summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/backref.c14
-rw-r--r--fs/btrfs/backref.h3
-rw-r--r--fs/btrfs/ctree.c21
-rw-r--r--fs/btrfs/ctree.h3
-rw-r--r--fs/btrfs/delayed-inode.c2
-rw-r--r--fs/btrfs/delayed-inode.h2
-rw-r--r--fs/btrfs/relocation.c7
-rw-r--r--fs/btrfs/super.c4
-rw-r--r--fs/btrfs/volumes.c2
-rw-r--r--fs/ceph/crypto.c2
-rw-r--r--fs/ceph/file.c2
-rw-r--r--fs/ceph/inode.c4
-rw-r--r--fs/fs_context.c34
-rw-r--r--fs/iomap/buffered-io.c10
-rw-r--r--fs/namei.c9
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c17
-rw-r--r--fs/nfs/nfs42proc.c3
-rw-r--r--fs/nfs/nfs4proc.c2
-rw-r--r--fs/nfs/pnfs.c33
-rw-r--r--fs/nfs/write.c4
-rw-r--r--fs/nfsd/vfs.c12
-rw-r--r--fs/notify/fanotify/fanotify_user.c25
-rw-r--r--fs/ntfs3/attrib.c12
-rw-r--r--fs/ntfs3/attrlist.c15
-rw-r--r--fs/ntfs3/bitmap.c4
-rw-r--r--fs/ntfs3/dir.c6
-rw-r--r--fs/ntfs3/file.c4
-rw-r--r--fs/ntfs3/frecord.c8
-rw-r--r--fs/ntfs3/fslog.c6
-rw-r--r--fs/ntfs3/fsntfs.c19
-rw-r--r--fs/ntfs3/index.c3
-rw-r--r--fs/ntfs3/inode.c5
-rw-r--r--fs/ntfs3/namei.c6
-rw-r--r--fs/ntfs3/ntfs.h2
-rw-r--r--fs/ntfs3/ntfs_fs.h4
-rw-r--r--fs/ntfs3/record.c74
-rw-r--r--fs/ntfs3/super.c104
-rw-r--r--fs/ntfs3/xattr.c7
-rw-r--r--fs/overlayfs/params.c119
-rw-r--r--fs/quota/dquot.c66
-rw-r--r--fs/smb/client/cached_dir.c141
-rw-r--r--fs/smb/client/cached_dir.h2
-rw-r--r--fs/smb/server/smb2pdu.c11
-rw-r--r--fs/smb/server/vfs_cache.c7
-rw-r--r--fs/xfs/libxfs/xfs_ag.c6
-rw-r--r--fs/xfs/scrub/xfile.c1
-rw-r--r--fs/xfs/xfs_extent_busy.c3
-rw-r--r--fs/xfs/xfs_iops.c5
-rw-r--r--fs/xfs/xfs_notify_failure.c6
49 files changed, 528 insertions, 333 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b7d54efb4728..a4a809efc92f 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -3196,12 +3196,14 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache,
* We still need to do a tree search to find out the parents. This is for
* TREE_BLOCK_REF backref (keyed or inlined).
*
+ * @trans: Transaction handle.
* @ref_key: The same as @ref_key in handle_direct_tree_backref()
* @tree_key: The first key of this tree block.
* @path: A clean (released) path, to avoid allocating path every time
* the function get called.
*/
-static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache,
+static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans,
+ struct btrfs_backref_cache *cache,
struct btrfs_path *path,
struct btrfs_key *ref_key,
struct btrfs_key *tree_key,
@@ -3315,7 +3317,7 @@ static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache,
* If we know the block isn't shared we can avoid
* checking its backrefs.
*/
- if (btrfs_block_can_be_shared(root, eb))
+ if (btrfs_block_can_be_shared(trans, root, eb))
upper->checked = 0;
else
upper->checked = 1;
@@ -3363,11 +3365,13 @@ out:
* links aren't yet bi-directional. Needs to finish such links.
* Use btrfs_backref_finish_upper_links() to finish such linkage.
*
+ * @trans: Transaction handle.
* @path: Released path for indirect tree backref lookup
* @iter: Released backref iter for extent tree search
* @node_key: The first key of the tree block
*/
-int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache,
+int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans,
+ struct btrfs_backref_cache *cache,
struct btrfs_path *path,
struct btrfs_backref_iter *iter,
struct btrfs_key *node_key,
@@ -3467,8 +3471,8 @@ int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache,
* offset means the root objectid. We need to search
* the tree to get its parent bytenr.
*/
- ret = handle_indirect_tree_backref(cache, path, &key, node_key,
- cur);
+ ret = handle_indirect_tree_backref(trans, cache, path,
+ &key, node_key, cur);
if (ret < 0)
goto out;
}
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 1616e3e3f1e4..71d535e03dca 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -540,7 +540,8 @@ static inline void btrfs_backref_panic(struct btrfs_fs_info *fs_info,
bytenr);
}
-int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache,
+int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans,
+ struct btrfs_backref_cache *cache,
struct btrfs_path *path,
struct btrfs_backref_iter *iter,
struct btrfs_key *node_key,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index da519c1b6ad0..617d4827eec2 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -367,7 +367,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
/*
* check if the tree block can be shared by multiple trees
*/
-int btrfs_block_can_be_shared(struct btrfs_root *root,
+int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
struct extent_buffer *buf)
{
/*
@@ -376,11 +377,21 @@ int btrfs_block_can_be_shared(struct btrfs_root *root,
* not allocated by tree relocation, we know the block is not shared.
*/
if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
- buf != root->node && buf != root->commit_root &&
+ buf != root->node &&
(btrfs_header_generation(buf) <=
btrfs_root_last_snapshot(&root->root_item) ||
- btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
- return 1;
+ btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) {
+ if (buf != root->commit_root)
+ return 1;
+ /*
+ * An extent buffer that used to be the commit root may still be
+ * shared because the tree height may have increased and it
+ * became a child of a higher level root. This can happen when
+ * snapshotting a subvolume created in the current transaction.
+ */
+ if (btrfs_header_generation(buf) == trans->transid)
+ return 1;
+ }
return 0;
}
@@ -415,7 +426,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
* are only allowed for blocks use full backrefs.
*/
- if (btrfs_block_can_be_shared(root, buf)) {
+ if (btrfs_block_can_be_shared(trans, root, buf)) {
ret = btrfs_lookup_extent_info(trans, fs_info, buf->start,
btrfs_header_level(buf), 1,
&refs, &flags);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9419f4e37a58..ff40acd63a37 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -540,7 +540,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *buf,
struct extent_buffer **cow_ret, u64 new_root_objectid);
-int btrfs_block_can_be_shared(struct btrfs_root *root,
+int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
struct extent_buffer *buf);
int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct btrfs_path *path, int level, int slot);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index caf0bbd028d1..90aaedce1548 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -313,7 +313,7 @@ static struct btrfs_delayed_item *btrfs_alloc_delayed_item(u16 data_len,
{
struct btrfs_delayed_item *item;
- item = kmalloc(sizeof(*item) + data_len, GFP_NOFS);
+ item = kmalloc(struct_size(item, data, data_len), GFP_NOFS);
if (item) {
item->data_len = data_len;
item->type = type;
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index dc1085b2a397..1da213197f55 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -95,7 +95,7 @@ struct btrfs_delayed_item {
bool logged;
/* The maximum leaf size is 64K, so u16 is more than enough. */
u16 data_len;
- char data[];
+ char data[] __counted_by(data_len);
};
static inline void btrfs_init_delayed_root(
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 9951a0caf5bb..c6d4bb8cbe29 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -466,6 +466,7 @@ static bool handle_useless_nodes(struct reloc_control *rc,
* cached.
*/
static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
+ struct btrfs_trans_handle *trans,
struct reloc_control *rc, struct btrfs_key *node_key,
int level, u64 bytenr)
{
@@ -499,8 +500,8 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
/* Breadth-first search to build backref cache */
do {
- ret = btrfs_backref_add_tree_node(cache, path, iter, node_key,
- cur);
+ ret = btrfs_backref_add_tree_node(trans, cache, path, iter,
+ node_key, cur);
if (ret < 0) {
err = ret;
goto out;
@@ -2803,7 +2804,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
/* Do tree relocation */
rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) {
- node = build_backref_tree(rc, &block->key,
+ node = build_backref_tree(trans, rc, &block->key,
block->level, block->bytenr);
if (IS_ERR(node)) {
err = PTR_ERR(node);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f49e597e197f..1a093ec0f7e3 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -954,10 +954,6 @@ static int btrfs_parse_subvol_options(const char *options, char **subvol_name,
*subvol_objectid = subvolid;
break;
- case Opt_err:
- btrfs_err(NULL, "unrecognized mount option '%s'", p);
- error = -EINVAL;
- goto out;
default:
break;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5a5a8d488a7b..b9ef6f54635c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5109,7 +5109,7 @@ static void init_alloc_chunk_ctl_policy_regular(
ASSERT(space_info);
ctl->max_chunk_size = READ_ONCE(space_info->chunk_size);
- ctl->max_stripe_size = ctl->max_chunk_size;
+ ctl->max_stripe_size = min_t(u64, ctl->max_chunk_size, SZ_1G);
if (ctl->type & BTRFS_BLOCK_GROUP_SYSTEM)
ctl->devs_max = min_t(int, ctl->devs_max, BTRFS_MAX_DEVS_SYS_CHUNK);
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index e1f31b86fd48..5b5112c78462 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -460,7 +460,7 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname,
out:
fscrypt_fname_free_buffer(&_tname);
out_inode:
- if ((dir != fname->dir) && !IS_ERR(dir)) {
+ if (dir != fname->dir) {
if ((dir->i_state & I_NEW))
discard_new_inode(dir);
else
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index b1da02f5dbe3..b5f8038065d7 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2969,7 +2969,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
ret = do_splice_direct(src_file, &src_off, dst_file,
&dst_off, src_objlen, flags);
/* Abort on short copies or on error */
- if (ret < src_objlen) {
+ if (ret < (long)src_objlen) {
dout("Failed partial copy (%zd)\n", ret);
goto out;
}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 800ab7920513..b79100f720b3 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -769,9 +769,7 @@ int ceph_fill_file_size(struct inode *inode, int issued,
ci->i_truncate_seq = truncate_seq;
/* the MDS should have revoked these caps */
- WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL |
- CEPH_CAP_FILE_RD |
- CEPH_CAP_FILE_WR |
+ WARN_ON_ONCE(issued & (CEPH_CAP_FILE_RD |
CEPH_CAP_FILE_LAZYIO));
/*
* If we hold relevant caps, or in the case where we're
diff --git a/fs/fs_context.c b/fs/fs_context.c
index a0ad7a0c4680..98589aae5208 100644
--- a/fs/fs_context.c
+++ b/fs/fs_context.c
@@ -192,17 +192,19 @@ int vfs_parse_fs_string(struct fs_context *fc, const char *key,
EXPORT_SYMBOL(vfs_parse_fs_string);
/**
- * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data
+ * vfs_parse_monolithic_sep - Parse key[=val][,key[=val]]* mount data
* @fc: The superblock configuration to fill in.
* @data: The data to parse
+ * @sep: callback for separating next option
*
- * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be
- * called from the ->monolithic_mount_data() fs_context operation.
+ * Parse a blob of data that's in key[=val][,key[=val]]* form with a custom
+ * option separator callback.
*
* Returns 0 on success or the error returned by the ->parse_option() fs_context
* operation on failure.
*/
-int generic_parse_monolithic(struct fs_context *fc, void *data)
+int vfs_parse_monolithic_sep(struct fs_context *fc, void *data,
+ char *(*sep)(char **))
{
char *options = data, *key;
int ret = 0;
@@ -214,7 +216,7 @@ int generic_parse_monolithic(struct fs_context *fc, void *data)
if (ret)
return ret;
- while ((key = strsep(&options, ",")) != NULL) {
+ while ((key = sep(&options)) != NULL) {
if (*key) {
size_t v_len = 0;
char *value = strchr(key, '=');
@@ -233,6 +235,28 @@ int generic_parse_monolithic(struct fs_context *fc, void *data)
return ret;
}
+EXPORT_SYMBOL(vfs_parse_monolithic_sep);
+
+static char *vfs_parse_comma_sep(char **s)
+{
+ return strsep(s, ",");
+}
+
+/**
+ * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data
+ * @fc: The superblock configuration to fill in.
+ * @data: The data to parse
+ *
+ * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be
+ * called from the ->monolithic_mount_data() fs_context operation.
+ *
+ * Returns 0 on success or the error returned by the ->parse_option() fs_context
+ * operation on failure.
+ */
+int generic_parse_monolithic(struct fs_context *fc, void *data)
+{
+ return vfs_parse_monolithic_sep(fc, data, vfs_parse_comma_sep);
+}
EXPORT_SYMBOL(generic_parse_monolithic);
/**
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 5db54ca29a35..2bc0aa23fde3 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -881,8 +881,10 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
size_t bytes; /* Bytes to write to folio */
size_t copied; /* Bytes copied from user */
+ bytes = iov_iter_count(i);
+retry:
offset = pos & (chunk - 1);
- bytes = min(chunk - offset, iov_iter_count(i));
+ bytes = min(chunk - offset, bytes);
status = balance_dirty_pages_ratelimited_flags(mapping,
bdp_flags);
if (unlikely(status))
@@ -933,10 +935,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
* halfway through, might be a race with munmap,
* might be severe memory pressure.
*/
- if (copied)
- bytes = copied;
if (chunk > PAGE_SIZE)
chunk /= 2;
+ if (copied) {
+ bytes = copied;
+ goto retry;
+ }
} else {
pos += status;
written += status;
diff --git a/fs/namei.c b/fs/namei.c
index 567ee547492b..94565bd7e73f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -188,7 +188,7 @@ getname_flags(const char __user *filename, int flags, int *empty)
}
}
- result->refcnt = 1;
+ atomic_set(&result->refcnt, 1);
/* The empty path is special. */
if (unlikely(!len)) {
if (empty)
@@ -249,7 +249,7 @@ getname_kernel(const char * filename)
memcpy((char *)result->name, filename, len);
result->uptr = NULL;
result->aname = NULL;
- result->refcnt = 1;
+ atomic_set(&result->refcnt, 1);
audit_getname(result);
return result;
@@ -261,9 +261,10 @@ void putname(struct filename *name)
if (IS_ERR(name))
return;
- BUG_ON(name->refcnt <= 0);
+ if (WARN_ON_ONCE(!atomic_read(&name->refcnt)))
+ return;
- if (--name->refcnt > 0)
+ if (!atomic_dec_and_test(&name->refcnt))
return;
if (name->name != name->iname) {
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index a1dc33864906..ef817a0475ff 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -2520,9 +2520,9 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
return i;
}
-static int
-ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
+static int ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
{
+ struct pnfs_layout_hdr *lo;
struct nfs4_flexfile_layout *ff_layout;
const int dev_count = PNFS_LAYOUTSTATS_MAXDEV;
@@ -2533,11 +2533,14 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
return -ENOMEM;
spin_lock(&args->inode->i_lock);
- ff_layout = FF_LAYOUT_FROM_HDR(NFS_I(args->inode)->layout);
- args->num_dev = ff_layout_mirror_prepare_stats(&ff_layout->generic_hdr,
- &args->devinfo[0],
- dev_count,
- NFS4_FF_OP_LAYOUTSTATS);
+ lo = NFS_I(args->inode)->layout;
+ if (lo && pnfs_layout_is_valid(lo)) {
+ ff_layout = FF_LAYOUT_FROM_HDR(lo);
+ args->num_dev = ff_layout_mirror_prepare_stats(
+ &ff_layout->generic_hdr, &args->devinfo[0], dev_count,
+ NFS4_FF_OP_LAYOUTSTATS);
+ } else
+ args->num_dev = 0;
spin_unlock(&args->inode->i_lock);
if (!args->num_dev) {
kfree(args->devinfo);
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 063e00aff87e..28704f924612 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -81,7 +81,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
if (status == 0) {
if (nfs_should_remove_suid(inode)) {
spin_lock(&inode->i_lock);
- nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE);
+ nfs_set_cache_invalid(inode,
+ NFS_INO_REVAL_FORCED | NFS_INO_INVALID_MODE);
spin_unlock(&inode->i_lock);
}
status = nfs_post_op_update_inode_force_wcc(inode,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7016eaadf555..5ee283eb9660 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8870,8 +8870,6 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre
/* Save the EXCHANGE_ID verifier session trunk tests */
memcpy(clp->cl_confirm.data, argp->verifier.data,
sizeof(clp->cl_confirm.data));
- if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS)
- set_bit(NFS_CS_DS, &clp->cl_flags);
out:
trace_nfs4_exchange_id(clp, status);
rpc_put_task(task);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 306cba0b9e69..84343aefbbd6 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -2634,31 +2634,44 @@ pnfs_should_return_unused_layout(struct pnfs_layout_hdr *lo,
return mode == 0;
}
-static int
-pnfs_layout_return_unused_byserver(struct nfs_server *server, void *data)
+static int pnfs_layout_return_unused_byserver(struct nfs_server *server,
+ void *data)
{
const struct pnfs_layout_range *range = data;
+ const struct cred *cred;
struct pnfs_layout_hdr *lo;
struct inode *inode;
+ nfs4_stateid stateid;
+ enum pnfs_iomode iomode;
+
restart:
rcu_read_lock();
list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) {
- if (!pnfs_layout_can_be_returned(lo) ||
+ inode = lo->plh_inode;
+ if (!inode || !pnfs_layout_can_be_returned(lo) ||
test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
continue;
- inode = lo->plh_inode;
spin_lock(&inode->i_lock);
- if (!pnfs_should_return_unused_layout(lo, range)) {
+ if (!lo->plh_inode ||
+ !pnfs_should_return_unused_layout(lo, range)) {
spin_unlock(&inode->i_lock);
continue;
}
+ pnfs_get_layout_hdr(lo);
+ pnfs_set_plh_return_info(lo, range->iomode, 0);
+ if (pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+ range, 0) != 0 ||
+ !pnfs_prepare_layoutreturn(lo, &stateid, &cred, &iomode)) {
+ spin_unlock(&inode->i_lock);
+ rcu_read_unlock();
+ pnfs_put_layout_hdr(lo);
+ cond_resched();
+ goto restart;
+ }
spin_unlock(&inode->i_lock);
- inode = pnfs_grab_inode_layout_hdr(lo);
- if (!inode)
- continue;
rcu_read_unlock();
- pnfs_mark_layout_for_return(inode, range);
- iput(inode);
+ pnfs_send_layoutreturn(lo, &stateid, &cred, iomode, false);
+ pnfs_put_layout_hdr(lo);
cond_resched();
goto restart;
}
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 7720b5e43014..9d82d50ce0b1 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -788,6 +788,8 @@ static void nfs_inode_add_request(struct nfs_page *req)
*/
static void nfs_inode_remove_request(struct nfs_page *req)
{
+ struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req));
+
if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
struct folio *folio = nfs_page_to_folio(req->wb_head);
struct address_space *mapping = folio_file_mapping(folio);
@@ -802,7 +804,7 @@ static void nfs_inode_remove_request(struct nfs_page *req)
}
if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) {
- atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests);
+ atomic_long_dec(&nfsi->nrequests);
nfs_release_request(req);
}
}
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 48260cf68fde..02f5fcaad03f 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1788,6 +1788,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen))
goto out;
+ err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev;
+ if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
+ goto out;
+ if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
+ goto out;
+
retry:
host_err = fh_want_write(ffhp);
if (host_err) {
@@ -1823,12 +1829,6 @@ retry:
if (ndentry == trap)
goto out_dput_new;
- host_err = -EXDEV;
- if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
- goto out_dput_new;
- if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
- goto out_dput_new;
-
if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) &&
nfsd_has_cached_files(ndentry)) {
close_cached = true;
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index f69c451018e3..62fe0b679e58 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -1585,16 +1585,25 @@ static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid)
}
/* Check if filesystem can encode a unique fid */
-static int fanotify_test_fid(struct dentry *dentry)
+static int fanotify_test_fid(struct dentry *dentry, unsigned int flags)
{
+ unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS;
+ const struct export_operations *nop = dentry->d_sb->s_export_op;
+
+ /*
+ * We need to make sure that the filesystem supports encoding of
+ * file handles so user can use name_to_handle_at() to compare fids
+ * reported with events to the file handle of watched objects.
+ */
+ if (!nop)
+ return -EOPNOTSUPP;
+
/*
- * We need to make sure that the file system supports at least
- * encoding a file handle so user can use name_to_handle_at() to
- * compare fid returned with event to the file handle of watched
- * objects. However, even the relaxed AT_HANDLE_FID flag requires
- * at least empty export_operations for ecoding unique file ids.
+ * For sb/mount mark, we also need to make sure that the filesystem
+ * supports decoding file handles, so user has a way to map back the
+ * reported fids to filesystem objects.
*/
- if (!dentry->d_sb->s_export_op)
+ if (mark_type != FAN_MARK_INODE && !nop->fh_to_dentry)
return -EOPNOTSUPP;
return 0;
@@ -1812,7 +1821,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
if (ret)
goto path_put_and_out;
- ret = fanotify_test_fid(path.dentry);
+ ret = fanotify_test_fid(path.dentry, flags);
if (ret)
goto path_put_and_out;
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index a9d82bbb4729..63f70259edc0 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -1106,10 +1106,10 @@ repack:
}
}
- /*
+ /*
* The code below may require additional cluster (to extend attribute list)
- * and / or one MFT record
- * It is too complex to undo operations if -ENOSPC occurs deep inside
+ * and / or one MFT record
+ * It is too complex to undo operations if -ENOSPC occurs deep inside
* in 'ni_insert_nonresident'.
* Return in advance -ENOSPC here if there are no free cluster and no free MFT.
*/
@@ -1736,10 +1736,8 @@ repack:
le_b = NULL;
attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
0, NULL, &mi_b);
- if (!attr_b) {
- err = -ENOENT;
- goto out;
- }
+ if (!attr_b)
+ return -ENOENT;
attr = attr_b;
le = le_b;
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 42631b31adf1..7c01735d1219 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -52,7 +52,8 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr)
if (!attr->non_res) {
lsize = le32_to_cpu(attr->res.data_size);
- le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN);
+ /* attr is resident: lsize < record_size (1K or 4K) */
+ le = kvmalloc(al_aligned(lsize), GFP_KERNEL);
if (!le) {
err = -ENOMEM;
goto out;
@@ -80,7 +81,17 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr)
if (err < 0)
goto out;
- le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN);
+ /* attr is nonresident.
+ * The worst case:
+ * 1T (2^40) extremely fragmented file.
+ * cluster = 4K (2^12) => 2^28 fragments
+ * 2^9 fragments per one record => 2^19 records
+ * 2^5 bytes of ATTR_LIST_ENTRY per one record => 2^24 bytes.
+ *
+ * the result is 16M bytes per attribute list.
+ * Use kvmalloc to allocate in range [several Kbytes - dozen Mbytes]
+ */
+ le = kvmalloc(al_aligned(lsize), GFP_KERNEL);
if (!le) {
err = -ENOMEM;
goto out;
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 107e808e06ea..63f14a0232f6 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -125,6 +125,7 @@ void wnd_close(struct wnd_bitmap *wnd)
struct rb_node *node, *next;
kfree(wnd->free_bits);
+ wnd->free_bits = NULL;
run_close(&wnd->run);
node = rb_first(&wnd->start_tree);
@@ -659,7 +660,8 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits)
wnd->bits_last = wbits;
wnd->free_bits =
- kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN);
+ kvmalloc_array(wnd->nwnd, sizeof(u16), GFP_KERNEL | __GFP_ZERO);
+
if (!wnd->free_bits)
return -ENOMEM;
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 063a6654199b..ec0566b322d5 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -309,7 +309,11 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
return 0;
}
- dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+ /* NTFS: symlinks are "dir + reparse" or "file + reparse" */
+ if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT)
+ dt_type = DT_LNK;
+ else
+ dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
}
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 962f12ce6c0a..1f7a194983c5 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -745,8 +745,8 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
}
static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t len, unsigned int flags)
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
{
struct inode *inode = in->f_mapping->host;
struct ntfs_inode *ni = ntfs_i(inode);
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 2b85cb10f0be..dad976a68985 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -2148,7 +2148,7 @@ out1:
for (i = 0; i < pages_per_frame; i++) {
pg = pages[i];
- if (i == idx)
+ if (i == idx || !pg)
continue;
unlock_page(pg);
put_page(pg);
@@ -3208,6 +3208,12 @@ static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup,
if (!fname || !memcmp(&fname->dup, dup, sizeof(fname->dup)))
continue;
+ /* Check simple case when parent inode equals current inode. */
+ if (ino_get(&fname->home) == ni->vfs_inode.i_ino) {
+ ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+ continue;
+ }
+
/* ntfs_iget5 may sleep. */
dir = ntfs_iget5(sb, &fname->home, NULL);
if (IS_ERR(dir)) {
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 12f28cdf5c83..98ccb6650858 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -2168,8 +2168,10 @@ file_is_valid:
if (!page) {
page = kmalloc(log->page_size, GFP_NOFS);
- if (!page)
- return -ENOMEM;
+ if (!page) {
+ err = -ENOMEM;
+ goto out;
+ }
}
/*
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 33afee0f5559..fbfe21dbb425 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -983,18 +983,11 @@ out:
if (err)
return err;
- mark_inode_dirty(&ni->vfs_inode);
+ mark_inode_dirty_sync(&ni->vfs_inode);
/* verify(!ntfs_update_mftmirr()); */
- /*
- * If we used wait=1, sync_inode_metadata waits for the io for the
- * inode to finish. It hangs when media is removed.
- * So wait=0 is sent down to sync_inode_metadata
- * and filemap_fdatawrite is used for the data blocks.
- */
- err = sync_inode_metadata(&ni->vfs_inode, 0);
- if (!err)
- err = filemap_fdatawrite(ni->vfs_inode.i_mapping);
+ /* write mft record on disk. */
+ err = _ni_write_inode(&ni->vfs_inode, 1);
return err;
}
@@ -2461,10 +2454,12 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
{
CLST end, i, zone_len, zlen;
struct wnd_bitmap *wnd = &sbi->used.bitmap;
+ bool dirty = false;
down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
if (!wnd_is_used(wnd, lcn, len)) {
- ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+ /* mark volume as dirty out of wnd->rw_lock */
+ dirty = true;
end = lcn + len;
len = 0;
@@ -2518,6 +2513,8 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
out:
up_write(&wnd->rw_lock);
+ if (dirty)
+ ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
}
/*
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index 124c6e822623..cf92b2433f7a 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -729,6 +729,9 @@ static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx,
u32 total = le32_to_cpu(hdr->total);
u16 offs[128];
+ if (unlikely(!cmp))
+ return NULL;
+
fill_table:
if (end > total)
return NULL;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index eb2ed0701495..d6d021e19aaa 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -170,8 +170,8 @@ next_attr:
nt2kernel(std5->cr_time, &ni->i_crtime);
#endif
nt2kernel(std5->a_time, &inode->i_atime);
- ctime = inode_get_ctime(inode);
nt2kernel(std5->c_time, &ctime);
+ inode_set_ctime_to_ts(inode, ctime);
nt2kernel(std5->m_time, &inode->i_mtime);
ni->std_fa = std5->fa;
@@ -1660,7 +1660,8 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
d_instantiate(dentry, inode);
/* Set original time. inode times (i_ctime) may be changed in ntfs_init_acl. */
- inode->i_atime = inode->i_mtime = inode_set_ctime_to_ts(inode, ni->i_crtime);
+ inode->i_atime = inode->i_mtime =
+ inode_set_ctime_to_ts(inode, ni->i_crtime);
dir->i_mtime = inode_set_ctime_to_ts(dir, ni->i_crtime);
mark_inode_dirty(dir);
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index ad430d50bd79..eedacf94edd8 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -156,8 +156,8 @@ static int ntfs_link(struct dentry *ode, struct inode *dir, struct dentry *de)
err = ntfs_link_inode(inode, de);
if (!err) {
- dir->i_mtime = inode_set_ctime_to_ts(inode,
- inode_set_ctime_current(dir));
+ dir->i_mtime = inode_set_ctime_to_ts(
+ inode, inode_set_ctime_current(dir));
mark_inode_dirty(inode);
mark_inode_dirty(dir);
d_instantiate(de, inode);
@@ -373,7 +373,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry,
#ifdef CONFIG_NTFS3_FS_POSIX_ACL
if (IS_POSIXACL(dir)) {
- /*
+ /*
* Load in cache current acl to avoid ni_lock(dir):
* ntfs_create_inode -> ntfs_init_acl -> posix_acl_create ->
* ntfs_get_acl -> ntfs_get_acl_ex -> ni_lock
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 98b76d1b09e7..86aecbb01a92 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -847,7 +847,7 @@ struct OBJECT_ID {
// Birth Volume Id is the Object Id of the Volume on.
// which the Object Id was allocated. It never changes.
struct GUID BirthVolumeId; //0x10:
-
+
// Birth Object Id is the first Object Id that was
// ever assigned to this MFT Record. I.e. If the Object Id
// is changed for some reason, this field will reflect the
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 629403ede6e5..0e6a2777870c 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -42,9 +42,11 @@ enum utf16_endian;
#define MINUS_ONE_T ((size_t)(-1))
/* Biggest MFT / smallest cluster */
#define MAXIMUM_BYTES_PER_MFT 4096
+#define MAXIMUM_SHIFT_BYTES_PER_MFT 12
#define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512)
#define MAXIMUM_BYTES_PER_INDEX 4096
+#define MAXIMUM_SHIFT_BYTES_PER_INDEX 12
#define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512)
/* NTFS specific error code when fixup failed. */
@@ -495,8 +497,6 @@ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path,
struct kstat *stat, u32 request_mask, u32 flags);
int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr);
-void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn,
- CLST len);
int ntfs_file_open(struct inode *inode, struct file *file);
int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index c12ebffc94da..53629b1f65e9 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -189,12 +189,19 @@ out:
return err;
}
+/*
+ * mi_enum_attr - start/continue attributes enumeration in record.
+ *
+ * NOTE: mi->mrec - memory of size sbi->record_size
+ * here we sure that mi->mrec->total == sbi->record_size (see mi_read)
+ */
struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
{
const struct MFT_REC *rec = mi->mrec;
u32 used = le32_to_cpu(rec->used);
- u32 t32, off, asize;
+ u32 t32, off, asize, prev_type;
u16 t16;
+ u64 data_size, alloc_size, tot_size;
if (!attr) {
u32 total = le32_to_cpu(rec->total);
@@ -213,6 +220,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
if (!is_rec_inuse(rec))
return NULL;
+ prev_type = 0;
attr = Add2Ptr(rec, off);
} else {
/* Check if input attr inside record. */
@@ -226,11 +234,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
return NULL;
}
- if (off + asize < off) {
- /* Overflow check. */
+ /* Overflow check. */
+ if (off + asize < off)
return NULL;
- }
+ prev_type = le32_to_cpu(attr->type);
attr = Add2Ptr(attr, asize);
off += asize;
}
@@ -250,7 +258,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
/* 0x100 is last known attribute for now. */
t32 = le32_to_cpu(attr->type);
- if ((t32 & 0xf) || (t32 > 0x100))
+ if (!t32 || (t32 & 0xf) || (t32 > 0x100))
+ return NULL;
+
+ /* attributes in record must be ordered by type */
+ if (t32 < prev_type)
return NULL;
/* Check overflow and boundary. */
@@ -259,16 +271,15 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
/* Check size of attribute. */
if (!attr->non_res) {
+ /* Check resident fields. */
if (asize < SIZEOF_RESIDENT)
return NULL;
t16 = le16_to_cpu(attr->res.data_off);
-
if (t16 > asize)
return NULL;
- t32 = le32_to_cpu(attr->res.data_size);
- if (t16 + t32 > asize)
+ if (t16 + le32_to_cpu(attr->res.data_size) > asize)
return NULL;
t32 = sizeof(short) * attr->name_len;
@@ -278,21 +289,52 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
return attr;
}
- /* Check some nonresident fields. */
- if (attr->name_len &&
- le16_to_cpu(attr->name_off) + sizeof(short) * attr->name_len >
- le16_to_cpu(attr->nres.run_off)) {
+ /* Check nonresident fields. */
+ if (attr->non_res != 1)
+ return NULL;
+
+ t16 = le16_to_cpu(attr->nres.run_off);
+ if (t16 > asize)
+ return NULL;
+
+ t32 = sizeof(short) * attr->name_len;
+ if (t32 && le16_to_cpu(attr->name_off) + t32 > t16)
+ return NULL;
+
+ /* Check start/end vcn. */
+ if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1)
return NULL;
- }
- if (attr->nres.svcn || !is_attr_ext(attr)) {
+ data_size = le64_to_cpu(attr->nres.data_size);
+ if (le64_to_cpu(attr->nres.valid_size) > data_size)
+ return NULL;
+
+ alloc_size = le64_to_cpu(attr->nres.alloc_size);
+ if (data_size > alloc_size)
+ return NULL;
+
+ t32 = mi->sbi->cluster_mask;
+ if (alloc_size & t32)
+ return NULL;
+
+ if (!attr->nres.svcn && is_attr_ext(attr)) {
+ /* First segment of sparse/compressed attribute */
+ if (asize + 8 < SIZEOF_NONRESIDENT_EX)
+ return NULL;
+
+ tot_size = le64_to_cpu(attr->nres.total_size);
+ if (tot_size & t32)
+ return NULL;
+
+ if (tot_size > alloc_size)
+ return NULL;
+ } else {
if (asize + 8 < SIZEOF_NONRESIDENT)
return NULL;
if (attr->nres.c_unit)
return NULL;
- } else if (asize + 8 < SIZEOF_NONRESIDENT_EX)
- return NULL;
+ }
return attr;
}
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 5661a363005e..f763e3256ccc 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -453,15 +453,23 @@ static struct proc_dir_entry *proc_info_root;
* ntfs3.1
* cluster size
* number of clusters
+ * total number of mft records
+ * number of used mft records ~= number of files + folders
+ * real state of ntfs "dirty"/"clean"
+ * current state of ntfs "dirty"/"clean"
*/
static int ntfs3_volinfo(struct seq_file *m, void *o)
{
struct super_block *sb = m->private;
struct ntfs_sb_info *sbi = sb->s_fs_info;
- seq_printf(m, "ntfs%d.%d\n%u\n%zu\n", sbi->volume.major_ver,
- sbi->volume.minor_ver, sbi->cluster_size,
- sbi->used.bitmap.nbits);
+ seq_printf(m, "ntfs%d.%d\n%u\n%zu\n\%zu\n%zu\n%s\n%s\n",
+ sbi->volume.major_ver, sbi->volume.minor_ver,
+ sbi->cluster_size, sbi->used.bitmap.nbits,
+ sbi->mft.bitmap.nbits,
+ sbi->mft.bitmap.nbits - wnd_zeroes(&sbi->mft.bitmap),
+ sbi->volume.real_dirty ? "dirty" : "clean",
+ (sbi->volume.flags & VOLUME_FLAG_DIRTY) ? "dirty" : "clean");
return 0;
}
@@ -488,9 +496,13 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer,
{
int err;
struct super_block *sb = pde_data(file_inode(file));
- struct ntfs_sb_info *sbi = sb->s_fs_info;
ssize_t ret = count;
- u8 *label = kmalloc(count, GFP_NOFS);
+ u8 *label;
+
+ if (sb_rdonly(sb))
+ return -EROFS;
+
+ label = kmalloc(count, GFP_NOFS);
if (!label)
return -ENOMEM;
@@ -502,7 +514,7 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer,
while (ret > 0 && label[ret - 1] == '\n')
ret -= 1;
- err = ntfs_set_label(sbi, label, ret);
+ err = ntfs_set_label(sb->s_fs_info, label, ret);
if (err < 0) {
ntfs_err(sb, "failed (%d) to write label", err);
@@ -576,20 +588,30 @@ static noinline void ntfs3_put_sbi(struct ntfs_sb_info *sbi)
wnd_close(&sbi->mft.bitmap);
wnd_close(&sbi->used.bitmap);
- if (sbi->mft.ni)
+ if (sbi->mft.ni) {
iput(&sbi->mft.ni->vfs_inode);
+ sbi->mft.ni = NULL;
+ }
- if (sbi->security.ni)
+ if (sbi->security.ni) {
iput(&sbi->security.ni->vfs_inode);
+ sbi->security.ni = NULL;
+ }
- if (sbi->reparse.ni)
+ if (sbi->reparse.ni) {
iput(&sbi->reparse.ni->vfs_inode);
+ sbi->reparse.ni = NULL;
+ }
- if (sbi->objid.ni)
+ if (sbi->objid.ni) {
iput(&sbi->objid.ni->vfs_inode);
+ sbi->objid.ni = NULL;
+ }
- if (sbi->volume.ni)
+ if (sbi->volume.ni) {
iput(&sbi->volume.ni->vfs_inode);
+ sbi->volume.ni = NULL;
+ }
ntfs_update_mftmirr(sbi, 0);
@@ -836,7 +858,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
struct ntfs_sb_info *sbi = sb->s_fs_info;
int err;
u32 mb, gb, boot_sector_size, sct_per_clst, record_size;
- u64 sectors, clusters, mlcn, mlcn2;
+ u64 sectors, clusters, mlcn, mlcn2, dev_size0;
struct NTFS_BOOT *boot;
struct buffer_head *bh;
struct MFT_REC *rec;
@@ -845,6 +867,9 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
u32 boot_off = 0;
const char *hint = "Primary boot";
+ /* Save original dev_size. Used with alternative boot. */
+ dev_size0 = dev_size;
+
sbi->volume.blocks = dev_size >> PAGE_SHIFT;
bh = ntfs_bread(sb, 0);
@@ -853,6 +878,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
check_boot:
err = -EINVAL;
+
+ /* Corrupted image; do not read OOB */
+ if (bh->b_size - sizeof(*boot) < boot_off)
+ goto out;
+
boot = (struct NTFS_BOOT *)Add2Ptr(bh->b_data, boot_off);
if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) {
@@ -899,9 +929,17 @@ check_boot:
goto out;
}
- sbi->record_size = record_size =
- boot->record_size < 0 ? 1 << (-boot->record_size) :
- (u32)boot->record_size << cluster_bits;
+ if (boot->record_size >= 0) {
+ record_size = (u32)boot->record_size << cluster_bits;
+ } else if (-boot->record_size <= MAXIMUM_SHIFT_BYTES_PER_MFT) {
+ record_size = 1u << (-boot->record_size);
+ } else {
+ ntfs_err(sb, "%s: invalid record size %d.", hint,
+ boot->record_size);
+ goto out;
+ }
+
+ sbi->record_size = record_size;
sbi->record_bits = blksize_bits(record_size);
sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes
@@ -918,9 +956,15 @@ check_boot:
goto out;
}
- sbi->index_size = boot->index_size < 0 ?
- 1u << (-boot->index_size) :
- (u32)boot->index_size << cluster_bits;
+ if (boot->index_size >= 0) {
+ sbi->index_size = (u32)boot->index_size << cluster_bits;
+ } else if (-boot->index_size <= MAXIMUM_SHIFT_BYTES_PER_INDEX) {
+ sbi->index_size = 1u << (-boot->index_size);
+ } else {
+ ntfs_err(sb, "%s: invalid index size %d.", hint,
+ boot->index_size);
+ goto out;
+ }
/* Check index record size. */
if (sbi->index_size < SECTOR_SIZE || !is_power_of_2(sbi->index_size)) {
@@ -1055,17 +1099,17 @@ check_boot:
if (bh->b_blocknr && !sb_rdonly(sb)) {
/*
- * Alternative boot is ok but primary is not ok.
- * Do not update primary boot here 'cause it may be faked boot.
- * Let ntfs to be mounted and update boot later.
- */
+ * Alternative boot is ok but primary is not ok.
+ * Do not update primary boot here 'cause it may be faked boot.
+ * Let ntfs to be mounted and update boot later.
+ */
*boot2 = kmemdup(boot, sizeof(*boot), GFP_NOFS | __GFP_NOWARN);
}
out:
- if (err == -EINVAL && !bh->b_blocknr && dev_size > PAGE_SHIFT) {
+ if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) {
u32 block_size = min_t(u32, sector_size, PAGE_SIZE);
- u64 lbo = dev_size - sizeof(*boot);
+ u64 lbo = dev_size0 - sizeof(*boot);
/*
* Try alternative boot (last sector)
@@ -1079,6 +1123,7 @@ out:
boot_off = lbo & (block_size - 1);
hint = "Alternative boot";
+ dev_size = dev_size0; /* restore original size. */
goto check_boot;
}
brelse(bh);
@@ -1367,7 +1412,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
}
bytes = inode->i_size;
- sbi->def_table = t = kmalloc(bytes, GFP_NOFS | __GFP_NOWARN);
+ sbi->def_table = t = kvmalloc(bytes, GFP_KERNEL);
if (!t) {
err = -ENOMEM;
goto put_inode_out;
@@ -1521,9 +1566,9 @@ load_root:
if (boot2) {
/*
- * Alternative boot is ok but primary is not ok.
- * Volume is recognized as NTFS. Update primary boot.
- */
+ * Alternative boot is ok but primary is not ok.
+ * Volume is recognized as NTFS. Update primary boot.
+ */
struct buffer_head *bh0 = sb_getblk(sb, 0);
if (bh0) {
if (buffer_locked(bh0))
@@ -1564,6 +1609,7 @@ put_inode_out:
out:
ntfs3_put_sbi(sbi);
kfree(boot2);
+ ntfs3_put_sbi(sbi);
return err;
}
@@ -1757,7 +1803,6 @@ static int __init init_ntfs_fs(void)
if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS))
pr_info("ntfs3: Read-only LZX/Xpress compression included\n");
-
#ifdef CONFIG_PROC_FS
/* Create "/proc/fs/ntfs3" */
proc_info_root = proc_mkdir("fs/ntfs3", NULL);
@@ -1799,7 +1844,6 @@ static void __exit exit_ntfs_fs(void)
if (proc_info_root)
remove_proc_entry("fs/ntfs3", NULL);
#endif
-
}
MODULE_LICENSE("GPL");
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 29fd391899e5..4920548192a0 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -211,7 +211,8 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
size = le32_to_cpu(info->size);
/* Enumerate all xattrs. */
- for (ret = 0, off = 0; off < size; off += ea_size) {
+ ret = 0;
+ for (off = 0; off + sizeof(struct EA_FULL) < size; off += ea_size) {
ea = Add2Ptr(ea_all, off);
ea_size = unpacked_ea_size(ea);
@@ -219,6 +220,10 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
break;
if (buffer) {
+ /* Check if we can use field ea->name */
+ if (off + ea_size > size)
+ break;
+
if (ret + ea->name_len + 1 > bytes_per_buffer) {
err = -ERANGE;
goto out;
diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c
index 95b751507ac8..f6ff23fd101c 100644
--- a/fs/overlayfs/params.c
+++ b/fs/overlayfs/params.c
@@ -157,6 +157,34 @@ const struct fs_parameter_spec ovl_parameter_spec[] = {
{}
};
+static char *ovl_next_opt(char **s)
+{
+ char *sbegin = *s;
+ char *p;
+
+ if (sbegin == NULL)
+ return NULL;
+
+ for (p = sbegin; *p; p++) {
+ if (*p == '\\') {
+ p++;
+ if (!*p)
+ break;
+ } else if (*p == ',') {
+ *p = '\0';
+ *s = p + 1;
+ return sbegin;
+ }
+ }
+ *s = NULL;
+ return sbegin;
+}
+
+static int ovl_parse_monolithic(struct fs_context *fc, void *data)
+{
+ return vfs_parse_monolithic_sep(fc, data, ovl_next_opt);
+}
+
static ssize_t ovl_parse_param_split_lowerdirs(char *str)
{
ssize_t nr_layers = 1, nr_colons = 0;
@@ -164,7 +192,8 @@ static ssize_t ovl_parse_param_split_lowerdirs(char *str)
for (s = d = str;; s++, d++) {
if (*s == '\\') {
- s++;
+ /* keep esc chars in split lowerdir */
+ *d++ = *s++;
} else if (*s == ':') {
bool next_colon = (*(s + 1) == ':');
@@ -239,7 +268,7 @@ static void ovl_unescape(char *s)
}
}
-static int ovl_mount_dir(const char *name, struct path *path)
+static int ovl_mount_dir(const char *name, struct path *path, bool upper)
{
int err = -ENOMEM;
char *tmp = kstrdup(name, GFP_KERNEL);
@@ -248,7 +277,7 @@ static int ovl_mount_dir(const char *name, struct path *path)
ovl_unescape(tmp);
err = ovl_mount_dir_noesc(tmp, path);
- if (!err && path->dentry->d_flags & DCACHE_OP_REAL) {
+ if (!err && upper && path->dentry->d_flags & DCACHE_OP_REAL) {
pr_err("filesystem on '%s' not supported as upperdir\n",
tmp);
path_put_init(path);
@@ -269,7 +298,7 @@ static int ovl_parse_param_upperdir(const char *name, struct fs_context *fc,
struct path path;
char *dup;
- err = ovl_mount_dir(name, &path);
+ err = ovl_mount_dir(name, &path, true);
if (err)
return err;
@@ -321,12 +350,6 @@ static void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx)
* Set "/lower1", "/lower2", and "/lower3" as lower layers and
* "/data1" and "/data2" as data lower layers. Any existing lower
* layers are replaced.
- * (2) lowerdir=:/lower4
- * Append "/lower4" to current stack of lower layers. This requires
- * that there already is at least one lower layer configured.
- * (3) lowerdir=::/lower5
- * Append data "/lower5" as data lower layer. This requires that
- * there's at least one regular lower layer present.
*/
static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
{
@@ -348,49 +371,9 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
return 0;
}
- if (strncmp(name, "::", 2) == 0) {
- /*
- * This is a data layer.
- * There must be at least one regular lower layer
- * specified.
- */
- if (ctx->nr == 0) {
- pr_err("data lower layers without regular lower layers not allowed");
- return -EINVAL;
- }
-
- /* Skip the leading "::". */
- name += 2;
- data_layer = true;
- /*
- * A data layer is automatically an append as there
- * must've been at least one regular lower layer.
- */
- append = true;
- } else if (*name == ':') {
- /*
- * This is a regular lower layer.
- * If users want to append a layer enforce that they
- * have already specified a first layer before. It's
- * better to be strict.
- */
- if (ctx->nr == 0) {
- pr_err("cannot append layer if no previous layer has been specified");
- return -EINVAL;
- }
-
- /*
- * Once a sequence of data layers has started regular
- * lower layers are forbidden.
- */
- if (ctx->nr_data > 0) {
- pr_err("regular lower layers cannot follow data lower layers");
- return -EINVAL;
- }
-
- /* Skip the leading ":". */
- name++;
- append = true;
+ if (*name == ':') {
+ pr_err("cannot append lower layer");
+ return -EINVAL;
}
dup = kstrdup(name, GFP_KERNEL);
@@ -472,7 +455,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc)
l = &ctx->lower[nr];
memset(l, 0, sizeof(*l));
- err = ovl_mount_dir_noesc(dup_iter, &l->path);
+ err = ovl_mount_dir(dup_iter, &l->path, false);
if (err)
goto out_put;
@@ -682,6 +665,7 @@ static int ovl_reconfigure(struct fs_context *fc)
}
static const struct fs_context_operations ovl_context_ops = {
+ .parse_monolithic = ovl_parse_monolithic,
.parse_param = ovl_parse_param,
.get_tree = ovl_get_tree,
.reconfigure = ovl_reconfigure,
@@ -950,16 +934,23 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry)
struct super_block *sb = dentry->d_sb;
struct ovl_fs *ofs = OVL_FS(sb);
size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer;
- char **lowerdatadirs = &ofs->config.lowerdirs[nr_merged_lower];
-
- /* lowerdirs[] starts from offset 1 */
- seq_printf(m, ",lowerdir=%s", ofs->config.lowerdirs[1]);
- /* dump regular lower layers */
- for (nr = 2; nr < nr_merged_lower; nr++)
- seq_printf(m, ":%s", ofs->config.lowerdirs[nr]);
- /* dump data lower layers */
- for (nr = 0; nr < ofs->numdatalayer; nr++)
- seq_printf(m, "::%s", lowerdatadirs[nr]);
+
+ /*
+ * lowerdirs[] starts from offset 1, then
+ * >= 0 regular lower layers prefixed with : and
+ * >= 0 data-only lower layers prefixed with ::
+ *
+ * we need to escase comma and space like seq_show_option() does and
+ * we also need to escape the colon separator from lowerdir paths.
+ */
+ seq_puts(m, ",lowerdir=");
+ for (nr = 1; nr < ofs->numlayer; nr++) {
+ if (nr > 1)
+ seq_putc(m, ':');
+ if (nr >= nr_merged_lower)
+ seq_putc(m, ':');
+ seq_escape(m, ofs->config.lowerdirs[nr], ":, \t\n\\");
+ }
if (ofs->config.upperdir) {
seq_show_option(m, "upperdir", ofs->config.upperdir);
seq_show_option(m, "workdir", ofs->config.workdir);
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 9e72bfe8bbad..31e897ad5e6a 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -233,19 +233,18 @@ static void put_quota_format(struct quota_format_type *fmt)
* All dquots are placed to the end of inuse_list when first created, and this
* list is used for invalidate operation, which must look at every dquot.
*
- * When the last reference of a dquot will be dropped, the dquot will be
- * added to releasing_dquots. We'd then queue work item which would call
+ * When the last reference of a dquot is dropped, the dquot is added to
+ * releasing_dquots. We'll then queue work item which will call
* synchronize_srcu() and after that perform the final cleanup of all the
- * dquots on the list. Both releasing_dquots and free_dquots use the
- * dq_free list_head in the dquot struct. When a dquot is removed from
- * releasing_dquots, a reference count is always subtracted, and if
- * dq_count == 0 at that point, the dquot will be added to the free_dquots.
+ * dquots on the list. Each cleaned up dquot is moved to free_dquots list.
+ * Both releasing_dquots and free_dquots use the dq_free list_head in the dquot
+ * struct.
*
- * Unused dquots (dq_count == 0) are added to the free_dquots list when freed,
- * and this list is searched whenever we need an available dquot. Dquots are
- * removed from the list as soon as they are used again, and
- * dqstats.free_dquots gives the number of dquots on the list. When
- * dquot is invalidated it's completely released from memory.
+ * Unused and cleaned up dquots are in the free_dquots list and this list is
+ * searched whenever we need an available dquot. Dquots are removed from the
+ * list as soon as they are used again and dqstats.free_dquots gives the number
+ * of dquots on the list. When dquot is invalidated it's completely released
+ * from memory.
*
* Dirty dquots are added to the dqi_dirty_list of quota_info when mark
* dirtied, and this list is searched when writing dirty dquots back to
@@ -321,6 +320,7 @@ static inline void put_dquot_last(struct dquot *dquot)
static inline void put_releasing_dquots(struct dquot *dquot)
{
list_add_tail(&dquot->dq_free, &releasing_dquots);
+ set_bit(DQ_RELEASING_B, &dquot->dq_flags);
}
static inline void remove_free_dquot(struct dquot *dquot)
@@ -328,8 +328,10 @@ static inline void remove_free_dquot(struct dquot *dquot)
if (list_empty(&dquot->dq_free))
return;
list_del_init(&dquot->dq_free);
- if (!atomic_read(&dquot->dq_count))
+ if (!test_bit(DQ_RELEASING_B, &dquot->dq_flags))
dqstats_dec(DQST_FREE_DQUOTS);
+ else
+ clear_bit(DQ_RELEASING_B, &dquot->dq_flags);
}
static inline void put_inuse(struct dquot *dquot)
@@ -581,12 +583,6 @@ restart:
continue;
/* Wait for dquot users */
if (atomic_read(&dquot->dq_count)) {
- /* dquot in releasing_dquots, flush and retry */
- if (!list_empty(&dquot->dq_free)) {
- spin_unlock(&dq_list_lock);
- goto restart;
- }
-
atomic_inc(&dquot->dq_count);
spin_unlock(&dq_list_lock);
/*
@@ -606,6 +602,15 @@ restart:
goto restart;
}
/*
+ * The last user already dropped its reference but dquot didn't
+ * get fully cleaned up yet. Restart the scan which flushes the
+ * work cleaning up released dquots.
+ */
+ if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) {
+ spin_unlock(&dq_list_lock);
+ goto restart;
+ }
+ /*
* Quota now has no users and it has been written on last
* dqput()
*/
@@ -696,6 +701,13 @@ int dquot_writeback_dquots(struct super_block *sb, int type)
dq_dirty);
WARN_ON(!dquot_active(dquot));
+ /* If the dquot is releasing we should not touch it */
+ if (test_bit(DQ_RELEASING_B, &dquot->dq_flags)) {
+ spin_unlock(&dq_list_lock);
+ flush_delayed_work(&quota_release_work);
+ spin_lock(&dq_list_lock);
+ continue;
+ }
/* Now we have active dquot from which someone is
* holding reference so we can safely just increase
@@ -809,18 +821,18 @@ static void quota_release_workfn(struct work_struct *work)
/* Exchange the list head to avoid livelock. */
list_replace_init(&releasing_dquots, &rls_head);
spin_unlock(&dq_list_lock);
+ synchronize_srcu(&dquot_srcu);
restart:
- synchronize_srcu(&dquot_srcu);
spin_lock(&dq_list_lock);
while (!list_empty(&rls_head)) {
dquot = list_first_entry(&rls_head, struct dquot, dq_free);
- /* Dquot got used again? */
- if (atomic_read(&dquot->dq_count) > 1) {
- remove_free_dquot(dquot);
- atomic_dec(&dquot->dq_count);
- continue;
- }
+ WARN_ON_ONCE(atomic_read(&dquot->dq_count));
+ /*
+ * Note that DQ_RELEASING_B protects us from racing with
+ * invalidate_dquots() calls so we are safe to work with the
+ * dquot even after we drop dq_list_lock.
+ */
if (dquot_dirty(dquot)) {
spin_unlock(&dq_list_lock);
/* Commit dquot before releasing */
@@ -834,7 +846,6 @@ restart:
}
/* Dquot is inactive and clean, now move it to free list */
remove_free_dquot(dquot);
- atomic_dec(&dquot->dq_count);
put_dquot_last(dquot);
}
spin_unlock(&dq_list_lock);
@@ -875,6 +886,7 @@ void dqput(struct dquot *dquot)
BUG_ON(!list_empty(&dquot->dq_free));
#endif
put_releasing_dquots(dquot);
+ atomic_dec(&dquot->dq_count);
spin_unlock(&dq_list_lock);
queue_delayed_work(system_unbound_wq, &quota_release_work, 1);
}
@@ -963,7 +975,7 @@ we_slept:
dqstats_inc(DQST_LOOKUPS);
}
/* Wait for dq_lock - after this we know that either dquot_release() is
- * already finished or it will be canceled due to dq_count > 1 test */
+ * already finished or it will be canceled due to dq_count > 0 test */
wait_on_dquot(dquot);
/* Read the dquot / allocate space in quota file */
if (!dquot_active(dquot)) {
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index e2be8aedb26e..fe1bf5b6e0cb 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -15,6 +15,7 @@
static struct cached_fid *init_cached_dir(const char *path);
static void free_cached_dir(struct cached_fid *cfid);
static void smb2_close_cached_fid(struct kref *ref);
+static void cfids_laundromat_worker(struct work_struct *work);
static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids,
const char *path,
@@ -169,15 +170,18 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
return -ENOENT;
}
/*
- * At this point we either have a lease already and we can just
- * return it. If not we are guaranteed to be the only thread accessing
- * this cfid.
+ * Return cached fid if it has a lease. Otherwise, it is either a new
+ * entry or laundromat worker removed it from @cfids->entries. Caller
+ * will put last reference if the latter.
*/
+ spin_lock(&cfids->cfid_list_lock);
if (cfid->has_lease) {
+ spin_unlock(&cfids->cfid_list_lock);
*ret_cfid = cfid;
kfree(utf16_path);
return 0;
}
+ spin_unlock(&cfids->cfid_list_lock);
/*
* Skip any prefix paths in @path as lookup_positive_unlocked() ends up
@@ -294,9 +298,11 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
goto oshr_free;
}
}
+ spin_lock(&cfids->cfid_list_lock);
cfid->dentry = dentry;
cfid->time = jiffies;
cfid->has_lease = true;
+ spin_unlock(&cfids->cfid_list_lock);
oshr_free:
kfree(utf16_path);
@@ -305,24 +311,28 @@ oshr_free:
free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
spin_lock(&cfids->cfid_list_lock);
- if (rc && !cfid->has_lease) {
- if (cfid->on_list) {
- list_del(&cfid->entry);
- cfid->on_list = false;
- cfids->num_entries--;
+ if (!cfid->has_lease) {
+ if (rc) {
+ if (cfid->on_list) {
+ list_del(&cfid->entry);
+ cfid->on_list = false;
+ cfids->num_entries--;
+ }
+ rc = -ENOENT;
+ } else {
+ /*
+ * We are guaranteed to have two references at this
+ * point. One for the caller and one for a potential
+ * lease. Release the Lease-ref so that the directory
+ * will be closed when the caller closes the cached
+ * handle.
+ */
+ spin_unlock(&cfids->cfid_list_lock);
+ kref_put(&cfid->refcount, smb2_close_cached_fid);
+ goto out;
}
- rc = -ENOENT;
}
spin_unlock(&cfids->cfid_list_lock);
- if (!rc && !cfid->has_lease) {
- /*
- * We are guaranteed to have two references at this point.
- * One for the caller and one for a potential lease.
- * Release the Lease-ref so that the directory will be closed
- * when the caller closes the cached handle.
- */
- kref_put(&cfid->refcount, smb2_close_cached_fid);
- }
if (rc) {
if (cfid->is_open)
SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid,
@@ -330,7 +340,7 @@ oshr_free:
free_cached_dir(cfid);
cfid = NULL;
}
-
+out:
if (rc == 0) {
*ret_cfid = cfid;
atomic_inc(&tcon->num_remote_opens);
@@ -572,53 +582,51 @@ static void free_cached_dir(struct cached_fid *cfid)
kfree(cfid);
}
-static int
-cifs_cfids_laundromat_thread(void *p)
+static void cfids_laundromat_worker(struct work_struct *work)
{
- struct cached_fids *cfids = p;
+ struct cached_fids *cfids;
struct cached_fid *cfid, *q;
- struct list_head entry;
+ LIST_HEAD(entry);
- while (!kthread_should_stop()) {
- ssleep(1);
- INIT_LIST_HEAD(&entry);
- if (kthread_should_stop())
- return 0;
- spin_lock(&cfids->cfid_list_lock);
- list_for_each_entry_safe(cfid, q, &cfids->entries, entry) {
- if (time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) {
- list_del(&cfid->entry);
- list_add(&cfid->entry, &entry);
- cfids->num_entries--;
- }
- }
- spin_unlock(&cfids->cfid_list_lock);
+ cfids = container_of(work, struct cached_fids, laundromat_work.work);
- list_for_each_entry_safe(cfid, q, &entry, entry) {
+ spin_lock(&cfids->cfid_list_lock);
+ list_for_each_entry_safe(cfid, q, &cfids->entries, entry) {
+ if (cfid->time &&
+ time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) {
cfid->on_list = false;
- list_del(&cfid->entry);
+ list_move(&cfid->entry, &entry);
+ cfids->num_entries--;
+ /* To prevent race with smb2_cached_lease_break() */
+ kref_get(&cfid->refcount);
+ }
+ }
+ spin_unlock(&cfids->cfid_list_lock);
+
+ list_for_each_entry_safe(cfid, q, &entry, entry) {
+ list_del(&cfid->entry);
+ /*
+ * Cancel and wait for the work to finish in case we are racing
+ * with it.
+ */
+ cancel_work_sync(&cfid->lease_break);
+ if (cfid->has_lease) {
/*
- * Cancel, and wait for the work to finish in
- * case we are racing with it.
+ * Our lease has not yet been cancelled from the server
+ * so we need to drop the reference.
*/
- cancel_work_sync(&cfid->lease_break);
- if (cfid->has_lease) {
- /*
- * We lease has not yet been cancelled from
- * the server so we need to drop the reference.
- */
- spin_lock(&cfids->cfid_list_lock);
- cfid->has_lease = false;
- spin_unlock(&cfids->cfid_list_lock);
- kref_put(&cfid->refcount, smb2_close_cached_fid);
- }
+ spin_lock(&cfids->cfid_list_lock);
+ cfid->has_lease = false;
+ spin_unlock(&cfids->cfid_list_lock);
+ kref_put(&cfid->refcount, smb2_close_cached_fid);
}
+ /* Drop the extra reference opened above */
+ kref_put(&cfid->refcount, smb2_close_cached_fid);
}
-
- return 0;
+ queue_delayed_work(cifsiod_wq, &cfids->laundromat_work,
+ dir_cache_timeout * HZ);
}
-
struct cached_fids *init_cached_dirs(void)
{
struct cached_fids *cfids;
@@ -629,19 +637,10 @@ struct cached_fids *init_cached_dirs(void)
spin_lock_init(&cfids->cfid_list_lock);
INIT_LIST_HEAD(&cfids->entries);
- /*
- * since we're in a cifs function already, we know that
- * this will succeed. No need for try_module_get().
- */
- __module_get(THIS_MODULE);
- cfids->laundromat = kthread_run(cifs_cfids_laundromat_thread,
- cfids, "cifsd-cfid-laundromat");
- if (IS_ERR(cfids->laundromat)) {
- cifs_dbg(VFS, "Failed to start cfids laundromat thread.\n");
- kfree(cfids);
- module_put(THIS_MODULE);
- return NULL;
- }
+ INIT_DELAYED_WORK(&cfids->laundromat_work, cfids_laundromat_worker);
+ queue_delayed_work(cifsiod_wq, &cfids->laundromat_work,
+ dir_cache_timeout * HZ);
+
return cfids;
}
@@ -657,11 +656,7 @@ void free_cached_dirs(struct cached_fids *cfids)
if (cfids == NULL)
return;
- if (cfids->laundromat) {
- kthread_stop(cfids->laundromat);
- cfids->laundromat = NULL;
- module_put(THIS_MODULE);
- }
+ cancel_delayed_work_sync(&cfids->laundromat_work);
spin_lock(&cfids->cfid_list_lock);
list_for_each_entry_safe(cfid, q, &cfids->entries, entry) {
diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h
index a82ff2cea789..81ba0fd5cc16 100644
--- a/fs/smb/client/cached_dir.h
+++ b/fs/smb/client/cached_dir.h
@@ -57,7 +57,7 @@ struct cached_fids {
spinlock_t cfid_list_lock;
int num_entries;
struct list_head entries;
- struct task_struct *laundromat;
+ struct delayed_work laundromat_work;
};
extern struct cached_fids *init_cached_dirs(void);
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 898860adf929..93262ca3f58a 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -231,11 +231,12 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err)
{
struct smb2_hdr *rsp_hdr;
- if (work->next_smb2_rcv_hdr_off)
- rsp_hdr = ksmbd_resp_buf_next(work);
- else
- rsp_hdr = smb2_get_msg(work->response_buf);
+ rsp_hdr = smb2_get_msg(work->response_buf);
rsp_hdr->Status = err;
+
+ work->iov_idx = 0;
+ work->iov_cnt = 0;
+ work->next_smb2_rcv_hdr_off = 0;
smb2_set_err_rsp(work);
}
@@ -6151,12 +6152,12 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work)
memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz);
nbytes = rpc_resp->payload_sz;
- kvfree(rpc_resp);
err = ksmbd_iov_pin_rsp_read(work, (void *)rsp,
offsetof(struct smb2_read_rsp, Buffer),
aux_payload_buf, nbytes);
if (err)
goto out;
+ kvfree(rpc_resp);
} else {
err = ksmbd_iov_pin_rsp(work, (void *)rsp,
offsetof(struct smb2_read_rsp, Buffer));
diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c
index c4b80ab7df74..c91eac6514dd 100644
--- a/fs/smb/server/vfs_cache.c
+++ b/fs/smb/server/vfs_cache.c
@@ -106,7 +106,7 @@ int ksmbd_query_inode_status(struct inode *inode)
ci = __ksmbd_inode_lookup(inode);
if (ci) {
ret = KSMBD_INODE_STATUS_OK;
- if (ci->m_flags & S_DEL_PENDING)
+ if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS))
ret = KSMBD_INODE_STATUS_PENDING_DELETE;
atomic_dec(&ci->m_count);
}
@@ -116,7 +116,7 @@ int ksmbd_query_inode_status(struct inode *inode)
bool ksmbd_inode_pending_delete(struct ksmbd_file *fp)
{
- return (fp->f_ci->m_flags & S_DEL_PENDING);
+ return (fp->f_ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS));
}
void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp)
@@ -603,6 +603,9 @@ err_out:
void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp,
unsigned int state)
{
+ if (!fp)
+ return;
+
write_lock(&ft->lock);
fp->f_state = state;
write_unlock(&ft->lock);
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index e9cc481b4ddf..f9f4d694640d 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -1001,6 +1001,12 @@ xfs_ag_shrink_space(
error = -ENOSPC;
goto resv_init_out;
}
+
+ /* Update perag geometry */
+ pag->block_count -= delta;
+ __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min,
+ &pag->agino_max);
+
xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH);
return 0;
diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c
index d98e8e77c684..090c3ead43fd 100644
--- a/fs/xfs/scrub/xfile.c
+++ b/fs/xfs/scrub/xfile.c
@@ -10,7 +10,6 @@
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
-#include "xfs_format.h"
#include "scrub/xfile.h"
#include "scrub/xfarray.h"
#include "scrub/scrub.h"
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 746814815b1d..9ecfdcdc752f 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -62,7 +62,8 @@ xfs_extent_busy_insert_list(
rb_link_node(&new->rb_node, parent, rbp);
rb_insert_color(&new->rb_node, &pag->pagb_tree);
- list_add(&new->list, busy_list);
+ /* always process discard lists in fifo order */
+ list_add_tail(&new->list, busy_list);
spin_unlock(&pag->pagb_lock);
}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 1c1e6171209d..2b3b05c28e9e 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -584,6 +584,11 @@ xfs_vn_getattr(
}
}
+ if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) {
+ stat->change_cookie = inode_query_iversion(inode);
+ stat->result_mask |= STATX_CHANGE_COOKIE;
+ }
+
/*
* Note: If you add another clause to set an attribute flag, please
* update attributes_mask below.
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index 4a9bbd3fe120..a7daa522e00f 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -126,8 +126,8 @@ xfs_dax_notify_ddev_failure(
struct xfs_rmap_irec ri_low = { };
struct xfs_rmap_irec ri_high;
struct xfs_agf *agf;
- xfs_agblock_t agend;
struct xfs_perag *pag;
+ xfs_agblock_t range_agend;
pag = xfs_perag_get(mp, agno);
error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp);
@@ -148,10 +148,10 @@ xfs_dax_notify_ddev_failure(
ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno);
agf = agf_bp->b_addr;
- agend = min(be32_to_cpu(agf->agf_length),
+ range_agend = min(be32_to_cpu(agf->agf_length) - 1,
ri_high.rm_startblock);
notify.startblock = ri_low.rm_startblock;
- notify.blockcount = agend - ri_low.rm_startblock;
+ notify.blockcount = range_agend + 1 - ri_low.rm_startblock;
error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
xfs_dax_failure_fn, &notify);