[PATCH v2] ext4: Gracefully handle ext4_break_layouts() failure during truncate

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



ext4_break_layouts() may fail e.g. due to a signal being delivered.
Thus we need to handle its failure gracefully and not by taking the
filesystem down. Currently ext4_break_layouts() failure is rare but it
may become more common once RDMA uses layout leases for handling
long-term page pins for DAX mappings.

To handle the failure we need to move ext4_break_layouts() earlier
during setattr handling before we do hard to undo changes such as
modifying inode size. To be able to do that we also have to move some
other checks which are better done without holding i_mmap_sem earlier.

Reported-and-tested-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
 fs/ext4/inode.c | 66 ++++++++++++++++++++++++++++++---------------------------
 1 file changed, 35 insertions(+), 31 deletions(-)

A version of the fix that passes also generic/092 test.

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c7f77c643008..c16071547c9c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5571,7 +5571,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	if (attr->ia_valid & ATTR_SIZE) {
 		handle_t *handle;
 		loff_t oldsize = inode->i_size;
-		int shrink = (attr->ia_size <= inode->i_size);
+		int shrink = (attr->ia_size < inode->i_size);
 
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -5585,18 +5585,33 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
 			inode_inc_iversion(inode);
 
-		if (ext4_should_order_data(inode) &&
-		    (attr->ia_size < inode->i_size)) {
-			error = ext4_begin_ordered_truncate(inode,
+		if (shrink) {
+			if (ext4_should_order_data(inode)) {
+				error = ext4_begin_ordered_truncate(inode,
 							    attr->ia_size);
-			if (error)
-				goto err_out;
+				if (error)
+					goto err_out;
+			}
+			/*
+			 * Blocks are going to be removed from the inode. Wait
+			 * for dio in flight.
+			 */
+			inode_dio_wait(inode);
+		}
+
+		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		rc = ext4_break_layouts(inode);
+		if (rc) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			return rc;
 		}
+
 		if (attr->ia_size != inode->i_size) {
 			handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
 			if (IS_ERR(handle)) {
 				error = PTR_ERR(handle);
-				goto err_out;
+				goto out_mmap_sem;
 			}
 			if (ext4_handle_valid(handle) && shrink) {
 				error = ext4_orphan_add(handle, inode);
@@ -5624,42 +5639,31 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				i_size_write(inode, attr->ia_size);
 			up_write(&EXT4_I(inode)->i_data_sem);
 			ext4_journal_stop(handle);
-			if (error) {
-				if (orphan && inode->i_nlink)
-					ext4_orphan_del(NULL, inode);
-				goto err_out;
+			if (error)
+				goto out_mmap_sem;
+			if (!shrink) {
+				pagecache_isize_extended(inode, oldsize,
+							 inode->i_size);
+			} else if (ext4_should_journal_data(inode)) {
+				ext4_wait_for_tail_page_commit(inode);
 			}
 		}
-		if (!shrink) {
-			pagecache_isize_extended(inode, oldsize, inode->i_size);
-		} else {
-			/*
-			 * Blocks are going to be removed from the inode. Wait
-			 * for dio in flight.
-			 */
-			inode_dio_wait(inode);
-		}
-		if (orphan && ext4_should_journal_data(inode))
-			ext4_wait_for_tail_page_commit(inode);
-		down_write(&EXT4_I(inode)->i_mmap_sem);
-
-		rc = ext4_break_layouts(inode);
-		if (rc) {
-			up_write(&EXT4_I(inode)->i_mmap_sem);
-			error = rc;
-			goto err_out;
-		}
 
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
 		 */
 		truncate_pagecache(inode, inode->i_size);
-		if (shrink) {
+		/*
+		 * Call ext4_truncate() even if i_size didn't change to
+		 * truncate possible preallocated blocks.
+		 */
+		if (attr->ia_size <= oldsize) {
 			rc = ext4_truncate(inode);
 			if (rc)
 				error = rc;
 		}
+out_mmap_sem:
 		up_write(&EXT4_I(inode)->i_mmap_sem);
 	}
 
-- 
2.16.4




[Index of Archives]     [Reiser Filesystem Development]     [Ceph FS]     [Kernel Newbies]     [Security]     [Netfilter]     [Bugtraq]     [Linux FS]     [Yosemite National Park]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Device Mapper]     [Linux Media]

  Powered by Linux