summaryrefslogtreecommitdiff
path: root/fs/ocfs2
diff options
context:
space:
mode:
authorAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-12-15 14:52:16 -0300
committerAndré Fabian Silva Delgado <emulatorman@parabola.nu>2015-12-15 14:52:16 -0300
commit8d91c1e411f55d7ea91b1183a2e9f8088fb4d5be (patch)
treee9891aa6c295060d065adffd610c4f49ecf884f3 /fs/ocfs2
parenta71852147516bc1cb5b0b3cbd13639bfd4022dc8 (diff)
Linux-libre 4.3.2-gnu
Diffstat (limited to 'fs/ocfs2')
-rw-r--r--fs/ocfs2/acl.c26
-rw-r--r--fs/ocfs2/alloc.c148
-rw-r--r--fs/ocfs2/aops.c54
-rw-r--r--fs/ocfs2/buffer_head_io.c6
-rw-r--r--fs/ocfs2/cluster/heartbeat.c78
-rw-r--r--fs/ocfs2/dir.c70
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c78
-rw-r--r--fs/ocfs2/dlm/dlmmaster.c25
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c2
-rw-r--r--fs/ocfs2/dlm/dlmthread.c10
-rw-r--r--fs/ocfs2/dlmglue.c2
-rw-r--r--fs/ocfs2/extent_map.c22
-rw-r--r--fs/ocfs2/file.c47
-rw-r--r--fs/ocfs2/inode.c49
-rw-r--r--fs/ocfs2/inode.h2
-rw-r--r--fs/ocfs2/journal.c32
-rw-r--r--fs/ocfs2/localalloc.c3
-rw-r--r--fs/ocfs2/move_extents.c8
-rw-r--r--fs/ocfs2/namei.c155
-rw-r--r--fs/ocfs2/ocfs2.h2
-rw-r--r--fs/ocfs2/ocfs2_fs.h4
-rw-r--r--fs/ocfs2/quota_local.c7
-rw-r--r--fs/ocfs2/refcounttree.c86
-rw-r--r--fs/ocfs2/stack_user.c9
-rw-r--r--fs/ocfs2/suballoc.c96
-rw-r--r--fs/ocfs2/super.c69
-rw-r--r--fs/ocfs2/super.h8
-rw-r--r--fs/ocfs2/xattr.c51
28 files changed, 609 insertions, 540 deletions
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index c58a1bcfd..0cdf497c9 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -284,7 +284,19 @@ int ocfs2_set_acl(handle_t *handle,
int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
- return ocfs2_set_acl(NULL, inode, NULL, type, acl, NULL, NULL);
+ struct buffer_head *bh = NULL;
+ int status = 0;
+
+ status = ocfs2_inode_lock(inode, &bh, 1);
+ if (status < 0) {
+ if (status != -ENOENT)
+ mlog_errno(status);
+ return status;
+ }
+ status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
+ ocfs2_inode_unlock(inode, 1);
+ brelse(bh);
+ return status;
}
struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
@@ -292,19 +304,21 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
struct ocfs2_super *osb;
struct buffer_head *di_bh = NULL;
struct posix_acl *acl;
- int ret = -EAGAIN;
+ int ret;
osb = OCFS2_SB(inode->i_sb);
if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
return NULL;
-
- ret = ocfs2_read_inode_block(inode, &di_bh);
- if (ret < 0)
+ ret = ocfs2_inode_lock(inode, &di_bh, 0);
+ if (ret < 0) {
+ if (ret != -ENOENT)
+ mlog_errno(ret);
return ERR_PTR(ret);
+ }
acl = ocfs2_get_acl_nolock(inode, type, di_bh);
+ ocfs2_inode_unlock(inode, 0);
brelse(di_bh);
-
return acl;
}
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 5997c00a1..86181d652 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -908,32 +908,30 @@ static int ocfs2_validate_extent_block(struct super_block *sb,
*/
if (!OCFS2_IS_VALID_EXTENT_BLOCK(eb)) {
- ocfs2_error(sb,
- "Extent block #%llu has bad signature %.*s",
- (unsigned long long)bh->b_blocknr, 7,
- eb->h_signature);
- return -EINVAL;
+ rc = ocfs2_error(sb,
+ "Extent block #%llu has bad signature %.*s\n",
+ (unsigned long long)bh->b_blocknr, 7,
+ eb->h_signature);
+ goto bail;
}
if (le64_to_cpu(eb->h_blkno) != bh->b_blocknr) {
- ocfs2_error(sb,
- "Extent block #%llu has an invalid h_blkno "
- "of %llu",
- (unsigned long long)bh->b_blocknr,
- (unsigned long long)le64_to_cpu(eb->h_blkno));
- return -EINVAL;
+ rc = ocfs2_error(sb,
+ "Extent block #%llu has an invalid h_blkno of %llu\n",
+ (unsigned long long)bh->b_blocknr,
+ (unsigned long long)le64_to_cpu(eb->h_blkno));
+ goto bail;
}
if (le32_to_cpu(eb->h_fs_generation) != OCFS2_SB(sb)->fs_generation) {
- ocfs2_error(sb,
- "Extent block #%llu has an invalid "
- "h_fs_generation of #%u",
- (unsigned long long)bh->b_blocknr,
- le32_to_cpu(eb->h_fs_generation));
- return -EINVAL;
+ rc = ocfs2_error(sb,
+ "Extent block #%llu has an invalid h_fs_generation of #%u\n",
+ (unsigned long long)bh->b_blocknr,
+ le32_to_cpu(eb->h_fs_generation));
+ goto bail;
}
-
- return 0;
+bail:
+ return rc;
}
int ocfs2_read_extent_block(struct ocfs2_caching_info *ci, u64 eb_blkno,
@@ -1446,8 +1444,7 @@ static int ocfs2_find_branch_target(struct ocfs2_extent_tree *et,
while(le16_to_cpu(el->l_tree_depth) > 1) {
if (le16_to_cpu(el->l_next_free_rec) == 0) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu has empty "
- "extent list (next_free_rec == 0)",
+ "Owner %llu has empty extent list (next_free_rec == 0)\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci));
status = -EIO;
goto bail;
@@ -1456,9 +1453,7 @@ static int ocfs2_find_branch_target(struct ocfs2_extent_tree *et,
blkno = le64_to_cpu(el->l_recs[i].e_blkno);
if (!blkno) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu has extent "
- "list where extent # %d has no physical "
- "block start",
+ "Owner %llu has extent list where extent # %d has no physical block start\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci), i);
status = -EIO;
goto bail;
@@ -1788,8 +1783,7 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci,
while (el->l_tree_depth) {
if (le16_to_cpu(el->l_next_free_rec) == 0) {
ocfs2_error(ocfs2_metadata_cache_get_super(ci),
- "Owner %llu has empty extent list at "
- "depth %u\n",
+ "Owner %llu has empty extent list at depth %u\n",
(unsigned long long)ocfs2_metadata_cache_owner(ci),
le16_to_cpu(el->l_tree_depth));
ret = -EROFS;
@@ -1814,8 +1808,7 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci,
blkno = le64_to_cpu(el->l_recs[i].e_blkno);
if (blkno == 0) {
ocfs2_error(ocfs2_metadata_cache_get_super(ci),
- "Owner %llu has bad blkno in extent list "
- "at depth %u (index %d)\n",
+ "Owner %llu has bad blkno in extent list at depth %u (index %d)\n",
(unsigned long long)ocfs2_metadata_cache_owner(ci),
le16_to_cpu(el->l_tree_depth), i);
ret = -EROFS;
@@ -1836,8 +1829,7 @@ static int __ocfs2_find_path(struct ocfs2_caching_info *ci,
if (le16_to_cpu(el->l_next_free_rec) >
le16_to_cpu(el->l_count)) {
ocfs2_error(ocfs2_metadata_cache_get_super(ci),
- "Owner %llu has bad count in extent list "
- "at block %llu (next free=%u, count=%u)\n",
+ "Owner %llu has bad count in extent list at block %llu (next free=%u, count=%u)\n",
(unsigned long long)ocfs2_metadata_cache_owner(ci),
(unsigned long long)bh->b_blocknr,
le16_to_cpu(el->l_next_free_rec),
@@ -2116,8 +2108,7 @@ static int ocfs2_rotate_subtree_right(handle_t *handle,
if (left_el->l_next_free_rec != left_el->l_count) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Inode %llu has non-full interior leaf node %llu"
- "(next free = %u)",
+ "Inode %llu has non-full interior leaf node %llu (next free = %u)\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
(unsigned long long)left_leaf_bh->b_blocknr,
le16_to_cpu(left_el->l_next_free_rec));
@@ -2256,8 +2247,7 @@ int ocfs2_find_cpos_for_left_leaf(struct super_block *sb,
* If we got here, we never found a valid node where
* the tree indicated one should be.
*/
- ocfs2_error(sb,
- "Invalid extent tree at extent block %llu\n",
+ ocfs2_error(sb, "Invalid extent tree at extent block %llu\n",
(unsigned long long)blkno);
ret = -EROFS;
goto out;
@@ -2872,8 +2862,7 @@ int ocfs2_find_cpos_for_right_leaf(struct super_block *sb,
* If we got here, we never found a valid node where
* the tree indicated one should be.
*/
- ocfs2_error(sb,
- "Invalid extent tree at extent block %llu\n",
+ ocfs2_error(sb, "Invalid extent tree at extent block %llu\n",
(unsigned long long)blkno);
ret = -EROFS;
goto out;
@@ -3131,6 +3120,30 @@ out:
return ret;
}
+static int ocfs2_remove_rightmost_empty_extent(struct ocfs2_super *osb,
+ struct ocfs2_extent_tree *et,
+ struct ocfs2_path *path,
+ struct ocfs2_cached_dealloc_ctxt *dealloc)
+{
+ handle_t *handle;
+ int ret;
+ int credits = path->p_tree_depth * 2 + 1;
+
+ handle = ocfs2_start_trans(osb, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ return ret;
+ }
+
+ ret = ocfs2_remove_rightmost_path(handle, et, path, dealloc);
+ if (ret)
+ mlog_errno(ret);
+
+ ocfs2_commit_trans(osb, handle);
+ return ret;
+}
+
/*
* Left rotation of btree records.
*
@@ -3200,7 +3213,7 @@ rightmost_no_delete:
if (le16_to_cpu(el->l_next_free_rec) == 0) {
ret = -EIO;
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu has empty extent block at %llu",
+ "Owner %llu has empty extent block at %llu\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
(unsigned long long)le64_to_cpu(eb->h_blkno));
goto out;
@@ -3930,7 +3943,7 @@ static void ocfs2_adjust_rightmost_records(handle_t *handle,
next_free = le16_to_cpu(el->l_next_free_rec);
if (next_free == 0) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu has a bad extent list",
+ "Owner %llu has a bad extent list\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci));
ret = -EIO;
return;
@@ -4355,10 +4368,7 @@ static int ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
bh = path_leaf_bh(left_path);
eb = (struct ocfs2_extent_block *)bh->b_data;
ocfs2_error(sb,
- "Extent block #%llu has an "
- "invalid l_next_free_rec of "
- "%d. It should have "
- "matched the l_count of %d",
+ "Extent block #%llu has an invalid l_next_free_rec of %d. It should have matched the l_count of %d\n",
(unsigned long long)le64_to_cpu(eb->h_blkno),
le16_to_cpu(new_el->l_next_free_rec),
le16_to_cpu(new_el->l_count));
@@ -4413,8 +4423,7 @@ static int ocfs2_figure_merge_contig_type(struct ocfs2_extent_tree *et,
bh = path_leaf_bh(right_path);
eb = (struct ocfs2_extent_block *)bh->b_data;
ocfs2_error(sb,
- "Extent block #%llu has an "
- "invalid l_next_free_rec of %d",
+ "Extent block #%llu has an invalid l_next_free_rec of %d\n",
(unsigned long long)le64_to_cpu(eb->h_blkno),
le16_to_cpu(new_el->l_next_free_rec));
status = -EINVAL;
@@ -4970,10 +4979,9 @@ leftright:
split_index = ocfs2_search_extent_list(el, cpos);
if (split_index == -1) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu has an extent at cpos %u "
- "which can no longer be found.\n",
- (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
- cpos);
+ "Owner %llu has an extent at cpos %u which can no longer be found\n",
+ (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
+ cpos);
ret = -EROFS;
goto out;
}
@@ -5158,10 +5166,9 @@ int ocfs2_change_extent_flag(handle_t *handle,
index = ocfs2_search_extent_list(el, cpos);
if (index == -1) {
ocfs2_error(sb,
- "Owner %llu has an extent at cpos %u which can no "
- "longer be found.\n",
- (unsigned long long)
- ocfs2_metadata_cache_owner(et->et_ci), cpos);
+ "Owner %llu has an extent at cpos %u which can no longer be found\n",
+ (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
+ cpos);
ret = -EROFS;
goto out;
}
@@ -5228,9 +5235,7 @@ int ocfs2_mark_extent_written(struct inode *inode,
cpos, len, phys);
if (!ocfs2_writes_unwritten_extents(OCFS2_SB(inode->i_sb))) {
- ocfs2_error(inode->i_sb, "Inode %llu has unwritten extents "
- "that are being written to, but the feature bit "
- "is not set in the super block.",
+ ocfs2_error(inode->i_sb, "Inode %llu has unwritten extents that are being written to, but the feature bit is not set in the super block\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
ret = -EROFS;
goto out;
@@ -5514,8 +5519,7 @@ int ocfs2_remove_extent(handle_t *handle,
index = ocfs2_search_extent_list(el, cpos);
if (index == -1) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu has an extent at cpos %u which can no "
- "longer be found.\n",
+ "Owner %llu has an extent at cpos %u which can no longer be found\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
cpos);
ret = -EROFS;
@@ -5580,7 +5584,7 @@ int ocfs2_remove_extent(handle_t *handle,
index = ocfs2_search_extent_list(el, cpos);
if (index == -1) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu: split at cpos %u lost record.",
+ "Owner %llu: split at cpos %u lost record\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
cpos);
ret = -EROFS;
@@ -5596,8 +5600,7 @@ int ocfs2_remove_extent(handle_t *handle,
ocfs2_rec_clusters(el, rec);
if (rec_range != trunc_range) {
ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
- "Owner %llu: error after split at cpos %u"
- "trunc len %u, existing record is (%u,%u)",
+ "Owner %llu: error after split at cpos %u trunc len %u, existing record is (%u,%u)\n",
(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
cpos, len, le32_to_cpu(rec->e_cpos),
ocfs2_rec_clusters(el, rec));
@@ -6175,7 +6178,7 @@ bail:
iput(tl_inode);
brelse(tl_bh);
- if (status < 0 && (*tl_copy)) {
+ if (status < 0) {
kfree(*tl_copy);
*tl_copy = NULL;
mlog_errno(status);
@@ -7108,15 +7111,23 @@ start:
* to check it up here before changing the tree.
*/
if (root_el->l_tree_depth && rec->e_int_clusters == 0) {
- ocfs2_error(inode->i_sb, "Inode %lu has an empty "
+ mlog(ML_ERROR, "Inode %lu has an empty "
"extent record, depth %u\n", inode->i_ino,
le16_to_cpu(root_el->l_tree_depth));
- status = -EROFS;
- goto bail;
+ status = ocfs2_remove_rightmost_empty_extent(osb,
+ &et, path, &dealloc);
+ if (status) {
+ mlog_errno(status);
+ goto bail;
+ }
+
+ ocfs2_reinit_path(path, 1);
+ goto start;
+ } else {
+ trunc_cpos = le32_to_cpu(rec->e_cpos);
+ trunc_len = 0;
+ blkno = 0;
}
- trunc_cpos = le32_to_cpu(rec->e_cpos);
- trunc_len = 0;
- blkno = 0;
} else if (le32_to_cpu(rec->e_cpos) >= new_highest_cpos) {
/*
* Truncate entire record.
@@ -7204,8 +7215,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
!ocfs2_supports_inline_data(osb)) {
ocfs2_error(inode->i_sb,
- "Inline data flags for inode %llu don't agree! "
- "Disk: 0x%x, Memory: 0x%x, Superblock: 0x%x\n",
+ "Inline data flags for inode %llu don't agree! Disk: 0x%x, Memory: 0x%x, Superblock: 0x%x\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
le16_to_cpu(di->i_dyn_features),
OCFS2_I(inode)->ip_dyn_features,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 0f5fd9db8..64b11d90e 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -227,7 +227,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) {
- ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag",
+ ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
return -EROFS;
}
@@ -237,7 +237,7 @@ int ocfs2_read_inline_data(struct inode *inode, struct page *page,
if (size > PAGE_CACHE_SIZE ||
size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
ocfs2_error(inode->i_sb,
- "Inode %llu has with inline data has bad size: %Lu",
+ "Inode %llu has with inline data has bad size: %Lu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)size);
return -EROFS;
@@ -533,10 +533,14 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
/* This figures out the size of the next contiguous block, and
* our logical offset */
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
if (ret) {
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
@@ -557,6 +561,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
alloc_locked = 1;
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
+
/* fill hole, allocate blocks can't be larger than the size
* of the hole */
clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
@@ -569,6 +575,7 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
ret = ocfs2_extend_allocation(inode, cpos,
clusters_to_alloc, 0);
if (ret < 0) {
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
mlog_errno(ret);
goto bail;
}
@@ -576,11 +583,13 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
if (ret < 0) {
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
ret = -EIO;
goto bail;
}
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
}
/*
@@ -627,10 +636,13 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
}
- ocfs2_iocb_clear_rw_locked(iocb);
+ /* Let rw unlock to be done later to protect append direct io write */
+ if (offset + bytes <= i_size_read(inode)) {
+ ocfs2_iocb_clear_rw_locked(iocb);
- level = ocfs2_iocb_rw_locked_level(iocb);
- ocfs2_rw_unlock(inode, level);
+ level = ocfs2_iocb_rw_locked_level(iocb);
+ ocfs2_rw_unlock(inode, level);
+ }
}
static int ocfs2_releasepage(struct page *page, gfp_t wait)
@@ -832,12 +844,17 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
/* zeroing out the previously allocated cluster tail
* that but not zeroed */
- if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+ if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) {
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
ret = ocfs2_direct_IO_zero_extend(osb, inode, offset,
zero_len_tail, cluster_align_tail);
- else
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+ } else {
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
ret = ocfs2_direct_IO_extend_no_holes(osb, inode,
offset);
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
+ }
if (ret < 0) {
mlog_errno(ret);
ocfs2_inode_unlock(inode, 1);
@@ -857,7 +874,8 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
offset, ocfs2_direct_IO_get_blocks,
ocfs2_dio_end_io, NULL, 0);
- if (unlikely(written < 0)) {
+ /* overwrite aio may return -EIOCBQUEUED, and it is not an error */
+ if ((written < 0) && (written != -EIOCBQUEUED)) {
loff_t i_size = i_size_read(inode);
if (offset + count > i_size) {
@@ -876,12 +894,14 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
+ di_bh = NULL;
goto clean_orphan;
}
}
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
+ di_bh = NULL;
ret = jbd2_journal_force_commit(journal);
if (ret < 0)
@@ -936,10 +956,12 @@ clean_orphan:
if (tmp_ret < 0) {
ret = tmp_ret;
mlog_errno(ret);
+ brelse(di_bh);
goto out;
}
ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
tmp_ret = jbd2_journal_force_commit(journal);
if (tmp_ret < 0) {
@@ -2185,10 +2207,7 @@ try_again:
if (ret)
goto out_commit;
}
- /*
- * We don't want this to fail in ocfs2_write_end(), so do it
- * here.
- */
+
ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
@@ -2345,7 +2364,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
- int i;
+ int i, ret;
unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
struct inode *inode = mapping->host;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2354,6 +2373,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
handle_t *handle = wc->w_handle;
struct page *tmppage;
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret) {
+ copied = ret;
+ mlog_errno(ret);
+ goto out;
+ }
+
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
ocfs2_write_end_inline(inode, pos, len, &copied, di, wc);
goto out_write_size;
@@ -2409,6 +2436,7 @@ out_write_size:
ocfs2_update_inode_fsync_trans(handle, inode, 1);
ocfs2_journal_dirty(handle, wc->w_di_bh);
+out:
/* unlock pages before dealloc since it needs acquiring j_trans_barrier
* lock, or it will cause a deadlock since journal commit threads holds
* this lock and will ask for the page lock when flushing the data.
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 1edcb141f..fe50ded1b 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -316,6 +316,12 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
bh = bhs[i];
if (!(flags & OCFS2_BH_READAHEAD)) {
+ if (status) {
+ /* Clear the rest of the buffers on error */
+ put_bh(bh);
+ bhs[i] = NULL;
+ continue;
+ }
/* We know this can't have changed as we hold the
* owner sem. Avoid doing any work on the bh if the
* journal has it. */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 16eff4572..fa15debcc 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -36,7 +36,7 @@
#include <linux/debugfs.h>
#include <linux/slab.h>
#include <linux/bitmap.h>
-
+#include <linux/ktime.h>
#include "heartbeat.h"
#include "tcp.h"
#include "nodemanager.h"
@@ -372,14 +372,13 @@ static void o2hb_wait_on_io(struct o2hb_region *reg,
wait_for_completion(&wc->wc_io_complete);
}
-static void o2hb_bio_end_io(struct bio *bio,
- int error)
+static void o2hb_bio_end_io(struct bio *bio)
{
struct o2hb_bio_wait_ctxt *wc = bio->bi_private;
- if (error) {
- mlog(ML_ERROR, "IO Error %d\n", error);
- wc->wc_error = error;
+ if (bio->bi_error) {
+ mlog(ML_ERROR, "IO Error %d\n", bio->bi_error);
+ wc->wc_error = bio->bi_error;
}
o2hb_bio_wait_dec(wc, 1);
@@ -1061,37 +1060,6 @@ bail:
return ret;
}
-/* Subtract b from a, storing the result in a. a *must* have a larger
- * value than b. */
-static void o2hb_tv_subtract(struct timeval *a,
- struct timeval *b)
-{
- /* just return 0 when a is after b */
- if (a->tv_sec < b->tv_sec ||
- (a->tv_sec == b->tv_sec && a->tv_usec < b->tv_usec)) {
- a->tv_sec = 0;
- a->tv_usec = 0;
- return;
- }
-
- a->tv_sec -= b->tv_sec;
- a->tv_usec -= b->tv_usec;
- while ( a->tv_usec < 0 ) {
- a->tv_sec--;
- a->tv_usec += 1000000;
- }
-}
-
-static unsigned int o2hb_elapsed_msecs(struct timeval *start,
- struct timeval *end)
-{
- struct timeval res = *end;
-
- o2hb_tv_subtract(&res, start);
-
- return res.tv_sec * 1000 + res.tv_usec / 1000;
-}
-
/*
* we ride the region ref that the region dir holds. before the region
* dir is removed and drops it ref it will wait to tear down this
@@ -1102,7 +1070,7 @@ static int o2hb_thread(void *data)
int i, ret;
struct o2hb_region *reg = data;
struct o2hb_bio_wait_ctxt write_wc;
- struct timeval before_hb, after_hb;
+ ktime_t before_hb, after_hb;
unsigned int elapsed_msec;
mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread running\n");
@@ -1119,18 +1087,18 @@ static int o2hb_thread(void *data)
* hr_timeout_ms between disk writes. On busy systems
* this should result in a heartbeat which is less
* likely to time itself out. */
- do_gettimeofday(&before_hb);
+ before_hb = ktime_get_real();
ret = o2hb_do_disk_heartbeat(reg);
- do_gettimeofday(&after_hb);
- elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb);
+ after_hb = ktime_get_real();
+
+ elapsed_msec = (unsigned int)
+ ktime_ms_delta(after_hb, before_hb);
mlog(ML_HEARTBEAT,
- "start = %lu.%lu, end = %lu.%lu, msec = %u, ret = %d\n",
- before_hb.tv_sec, (unsigned long) before_hb.tv_usec,
- after_hb.tv_sec, (unsigned long) after_hb.tv_usec,
- elapsed_msec, ret);
+ "start = %lld, end = %lld, msec = %u, ret = %d\n",
+ before_hb.tv64, after_hb.tv64, elapsed_msec, ret);
if (!kthread_should_stop() &&
elapsed_msec < reg->hr_timeout_ms) {
@@ -1620,17 +1588,13 @@ static int o2hb_map_slot_data(struct o2hb_region *reg)
struct o2hb_disk_slot *slot;
reg->hr_tmp_block = kmalloc(reg->hr_block_bytes, GFP_KERNEL);
- if (reg->hr_tmp_block == NULL) {
- mlog_errno(-ENOMEM);
+ if (reg->hr_tmp_block == NULL)
return -ENOMEM;
- }
reg->hr_slots = kcalloc(reg->hr_blocks,
sizeof(struct o2hb_disk_slot), GFP_KERNEL);
- if (reg->hr_slots == NULL) {
- mlog_errno(-ENOMEM);
+ if (reg->hr_slots == NULL)
return -ENOMEM;
- }
for(i = 0; i < reg->hr_blocks; i++) {
slot = &reg->hr_slots[i];
@@ -1646,17 +1610,13 @@ static int o2hb_map_slot_data(struct o2hb_region *reg)
reg->hr_slot_data = kcalloc(reg->hr_num_pages, sizeof(struct page *),
GFP_KERNEL);
- if (!reg->hr_slot_data) {
- mlog_errno(-ENOMEM);
+ if (!reg->hr_slot_data)
return -ENOMEM;
- }
for(i = 0; i < reg->hr_num_pages; i++) {
page = alloc_page(GFP_KERNEL);
- if (!page) {
- mlog_errno(-ENOMEM);
+ if (!page)
return -ENOMEM;
- }
reg->hr_slot_data[i] = page;
@@ -1688,10 +1648,8 @@ static int o2hb_populate_slot_data(struct o2hb_region *reg)
struct o2hb_disk_heartbeat_block *hb_block;
ret = o2hb_read_slots(reg, reg->hr_blocks);
- if (ret) {
- mlog_errno(ret);
+ if (ret)
goto out;
- }
/* We only want to get an idea of the values initially in each
* slot, so we do no verification - o2hb_check_slot will
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 02878a83f..ffecf89c8 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -480,33 +480,26 @@ static int ocfs2_check_dir_trailer(struct inode *dir, struct buffer_head *bh)
trailer = ocfs2_trailer_from_bh(bh, dir->i_sb);
if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) {
- rc = -EINVAL;
- ocfs2_error(dir->i_sb,
- "Invalid dirblock #%llu: "
- "signature = %.*s\n",
- (unsigned long long)bh->b_blocknr, 7,
- trailer->db_signature);
+ rc = ocfs2_error(dir->i_sb,
+ "Invalid dirblock #%llu: signature = %.*s\n",
+ (unsigned long long)bh->b_blocknr, 7,
+ trailer->db_signature);
goto out;
}
if (le64_to_cpu(trailer->db_blkno) != bh->b_blocknr) {
- rc = -EINVAL;
- ocfs2_error(dir->i_sb,
- "Directory block #%llu has an invalid "
- "db_blkno of %llu",
- (unsigned long long)bh->b_blocknr,
- (unsigned long long)le64_to_cpu(trailer->db_blkno));
+ rc = ocfs2_error(dir->i_sb,
+ "Directory block #%llu has an invalid db_blkno of %llu\n",
+ (unsigned long long)bh->b_blocknr,
+ (unsigned long long)le64_to_cpu(trailer->db_blkno));
goto out;
}
if (le64_to_cpu(trailer->db_parent_dinode) !=
OCFS2_I(dir)->ip_blkno) {
- rc = -EINVAL;
- ocfs2_error(dir->i_sb,
- "Directory block #%llu on dinode "
- "#%llu has an invalid parent_dinode "
- "of %llu",
- (unsigned long long)bh->b_blocknr,
- (unsigned long long)OCFS2_I(dir)->ip_blkno,
- (unsigned long long)le64_to_cpu(trailer->db_blkno));
+ rc = ocfs2_error(dir->i_sb,
+ "Directory block #%llu on dinode #%llu has an invalid parent_dinode of %llu\n",
+ (unsigned long long)bh->b_blocknr,
+ (unsigned long long)OCFS2_I(dir)->ip_blkno,
+ (unsigned long long)le64_to_cpu(trailer->db_blkno));
goto out;
}
out:
@@ -604,14 +597,13 @@ static int ocfs2_validate_dx_root(struct super_block *sb,
}
if (!OCFS2_IS_VALID_DX_ROOT(dx_root)) {
- ocfs2_error(sb,
- "Dir Index Root # %llu has bad signature %.*s",
- (unsigned long long)le64_to_cpu(dx_root->dr_blkno),
- 7, dx_root->dr_signature);
- return -EINVAL;
+ ret = ocfs2_error(sb,
+ "Dir Index Root # %llu has bad signature %.*s\n",
+ (unsigned long long)le64_to_cpu(dx_root->dr_blkno),
+ 7, dx_root->dr_signature);
}
- return 0;
+ return ret;
}
static int ocfs2_read_dx_root(struct inode *dir, struct ocfs2_dinode *di,
@@ -648,12 +640,11 @@ static int ocfs2_validate_dx_leaf(struct super_block *sb,
}
if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) {
- ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s",
- 7, dx_leaf->dl_signature);
- return -EROFS;
+ ret = ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s\n",
+ 7, dx_leaf->dl_signature);
}
- return 0;
+ return ret;
}
static int ocfs2_read_dx_leaf(struct inode *dir, u64 blkno,
@@ -812,11 +803,10 @@ static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
el = &eb->h_list;
if (el->l_tree_depth) {
- ocfs2_error(inode->i_sb,
- "Inode %lu has non zero tree depth in "
- "btree tree block %llu\n", inode->i_ino,
- (unsigned long long)eb_bh->b_blocknr);
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb,
+ "Inode %lu has non zero tree depth in btree tree block %llu\n",
+ inode->i_ino,
+ (unsigned long long)eb_bh->b_blocknr);
goto out;
}
}
@@ -832,11 +822,11 @@ static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
}
if (!found) {
- ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
- "record (%u, %u, 0) in btree", inode->i_ino,
- le32_to_cpu(rec->e_cpos),
- ocfs2_rec_clusters(el, rec));
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb,
+ "Inode %lu has bad extent record (%u, %u, 0) in btree\n",
+ inode->i_ino,
+ le32_to_cpu(rec->e_cpos),
+ ocfs2_rec_clusters(el, rec));
goto out;
}
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 7df88a6dd..6918f30d0 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1465,39 +1465,46 @@ static int dlm_request_join(struct dlm_ctxt *dlm,
if (status == -ENOPROTOOPT) {
status = 0;
*response = JOIN_OK_NO_MAP;
- } else if (packet.code == JOIN_DISALLOW ||
- packet.code == JOIN_OK_NO_MAP) {
- *response = packet.code;
- } else if (packet.code == JOIN_PROTOCOL_MISMATCH) {
- mlog(ML_NOTICE,
- "This node requested DLM locking protocol %u.%u and "
- "filesystem locking protocol %u.%u. At least one of "
- "the protocol versions on node %d is not compatible, "
- "disconnecting\n",
- dlm->dlm_locking_proto.pv_major,
- dlm->dlm_locking_proto.pv_minor,
- dlm->fs_locking_proto.pv_major,
- dlm->fs_locking_proto.pv_minor,
- node);
- status = -EPROTO;
- *response = packet.code;
- } else if (packet.code == JOIN_OK) {
- *response = packet.code;
- /* Use the same locking protocol as the remote node */
- dlm->dlm_locking_proto.pv_minor = packet.dlm_minor;
- dlm->fs_locking_proto.pv_minor = packet.fs_minor;
- mlog(0,
- "Node %d responds JOIN_OK with DLM locking protocol "
- "%u.%u and fs locking protocol %u.%u\n",
- node,
- dlm->dlm_locking_proto.pv_major,
- dlm->dlm_locking_proto.pv_minor,
- dlm->fs_locking_proto.pv_major,
- dlm->fs_locking_proto.pv_minor);
} else {
- status = -EINVAL;
- mlog(ML_ERROR, "invalid response %d from node %u\n",
- packet.code, node);
+ *response = packet.code;
+ switch (packet.code) {
+ case JOIN_DISALLOW:
+ case JOIN_OK_NO_MAP:
+ break;
+ case JOIN_PROTOCOL_MISMATCH:
+ mlog(ML_NOTICE,
+ "This node requested DLM locking protocol %u.%u and "
+ "filesystem locking protocol %u.%u. At least one of "
+ "the protocol versions on node %d is not compatible, "
+ "disconnecting\n",
+ dlm->dlm_locking_proto.pv_major,
+ dlm->dlm_locking_proto.pv_minor,
+ dlm->fs_locking_proto.pv_major,
+ dlm->fs_locking_proto.pv_minor,
+ node);
+ status = -EPROTO;
+ break;
+ case JOIN_OK:
+ /* Use the same locking protocol as the remote node */
+ dlm->dlm_locking_proto.pv_minor = packet.dlm_minor;
+ dlm->fs_locking_proto.pv_minor = packet.fs_minor;
+ mlog(0,
+ "Node %d responds JOIN_OK with DLM locking protocol "
+ "%u.%u and fs locking protocol %u.%u\n",
+ node,
+ dlm->dlm_locking_proto.pv_major,
+ dlm->dlm_locking_proto.pv_minor,
+ dlm->fs_locking_proto.pv_major,
+ dlm->fs_locking_proto.pv_minor);
+ break;
+ default:
+ status = -EINVAL;
+ mlog(ML_ERROR, "invalid response %d from node %u\n",
+ packet.code, node);
+ /* Reset response to JOIN_DISALLOW */
+ *response = JOIN_DISALLOW;
+ break;
+ }
}
mlog(0, "status %d, node %d response is %d\n", status, node,
@@ -1725,12 +1732,13 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
o2hb_setup_callback(&dlm->dlm_hb_down, O2HB_NODE_DOWN_CB,
dlm_hb_node_down_cb, dlm, DLM_HB_NODE_DOWN_PRI);
+ o2hb_setup_callback(&dlm->dlm_hb_up, O2HB_NODE_UP_CB,
+ dlm_hb_node_up_cb, dlm, DLM_HB_NODE_UP_PRI);
+
status = o2hb_register_callback(dlm->name, &dlm->dlm_hb_down);
if (status)
goto bail;
- o2hb_setup_callback(&dlm->dlm_hb_up, O2HB_NODE_UP_CB,
- dlm_hb_node_up_cb, dlm, DLM_HB_NODE_UP_PRI);
status = o2hb_register_callback(dlm->name, &dlm->dlm_hb_up);
if (status)
goto bail;
@@ -1845,8 +1853,6 @@ static int dlm_register_domain_handlers(struct dlm_ctxt *dlm)
sizeof(struct dlm_exit_domain),
dlm_begin_exit_domain_handler,
dlm, NULL, &dlm->dlm_domain_handlers);
- if (status)
- goto bail;
bail:
if (status)
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 482cfd344..ce38b4ccc 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -498,16 +498,6 @@ static void dlm_lockres_release(struct kref *kref)
mlog(0, "destroying lockres %.*s\n", res->lockname.len,
res->lockname.name);
- spin_lock(&dlm->track_lock);
- if (!list_empty(&res->tracking))
- list_del_init(&res->tracking);
- else {
- mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
- res->lockname.len, res->lockname.name);
- dlm_print_one_lock_resource(res);
- }
- spin_unlock(&dlm->track_lock);
-
atomic_dec(&dlm->res_cur_count);
if (!hlist_unhashed(&res->hash_node) ||
@@ -795,8 +785,18 @@ lookup:
dlm_lockres_grab_inflight_ref(dlm, tmpres);
spin_unlock(&tmpres->spinlock);
- if (res)
+ if (res) {
+ spin_lock(&dlm->track_lock);
+ if (!list_empty(&res->tracking))
+ list_del_init(&res->tracking);
+ else
+ mlog(ML_ERROR, "Resource %.*s not "
+ "on the Tracking list\n",
+ res->lockname.len,
+ res->lockname.name);
+ spin_unlock(&dlm->track_lock);
dlm_lockres_put(res);
+ }
res = tmpres;
goto leave;
}
@@ -1658,12 +1658,13 @@ send_response:
if (ret < 0) {
mlog(ML_ERROR, "failed to dispatch assert master work\n");
response = DLM_MASTER_RESP_ERROR;
+ spin_unlock(&res->spinlock);
dlm_lockres_put(res);
} else {
dispatched = 1;
__dlm_lockres_grab_inflight_worker(dlm, res);
+ spin_unlock(&res->spinlock);
}
- spin_unlock(&res->spinlock);
} else {
if (res)
dlm_lockres_put(res);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 3d90ad7ff..58eaa5c0d 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1723,8 +1723,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
} else {
dispatched = 1;
__dlm_lockres_grab_inflight_worker(dlm, res);
+ spin_unlock(&res->spinlock);
}
- spin_unlock(&res->spinlock);
} else {
/* put.. incase we are not the master */
spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 69aac6f08..2e5e6d5ff 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
__dlm_unhash_lockres(dlm, res);
+ spin_lock(&dlm->track_lock);
+ if (!list_empty(&res->tracking))
+ list_del_init(&res->tracking);
+ else {
+ mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+ res->lockname.len, res->lockname.name);
+ __dlm_print_one_lock_resource(res);
+ }
+ spin_unlock(&dlm->track_lock);
+
/* lockres is not in the hash now. drop the flag and wake up
* any processes waiting in dlm_get_lock_resource. */
if (!master) {
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 23157e40d..1c91103c1 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3035,8 +3035,6 @@ local:
ocfs2_orphan_scan_lock_res_init(&osb->osb_orphan_scan.os_lockres, osb);
osb->cconn = conn;
-
- status = 0;
bail:
if (status < 0) {
ocfs2_dlm_shutdown_debug(osb);
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 767370b65..e4719e0a3 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -305,8 +305,8 @@ static int ocfs2_last_eb_is_empty(struct inode *inode,
if (el->l_tree_depth) {
ocfs2_error(inode->i_sb,
- "Inode %lu has non zero tree depth in "
- "leaf block %llu\n", inode->i_ino,
+ "Inode %lu has non zero tree depth in leaf block %llu\n",
+ inode->i_ino,
(unsigned long long)eb_bh->b_blocknr);
ret = -EROFS;
goto out;
@@ -441,8 +441,8 @@ static int ocfs2_get_clusters_nocache(struct inode *inode,
if (el->l_tree_depth) {
ocfs2_error(inode->i_sb,
- "Inode %lu has non zero tree depth in "
- "leaf block %llu\n", inode->i_ino,
+ "Inode %lu has non zero tree depth in leaf block %llu\n",
+ inode->i_ino,
(unsigned long long)eb_bh->b_blocknr);
ret = -EROFS;
goto out;
@@ -475,8 +475,9 @@ static int ocfs2_get_clusters_nocache(struct inode *inode,
BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
if (!rec->e_blkno) {
- ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
- "record (%u, %u, 0)", inode->i_ino,
+ ocfs2_error(inode->i_sb,
+ "Inode %lu has bad extent record (%u, %u, 0)\n",
+ inode->i_ino,
le32_to_cpu(rec->e_cpos),
ocfs2_rec_clusters(el, rec));
ret = -EROFS;
@@ -564,8 +565,8 @@ int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
if (el->l_tree_depth) {
ocfs2_error(inode->i_sb,
- "Inode %lu has non zero tree depth in "
- "xattr leaf block %llu\n", inode->i_ino,
+ "Inode %lu has non zero tree depth in xattr leaf block %llu\n",
+ inode->i_ino,
(unsigned long long)eb_bh->b_blocknr);
ret = -EROFS;
goto out;
@@ -582,8 +583,9 @@ int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
BUG_ON(v_cluster < le32_to_cpu(rec->e_cpos));
if (!rec->e_blkno) {
- ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
- "record (%u, %u, 0) in xattr", inode->i_ino,
+ ocfs2_error(inode->i_sb,
+ "Inode %lu has bad extent record (%u, %u, 0) in xattr\n",
+ inode->i_ino,
le32_to_cpu(rec->e_cpos),
ocfs2_rec_clusters(el, rec));
ret = -EROFS;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 33efa334e..0e5b4515f 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -105,8 +105,11 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
file->f_path.dentry->d_name.len,
file->f_path.dentry->d_name.name, mode);
- if (file->f_mode & FMODE_WRITE)
- dquot_initialize(inode);
+ if (file->f_mode & FMODE_WRITE) {
+ status = dquot_initialize(inode);
+ if (status)
+ goto leave;
+ }
spin_lock(&oi->ip_lock);
@@ -1127,6 +1130,7 @@ out:
int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
{
int status = 0, size_change;
+ int inode_locked = 0;
struct inode *inode = d_inode(dentry);
struct super_block *sb = inode->i_sb;
struct ocfs2_super *osb = OCFS2_SB(sb);
@@ -1155,8 +1159,11 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
if (status)
return status;
- if (is_quota_modification(inode, attr))
- dquot_initialize(inode);
+ if (is_quota_modification(inode, attr)) {
+ status = dquot_initialize(inode);
+ if (status)
+ return status;
+ }
size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE;
if (size_change) {
status = ocfs2_rw_lock(inode, 1);
@@ -1172,6 +1179,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
mlog_errno(status);
goto bail_unlock_rw;
}
+ inode_locked = 1;
if (size_change) {
status = inode_newsize_ok(inode, attr->ia_size);
@@ -1209,8 +1217,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
&& OCFS2_HAS_RO_COMPAT_FEATURE(sb,
OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) {
transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid));
- if (!transfer_to[USRQUOTA]) {
- status = -ESRCH;
+ if (IS_ERR(transfer_to[USRQUOTA])) {
+ status = PTR_ERR(transfer_to[USRQUOTA]);
goto bail_unlock;
}
}
@@ -1218,8 +1226,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
&& OCFS2_HAS_RO_COMPAT_FEATURE(sb,
OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) {
transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid));
- if (!transfer_to[GRPQUOTA]) {
- status = -ESRCH;
+ if (IS_ERR(transfer_to[GRPQUOTA])) {
+ status = PTR_ERR(transfer_to[GRPQUOTA]);
goto bail_unlock;
}
}
@@ -1252,7 +1260,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
bail_commit:
ocfs2_commit_trans(osb, handle);
bail_unlock:
- ocfs2_inode_unlock(inode, 1);
+ if (status) {
+ ocfs2_inode_unlock(inode, 1);
+ inode_locked = 0;
+ }
bail_unlock_rw:
if (size_change)
ocfs2_rw_unlock(inode, 1);
@@ -1268,6 +1279,8 @@ bail:
if (status < 0)
mlog_errno(status);
}
+ if (inode_locked)
+ ocfs2_inode_unlock(inode, 1);
return status;
}
@@ -2256,8 +2269,6 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
ssize_t written = 0;
ssize_t ret;
size_t count = iov_iter_count(from), orig_count;
- loff_t old_size;
- u32 old_clusters;
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2265,6 +2276,8 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
OCFS2_MOUNT_COHERENCY_BUFFERED);
int unaligned_dio = 0;
int dropped_dio = 0;
+ int append_write = ((iocb->ki_pos + count) >=
+ i_size_read(inode) ? 1 : 0);
trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2284,8 +2297,9 @@ relock:
/*
* Concurrent O_DIRECT writes are allowed with
* mount_option "coherency=buffered".
+ * For append write, we must take rw EX.
*/
- rw_level = (!direct_io || full_coherency);
+ rw_level = (!direct_io || full_coherency || append_write);
ret = ocfs2_rw_lock(inode, rw_level);
if (ret < 0) {
@@ -2358,13 +2372,6 @@ relock:
ocfs2_iocb_set_unaligned_aio(iocb);
}
- /*
- * To later detect whether a journal commit for sync writes is
- * necessary, we sample i_size, and cluster count here.
- */
- old_size = i_size_read(inode);
- old_clusters = OCFS2_I(inode)->ip_clusters;
-
/* communicate with ocfs2_dio_end_io */
ocfs2_iocb_set_rw_locked(iocb, rw_level);
@@ -2410,7 +2417,7 @@ relock:
}
no_sync:
- if (unaligned_dio) {
+ if (unaligned_dio && ocfs2_iocb_is_unaligned_aio(iocb)) {
ocfs2_iocb_clear_unaligned_aio(iocb);
mutex_unlock(&OCFS2_I(inode)->ip_unaligned_aio);
}
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index b254416dc..8f87e05ee 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -971,6 +971,7 @@ static void ocfs2_delete_inode(struct inode *inode)
int wipe, status;
sigset_t oldset;
struct buffer_head *di_bh = NULL;
+ struct ocfs2_dinode *di = NULL;
trace_ocfs2_delete_inode(inode->i_ino,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1025,6 +1026,14 @@ static void ocfs2_delete_inode(struct inode *inode)
goto bail_unlock_nfs_sync;
}
+ di = (struct ocfs2_dinode *)di_bh->b_data;
+ /* Skip inode deletion and wait for dio orphan entry recovered
+ * first */
+ if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
+ ocfs2_cleanup_delete_inode(inode, 0);
+ goto bail_unlock_inode;
+ }
+
/* Query the cluster. This will be the final decision made
* before we go ahead and wipe the inode. */
status = ocfs2_query_inode_wipe(inode, di_bh, &wipe);
@@ -1191,17 +1200,19 @@ void ocfs2_evict_inode(struct inode *inode)
int ocfs2_drop_inode(struct inode *inode)
{
struct ocfs2_inode_info *oi = OCFS2_I(inode);
- int res;
trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno,
inode->i_nlink, oi->ip_flags);
- if (oi->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)
- res = 1;
- else
- res = generic_drop_inode(inode);
+ assert_spin_locked(&inode->i_lock);
+ inode->i_state |= I_WILL_FREE;
+ spin_unlock(&inode->i_lock);
+ write_inode_now(inode, 1);
+ spin_lock(&inode->i_lock);
+ WARN_ON(inode->i_state & I_NEW);
+ inode->i_state &= ~I_WILL_FREE;
- return res;
+ return 1;
}
/*
@@ -1350,32 +1361,32 @@ int ocfs2_validate_inode_block(struct super_block *sb,
rc = -EINVAL;
if (!OCFS2_IS_VALID_DINODE(di)) {
- ocfs2_error(sb, "Invalid dinode #%llu: signature = %.*s\n",
- (unsigned long long)bh->b_blocknr, 7,
- di->i_signature);
+ rc = ocfs2_error(sb, "Invalid dinode #%llu: signature = %.*s\n",
+ (unsigned long long)bh->b_blocknr, 7,
+ di->i_signature);
goto bail;
}
if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
- ocfs2_error(sb, "Invalid dinode #%llu: i_blkno is %llu\n",
- (unsigned long long)bh->b_blocknr,
- (unsigned long long)le64_to_cpu(di->i_blkno));
+ rc = ocfs2_error(sb, "Invalid dinode #%llu: i_blkno is %llu\n",
+ (unsigned long long)bh->b_blocknr,
+ (unsigned long long)le64_to_cpu(di->i_blkno));
goto bail;
}
if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
- ocfs2_error(sb,
- "Invalid dinode #%llu: OCFS2_VALID_FL not set\n",
- (unsigned long long)bh->b_blocknr);
+ rc = ocfs2_error(sb,
+ "Invalid dinode #%llu: OCFS2_VALID_FL not set\n",
+ (unsigned long long)bh->b_blocknr);
goto bail;
}
if (le32_to_cpu(di->i_fs_generation) !=
OCFS2_SB(sb)->fs_generation) {
- ocfs2_error(sb,
- "Invalid dinode #%llu: fs_generation is %u\n",
- (unsigned long long)bh->b_blocknr,
- le32_to_cpu(di->i_fs_generation));
+ rc = ocfs2_error(sb,
+ "Invalid dinode #%llu: fs_generation is %u\n",
+ (unsigned long long)bh->b_blocknr,
+ le32_to_cpu(di->i_fs_generation));
goto bail;
}
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 5e86b247c..ca3431ee7 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -81,8 +81,6 @@ struct ocfs2_inode_info
tid_t i_sync_tid;
tid_t i_datasync_tid;
- wait_queue_head_t append_dio_wq;
-
struct dquot *i_dquot[MAXQUOTAS];
};
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 7c099f703..ff82b2846 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -374,7 +374,7 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
mlog_errno(PTR_ERR(handle));
if (is_journal_aborted(journal)) {
- ocfs2_abort(osb->sb, "Detected aborted journal");
+ ocfs2_abort(osb->sb, "Detected aborted journal\n");
handle = ERR_PTR(-EROFS);
}
} else {
@@ -668,7 +668,23 @@ static int __ocfs2_journal_access(handle_t *handle,
mlog(ML_ERROR, "giving me a buffer that's not uptodate!\n");
mlog(ML_ERROR, "b_blocknr=%llu\n",
(unsigned long long)bh->b_blocknr);
- BUG();
+
+ lock_buffer(bh);
+ /*
+ * A previous attempt to write this buffer head failed.
+ * Nothing we can do but to retry the write and hope for
+ * the best.
+ */
+ if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) {
+ clear_buffer_write_io_error(bh);
+ set_buffer_uptodate(bh);
+ }
+
+ if (!buffer_uptodate(bh)) {
+ unlock_buffer(bh);
+ return -EIO;
+ }
+ unlock_buffer(bh);
}
/* Set the current transaction information on the ci so
@@ -2170,6 +2186,7 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
iter = oi->ip_next_orphan;
oi->ip_next_orphan = NULL;
+ mutex_lock(&inode->i_mutex);
ret = ocfs2_rw_lock(inode, 1);
if (ret < 0) {
mlog_errno(ret);
@@ -2193,7 +2210,9 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
* ocfs2_delete_inode. */
oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
spin_unlock(&oi->ip_lock);
- } else if ((orphan_reco_type == ORPHAN_NEED_TRUNCATE) &&
+ }
+
+ if ((orphan_reco_type == ORPHAN_NEED_TRUNCATE) &&
(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
ret = ocfs2_truncate_file(inode, di_bh,
i_size_read(inode));
@@ -2206,17 +2225,16 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
if (ret)
mlog_errno(ret);
-
- wake_up(&OCFS2_I(inode)->append_dio_wq);
} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
unlock_inode:
ocfs2_inode_unlock(inode, 1);
+ brelse(di_bh);
+ di_bh = NULL;
unlock_rw:
ocfs2_rw_unlock(inode, 1);
next:
+ mutex_unlock(&inode->i_mutex);
iput(inode);
- brelse(di_bh);
- di_bh = NULL;
inode = iter;
}
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 857bbbcd3..0a4457fb0 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -665,8 +665,7 @@ int ocfs2_reserve_local_alloc_bits(struct ocfs2_super *osb,
#ifdef CONFIG_OCFS2_DEBUG_FS
if (le32_to_cpu(alloc->id1.bitmap1.i_used) !=
ocfs2_local_alloc_count_bits(alloc)) {
- ocfs2_error(osb->sb, "local alloc inode %llu says it has "
- "%u used bits, but a count shows %u",
+ ocfs2_error(osb->sb, "local alloc inode %llu says it has %u used bits, but a count shows %u\n",
(unsigned long long)le64_to_cpu(alloc->i_blkno),
le32_to_cpu(alloc->id1.bitmap1.i_used),
ocfs2_local_alloc_count_bits(alloc));
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 56a768d06..124471d26 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -99,11 +99,9 @@ static int __ocfs2_move_extent(handle_t *handle,
index = ocfs2_search_extent_list(el, cpos);
if (index == -1) {
- ocfs2_error(inode->i_sb,
- "Inode %llu has an extent at cpos %u which can no "
- "longer be found.\n",
- (unsigned long long)ino, cpos);
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb,
+ "Inode %llu has an extent at cpos %u which can no longer be found\n",
+ (unsigned long long)ino, cpos);
goto out;
}
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 6e6abb93f..b7dfac226 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -200,11 +200,12 @@ bail:
static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode)
{
struct inode *inode;
+ int status;
inode = new_inode(dir->i_sb);
if (!inode) {
mlog(ML_ERROR, "new_inode failed!\n");
- return NULL;
+ return ERR_PTR(-ENOMEM);
}
/* populate as many fields early on as possible - many of
@@ -213,7 +214,10 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode)
if (S_ISDIR(mode))
set_nlink(inode, 2);
inode_init_owner(inode, dir, mode);
- dquot_initialize(inode);
+ status = dquot_initialize(inode);
+ if (status)
+ return ERR_PTR(status);
+
return inode;
}
@@ -264,7 +268,11 @@ static int ocfs2_mknod(struct inode *dir,
(unsigned long long)OCFS2_I(dir)->ip_blkno,
(unsigned long)dev, mode);
- dquot_initialize(dir);
+ status = dquot_initialize(dir);
+ if (status) {
+ mlog_errno(status);
+ return status;
+ }
/* get our super block */
osb = OCFS2_SB(dir->i_sb);
@@ -311,8 +319,9 @@ static int ocfs2_mknod(struct inode *dir,
}
inode = ocfs2_get_init_inode(dir, mode);
- if (!inode) {
- status = -ENOMEM;
+ if (IS_ERR(inode)) {
+ status = PTR_ERR(inode);
+ inode = NULL;
mlog_errno(status);
goto leave;
}
@@ -708,7 +717,11 @@ static int ocfs2_link(struct dentry *old_dentry,
if (S_ISDIR(inode->i_mode))
return -EPERM;
- dquot_initialize(dir);
+ err = dquot_initialize(dir);
+ if (err) {
+ mlog_errno(err);
+ return err;
+ }
err = ocfs2_double_lock(osb, &old_dir_bh, old_dir,
&parent_fe_bh, dir, 0);
@@ -896,7 +909,11 @@ static int ocfs2_unlink(struct inode *dir,
(unsigned long long)OCFS2_I(dir)->ip_blkno,
(unsigned long long)OCFS2_I(inode)->ip_blkno);
- dquot_initialize(dir);
+ status = dquot_initialize(dir);
+ if (status) {
+ mlog_errno(status);
+ return status;
+ }
BUG_ON(d_inode(dentry->d_parent) != dir);
@@ -1018,11 +1035,6 @@ leave:
if (handle)
ocfs2_commit_trans(osb, handle);
- if (child_locked)
- ocfs2_inode_unlock(inode, 1);
-
- ocfs2_inode_unlock(dir, 1);
-
if (orphan_dir) {
/* This was locked for us in ocfs2_prepare_orphan_dir() */
ocfs2_inode_unlock(orphan_dir, 1);
@@ -1030,6 +1042,11 @@ leave:
iput(orphan_dir);
}
+ if (child_locked)
+ ocfs2_inode_unlock(inode, 1);
+
+ ocfs2_inode_unlock(dir, 1);
+
brelse(fe_bh);
brelse(parent_node_bh);
@@ -1230,8 +1247,16 @@ static int ocfs2_rename(struct inode *old_dir,
old_dentry->d_name.len, old_dentry->d_name.name,
new_dentry->d_name.len, new_dentry->d_name.name);
- dquot_initialize(old_dir);
- dquot_initialize(new_dir);
+ status = dquot_initialize(old_dir);
+ if (status) {
+ mlog_errno(status);
+ goto bail;
+ }
+ status = dquot_initialize(new_dir);
+ if (status) {
+ mlog_errno(status);
+ goto bail;
+ }
osb = OCFS2_SB(old_dir->i_sb);
@@ -1284,6 +1309,11 @@ static int ocfs2_rename(struct inode *old_dir,
}
parents_locked = 1;
+ if (!new_dir->i_nlink) {
+ status = -EACCES;
+ goto bail;
+ }
+
/* make sure both dirs have bhs
* get an extra ref on old_dir_bh if old==new */
if (!new_dir_bh) {
@@ -1544,12 +1574,25 @@ static int ocfs2_rename(struct inode *old_dir,
status = ocfs2_find_entry(old_dentry->d_name.name,
old_dentry->d_name.len, old_dir,
&old_entry_lookup);
- if (status)
+ if (status) {
+ if (!is_journal_aborted(osb->journal->j_journal)) {
+ ocfs2_error(osb->sb, "new entry %.*s is added, but old entry %.*s "
+ "is not deleted.",
+ new_dentry->d_name.len, new_dentry->d_name.name,
+ old_dentry->d_name.len, old_dentry->d_name.name);
+ }
goto bail;
+ }
status = ocfs2_delete_entry(handle, old_dir, &old_entry_lookup);
if (status < 0) {
mlog_errno(status);
+ if (!is_journal_aborted(osb->journal->j_journal)) {
+ ocfs2_error(osb->sb, "new entry %.*s is added, but old entry %.*s "
+ "is not deleted.",
+ new_dentry->d_name.len, new_dentry->d_name.name,
+ old_dentry->d_name.len, old_dentry->d_name.name);
+ }
goto bail;
}
@@ -1608,21 +1651,9 @@ static int ocfs2_rename(struct inode *old_dir,
ocfs2_dentry_move(old_dentry, new_dentry, old_dir, new_dir);
status = 0;
bail:
- if (rename_lock)
- ocfs2_rename_unlock(osb);
-
if (handle)
ocfs2_commit_trans(osb, handle);
- if (parents_locked)
- ocfs2_double_unlock(old_dir, new_dir);
-
- if (old_child_locked)
- ocfs2_inode_unlock(old_inode, 1);
-
- if (new_child_locked)
- ocfs2_inode_unlock(new_inode, 1);
-
if (orphan_dir) {
/* This was locked for us in ocfs2_prepare_orphan_dir() */
ocfs2_inode_unlock(orphan_dir, 1);
@@ -1630,6 +1661,18 @@ bail:
iput(orphan_dir);
}
+ if (new_child_locked)
+ ocfs2_inode_unlock(new_inode, 1);
+
+ if (old_child_locked)
+ ocfs2_inode_unlock(old_inode, 1);
+
+ if (parents_locked)
+ ocfs2_double_unlock(old_dir, new_dir);
+
+ if (rename_lock)
+ ocfs2_rename_unlock(osb);
+
if (new_inode)
sync_mapping_buffers(old_inode->i_mapping);
@@ -1786,7 +1829,11 @@ static int ocfs2_symlink(struct inode *dir,
trace_ocfs2_symlink_begin(dir, dentry, symname,
dentry->d_name.len, dentry->d_name.name);
- dquot_initialize(dir);
+ status = dquot_initialize(dir);
+ if (status) {
+ mlog_errno(status);
+ goto bail;
+ }
sb = dir->i_sb;
osb = OCFS2_SB(sb);
@@ -1831,8 +1878,9 @@ static int ocfs2_symlink(struct inode *dir,
}
inode = ocfs2_get_init_inode(dir, S_IFLNK | S_IRWXUGO);
- if (!inode) {
- status = -ENOMEM;
+ if (IS_ERR(inode)) {
+ status = PTR_ERR(inode);
+ inode = NULL;
mlog_errno(status);
goto bail;
}
@@ -2485,8 +2533,9 @@ int ocfs2_create_inode_in_orphan(struct inode *dir,
}
inode = ocfs2_get_init_inode(dir, mode);
- if (!inode) {
- status = -ENOMEM;
+ if (IS_ERR(inode)) {
+ status = PTR_ERR(inode);
+ inode = NULL;
mlog_errno(status);
goto leave;
}
@@ -2570,27 +2619,6 @@ leave:
return status;
}
-static int ocfs2_dio_orphan_recovered(struct inode *inode)
-{
- int ret;
- struct buffer_head *di_bh = NULL;
- struct ocfs2_dinode *di = NULL;
-
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret < 0) {
- mlog_errno(ret);
- return 0;
- }
-
- di = (struct ocfs2_dinode *) di_bh->b_data;
- ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
-
- return ret;
-}
-
-#define OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL 10000
int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
struct inode *inode)
{
@@ -2602,7 +2630,6 @@ int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
handle_t *handle = NULL;
struct ocfs2_dinode *di = NULL;
-restart:
status = ocfs2_inode_lock(inode, &di_bh, 1);
if (status < 0) {
mlog_errno(status);
@@ -2612,15 +2639,21 @@ restart:
di = (struct ocfs2_dinode *) di_bh->b_data;
/*
* Another append dio crashed?
- * If so, wait for recovery first.
+ * If so, manually recover it first.
*/
if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
- ocfs2_inode_unlock(inode, 1);
- brelse(di_bh);
- wait_event_interruptible_timeout(OCFS2_I(inode)->append_dio_wq,
- ocfs2_dio_orphan_recovered(inode),
- msecs_to_jiffies(OCFS2_DIO_ORPHANED_FL_CHECK_INTERVAL));
- goto restart;
+ status = ocfs2_truncate_file(inode, di_bh, i_size_read(inode));
+ if (status < 0) {
+ if (status != -ENOSPC)
+ mlog_errno(status);
+ goto bail_unlock_inode;
+ }
+
+ status = ocfs2_del_inode_from_orphan(osb, inode, di_bh, 0, 0);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail_unlock_inode;
+ }
}
status = ocfs2_prepare_orphan_dir(osb, &orphan_dir_inode,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 690ddc601..7a0126267 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -286,6 +286,8 @@ enum ocfs2_mount_options
OCFS2_MOUNT_HB_GLOBAL = 1 << 14, /* Global heartbeat */
OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */
+ OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
+ OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
};
#define OCFS2_OSB_SOFT_RO 0x0001
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index db64ce2d4..540ab5b75 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -168,7 +168,7 @@
/* Refcount tree support */
#define OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE 0x1000
-/* Discontigous block groups */
+/* Discontiguous block groups */
#define OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG 0x2000
/*
@@ -939,7 +939,7 @@ struct ocfs2_group_desc
/*
* Block groups may be discontiguous when
* OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG is set.
- * The extents of a discontigous block group are
+ * The extents of a discontiguous block group are
* stored in bg_list. It is a flat list.
* l_tree_depth must always be zero. A
* discontiguous group is signified by a non-zero
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 3d0b63d34..8a54fd8a4 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -138,8 +138,7 @@ static int ocfs2_read_quota_block(struct inode *inode, u64 v_block,
if (i_size_read(inode) >> inode->i_sb->s_blocksize_bits <= v_block) {
ocfs2_error(inode->i_sb,
- "Quota file %llu is probably corrupted! Requested "
- "to read block %Lu but file has size only %Lu\n",
+ "Quota file %llu is probably corrupted! Requested to read block %Lu but file has size only %Lu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)v_block,
(unsigned long long)i_size_read(inode));
@@ -499,8 +498,8 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode,
dquot = dqget(sb,
make_kqid(&init_user_ns, type,
le64_to_cpu(dqblk->dqb_id)));
- if (!dquot) {
- status = -EIO;
+ if (IS_ERR(dquot)) {
+ status = PTR_ERR(dquot);
mlog(ML_ERROR, "Failed to get quota structure "
"for id %u, type %d. Cannot finish quota "
"file recovery.\n",
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index b69dd14c0..e5d57cd32 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -102,32 +102,30 @@ static int ocfs2_validate_refcount_block(struct super_block *sb,
if (!OCFS2_IS_VALID_REFCOUNT_BLOCK(rb)) {
- ocfs2_error(sb,
- "Refcount block #%llu has bad signature %.*s",
- (unsigned long long)bh->b_blocknr, 7,
- rb->rf_signature);
- return -EINVAL;
+ rc = ocfs2_error(sb,
+ "Refcount block #%llu has bad signature %.*s\n",
+ (unsigned long long)bh->b_blocknr, 7,
+ rb->rf_signature);
+ goto out;
}
if (le64_to_cpu(rb->rf_blkno) != bh->b_blocknr) {
- ocfs2_error(sb,
- "Refcount block #%llu has an invalid rf_blkno "
- "of %llu",
- (unsigned long long)bh->b_blocknr,
- (unsigned long long)le64_to_cpu(rb->rf_blkno));
- return -EINVAL;
+ rc = ocfs2_error(sb,
+ "Refcount block #%llu has an invalid rf_blkno of %llu\n",
+ (unsigned long long)bh->b_blocknr,
+ (unsigned long long)le64_to_cpu(rb->rf_blkno));
+ goto out;
}
if (le32_to_cpu(rb->rf_fs_generation) != OCFS2_SB(sb)->fs_generation) {
- ocfs2_error(sb,
- "Refcount block #%llu has an invalid "
- "rf_fs_generation of #%u",
- (unsigned long long)bh->b_blocknr,
- le32_to_cpu(rb->rf_fs_generation));
- return -EINVAL;
+ rc = ocfs2_error(sb,
+ "Refcount block #%llu has an invalid rf_fs_generation of #%u\n",
+ (unsigned long long)bh->b_blocknr,
+ le32_to_cpu(rb->rf_fs_generation));
+ goto out;
}
-
- return 0;
+out:
+ return rc;
}
static int ocfs2_read_refcount_block(struct ocfs2_caching_info *ci,
@@ -1102,12 +1100,10 @@ static int ocfs2_get_refcount_rec(struct ocfs2_caching_info *ci,
el = &eb->h_list;
if (el->l_tree_depth) {
- ocfs2_error(sb,
- "refcount tree %llu has non zero tree "
- "depth in leaf btree tree block %llu\n",
- (unsigned long long)ocfs2_metadata_cache_owner(ci),
- (unsigned long long)eb_bh->b_blocknr);
- ret = -EROFS;
+ ret = ocfs2_error(sb,
+ "refcount tree %llu has non zero tree depth in leaf btree tree block %llu\n",
+ (unsigned long long)ocfs2_metadata_cache_owner(ci),
+ (unsigned long long)eb_bh->b_blocknr);
goto out;
}
}
@@ -2359,10 +2355,8 @@ static int ocfs2_mark_extent_refcounted(struct inode *inode,
cpos, len, phys);
if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
- ocfs2_error(inode->i_sb, "Inode %lu want to use refcount "
- "tree, but the feature bit is not set in the "
- "super block.", inode->i_ino);
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
+ inode->i_ino);
goto out;
}
@@ -2545,10 +2539,8 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode,
u64 start_cpos = ocfs2_blocks_to_clusters(inode->i_sb, phys_blkno);
if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
- ocfs2_error(inode->i_sb, "Inode %lu want to use refcount "
- "tree, but the feature bit is not set in the "
- "super block.", inode->i_ino);
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
+ inode->i_ino);
goto out;
}
@@ -2672,11 +2664,10 @@ static int ocfs2_refcount_cal_cow_clusters(struct inode *inode,
el = &eb->h_list;
if (el->l_tree_depth) {
- ocfs2_error(inode->i_sb,
- "Inode %lu has non zero tree depth in "
- "leaf block %llu\n", inode->i_ino,
- (unsigned long long)eb_bh->b_blocknr);
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb,
+ "Inode %lu has non zero tree depth in leaf block %llu\n",
+ inode->i_ino,
+ (unsigned long long)eb_bh->b_blocknr);
goto out;
}
}
@@ -3106,11 +3097,9 @@ static int ocfs2_clear_ext_refcount(handle_t *handle,
index = ocfs2_search_extent_list(el, cpos);
if (index == -1) {
- ocfs2_error(sb,
- "Inode %llu has an extent at cpos %u which can no "
- "longer be found.\n",
- (unsigned long long)ino, cpos);
- ret = -EROFS;
+ ret = ocfs2_error(sb,
+ "Inode %llu has an extent at cpos %u which can no longer be found\n",
+ (unsigned long long)ino, cpos);
goto out;
}
@@ -3376,10 +3365,8 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
- ocfs2_error(inode->i_sb, "Inode %lu want to use refcount "
- "tree, but the feature bit is not set in the "
- "super block.", inode->i_ino);
- return -EROFS;
+ return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
+ inode->i_ino);
}
ocfs2_init_dealloc_ctxt(&context->dealloc);
@@ -4419,8 +4406,9 @@ static int ocfs2_vfs_reflink(struct dentry *old_dentry, struct inode *dir,
}
mutex_lock(&inode->i_mutex);
- dquot_initialize(dir);
- error = ocfs2_reflink(old_dentry, dir, new_dentry, preserve);
+ error = dquot_initialize(dir);
+ if (!error)
+ error = ocfs2_reflink(old_dentry, dir, new_dentry, preserve);
mutex_unlock(&inode->i_mutex);
if (!error)
fsnotify_create(dir, new_dentry);
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 2768eb1da..ced70c813 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -655,14 +655,7 @@ static int ocfs2_control_init(void)
static void ocfs2_control_exit(void)
{
- int rc;
-
- rc = misc_deregister(&ocfs2_control_device);
- if (rc)
- printk(KERN_ERR
- "ocfs2: Unable to deregister ocfs2_control device "
- "(errno %d)\n",
- -rc);
+ misc_deregister(&ocfs2_control_device);
}
static void fsdlm_lock_ast_wrapper(void *astarg)
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 447902963..d83d2602c 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -149,10 +149,8 @@ void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
brelse(ac->ac_bh);
ac->ac_bh = NULL;
ac->ac_resv = NULL;
- if (ac->ac_find_loc_priv) {
- kfree(ac->ac_find_loc_priv);
- ac->ac_find_loc_priv = NULL;
- }
+ kfree(ac->ac_find_loc_priv);
+ ac->ac_find_loc_priv = NULL;
}
void ocfs2_free_alloc_context(struct ocfs2_alloc_context *ac)
@@ -167,12 +165,12 @@ static u32 ocfs2_bits_per_group(struct ocfs2_chain_list *cl)
}
#define do_error(fmt, ...) \
- do{ \
- if (resize) \
- mlog(ML_ERROR, fmt "\n", ##__VA_ARGS__); \
- else \
- ocfs2_error(sb, fmt, ##__VA_ARGS__); \
- } while (0)
+do { \
+ if (resize) \
+ mlog(ML_ERROR, fmt, ##__VA_ARGS__); \
+ else \
+ return ocfs2_error(sb, fmt, ##__VA_ARGS__); \
+} while (0)
static int ocfs2_validate_gd_self(struct super_block *sb,
struct buffer_head *bh,
@@ -181,44 +179,35 @@ static int ocfs2_validate_gd_self(struct super_block *sb,
struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
if (!OCFS2_IS_VALID_GROUP_DESC(gd)) {
- do_error("Group descriptor #%llu has bad signature %.*s",
+ do_error("Group descriptor #%llu has bad signature %.*s\n",
(unsigned long long)bh->b_blocknr, 7,
gd->bg_signature);
- return -EINVAL;
}
if (le64_to_cpu(gd->bg_blkno) != bh->b_blocknr) {
- do_error("Group descriptor #%llu has an invalid bg_blkno "
- "of %llu",
+ do_error("Group descriptor #%llu has an invalid bg_blkno of %llu\n",
(unsigned long long)bh->b_blocknr,
(unsigned long long)le64_to_cpu(gd->bg_blkno));
- return -EINVAL;
}
if (le32_to_cpu(gd->bg_generation) != OCFS2_SB(sb)->fs_generation) {
- do_error("Group descriptor #%llu has an invalid "
- "fs_generation of #%u",
+ do_error("Group descriptor #%llu has an invalid fs_generation of #%u\n",
(unsigned long long)bh->b_blocknr,
le32_to_cpu(gd->bg_generation));
- return -EINVAL;
}
if (le16_to_cpu(gd->bg_free_bits_count) > le16_to_cpu(gd->bg_bits)) {
- do_error("Group descriptor #%llu has bit count %u but "
- "claims that %u are free",
+ do_error("Group descriptor #%llu has bit count %u but claims that %u are free\n",
(unsigned long long)bh->b_blocknr,
le16_to_cpu(gd->bg_bits),
le16_to_cpu(gd->bg_free_bits_count));
- return -EINVAL;
}
if (le16_to_cpu(gd->bg_bits) > (8 * le16_to_cpu(gd->bg_size))) {
- do_error("Group descriptor #%llu has bit count %u but "
- "max bitmap bits of %u",
+ do_error("Group descriptor #%llu has bit count %u but max bitmap bits of %u\n",
(unsigned long long)bh->b_blocknr,
le16_to_cpu(gd->bg_bits),
8 * le16_to_cpu(gd->bg_size));
- return -EINVAL;
}
return 0;
@@ -233,20 +222,17 @@ static int ocfs2_validate_gd_parent(struct super_block *sb,
struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data;
if (di->i_blkno != gd->bg_parent_dinode) {
- do_error("Group descriptor #%llu has bad parent "
- "pointer (%llu, expected %llu)",
+ do_error("Group descriptor #%llu has bad parent pointer (%llu, expected %llu)\n",
(unsigned long long)bh->b_blocknr,
(unsigned long long)le64_to_cpu(gd->bg_parent_dinode),
(unsigned long long)le64_to_cpu(di->i_blkno));
- return -EINVAL;
}
max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc);
if (le16_to_cpu(gd->bg_bits) > max_bits) {
- do_error("Group descriptor #%llu has bit count of %u",
+ do_error("Group descriptor #%llu has bit count of %u\n",
(unsigned long long)bh->b_blocknr,
le16_to_cpu(gd->bg_bits));
- return -EINVAL;
}
/* In resize, we may meet the case bg_chain == cl_next_free_rec. */
@@ -254,10 +240,9 @@ static int ocfs2_validate_gd_parent(struct super_block *sb,
le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) ||
((le16_to_cpu(gd->bg_chain) ==
le16_to_cpu(di->id2.i_chain.cl_next_free_rec)) && !resize)) {
- do_error("Group descriptor #%llu has bad chain %u",
+ do_error("Group descriptor #%llu has bad chain %u\n",
(unsigned long long)bh->b_blocknr,
le16_to_cpu(gd->bg_chain));
- return -EINVAL;
}
return 0;
@@ -384,11 +369,10 @@ static int ocfs2_block_group_fill(handle_t *handle,
struct super_block * sb = alloc_inode->i_sb;
if (((unsigned long long) bg_bh->b_blocknr) != group_blkno) {
- ocfs2_error(alloc_inode->i_sb, "group block (%llu) != "
- "b_blocknr (%llu)",
- (unsigned long long)group_blkno,
- (unsigned long long) bg_bh->b_blocknr);
- status = -EIO;
+ status = ocfs2_error(alloc_inode->i_sb,
+ "group block (%llu) != b_blocknr (%llu)\n",
+ (unsigned long long)group_blkno,
+ (unsigned long long) bg_bh->b_blocknr);
goto bail;
}
@@ -834,9 +818,9 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
BUG_ON(!OCFS2_IS_VALID_DINODE(fe));
if (!(fe->i_flags & cpu_to_le32(OCFS2_CHAIN_FL))) {
- ocfs2_error(alloc_inode->i_sb, "Invalid chain allocator %llu",
- (unsigned long long)le64_to_cpu(fe->i_blkno));
- status = -EIO;
+ status = ocfs2_error(alloc_inode->i_sb,
+ "Invalid chain allocator %llu\n",
+ (unsigned long long)le64_to_cpu(fe->i_blkno));
goto bail;
}
@@ -1370,12 +1354,11 @@ int ocfs2_block_group_set_bits(handle_t *handle,
le16_add_cpu(&bg->bg_free_bits_count, -num_bits);
if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
- ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
- " count %u but claims %u are freed. num_bits %d",
- (unsigned long long)le64_to_cpu(bg->bg_blkno),
- le16_to_cpu(bg->bg_bits),
- le16_to_cpu(bg->bg_free_bits_count), num_bits);
- return -EROFS;
+ return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n",
+ (unsigned long long)le64_to_cpu(bg->bg_blkno),
+ le16_to_cpu(bg->bg_bits),
+ le16_to_cpu(bg->bg_free_bits_count),
+ num_bits);
}
while(num_bits--)
ocfs2_set_bit(bit_off++, bitmap);
@@ -1905,13 +1888,11 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
if (le32_to_cpu(fe->id1.bitmap1.i_used) >=
le32_to_cpu(fe->id1.bitmap1.i_total)) {
- ocfs2_error(ac->ac_inode->i_sb,
- "Chain allocator dinode %llu has %u used "
- "bits but only %u total.",
- (unsigned long long)le64_to_cpu(fe->i_blkno),
- le32_to_cpu(fe->id1.bitmap1.i_used),
- le32_to_cpu(fe->id1.bitmap1.i_total));
- status = -EIO;
+ status = ocfs2_error(ac->ac_inode->i_sb,
+ "Chain allocator dinode %llu has %u used bits but only %u total\n",
+ (unsigned long long)le64_to_cpu(fe->i_blkno),
+ le32_to_cpu(fe->id1.bitmap1.i_used),
+ le32_to_cpu(fe->id1.bitmap1.i_total));
goto bail;
}
@@ -2429,12 +2410,11 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
}
le16_add_cpu(&bg->bg_free_bits_count, num_bits);
if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
- ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit"
- " count %u but claims %u are freed. num_bits %d",
- (unsigned long long)le64_to_cpu(bg->bg_blkno),
- le16_to_cpu(bg->bg_bits),
- le16_to_cpu(bg->bg_free_bits_count), num_bits);
- return -EROFS;
+ return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n",
+ (unsigned long long)le64_to_cpu(bg->bg_blkno),
+ le16_to_cpu(bg->bg_bits),
+ le16_to_cpu(bg->bg_free_bits_count),
+ num_bits);
}
if (undo_fn)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a482e312c..2de4c8a93 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -192,6 +192,7 @@ enum {
Opt_resv_level,
Opt_dir_resv_level,
Opt_journal_async_commit,
+ Opt_err_cont,
Opt_err,
};
@@ -224,6 +225,7 @@ static const match_table_t tokens = {
{Opt_resv_level, "resv_level=%u"},
{Opt_dir_resv_level, "dir_resv_level=%u"},
{Opt_journal_async_commit, "journal_async_commit"},
+ {Opt_err_cont, "errors=continue"},
{Opt_err, NULL}
};
@@ -1330,10 +1332,19 @@ static int ocfs2_parse_options(struct super_block *sb,
mopt->mount_opt |= OCFS2_MOUNT_NOINTR;
break;
case Opt_err_panic:
+ mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT;
+ mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS;
mopt->mount_opt |= OCFS2_MOUNT_ERRORS_PANIC;
break;
case Opt_err_ro:
+ mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_CONT;
mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC;
+ mopt->mount_opt |= OCFS2_MOUNT_ERRORS_ROFS;
+ break;
+ case Opt_err_cont:
+ mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_ROFS;
+ mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC;
+ mopt->mount_opt |= OCFS2_MOUNT_ERRORS_CONT;
break;
case Opt_data_ordered:
mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK;
@@ -1530,6 +1541,8 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
if (opts & OCFS2_MOUNT_ERRORS_PANIC)
seq_printf(s, ",errors=panic");
+ else if (opts & OCFS2_MOUNT_ERRORS_CONT)
+ seq_printf(s, ",errors=continue");
else
seq_printf(s, ",errors=remount-ro");
@@ -1746,8 +1759,6 @@ static void ocfs2_inode_init_once(void *data)
ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
ocfs2_lock_res_init_once(&oi->ip_open_lockres);
- init_waitqueue_head(&oi->append_dio_wq);
-
ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
&ocfs2_inode_caching_ops);
@@ -2541,31 +2552,43 @@ static void ocfs2_delete_osb(struct ocfs2_super *osb)
memset(osb, 0, sizeof(struct ocfs2_super));
}
-/* Put OCFS2 into a readonly state, or (if the user specifies it),
- * panic(). We do not support continue-on-error operation. */
-static void ocfs2_handle_error(struct super_block *sb)
+/* Depending on the mount option passed, perform one of the following:
+ * Put OCFS2 into a readonly state (default)
+ * Return EIO so that only the process errs
+ * Fix the error as if fsck.ocfs2 -y
+ * panic
+ */
+static int ocfs2_handle_error(struct super_block *sb)
{
struct ocfs2_super *osb = OCFS2_SB(sb);
-
- if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_PANIC)
- panic("OCFS2: (device %s): panic forced after error\n",
- sb->s_id);
+ int rv = 0;
ocfs2_set_osb_flag(osb, OCFS2_OSB_ERROR_FS);
+ pr_crit("On-disk corruption discovered. "
+ "Please run fsck.ocfs2 once the filesystem is unmounted.\n");
- if (sb->s_flags & MS_RDONLY &&
- (ocfs2_is_soft_readonly(osb) ||
- ocfs2_is_hard_readonly(osb)))
- return;
-
- printk(KERN_CRIT "File system is now read-only due to the potential "
- "of on-disk corruption. Please run fsck.ocfs2 once the file "
- "system is unmounted.\n");
- sb->s_flags |= MS_RDONLY;
- ocfs2_set_ro_flag(osb, 0);
+ if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_PANIC) {
+ panic("OCFS2: (device %s): panic forced after error\n",
+ sb->s_id);
+ } else if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_CONT) {
+ pr_crit("OCFS2: Returning error to the calling process.\n");
+ rv = -EIO;
+ } else { /* default option */
+ rv = -EROFS;
+ if (sb->s_flags & MS_RDONLY &&
+ (ocfs2_is_soft_readonly(osb) ||
+ ocfs2_is_hard_readonly(osb)))
+ return rv;
+
+ pr_crit("OCFS2: File system is now read-only.\n");
+ sb->s_flags |= MS_RDONLY;
+ ocfs2_set_ro_flag(osb, 0);
+ }
+
+ return rv;
}
-void __ocfs2_error(struct super_block *sb, const char *function,
+int __ocfs2_error(struct super_block *sb, const char *function,
const char *fmt, ...)
{
struct va_format vaf;
@@ -2577,12 +2600,12 @@ void __ocfs2_error(struct super_block *sb, const char *function,
/* Not using mlog here because we want to show the actual
* function the error came from. */
- printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %pV\n",
+ printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %pV",
sb->s_id, function, &vaf);
va_end(args);
- ocfs2_handle_error(sb);
+ return ocfs2_handle_error(sb);
}
/* Handle critical errors. This is intentionally more drastic than
@@ -2599,7 +2622,7 @@ void __ocfs2_abort(struct super_block *sb, const char *function,
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_CRIT "OCFS2: abort (device %s): %s: %pV\n",
+ printk(KERN_CRIT "OCFS2: abort (device %s): %s: %pV",
sb->s_id, function, &vaf);
va_end(args);
diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h
index 74ff74cf7..b477d0b1c 100644
--- a/fs/ocfs2/super.h
+++ b/fs/ocfs2/super.h
@@ -32,16 +32,18 @@ int ocfs2_publish_get_mount_state(struct ocfs2_super *osb,
int node_num);
__printf(3, 4)
-void __ocfs2_error(struct super_block *sb, const char *function,
+int __ocfs2_error(struct super_block *sb, const char *function,
const char *fmt, ...);
-#define ocfs2_error(sb, fmt, args...) __ocfs2_error(sb, __PRETTY_FUNCTION__, fmt, ##args)
+#define ocfs2_error(sb, fmt, ...) \
+ __ocfs2_error(sb, __PRETTY_FUNCTION__, fmt, ##__VA_ARGS__)
__printf(3, 4)
void __ocfs2_abort(struct super_block *sb, const char *function,
const char *fmt, ...);
-#define ocfs2_abort(sb, fmt, args...) __ocfs2_abort(sb, __PRETTY_FUNCTION__, fmt, ##args)
+#define ocfs2_abort(sb, fmt, ...) \
+ __ocfs2_abort(sb, __PRETTY_FUNCTION__, fmt, ##__VA_ARGS__)
/*
* Void signal blockers, because in-kernel sigprocmask() only fails
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 889f3796a..ebfdea786 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -499,30 +499,24 @@ static int ocfs2_validate_xattr_block(struct super_block *sb,
*/
if (!OCFS2_IS_VALID_XATTR_BLOCK(xb)) {
- ocfs2_error(sb,
- "Extended attribute block #%llu has bad "
- "signature %.*s",
- (unsigned long long)bh->b_blocknr, 7,
- xb->xb_signature);
- return -EINVAL;
+ return ocfs2_error(sb,
+ "Extended attribute block #%llu has bad signature %.*s\n",
+ (unsigned long long)bh->b_blocknr, 7,
+ xb->xb_signature);
}
if (le64_to_cpu(xb->xb_blkno) != bh->b_blocknr) {
- ocfs2_error(sb,
- "Extended attribute block #%llu has an "
- "invalid xb_blkno of %llu",
- (unsigned long long)bh->b_blocknr,
- (unsigned long long)le64_to_cpu(xb->xb_blkno));
- return -EINVAL;
+ return ocfs2_error(sb,
+ "Extended attribute block #%llu has an invalid xb_blkno of %llu\n",
+ (unsigned long long)bh->b_blocknr,
+ (unsigned long long)le64_to_cpu(xb->xb_blkno));
}
if (le32_to_cpu(xb->xb_fs_generation) != OCFS2_SB(sb)->fs_generation) {
- ocfs2_error(sb,
- "Extended attribute block #%llu has an invalid "
- "xb_fs_generation of #%u",
- (unsigned long long)bh->b_blocknr,
- le32_to_cpu(xb->xb_fs_generation));
- return -EINVAL;
+ return ocfs2_error(sb,
+ "Extended attribute block #%llu has an invalid xb_fs_generation of #%u\n",
+ (unsigned long long)bh->b_blocknr,
+ le32_to_cpu(xb->xb_fs_generation));
}
return 0;
@@ -3694,11 +3688,10 @@ static int ocfs2_xattr_get_rec(struct inode *inode,
el = &eb->h_list;
if (el->l_tree_depth) {
- ocfs2_error(inode->i_sb,
- "Inode %lu has non zero tree depth in "
- "xattr tree block %llu\n", inode->i_ino,
- (unsigned long long)eb_bh->b_blocknr);
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb,
+ "Inode %lu has non zero tree depth in xattr tree block %llu\n",
+ inode->i_ino,
+ (unsigned long long)eb_bh->b_blocknr);
goto out;
}
}
@@ -3713,11 +3706,10 @@ static int ocfs2_xattr_get_rec(struct inode *inode,
}
if (!e_blkno) {
- ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
- "record (%u, %u, 0) in xattr", inode->i_ino,
- le32_to_cpu(rec->e_cpos),
- ocfs2_rec_clusters(el, rec));
- ret = -EROFS;
+ ret = ocfs2_error(inode->i_sb, "Inode %lu has bad extent record (%u, %u, 0) in xattr\n",
+ inode->i_ino,
+ le32_to_cpu(rec->e_cpos),
+ ocfs2_rec_clusters(el, rec));
goto out;
}
@@ -7334,6 +7326,9 @@ static size_t ocfs2_xattr_trusted_list(struct dentry *dentry, char *list,
const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
+ if (!capable(CAP_SYS_ADMIN))
+ return 0;
+
if (list && total_len <= list_size) {
memcpy(list, XATTR_TRUSTED_PREFIX, prefix_len);
memcpy(list + prefix_len, name, name_len);