From 28fd129827b00e12829d48a5290f46277600619b Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Sun, 8 Jan 2006 01:02:14 -0800 Subject: [PATCH] [PATCH] Fix and add EXPORT_SYMBOL(filemap_write_and_wait) This patch add EXPORT_SYMBOL(filemap_write_and_wait) and use it. See mm/filemap.c: And changes the filemap_write_and_wait() and filemap_write_and_wait_range(). Current filemap_write_and_wait() doesn't wait if filemap_fdatawrite() returns error. However, even if filemap_fdatawrite() returned an error, it may have submitted the partially data pages to the device. (e.g. in the case of -ENOSPC) Andrew Morton writes, If filemap_fdatawrite() returns an error, this might be due to some I/O problem: dead disk, unplugged cable, etc. Given the generally crappy quality of the kernel's handling of such exceptions, there's a good chance that the filemap_fdatawait() will get stuck in D state forever. So, this patch doesn't wait if filemap_fdatawrite() returns the -EIO. Trond, could you please review the nfs part? Especially I'm not sure, nfs must use the "filemap_fdatawrite(inode->i_mapping) == 0", or not. Acked-by: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/vfs_dir.c | 3 +-- fs/9p/vfs_file.c | 3 +-- fs/buffer.c | 10 ++------- fs/cifs/file.c | 6 ++--- fs/cifs/inode.c | 3 +-- fs/jfs/jfs_dmap.c | 3 +-- fs/jfs/jfs_imap.c | 6 ++--- fs/jfs/jfs_txnmgr.c | 6 ++--- fs/jfs/jfs_umount.c | 6 ++--- fs/jfs/resize.c | 3 +-- fs/jfs/super.c | 3 +-- fs/nfs/inode.c | 8 ++----- fs/smbfs/file.c | 3 +-- fs/smbfs/inode.c | 3 +-- fs/xfs/linux-2.6/xfs_fs_subr.c | 3 +-- mm/filemap.c | 40 +++++++++++++++++++++++----------- 16 files changed, 48 insertions(+), 61 deletions(-) diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 57a43b8feef5..17089d1905ff 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -193,8 +193,7 @@ int v9fs_dir_release(struct inode *inode, struct file *filp) fid->fid); fidnum = fid->fid; - filemap_fdatawrite(inode->i_mapping); - filemap_fdatawait(inode->i_mapping); + filemap_write_and_wait(inode->i_mapping); if (fidnum >= 0) { dprintk(DEBUG_VFS, "fidopen: %d v9f->fid: %d\n", fid->fidopen, diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 89c849da8504..e13577da9130 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -165,8 +165,7 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl) return -ENOLCK; if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { - filemap_fdatawrite(inode->i_mapping); - filemap_fdatawait(inode->i_mapping); + filemap_write_and_wait(inode->i_mapping); invalidate_inode_pages(&inode->i_data); } diff --git a/fs/buffer.c b/fs/buffer.c index 55023231e460..263df0f192aa 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -153,14 +153,8 @@ int sync_blockdev(struct block_device *bdev) { int ret = 0; - if (bdev) { - int err; - - ret = filemap_fdatawrite(bdev->bd_inode->i_mapping); - err = filemap_fdatawait(bdev->bd_inode->i_mapping); - if (!ret) - ret = err; - } + if (bdev) + ret = filemap_write_and_wait(bdev->bd_inode->i_mapping); return ret; } EXPORT_SYMBOL(sync_blockdev); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 14a1c72ced92..5ade53d7bca8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -127,8 +127,7 @@ static inline int cifs_open_inode_helper(struct inode *inode, struct file *file, if (file->f_dentry->d_inode->i_mapping) { /* BB no need to lock inode until after invalidate since namei code should already have it locked? */ - filemap_fdatawrite(file->f_dentry->d_inode->i_mapping); - filemap_fdatawait(file->f_dentry->d_inode->i_mapping); + filemap_write_and_wait(file->f_dentry->d_inode->i_mapping); } cFYI(1, ("invalidating remote inode since open detected it " "changed")); @@ -419,8 +418,7 @@ static int cifs_reopen_file(struct inode *inode, struct file *file, pCifsInode = CIFS_I(inode); if (pCifsInode) { if (can_flush) { - filemap_fdatawrite(inode->i_mapping); - filemap_fdatawait(inode->i_mapping); + filemap_write_and_wait(inode->i_mapping); /* temporarily disable caching while we go to server to get inode info */ pCifsInode->clientCanCacheAll = FALSE; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 411c1f7f84da..9558f51bca55 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1148,8 +1148,7 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs) /* BB check if we need to refresh inode from server now ? BB */ /* need to flush data before changing file size on server */ - filemap_fdatawrite(direntry->d_inode->i_mapping); - filemap_fdatawait(direntry->d_inode->i_mapping); + filemap_write_and_wait(direntry->d_inode->i_mapping); if (attrs->ia_valid & ATTR_SIZE) { /* To avoid spurious oplock breaks from server, in the case of diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 68000a50ceb6..2967b7393415 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -302,8 +302,7 @@ int dbSync(struct inode *ipbmap) /* * write out dirty pages of bmap */ - filemap_fdatawrite(ipbmap->i_mapping); - filemap_fdatawait(ipbmap->i_mapping); + filemap_write_and_wait(ipbmap->i_mapping); diWriteSpecial(ipbmap, 0); diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 28201b194f53..31b4aa13dd4b 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -265,8 +265,7 @@ int diSync(struct inode *ipimap) /* * write out dirty pages of imap */ - filemap_fdatawrite(ipimap->i_mapping); - filemap_fdatawait(ipimap->i_mapping); + filemap_write_and_wait(ipimap->i_mapping); diWriteSpecial(ipimap, 0); @@ -565,8 +564,7 @@ void diFreeSpecial(struct inode *ip) jfs_err("diFreeSpecial called with NULL ip!"); return; } - filemap_fdatawrite(ip->i_mapping); - filemap_fdatawait(ip->i_mapping); + filemap_write_and_wait(ip->i_mapping); truncate_inode_pages(ip->i_mapping, 0); iput(ip); } diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index b660c93c92de..2ddb6b892bcf 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1231,10 +1231,8 @@ int txCommit(tid_t tid, /* transaction identifier */ * when we don't need to worry about it at all. * * if ((!S_ISDIR(ip->i_mode)) - * && (tblk->flag & COMMIT_DELETE) == 0) { - * filemap_fdatawrite(ip->i_mapping); - * filemap_fdatawait(ip->i_mapping); - * } + * && (tblk->flag & COMMIT_DELETE) == 0) + * filemap_write_and_wait(ip->i_mapping); */ /* diff --git a/fs/jfs/jfs_umount.c b/fs/jfs/jfs_umount.c index 5cf91785b541..21eaf7ac0fcb 100644 --- a/fs/jfs/jfs_umount.c +++ b/fs/jfs/jfs_umount.c @@ -108,8 +108,7 @@ int jfs_umount(struct super_block *sb) * Make sure all metadata makes it to disk before we mark * the superblock as clean */ - filemap_fdatawrite(sbi->direct_inode->i_mapping); - filemap_fdatawait(sbi->direct_inode->i_mapping); + filemap_write_and_wait(sbi->direct_inode->i_mapping); /* * ensure all file system file pages are propagated to their @@ -161,8 +160,7 @@ int jfs_umount_rw(struct super_block *sb) * mark the superblock clean before everything is flushed to * disk. */ - filemap_fdatawrite(sbi->direct_inode->i_mapping); - filemap_fdatawait(sbi->direct_inode->i_mapping); + filemap_write_and_wait(sbi->direct_inode->i_mapping); updateSuper(sb, FM_CLEAN); diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index c6dc254d3253..45180361871c 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -376,8 +376,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) * by txCommit(); */ filemap_fdatawait(ipbmap->i_mapping); - filemap_fdatawrite(ipbmap->i_mapping); - filemap_fdatawait(ipbmap->i_mapping); + filemap_write_and_wait(ipbmap->i_mapping); diWriteSpecial(ipbmap, 0); newPage = nPages; /* first new page number */ diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 4226af3ea91b..8d31f1336431 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -502,8 +502,7 @@ out_no_rw: jfs_err("jfs_umount failed with return code %d", rc); } out_mount_failed: - filemap_fdatawrite(sbi->direct_inode->i_mapping); - filemap_fdatawait(sbi->direct_inode->i_mapping); + filemap_write_and_wait(sbi->direct_inode->i_mapping); truncate_inode_pages(sbi->direct_inode->i_mapping, 0); make_bad_inode(sbi->direct_inode); iput(sbi->direct_inode); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e7bd0d92600f..3e4ba9cb7f80 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -644,10 +644,7 @@ int nfs_sync_mapping(struct address_space *mapping) if (mapping->nrpages == 0) return 0; unmap_mapping_range(mapping, 0, 0, 0); - ret = filemap_fdatawrite(mapping); - if (ret != 0) - goto out; - ret = filemap_fdatawait(mapping); + ret = filemap_write_and_wait(mapping); if (ret != 0) goto out; ret = nfs_wb_all(mapping->host); @@ -864,8 +861,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) nfs_begin_data_update(inode); /* Write all dirty data if we're changing file permissions or size */ if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE)) != 0) { - if (filemap_fdatawrite(inode->i_mapping) == 0) - filemap_fdatawait(inode->i_mapping); + filemap_write_and_wait(inode->i_mapping); nfs_wb_all(inode); } /* diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c index b4fcfa8b55a1..3c6eb3ba718e 100644 --- a/fs/smbfs/file.c +++ b/fs/smbfs/file.c @@ -374,8 +374,7 @@ smb_file_release(struct inode *inode, struct file * file) /* We must flush any dirty pages now as we won't be able to write anything after close. mmap can trigger this. "openers" should perhaps include mmap'ers ... */ - filemap_fdatawrite(inode->i_mapping); - filemap_fdatawait(inode->i_mapping); + filemap_write_and_wait(inode->i_mapping); smb_close(inode); } unlock_kernel(); diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 10b994428fef..6ec88bf59b2d 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -697,8 +697,7 @@ smb_notify_change(struct dentry *dentry, struct iattr *attr) DENTRY_PATH(dentry), (long) inode->i_size, (long) attr->ia_size); - filemap_fdatawrite(inode->i_mapping); - filemap_fdatawait(inode->i_mapping); + filemap_write_and_wait(inode->i_mapping); error = smb_open(dentry, O_WRONLY); if (error) diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c index f89340c61bf2..4fa4b1a5187e 100644 --- a/fs/xfs/linux-2.6/xfs_fs_subr.c +++ b/fs/xfs/linux-2.6/xfs_fs_subr.c @@ -79,8 +79,7 @@ fs_flushinval_pages( struct inode *ip = LINVFS_GET_IP(vp); if (VN_CACHED(vp)) { - filemap_fdatawrite(ip->i_mapping); - filemap_fdatawait(ip->i_mapping); + filemap_write_and_wait(ip->i_mapping); truncate_inode_pages(ip->i_mapping, first); } diff --git a/mm/filemap.c b/mm/filemap.c index 8fdf36508023..478f4c74cc31 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -343,30 +343,44 @@ EXPORT_SYMBOL(filemap_fdatawait); int filemap_write_and_wait(struct address_space *mapping) { - int retval = 0; + int err = 0; if (mapping->nrpages) { - retval = filemap_fdatawrite(mapping); - if (retval == 0) - retval = filemap_fdatawait(mapping); + err = filemap_fdatawrite(mapping); + /* + * Even if the above returned error, the pages may be + * written partially (e.g. -ENOSPC), so we wait for it. + * But the -EIO is special case, it may indicate the worst + * thing (e.g. bug) happened, so we avoid waiting for it. + */ + if (err != -EIO) { + int err2 = filemap_fdatawait(mapping); + if (!err) + err = err2; + } } - return retval; + return err; } +EXPORT_SYMBOL(filemap_write_and_wait); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { - int retval = 0; + int err = 0; if (mapping->nrpages) { - retval = __filemap_fdatawrite_range(mapping, lstart, lend, - WB_SYNC_ALL); - if (retval == 0) - retval = wait_on_page_writeback_range(mapping, - lstart >> PAGE_CACHE_SHIFT, - lend >> PAGE_CACHE_SHIFT); + err = __filemap_fdatawrite_range(mapping, lstart, lend, + WB_SYNC_ALL); + /* See comment of filemap_write_and_wait() */ + if (err != -EIO) { + int err2 = wait_on_page_writeback_range(mapping, + lstart >> PAGE_CACHE_SHIFT, + lend >> PAGE_CACHE_SHIFT); + if (!err) + err = err2; + } } - return retval; + return err; } /*