__write_end, ext4_da_write_end, TP_ARGS(inode, pos, len, copied) ); -TRACE_EVENT(ext4_da_writepages, +TRACE_EVENT(ext4_writepages, TP_PROTO(struct inode *inode, struct writeback_control *wbc), TP_ARGS(inode, wbc), @@ -379,7 +379,7 @@ TRACE_EVENT(ext4_da_write_pages_extent, __entry->flags) ); -TRACE_EVENT(ext4_da_writepages_result, +TRACE_EVENT(ext4_writepages_result, TP_PROTO(struct inode *inode, struct writeback_control *wbc, int ret, int pages_written), -- cgit v1.2.3-58-ga151 From 9ff864462477206bc23b405a6ae506e92fb6dc9c Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 12 Jun 2013 22:24:07 -0400 Subject: jbd2: optimize jbd2_journal_force_commit Current implementation of jbd2_journal_force_commit() is suboptimal because result in empty and useless commits. But callers just want to force and wait any unfinished commits. We already have jbd2_journal_force_commit_nested() which does exactly what we want, except we are guaranteed that we do not hold journal transaction open. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/jbd2/journal.c | 62 +++++++++++++++++++++++++++++++++++++++------------ fs/jbd2/transaction.c | 23 ------------------- include/linux/jbd2.h | 2 +- 3 files changed, 49 insertions(+), 38 deletions(-) (limited to 'include') diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 70990d682a0c..0e6c13bdcc14 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -529,20 +529,17 @@ int jbd2_log_start_commit(journal_t *journal, tid_t tid) } /* - * Force and wait upon a commit if the calling process is not within - * transaction. This is used for forcing out undo-protected data which contains - * bitmaps, when the fs is running out of space. - * - * We can only force the running transaction if we don't have an active handle; - * otherwise, we will deadlock. - * - * Returns true if a transaction was started. + * Force and wait any uncommitted transactions. We can only force the running + * transaction if we don't have an active handle, otherwise, we will deadlock. + * Returns: <0 in case of error, + * 0 if nothing to commit, + * 1 if transaction was successfully committed. */ -int jbd2_journal_force_commit_nested(journal_t *journal) +static int __jbd2_journal_force_commit(journal_t *journal) { transaction_t *transaction = NULL; tid_t tid; - int need_to_start = 0; + int need_to_start = 0, ret = 0; read_lock(&journal->j_state_lock); if (journal->j_running_transaction && !current->journal_info) { @@ -553,16 +550,53 @@ int jbd2_journal_force_commit_nested(journal_t *journal) transaction = journal->j_committing_transaction; if (!transaction) { + /* Nothing to commit */ read_unlock(&journal->j_state_lock); - return 0; /* Nothing to retry */ + return 0; } - tid = transaction->t_tid; read_unlock(&journal->j_state_lock); if (need_to_start) jbd2_log_start_commit(journal, tid); - jbd2_log_wait_commit(journal, tid); - return 1; + ret = jbd2_log_wait_commit(journal, tid); + if (!ret) + ret = 1; + + return ret; +} + +/** + * Force and wait upon a commit if the calling process is not within + * transaction. This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. + * + * @journal: journal to force + * Returns true if progress was made. + */ +int jbd2_journal_force_commit_nested(journal_t *journal) +{ + int ret; + + ret = __jbd2_journal_force_commit(journal); + return ret > 0; +} + +/** + * int journal_force_commit() - force any uncommitted transactions + * @journal: journal to force + * + * Caller want unconditional commit. We can only force the running transaction + * if we don't have an active handle, otherwise, we will deadlock. + */ +int jbd2_journal_force_commit(journal_t *journal) +{ + int ret; + + J_ASSERT(!current->journal_info); + ret = __jbd2_journal_force_commit(journal); + if (ret > 0) + ret = 0; + return ret; } /* diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f33342a2a95e..dd422e680418 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1661,29 +1661,6 @@ int jbd2_journal_stop(handle_t *handle) return err; } -/** - * int jbd2_journal_force_commit() - force any uncommitted transactions - * @journal: journal to force - * - * For synchronous operations: force any uncommitted transactions - * to disk. May seem kludgy, but it reuses all the handle batching - * code in a very simple manner. - */ -int jbd2_journal_force_commit(journal_t *journal) -{ - handle_t *handle; - int ret; - - handle = jbd2_journal_start(journal, 1); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - } else { - handle->h_sync = 1; - ret = jbd2_journal_stop(handle); - } - return ret; -} - /* * * List management code snippets: various functions for manipulating the diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fb91c8debe6a..c3645b9475f1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1160,6 +1160,7 @@ extern void jbd2_journal_ack_err (journal_t *); extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); +extern int jbd2_journal_force_commit_nested(journal_t *); extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); @@ -1235,7 +1236,6 @@ extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); int jbd2_log_start_commit(journal_t *journal, tid_t tid); int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); -int jbd2_journal_force_commit_nested(journal_t *journal); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); -- cgit v1.2.3-58-ga151 From 06a407f13daf9e48f0ef7189c7e54082b53940c7 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 12 Jun 2013 22:25:07 -0400 Subject: ext4: fix data integrity for ext4_sync_fs Inode's data or non journaled quota may be written w/o jounral so we _must_ send a barrier at the end of ext4_sync_fs. But it can be skipped if journal commit will do it for us. Also fix data integrity for nojournal mode. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 36 +++++++++++++++++++++++++++++++++++- include/linux/jbd2.h | 13 +++++++++++++ 2 files changed, 48 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7c8e1713e203..0f77c2e4b888 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -69,6 +69,7 @@ static void ext4_mark_recovery_complete(struct super_block *sb, static void ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); +static int ext4_sync_fs_nojournal(struct super_block *sb, int wait); static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); @@ -1097,6 +1098,7 @@ static const struct super_operations ext4_nojournal_sops = { .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, + .sync_fs = ext4_sync_fs_nojournal, .put_super = ext4_put_super, .statfs = ext4_statfs, .remount_fs = ext4_remount, @@ -4553,6 +4555,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; tid_t target; + bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); trace_ext4_sync_fs(sb, wait); @@ -4563,10 +4566,41 @@ static int ext4_sync_fs(struct super_block *sb, int wait) * no dirty dquots */ dquot_writeback_dquots(sb, -1); + /* + * Data writeback is possible w/o journal transaction, so barrier must + * being sent at the end of the function. But we can skip it if + * transaction_commit will do it for us. + */ + target = jbd2_get_latest_transaction(sbi->s_journal); + if (wait && sbi->s_journal->j_flags & JBD2_BARRIER && + !jbd2_trans_will_send_data_barrier(sbi->s_journal, target)) + needs_barrier = true; + if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) - jbd2_log_wait_commit(sbi->s_journal, target); + ret = jbd2_log_wait_commit(sbi->s_journal, target); + } + if (needs_barrier) { + int err; + err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL); + if (!ret) + ret = err; } + + return ret; +} + +static int ext4_sync_fs_nojournal(struct super_block *sb, int wait) +{ + int ret = 0; + + trace_ext4_sync_fs(sb, wait); + flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq); + flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq); + dquot_writeback_dquots(sb, -1); + if (wait && test_opt(sb, BARRIER)) + ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL); + return ret; } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index c3645b9475f1..a79783faecad 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1374,6 +1374,19 @@ static inline u32 jbd2_chksum(journal_t *journal, u32 crc, return *(u32 *)desc.ctx; } +/* Return most recent uncommitted transaction */ +static inline tid_t jbd2_get_latest_transaction(journal_t *journal) +{ + tid_t tid; + + read_lock(&journal->j_state_lock); + tid = journal->j_commit_request; + if (journal->j_running_transaction) + tid = journal->j_running_transaction->t_tid; + read_unlock(&journal->j_state_lock); + return tid; +} + #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) -- cgit v1.2.3-58-ga151 From c9b3a8ccb77e063a28a9567eb72e0c1222c4ade4 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 12 Jun 2013 23:02:35 -0400 Subject: jbd/jbd2: relocate bit_spinlock header to jbd_common The bit_spinlock functions are only used for the jbd_lock_bh_state functions (and friends) in jbd_common.h and are not directly used by either of jbd.h or jbd2.h content. The jbd_common file is new as of commit 446066724c36 ("jdb/jbd2: factor out common functions from the jbd[2] header files") but common (and isolated) headers were not considered for factoring at that time. Signed-off-by: Paul Gortmaker Signed-off-by: "Theodore Ts'o" --- include/linux/jbd.h | 1 - include/linux/jbd2.h | 1 - include/linux/jbd_common.h | 2 ++ 3 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 2439054a6c9a..8685d1be12c7 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index a79783faecad..25d9c9ea7a14 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include diff --git a/include/linux/jbd_common.h b/include/linux/jbd_common.h index b1f708976ffd..3dc53432355f 100644 --- a/include/linux/jbd_common.h +++ b/include/linux/jbd_common.h @@ -1,6 +1,8 @@ #ifndef _LINUX_JBD_STATE_H #define _LINUX_JBD_STATE_H +#include + static inline struct buffer_head *jh2bh(struct journal_head *jh) { return jh->b_bh; -- cgit v1.2.3-58-ga151 From 169f1a2a87aae44034da4b9f81be1683d33de6d0 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 12 Jun 2013 23:04:04 -0400 Subject: jbd2: use a single printk for jbd_debug() Since the jbd_debug() is implemented with two separate printk() calls, it can lead to corrupted and misleading debug output like the following (see lines marked with "*"): [ 290.339362] (fs/jbd2/journal.c, 203): kjournald2: kjournald2 wakes [ 290.339365] (fs/jbd2/journal.c, 155): kjournald2: commit_sequence=42103, commit_request=42104 [ 290.339369] (fs/jbd2/journal.c, 158): kjournald2: OK, requests differ [* 290.339376] (fs/jbd2/journal.c, 648): jbd2_log_wait_commit: [* 290.339379] (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: want 42104, j_commit_sequence=42103 [* 290.339382] JBD2: starting commit of transaction 42104 [ 290.339410] (fs/jbd2/revoke.c, 566): jbd2_journal_write_revoke_records: Wrote 0 revoke records [ 290.376555] (fs/jbd2/commit.c, 1088): jbd2_journal_commit_transaction: JBD2: commit 42104 complete, head 42079 i.e. the debug output from log_wait_commit and journal_commit_transaction have become interleaved. The output should have been: (fs/jbd2/journal.c, 648): jbd2_log_wait_commit: JBD2: want 42104, j_commit_sequence=42103 (fs/jbd2/commit.c, 370): jbd2_journal_commit_transaction: JBD2: starting commit of transaction 42104 It is expected that this is not easy to replicate -- I was only able to cause it on preempt-rt kernels, and even then only under heavy I/O load. Reported-by: Paul Gortmaker Suggested-by: "Theodore Ts'o" Signed-off-by: Paul Gortmaker Signed-off-by: "Theodore Ts'o" --- fs/jbd2/journal.c | 18 ++++++++++++++++++ include/linux/jbd2.h | 14 +++++--------- 2 files changed, 23 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0e6c13bdcc14..915dd575cd46 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -103,6 +103,24 @@ EXPORT_SYMBOL(jbd2_inode_cache); static void __journal_abort_soft (journal_t *journal, int errno); static int jbd2_journal_create_slab(size_t slab_size); +#ifdef CONFIG_JBD2_DEBUG +void __jbd2_debug(int level, const char *file, const char *func, + unsigned int line, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + if (level > jbd2_journal_enable_debug) + return; + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf); + va_end(args); +} +EXPORT_SYMBOL(__jbd2_debug); +#endif + /* Checksumming functions */ int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) { diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 25d9c9ea7a14..0302f3f14063 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -56,17 +56,13 @@ */ #define JBD2_EXPENSIVE_CHECKING extern ushort jbd2_journal_enable_debug; +void __jbd2_debug(int level, const char *file, const char *func, + unsigned int line, const char *fmt, ...); -#define jbd_debug(n, f, a...) \ - do { \ - if ((n) <= jbd2_journal_enable_debug) { \ - printk (KERN_DEBUG "(%s, %d): %s: ", \ - __FILE__, __LINE__, __func__); \ - printk (f, ## a); \ - } \ - } while (0) +#define jbd_debug(n, fmt, a...) \ + __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else -#define jbd_debug(f, a...) /**/ +#define jbd_debug(n, fmt, a...) /**/ #endif extern void *jbd2_alloc(size_t size, gfp_t flags); -- cgit v1.2.3-58-ga151 From 21ddd568c133024196d394c43923f55cad1e7bd0 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 1 Jul 2013 08:12:40 -0400 Subject: ext4: translate flag bits to strings in tracepoints Translate the bitfields used in various flags argument to strings to make the tracepoint output more human-readable. Signed-off-by: "Theodore Ts'o" --- fs/ext4/extents.c | 2 +- fs/ext4/indirect.c | 2 +- include/trace/events/ext4.h | 135 +++++++++++++++++++++++++++++++------------- 3 files changed, 98 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 937593e2f006..575faa090253 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4380,7 +4380,7 @@ out2: } out3: - trace_ext4_ext_map_blocks_exit(inode, map, err ? err : allocated); + trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); return err ? err : allocated; } diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 963d23dc1028..87b30cd357e7 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -624,7 +624,7 @@ cleanup: partial--; } out: - trace_ext4_ind_map_blocks_exit(inode, map, err); + trace_ext4_ind_map_blocks_exit(inode, flags, map, err); return err; } diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 72f523eb82e0..2068db241f22 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -19,6 +19,57 @@ struct extent_status; #define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode)) +#define show_mballoc_flags(flags) __print_flags(flags, "|", \ + { EXT4_MB_HINT_MERGE, "HINT_MERGE" }, \ + { EXT4_MB_HINT_RESERVED, "HINT_RESV" }, \ + { EXT4_MB_HINT_METADATA, "HINT_MDATA" }, \ + { EXT4_MB_HINT_FIRST, "HINT_FIRST" }, \ + { EXT4_MB_HINT_BEST, "HINT_BEST" }, \ + { EXT4_MB_HINT_DATA, "HINT_DATA" }, \ + { EXT4_MB_HINT_NOPREALLOC, "HINT_NOPREALLOC" }, \ + { EXT4_MB_HINT_GROUP_ALLOC, "HINT_GRP_ALLOC" }, \ + { EXT4_MB_HINT_GOAL_ONLY, "HINT_GOAL_ONLY" }, \ + { EXT4_MB_HINT_TRY_GOAL, "HINT_TRY_GOAL" }, \ + { EXT4_MB_DELALLOC_RESERVED, "DELALLOC_RESV" }, \ + { EXT4_MB_STREAM_ALLOC, "STREAM_ALLOC" }, \ + { EXT4_MB_USE_ROOT_BLOCKS, "USE_ROOT_BLKS" }, \ + { EXT4_MB_USE_RESERVED, "USE_RESV" }) + +#define show_map_flags(flags) __print_flags(flags, "|", \ + { EXT4_GET_BLOCKS_CREATE, "CREATE" }, \ + { EXT4_GET_BLOCKS_UNINIT_EXT, "UNINIT" }, \ + { EXT4_GET_BLOCKS_DELALLOC_RESERVE, "DELALLOC" }, \ + { EXT4_GET_BLOCKS_PRE_IO, "PRE_IO" }, \ + { EXT4_GET_BLOCKS_CONVERT, "CONVERT" }, \ + { EXT4_GET_BLOCKS_METADATA_NOFAIL, "METADATA_NOFAIL" }, \ + { EXT4_GET_BLOCKS_NO_NORMALIZE, "NO_NORMALIZE" }, \ + { EXT4_GET_BLOCKS_KEEP_SIZE, "KEEP_SIZE" }, \ + { EXT4_GET_BLOCKS_NO_LOCK, "NO_LOCK" }, \ + { EXT4_GET_BLOCKS_NO_PUT_HOLE, "NO_PUT_HOLE" }) + +#define show_mflags(flags) __print_flags(flags, "", \ + { EXT4_MAP_NEW, "N" }, \ + { EXT4_MAP_MAPPED, "M" }, \ + { EXT4_MAP_UNWRITTEN, "U" }, \ + { EXT4_MAP_BOUNDARY, "B" }, \ + { EXT4_MAP_UNINIT, "u" }, \ + { EXT4_MAP_FROM_CLUSTER, "C" }) + +#define show_free_flags(flags) __print_flags(flags, "|", \ + { EXT4_FREE_BLOCKS_METADATA, "METADATA" }, \ + { EXT4_FREE_BLOCKS_FORGET, "FORGET" }, \ + { EXT4_FREE_BLOCKS_VALIDATED, "VALIDATED" }, \ + { EXT4_FREE_BLOCKS_NO_QUOT_UPDATE, "NO_QUOTA" }, \ + { EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER,"1ST_CLUSTER" },\ + { EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER, "LAST_CLUSTER" }) + +#define show_extent_status(status) __print_flags(status, "", \ + { (1 << 3), "W" }, \ + { (1 << 2), "U" }, \ + { (1 << 1), "D" }, \ + { (1 << 0), "H" }) + + TRACE_EVENT(ext4_free_inode, TP_PROTO(struct inode *inode), @@ -373,10 +424,10 @@ TRACE_EVENT(ext4_da_write_pages_extent, __entry->flags = map->m_flags; ), - TP_printk("dev %d,%d ino %lu lblk %llu len %u flags 0x%04x", + TP_printk("dev %d,%d ino %lu lblk %llu len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, - __entry->flags) + show_mflags(__entry->flags)) ); TRACE_EVENT(ext4_writepages_result, @@ -691,10 +742,10 @@ TRACE_EVENT(ext4_request_blocks, __entry->flags = ar->flags; ), - TP_printk("dev %d,%d ino %lu flags %u len %u lblk %u goal %llu " + TP_printk("dev %d,%d ino %lu flags %s len %u lblk %u goal %llu " "lleft %u lright %u pleft %llu pright %llu ", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, __entry->flags, + (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) @@ -733,10 +784,10 @@ TRACE_EVENT(ext4_allocate_blocks, __entry->flags = ar->flags; ), - TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %u " + TP_printk("dev %d,%d ino %lu flags %s len %u block %llu lblk %u " "goal %llu lleft %u lright %u pleft %llu pright %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino, __entry->flags, + (unsigned long) __entry->ino, show_mballoc_flags(__entry->flags), __entry->len, __entry->block, __entry->logical, __entry->goal, __entry->lleft, __entry->lright, __entry->pleft, __entry->pright) @@ -766,11 +817,11 @@ TRACE_EVENT(ext4_free_blocks, __entry->mode = inode->i_mode; ), - TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %d", + TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->mode, __entry->block, __entry->count, - __entry->flags) + show_free_flags(__entry->flags)) ); TRACE_EVENT(ext4_sync_file_enter, @@ -921,7 +972,7 @@ TRACE_EVENT(ext4_mballoc_alloc, ), TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u " - "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x " + "result %u/%d/%u@%u blks %u grps %u cr %u flags %s " "tail %u broken %u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, @@ -932,7 +983,7 @@ TRACE_EVENT(ext4_mballoc_alloc, __entry->result_group, __entry->result_start, __entry->result_len, __entry->result_logical, __entry->found, __entry->groups, __entry->cr, - __entry->flags, __entry->tail, + show_mballoc_flags(__entry->flags), __entry->tail, __entry->buddy ? 1 << __entry->buddy : 0) ); @@ -1546,10 +1597,10 @@ DECLARE_EVENT_CLASS(ext4__map_blocks_enter, __entry->flags = flags; ), - TP_printk("dev %d,%d ino %lu lblk %u len %u flags %u", + TP_printk("dev %d,%d ino %lu lblk %u len %u flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->lblk, __entry->len, __entry->flags) + __entry->lblk, __entry->len, show_map_flags(__entry->flags)) ); DEFINE_EVENT(ext4__map_blocks_enter, ext4_ext_map_blocks_enter, @@ -1567,47 +1618,53 @@ DEFINE_EVENT(ext4__map_blocks_enter, ext4_ind_map_blocks_enter, ); DECLARE_EVENT_CLASS(ext4__map_blocks_exit, - TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret), + TP_PROTO(struct inode *inode, unsigned flags, struct ext4_map_blocks *map, + int ret), - TP_ARGS(inode, map, ret), + TP_ARGS(inode, flags, map, ret), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) + __field( unsigned int, flags ) __field( ext4_fsblk_t, pblk ) __field( ext4_lblk_t, lblk ) __field( unsigned int, len ) - __field( unsigned int, flags ) + __field( unsigned int, mflags ) __field( int, ret ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; + __entry->flags = flags; __entry->pblk = map->m_pblk; __entry->lblk = map->m_lblk; __entry->len = map->m_len; - __entry->flags = map->m_flags; + __entry->mflags = map->m_flags; __entry->ret = ret; ), - TP_printk("dev %d,%d ino %lu lblk %u pblk %llu len %u flags %x ret %d", + TP_printk("dev %d,%d ino %lu flags %s lblk %u pblk %llu len %u " + "mflags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, - __entry->lblk, __entry->pblk, - __entry->len, __entry->flags, __entry->ret) + show_map_flags(__entry->flags), __entry->lblk, __entry->pblk, + __entry->len, show_mflags(__entry->mflags), __entry->ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ext_map_blocks_exit, - TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret), + TP_PROTO(struct inode *inode, unsigned flags, + struct ext4_map_blocks *map, int ret), - TP_ARGS(inode, map, ret) + TP_ARGS(inode, flags, map, ret) ); DEFINE_EVENT(ext4__map_blocks_exit, ext4_ind_map_blocks_exit, - TP_PROTO(struct inode *inode, struct ext4_map_blocks *map, int ret), + TP_PROTO(struct inode *inode, unsigned flags, + struct ext4_map_blocks *map, int ret), - TP_ARGS(inode, map, ret) + TP_ARGS(inode, flags, map, ret) ); TRACE_EVENT(ext4_ext_load_extent, @@ -1779,12 +1836,12 @@ TRACE_EVENT(ext4_ext_handle_uninitialized_extents, __entry->newblk = newblock; ), - TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %x " + TP_printk("dev %d,%d ino %lu m_lblk %u m_pblk %llu m_len %u flags %s " "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, + __entry->len, show_map_flags(__entry->flags), (unsigned int) __entry->allocated, (unsigned long long) __entry->newblk) ); @@ -1812,10 +1869,10 @@ TRACE_EVENT(ext4_get_implied_cluster_alloc_exit, __entry->ret = ret; ), - TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %u ret %d", + TP_printk("dev %d,%d m_lblk %u m_pblk %llu m_len %u m_flags %s ret %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lblk, (unsigned long long) __entry->pblk, - __entry->len, __entry->flags, __entry->ret) + __entry->len, show_mflags(__entry->flags), __entry->ret) ); TRACE_EVENT(ext4_ext_put_in_cache, @@ -2146,7 +2203,7 @@ TRACE_EVENT(ext4_es_insert_extent, __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) - __field( unsigned long long, status ) + __field( char, status ) ), TP_fast_assign( @@ -2155,14 +2212,14 @@ TRACE_EVENT(ext4_es_insert_extent, __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_pblock(es); - __entry->status = ext4_es_status(es); + __entry->status = ext4_es_status(es) >> 60; ), - TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %llx", + TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, - __entry->pblk, __entry->status) + __entry->pblk, show_extent_status(__entry->status)) ); TRACE_EVENT(ext4_es_remove_extent, @@ -2223,7 +2280,7 @@ TRACE_EVENT(ext4_es_find_delayed_extent_range_exit, __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) - __field( unsigned long long, status ) + __field( char, status ) ), TP_fast_assign( @@ -2232,14 +2289,14 @@ TRACE_EVENT(ext4_es_find_delayed_extent_range_exit, __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_pblock(es); - __entry->status = ext4_es_status(es); + __entry->status = ext4_es_status(es) >> 60; ), - TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %llx", + TP_printk("dev %d,%d ino %lu es [%u/%u) mapped %llu status %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->lblk, __entry->len, - __entry->pblk, __entry->status) + __entry->pblk, show_extent_status(__entry->status)) ); TRACE_EVENT(ext4_es_lookup_extent_enter, @@ -2276,7 +2333,7 @@ TRACE_EVENT(ext4_es_lookup_extent_exit, __field( ext4_lblk_t, lblk ) __field( ext4_lblk_t, len ) __field( ext4_fsblk_t, pblk ) - __field( unsigned long long, status ) + __field( char, status ) __field( int, found ) ), @@ -2286,16 +2343,16 @@ TRACE_EVENT(ext4_es_lookup_extent_exit, __entry->lblk = es->es_lblk; __entry->len = es->es_len; __entry->pblk = ext4_es_pblock(es); - __entry->status = ext4_es_status(es); + __entry->status = ext4_es_status(es) >> 60; __entry->found = found; ), - TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %llx", + TP_printk("dev %d,%d ino %lu found %d [%u/%u) %llu %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino, __entry->found, __entry->lblk, __entry->len, __entry->found ? __entry->pblk : 0, - __entry->found ? __entry->status : 0) + show_extent_status(__entry->found ? __entry->status : 0)) ); TRACE_EVENT(ext4_es_shrink_enter, -- cgit v1.2.3-58-ga151 From 41a5b913197c3a25fddef1735dc9b3d1fdc57428 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 1 Jul 2013 08:12:41 -0400 Subject: jbd2: invalidate handle if jbd2_journal_restart() fails If jbd2_journal_restart() fails the handle will have been disconnected from the current transaction. In this situation, the handle must not be used for for any jbd2 function other than jbd2_journal_stop(). Enforce this with by treating a handle which has a NULL transaction pointer as an aborted handle, and issue a kernel warning if jbd2_journal_extent(), jbd2_journal_get_write_access(), jbd2_journal_dirty_metadata(), etc. is called with an invalid handle. This commit also fixes a bug where jbd2_journal_stop() would trip over a kernel jbd2 assertion check when trying to free an invalid handle. Also move the responsibility of setting current->journal_info to start_this_handle(), simplifying the three users of this function. Signed-off-by: "Theodore Ts'o" Reported-by: Younger Liu Cc: Jan Kara --- fs/jbd2/transaction.c | 74 ++++++++++++++++++++++++++++++--------------------- include/linux/jbd2.h | 2 +- 2 files changed, 44 insertions(+), 32 deletions(-) (limited to 'include') diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 383b0fbc6e19..7aa9a32573bb 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -368,6 +368,7 @@ repeat: atomic_read(&transaction->t_outstanding_credits), jbd2_log_space_left(journal)); read_unlock(&journal->j_state_lock); + current->journal_info = handle; lock_map_acquire(&handle->h_lockdep_map); jbd2_journal_free_transaction(new_transaction); @@ -442,14 +443,11 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, handle->h_rsv_handle = rsv_handle; } - current->journal_info = handle; - err = start_this_handle(journal, handle, gfp_mask); if (err < 0) { if (handle->h_rsv_handle) jbd2_free_handle(handle->h_rsv_handle); jbd2_free_handle(handle); - current->journal_info = NULL; return ERR_PTR(err); } handle->h_type = type; @@ -511,16 +509,13 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, } handle->h_journal = NULL; - current->journal_info = handle; /* * GFP_NOFS is here because callers are likely from writeback or * similarly constrained call sites */ ret = start_this_handle(journal, handle, GFP_NOFS); - if (ret < 0) { - current->journal_info = NULL; + if (ret < 0) jbd2_journal_free_reserved(handle); - } handle->h_type = type; handle->h_line_no = line_no; return ret; @@ -550,20 +545,21 @@ EXPORT_SYMBOL(jbd2_journal_start_reserved); int jbd2_journal_extend(handle_t *handle, int nblocks) { transaction_t *transaction = handle->h_transaction; - journal_t *journal = transaction->t_journal; + journal_t *journal; int result; int wanted; - result = -EIO; + WARN_ON(!transaction); if (is_handle_aborted(handle)) - goto out; + return -EROFS; + journal = transaction->t_journal; result = 1; read_lock(&journal->j_state_lock); /* Don't extend a locked-down transaction! */ - if (handle->h_transaction->t_state != T_RUNNING) { + if (transaction->t_state != T_RUNNING) { jbd_debug(3, "denied handle %p %d blocks: " "transaction not running\n", handle, nblocks); goto error_out; @@ -589,7 +585,7 @@ int jbd2_journal_extend(handle_t *handle, int nblocks) } trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev, - handle->h_transaction->t_tid, + transaction->t_tid, handle->h_type, handle->h_line_no, handle->h_buffer_credits, nblocks); @@ -603,7 +599,6 @@ unlock: spin_unlock(&transaction->t_handle_lock); error_out: read_unlock(&journal->j_state_lock); -out: return result; } @@ -626,14 +621,16 @@ out: int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) { transaction_t *transaction = handle->h_transaction; - journal_t *journal = transaction->t_journal; + journal_t *journal; tid_t tid; int need_to_start, ret; + WARN_ON(!transaction); /* If we've had an abort of any type, don't even think about * actually doing the restart! */ if (is_handle_aborted(handle)) return 0; + journal = transaction->t_journal; /* * First unlink the handle from its current transaction, and start the @@ -654,6 +651,8 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) wake_up(&journal->j_wait_updates); tid = transaction->t_tid; spin_unlock(&transaction->t_handle_lock); + handle->h_transaction = NULL; + current->journal_info = NULL; jbd_debug(2, "restarting handle %p\n", handle); need_to_start = !tid_geq(journal->j_commit_request, tid); @@ -783,17 +782,16 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, int force_copy) { struct buffer_head *bh; - transaction_t *transaction; + transaction_t *transaction = handle->h_transaction; journal_t *journal; int error; char *frozen_buffer = NULL; int need_copy = 0; unsigned long start_lock, time_lock; + WARN_ON(!transaction); if (is_handle_aborted(handle)) return -EROFS; - - transaction = handle->h_transaction; journal = transaction->t_journal; jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy); @@ -1052,14 +1050,16 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; - journal_t *journal = transaction->t_journal; + journal_t *journal; struct journal_head *jh = jbd2_journal_add_journal_head(bh); int err; jbd_debug(5, "journal_head %p\n", jh); + WARN_ON(!transaction); err = -EROFS; if (is_handle_aborted(handle)) goto out; + journal = transaction->t_journal; err = 0; JBUFFER_TRACE(jh, "entry"); @@ -1265,12 +1265,14 @@ void jbd2_buffer_abort_trigger(struct journal_head *jh, int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; - journal_t *journal = transaction->t_journal; + journal_t *journal; struct journal_head *jh; int ret = 0; + WARN_ON(!transaction); if (is_handle_aborted(handle)) - goto out; + return -EROFS; + journal = transaction->t_journal; jh = jbd2_journal_grab_journal_head(bh); if (!jh) { ret = -EUCLEAN; @@ -1364,7 +1366,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "file as BJ_Metadata"); spin_lock(&journal->j_list_lock); - __jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_Metadata); + __jbd2_journal_file_buffer(jh, transaction, BJ_Metadata); spin_unlock(&journal->j_list_lock); out_unlock_bh: jbd_unlock_bh_state(bh); @@ -1395,12 +1397,17 @@ out: int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) { transaction_t *transaction = handle->h_transaction; - journal_t *journal = transaction->t_journal; + journal_t *journal; struct journal_head *jh; int drop_reserve = 0; int err = 0; int was_modified = 0; + WARN_ON(!transaction); + if (is_handle_aborted(handle)) + return -EROFS; + journal = transaction->t_journal; + BUFFER_TRACE(bh, "entry"); jbd_lock_bh_state(bh); @@ -1427,7 +1434,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) */ jh->b_modified = 0; - if (jh->b_transaction == handle->h_transaction) { + if (jh->b_transaction == transaction) { J_ASSERT_JH(jh, !jh->b_frozen_data); /* If we are forgetting a buffer which is already part @@ -1522,19 +1529,21 @@ drop: int jbd2_journal_stop(handle_t *handle) { transaction_t *transaction = handle->h_transaction; - journal_t *journal = transaction->t_journal; - int err, wait_for_commit = 0; + journal_t *journal; + int err = 0, wait_for_commit = 0; tid_t tid; pid_t pid; + if (!transaction) + goto free_and_exit; + journal = transaction->t_journal; + J_ASSERT(journal_current_handle() == handle); if (is_handle_aborted(handle)) err = -EIO; - else { + else J_ASSERT(atomic_read(&transaction->t_updates) > 0); - err = 0; - } if (--handle->h_ref > 0) { jbd_debug(4, "h_ref %d -> %d\n", handle->h_ref + 1, @@ -1544,7 +1553,7 @@ int jbd2_journal_stop(handle_t *handle) jbd_debug(4, "Handle %p going down\n", handle); trace_jbd2_handle_stats(journal->j_fs_dev->bd_dev, - handle->h_transaction->t_tid, + transaction->t_tid, handle->h_type, handle->h_line_no, jiffies - handle->h_start_jiffies, handle->h_sync, handle->h_requested_credits, @@ -1657,6 +1666,7 @@ int jbd2_journal_stop(handle_t *handle) if (handle->h_rsv_handle) jbd2_journal_free_reserved(handle->h_rsv_handle); +free_and_exit: jbd2_free_handle(handle); return err; } @@ -2362,10 +2372,12 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode) { transaction_t *transaction = handle->h_transaction; - journal_t *journal = transaction->t_journal; + journal_t *journal; + WARN_ON(!transaction); if (is_handle_aborted(handle)) - return -EIO; + return -EROFS; + journal = transaction->t_journal; jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, transaction->t_tid); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 0302f3f14063..d5b50a19463c 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1266,7 +1266,7 @@ static inline int is_journal_aborted(journal_t *journal) static inline int is_handle_aborted(handle_t *handle) { - if (handle->h_aborted) + if (handle->h_aborted || !handle->h_transaction) return 1; return is_journal_aborted(handle->h_transaction->t_journal); } -- cgit v1.2.3-58-ga151