summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/btrfs_inode.h2
-rw-r--r--fs/btrfs/inode.c44
-rw-r--r--fs/btrfs/tree-log.c78
-rw-r--r--fs/efivarfs/super.c4
-rw-r--r--fs/ocfs2/inode.c3
-rw-r--r--fs/proc/generic.c38
-rw-r--r--fs/smb/client/cifsfs.c14
-rw-r--r--fs/smb/client/smb2inode.c7
-rw-r--r--fs/xfs/Kconfig1
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.c7
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c6
-rw-r--r--fs/xfs/xfs_aops.c3
-rw-r--r--fs/xfs/xfs_zone_alloc.c45
-rw-r--r--fs/xfs/xfs_zone_space_resv.c6
14 files changed, 148 insertions, 110 deletions
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index b99fb0273292..0387b9f43a52 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -248,7 +248,7 @@ struct btrfs_inode {
u64 new_delalloc_bytes;
/*
* The offset of the last dir index key that was logged.
- * This is used only for directories.
+ * This is used only for directories. Protected by 'log_mutex'.
*/
u64 last_dir_index_offset;
};
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9e4aec7330cb..dd82dcc7b2b7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6805,7 +6805,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
struct fscrypt_name fname;
u64 index;
int ret;
- int drop_inode = 0;
/* do not allow sys_link's with other subvols of the same device */
if (btrfs_root_id(root) != btrfs_root_id(BTRFS_I(inode)->root))
@@ -6837,44 +6836,44 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
/* There are several dir indexes for this inode, clear the cache. */
BTRFS_I(inode)->dir_index = 0ULL;
- inc_nlink(inode);
inode_inc_iversion(inode);
inode_set_ctime_current(inode);
- ihold(inode);
set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
&fname.disk_name, 1, index);
+ if (ret)
+ goto fail;
+ /* Link added now we update the inode item with the new link count. */
+ inc_nlink(inode);
+ ret = btrfs_update_inode(trans, BTRFS_I(inode));
if (ret) {
- drop_inode = 1;
- } else {
- struct dentry *parent = dentry->d_parent;
+ btrfs_abort_transaction(trans, ret);
+ goto fail;
+ }
- ret = btrfs_update_inode(trans, BTRFS_I(inode));
- if (ret)
+ if (inode->i_nlink == 1) {
+ /*
+ * If the new hard link count is 1, it's a file created with the
+ * open(2) O_TMPFILE flag.
+ */
+ ret = btrfs_orphan_del(trans, BTRFS_I(inode));
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
goto fail;
- if (inode->i_nlink == 1) {
- /*
- * If new hard link count is 1, it's a file created
- * with open(2) O_TMPFILE flag.
- */
- ret = btrfs_orphan_del(trans, BTRFS_I(inode));
- if (ret)
- goto fail;
}
- d_instantiate(dentry, inode);
- btrfs_log_new_name(trans, old_dentry, NULL, 0, parent);
}
+ /* Grab reference for the new dentry passed to d_instantiate(). */
+ ihold(inode);
+ d_instantiate(dentry, inode);
+ btrfs_log_new_name(trans, old_dentry, NULL, 0, dentry->d_parent);
+
fail:
fscrypt_free_filename(&fname);
if (trans)
btrfs_end_transaction(trans);
- if (drop_inode) {
- inode_dec_link_count(inode);
- iput(inode);
- }
btrfs_btree_balance_dirty(fs_info);
return ret;
}
@@ -7830,6 +7829,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
ei->last_sub_trans = 0;
ei->logged_trans = 0;
ei->delalloc_bytes = 0;
+ /* new_delalloc_bytes and last_dir_index_offset are in a union. */
ei->new_delalloc_bytes = 0;
ei->defrag_bytes = 0;
ei->disk_i_size = 0;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 69e11557fd13..7d5d90845ca9 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3340,6 +3340,31 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
return 0;
}
+static bool mark_inode_as_not_logged(const struct btrfs_trans_handle *trans,
+ struct btrfs_inode *inode)
+{
+ bool ret = false;
+
+ /*
+ * Do this only if ->logged_trans is still 0 to prevent races with
+ * concurrent logging as we may see the inode not logged when
+ * inode_logged() is called but it gets logged after inode_logged() did
+ * not find it in the log tree and we end up setting ->logged_trans to a
+ * value less than trans->transid after the concurrent logging task has
+ * set it to trans->transid. As a consequence, subsequent rename, unlink
+ * and link operations may end up not logging new names and removing old
+ * names from the log.
+ */
+ spin_lock(&inode->lock);
+ if (inode->logged_trans == 0)
+ inode->logged_trans = trans->transid - 1;
+ else if (inode->logged_trans == trans->transid)
+ ret = true;
+ spin_unlock(&inode->lock);
+
+ return ret;
+}
+
/*
* Check if an inode was logged in the current transaction. This correctly deals
* with the case where the inode was logged but has a logged_trans of 0, which
@@ -3357,15 +3382,32 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
struct btrfs_key key;
int ret;
- if (inode->logged_trans == trans->transid)
+ /*
+ * Quick lockless call, since once ->logged_trans is set to the current
+ * transaction, we never set it to a lower value anywhere else.
+ */
+ if (data_race(inode->logged_trans) == trans->transid)
return 1;
/*
- * If logged_trans is not 0, then we know the inode logged was not logged
- * in this transaction, so we can return false right away.
+ * If logged_trans is not 0 and not trans->transid, then we know the
+ * inode was not logged in this transaction, so we can return false
+ * right away. We take the lock to avoid a race caused by load/store
+ * tearing with a concurrent btrfs_log_inode() call or a concurrent task
+ * in this function further below - an update to trans->transid can be
+ * teared into two 32 bits updates for example, in which case we could
+ * see a positive value that is not trans->transid and assume the inode
+ * was not logged when it was.
*/
- if (inode->logged_trans > 0)
+ spin_lock(&inode->lock);
+ if (inode->logged_trans == trans->transid) {
+ spin_unlock(&inode->lock);
+ return 1;
+ } else if (inode->logged_trans > 0) {
+ spin_unlock(&inode->lock);
return 0;
+ }
+ spin_unlock(&inode->lock);
/*
* If no log tree was created for this root in this transaction, then
@@ -3374,10 +3416,8 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
* transaction's ID, to avoid the search below in a future call in case
* a log tree gets created after this.
*/
- if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state)) {
- inode->logged_trans = trans->transid - 1;
- return 0;
- }
+ if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &inode->root->state))
+ return mark_inode_as_not_logged(trans, inode);
/*
* We have a log tree and the inode's logged_trans is 0. We can't tell
@@ -3431,8 +3471,7 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
* Set logged_trans to a value greater than 0 and less then the
* current transaction to avoid doing the search in future calls.
*/
- inode->logged_trans = trans->transid - 1;
- return 0;
+ return mark_inode_as_not_logged(trans, inode);
}
/*
@@ -3440,20 +3479,9 @@ static int inode_logged(const struct btrfs_trans_handle *trans,
* the current transacion's ID, to avoid future tree searches as long as
* the inode is not evicted again.
*/
+ spin_lock(&inode->lock);
inode->logged_trans = trans->transid;
-
- /*
- * If it's a directory, then we must set last_dir_index_offset to the
- * maximum possible value, so that the next attempt to log the inode does
- * not skip checking if dir index keys found in modified subvolume tree
- * leaves have been logged before, otherwise it would result in attempts
- * to insert duplicate dir index keys in the log tree. This must be done
- * because last_dir_index_offset is an in-memory only field, not persisted
- * in the inode item or any other on-disk structure, so its value is lost
- * once the inode is evicted.
- */
- if (S_ISDIR(inode->vfs_inode.i_mode))
- inode->last_dir_index_offset = (u64)-1;
+ spin_unlock(&inode->lock);
return 1;
}
@@ -4045,7 +4073,7 @@ done:
/*
* If the inode was logged before and it was evicted, then its
- * last_dir_index_offset is (u64)-1, so we don't the value of the last index
+ * last_dir_index_offset is 0, so we don't know the value of the last index
* key offset. If that's the case, search for it and update the inode. This
* is to avoid lookups in the log tree every time we try to insert a dir index
* key from a leaf changed in the current transaction, and to allow us to always
@@ -4061,7 +4089,7 @@ static int update_last_dir_index_offset(struct btrfs_inode *inode,
lockdep_assert_held(&inode->log_mutex);
- if (inode->last_dir_index_offset != (u64)-1)
+ if (inode->last_dir_index_offset != 0)
return 0;
if (!ctx->logged_before) {
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index c4a139911356..4bb4002e3cdf 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -152,6 +152,10 @@ static int efivarfs_d_compare(const struct dentry *dentry,
{
int guid = len - EFI_VARIABLE_GUID_LEN;
+ /* Parallel lookups may produce a temporary invalid filename */
+ if (guid <= 0)
+ return 1;
+
if (name->len != len)
return 1;
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 14bf440ea4df..6c4f78f473fb 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1281,6 +1281,9 @@ static void ocfs2_clear_inode(struct inode *inode)
* the journal is flushed before journal shutdown. Thus it is safe to
* have inodes get cleaned up after journal shutdown.
*/
+ if (!osb->journal)
+ return;
+
jbd2_journal_release_jbd_inode(osb->journal->j_journal,
&oi->ip_jinode);
}
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 76e800e38c8f..bd0c099cfdd2 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -367,6 +367,25 @@ static const struct inode_operations proc_dir_inode_operations = {
.setattr = proc_notify_change,
};
+static void pde_set_flags(struct proc_dir_entry *pde)
+{
+ const struct proc_ops *proc_ops = pde->proc_ops;
+
+ if (!proc_ops)
+ return;
+
+ if (proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
+ pde->flags |= PROC_ENTRY_PERMANENT;
+ if (proc_ops->proc_read_iter)
+ pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+ if (proc_ops->proc_compat_ioctl)
+ pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
+ if (proc_ops->proc_lseek)
+ pde->flags |= PROC_ENTRY_proc_lseek;
+}
+
/* returns the registered entry, or frees dp and returns NULL on failure */
struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
struct proc_dir_entry *dp)
@@ -374,6 +393,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir,
if (proc_alloc_inum(&dp->low_ino))
goto out_free_entry;
+ pde_set_flags(dp);
+
write_lock(&proc_subdir_lock);
dp->parent = dir;
if (pde_subdir_insert(dir, dp) == false) {
@@ -561,20 +582,6 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
return p;
}
-static void pde_set_flags(struct proc_dir_entry *pde)
-{
- if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
- pde->flags |= PROC_ENTRY_PERMANENT;
- if (pde->proc_ops->proc_read_iter)
- pde->flags |= PROC_ENTRY_proc_read_iter;
-#ifdef CONFIG_COMPAT
- if (pde->proc_ops->proc_compat_ioctl)
- pde->flags |= PROC_ENTRY_proc_compat_ioctl;
-#endif
- if (pde->proc_ops->proc_lseek)
- pde->flags |= PROC_ENTRY_proc_lseek;
-}
-
struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
struct proc_dir_entry *parent,
const struct proc_ops *proc_ops, void *data)
@@ -585,7 +592,6 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
if (!p)
return NULL;
p->proc_ops = proc_ops;
- pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_data);
@@ -636,7 +642,6 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
p->proc_ops = &proc_seq_ops;
p->seq_ops = ops;
p->state_size = state_size;
- pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_seq_private);
@@ -667,7 +672,6 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
return NULL;
p->proc_ops = &proc_single_ops;
p->single_show = show;
- pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_single_data);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 3bd85ab2deb1..e1848276bab4 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1358,6 +1358,20 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off,
truncate_setsize(target_inode, new_size);
fscache_resize_cookie(cifs_inode_cookie(target_inode),
new_size);
+ } else if (rc == -EOPNOTSUPP) {
+ /*
+ * copy_file_range syscall man page indicates EINVAL
+ * is returned e.g when "fd_in and fd_out refer to the
+ * same file and the source and target ranges overlap."
+ * Test generic/157 was what showed these cases where
+ * we need to remap EOPNOTSUPP to EINVAL
+ */
+ if (off >= src_inode->i_size) {
+ rc = -EINVAL;
+ } else if (src_inode == target_inode) {
+ if (off + len > destoff)
+ rc = -EINVAL;
+ }
}
if (rc == 0 && new_size > target_cifsi->netfs.zero_point)
target_cifsi->netfs.zero_point = new_size;
diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
index 2a0316c514e4..31c13fb5b85b 100644
--- a/fs/smb/client/smb2inode.c
+++ b/fs/smb/client/smb2inode.c
@@ -207,8 +207,10 @@ replay_again:
server = cifs_pick_channel(ses);
vars = kzalloc(sizeof(*vars), GFP_ATOMIC);
- if (vars == NULL)
- return -ENOMEM;
+ if (vars == NULL) {
+ rc = -ENOMEM;
+ goto out;
+ }
rqst = &vars->rqst[0];
rsp_iov = &vars->rsp_iov[0];
@@ -864,6 +866,7 @@ finished:
smb2_should_replay(tcon, &retries, &cur_sleep))
goto replay_again;
+out:
if (cfile)
cifsFileInfo_put(cfile);
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index ae0ca6858496..065953475cf5 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -105,6 +105,7 @@ config XFS_POSIX_ACL
config XFS_RT
bool "XFS Realtime subvolume support"
depends on XFS_FS
+ default BLK_DEV_ZONED
help
If you say Y here you will be able to mount and use XFS filesystems
which contain a realtime subvolume. The realtime subvolume is a
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 4c44ce1c8a64..bff3dc226f81 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -435,6 +435,13 @@ xfs_attr_rmtval_get(
0, &bp, &xfs_attr3_rmt_buf_ops);
if (xfs_metadata_is_sick(error))
xfs_dirattr_mark_sick(args->dp, XFS_ATTR_FORK);
+ /*
+ * ENODATA from disk implies a disk medium failure;
+ * ENODATA for xattrs means attribute not found, so
+ * disambiguate that here.
+ */
+ if (error == -ENODATA)
+ error = -EIO;
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 17d9e6154f19..723a0643b838 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2833,6 +2833,12 @@ xfs_da_read_buf(
&bp, ops);
if (xfs_metadata_is_sick(error))
xfs_dirattr_mark_sick(dp, whichfork);
+ /*
+ * ENODATA from disk implies a disk medium failure; ENODATA for
+ * xattrs means attribute not found, so disambiguate that here.
+ */
+ if (error == -ENODATA && whichfork == XFS_ATTR_FORK)
+ error = -EIO;
if (error)
goto out_free;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 1ee4f835ac3c..a26f79815533 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -760,6 +760,9 @@ xfs_vm_swap_activate(
{
struct xfs_inode *ip = XFS_I(file_inode(swap_file));
+ if (xfs_is_zoned_inode(ip))
+ return -EINVAL;
+
/*
* Swap file activation can race against concurrent shared extent
* removal in files that have been cloned. If this happens,
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index f8bd6d741755..f28214c28ab5 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -374,44 +374,6 @@ xfs_zone_free_blocks(
return 0;
}
-/*
- * Check if the zone containing the data just before the offset we are
- * writing to is still open and has space.
- */
-static struct xfs_open_zone *
-xfs_last_used_zone(
- struct iomap_ioend *ioend)
-{
- struct xfs_inode *ip = XFS_I(ioend->io_inode);
- struct xfs_mount *mp = ip->i_mount;
- xfs_fileoff_t offset_fsb = XFS_B_TO_FSB(mp, ioend->io_offset);
- struct xfs_rtgroup *rtg = NULL;
- struct xfs_open_zone *oz = NULL;
- struct xfs_iext_cursor icur;
- struct xfs_bmbt_irec got;
-
- xfs_ilock(ip, XFS_ILOCK_SHARED);
- if (!xfs_iext_lookup_extent_before(ip, &ip->i_df, &offset_fsb,
- &icur, &got)) {
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- return NULL;
- }
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
- rtg = xfs_rtgroup_grab(mp, xfs_rtb_to_rgno(mp, got.br_startblock));
- if (!rtg)
- return NULL;
-
- xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
- oz = READ_ONCE(rtg->rtg_open_zone);
- if (oz && (oz->oz_is_gc || !atomic_inc_not_zero(&oz->oz_ref)))
- oz = NULL;
- xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
-
- xfs_rtgroup_rele(rtg);
- return oz;
-}
-
static struct xfs_group *
xfs_find_free_zone(
struct xfs_mount *mp,
@@ -918,12 +880,9 @@ xfs_zone_alloc_and_submit(
goto out_error;
/*
- * If we don't have a cached zone in this write context, see if the
- * last extent before the one we are writing to points to an active
- * zone. If so, just continue writing to it.
+ * If we don't have a locally cached zone in this write context, see if
+ * the inode is still associated with a zone and use that if so.
*/
- if (!*oz && ioend->io_offset)
- *oz = xfs_last_used_zone(ioend);
if (!*oz)
*oz = xfs_cached_zone(mp, ip);
diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c
index 1313c55b8cbe..9cd38716fd25 100644
--- a/fs/xfs/xfs_zone_space_resv.c
+++ b/fs/xfs/xfs_zone_space_resv.c
@@ -10,6 +10,7 @@
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_rtbitmap.h"
+#include "xfs_icache.h"
#include "xfs_zone_alloc.h"
#include "xfs_zone_priv.h"
#include "xfs_zones.h"
@@ -230,6 +231,11 @@ xfs_zoned_space_reserve(
error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
flags & XFS_ZR_RESERVED);
+ if (error == -ENOSPC && !(flags & XFS_ZR_NOWAIT)) {
+ xfs_inodegc_flush(mp);
+ error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
+ flags & XFS_ZR_RESERVED);
+ }
if (error == -ENOSPC && (flags & XFS_ZR_GREEDY) && count_fsb > 1)
error = xfs_zoned_reserve_extents_greedy(mp, &count_fsb, flags);
if (error)
generated by cgit (git 2.34.1) at 2025-09-03 11:37:57 +0000