aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/main.c6
-rw-r--r--fs/block_dev.c10
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/block-group.c13
-rw-r--r--fs/btrfs/ctree.h3
-rw-r--r--fs/btrfs/extent-tree.c71
-rw-r--r--fs/btrfs/free-space-tree.c10
-rw-r--r--fs/btrfs/send.c15
-rw-r--r--fs/btrfs/transaction.c8
-rw-r--r--fs/btrfs/volumes.c4
-rw-r--r--fs/btrfs/volumes.h11
-rw-r--r--fs/cachefiles/rdwr.c2
-rw-r--r--fs/ceph/mds_client.c34
-rw-r--r--fs/cifs/cifs_dfs_ref.c12
-rw-r--r--fs/cifs/cifsfs.c2
-rw-r--r--fs/cifs/cifsproto.h6
-rw-r--r--fs/cifs/connect.c36
-rw-r--r--fs/cifs/dfs_cache.c8
-rw-r--r--fs/cifs/dir.c22
-rw-r--r--fs/cifs/fs_context.c41
-rw-r--r--fs/cifs/smb2pdu.h2
-rw-r--r--fs/cifs/transport.c22
-rw-r--r--fs/ecryptfs/inode.c10
-rw-r--r--fs/fs-writeback.c24
-rw-r--r--fs/hugetlbfs/inode.c3
-rw-r--r--fs/io_uring.c165
-rw-r--r--fs/kernfs/file.c65
-rw-r--r--fs/nfs/pnfs.c69
-rw-r--r--fs/nfsd/nfs3xdr.c7
-rw-r--r--fs/overlayfs/copy_up.c15
-rw-r--r--fs/overlayfs/dir.c2
-rw-r--r--fs/overlayfs/file.c5
-rw-r--r--fs/overlayfs/inode.c2
-rw-r--r--fs/overlayfs/overlayfs.h1
-rw-r--r--fs/overlayfs/ovl_entry.h2
-rw-r--r--fs/overlayfs/readdir.c28
-rw-r--r--fs/overlayfs/super.c38
-rw-r--r--fs/overlayfs/util.c27
-rw-r--r--fs/pipe.c1
-rw-r--r--fs/proc/proc_sysctl.c7
-rw-r--r--fs/udf/super.c7
41 files changed, 517 insertions, 301 deletions
diff --git a/fs/afs/main.c b/fs/afs/main.c
index accdd8970e7c..b2975256dadb 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -193,7 +193,7 @@ static int __init afs_init(void)
goto error_cache;
#endif
- ret = register_pernet_subsys(&afs_net_ops);
+ ret = register_pernet_device(&afs_net_ops);
if (ret < 0)
goto error_net;
@@ -213,7 +213,7 @@ static int __init afs_init(void)
error_proc:
afs_fs_exit();
error_fs:
- unregister_pernet_subsys(&afs_net_ops);
+ unregister_pernet_device(&afs_net_ops);
error_net:
#ifdef CONFIG_AFS_FSCACHE
fscache_unregister_netfs(&afs_cache_netfs);
@@ -244,7 +244,7 @@ static void __exit afs_exit(void)
proc_remove(afs_proc_symlink);
afs_fs_exit();
- unregister_pernet_subsys(&afs_net_ops);
+ unregister_pernet_device(&afs_net_ops);
#ifdef CONFIG_AFS_FSCACHE
fscache_unregister_netfs(&afs_cache_netfs);
#endif
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3b8963e228a1..235b5042672e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -130,7 +130,15 @@ EXPORT_SYMBOL(truncate_bdev_range);
static void set_init_blocksize(struct block_device *bdev)
{
- bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev));
+ unsigned int bsize = bdev_logical_block_size(bdev);
+ loff_t size = i_size_read(bdev->bd_inode);
+
+ while (bsize < PAGE_SIZE) {
+ if (size & bsize)
+ break;
+ bsize <<= 1;
+ }
+ bdev->bd_inode->i_blkbits = blksize_bits(bsize);
}
int set_blocksize(struct block_device *bdev, int size)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 02d7d7b2563b..9cadacf3ec27 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -3117,7 +3117,7 @@ void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache,
list_del_init(&lower->list);
if (lower == node)
node = NULL;
- btrfs_backref_free_node(cache, lower);
+ btrfs_backref_drop_node(cache, lower);
}
btrfs_backref_cleanup_node(cache, node);
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 52f2198d44c9..48ebc106a606 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -673,7 +673,15 @@ static noinline void caching_thread(struct btrfs_work *work)
wake_up(&caching_ctl->wait);
}
- if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
+ /*
+ * If we are in the transaction that populated the free space tree we
+ * can't actually cache from the free space tree as our commit root and
+ * real root are the same, so we could change the contents of the blocks
+ * while caching. Instead do the slow caching in this case, and after
+ * the transaction has committed we will be safe.
+ */
+ if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
+ !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags)))
ret = load_free_space_tree(caching_ctl);
else
ret = load_extent_tree_free(caching_ctl);
@@ -2669,7 +2677,8 @@ again:
* Go through delayed refs for all the stuff we've just kicked off
* and then loop back (just once)
*/
- ret = btrfs_run_delayed_refs(trans, 0);
+ if (!ret)
+ ret = btrfs_run_delayed_refs(trans, 0);
if (!ret && loops == 0) {
loops++;
spin_lock(&cur_trans->dirty_bgs_lock);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e6e37591f1de..4debdbdde2ab 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -563,6 +563,9 @@ enum {
/* Indicate that we need to cleanup space cache v1 */
BTRFS_FS_CLEANUP_SPACE_CACHE_V1,
+
+ /* Indicate that we can't trust the free space tree for caching yet */
+ BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED,
};
/*
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d79b8369e6aa..0c335dae5af7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2602,8 +2602,6 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
struct btrfs_block_group *cache;
int ret;
- btrfs_add_excluded_extent(trans->fs_info, bytenr, num_bytes);
-
cache = btrfs_lookup_block_group(trans->fs_info, bytenr);
if (!cache)
return -EINVAL;
@@ -2615,11 +2613,19 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_trans_handle *trans,
* the pinned extents.
*/
btrfs_cache_block_group(cache, 1);
+ /*
+ * Make sure we wait until the cache is completely built in case it is
+ * missing or is invalid and therefore needs to be rebuilt.
+ */
+ ret = btrfs_wait_block_group_cache_done(cache);
+ if (ret)
+ goto out;
pin_down_extent(trans, cache, bytenr, num_bytes, 0);
/* remove us from the free space cache (if we're there at all) */
ret = btrfs_remove_free_space(cache, bytenr, num_bytes);
+out:
btrfs_put_block_group(cache);
return ret;
}
@@ -2629,50 +2635,22 @@ static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
{
int ret;
struct btrfs_block_group *block_group;
- struct btrfs_caching_control *caching_ctl;
block_group = btrfs_lookup_block_group(fs_info, start);
if (!block_group)
return -EINVAL;
- btrfs_cache_block_group(block_group, 0);
- caching_ctl = btrfs_get_caching_control(block_group);
-
- if (!caching_ctl) {
- /* Logic error */
- BUG_ON(!btrfs_block_group_done(block_group));
- ret = btrfs_remove_free_space(block_group, start, num_bytes);
- } else {
- /*
- * We must wait for v1 caching to finish, otherwise we may not
- * remove our space.
- */
- btrfs_wait_space_cache_v1_finished(block_group, caching_ctl);
- mutex_lock(&caching_ctl->mutex);
-
- if (start >= caching_ctl->progress) {
- ret = btrfs_add_excluded_extent(fs_info, start,
- num_bytes);
- } else if (start + num_bytes <= caching_ctl->progress) {
- ret = btrfs_remove_free_space(block_group,
- start, num_bytes);
- } else {
- num_bytes = caching_ctl->progress - start;
- ret = btrfs_remove_free_space(block_group,
- start, num_bytes);
- if (ret)
- goto out_lock;
+ btrfs_cache_block_group(block_group, 1);
+ /*
+ * Make sure we wait until the cache is completely built in case it is
+ * missing or is invalid and therefore needs to be rebuilt.
+ */
+ ret = btrfs_wait_block_group_cache_done(block_group);
+ if (ret)
+ goto out;
- num_bytes = (start + num_bytes) -
- caching_ctl->progress;
- start = caching_ctl->progress;
- ret = btrfs_add_excluded_extent(fs_info, start,
- num_bytes);
- }
-out_lock:
- mutex_unlock(&caching_ctl->mutex);
- btrfs_put_caching_control(caching_ctl);
- }
+ ret = btrfs_remove_free_space(block_group, start, num_bytes);
+out:
btrfs_put_block_group(block_group);
return ret;
}
@@ -2863,9 +2841,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
mutex_unlock(&fs_info->unused_bg_unpin_mutex);
break;
}
- if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
- clear_extent_bits(&fs_info->excluded_extents, start,
- end, EXTENT_UPTODATE);
if (btrfs_test_opt(fs_info, DISCARD_SYNC))
ret = btrfs_discard_extent(fs_info, start,
@@ -5549,7 +5524,15 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
goto out_free;
}
- trans = btrfs_start_transaction(tree_root, 0);
+ /*
+ * Use join to avoid potential EINTR from transaction
+ * start. See wait_reserve_ticket and the whole
+ * reservation callchain.
+ */
+ if (for_reloc)
+ trans = btrfs_join_transaction(tree_root);
+ else
+ trans = btrfs_start_transaction(tree_root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out_free;
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index e33a65bd9a0c..a33bca94d133 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1150,6 +1150,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
return PTR_ERR(trans);
set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+ set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
free_space_root = btrfs_create_tree(trans,
BTRFS_FREE_SPACE_TREE_OBJECTID);
if (IS_ERR(free_space_root)) {
@@ -1171,11 +1172,18 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE);
btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+ ret = btrfs_commit_transaction(trans);
- return btrfs_commit_transaction(trans);
+ /*
+ * Now that we've committed the transaction any reading of our commit
+ * root will be safe, so we can cache from the free space tree now.
+ */
+ clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
+ return ret;
abort:
clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
+ clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags);
btrfs_abort_transaction(trans, ret);
btrfs_end_transaction(trans);
return ret;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index ae97f4dbaff3..78a35374d492 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5512,6 +5512,21 @@ static int clone_range(struct send_ctx *sctx,
break;
offset += clone_len;
clone_root->offset += clone_len;
+
+ /*
+ * If we are cloning from the file we are currently processing,
+ * and using the send root as the clone root, we must stop once
+ * the current clone offset reaches the current eof of the file
+ * at the receiver, otherwise we would issue an invalid clone
+ * operation (source range going beyond eof) and cause the
+ * receiver to fail. So if we reach the current eof, bail out
+ * and fallback to a regular write.
+ */
+ if (clone_root->root == sctx->send_root &&
+ clone_root->ino == sctx->cur_ino &&
+ clone_root->offset >= sctx->cur_inode_next_write_offset)
+ break;
+
data_offset += clone_len;
next:
path->slots[0]++;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8e0f7a1029c6..6af7f2bf92de 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2265,14 +2265,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
btrfs_free_log_root_tree(trans, fs_info);
/*
- * commit_fs_roots() can call btrfs_save_ino_cache(), which generates
- * new delayed refs. Must handle them or qgroup can be wrong.
- */
- ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
- if (ret)
- goto unlock_tree_log;
-
- /*
* Since fs roots are all committed, we can get a quite accurate
* new_roots. So let's do quota accounting.
*/
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b62be84833e9..d6c24c8ad749 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -433,7 +433,7 @@ static struct btrfs_device *__alloc_device(struct btrfs_fs_info *fs_info)
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
- btrfs_device_data_ordered_init(dev, fs_info);
+ btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
extent_io_tree_init(fs_info, &dev->alloc_state,
@@ -4317,6 +4317,8 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
btrfs_warn(fs_info,
"balance: cannot set exclusive op status, resume manually");
+ btrfs_release_path(path);
+
mutex_lock(&fs_info->balance_mutex);
BUG_ON(fs_info->balance_ctl);
spin_lock(&fs_info->balance_lock);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1997a4649a66..c43663d9c22e 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -39,10 +39,10 @@ struct btrfs_io_geometry {
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __BTRFS_NEED_DEVICE_DATA_ORDERED
-#define btrfs_device_data_ordered_init(device, info) \
- seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex)
+#define btrfs_device_data_ordered_init(device) \
+ seqcount_init(&device->data_seqcount)
#else
-#define btrfs_device_data_ordered_init(device, info) do { } while (0)
+#define btrfs_device_data_ordered_init(device) do { } while (0)
#endif
#define BTRFS_DEV_STATE_WRITEABLE (0)
@@ -76,8 +76,7 @@ struct btrfs_device {
blk_status_t last_flush_error;
#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
- /* A seqcount_t with associated chunk_mutex (for lockdep) */
- seqcount_mutex_t data_seqcount;
+ seqcount_t data_seqcount;
#endif
/* the internal btrfs device id */
@@ -168,9 +167,11 @@ btrfs_device_get_##name(const struct btrfs_device *dev) \
static inline void \
btrfs_device_set_##name(struct btrfs_device *dev, u64 size) \
{ \
+ preempt_disable(); \
write_seqcount_begin(&dev->data_seqcount); \
dev->name = size; \
write_seqcount_end(&dev->data_seqcount); \
+ preempt_enable(); \
}
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
#define BTRFS_DEVICE_GETSET_FUNCS(name) \
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 8bda092e60c5..e027c718ca01 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -413,7 +413,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
@@ -713,7 +712,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 840587037b59..d87bd852ed96 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -5038,7 +5038,7 @@ bad:
return;
}
-static struct ceph_connection *con_get(struct ceph_connection *con)
+static struct ceph_connection *mds_get_con(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
@@ -5047,7 +5047,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con)
return NULL;
}
-static void con_put(struct ceph_connection *con)
+static void mds_put_con(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
@@ -5058,7 +5058,7 @@ static void con_put(struct ceph_connection *con)
* if the client is unresponsive for long enough, the mds will kill
* the session entirely.
*/
-static void peer_reset(struct ceph_connection *con)
+static void mds_peer_reset(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5067,7 +5067,7 @@ static void peer_reset(struct ceph_connection *con)
send_mds_reconnect(mdsc, s);
}
-static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
+static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5125,8 +5125,8 @@ out:
* Note: returned pointer is the address of a structure that's
* managed separately. Caller must *not* attempt to free it.
*/
-static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
- int *proto, int force_new)
+static struct ceph_auth_handshake *
+mds_get_authorizer(struct ceph_connection *con, int *proto, int force_new)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5142,7 +5142,7 @@ static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
return auth;
}
-static int add_authorizer_challenge(struct ceph_connection *con,
+static int mds_add_authorizer_challenge(struct ceph_connection *con,
void *challenge_buf, int challenge_buf_len)
{
struct ceph_mds_session *s = con->private;
@@ -5153,7 +5153,7 @@ static int add_authorizer_challenge(struct ceph_connection *con,
challenge_buf, challenge_buf_len);
}
-static int verify_authorizer_reply(struct ceph_connection *con)
+static int mds_verify_authorizer_reply(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5165,7 +5165,7 @@ static int verify_authorizer_reply(struct ceph_connection *con)
NULL, NULL, NULL, NULL);
}
-static int invalidate_authorizer(struct ceph_connection *con)
+static int mds_invalidate_authorizer(struct ceph_connection *con)
{
struct ceph_mds_session *s = con->private;
struct ceph_mds_client *mdsc = s->s_mdsc;
@@ -5288,15 +5288,15 @@ static int mds_check_message_signature(struct ceph_msg *msg)
}
static const struct ceph_connection_operations mds_con_ops = {
- .get = con_get,
- .put = con_put,
- .dispatch = dispatch,
- .get_authorizer = get_authorizer,
- .add_authorizer_challenge = add_authorizer_challenge,
- .verify_authorizer_reply = verify_authorizer_reply,
- .invalidate_authorizer = invalidate_authorizer,
- .peer_reset = peer_reset,
+ .get = mds_get_con,
+ .put = mds_put_con,
.alloc_msg = mds_alloc_msg,
+ .dispatch = mds_dispatch,
+ .peer_reset = mds_peer_reset,
+ .get_authorizer = mds_get_authorizer,
+ .add_authorizer_challenge = mds_add_authorizer_challenge,
+ .verify_authorizer_reply = mds_verify_authorizer_reply,
+ .invalidate_authorizer = mds_invalidate_authorizer,
.sign_message = mds_sign_message,
.check_message_signature = mds_check_message_signature,
.get_auth_request = mds_get_auth_request,
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index e4c6ae47a796..6b1ce4efb591 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -133,8 +133,9 @@ cifs_build_devname(char *nodename, const char *prepath)
* Caller is responsible for freeing returned value if it is not error.
*/
char *cifs_compose_mount_options(const char *sb_mountdata,
- const char *fullpath,
- const struct dfs_info3_param *ref)
+ const char *fullpath,
+ const struct dfs_info3_param *ref,
+ char **devname)
{
int rc;
char *name;
@@ -231,7 +232,10 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
strcat(mountdata, "ip=");
strcat(mountdata, srvIP);
- kfree(name);
+ if (devname)
+ *devname = name;
+ else
+ kfree(name);
/*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/
/*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/
@@ -278,7 +282,7 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt,
/* strip first '\' from fullpath */
mountdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options,
- fullpath + 1, NULL);
+ fullpath + 1, NULL, NULL);
if (IS_ERR(mountdata)) {
kfree(devname);
return (struct vfsmount *)mountdata;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index ce0d0037fd0a..e46da536ed33 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -822,7 +822,7 @@ cifs_smb3_do_mount(struct file_system_type *fs_type,
goto out;
}
- rc = cifs_setup_volume_info(cifs_sb->ctx);
+ rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC);
if (rc) {
root = ERR_PTR(rc);
goto out;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 340ff81ee87b..32f7a013402e 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -78,7 +78,8 @@ extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx,
int add_treename);
extern char *build_wildcard_path_from_dentry(struct dentry *direntry);
extern char *cifs_compose_mount_options(const char *sb_mountdata,
- const char *fullpath, const struct dfs_info3_param *ref);
+ const char *fullpath, const struct dfs_info3_param *ref,
+ char **devname);
/* extern void renew_parental_timestamps(struct dentry *direntry);*/
extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
struct TCP_Server_Info *server);
@@ -89,6 +90,7 @@ extern void cifs_wake_up_task(struct mid_q_entry *mid);
extern int cifs_handle_standard(struct TCP_Server_Info *server,
struct mid_q_entry *mid);
extern int smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx);
+extern int smb3_parse_opt(const char *options, const char *key, char **val);
extern bool cifs_match_ipaddr(struct sockaddr *srcaddr, struct sockaddr *rhs);
extern int cifs_discard_remaining_data(struct TCP_Server_Info *server);
extern int cifs_call_async(struct TCP_Server_Info *server,
@@ -549,7 +551,7 @@ extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8,
unsigned char *p24);
extern int
-cifs_setup_volume_info(struct smb3_fs_context *ctx);
+cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname);
extern struct TCP_Server_Info *
cifs_find_tcp_session(struct smb3_fs_context *ctx);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5d39129406ea..10fe6d6d2dee 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2195,7 +2195,7 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING)
tcon->nohandlecache = ctx->nohandlecache;
else
- tcon->nohandlecache = 1;
+ tcon->nohandlecache = true;
tcon->nodelete = ctx->nodelete;
tcon->local_lease = ctx->local_lease;
INIT_LIST_HEAD(&tcon->pending_opens);
@@ -2628,7 +2628,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
} else if (ctx)
tcon->unix_ext = 1; /* Unix Extensions supported */
- if (tcon->unix_ext == 0) {
+ if (!tcon->unix_ext) {
cifs_dbg(FYI, "Unix extensions disabled so not set on reconnect\n");
return;
}
@@ -2972,17 +2972,20 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses,
rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb),
ref_path, &referral, NULL);
if (!rc) {
+ char *fake_devname = NULL;
+
mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options,
- full_path + 1, &referral);
+ full_path + 1, &referral,
+ &fake_devname);
free_dfs_info_param(&referral);
if (IS_ERR(mdata)) {
rc = PTR_ERR(mdata);
mdata = NULL;
} else {
- smb3_cleanup_fs_context_contents(ctx);
- rc = cifs_setup_volume_info(ctx);
+ rc = cifs_setup_volume_info(ctx, mdata, fake_devname);
}
+ kfree(fake_devname);
kfree(cifs_sb->ctx->mount_options);
cifs_sb->ctx->mount_options = mdata;
}
@@ -3036,6 +3039,7 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path,
struct dfs_info3_param ref = {0};
char *mdata = NULL;
struct smb3_fs_context fake_ctx = {NULL};
+ char *fake_devname = NULL;
cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path);
@@ -3044,16 +3048,18 @@ static int setup_dfs_tgt_conn(const char *path, const char *full_path,
return rc;
mdata = cifs_compose_mount_options(cifs_sb->ctx->mount_options,
- full_path + 1, &ref);
+ full_path + 1, &ref,
+ &fake_devname);
free_dfs_info_param(&ref);
if (IS_ERR(mdata)) {
rc = PTR_ERR(mdata);
mdata = NULL;
} else
- rc = cifs_setup_volume_info(&fake_ctx);
+ rc = cifs_setup_volume_info(&fake_ctx, mdata, fake_devname);
kfree(mdata);
+ kfree(fake_devname);
if (!rc) {
/*
@@ -3122,10 +3128,24 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_
* we should pass a clone of the original context?
*/
int
-cifs_setup_volume_info(struct smb3_fs_context *ctx)
+cifs_setup_volume_info(struct smb3_fs_context *ctx, const char *mntopts, const char *devname)
{
int rc = 0;
+ smb3_parse_devname(devname, ctx);
+
+ if (mntopts) {
+ char *ip;
+
+ cifs_dbg(FYI, "%s: mntopts=%s\n", __func__, mntopts);
+ rc = smb3_parse_opt(mntopts, "ip", &ip);
+ if (!rc && !cifs_convert_address((struct sockaddr *)&ctx->dstaddr, ip,
+ strlen(ip))) {
+ cifs_dbg(VFS, "%s: failed to convert ip address\n", __func__);
+ return -EINVAL;
+ }
+ }
+
if (ctx->nullauth) {
cifs_dbg(FYI, "Anonymous login\n");
kfree(ctx->username);
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 0fdb0de7ff86..4950ab0486ae 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1417,7 +1417,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi,
int rc;
struct cache_entry *ce;
struct dfs_info3_param ref = {0};
- char *mdata = NULL;
+ char *mdata = NULL, *devname = NULL;
struct TCP_Server_Info *server;
struct cifs_ses *ses;
struct smb3_fs_context ctx = {NULL};
@@ -1444,7 +1444,8 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi,
up_read(&htable_rw_lock);
- mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref);
+ mdata = cifs_compose_mount_options(vi->mntdata, rpath, &ref,
+ &devname);
free_dfs_info_param(&ref);
if (IS_ERR(mdata)) {
@@ -1453,7 +1454,7 @@ static struct cifs_ses *find_root_ses(struct vol_info *vi,
goto out;
}
- rc = cifs_setup_volume_info(&ctx);
+ rc = cifs_setup_volume_info(&ctx, NULL, devname);
if (rc) {
ses = ERR_PTR(rc);
@@ -1472,6 +1473,7 @@ out:
smb3_cleanup_fs_context_contents(&ctx);
kfree(mdata);
kfree(rpath);
+ kfree(devname);
return ses;
}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 68900f1629bf..97ac363b5df1 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -737,6 +737,7 @@ static int
cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
{
struct inode *inode;
+ int rc;
if (flags & LOOKUP_RCU)
return -ECHILD;
@@ -746,8 +747,25 @@ cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
if ((flags & LOOKUP_REVAL) && !CIFS_CACHE_READ(CIFS_I(inode)))
CIFS_I(inode)->time = 0; /* force reval */
- if (cifs_revalidate_dentry(direntry))
- return 0;
+ rc = cifs_revalidate_dentry(direntry);
+ if (rc) {
+ cifs_dbg(FYI, "cifs_revalidate_dentry failed with rc=%d", rc);
+ switch (rc) {
+ case -ENOENT:
+ case -ESTALE:
+ /*
+ * Those errors mean the dentry is invalid
+ * (file was deleted or recreated)
+ */
+ return 0;
+ default:
+ /*
+ * Otherwise some unexpected error happened
+ * report it as-is to VFS layer
+ */
+ return rc;
+ }
+ }
else {
/*
* If the inode wasn't known to be a dfs entry when
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 076bcadc756a..5111aadfdb6b 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -175,8 +175,10 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
fsparam_flag_no("exec", Opt_ignore),
fsparam_flag_no("dev", Opt_ignore),
fsparam_flag_no("mand", Opt_ignore),
+ fsparam_flag_no("auto", Opt_ignore),
fsparam_string("cred", Opt_ignore),
fsparam_string("credentials", Opt_ignore),
+ fsparam_string("prefixpath", Opt_ignore),
{}
};
@@ -399,6 +401,37 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
return 0;
}
+int smb3_parse_opt(const char *options, const char *key, char **val)
+{
+ int rc = -ENOENT;
+ char *opts, *orig, *p;
+
+ orig = opts = kstrdup(options, GFP_KERNEL);
+ if (!opts)
+ return -ENOMEM;
+
+ while ((p = strsep(&opts, ","))) {
+ char *nval;
+
+ if (!*p)
+ continue;
+ if (strncasecmp(p, key, strlen(key)))
+ continue;
+ nval = strchr(p, '=');
+ if (nval) {
+ if (nval == p)
+ continue;
+ *nval++ = 0;
+ *val = kstrndup(nval, strlen(nval), GFP_KERNEL);
+ rc = !*val ? -ENOMEM : 0;
+ goto out;
+ }
+ }
+out:
+ kfree(orig);
+ return rc;
+}
+
/*
* Parse a devname into substrings and populate the ctx->UNC and ctx->prepath
* fields with the result. Returns 0 on success and an error otherwise
@@ -531,7 +564,7 @@ static int smb3_fs_context_validate(struct fs_context *fc)
if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) {
cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n");
- return -1;
+ return -EOPNOTSUPP;
}
#ifndef CONFIG_KEYS
@@ -554,7 +587,7 @@ static int smb3_fs_context_validate(struct fs_context *fc)
/* make sure UNC has a share name */
if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) {
cifs_dbg(VFS, "Malformed UNC. Unable to find share name.\n");
- return -1;
+ return -ENOENT;
}
if (!ctx->got_ip) {
@@ -568,7 +601,7 @@ static int smb3_fs_context_validate(struct fs_context *fc)
if (!cifs_convert_address((struct sockaddr *)&ctx->dstaddr,
&ctx->UNC[2], len)) {
pr_err("Unable to determine destination address\n");
- return -1;
+ return -EHOSTUNREACH;
}
}
@@ -1263,7 +1296,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
return 0;
cifs_parse_mount_err:
- return 1;
+ return -EINVAL;
}
int smb3_init_fs_context(struct fs_context *fc)
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index d85edf5d1429..a5a9e33c0d73 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -286,7 +286,7 @@ struct smb2_negotiate_req {
__le32 NegotiateContextOffset; /* SMB3.1.1 only. MBZ earlier */
__le16 NegotiateContextCount; /* SMB3.1.1 only. MBZ earlier */
__le16 Reserved2;
- __le16 Dialects[1]; /* One dialect (vers=) at a time for now */
+ __le16 Dialects[4]; /* BB expand this if autonegotiate > 4 dialects */
} __packed;
/* Dialects */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index e9abb41aa89b..4a2b836eb017 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -338,7 +338,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
if (ssocket == NULL)
return -EAGAIN;
- if (signal_pending(current)) {
+ if (fatal_signal_pending(current)) {
cifs_dbg(FYI, "signal pending before send request\n");
return -ERESTARTSYS;
}
@@ -429,7 +429,7 @@ unmask:
if (signal_pending(current) && (total_len != send_length)) {
cifs_dbg(FYI, "signal is pending after attempt to send\n");
- rc = -EINTR;
+ rc = -ERESTARTSYS;
}
/* uncork it */
@@ -666,10 +666,22 @@ wait_for_compound_request(struct TCP_Server_Info *server, int num,
if (*credits < num) {
/*
- * Return immediately if not too many requests in flight since
- * we will likely be stuck on waiting for credits.
+ * If the server is tight on resources or just gives us less
+ * credits for other reasons (e.g. requests are coming out of
+ * order and the server delays granting more credits until it
+ * processes a missing mid) and we exhausted most available
+ * credits there may be situations when we try to send
+ * a compound request but we don't have enough credits. At this
+ * point the client needs to decide if it should wait for
+ * additional credits or fail the request. If at least one
+ * request is in flight there is a high probability that the
+ * server will return enough credits to satisfy this compound
+ * request.
+ *
+ * Return immediately if no requests in flight since we will be
+ * stuck on waiting for credits.
*/
- if (server->in_flight < num - *credits) {
+ if (server->in_flight == 0) {
spin_unlock(&server->req_lock);
trace_smb3_insufficient_credits(server->CurrentMid,
server->hostname, scredits, sin_flight);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e23752d9a79f..58d0f7187997 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1016,15 +1016,19 @@ ecryptfs_setxattr(struct dentry *dentry, struct inode *inode,
{
int rc;
struct dentry *lower_dentry;
+ struct inode *lower_inode;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
- if (!(d_inode(lower_dentry)->i_opflags & IOP_XATTR)) {
+ lower_inode = d_inode(lower_dentry);
+ if (!(lower_inode->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
- rc = vfs_setxattr(lower_dentry, name, value, size, flags);
+ inode_lock(lower_inode);
+ rc = __vfs_setxattr_locked(lower_dentry, name, value, size, flags, NULL);
+ inode_unlock(lower_inode);
if (!rc && inode)
- fsstack_copy_attr_all(inode, d_inode(lower_dentry));
+ fsstack_copy_attr_all(inode, lower_inode);
out:
return rc;
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index acfb55834af2..c41cb887eb7d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1474,21 +1474,25 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
}
/*
- * Some filesystems may redirty the inode during the writeback
- * due to delalloc, clear dirty metadata flags right before
- * write_inode()
+ * If the inode has dirty timestamps and we need to write them, call
+ * mark_inode_dirty_sync() to notify the filesystem about it and to
+ * change I_DIRTY_TIME into I_DIRTY_SYNC.
*/
- spin_lock(&inode->i_lock);
-
- dirty = inode->i_state & I_DIRTY;
if ((inode->i_state & I_DIRTY_TIME) &&
- ((dirty & I_DIRTY_INODE) ||
- wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
+ (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync ||
time_after(jiffies, inode->dirtied_time_when +
dirtytime_expire_interval * HZ))) {
- dirty |= I_DIRTY_TIME;
trace_writeback_lazytime(inode);
+ mark_inode_dirty_sync(inode);
}
+
+ /*
+ * Some filesystems may redirty the inode during the writeback
+ * due to delalloc, clear dirty metadata flags right before
+ * write_inode()
+ */
+ spin_lock(&inode->i_lock);
+ dirty = inode->i_state & I_DIRTY;
inode->i_state &= ~dirty;
/*
@@ -1509,8 +1513,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
spin_unlock(&inode->i_lock);
- if (dirty & I_DIRTY_TIME)
- mark_inode_dirty_sync(inode);
/* Don't write the inode if only I_DIRTY_PAGES was set */
if (dirty & ~I_DIRTY_PAGES) {
int err = write_inode(inode, wbc);
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b5c109703daa..21c20fd5f9ee 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -735,9 +735,10 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ set_page_huge_active(page);
/*
* unlock_page because locked by add_to_page_cache()
- * page_put due to reference from alloc_huge_page()
+ * put_page() due to reference from alloc_huge_page()
*/
unlock_page(page);
put_page(page);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 985a9e3f976d..1f68105a41ed 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1025,6 +1025,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req,
static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
const struct iovec *fast_iov,
struct iov_iter *iter, bool force);
+static void io_req_drop_files(struct io_kiocb *req);
+static void io_req_task_queue(struct io_kiocb *req);
static struct kmem_cache *req_cachep;
@@ -1048,8 +1050,7 @@ EXPORT_SYMBOL(io_uring_get_socket);
static inline void io_clean_op(struct io_kiocb *req)
{
- if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED |
- REQ_F_INFLIGHT))
+ if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED))
__io_clean_op(req);
}
@@ -1069,14 +1070,21 @@ static bool io_match_task(struct io_kiocb *head,
{
struct io_kiocb *req;
- if (task && head->task != task)
+ if (task && head->task != task) {
+ /* in terms of cancelation, always match if req task is dead */
+ if (head->task->flags & PF_EXITING)
+ return true;
return false;
+ }
if (!files)
return true;
io_for_each_link(req, head) {
- if ((req->flags & REQ_F_WORK_INITIALIZED) &&
- (req->work.flags & IO_WQ_WORK_FILES) &&
+ if (!(req->flags & REQ_F_WORK_INITIALIZED))
+ continue;
+ if (req->file && req->file->f_op == &io_uring_fops)
+ return true;
+ if ((req->work.flags & IO_WQ_WORK_FILES) &&
req->work.identity->files == files)
return true;
}
@@ -1394,6 +1402,8 @@ static void io_req_clean_work(struct io_kiocb *req)
free_fs_struct(fs);
req->work.flags &= ~IO_WQ_WORK_FS;
}
+ if (req->flags & REQ_F_INFLIGHT)
+ io_req_drop_files(req);
io_put_identity(req->task->io_uring, req);
}
@@ -1503,11 +1513,14 @@ static bool io_grab_identity(struct io_kiocb *req)
return false;
atomic_inc(&id->files->count);
get_nsproxy(id->nsproxy);
- req->flags |= REQ_F_INFLIGHT;
- spin_lock_irq(&ctx->inflight_lock);
- list_add(&req->inflight_entry, &ctx->inflight_list);
- spin_unlock_irq(&ctx->inflight_lock);
+ if (!(req->flags & REQ_F_INFLIGHT)) {
+ req->flags |= REQ_F_INFLIGHT;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_add(&req->inflight_entry, &ctx->inflight_list);
+ spin_unlock_irq(&ctx->inflight_lock);
+ }
req->work.flags |= IO_WQ_WORK_FILES;
}
if (!(req->work.flags & IO_WQ_WORK_MM) &&
@@ -1622,18 +1635,11 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx)
do {
struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
struct io_defer_entry, list);
- struct io_kiocb *link;
if (req_need_defer(de->req, de->seq))
break;
list_del_init(&de->list);
- /* punt-init is done before queueing for defer */
- link = __io_queue_async_work(de->req);
- if (link) {
- __io_queue_linked_timeout(link);
- /* drop submission reference */
- io_put_req_deferred(link, 1);
- }
+ io_req_task_queue(de->req);
kfree(de);
} while (!list_empty(&ctx->defer_list));
}
@@ -1767,12 +1773,13 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
struct io_kiocb *req, *tmp;
struct io_uring_cqe *cqe;
unsigned long flags;
- bool all_flushed;
+ bool all_flushed, posted;
LIST_HEAD(list);
if (!force && __io_cqring_events(ctx) == rings->cq_ring_entries)
return false;
+ posted = false;
spin_lock_irqsave(&ctx->completion_lock, flags);
list_for_each_entry_safe(req, tmp, &ctx->cq_overflow_list, compl.list) {
if (!io_match_task(req, tsk, files))
@@ -1792,6 +1799,7 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
WRITE_ONCE(ctx->rings->cq_overflow,
ctx->cached_cq_overflow);
}
+ posted = true;
}
all_flushed = list_empty(&ctx->cq_overflow_list);
@@ -1801,9 +1809,11 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force,
ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW;
}
- io_commit_cqring(ctx);
+ if (posted)
+ io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
- io_cqring_ev_posted(ctx);
+ if (posted)
+ io_cqring_ev_posted(ctx);
while (!list_empty(&list)) {
req = list_first_entry(&list, struct io_kiocb, compl.list);
@@ -2195,6 +2205,9 @@ static void __io_req_task_submit(struct io_kiocb *req)
else
__io_req_task_cancel(req, -EFAULT);
mutex_unlock(&ctx->uring_lock);
+
+ if (ctx->flags & IORING_SETUP_SQPOLL)
+ io_sq_thread_drop_mm_files();
}
static void io_req_task_submit(struct callback_head *cb)
@@ -2270,6 +2283,8 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
struct io_uring_task *tctx = rb->task->io_uring;
percpu_counter_sub(&tctx->inflight, rb->task_refs);
+ if (atomic_read(&tctx->in_idle))
+ wake_up(&tctx->wait);
put_task_struct_many(rb->task, rb->task_refs);
rb->task = NULL;
}
@@ -2288,6 +2303,8 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
struct io_uring_task *tctx = rb->task->io_uring;
percpu_counter_sub(&tctx->inflight, rb->task_refs);
+ if (atomic_read(&tctx->in_idle))
+ wake_up(&tctx->wait);
put_task_struct_many(rb->task, rb->task_refs);
}
rb->task = req->task;
@@ -3548,7 +3565,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock,
/* read it all, or we did blocking attempt. no retry. */
if (!iov_iter_count(iter) || !force_nonblock ||
- (req->file->f_flags & O_NONBLOCK))
+ (req->file->f_flags & O_NONBLOCK) || !(req->flags & REQ_F_ISREG))
goto done;
io_size -= ret;
@@ -4468,7 +4485,6 @@ static int io_close_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
* io_wq_work.flags, so initialize io_wq_work firstly.
*/
io_req_init_async(req);
- req->work.flags |= IO_WQ_WORK_NO_CANCEL;
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
@@ -4501,6 +4517,8 @@ static int io_close(struct io_kiocb *req, bool force_nonblock,
/* if the file has a flush method, be safe and punt to async */
if (close->put_file->f_op->flush && force_nonblock) {
+ /* not safe to cancel at this point */
+ req->work.flags |= IO_WQ_WORK_NO_CANCEL;
/* was never set, but play safe */
req->flags &= ~REQ_F_NOWAIT;
/* avoid grabbing files - we don't need the files */
@@ -6157,8 +6175,10 @@ static void io_req_drop_files(struct io_kiocb *req)
struct io_uring_task *tctx = req->task->io_uring;
unsigned long flags;
- put_files_struct(req->work.identity->files);
- put_nsproxy(req->work.identity->nsproxy);
+ if (req->work.flags & IO_WQ_WORK_FILES) {
+ put_files_struct(req->work.identity->files);
+ put_nsproxy(req->work.identity->nsproxy);
+ }
spin_lock_irqsave(&ctx->inflight_lock, flags);
list_del(&req->inflight_entry);
spin_unlock_irqrestore(&ctx->inflight_lock, flags);
@@ -6225,9 +6245,6 @@ static void __io_clean_op(struct io_kiocb *req)
}
req->flags &= ~REQ_F_NEED_CLEANUP;
}
-
- if (req->flags & REQ_F_INFLIGHT)
- io_req_drop_files(req);
}
static int io_issue_sqe(struct io_kiocb *req, bool force_nonblock,
@@ -6446,6 +6463,16 @@ static struct file *io_file_get(struct io_submit_state *state,
file = __io_file_get(state, fd);
}
+ if (file && file->f_op == &io_uring_fops &&
+ !(req->flags & REQ_F_INFLIGHT)) {
+ io_req_init_async(req);
+ req->flags |= REQ_F_INFLIGHT;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_add(&req->inflight_entry, &ctx->inflight_list);
+ spin_unlock_irq(&ctx->inflight_lock);
+ }
+
return file;
}
@@ -7245,14 +7272,18 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
TASK_INTERRUPTIBLE);
/* make sure we run task_work before checking for signals */
ret = io_run_task_work_sig();
- if (ret > 0)
+ if (ret > 0) {
+ finish_wait(&ctx->wait, &iowq.wq);
continue;
+ }
else if (ret < 0)
break;
if (io_should_wake(&iowq))
break;
- if (test_bit(0, &ctx->cq_check_overflow))
+ if (test_bit(0, &ctx->cq_check_overflow)) {
+ finish_wait(&ctx->wait, &iowq.wq);
continue;
+ }
if (uts) {
timeout = schedule_timeout(timeout);
if (timeout == 0) {
@@ -8844,39 +8875,44 @@ static void io_cancel_defer_files(struct io_ring_ctx *ctx,
}
}
+static int io_uring_count_inflight(struct io_ring_ctx *ctx,
+ struct task_struct *task,
+ struct files_struct *files)
+{
+ struct io_kiocb *req;
+ int cnt = 0;
+
+ spin_lock_irq(&ctx->inflight_lock);
+ list_for_each_entry(req, &ctx->inflight_list, inflight_entry)
+ cnt += io_match_task(req, task, files);
+ spin_unlock_irq(&ctx->inflight_lock);
+ return cnt;
+}
+
static void io_uring_cancel_files(struct io_ring_ctx *ctx,
struct task_struct *task,
struct files_struct *files)
{
while (!list_empty_careful(&ctx->inflight_list)) {
struct io_task_cancel cancel = { .task = task, .files = files };
- struct io_kiocb *req;
DEFINE_WAIT(wait);
- bool found = false;
-
- spin_lock_irq(&ctx->inflight_lock);
- list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
- if (req->task != task ||
- req->work.identity->files != files)
- continue;
- found = true;
- break;
- }
- if (found)
- prepare_to_wait(&task->io_uring->wait, &wait,
- TASK_UNINTERRUPTIBLE);
- spin_unlock_irq(&ctx->inflight_lock);
+ int inflight;
- /* We need to keep going until we don't find a matching req */
- if (!found)
+ inflight = io_uring_count_inflight(ctx, task, files);
+ if (!inflight)
break;
io_wq_cancel_cb(ctx->io_wq, io_cancel_task_cb, &cancel, true);
io_poll_remove_all(ctx, task, files);
io_kill_timeouts(ctx, task, files);
+ io_cqring_overflow_flush(ctx, true, task, files);
/* cancellations _may_ trigger task work */
io_run_task_work();
- schedule();
+
+ prepare_to_wait(&task->io_uring->wait, &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (inflight == io_uring_count_inflight(ctx, task, files))
+ schedule();
finish_wait(&task->io_uring->wait, &wait);
}
}
@@ -8914,8 +8950,6 @@ static void __io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
static void io_disable_sqo_submit(struct io_ring_ctx *ctx)
{
- WARN_ON_ONCE(ctx->sqo_task != current);
-
mutex_lock(&ctx->uring_lock);
ctx->sqo_dead = 1;
mutex_unlock(&ctx->uring_lock);
@@ -8936,7 +8970,6 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
struct task_struct *task = current;
if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
- /* for SQPOLL only sqo_task has task notes */
io_disable_sqo_submit(ctx);
task = ctx->sq_data->thread;
atomic_inc(&task->io_uring->in_idle);
@@ -8946,19 +8979,12 @@ static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
io_cancel_defer_files(ctx, task, files);
io_cqring_overflow_flush(ctx, true, task, files);
+ io_uring_cancel_files(ctx, task, files);
if (!files)
__io_uring_cancel_task_requests(ctx, task);
- else
- io_uring_cancel_files(ctx, task, files);
if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
atomic_dec(&task->io_uring->in_idle);
- /*
- * If the files that are going away are the ones in the thread
- * identity, clear them out.
- */
- if (task->io_uring->identity->files == files)
- task->io_uring->identity->files = NULL;
io_sq_thread_unpark(ctx->sq_data);
}
}
@@ -9082,6 +9108,10 @@ void __io_uring_task_cancel(void)
/* make sure overflow events are dropped */
atomic_inc(&tctx->in_idle);
+ /* trigger io_disable_sqo_submit() */
+ if (tctx->sqpoll)
+ __io_uring_files_cancel(NULL);
+
do {
/* read completions before cancelations */
inflight = tctx_inflight(tctx);
@@ -9092,16 +9122,15 @@ void __io_uring_task_cancel(void)
prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
/*
- * If we've seen completions, retry. This avoids a race where
- * a completion comes in before we did prepare_to_wait().
+ * If we've seen completions, retry without waiting. This
+ * avoids a race where a completion comes in before we did
+ * prepare_to_wait().
*/
- if (inflight != tctx_inflight(tctx))
- continue;
- schedule();
+ if (inflight == tctx_inflight(tctx))
+ schedule();
finish_wait(&tctx->wait, &wait);
} while (1);
- finish_wait(&tctx->wait, &wait);
atomic_dec(&tctx->in_idle);
io_uring_remove_task_files(tctx);
@@ -9112,6 +9141,9 @@ static int io_uring_flush(struct file *file, void *data)
struct io_uring_task *tctx = current->io_uring;
struct io_ring_ctx *ctx = file->private_data;
+ if (fatal_signal_pending(current) || (current->flags & PF_EXITING))
+ io_uring_cancel_task_requests(ctx, NULL);
+
if (!tctx)
return 0;
@@ -9128,7 +9160,10 @@ static int io_uring_flush(struct file *file, void *data)
if (ctx->flags & IORING_SETUP_SQPOLL) {
/* there is only one file note, which is owned by sqo_task */
- WARN_ON_ONCE((ctx->sqo_task == current) ==
+ WARN_ON_ONCE(ctx->sqo_task != current &&
+ xa_load(&tctx->xa, (unsigned long)file));
+ /* sqo_dead check is for when this happens after cancellation */
+ WARN_ON_ONCE(ctx->sqo_task == current && !ctx->sqo_dead &&
!xa_load(&tctx->xa, (unsigned long)file));
io_disable_sqo_submit(ctx);
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index f277d023ebcd..c75719312147 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -14,6 +14,7 @@
#include <linux/pagemap.h>
#include <linux/sched/mm.h>
#include <linux/fsnotify.h>
+#include <linux/uio.h>
#include "kernfs-internal.h"
@@ -180,11 +181,10 @@ static const struct seq_operations kernfs_seq_ops = {
* it difficult to use seq_file. Implement simplistic custom buffering for
* bin files.
*/
-static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
- char __user *user_buf, size_t count,
- loff_t *ppos)
+static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
- ssize_t len = min_t(size_t, count, PAGE_SIZE);
+ struct kernfs_open_file *of = kernfs_of(iocb->ki_filp);
+ ssize_t len = min_t(size_t, iov_iter_count(iter), PAGE_SIZE);
const struct kernfs_ops *ops;
char *buf;
@@ -210,7 +210,7 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
of->event = atomic_read(&of->kn->attr.open->event);
ops = kernfs_ops(of->kn);
if (ops->read)
- len = ops->read(of, buf, len, *ppos);
+ len = ops->read(of, buf, len, iocb->ki_pos);
else
len = -EINVAL;
@@ -220,12 +220,12 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
if (len < 0)
goto out_free;
- if (copy_to_user(user_buf, buf, len)) {
+ if (copy_to_iter(buf, len, iter) != len) {
len = -EFAULT;
goto out_free;
}
- *ppos += len;
+ iocb->ki_pos += len;
out_free:
if (buf == of->prealloc_buf)
@@ -235,31 +235,14 @@ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of,
return len;
}
-/**
- * kernfs_fop_read - kernfs vfs read callback
- * @file: file pointer
- * @user_buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
- */
-static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
- size_t count, loff_t *ppos)
+static ssize_t kernfs_fop_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
- struct kernfs_open_file *of = kernfs_of(file);
-
- if (of->kn->flags & KERNFS_HAS_SEQ_SHOW)
- return seq_read(file, user_buf, count, ppos);
- else
- return kernfs_file_direct_read(of, user_buf, count, ppos);
+ if (kernfs_of(iocb->ki_filp)->kn->flags & KERNFS_HAS_SEQ_SHOW)
+ return seq_read_iter(iocb, iter);
+ return kernfs_file_read_iter(iocb, iter);
}
-/**
- * kernfs_fop_write - kernfs vfs write callback
- * @file: file pointer
- * @user_buf: data to write
- * @count: number of bytes
- * @ppos: starting offset
- *
+/*
* Copy data in from userland and pass it to the matching kernfs write
* operation.
*
@@ -269,20 +252,18 @@ static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf,
* modify only the the value you're changing, then write entire buffer
* back.
*/
-static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
- size_t count, loff_t *ppos)
+static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter)
{
- struct kernfs_open_file *of = kernfs_of(file);
+ struct kernfs_open_file *of = kernfs_of(iocb->ki_filp);
+ ssize_t len = iov_iter_count(iter);
const struct kernfs_ops *ops;
- ssize_t len;
char *buf;
if (of->atomic_write_len) {
- len = count;
if (len > of->atomic_write_len)
return -E2BIG;
} else {
- len = min_t(size_t, count, PAGE_SIZE);
+ len = min_t(size_t, len, PAGE_SIZE);
}
buf = of->prealloc_buf;
@@ -293,7 +274,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
if (!buf)
return -ENOMEM;
- if (copy_from_user(buf, user_buf, len)) {
+ if (copy_from_iter(buf, len, iter) != len) {
len = -EFAULT;
goto out_free;
}
@@ -312,7 +293,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
ops = kernfs_ops(of->kn);
if (ops->write)
- len = ops->write(of, buf, len, *ppos);
+ len = ops->write(of, buf, len, iocb->ki_pos);
else
len = -EINVAL;
@@ -320,7 +301,7 @@ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf,
mutex_unlock(&of->mutex);
if (len > 0)
- *ppos += len;
+ iocb->ki_pos += len;
out_free:
if (buf == of->prealloc_buf)
@@ -673,7 +654,7 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
/*
* Write path needs to atomic_write_len outside active reference.
- * Cache it in open_file. See kernfs_fop_write() for details.
+ * Cache it in open_file. See kernfs_fop_write_iter() for details.
*/
of->atomic_write_len = ops->atomic_write_len;
@@ -960,14 +941,16 @@ void kernfs_notify(struct kernfs_node *kn)
EXPORT_SYMBOL_GPL(kernfs_notify);
const struct file_operations kernfs_file_fops = {
- .read = kernfs_fop_read,
- .write = kernfs_fop_write,
+ .read_iter = kernfs_fop_read_iter,
+ .write_iter = kernfs_fop_write_iter,
.llseek = generic_file_llseek,
.mmap = kernfs_fop_mmap,
.open = kernfs_fop_open,
.release = kernfs_fop_release,
.poll = kernfs_fop_poll,
.fsync = noop_fsync,
+ .splice_read = generic_file_splice_read,
+ .splice_write = iter_file_splice_write,
};
/**
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 4f274f21c4ab..af64b4e6fd1f 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -324,6 +324,21 @@ pnfs_grab_inode_layout_hdr(struct pnfs_layout_hdr *lo)
return NULL;
}
+/*
+ * Compare 2 layout stateid sequence ids, to see which is newer,
+ * taking into account wraparound issues.
+ */
+static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
+{
+ return (s32)(s1 - s2) > 0;
+}
+
+static void pnfs_barrier_update(struct pnfs_layout_hdr *lo, u32 newseq)
+{
+ if (pnfs_seqid_is_newer(newseq, lo->plh_barrier))
+ lo->plh_barrier = newseq;
+}
+
static void
pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
u32 seq)
@@ -335,6 +350,7 @@ pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
if (seq != 0) {
WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq);
lo->plh_return_seq = seq;
+ pnfs_barrier_update(lo, seq);
}
}
@@ -639,15 +655,6 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
return rv;
}
-/*
- * Compare 2 layout stateid sequence ids, to see which is newer,
- * taking into account wraparound issues.
- */
-static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
-{
- return (s32)(s1 - s2) > 0;
-}
-
static bool
pnfs_should_free_range(const struct pnfs_layout_range *lseg_range,
const struct pnfs_layout_range *recall_range)
@@ -984,8 +991,7 @@ pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
new_barrier = be32_to_cpu(new->seqid);
else if (new_barrier == 0)
return;
- if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
- lo->plh_barrier = new_barrier;
+ pnfs_barrier_update(lo, new_barrier);
}
static bool
@@ -994,7 +1000,7 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
{
u32 seqid = be32_to_cpu(stateid->seqid);
- return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
+ return !pnfs_seqid_is_newer(seqid, lo->plh_barrier) && lo->plh_barrier;
}
/* lget is set to 1 if called from inside send_layoutget call chain */
@@ -1183,20 +1189,17 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
return false;
set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
pnfs_get_layout_hdr(lo);
+ nfs4_stateid_copy(stateid, &lo->plh_stateid);
+ *cred = get_cred(lo->plh_lc_cred);
if (test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) {
- nfs4_stateid_copy(stateid, &lo->plh_stateid);
- *cred = get_cred(lo->plh_lc_cred);
if (lo->plh_return_seq != 0)
stateid->seqid = cpu_to_be32(lo->plh_return_seq);
if (iomode != NULL)
*iomode = lo->plh_return_iomode;
pnfs_clear_layoutreturn_info(lo);
- return true;
- }
- nfs4_stateid_copy(stateid, &lo->plh_stateid);
- *cred = get_cred(lo->plh_lc_cred);
- if (iomode != NULL)
+ } else if (iomode != NULL)
*iomode = IOMODE_ANY;
+ pnfs_barrier_update(lo, be32_to_cpu(stateid->seqid));
return true;
}
@@ -1909,6 +1912,11 @@ static void nfs_layoutget_end(struct pnfs_layout_hdr *lo)
wake_up_var(&lo->plh_outstanding);
}
+static bool pnfs_is_first_layoutget(struct pnfs_layout_hdr *lo)
+{
+ return test_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags);
+}
+
static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
{
unsigned long *bitlock = &lo->plh_flags;
@@ -2383,23 +2391,34 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
goto out_forget;
}
- if (!pnfs_layout_is_valid(lo)) {
- /* We have a completely new layout */
- pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true);
- } else if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
+ if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
/* existing state ID, make sure the sequence number matches. */
if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
+ if (!pnfs_layout_is_valid(lo) &&
+ pnfs_is_first_layoutget(lo))
+ lo->plh_barrier = 0;
dprintk("%s forget reply due to sequence\n", __func__);
goto out_forget;
}
pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, false);
- } else {
+ } else if (pnfs_layout_is_valid(lo)) {
/*
* We got an entirely new state ID. Mark all segments for the
* inode invalid, and retry the layoutget
*/
- pnfs_mark_layout_stateid_invalid(lo, &free_me);
+ struct pnfs_layout_range range = {
+ .iomode = IOMODE_ANY,
+ .length = NFS4_MAX_UINT64,
+ };
+ pnfs_set_plh_return_info(lo, IOMODE_ANY, 0);
+ pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs,
+ &range, 0);
goto out_forget;
+ } else {
+ /* We have a completely new layout */
+ if (!pnfs_is_first_layoutget(lo))
+ goto out_forget;
+ pnfs_set_layout_stateid(lo, &res->stateid, lgp->cred, true);
}
pnfs_get_lseg(lseg);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 821db21ba072..34b880211e5e 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -865,9 +865,14 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
if (isdotent(name, namlen)) {
if (namlen == 2) {
dchild = dget_parent(dparent);
- /* filesystem root - cannot return filehandle for ".." */
+ /*
+ * Don't return filehandle for ".." if we're at
+ * the filesystem or export root:
+ */
if (dchild == dparent)
goto out;
+ if (dparent == exp->ex_path.dentry)
+ goto out;
} else
dchild = dget(dparent);
} else
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index e5b616c93e11..0fed532efa68 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -84,6 +84,14 @@ int ovl_copy_xattr(struct super_block *sb, struct dentry *old,
if (ovl_is_private_xattr(sb, name))
continue;
+
+ error = security_inode_copy_up_xattr(name);
+ if (error < 0 && error != -EOPNOTSUPP)
+ break;
+ if (error == 1) {
+ error = 0;
+ continue; /* Discard */
+ }
retry:
size = vfs_getxattr(old, name, value, value_size);
if (size == -ERANGE)
@@ -107,13 +115,6 @@ retry:
goto retry;
}
- error = security_inode_copy_up_xattr(name);
- if (error < 0 && error != -EOPNOTSUPP)
- break;
- if (error == 1) {
- error = 0;
- continue; /* Discard */
- }
error = vfs_setxattr(new, name, value, size, 0);
if (error) {
if (error != -EOPNOTSUPP || ovl_must_copy_xattr(name))
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 28a075b5f5b2..d1efa3a5a503 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -992,8 +992,8 @@ static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect)
buflen -= thislen;
memcpy(&buf[buflen], name, thislen);
- tmp = dget_dlock(d->d_parent);
spin_unlock(&d->d_lock);
+ tmp = dget_parent(d);
dput(d);
d = tmp;
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index bd9dd38347ae..077d3ad343f6 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -398,8 +398,9 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
const struct cred *old_cred;
int ret;
- if (!ovl_should_sync(OVL_FS(file_inode(file)->i_sb)))
- return 0;
+ ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb));
+ if (ret <= 0)
+ return ret;
ret = ovl_real_fdget_meta(file, &real, !datasync);
if (ret)
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index d739e14c6814..cf41bcb664bc 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -352,7 +352,9 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
goto out;
if (!value && !upperdentry) {
+ old_cred = ovl_override_creds(dentry->d_sb);
err = vfs_getxattr(realdentry, name, NULL, 0);
+ revert_creds(old_cred);
if (err < 0)
goto out_drop_write;
}
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b487e48c7fd4..cb4e2d60ecf9 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -324,6 +324,7 @@ int ovl_check_metacopy_xattr(struct ovl_fs *ofs, struct dentry *dentry);
bool ovl_is_metacopy_dentry(struct dentry *dentry);
char *ovl_get_redirect_xattr(struct ovl_fs *ofs, struct dentry *dentry,
int padding);
+int ovl_sync_status(struct ovl_fs *ofs);
static inline bool ovl_is_impuredir(struct super_block *sb,
struct dentry *dentry)
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index fbd5e27ce66b..63efee554f69 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -81,6 +81,8 @@ struct ovl_fs {
atomic_long_t last_ino;
/* Whiteout dentry cache */
struct dentry *whiteout;
+ /* r/o snapshot of upperdir sb's only taken on volatile mounts */
+ errseq_t errseq;
};
static inline struct vfsmount *ovl_upper_mnt(struct ovl_fs *ofs)
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 01620ebae1bd..f404a78e6b60 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -865,7 +865,7 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper)
struct ovl_dir_file *od = file->private_data;
struct dentry *dentry = file->f_path.dentry;
- struct file *realfile = od->realfile;
+ struct file *old, *realfile = od->realfile;
if (!OVL_TYPE_UPPER(ovl_path_type(dentry)))
return want_upper ? NULL : realfile;
@@ -874,29 +874,20 @@ struct file *ovl_dir_real_file(const struct file *file, bool want_upper)
* Need to check if we started out being a lower dir, but got copied up
*/
if (!od->is_upper) {
- struct inode *inode = file_inode(file);
-
realfile = READ_ONCE(od->upperfile);
if (!realfile) {
struct path upperpath;
ovl_path_upper(dentry, &upperpath);
realfile = ovl_dir_open_realfile(file, &upperpath);
+ if (IS_ERR(realfile))
+ return realfile;
- inode_lock(inode);
- if (!od->upperfile) {
- if (IS_ERR(realfile)) {
- inode_unlock(inode);
- return realfile;
- }
- smp_store_release(&od->upperfile, realfile);
- } else {
- /* somebody has beaten us to it */
- if (!IS_ERR(realfile))
- fput(realfile);
- realfile = od->upperfile;
+ old = cmpxchg_release(&od->upperfile, NULL, realfile);
+ if (old) {
+ fput(realfile);
+ realfile = old;
}
- inode_unlock(inode);
}
}
@@ -909,8 +900,9 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end,
struct file *realfile;
int err;
- if (!ovl_should_sync(OVL_FS(file->f_path.dentry->d_sb)))
- return 0;
+ err = ovl_sync_status(OVL_FS(file->f_path.dentry->d_sb));
+ if (err <= 0)
+ return err;
realfile = ovl_dir_real_file(file, true);
err = PTR_ERR_OR_ZERO(realfile);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 2bd570cbe8a4..d58b8f2bf9d0 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -264,11 +264,20 @@ static int ovl_sync_fs(struct super_block *sb, int wait)
struct super_block *upper_sb;
int ret;
- if (!ovl_upper_mnt(ofs))
- return 0;
+ ret = ovl_sync_status(ofs);
+ /*
+ * We have to always set the err, because the return value isn't
+ * checked in syncfs, and instead indirectly return an error via
+ * the sb's writeback errseq, which VFS inspects after this call.
+ */
+ if (ret < 0) {
+ errseq_set(&sb->s_wb_err, -EIO);
+ return -EIO;
+ }
+
+ if (!ret)
+ return ret;
- if (!ovl_should_sync(ofs))
- return 0;
/*
* Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC).
* All the super blocks will be iterated, including upper_sb.
@@ -1923,6 +1932,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
unsigned int numlower;
int err;
+ err = -EIO;
+ if (WARN_ON(sb->s_user_ns != current_user_ns()))
+ goto out;
+
sb->s_d_op = &ovl_dentry_operations;
err = -ENOMEM;
@@ -1989,6 +2002,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
sb->s_op = &ovl_super_operations;
if (ofs->config.upperdir) {
+ struct super_block *upper_sb;
+
if (!ofs->config.workdir) {
pr_err("missing 'workdir'\n");
goto out_err;
@@ -1998,6 +2013,16 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (err)
goto out_err;
+ upper_sb = ovl_upper_mnt(ofs)->mnt_sb;
+ if (!ovl_should_sync(ofs)) {
+ ofs->errseq = errseq_sample(&upper_sb->s_wb_err);
+ if (errseq_check(&upper_sb->s_wb_err, ofs->errseq)) {
+ err = -EIO;
+ pr_err("Cannot mount volatile when upperdir has an unseen error. Sync upperdir fs to clear state.\n");
+ goto out_err;
+ }
+ }
+
err = ovl_get_workdir(sb, ofs, &upperpath);
if (err)
goto out_err;
@@ -2005,9 +2030,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
if (!ofs->workdir)
sb->s_flags |= SB_RDONLY;
- sb->s_stack_depth = ovl_upper_mnt(ofs)->mnt_sb->s_stack_depth;
- sb->s_time_gran = ovl_upper_mnt(ofs)->mnt_sb->s_time_gran;
-
+ sb->s_stack_depth = upper_sb->s_stack_depth;
+ sb->s_time_gran = upper_sb->s_time_gran;
}
oe = ovl_get_lowerstack(sb, splitlower, numlower, ofs, layers);
err = PTR_ERR(oe);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 6569031af3cd..9826b003f1d2 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -962,3 +962,30 @@ err_free:
kfree(buf);
return ERR_PTR(res);
}
+
+/*
+ * ovl_sync_status() - Check fs sync status for volatile mounts
+ *
+ * Returns 1 if this is not a volatile mount and a real sync is required.
+ *
+ * Returns 0 if syncing can be skipped because mount is volatile, and no errors
+ * have occurred on the upperdir since the mount.
+ *
+ * Returns -errno if it is a volatile mount, and the error that occurred since
+ * the last mount. If the error code changes, it'll return the latest error
+ * code.
+ */
+
+int ovl_sync_status(struct ovl_fs *ofs)
+{
+ struct vfsmount *mnt;
+
+ if (ovl_should_sync(ofs))
+ return 1;
+
+ mnt = ovl_upper_mnt(ofs);
+ if (!mnt)
+ return 0;
+
+ return errseq_check(&mnt->mnt_sb->s_wb_err, ofs->errseq);
+}
diff --git a/fs/pipe.c b/fs/pipe.c
index c5989cfd564d..39c96845a72f 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1206,6 +1206,7 @@ const struct file_operations pipefifo_fops = {
.unlocked_ioctl = pipe_ioctl,
.release = pipe_release,
.fasync = pipe_fasync,
+ .splice_write = iter_file_splice_write,
};
/*
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 317899222d7f..d2018f70d1fa 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1770,6 +1770,12 @@ static int process_sysctl_arg(char *param, char *val,
return 0;
}
+ if (!val)
+ return -EINVAL;
+ len = strlen(val);
+ if (len == 0)
+ return -EINVAL;
+
/*
* To set sysctl options, we use a temporary mount of proc, look up the
* respective sys/ file and write to it. To avoid mounting it when no
@@ -1811,7 +1817,6 @@ static int process_sysctl_arg(char *param, char *val,
file, param, val);
goto out;
}
- len = strlen(val);
wret = kernel_write(file, val, len, &pos);
if (wret < 0) {
err = wret;
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 5bef3a68395d..d0df217f4712 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -705,6 +705,7 @@ static int udf_check_vsd(struct super_block *sb)
struct buffer_head *bh = NULL;
int nsr = 0;
struct udf_sb_info *sbi;
+ loff_t session_offset;
sbi = UDF_SB(sb);
if (sb->s_blocksize < sizeof(struct volStructDesc))
@@ -712,7 +713,8 @@ static int udf_check_vsd(struct super_block *sb)
else
sectorsize = sb->s_blocksize;
- sector += (((loff_t)sbi->s_session) << sb->s_blocksize_bits);
+ session_offset = (loff_t)sbi->s_session << sb->s_blocksize_bits;
+ sector += session_offset;
udf_debug("Starting at sector %u (%lu byte sectors)\n",
(unsigned int)(sector >> sb->s_blocksize_bits),
@@ -757,8 +759,7 @@ static int udf_check_vsd(struct super_block *sb)
if (nsr > 0)
return 1;
- else if (!bh && sector - (sbi->s_session << sb->s_blocksize_bits) ==
- VSD_FIRST_SECTOR_OFFSET)
+ else if (!bh && sector - session_offset == VSD_FIRST_SECTOR_OFFSET)
return -1;
else
return 0;