Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 bugfixes from Ted Ts'o:
"Bug fixes (all for stable kernels) for ext4:
- address corner cases for indirect blocks->extent migration
- fix reserved block accounting invalidate_page when
page_size != block_size (i.e., ppc or 1k block size file systems)
- fix deadlocks when a memcg is under heavy memory pressure
- fix fencepost error in lazytime optimization"
* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
ext4: replace open coded nofail allocation in ext4_free_blocks()
ext4: correctly migrate a file with a hole at the beginning
ext4: be more strict when migrating to non-extent based file
ext4: fix reservation release on invalidatepage for delalloc fs
ext4: avoid deadlocks in the writeback path by using sb_getblk_gfp
bufferhead: Add _gfp version for sb_getblk()
ext4: fix fencepost error in lazytime optimization
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index aadb728..2553aa8 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -504,7 +504,7 @@
struct buffer_head *bh;
int err;
- bh = sb_getblk(inode->i_sb, pblk);
+ bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
@@ -1089,7 +1089,7 @@
err = -EIO;
goto cleanup;
}
- bh = sb_getblk(inode->i_sb, newblock);
+ bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh)) {
err = -ENOMEM;
goto cleanup;
@@ -1283,7 +1283,7 @@
if (newblock == 0)
return err;
- bh = sb_getblk(inode->i_sb, newblock);
+ bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
if (unlikely(!bh))
return -ENOMEM;
lock_buffer(bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 41f8e55..cecf9aa 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1323,7 +1323,7 @@
unsigned int offset,
unsigned int length)
{
- int to_release = 0;
+ int to_release = 0, contiguous_blks = 0;
struct buffer_head *head, *bh;
unsigned int curr_off = 0;
struct inode *inode = page->mapping->host;
@@ -1344,14 +1344,23 @@
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
+ contiguous_blks++;
clear_buffer_delay(bh);
+ } else if (contiguous_blks) {
+ lblk = page->index <<
+ (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ lblk += (curr_off >> inode->i_blkbits) -
+ contiguous_blks;
+ ext4_es_remove_extent(inode, lblk, contiguous_blks);
+ contiguous_blks = 0;
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
- if (to_release) {
+ if (contiguous_blks) {
lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- ext4_es_remove_extent(inode, lblk, to_release);
+ lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
+ ext4_es_remove_extent(inode, lblk, contiguous_blks);
}
/* If we have released all the blocks belonging to a cluster, then we
@@ -4344,7 +4353,12 @@
int inode_size = EXT4_INODE_SIZE(sb);
oi.orig_ino = orig_ino;
- ino = (orig_ino & ~(inodes_per_block - 1)) + 1;
+ /*
+ * Calculate the first inode in the inode table block. Inode
+ * numbers are one-based. That is, the first inode in a block
+ * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
+ */
+ ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
if (ino == orig_ino)
continue;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f6aedf8..34b610e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4816,18 +4816,12 @@
/*
* blocks being freed are metadata. these blocks shouldn't
* be used until this transaction is committed
+ *
+ * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
+ * to fail.
*/
- retry:
- new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
- if (!new_entry) {
- /*
- * We use a retry loop because
- * ext4_free_blocks() is not allowed to fail.
- */
- cond_resched();
- congestion_wait(BLK_RW_ASYNC, HZ/50);
- goto retry;
- }
+ new_entry = kmem_cache_alloc(ext4_free_data_cachep,
+ GFP_NOFS|__GFP_NOFAIL);
new_entry->efd_start_cluster = bit;
new_entry->efd_group = block_group;
new_entry->efd_count = count_clusters;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b52374e..6163ad2 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -620,6 +620,7 @@
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
+ ext4_lblk_t start, end;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
@@ -633,6 +634,14 @@
EXT4_FEATURE_RO_COMPAT_BIGALLOC))
return -EOPNOTSUPP;
+ /*
+ * In order to get correct extent info, force all delayed allocation
+ * blocks to be allocated, otherwise delayed allocation blocks may not
+ * be reflected and bypass the checks on extent header.
+ */
+ if (test_opt(inode->i_sb, DELALLOC))
+ ext4_alloc_da_blocks(inode);
+
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
@@ -650,11 +659,13 @@
goto errout;
}
if (eh->eh_entries == 0)
- blk = len = 0;
+ blk = len = start = end = 0;
else {
len = le16_to_cpu(ex->ee_len);
blk = ext4_ext_pblock(ex);
- if (len > EXT4_NDIR_BLOCKS) {
+ start = le32_to_cpu(ex->ee_block);
+ end = start + len - 1;
+ if (end >= EXT4_NDIR_BLOCKS) {
ret = -EOPNOTSUPP;
goto errout;
}
@@ -662,7 +673,7 @@
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
memset(ei->i_data, 0, sizeof(ei->i_data));
- for (i=0; i < len; i++)
+ for (i = start; i <= end; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
errout:
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 73b4522..e6797de 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -317,6 +317,13 @@
return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
}
+
+static inline struct buffer_head *
+sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
+{
+ return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
+}
+
static inline struct buffer_head *
sb_find_get_block(struct super_block *sb, sector_t block)
{
