summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorMichael Bestas <mkbestas@lineageos.org>2020-03-08 00:00:18 +0200
committerMichael Bestas <mkbestas@lineageos.org>2020-03-08 00:00:18 +0200
commit3010be7cfa594aac6134887b8505b3f1bd619ad4 (patch)
tree867d21a3537efafc20045dc58ffd18104f0ca474 /fs
parenta0edb0970a4d09aed24b6f37cd6fd0c545565485 (diff)
parent4db1ebdd40ec0b6ee8fb5744b20274a37aea267d (diff)
Merge branch 'android-4.4-p' of https://android.googlesource.com/kernel/common into lineage-17.1-caf-msm8998
This brings LA.UM.8.4.r1-05200-8x98.0 up to date with https://android.googlesource.com/kernel/common/ android-4.4-p at commit: 4db1ebdd40ec0 FROMLIST: HID: nintendo: add nintendo switch controller driver Conflicts: arch/arm64/boot/Makefile arch/arm64/kernel/psci.c arch/x86/configs/x86_64_cuttlefish_defconfig drivers/md/dm.c drivers/of/Kconfig drivers/thermal/thermal_core.c fs/proc/meminfo.c kernel/locking/spinlock_debug.c kernel/time/hrtimer.c net/wireless/util.c Change-Id: I5b5163497b7c6ab8487ffbb2d036e4cda01ed670
Diffstat (limited to 'fs')
-rw-r--r--fs/autofs4/expire.c5
-rw-r--r--fs/btrfs/ctree.c66
-rw-r--r--fs/btrfs/ctree.h6
-rw-r--r--fs/btrfs/delayed-ref.c11
-rw-r--r--fs/btrfs/disk-io.c4
-rw-r--r--fs/btrfs/extent_io.c14
-rw-r--r--fs/btrfs/extent_map.c11
-rw-r--r--fs/btrfs/file.c2
-rw-r--r--fs/btrfs/free-space-cache.c6
-rw-r--r--fs/btrfs/inode-map.c1
-rw-r--r--fs/btrfs/inode.c1
-rw-r--r--fs/btrfs/ioctl.c10
-rw-r--r--fs/btrfs/ordered-data.c7
-rw-r--r--fs/btrfs/relocation.c1
-rw-r--r--fs/btrfs/super.c26
-rw-r--r--fs/btrfs/tests/btrfs-tests.c1
-rw-r--r--fs/btrfs/tests/qgroup-tests.c4
-rw-r--r--fs/btrfs/transaction.c8
-rw-r--r--fs/btrfs/tree-log.c7
-rw-r--r--fs/btrfs/uuid-tree.c2
-rw-r--r--fs/btrfs/volumes.h1
-rw-r--r--fs/char_dev.c2
-rw-r--r--fs/cifs/connect.c3
-rw-r--r--fs/cifs/file.c14
-rw-r--r--fs/cifs/smb2file.c2
-rw-r--r--fs/cifs/smb2misc.c7
-rw-r--r--fs/cifs/smb2pdu.c10
-rw-r--r--fs/dlm/lockspace.c1
-rw-r--r--fs/dlm/memory.c9
-rw-r--r--fs/dlm/user.c3
-rw-r--r--fs/ecryptfs/crypto.c6
-rw-r--r--fs/ecryptfs/keystore.c2
-rw-r--r--fs/ecryptfs/messaging.c1
-rw-r--r--fs/exportfs/expfs.c1
-rw-r--r--fs/ext2/super.c6
-rw-r--r--fs/ext4/dir.c19
-rw-r--r--fs/ext4/ext4.h7
-rw-r--r--fs/ext4/inline.c2
-rw-r--r--fs/ext4/inode.c29
-rw-r--r--fs/ext4/namei.c19
-rw-r--r--fs/ext4/super.c60
-rw-r--r--fs/fuse/dir.c27
-rw-r--r--fs/fuse/fuse_i.h2
-rw-r--r--fs/gfs2/bmap.c2
-rw-r--r--fs/jbd2/checkpoint.c2
-rw-r--r--fs/jbd2/commit.c54
-rw-r--r--fs/jbd2/journal.c21
-rw-r--r--fs/jbd2/transaction.c10
-rw-r--r--fs/jfs/jfs_txnmgr.c3
-rw-r--r--fs/locks.c2
-rw-r--r--fs/namei.c17
-rw-r--r--fs/nfs/Kconfig2
-rw-r--r--fs/nfs/callback_proc.c2
-rw-r--r--fs/nfs/dir.c59
-rw-r--r--fs/nfs/nfs4client.c2
-rw-r--r--fs/nfs/super.c2
-rw-r--r--fs/nfsd/nfs4recover.c17
-rw-r--r--fs/nfsd/vfs.c17
-rw-r--r--fs/ocfs2/acl.c4
-rw-r--r--fs/ocfs2/journal.c14
-rw-r--r--fs/ocfs2/journal.h8
-rw-r--r--fs/ocfs2/quota_global.c2
-rw-r--r--fs/overlayfs/inode.c13
-rw-r--r--fs/proc/array.c18
-rw-r--r--fs/proc/meminfo.c38
-rw-r--r--fs/pstore/ram.c11
-rw-r--r--fs/quota/dquot.c40
-rw-r--r--fs/readdir.c40
-rw-r--r--fs/reiserfs/stree.c3
-rw-r--r--fs/reiserfs/super.c4
-rw-r--r--fs/ubifs/file.c5
-rw-r--r--fs/xfs/xfs_ioctl32.c6
-rw-r--r--fs/xfs/xfs_log.c2
-rw-r--r--fs/xfs/xfs_quotaops.c3
-rw-r--r--fs/xfs/xfs_rtalloc.c4
75 files changed, 528 insertions, 325 deletions
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 0d8b9c4f27f2..5124f06c32bc 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -467,9 +467,10 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
*/
flags &= ~AUTOFS_EXP_LEAVES;
found = should_expire(expired, mnt, timeout, how);
- if (!found || found != expired)
- /* Something has changed, continue */
+ if (found != expired) { // something has changed, continue
+ dput(found);
goto next;
+ }
if (expired != dentry)
dput(dentry);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index a980b3309770..8eac5f75bca3 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -332,26 +332,6 @@ struct tree_mod_elem {
struct tree_mod_root old_root;
};
-static inline void tree_mod_log_read_lock(struct btrfs_fs_info *fs_info)
-{
- read_lock(&fs_info->tree_mod_log_lock);
-}
-
-static inline void tree_mod_log_read_unlock(struct btrfs_fs_info *fs_info)
-{
- read_unlock(&fs_info->tree_mod_log_lock);
-}
-
-static inline void tree_mod_log_write_lock(struct btrfs_fs_info *fs_info)
-{
- write_lock(&fs_info->tree_mod_log_lock);
-}
-
-static inline void tree_mod_log_write_unlock(struct btrfs_fs_info *fs_info)
-{
- write_unlock(&fs_info->tree_mod_log_lock);
-}
-
/*
* Pull a new tree mod seq number for our operation.
*/
@@ -371,14 +351,12 @@ static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info)
u64 btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info,
struct seq_list *elem)
{
- tree_mod_log_write_lock(fs_info);
- spin_lock(&fs_info->tree_mod_seq_lock);
+ write_lock(&fs_info->tree_mod_log_lock);
if (!elem->seq) {
elem->seq = btrfs_inc_tree_mod_seq(fs_info);
list_add_tail(&elem->list, &fs_info->tree_mod_seq_list);
}
- spin_unlock(&fs_info->tree_mod_seq_lock);
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&fs_info->tree_mod_log_lock);
return elem->seq;
}
@@ -397,7 +375,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
if (!seq_putting)
return;
- spin_lock(&fs_info->tree_mod_seq_lock);
+ write_lock(&fs_info->tree_mod_log_lock);
list_del(&elem->list);
elem->seq = 0;
@@ -408,29 +386,27 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
* blocker with lower sequence number exists, we
* cannot remove anything from the log
*/
- spin_unlock(&fs_info->tree_mod_seq_lock);
+ write_unlock(&fs_info->tree_mod_log_lock);
return;
}
min_seq = cur_elem->seq;
}
}
- spin_unlock(&fs_info->tree_mod_seq_lock);
/*
* anything that's lower than the lowest existing (read: blocked)
* sequence number can be removed from the tree.
*/
- tree_mod_log_write_lock(fs_info);
tm_root = &fs_info->tree_mod_log;
for (node = rb_first(tm_root); node; node = next) {
next = rb_next(node);
tm = container_of(node, struct tree_mod_elem, node);
- if (tm->seq > min_seq)
+ if (tm->seq >= min_seq)
continue;
rb_erase(node, tm_root);
kfree(tm);
}
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&fs_info->tree_mod_log_lock);
}
/*
@@ -441,7 +417,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
* operations, or the shifted logical of the affected block for all other
* operations.
*
- * Note: must be called with write lock (tree_mod_log_write_lock).
+ * Note: must be called with write lock for fs_info::tree_mod_log_lock.
*/
static noinline int
__tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
@@ -481,7 +457,7 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
* Determines if logging can be omitted. Returns 1 if it can. Otherwise, it
* returns zero with the tree_mod_log_lock acquired. The caller must hold
* this until all tree mod log insertions are recorded in the rb tree and then
- * call tree_mod_log_write_unlock() to release.
+ * write unlock fs_info::tree_mod_log_lock.
*/
static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb) {
@@ -491,9 +467,9 @@ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info,
if (eb && btrfs_header_level(eb) == 0)
return 1;
- tree_mod_log_write_lock(fs_info);
+ write_lock(&fs_info->tree_mod_log_lock);
if (list_empty(&(fs_info)->tree_mod_seq_list)) {
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&fs_info->tree_mod_log_lock);
return 1;
}
@@ -557,7 +533,7 @@ tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
}
ret = __tree_mod_log_insert(fs_info, tm);
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
if (ret)
kfree(tm);
@@ -621,7 +597,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
ret = __tree_mod_log_insert(fs_info, tm);
if (ret)
goto free_tms;
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
kfree(tm_list);
return 0;
@@ -632,7 +608,7 @@ free_tms:
kfree(tm_list[i]);
}
if (locked)
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
kfree(tm_list);
kfree(tm);
@@ -713,7 +689,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
if (!ret)
ret = __tree_mod_log_insert(fs_info, tm);
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&fs_info->tree_mod_log_lock);
if (ret)
goto free_tms;
kfree(tm_list);
@@ -741,7 +717,7 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
struct tree_mod_elem *found = NULL;
u64 index = start >> PAGE_CACHE_SHIFT;
- tree_mod_log_read_lock(fs_info);
+ read_lock(&fs_info->tree_mod_log_lock);
tm_root = &fs_info->tree_mod_log;
node = tm_root->rb_node;
while (node) {
@@ -769,7 +745,7 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
break;
}
}
- tree_mod_log_read_unlock(fs_info);
+ read_unlock(&fs_info->tree_mod_log_lock);
return found;
}
@@ -850,7 +826,7 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
goto free_tms;
}
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&fs_info->tree_mod_log_lock);
kfree(tm_list);
return 0;
@@ -862,7 +838,7 @@ free_tms:
kfree(tm_list[i]);
}
if (locked)
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&fs_info->tree_mod_log_lock);
kfree(tm_list);
return ret;
@@ -922,7 +898,7 @@ tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
goto free_tms;
ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems);
- tree_mod_log_write_unlock(fs_info);
+ write_unlock(&eb->fs_info->tree_mod_log_lock);
if (ret)
goto free_tms;
kfree(tm_list);
@@ -1284,7 +1260,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
unsigned long p_size = sizeof(struct btrfs_key_ptr);
n = btrfs_header_nritems(eb);
- tree_mod_log_read_lock(fs_info);
+ read_lock(&fs_info->tree_mod_log_lock);
while (tm && tm->seq >= time_seq) {
/*
* all the operations are recorded with the operator used for
@@ -1339,7 +1315,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
if (tm->index != first_tm->index)
break;
}
- tree_mod_log_read_unlock(fs_info);
+ read_unlock(&fs_info->tree_mod_log_lock);
btrfs_set_header_nritems(eb, n);
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4a91d3119e59..0b06d4942da7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1576,14 +1576,12 @@ struct btrfs_fs_info {
struct list_head delayed_iputs;
struct mutex cleaner_delayed_iput_mutex;
- /* this protects tree_mod_seq_list */
- spinlock_t tree_mod_seq_lock;
atomic64_t tree_mod_seq;
- struct list_head tree_mod_seq_list;
- /* this protects tree_mod_log */
+ /* this protects tree_mod_log and tree_mod_seq_list */
rwlock_t tree_mod_log_lock;
struct rb_root tree_mod_log;
+ struct list_head tree_mod_seq_list;
atomic_t nr_async_submits;
atomic_t async_submit_draining;
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index e06dd75ad13f..bb1e32f77b69 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -193,8 +193,6 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
ref->in_tree = 0;
btrfs_put_delayed_ref(ref);
atomic_dec(&delayed_refs->num_entries);
- if (trans->delayed_ref_updates)
- trans->delayed_ref_updates--;
}
static bool merge_ref(struct btrfs_trans_handle *trans,
@@ -281,7 +279,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
if (head->is_data)
return;
- spin_lock(&fs_info->tree_mod_seq_lock);
+ read_lock(&fs_info->tree_mod_log_lock);
if (!list_empty(&fs_info->tree_mod_seq_list)) {
struct seq_list *elem;
@@ -289,7 +287,7 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
struct seq_list, list);
seq = elem->seq;
}
- spin_unlock(&fs_info->tree_mod_seq_lock);
+ read_unlock(&fs_info->tree_mod_log_lock);
ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
list);
@@ -317,7 +315,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
struct seq_list *elem;
int ret = 0;
- spin_lock(&fs_info->tree_mod_seq_lock);
+ read_lock(&fs_info->tree_mod_log_lock);
if (!list_empty(&fs_info->tree_mod_seq_list)) {
elem = list_first_entry(&fs_info->tree_mod_seq_list,
struct seq_list, list);
@@ -330,7 +328,7 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
}
}
- spin_unlock(&fs_info->tree_mod_seq_lock);
+ read_unlock(&fs_info->tree_mod_log_lock);
return ret;
}
@@ -444,7 +442,6 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
add_tail:
list_add_tail(&ref->list, &href->ref_list);
atomic_inc(&root->num_entries);
- trans->delayed_ref_updates++;
spin_unlock(&href->lock);
return ret;
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 78722aaffecd..656f0b768185 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1698,8 +1698,8 @@ static void end_workqueue_fn(struct btrfs_work *work)
bio->bi_error = end_io_wq->error;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
- kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
bio_endio(bio);
+ kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
}
static int cleaner_kthread(void *arg)
@@ -2481,7 +2481,6 @@ int open_ctree(struct super_block *sb,
spin_lock_init(&fs_info->delayed_iput_lock);
spin_lock_init(&fs_info->defrag_inodes_lock);
spin_lock_init(&fs_info->free_chunk_lock);
- spin_lock_init(&fs_info->tree_mod_seq_lock);
spin_lock_init(&fs_info->super_lock);
spin_lock_init(&fs_info->qgroup_op_lock);
spin_lock_init(&fs_info->buffer_lock);
@@ -2973,6 +2972,7 @@ retry_root_backup:
/* do not make disk changes in broken FS */
if (btrfs_super_log_root(disk_super) != 0) {
+ btrfs_info(fs_info, "start tree-log replay");
ret = btrfs_replay_log(fs_info, fs_devices);
if (ret) {
err = ret;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 315f21191643..9ab5056462b6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4153,6 +4153,14 @@ retry:
*/
scanned = 1;
index = 0;
+
+ /*
+ * If we're looping we could run into a page that is locked by a
+ * writer and that writer could be waiting on writeback for a
+ * page in our current bio, and thus deadlock, so flush the
+ * write bio here.
+ */
+ flush_write_bio(data);
goto retry;
}
btrfs_add_delayed_iput(inode);
@@ -4937,12 +4945,14 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
return eb;
eb = alloc_dummy_extent_buffer(fs_info, start);
if (!eb)
- return NULL;
+ return ERR_PTR(-ENOMEM);
eb->fs_info = fs_info;
again:
ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
- if (ret)
+ if (ret) {
+ exists = ERR_PTR(ret);
goto free_eb;
+ }
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
start >> PAGE_CACHE_SHIFT, eb);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 84fb56d5c018..3818b65b0682 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -227,6 +227,17 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
struct extent_map *merge = NULL;
struct rb_node *rb;
+ /*
+ * We can't modify an extent map that is in the tree and that is being
+ * used by another task, as it can cause that other task to see it in
+ * inconsistent state during the merging. We always have 1 reference for
+ * the tree and 1 for this task (which is unpinning the extent map or
+ * clearing the logging flag), so anything > 2 means it's being used by
+ * other tasks too.
+ */
+ if (atomic_read(&em->refs) > 2)
+ return;
+
if (em->start != 0) {
rb = rb_prev(&em->rb_node);
if (rb)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d056060529f8..73b547f88bfc 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1525,6 +1525,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
}
reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+ only_release_metadata = false;
if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
BTRFS_INODE_PREALLOC)) &&
@@ -1659,7 +1660,6 @@ again:
set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
lockend, EXTENT_NORESERVE, NULL,
NULL, GFP_NOFS);
- only_release_metadata = false;
}
btrfs_drop_pages(pages, num_pages);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 6c0161284a9e..e5351d9a8dfb 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -391,6 +391,12 @@ static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, struct inode *inode
if (uptodate && !PageUptodate(page)) {
btrfs_readpage(NULL, page);
lock_page(page);
+ if (page->mapping != inode->i_mapping) {
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "free space cache page truncated");
+ io_ctl_drop_pages(io_ctl);
+ return -EIO;
+ }
if (!PageUptodate(page)) {
btrfs_err(BTRFS_I(inode)->root->fs_info,
"error reading free space cache");
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 07573dc1614a..3469c7ce7cb6 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -158,6 +158,7 @@ static void start_caching(struct btrfs_root *root)
spin_lock(&root->ino_cache_lock);
root->ino_cache_state = BTRFS_CACHE_FINISHED;
spin_unlock(&root->ino_cache_lock);
+ wake_up(&root->ino_cache_wait);
return;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d2c3edb50702..0067de1b38fc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5506,7 +5506,6 @@ static void inode_tree_del(struct inode *inode)
spin_unlock(&root->inode_lock);
if (empty && btrfs_root_refs(&root->root_item) == 0) {
- synchronize_srcu(&root->fs_info->subvol_srcu);
spin_lock(&root->inode_lock);
empty = RB_EMPTY_ROOT(&root->inode_tree);
spin_unlock(&root->inode_lock);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 3379490ce54d..119b1c5c279b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -594,12 +594,18 @@ static noinline int create_subvol(struct inode *dir,
btrfs_i_size_write(dir, dir->i_size + namelen * 2);
ret = btrfs_update_inode(trans, root, dir);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto fail;
+ }
ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
objectid, root->root_key.objectid,
btrfs_ino(dir), index, name, namelen);
- BUG_ON(ret);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto fail;
+ }
ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 8c27292ea9ea..2eadc8f8c9ef 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -820,10 +820,15 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len)
}
btrfs_start_ordered_extent(inode, ordered, 1);
end = ordered->file_offset;
+ /*
+ * If the ordered extent had an error save the error but don't
+ * exit without waiting first for all other ordered extents in
+ * the range to complete.
+ */
if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
ret = -EIO;
btrfs_put_ordered_extent(ordered);
- if (ret || end == 0 || end == start)
+ if (end == 0 || end == start)
break;
end--;
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index d6ccfb31aef0..f38bac9456fd 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4454,6 +4454,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
reloc_root->root_key.offset);
if (IS_ERR(fs_root)) {
err = PTR_ERR(fs_root);
+ list_add_tail(&reloc_root->root_list, &reloc_roots);
goto out_free;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0f99336c37eb..404051bf5cba 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1702,6 +1702,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
}
if (btrfs_super_log_root(fs_info->super_copy) != 0) {
+ btrfs_warn(fs_info,
+ "mount required to replay tree-log, cannot remount read-write");
ret = -EINVAL;
goto restore;
}
@@ -1978,6 +1980,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
u64 thresh = 0;
+ int mixed = 0;
/*
* holding chunk_muext to avoid allocating new chunks, holding
@@ -2003,8 +2006,17 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
}
}
}
- if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
- total_free_meta += found->disk_total - found->disk_used;
+
+ /*
+ * Metadata in mixed block goup profiles are accounted in data
+ */
+ if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
+ if (found->flags & BTRFS_BLOCK_GROUP_DATA)
+ mixed = 1;
+ else
+ total_free_meta += found->disk_total -
+ found->disk_used;
+ }
total_used += found->disk_used;
}
@@ -2042,7 +2054,15 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
*/
thresh = 4 * 1024 * 1024;
- if (total_free_meta - thresh < block_rsv->size)
+ /*
+ * We only want to claim there's no available space if we can no longer
+ * allocate chunks for our metadata profile and our global reserve will
+ * not fit in the free metadata space. If we aren't ->full then we
+ * still can allocate chunks and thus are fine using the currently
+ * calculated f_bavail.
+ */
+ if (!mixed && block_rsv->space_info->full &&
+ total_free_meta - thresh < block_rsv->size)
buf->f_bavail = 0;
buf->f_type = BTRFS_SUPER_MAGIC;
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index 9626252ee6b4..69255148f0c8 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -109,7 +109,6 @@ struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void)
spin_lock_init(&fs_info->qgroup_op_lock);
spin_lock_init(&fs_info->super_lock);
spin_lock_init(&fs_info->fs_roots_radix_lock);
- spin_lock_init(&fs_info->tree_mod_seq_lock);
mutex_init(&fs_info->qgroup_ioctl_lock);
mutex_init(&fs_info->qgroup_rescan_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 2b2978c04e80..1efec40455f8 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -477,9 +477,9 @@ int btrfs_test_qgroups(void)
* *cough*backref walking code*cough*
*/
root->node = alloc_test_extent_buffer(root->fs_info, 4096);
- if (!root->node) {
+ if (IS_ERR(root->node)) {
test_msg("Couldn't allocate dummy buffer\n");
- ret = -ENOMEM;
+ ret = PTR_ERR(root->node);
goto out;
}
btrfs_set_header_level(root->node, 0);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 098016338f98..64e449eb2ecd 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1814,6 +1814,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
struct btrfs_inode *btree_ino = BTRFS_I(root->fs_info->btree_inode);
int ret;
+ /*
+ * Some places just start a transaction to commit it. We need to make
+ * sure that if this commit fails that the abort code actually marks the
+ * transaction as failed, so set trans->dirty to make the abort code do
+ * the right thing.
+ */
+ trans->dirty = true;
+
/* Stop the commit early if ->aborted is set */
if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
ret = cur_trans->aborted;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f9c3907bf159..4320f346b0b9 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4404,13 +4404,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
struct btrfs_file_extent_item);
if (btrfs_file_extent_type(leaf, extent) ==
- BTRFS_FILE_EXTENT_INLINE) {
- len = btrfs_file_extent_inline_len(leaf,
- path->slots[0],
- extent);
- ASSERT(len == i_size);
+ BTRFS_FILE_EXTENT_INLINE)
return 0;
- }
len = btrfs_file_extent_num_bytes(leaf, extent);
/* Last extent goes beyond i_size, no need to log a hole. */
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index 837a9a8d579e..24eb6283dc62 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -332,6 +332,8 @@ again_search_slot:
}
if (ret < 0 && ret != -ENOENT)
goto out;
+ key.offset++;
+ goto again_search_slot;
}
item_size -= sizeof(subid_le);
offset += sizeof(subid_le);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 7feac2d9da56..d24f3ceb0691 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -312,7 +312,6 @@ struct btrfs_bio {
u64 map_type; /* get from map_lookup->type */
bio_end_io_t *end_io;
struct bio *orig_bio;
- unsigned long flags;
void *private;
atomic_t error;
int max_errors;
diff --git a/fs/char_dev.c b/fs/char_dev.c
index d0655ca89481..f1f3bb812799 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -332,7 +332,7 @@ static struct kobject *cdev_get(struct cdev *p)
if (owner && !try_module_get(owner))
return NULL;
- kobj = kobject_get(&p->kobj);
+ kobj = kobject_get_unless_zero(&p->kobj);
if (!kobj)
module_put(owner);
return kobj;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 63108343124a..4bde8acca455 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -939,6 +939,7 @@ cifs_demultiplex_thread(void *p)
mempool_resize(cifs_req_poolp, length + cifs_min_rcv);
set_freezable();
+ allow_kernel_signal(SIGKILL);
while (server->tcpStatus != CifsExiting) {
if (try_to_freeze())
continue;
@@ -2246,7 +2247,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
task = xchg(&server->tsk, NULL);
if (task)
- force_sig(SIGKILL, task);
+ send_sig(SIGKILL, task, 1);
}
static struct TCP_Server_Info *
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5cad1109ed80..18ecfa4d9757 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -312,9 +312,6 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
INIT_LIST_HEAD(&fdlocks->locks);
fdlocks->cfile = cfile;
cfile->llist = fdlocks;
- cifs_down_write(&cinode->lock_sem);
- list_add(&fdlocks->llist, &cinode->llist);
- up_write(&cinode->lock_sem);
cfile->count = 1;
cfile->pid = current->tgid;
@@ -338,6 +335,10 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
oplock = 0;
}
+ cifs_down_write(&cinode->lock_sem);
+ list_add(&fdlocks->llist, &cinode->llist);
+ up_write(&cinode->lock_sem);
+
spin_lock(&tcon->open_file_lock);
if (fid->pending_open->oplock != CIFS_OPLOCK_NO_CHANGE && oplock)
oplock = fid->pending_open->oplock;
@@ -702,6 +703,13 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;
+ /* O_SYNC also has bit for O_DSYNC so following check picks up either */
+ if (cfile->f_flags & O_SYNC)
+ create_options |= CREATE_WRITE_THROUGH;
+
+ if (cfile->f_flags & O_DIRECT)
+ create_options |= CREATE_NO_BUFFER;
+
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &cfile->fid);
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 41f1a5dd33a5..4dcce3f034f4 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -69,7 +69,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
goto out;
- if (oparms->tcon->use_resilient) {
+ if (oparms->tcon->use_resilient) {
nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */
nr_ioctl_req.Reserved = 0;
rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid,
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 0e62bf1ebbd7..44198b9a5315 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -582,10 +582,10 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
spin_lock(&cifs_tcp_ses_lock);
list_for_each(tmp, &server->smb_ses_list) {
ses = list_entry(tmp, struct cifs_ses, smb_ses_list);
+
list_for_each(tmp1, &ses->tcon_list) {
tcon = list_entry(tmp1, struct cifs_tcon, tcon_list);
- cifs_stats_inc(&tcon->stats.cifs_stats.num_oplock_brks);
spin_lock(&tcon->open_file_lock);
list_for_each(tmp2, &tcon->openFileList) {
cfile = list_entry(tmp2, struct cifsFileInfo,
@@ -597,6 +597,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
continue;
cifs_dbg(FYI, "file id match, oplock break\n");
+ cifs_stats_inc(
+ &tcon->stats.cifs_stats.num_oplock_brks);
cinode = CIFS_I(d_inode(cfile->dentry));
spin_lock(&cfile->file_info_lock);
if (!CIFS_CACHE_WRITE(cinode) &&
@@ -628,9 +630,6 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
return true;
}
spin_unlock(&tcon->open_file_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- cifs_dbg(FYI, "No matching file for oplock break\n");
- return true;
}
}
spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 84e60b3a5c7c..d4472a494758 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -250,9 +250,14 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
*/
mutex_lock(&tcon->ses->session_mutex);
rc = cifs_negotiate_protocol(0, tcon->ses);
- if (!rc && tcon->ses->need_reconnect)
+ if (!rc && tcon->ses->need_reconnect) {
rc = cifs_setup_session(0, tcon->ses, nls_codepage);
-
+ if ((rc == -EACCES) && !tcon->retry) {
+ rc = -EHOSTDOWN;
+ mutex_unlock(&tcon->ses->session_mutex);
+ goto failed;
+ }
+ }
if (rc || !tcon->need_reconnect) {
mutex_unlock(&tcon->ses->session_mutex);
goto out;
@@ -286,6 +291,7 @@ out:
case SMB2_SET_INFO:
rc = -EAGAIN;
}
+failed:
unload_nls(nls_codepage);
return rc;
}
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 30e4e01db35a..b14bb2c46042 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -800,6 +800,7 @@ static int release_lockspace(struct dlm_ls *ls, int force)
dlm_delete_debug_file(ls);
+ idr_destroy(&ls->ls_recover_idr);
kfree(ls->ls_recover_buf);
/*
diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c
index 7cd24bccd4fe..37be29f21d04 100644
--- a/fs/dlm/memory.c
+++ b/fs/dlm/memory.c
@@ -38,10 +38,8 @@ int __init dlm_memory_init(void)
void dlm_memory_exit(void)
{
- if (lkb_cache)
- kmem_cache_destroy(lkb_cache);
- if (rsb_cache)
- kmem_cache_destroy(rsb_cache);
+ kmem_cache_destroy(lkb_cache);
+ kmem_cache_destroy(rsb_cache);
}
char *dlm_allocate_lvb(struct dlm_ls *ls)
@@ -86,8 +84,7 @@ void dlm_free_lkb(struct dlm_lkb *lkb)
struct dlm_user_args *ua;
ua = lkb->lkb_ua;
if (ua) {
- if (ua->lksb.sb_lvbptr)
- kfree(ua->lksb.sb_lvbptr);
+ kfree(ua->lksb.sb_lvbptr);
kfree(ua);
}
}
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index dd2b7416e40a..761d74a84f92 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -25,6 +25,7 @@
#include "lvb_table.h"
#include "user.h"
#include "ast.h"
+#include "config.h"
static const char name_prefix[] = "dlm";
static const struct file_operations device_fops;
@@ -402,7 +403,7 @@ static int device_create_lockspace(struct dlm_lspace_params *params)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- error = dlm_new_lockspace(params->name, NULL, params->flags,
+ error = dlm_new_lockspace(params->name, dlm_config.ci_cluster_name, params->flags,
DLM_USER_LVB_LEN, NULL, NULL, NULL,
&lockspace);
if (error)
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 27d1db57f578..d173e40042e8 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -347,8 +347,10 @@ static int crypt_scatterlist(struct ecryptfs_crypt_stat *crypt_stat,
struct extent_crypt_result ecr;
int rc = 0;
- BUG_ON(!crypt_stat || !crypt_stat->tfm
- || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED));
+ if (!crypt_stat || !crypt_stat->tfm
+ || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
+ return -EINVAL;
+
if (unlikely(ecryptfs_verbosity > 0)) {
ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n",
ecryptfs_get_key_size_to_enc_data(crypt_stat));
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index ea3d99ebb6ee..06be4269b0b5 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1296,7 +1296,7 @@ parse_tag_1_packet(struct ecryptfs_crypt_stat *crypt_stat,
printk(KERN_ERR "Enter w/ first byte != 0x%.2x\n",
ECRYPTFS_TAG_1_PACKET_TYPE);
rc = -EINVAL;
- goto out;
+ goto out_free;
}
/* Released: wipe_auth_tok_list called in ecryptfs_parse_packet_set or
* at end of function upon failure */
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index 4f457d5c4933..26464f9d9b76 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -397,6 +397,7 @@ int __init ecryptfs_init_messaging(void)
* ecryptfs_message_buf_len),
GFP_KERNEL);
if (!ecryptfs_msg_ctx_arr) {
+ kfree(ecryptfs_daemon_hash);
rc = -ENOMEM;
printk(KERN_ERR "%s: Failed to allocate memory\n", __func__);
goto out;
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 6599c6124552..01cbdd0987c0 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -148,6 +148,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt,
mutex_unlock(&parent->d_inode->i_mutex);
if (IS_ERR(tmp)) {
dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp));
+ err = PTR_ERR(tmp);
goto out_err;
}
if (tmp != dentry) {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 7600c98a8f86..f5cf7faf43c1 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1054,9 +1054,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
goto cantfind_ext2;
- sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
- le32_to_cpu(es->s_first_data_block) - 1)
- / EXT2_BLOCKS_PER_GROUP(sb)) + 1;
+ sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
+ le32_to_cpu(es->s_first_data_block) - 1)
+ / EXT2_BLOCKS_PER_GROUP(sb)) + 1;
db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
EXT2_DESC_PER_BLOCK(sb);
sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL);
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index e452f9a9f174..3dc54352c9e7 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -75,6 +75,11 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
error_msg = "rec_len is too small for name_len";
else if (unlikely(((char *) de - buf) + rlen > size))
error_msg = "directory entry overrun";
+ else if (unlikely(((char *) de - buf) + rlen >
+ size - EXT4_DIR_REC_LEN(1) &&
+ ((char *) de - buf) + rlen != size)) {
+ error_msg = "directory entry too close to block end";
+ }
else if (unlikely(le32_to_cpu(de->inode) >
le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
error_msg = "inode out of bounds";
@@ -120,12 +125,14 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx)
if (err != ERR_BAD_DX_DIR) {
return err;
}
- /*
- * We don't set the inode dirty flag since it's not
- * critical that it get flushed back to the disk.
- */
- ext4_clear_inode_flag(file_inode(file),
- EXT4_INODE_INDEX);
+ /* Can we just clear INDEX flag to ignore htree information? */
+ if (!ext4_has_metadata_csum(sb)) {
+ /*
+ * We don't set the inode dirty flag since it's not
+ * critical that it gets flushed back to the disk.
+ */
+ ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+ }
}
if (ext4_has_inline_data(inode)) {
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index c161f9a9e7e1..9882af3428df 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2408,8 +2408,11 @@ int ext4_insert_dentry(struct inode *dir,
struct ext4_filename *fname);
static inline void ext4_update_dx_flag(struct inode *inode)
{
- if (!ext4_has_feature_dir_index(inode->i_sb))
+ if (!ext4_has_feature_dir_index(inode->i_sb)) {
+ /* ext4_iget() should have caught this... */
+ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb));
ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
+ }
}
static unsigned char ext4_filetype_table[] = {
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
@@ -2878,7 +2881,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
!mutex_is_locked(&inode->i_mutex));
down_write(&EXT4_I(inode)->i_data_sem);
if (newsize > EXT4_I(inode)->i_disksize)
- EXT4_I(inode)->i_disksize = newsize;
+ WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
up_write(&EXT4_I(inode)->i_data_sem);
}
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index ec506c2733ee..f7ed5072436e 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1430,7 +1430,7 @@ int htree_inlinedir_to_tree(struct file *dir_file,
err = ext4_htree_store_dirent(dir_file, hinfo->hash,
hinfo->minor_hash, de, &tmp_str);
if (err) {
- count = err;
+ ret = err;
goto out;
}
count++;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index a8eeea6bcb7c..66983dbfd1f9 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2350,7 +2350,7 @@ update_disksize:
* truncate are avoided by checking i_size under i_data_sem.
*/
disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
- if (disksize > EXT4_I(inode)->i_disksize) {
+ if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
int err2;
loff_t i_size;
@@ -4401,6 +4401,18 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ret = -EFSCORRUPTED;
goto bad_inode;
}
+ /*
+ * If dir_index is not enabled but there's dir with INDEX flag set,
+ * we'd normally treat htree data as empty space. But with metadata
+ * checksumming that corrupts checksums so forbid that.
+ */
+ if (!ext4_has_feature_dir_index(sb) && ext4_has_metadata_csum(sb) &&
+ ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) {
+ EXT4_ERROR_INODE(inode,
+ "iget: Dir with htree data on filesystem without dir_index feature.");
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
ei->i_disksize = inode->i_size;
#ifdef CONFIG_QUOTA
ei->i_reserved_quota = 0;
@@ -5265,10 +5277,25 @@ static int ext4_expand_extra_isize(struct inode *inode,
{
struct ext4_inode *raw_inode;
struct ext4_xattr_ibody_header *header;
+ unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb);
+ struct ext4_inode_info *ei = EXT4_I(inode);
if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
return 0;
+ /* this was checked at iget time, but double check for good measure */
+ if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) ||
+ (ei->i_extra_isize & 3)) {
+ EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)",
+ ei->i_extra_isize,
+ EXT4_INODE_SIZE(inode->i_sb));
+ return -EFSCORRUPTED;
+ }
+ if ((new_extra_isize < ei->i_extra_isize) ||
+ (new_extra_isize < 4) ||
+ (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE))
+ return -EINVAL; /* Should never happen */
+
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index c455a8b649a1..c95bbf87ee67 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1418,6 +1418,7 @@ restart:
/*
* We deal with the read-ahead logic here.
*/
+ cond_resched();
if (ra_ptr >= ra_max) {
/* Refill the readahead buffer */
ra_ptr = 0;
@@ -2119,6 +2120,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
retval = ext4_dx_add_entry(handle, &fname, dir, inode);
if (!retval || (retval != ERR_BAD_DX_DIR))
goto out;
+ /* Can we just ignore htree data? */
+ if (ext4_has_metadata_csum(sb)) {
+ EXT4_ERROR_INODE(dir,
+ "Directory has corrupted htree index.");
+ retval = -EFSCORRUPTED;
+ goto out;
+ }
ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
dx_fallback++;
ext4_mark_inode_dirty(handle, dir);
@@ -3039,18 +3047,17 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
- if (inode->i_nlink == 0) {
- ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
- dentry->d_name.len, dentry->d_name.name);
- set_nlink(inode, 1);
- }
retval = ext4_delete_entry(handle, dir, de, bh);
if (retval)
goto end_unlink;
dir->i_ctime = dir->i_mtime = ext4_current_time(dir);
ext4_update_dx_flag(dir);
ext4_mark_inode_dirty(handle, dir);
- drop_nlink(inode);
+ if (inode->i_nlink == 0)
+ ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
+ dentry->d_name.len, dentry->d_name.name);
+ else
+ drop_nlink(inode);
if (!inode->i_nlink)
ext4_orphan_add(handle, inode);
inode->i_ctime = ext4_current_time(inode);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9a652931eef8..aeb6b9aa326b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3168,6 +3168,40 @@ int ext4_calculate_overhead(struct super_block *sb)
return 0;
}
+static void ext4_clamp_want_extra_isize(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ unsigned def_extra_isize = sizeof(struct ext4_inode) -
+ EXT4_GOOD_OLD_INODE_SIZE;
+
+ if (sbi->s_inode_size == EXT4_GOOD_OLD_INODE_SIZE) {
+ sbi->s_want_extra_isize = 0;
+ return;
+ }
+ if (sbi->s_want_extra_isize < 4) {
+ sbi->s_want_extra_isize = def_extra_isize;
+ if (ext4_has_feature_extra_isize(sb)) {
+ if (sbi->s_want_extra_isize <
+ le16_to_cpu(es->s_want_extra_isize))
+ sbi->s_want_extra_isize =
+ le16_to_cpu(es->s_want_extra_isize);
+ if (sbi->s_want_extra_isize <
+ le16_to_cpu(es->s_min_extra_isize))
+ sbi->s_want_extra_isize =
+ le16_to_cpu(es->s_min_extra_isize);
+ }
+ }
+ /* Check if enough inode space is available */
+ if ((sbi->s_want_extra_isize > sbi->s_inode_size) ||
+ (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
+ sbi->s_inode_size)) {
+ sbi->s_want_extra_isize = def_extra_isize;
+ ext4_msg(sb, KERN_INFO,
+ "required extra inode space not available");
+ }
+}
+
static void ext4_set_resv_clusters(struct super_block *sb)
{
ext4_fsblk_t resv_clusters;
@@ -3990,29 +4024,7 @@ no_journal:
if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY))
sb->s_flags |= MS_RDONLY;
- /* determine the minimum size of new large inodes, if present */
- if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
- sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
- EXT4_GOOD_OLD_INODE_SIZE;
- if (ext4_has_feature_extra_isize(sb)) {
- if (sbi->s_want_extra_isize <
- le16_to_cpu(es->s_want_extra_isize))
- sbi->s_want_extra_isize =
- le16_to_cpu(es->s_want_extra_isize);
- if (sbi->s_want_extra_isize <
- le16_to_cpu(es->s_min_extra_isize))
- sbi->s_want_extra_isize =
- le16_to_cpu(es->s_min_extra_isize);
- }
- }
- /* Check if enough inode space is available */
- if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
- sbi->s_inode_size) {
- sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
- EXT4_GOOD_OLD_INODE_SIZE;
- ext4_msg(sb, KERN_INFO, "required extra inode space not"
- "available");
- }
+ ext4_clamp_want_extra_isize(sb);
ext4_set_resv_clusters(sb);
@@ -4769,6 +4781,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
+ ext4_clamp_want_extra_isize(sb);
+
if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
test_opt(sb, JOURNAL_CHECKSUM)) {
ext4_msg(sb, KERN_ERR, "changing journal_checksum "
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 4a9f20a861cf..7a5ff8d5afbd 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -240,7 +240,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
kfree(forget);
if (ret == -ENOMEM)
goto out;
- if (ret || (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
+ if (ret || fuse_invalid_attr(&outarg.attr) ||
+ (outarg.attr.mode ^ inode->i_mode) & S_IFMT)
goto invalid;
fuse_change_attributes(inode, &outarg.attr,
@@ -327,6 +328,12 @@ int fuse_valid_type(int m)
S_ISBLK(m) || S_ISFIFO(m) || S_ISSOCK(m);
}
+bool fuse_invalid_attr(struct fuse_attr *attr)
+{
+ return !fuse_valid_type(attr->mode) ||
+ attr->size > LLONG_MAX;
+}
+
int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
struct fuse_entry_out *outarg, struct inode **inode)
{
@@ -358,7 +365,7 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, struct qstr *name,
err = -EIO;
if (!outarg->nodeid)
goto out_put_forget;
- if (!fuse_valid_type(outarg->attr.mode))
+ if (fuse_invalid_attr(&outarg->attr))
goto out_put_forget;
*inode = fuse_iget(sb, outarg->nodeid, outarg->generation,
@@ -479,7 +486,8 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
goto out_free_ff;
err = -EIO;
- if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid))
+ if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid) ||
+ fuse_invalid_attr(&outentry.attr))
goto out_free_ff;
ff->fh = outopen.fh;
@@ -587,7 +595,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
goto out_put_forget_req;
err = -EIO;
- if (invalid_nodeid(outarg.nodeid))
+ if (invalid_nodeid(outarg.nodeid) || fuse_invalid_attr(&outarg.attr))
goto out_put_forget_req;
if ((outarg.attr.mode ^ mode) & S_IFMT)
@@ -860,7 +868,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir,
spin_lock(&fc->lock);
fi->attr_version = ++fc->attr_version;
- inc_nlink(inode);
+ if (likely(inode->i_nlink < UINT_MAX))
+ inc_nlink(inode);
spin_unlock(&fc->lock);
fuse_invalidate_attr(inode);
fuse_update_ctime(inode);
@@ -940,7 +949,8 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat,
args.out.args[0].value = &outarg;
err = fuse_simple_request(fc, &args);
if (!err) {
- if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
+ if (fuse_invalid_attr(&outarg.attr) ||
+ (inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
} else {
@@ -1245,7 +1255,7 @@ static int fuse_direntplus_link(struct file *file,
if (invalid_nodeid(o->nodeid))
return -EIO;
- if (!fuse_valid_type(o->attr.mode))
+ if (fuse_invalid_attr(&o->attr))
return -EIO;
fc = get_fuse_conn(dir);
@@ -1717,7 +1727,8 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr,
goto error;
}
- if ((inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
+ if (fuse_invalid_attr(&outarg.attr) ||
+ (inode->i_mode ^ outarg.attr.mode) & S_IFMT) {
make_bad_inode(inode);
err = -EIO;
goto error;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 5a8cef204cda..f7b70b858157 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -901,6 +901,8 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc);
*/
int fuse_valid_type(int m);
+bool fuse_invalid_attr(struct fuse_attr *attr);
+
/**
* Is current process allowed to perform filesystem operation?
*/
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 09476bb8f6cd..f0302e09eff9 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1235,6 +1235,8 @@ static int do_grow(struct inode *inode, u64 size)
}
error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT +
+ (unstuff &&
+ gfs2_is_jdata(ip) ? RES_JDATA : 0) +
(sdp->sd_args.ar_quota == GFS2_QUOTA_OFF ?
0 : RES_QUOTA), 0);
if (error)
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 4d5a5a4cc017..addb0784dd1c 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -168,7 +168,7 @@ void __jbd2_log_wait_for_space(journal_t *journal)
"journal space in %s\n", __func__,
journal->j_devname);
WARN_ON(1);
- jbd2_journal_abort(journal, 0);
+ jbd2_journal_abort(journal, -EIO);
}
write_lock(&journal->j_state_lock);
} else {
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2d964ce45606..a7d12dd6d56e 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -740,7 +740,6 @@ start_journal_io:
submit_bh(WRITE_SYNC, bh);
}
cond_resched();
- stats.run.rs_blocks_logged += bufs;
/* Force a new descriptor to be generated next
time round the loop. */
@@ -798,7 +797,7 @@ start_journal_io:
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
- __jbd2_journal_abort_hard(journal);
+ jbd2_journal_abort(journal, err);
}
blk_finish_plug(&plug);
@@ -827,6 +826,7 @@ start_journal_io:
if (unlikely(!buffer_uptodate(bh)))
err = -EIO;
jbd2_unfile_log_bh(bh);
+ stats.run.rs_blocks_logged++;
/*
* The list contains temporary buffer heads created by
@@ -872,6 +872,7 @@ start_journal_io:
BUFFER_TRACE(bh, "ph5: control buffer writeout done: unfile");
clear_buffer_jwrite(bh);
jbd2_unfile_log_bh(bh);
+ stats.run.rs_blocks_logged++;
__brelse(bh); /* One for getblk */
/* AKPM: bforget here */
}
@@ -889,10 +890,11 @@ start_journal_io:
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
- __jbd2_journal_abort_hard(journal);
+ jbd2_journal_abort(journal, err);
}
if (cbh)
err = journal_wait_on_commit_record(journal, cbh);
+ stats.run.rs_blocks_logged++;
if (jbd2_has_feature_async_commit(journal) &&
journal->j_flags & JBD2_BARRIER) {
blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL);
@@ -985,29 +987,33 @@ restart_loop:
* it. */
/*
- * A buffer which has been freed while still being journaled by
- * a previous transaction.
- */
- if (buffer_freed(bh)) {
+ * A buffer which has been freed while still being journaled
+ * by a previous transaction, refile the buffer to BJ_Forget of
+ * the running transaction. If the just committed transaction
+ * contains "add to orphan" operation, we can completely
+ * invalidate the buffer now. We are rather through in that
+ * since the buffer may be still accessible when blocksize <
+ * pagesize and it is attached to the last partial page.
+ */
+ if (buffer_freed(bh) && !jh->b_next_transaction) {
+ struct address_space *mapping;
+
+ clear_buffer_freed(bh);
+ clear_buffer_jbddirty(bh);
+
/*
- * If the running transaction is the one containing
- * "add to orphan" operation (b_next_transaction !=
- * NULL), we have to wait for that transaction to
- * commit before we can really get rid of the buffer.
- * So just clear b_modified to not confuse transaction
- * credit accounting and refile the buffer to
- * BJ_Forget of the running transaction. If the just
- * committed transaction contains "add to orphan"
- * operation, we can completely invalidate the buffer
- * now. We are rather through in that since the
- * buffer may be still accessible when blocksize <
- * pagesize and it is attached to the last partial
- * page.
+ * Block device buffers need to stay mapped all the
+ * time, so it is enough to clear buffer_jbddirty and
+ * buffer_freed bits. For the file mapping buffers (i.e.
+ * journalled data) we need to unmap buffer and clear
+ * more bits. We also need to be careful about the check
+ * because the data page mapping can get cleared under
+ * out hands, which alse need not to clear more bits
+ * because the page and buffers will be freed and can
+ * never be reused once we are done with them.
*/
- jh->b_modified = 0;
- if (!jh->b_next_transaction) {
- clear_buffer_freed(bh);
- clear_buffer_jbddirty(bh);
+ mapping = READ_ONCE(bh->b_page->mapping);
+ if (mapping && !sb_is_blkdev_sb(mapping->host->i_sb)) {
clear_buffer_mapped(bh);
clear_buffer_new(bh);
clear_buffer_req(bh);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 9398d1b70545..d62435897d0d 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1656,6 +1656,11 @@ int jbd2_journal_load(journal_t *journal)
journal->j_devname);
return -EFSCORRUPTED;
}
+ /*
+ * clear JBD2_ABORT flag initialized in journal_init_common
+ * here to update log tail information with the newest seq.
+ */
+ journal->j_flags &= ~JBD2_ABORT;
/* OK, we've finished with the dynamic journal bits:
* reinitialise the dynamic contents of the superblock in memory
@@ -1663,7 +1668,6 @@ int jbd2_journal_load(journal_t *journal)
if (journal_reset(journal))
goto recovery_error;
- journal->j_flags &= ~JBD2_ABORT;
journal->j_flags |= JBD2_LOADED;
return 0;
@@ -2082,12 +2086,10 @@ static void __journal_abort_soft (journal_t *journal, int errno)
__jbd2_journal_abort_hard(journal);
- if (errno) {
- jbd2_journal_update_sb_errno(journal);
- write_lock(&journal->j_state_lock);
- journal->j_flags |= JBD2_REC_ERR;
- write_unlock(&journal->j_state_lock);
- }
+ jbd2_journal_update_sb_errno(journal);
+ write_lock(&journal->j_state_lock);
+ journal->j_flags |= JBD2_REC_ERR;
+ write_unlock(&journal->j_state_lock);
}
/**
@@ -2129,11 +2131,6 @@ static void __journal_abort_soft (journal_t *journal, int errno)
* failure to disk. ext3_error, for example, now uses this
* functionality.
*
- * Errors which originate from within the journaling layer will NOT
- * supply an errno; a null errno implies that absolutely no further
- * writes are done to the journal (unless there are any already in
- * progress).
- *
*/
void jbd2_journal_abort(journal_t *journal, int errno)
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index c34433432d47..6457023d8fac 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2223,14 +2223,16 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
return -EBUSY;
}
/*
- * OK, buffer won't be reachable after truncate. We just set
- * j_next_transaction to the running transaction (if there is
- * one) and mark buffer as freed so that commit code knows it
- * should clear dirty bits when it is done with the buffer.
+ * OK, buffer won't be reachable after truncate. We just clear
+ * b_modified to not confuse transaction credit accounting, and
+ * set j_next_transaction to the running transaction (if there
+ * is one) and mark buffer as freed so that commit code knows
+ * it should clear dirty bits when it is done with the buffer.
*/
set_buffer_freed(bh);
if (journal->j_running_transaction && buffer_jbddirty(bh))
jh->b_next_transaction = journal->j_running_transaction;
+ jh->b_modified = 0;
jbd2_journal_put_journal_head(jh);
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index d595856453b2..de6351c1c8db 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -1928,8 +1928,7 @@ static void xtLog(struct jfs_log * log, struct tblock * tblk, struct lrd * lrd,
* header ?
*/
if (tlck->type & tlckTRUNCATE) {
- /* This odd declaration suppresses a bogus gcc warning */
- pxd_t pxd = pxd; /* truncated extent of xad */
+ pxd_t pxd; /* truncated extent of xad */
int twm;
/*
diff --git a/fs/locks.c b/fs/locks.c
index b515e65f1376..2c8e1e429cf7 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2599,7 +2599,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
}
if (inode) {
/* userspace relies on this representation of dev_t */
- seq_printf(f, "%d %02x:%02x:%ld ", fl_pid,
+ seq_printf(f, "%d %02x:%02x:%lu ", fl_pid,
MAJOR(inode->i_sb->s_dev),
MINOR(inode->i_sb->s_dev), inode->i_ino);
} else {
diff --git a/fs/namei.c b/fs/namei.c
index 8c4706e99762..69c053fd62a6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1087,7 +1087,8 @@ static int may_linkat(struct path *link)
* may_create_in_sticky - Check whether an O_CREAT open in a sticky directory
* should be allowed, or not, on files that already
* exist.
- * @dir: the sticky parent directory
+ * @dir_mode: mode bits of directory
+ * @dir_uid: owner of directory
* @inode: the inode of the file to open
*
* Block an O_CREAT open of a FIFO (or a regular file) when:
@@ -1103,18 +1104,18 @@ static int may_linkat(struct path *link)
*
* Returns 0 if the open is allowed, -ve on error.
*/
-static int may_create_in_sticky(struct dentry * const dir,
+static int may_create_in_sticky(umode_t dir_mode, kuid_t dir_uid,
struct inode * const inode)
{
if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) ||
(!sysctl_protected_regular && S_ISREG(inode->i_mode)) ||
- likely(!(dir->d_inode->i_mode & S_ISVTX)) ||
- uid_eq(inode->i_uid, dir->d_inode->i_uid) ||
+ likely(!(dir_mode & S_ISVTX)) ||
+ uid_eq(inode->i_uid, dir_uid) ||
uid_eq(current_fsuid(), inode->i_uid))
return 0;
- if (likely(dir->d_inode->i_mode & 0002) ||
- (dir->d_inode->i_mode & 0020 &&
+ if (likely(dir_mode & 0002) ||
+ (dir_mode & 0020 &&
((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) ||
(sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) {
return -EACCES;
@@ -3181,6 +3182,8 @@ static int do_last(struct nameidata *nd,
int *opened)
{
struct dentry *dir = nd->path.dentry;
+ kuid_t dir_uid = nd->inode->i_uid;
+ umode_t dir_mode = nd->inode->i_mode;
int open_flag = op->open_flag;
bool will_truncate = (open_flag & O_TRUNC) != 0;
bool got_write = false;
@@ -3333,7 +3336,7 @@ finish_open:
error = -EISDIR;
if (d_is_dir(nd->path.dentry))
goto out;
- error = may_create_in_sticky(dir,
+ error = may_create_in_sticky(dir_mode, dir_uid,
d_backing_inode(nd->path.dentry));
if (unlikely(error))
goto out;
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index b1daeafbea92..c3428767332c 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -89,7 +89,7 @@ config NFS_V4
config NFS_SWAP
bool "Provide swap over NFS support"
default n
- depends on NFS_FS
+ depends on NFS_FS && SWAP
select SUNRPC_SWAP
help
This option enables swapon to work on files located on NFS mounts.
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 807eb6ef4f91..6f4f68967c31 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -368,7 +368,7 @@ static bool referring_call_exists(struct nfs_client *clp,
uint32_t nrclists,
struct referring_call_list *rclists)
{
- bool status = 0;
+ bool status = false;
int i, j;
struct nfs4_session *session;
struct nfs4_slot_table *tbl;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c690a1c0c4e5..2ac3d2527ad2 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -169,6 +169,17 @@ typedef struct {
unsigned int eof:1;
} nfs_readdir_descriptor_t;
+static
+void nfs_readdir_init_array(struct page *page)
+{
+ struct nfs_cache_array *array;
+
+ array = kmap_atomic(page);
+ memset(array, 0, sizeof(struct nfs_cache_array));
+ array->eof_index = -1;
+ kunmap_atomic(array);
+}
+
/*
* The caller is responsible for calling nfs_readdir_release_array(page)
*/
@@ -202,6 +213,7 @@ void nfs_readdir_clear_array(struct page *page)
array = kmap_atomic(page);
for (i = 0; i < array->size; i++)
kfree(array->array[i].string.name);
+ array->size = 0;
kunmap_atomic(array);
}
@@ -277,7 +289,7 @@ int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descri
desc->cache_entry_index = index;
return 0;
out_eof:
- desc->eof = 1;
+ desc->eof = true;
return -EBADCOOKIE;
}
@@ -331,7 +343,7 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
if (array->eof_index >= 0) {
status = -EBADCOOKIE;
if (*desc->dir_cookie == array->last_cookie)
- desc->eof = 1;
+ desc->eof = true;
}
out:
return status;
@@ -622,6 +634,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
int status = -ENOMEM;
unsigned int array_size = ARRAY_SIZE(pages);
+ nfs_readdir_init_array(page);
+
entry.prev_cookie = 0;
entry.cookie = desc->last_cookie;
entry.eof = 0;
@@ -642,8 +656,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
status = PTR_ERR(array);
goto out_label_free;
}
- memset(array, 0, sizeof(struct nfs_cache_array));
- array->eof_index = -1;
+
+ array = kmap(page);
status = nfs_readdir_alloc_pages(pages, array_size);
if (status < 0)
@@ -698,6 +712,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
unlock_page(page);
return 0;
error:
+ nfs_readdir_clear_array(page);
unlock_page(page);
return ret;
}
@@ -705,8 +720,6 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
static
void cache_page_release(nfs_readdir_descriptor_t *desc)
{
- if (!desc->page->mapping)
- nfs_readdir_clear_array(desc->page);
page_cache_release(desc->page);
desc->page = NULL;
}
@@ -720,19 +733,28 @@ struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
/*
* Returns 0 if desc->dir_cookie was found on page desc->page_index
+ * and locks the page to prevent removal from the page cache.
*/
static
-int find_cache_page(nfs_readdir_descriptor_t *desc)
+int find_and_lock_cache_page(nfs_readdir_descriptor_t *desc)
{
int res;
desc->page = get_cache_page(desc);
if (IS_ERR(desc->page))
return PTR_ERR(desc->page);
-
- res = nfs_readdir_search_array(desc);
+ res = lock_page_killable(desc->page);
if (res != 0)
- cache_page_release(desc);
+ goto error;
+ res = -EAGAIN;
+ if (desc->page->mapping != NULL) {
+ res = nfs_readdir_search_array(desc);
+ if (res == 0)
+ return 0;
+ }
+ unlock_page(desc->page);
+error:
+ cache_page_release(desc);
return res;
}
@@ -747,7 +769,7 @@ int readdir_search_pagecache(nfs_readdir_descriptor_t *desc)
desc->last_cookie = 0;
}
do {
- res = find_cache_page(desc);
+ res = find_and_lock_cache_page(desc);
} while (res == -EAGAIN);
return res;
}
@@ -776,7 +798,7 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
ent = &array->array[i];
if (!dir_emit(desc->ctx, ent->string.name, ent->string.len,
nfs_compat_user_ino64(ent->ino), ent->d_type)) {
- desc->eof = 1;
+ desc->eof = true;
break;
}
desc->ctx->pos++;
@@ -788,11 +810,10 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
ctx->duped = 1;
}
if (array->eof_index >= 0)
- desc->eof = 1;
+ desc->eof = true;
nfs_readdir_release_array(desc->page);
out:
- cache_page_release(desc);
dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
(unsigned long long)*desc->dir_cookie, res);
return res;
@@ -838,13 +859,13 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc)
status = nfs_do_filldir(desc);
+ out_release:
+ nfs_readdir_clear_array(desc->page);
+ cache_page_release(desc);
out:
dfprintk(DIRCACHE, "NFS: %s: returns %d\n",
__func__, status);
return status;
- out_release:
- cache_page_release(desc);
- goto out;
}
/* The file offset position represents the dirent entry number. A
@@ -890,7 +911,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
if (res == -EBADCOOKIE) {
res = 0;
/* This means either end of directory */
- if (*desc->dir_cookie && desc->eof == 0) {
+ if (*desc->dir_cookie && !desc->eof) {
/* Or that the server has 'lost' a cookie */
res = uncached_readdir(desc);
if (res == 0)
@@ -910,6 +931,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
break;
res = nfs_do_filldir(desc);
+ unlock_page(desc->page);
+ cache_page_release(desc);
if (res < 0)
break;
} while (!desc->eof);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index dac20f31f01f..92895f41d9a0 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -751,7 +751,7 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
spin_lock(&nn->nfs_client_lock);
list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
- if (nfs4_cb_match_client(addr, clp, minorversion) == false)
+ if (!nfs4_cb_match_client(addr, clp, minorversion))
continue;
if (!nfs4_has_session(clp))
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index dced329a8584..47a7751146cf 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1901,7 +1901,7 @@ static int nfs_parse_devname(const char *dev_name,
/* kill possible hostname list: not supported */
comma = strchr(dev_name, ',');
if (comma != NULL && comma < end)
- *comma = 0;
+ len = comma - dev_name;
}
if (len > maxnamlen)
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index e3d47091b191..2cb2e61cdbf6 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -655,7 +655,7 @@ struct cld_net {
struct cld_upcall {
struct list_head cu_list;
struct cld_net *cu_net;
- struct task_struct *cu_task;
+ struct completion cu_done;
struct cld_msg cu_msg;
};
@@ -664,23 +664,18 @@ __cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
{
int ret;
struct rpc_pipe_msg msg;
+ struct cld_upcall *cup = container_of(cmsg, struct cld_upcall, cu_msg);
memset(&msg, 0, sizeof(msg));
msg.data = cmsg;
msg.len = sizeof(*cmsg);
- /*
- * Set task state before we queue the upcall. That prevents
- * wake_up_process in the downcall from racing with schedule.
- */
- set_current_state(TASK_UNINTERRUPTIBLE);
ret = rpc_queue_upcall(pipe, &msg);
if (ret < 0) {
- set_current_state(TASK_RUNNING);
goto out;
}
- schedule();
+ wait_for_completion(&cup->cu_done);
if (msg.errno < 0)
ret = msg.errno;
@@ -747,7 +742,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
if (copy_from_user(&cup->cu_msg, src, mlen) != 0)
return -EFAULT;
- wake_up_process(cup->cu_task);
+ complete(&cup->cu_done);
return mlen;
}
@@ -762,7 +757,7 @@ cld_pipe_destroy_msg(struct rpc_pipe_msg *msg)
if (msg->errno >= 0)
return;
- wake_up_process(cup->cu_task);
+ complete(&cup->cu_done);
}
static const struct rpc_pipe_ops cld_upcall_ops = {
@@ -893,7 +888,7 @@ restart_search:
goto restart_search;
}
}
- new->cu_task = current;
+ init_completion(&new->cu_done);
new->cu_msg.cm_vers = CLD_UPCALL_VERSION;
put_unaligned(cn->cn_xid++, &new->cu_msg.cm_xid);
new->cu_net = cn;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 17138a97f306..7745d0a9029c 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -387,10 +387,23 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
bool get_write_count;
bool size_change = (iap->ia_valid & ATTR_SIZE);
- if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
+ if (iap->ia_valid & ATTR_SIZE) {
accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
- if (iap->ia_valid & ATTR_SIZE)
ftype = S_IFREG;
+ }
+
+ /*
+ * If utimes(2) and friends are called with times not NULL, we should
+ * not set NFSD_MAY_WRITE bit. Otherwise fh_verify->nfsd_permission
+ * will return EACCESS, when the caller's effective UID does not match
+ * the owner of the file, and the caller is not privileged. In this
+ * situation, we should return EPERM(notify_change will return this).
+ */
+ if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME)) {
+ accmode |= NFSD_MAY_OWNER_OVERRIDE;
+ if (!(iap->ia_valid & (ATTR_ATIME_SET | ATTR_MTIME_SET)))
+ accmode |= NFSD_MAY_WRITE;
+ }
/* Callers that do fh_verify should do the fh_want_write: */
get_write_count = !fhp->fh_dentry;
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 1e0d8da0d3cd..80b92120c812 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -338,8 +338,8 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh)
down_read(&OCFS2_I(inode)->ip_xattr_sem);
acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh);
up_read(&OCFS2_I(inode)->ip_xattr_sem);
- if (IS_ERR(acl) || !acl)
- return PTR_ERR(acl);
+ if (IS_ERR_OR_NULL(acl))
+ return PTR_ERR_OR_ZERO(acl);
ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
if (ret)
return ret;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 722eb5bc9b8f..bbf1634ff427 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1017,7 +1017,8 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
mlog_errno(status);
}
- if (status == 0) {
+ /* Shutdown the kernel journal system */
+ if (!jbd2_journal_destroy(journal->j_journal) && !status) {
/*
* Do not toggle if flush was unsuccessful otherwise
* will leave dirty metadata in a "clean" journal
@@ -1026,9 +1027,6 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
if (status < 0)
mlog_errno(status);
}
-
- /* Shutdown the kernel journal system */
- jbd2_journal_destroy(journal->j_journal);
journal->j_journal = NULL;
OCFS2_I(inode)->ip_open_count--;
@@ -1082,6 +1080,14 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
ocfs2_clear_journal_error(osb->sb, journal->j_journal, osb->slot_num);
+ if (replayed) {
+ jbd2_journal_lock_updates(journal->j_journal);
+ status = jbd2_journal_flush(journal->j_journal);
+ jbd2_journal_unlock_updates(journal->j_journal);
+ if (status < 0)
+ mlog_errno(status);
+ }
+
status = ocfs2_journal_toggle_dirty(osb, 1, replayed);
if (status < 0) {
mlog_errno(status);
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index f4cd3c3e9fb7..0a4d2cbf512f 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -637,9 +637,11 @@ static inline void ocfs2_update_inode_fsync_trans(handle_t *handle,
{
struct ocfs2_inode_info *oi = OCFS2_I(inode);
- oi->i_sync_tid = handle->h_transaction->t_tid;
- if (datasync)
- oi->i_datasync_tid = handle->h_transaction->t_tid;
+ if (!is_handle_aborted(handle)) {
+ oi->i_sync_tid = handle->h_transaction->t_tid;
+ if (datasync)
+ oi->i_datasync_tid = handle->h_transaction->t_tid;
+ }
}
#endif /* OCFS2_JOURNAL_H */
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index c93d67220887..3e5cfcfc8133 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -714,7 +714,7 @@ static int ocfs2_release_dquot(struct dquot *dquot)
mutex_lock(&dquot->dq_lock);
/* Check whether we are not racing with some other dqget() */
- if (atomic_read(&dquot->dq_count) > 1)
+ if (dquot_is_busy(dquot))
goto out;
/* Running from downconvert thread? Postpone quota processing to wq */
if (current == osb->dc_task) {
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 060482e349ef..013d27dc6f58 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -9,7 +9,6 @@
#include <linux/fs.h>
#include <linux/slab.h>
-#include <linux/cred.h>
#include <linux/xattr.h>
#include "overlayfs.h"
@@ -92,7 +91,6 @@ int ovl_permission(struct inode *inode, int mask)
struct ovl_entry *oe;
struct dentry *alias = NULL;
struct inode *realinode;
- const struct cred *old_cred;
struct dentry *realdentry;
bool is_upper;
int err;
@@ -145,18 +143,7 @@ int ovl_permission(struct inode *inode, int mask)
goto out_dput;
}
- /*
- * Check overlay inode with the creds of task and underlying inode
- * with creds of mounter
- */
- err = generic_permission(inode, mask);
- if (err)
- goto out_dput;
-
- old_cred = ovl_override_creds(inode->i_sb);
err = __inode_permission(realinode, mask);
- revert_creds(old_cred);
-
out_dput:
dput(alias);
return err;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 015cdc615dfb..d4b1c2361adf 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -425,9 +425,21 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
- if (permitted) {
- eip = KSTK_EIP(task);
- esp = KSTK_ESP(task);
+ /*
+ * esp and eip are intentionally zeroed out. There is no
+ * non-racy way to read them without freezing the task.
+ * Programs that need reliable values can use ptrace(2).
+ *
+ * The only exception is if the task is core dumping because
+ * a program is not able to use ptrace(2) in that case. It is
+ * safe because the task has stopped executing permanently.
+ */
+ if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) {
+ if (try_get_task_stack(task)) {
+ eip = KSTK_EIP(task);
+ esp = KSTK_ESP(task);
+ put_task_stack(task);
+ }
}
}
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 5e5c443591ea..83720460c5bc 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -29,10 +29,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
unsigned long committed;
long cached;
long available;
- unsigned long pagecache;
- unsigned long wmark_low = 0;
unsigned long pages[NR_LRU_LISTS];
- struct zone *zone;
int lru;
/*
@@ -51,40 +48,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
pages[lru] = global_page_state(NR_LRU_BASE + lru);
- for_each_zone(zone)
- wmark_low += zone->watermark[WMARK_LOW];
-
- /*
- * Estimate the amount of memory available for userspace allocations,
- * without causing swapping.
- */
- available = i.freeram - totalreserve_pages;
-
- /*
- * Not all the page cache can be freed, otherwise the system will
- * start swapping. Assume at least half of the page cache, or the
- * low watermark worth of cache, needs to stay.
- */
- pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
- pagecache -= min(pagecache / 2, wmark_low);
- available += pagecache;
-
- /*
- * Part of the reclaimable slab consists of items that are in use,
- * and cannot be freed. Cap this estimate at the low watermark.
- */
- available += global_page_state(NR_SLAB_RECLAIMABLE) -
- min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
-
- /*
- * Part of the kernel memory, which can be released under memory
- * pressure.
- */
- available += global_page_state(NR_INDIRECTLY_RECLAIMABLE_BYTES) >>
- PAGE_SHIFT;
-
- if (available < 0)
- available = 0;
+ available = si_mem_available();
/*
* Tagged format, for easy grepping and expansion.
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 1e6a9597aff3..2a004480fc4f 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -321,6 +321,17 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
prz = cxt->przs[cxt->dump_write_cnt];
+ /*
+ * Since this is a new crash dump, we need to reset the buffer in
+ * case it still has an old dump present. Without this, the new dump
+ * will get appended, which would seriously confuse anything trying
+ * to check dump file contents. Specifically, ramoops_read_kmsg_hdr()
+ * expects to find a dump header in the beginning of buffer data, so
+ * we must to reset the buffer values, in order to ensure that the
+ * header will be written to the beginning of the buffer.
+ */
+ persistent_ram_zap(prz);
+
hlen = ramoops_write_kmsg_hdr(prz, compressed);
if (size + hlen > prz->buffer_size)
size = prz->buffer_size - hlen;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 1cb1d02c5937..b7d5e254792c 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -472,7 +472,7 @@ int dquot_release(struct dquot *dquot)
mutex_lock(&dquot->dq_lock);
/* Check whether we are not racing with some other dqget() */
- if (atomic_read(&dquot->dq_count) > 1)
+ if (dquot_is_busy(dquot))
goto out_dqlock;
mutex_lock(&dqopt->dqio_mutex);
if (dqopt->ops[dquot->dq_id.type]->release_dqblk) {
@@ -604,7 +604,7 @@ EXPORT_SYMBOL(dquot_scan_active);
/* Write all dquot structures to quota files */
int dquot_writeback_dquots(struct super_block *sb, int type)
{
- struct list_head *dirty;
+ struct list_head dirty;
struct dquot *dquot;
struct quota_info *dqopt = sb_dqopt(sb);
int cnt;
@@ -617,9 +617,10 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
if (!sb_has_quota_active(sb, cnt))
continue;
spin_lock(&dq_list_lock);
- dirty = &dqopt->info[cnt].dqi_dirty_list;
- while (!list_empty(dirty)) {
- dquot = list_first_entry(dirty, struct dquot,
+ /* Move list away to avoid livelock. */
+ list_replace_init(&dqopt->info[cnt].dqi_dirty_list, &dirty);
+ while (!list_empty(&dirty)) {
+ dquot = list_first_entry(&dirty, struct dquot,
dq_dirty);
/* Dirty and inactive can be only bad dquot... */
if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
@@ -2782,68 +2783,73 @@ EXPORT_SYMBOL(dquot_quotactl_sysfile_ops);
static int do_proc_dqstats(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- unsigned int type = (int *)table->data - dqstats.stat;
+ unsigned int type = (unsigned long *)table->data - dqstats.stat;
+ s64 value = percpu_counter_sum(&dqstats.counter[type]);
+
+ /* Filter negative values for non-monotonic counters */
+ if (value < 0 && (type == DQST_ALLOC_DQUOTS ||
+ type == DQST_FREE_DQUOTS))
+ value = 0;
/* Update global table */
- dqstats.stat[type] =
- percpu_counter_sum_positive(&dqstats.counter[type]);
- return proc_dointvec(table, write, buffer, lenp, ppos);
+ dqstats.stat[type] = value;
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
static struct ctl_table fs_dqstats_table[] = {
{
.procname = "lookups",
.data = &dqstats.stat[DQST_LOOKUPS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "drops",
.data = &dqstats.stat[DQST_DROPS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "reads",
.data = &dqstats.stat[DQST_READS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "writes",
.data = &dqstats.stat[DQST_WRITES],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "cache_hits",
.data = &dqstats.stat[DQST_CACHE_HITS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "allocated_dquots",
.data = &dqstats.stat[DQST_ALLOC_DQUOTS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "free_dquots",
.data = &dqstats.stat[DQST_FREE_DQUOTS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
{
.procname = "syncs",
.data = &dqstats.stat[DQST_SYNCS],
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0444,
.proc_handler = do_proc_dqstats,
},
diff --git a/fs/readdir.c b/fs/readdir.c
index ced679179cac..3494d7a8ff65 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -51,6 +51,40 @@ out:
EXPORT_SYMBOL(iterate_dir);
/*
+ * POSIX says that a dirent name cannot contain NULL or a '/'.
+ *
+ * It's not 100% clear what we should really do in this case.
+ * The filesystem is clearly corrupted, but returning a hard
+ * error means that you now don't see any of the other names
+ * either, so that isn't a perfect alternative.
+ *
+ * And if you return an error, what error do you use? Several
+ * filesystems seem to have decided on EUCLEAN being the error
+ * code for EFSCORRUPTED, and that may be the error to use. Or
+ * just EIO, which is perhaps more obvious to users.
+ *
+ * In order to see the other file names in the directory, the
+ * caller might want to make this a "soft" error: skip the
+ * entry, and return the error at the end instead.
+ *
+ * Note that this should likely do a "memchr(name, 0, len)"
+ * check too, since that would be filesystem corruption as
+ * well. However, that case can't actually confuse user space,
+ * which has to do a strlen() on the name anyway to find the
+ * filename length, and the above "soft error" worry means
+ * that it's probably better left alone until we have that
+ * issue clarified.
+ */
+static int verify_dirent_name(const char *name, int len)
+{
+ if (!len)
+ return -EIO;
+ if (memchr(name, '/', len))
+ return -EIO;
+ return 0;
+}
+
+/*
* Traditional linux readdir() handling..
*
* "count=1" is a special case, meaning that the buffer is one
@@ -159,6 +193,9 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen,
int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2,
sizeof(long));
+ buf->error = verify_dirent_name(name, namlen);
+ if (unlikely(buf->error))
+ return buf->error;
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
return -EINVAL;
@@ -243,6 +280,9 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen,
int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
sizeof(u64));
+ buf->error = verify_dirent_name(name, namlen);
+ if (unlikely(buf->error))
+ return buf->error;
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
return -EINVAL;
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 24cbe013240f..e3a4cbad9620 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -2249,7 +2249,8 @@ error_out:
/* also releases the path */
unfix_nodes(&s_ins_balance);
#ifdef REISERQUOTA_DEBUG
- reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
+ if (inode)
+ reiserfs_debug(th->t_super, REISERFS_DEBUG_CODE,
"reiserquota insert_item(): freeing %u id=%u type=%c",
quota_bytes, inode->i_uid, head2type(ih));
#endif
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index ee095246da4e..f9796fd51531 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -599,6 +599,7 @@ static void reiserfs_put_super(struct super_block *s)
reiserfs_write_unlock(s);
mutex_destroy(&REISERFS_SB(s)->lock);
destroy_workqueue(REISERFS_SB(s)->commit_wq);
+ kfree(REISERFS_SB(s)->s_jdev);
kfree(s->s_fs_info);
s->s_fs_info = NULL;
}
@@ -1920,7 +1921,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
if (!sbi->s_jdev) {
SWARN(silent, s, "", "Cannot allocate memory for "
"journal device name");
- goto error;
+ goto error_unlocked;
}
}
#ifdef CONFIG_QUOTA
@@ -2208,6 +2209,7 @@ error_unlocked:
kfree(qf_names[j]);
}
#endif
+ kfree(sbi->s_jdev);
kfree(sbi);
s->s_fs_info = NULL;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index b895af7d8d80..e6d0a7df341d 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -782,8 +782,9 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
if (page_offset > end_index)
break;
- page = find_or_create_page(mapping, page_offset,
- GFP_NOFS | __GFP_COLD);
+ page = pagecache_get_page(mapping, page_offset,
+ FGP_LOCK|FGP_ACCESSED|FGP_CREAT|FGP_NOWAIT,
+ GFP_NOFS | __GFP_COLD);
if (!page)
break;
if (!PageUptodate(page))
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 1a05d8ae327d..e7372cef5ac3 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -346,6 +346,7 @@ xfs_compat_attrlist_by_handle(
{
int error;
attrlist_cursor_kern_t *cursor;
+ compat_xfs_fsop_attrlist_handlereq_t __user *p = arg;
compat_xfs_fsop_attrlist_handlereq_t al_hreq;
struct dentry *dentry;
char *kbuf;
@@ -380,6 +381,11 @@ xfs_compat_attrlist_by_handle(
if (error)
goto out_kfree;
+ if (copy_to_user(&p->pos, cursor, sizeof(attrlist_cursor_kern_t))) {
+ error = -EFAULT;
+ goto out_kfree;
+ }
+
if (copy_to_user(compat_ptr(al_hreq.buffer), kbuf, al_hreq.buflen))
error = -EFAULT;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 73b725f965eb..065aa4752607 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1503,6 +1503,8 @@ out_free_iclog:
if (iclog->ic_bp)
xfs_buf_free(iclog->ic_bp);
kmem_free(iclog);
+ if (prev_iclog == log->l_iclog)
+ break;
}
spinlock_destroy(&log->l_icloglock);
xfs_buf_free(log->l_xbuf);
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 7795e0d01382..4b94db85b2a0 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -214,6 +214,9 @@ xfs_fs_rm_xquota(
if (XFS_IS_QUOTA_ON(mp))
return -EINVAL;
+ if (uflags & ~(FS_USER_QUOTA | FS_GROUP_QUOTA | FS_PROJ_QUOTA))
+ return -EINVAL;
+
if (uflags & FS_USER_QUOTA)
flags |= XFS_DQ_USER;
if (uflags & FS_GROUP_QUOTA)
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index ab1bac6a3a1c..919b6544b61a 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1225,13 +1225,11 @@ xfs_rtmount_inodes(
xfs_sb_t *sbp;
sbp = &mp->m_sb;
- if (sbp->sb_rbmino == NULLFSINO)
- return 0;
error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip);
if (error)
return error;
ASSERT(mp->m_rbmip != NULL);
- ASSERT(sbp->sb_rsumino != NULLFSINO);
+
error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
if (error) {
IRELE(mp->m_rbmip);