From 9ea7df534ed2a18157434a496a12cf073ca00c52 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 24 Jun 2011 14:29:41 -0400 Subject: ext4: Rewrite ext4_page_mkwrite() to use generic helpers Rewrite ext4_page_mkwrite() to use __block_page_mkwrite() helper. This removes the need of using i_alloc_sem to avoid races with truncate which seems to be the wrong locking order according to lock ordering documented in mm/rmap.c. Also calling ext4_da_write_begin() as used by the old code seems to be problematic because we can decide to flush delay-allocated blocks which will acquire s_umount semaphore - again creating unpleasant lock dependency if not directly a deadlock. Also add a check for frozen filesystem so that we don't busyloop in page fault when the filesystem is frozen. Signed-off-by: Jan Kara Signed-off-by: Al Viro --- fs/ext4/inode.c | 106 +++++++++++++++++++++++++++++--------------------------- 1 file changed, 55 insertions(+), 51 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index e3126c05100..bd309764557 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5843,80 +5843,84 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) struct page *page = vmf->page; loff_t size; unsigned long len; - int ret = -EINVAL; - void *fsdata; + int ret; struct file *file = vma->vm_file; struct inode *inode = file->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; + handle_t *handle; + get_block_t *get_block; + int retries = 0; /* - * Get i_alloc_sem to stop truncates messing with the inode. We cannot - * get i_mutex because we are already holding mmap_sem. + * This check is racy but catches the common case. We rely on + * __block_page_mkwrite() to do a reliable check. */ - down_read(&inode->i_alloc_sem); - size = i_size_read(inode); - if (page->mapping != mapping || size <= page_offset(page) - || !PageUptodate(page)) { - /* page got truncated from under us? */ - goto out_unlock; + vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); + /* Delalloc case is easy... */ + if (test_opt(inode->i_sb, DELALLOC) && + !ext4_should_journal_data(inode) && + !ext4_nonda_switch(inode->i_sb)) { + do { + ret = __block_page_mkwrite(vma, vmf, + ext4_da_get_block_prep); + } while (ret == -ENOSPC && + ext4_should_retry_alloc(inode->i_sb, &retries)); + goto out_ret; } - ret = 0; lock_page(page); - wait_on_page_writeback(page); - if (PageMappedToDisk(page)) { - up_read(&inode->i_alloc_sem); - return VM_FAULT_LOCKED; + size = i_size_read(inode); + /* Page got truncated from under us? */ + if (page->mapping != mapping || page_offset(page) > size) { + unlock_page(page); + ret = VM_FAULT_NOPAGE; + goto out; } if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; else len = PAGE_CACHE_SIZE; - /* - * return if we have all the buffers mapped. This avoid - * the need to call write_begin/write_end which does a - * journal_start/journal_stop which can block and take - * long time + * Return if we have all the buffers mapped. This avoids the need to do + * journal_start/journal_stop which can block and take a long time */ if (page_has_buffers(page)) { if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, ext4_bh_unmapped)) { - up_read(&inode->i_alloc_sem); - return VM_FAULT_LOCKED; + /* Wait so that we don't change page under IO */ + wait_on_page_writeback(page); + ret = VM_FAULT_LOCKED; + goto out; } } unlock_page(page); - /* - * OK, we need to fill the hole... Do write_begin write_end - * to do block allocation/reservation.We are not holding - * inode.i__mutex here. That allow * parallel write_begin, - * write_end call. lock_page prevent this from happening - * on the same page though - */ - ret = mapping->a_ops->write_begin(file, mapping, page_offset(page), - len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata); - if (ret < 0) - goto out_unlock; - ret = mapping->a_ops->write_end(file, mapping, page_offset(page), - len, len, page, fsdata); - if (ret < 0) - goto out_unlock; - ret = 0; - - /* - * write_begin/end might have created a dirty page and someone - * could wander in and start the IO. Make sure that hasn't - * happened. - */ - lock_page(page); - wait_on_page_writeback(page); - up_read(&inode->i_alloc_sem); - return VM_FAULT_LOCKED; -out_unlock: - if (ret) + /* OK, we need to fill the hole... */ + if (ext4_should_dioread_nolock(inode)) + get_block = ext4_get_block_write; + else + get_block = ext4_get_block; +retry_alloc: + handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); + if (IS_ERR(handle)) { ret = VM_FAULT_SIGBUS; - up_read(&inode->i_alloc_sem); + goto out; + } + ret = __block_page_mkwrite(vma, vmf, get_block); + if (!ret && ext4_should_journal_data(inode)) { + if (walk_page_buffers(handle, page_buffers(page), 0, + PAGE_CACHE_SIZE, NULL, do_journal_get_write_access)) { + unlock_page(page); + ret = VM_FAULT_SIGBUS; + goto out; + } + ext4_set_inode_state(inode, EXT4_STATE_JDATA); + } + ext4_journal_stop(handle); + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry_alloc; +out_ret: + ret = block_page_mkwrite_return(ret); +out: return ret; } -- cgit v1.2.3-70-g09d2 From 562c72aa57c36b178eacc3500a0215651eca9429 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Jun 2011 14:29:45 -0400 Subject: fs: move inode_dio_wait calls into ->setattr Let filesystems handle waiting for direct I/O requests themselves instead of doing it beforehand. This means filesystem-specific locks to prevent new dio referenes from appearing can be held. This is important to allow generalizing i_dio_count to non-DIO_LOCKING filesystems. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/attr.c | 3 --- fs/ext2/inode.c | 2 ++ fs/ext3/inode.c | 3 +++ fs/ext4/inode.c | 2 ++ fs/fat/file.c | 2 ++ fs/gfs2/bmap.c | 2 ++ fs/hfs/inode.c | 2 ++ fs/hfsplus/inode.c | 2 ++ fs/jfs/file.c | 2 ++ fs/nilfs2/inode.c | 2 ++ fs/ocfs2/file.c | 2 ++ fs/reiserfs/inode.c | 3 +++ 12 files changed, 24 insertions(+), 3 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/attr.c b/fs/attr.c index f177ac86fa4..538e27959d3 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -232,9 +232,6 @@ int notify_change(struct dentry * dentry, struct iattr * attr) if (error) return error; - if (ia_valid & ATTR_SIZE) - inode_dio_wait(inode); - if (inode->i_op->setattr) error = inode->i_op->setattr(dentry, attr); else diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 788e09a07f7..06e7c767ab3 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1184,6 +1184,8 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) return -EPERM; + inode_dio_wait(inode); + if (mapping_is_xip(inode->i_mapping)) error = xip_truncate_page(inode->i_mapping, newsize); else if (test_opt(inode->i_sb, NOBH)) diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 3451d23c3ba..99c28b246b8 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3216,6 +3216,9 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) ext3_journal_stop(handle); } + if (attr->ia_valid & ATTR_SIZE) + inode_dio_wait(inode); + if (S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE && attr->ia_size < inode->i_size) { handle_t *handle; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bd309764557..9ec0a2ba250 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5351,6 +5351,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { + inode_dio_wait(inode); + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); diff --git a/fs/fat/file.c b/fs/fat/file.c index a4a3a3c0643..e1587c54d3c 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -397,6 +397,8 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) * sequence. */ if (attr->ia_valid & ATTR_SIZE) { + inode_dio_wait(inode); + if (attr->ia_size > inode->i_size) { error = fat_cont_expand(inode, attr->ia_size); if (error || attr->ia_valid == ATTR_SIZE) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index e65493a8ac0..2cd0e56b889 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1224,6 +1224,8 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize) if (ret) return ret; + inode_dio_wait(inode); + oldsize = inode->i_size; if (newsize >= oldsize) return do_grow(inode, newsize); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index fff16c968e6..48d567cc203 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -615,6 +615,8 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr) if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size != i_size_read(inode)) { + inode_dio_wait(inode); + error = vmtruncate(inode, attr->ia_size); if (error) return error; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b248a6cfcad..b0a0a4b621e 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -296,6 +296,8 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr) if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size != i_size_read(inode)) { + inode_dio_wait(inode); + error = vmtruncate(inode, attr->ia_size); if (error) return error; diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 2f3f531f360..9f32315acef 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -110,6 +110,8 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr) if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) { + inode_dio_wait(inode); + rc = vmtruncate(inode, iattr->ia_size); if (rc) return rc; diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index be8664c6a82..13f113154a9 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -778,6 +778,8 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr) if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size != i_size_read(inode)) { + inode_dio_wait(inode); + err = vmtruncate(inode, iattr->ia_size); if (unlikely(err)) goto out_err; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 2c3a465514a..736283ca4a4 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1142,6 +1142,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) if (status) goto bail_unlock; + inode_dio_wait(inode); + if (i_size_read(inode) > attr->ia_size) { if (ocfs2_should_order_data(inode)) { status = ocfs2_begin_ordered_truncate(inode, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 4fd5bb33dbb..dcf543d8caf 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3114,6 +3114,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) error = -EFBIG; goto out; } + + inode_dio_wait(inode); + /* fill in hole pointers in the expanding truncate case. */ if (attr->ia_size > inode->i_size) { error = generic_cont_expand_simple(inode, attr->ia_size); -- cgit v1.2.3-70-g09d2 From aacfc19c626ebd3daa675652457d71019a1f583f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Jun 2011 14:29:47 -0400 Subject: fs: simplify the blockdev_direct_IO prototype Simple filesystems always pass inode->i_sb_bdev as the block device argument, and never need a end_io handler. Let's simply things for them and for my grepping activity by dropping these arguments. The only thing not falling into that scheme is ext4, which passes and end_io handler without needing special flags (yet), but given how messy the direct I/O code there is use of __blockdev_direct_IO in one instead of two out of three cases isn't going to make a large difference anyway. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/ext2/inode.c | 4 ++-- fs/ext3/inode.c | 5 ++--- fs/ext4/inode.c | 12 ++++++------ fs/fat/inode.c | 4 ++-- fs/hfs/inode.c | 4 ++-- fs/hfsplus/inode.c | 4 ++-- fs/jfs/inode.c | 4 ++-- fs/nilfs2/inode.c | 4 ++-- fs/reiserfs/inode.c | 5 ++--- include/linux/fs.h | 9 ++++----- 10 files changed, 26 insertions(+), 29 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 06e7c767ab3..a8a58f63f07 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -843,8 +843,8 @@ ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, struct inode *inode = mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, - iov, offset, nr_segs, ext2_get_block, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + ext2_get_block); if (ret < 0 && (rw & WRITE)) ext2_write_failed(mapping, offset + iov_length(iov, nr_segs)); return ret; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 99c28b246b8..2978a2a17a5 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1816,9 +1816,8 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, } retry: - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext3_get_block, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + ext3_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9ec0a2ba250..1f35573a34e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3501,10 +3501,8 @@ retry: offset, nr_segs, ext4_get_block, NULL, NULL, 0); else { - ret = blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, - ext4_get_block, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, + offset, nr_segs, ext4_get_block); if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); @@ -3748,11 +3746,13 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, EXT4_I(inode)->cur_aio_dio = iocb->private; } - ret = blockdev_direct_IO(rw, iocb, inode, + ret = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, ext4_get_block_write, - ext4_end_io_dio); + ext4_end_io_dio, + NULL, + DIO_LOCKING | DIO_SKIP_HOLES); if (iocb->private) EXT4_I(inode)->cur_aio_dio = NULL; /* diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 3decce46c38..5942fec22c6 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -211,8 +211,8 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, - iov, offset, nr_segs, fat_get_block, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + fat_get_block); if (ret < 0 && (rw & WRITE)) fat_write_failed(mapping, offset + iov_length(iov, nr_segs)); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 48d567cc203..5e7c3f30961 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -123,8 +123,8 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, hfs_get_block, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + hfs_get_block); /* * In case of error extending write may have instantiated a few diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b0a0a4b621e..5b1cb98741c 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -119,8 +119,8 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, hfsplus_get_block, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + hfsplus_get_block); /* * In case of error extending write may have instantiated a few diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 109655904bb..77b69b27f82 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -329,8 +329,8 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, struct inode *inode = file->f_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, jfs_get_block, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + jfs_get_block); /* * In case of error extending write may have instantiated a few diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 13f113154a9..666628b395f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -259,8 +259,8 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, return 0; /* Needs synchronization with the cleaner */ - size = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, nilfs_get_block, NULL); + size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + nilfs_get_block); /* * In case of error extending write may have instantiated a few diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index dcf543d8caf..2922b90ceac 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3068,9 +3068,8 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, struct inode *inode = file->f_mapping->host; ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, - reiserfs_get_blocks_direct_io, NULL); + ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + reiserfs_get_blocks_direct_io); /* * In case of error extending write may have instantiated a few diff --git a/include/linux/fs.h b/include/linux/fs.h index 2fe920774ab..824453be9fe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2418,12 +2418,11 @@ ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, dio_submit_t submit_io, int flags); static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, - struct inode *inode, struct block_device *bdev, const struct iovec *iov, - loff_t offset, unsigned long nr_segs, get_block_t get_block, - dio_iodone_t end_io) + struct inode *inode, const struct iovec *iov, loff_t offset, + unsigned long nr_segs, get_block_t get_block) { - return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, NULL, + return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, + offset, nr_segs, get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif -- cgit v1.2.3-70-g09d2 From 72c5052ddc3956d847f21c2b8d55c93664a51b2c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Jun 2011 14:29:48 -0400 Subject: fs: move inode_dio_done to the end_io handler For filesystems that delay their end_io processing we should keep our i_dio_count until the the processing is done. Enable this by moving the inode_dio_done call to the end_io handler if one exist. Note that the actual move to the workqueue for ext4 and XFS is not done in this patch yet, but left to the filesystem maintainers. At least for XFS it's not needed yet either as XFS has an internal equivalent to i_dio_count. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/direct-io.c | 7 ++++--- fs/ext4/inode.c | 5 +++++ fs/ocfs2/aops.c | 1 + fs/xfs/linux-2.6/xfs_aops.c | 3 +++ 4 files changed, 13 insertions(+), 3 deletions(-) (limited to 'fs/ext4/inode.c') diff --git a/fs/direct-io.c b/fs/direct-io.c index 0a073c7125a..01d2d9ef609 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -293,11 +293,12 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is if (dio->end_io && dio->result) { dio->end_io(dio->iocb, offset, transferred, dio->map_bh.b_private, ret, is_async); - } else if (is_async) { - aio_complete(dio->iocb, ret, 0); + } else { + if (is_async) + aio_complete(dio->iocb, ret, 0); + inode_dio_done(dio->inode); } - inode_dio_done(dio->inode); return ret; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1f35573a34e..678cde834f1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3573,6 +3573,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, ssize_t size, void *private, int ret, bool is_async) { + struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; ext4_io_end_t *io_end = iocb->private; struct workqueue_struct *wq; unsigned long flags; @@ -3594,6 +3595,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, out: if (is_async) aio_complete(iocb, ret, 0); + inode_dio_done(inode); return; } @@ -3614,6 +3616,9 @@ out: /* queue the work to convert unwritten extents to written */ queue_work(wq, &io_end->work); iocb->private = NULL; + + /* XXX: probably should move into the real I/O completion handler */ + inode_dio_done(inode); } static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 524d6167fb6..c1efe939c77 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -577,6 +577,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb, if (is_async) aio_complete(iocb, ret, 0); + inode_dio_done(inode); } /* diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c index 79ce38be15a..b3b418f519f 100644 --- a/fs/xfs/linux-2.6/xfs_aops.c +++ b/fs/xfs/linux-2.6/xfs_aops.c @@ -1339,6 +1339,9 @@ xfs_end_io_direct_write( } else { xfs_finish_ioend_sync(ioend); } + + /* XXX: probably should move into the real I/O completion handler */ + inode_dio_done(ioend->io_inode); } STATIC ssize_t -- cgit v1.2.3-70-g09d2