summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/9p/fid.c9
-rw-r--r--fs/Kconfig4
-rw-r--r--fs/Makefile2
-rw-r--r--fs/binfmt_misc.c6
-rw-r--r--fs/btrfs/block-group.c39
-rw-r--r--fs/btrfs/ctree.h6
-rw-r--r--fs/btrfs/ioctl.c97
-rw-r--r--fs/btrfs/qgroup.c21
-rw-r--r--fs/btrfs/transaction.c24
-rw-r--r--fs/btrfs/transaction.h2
-rw-r--r--fs/btrfs/tree-checker.c15
-rw-r--r--fs/btrfs/tree-log.c23
-rw-r--r--fs/cachefiles/io.c59
-rw-r--r--fs/ceph/caps.c55
-rw-r--r--fs/ceph/file.c9
-rw-r--r--fs/cifs/connect.c23
-rw-r--r--fs/cifs/file.c221
-rw-r--r--fs/cifs/fscache.c126
-rw-r--r--fs/cifs/fscache.h79
-rw-r--r--fs/cifs/inode.c8
-rw-r--r--fs/cifs/sess.c6
-rw-r--r--fs/configfs/dir.c6
-rw-r--r--fs/devpts/inode.c2
-rw-r--r--fs/erofs/data.c8
-rw-r--r--fs/erofs/zdata.c113
-rw-r--r--fs/erofs/zmap.c7
-rw-r--r--fs/ext4/acl.c8
-rw-r--r--fs/ext4/ext4.h31
-rw-r--r--fs/ext4/ext4_jbd2.h2
-rw-r--r--fs/ext4/extents.c16
-rw-r--r--fs/ext4/fast_commit.c133
-rw-r--r--fs/ext4/hash.c2
-rw-r--r--fs/ext4/indirect.c2
-rw-r--r--fs/ext4/inline.c23
-rw-r--r--fs/ext4/inode.c12
-rw-r--r--fs/ext4/ioctl.c4
-rw-r--r--fs/ext4/mballoc.c26
-rw-r--r--fs/ext4/migrate.c2
-rw-r--r--fs/ext4/namei.c16
-rw-r--r--fs/ext4/orphan.c4
-rw-r--r--fs/ext4/super.c14
-rw-r--r--fs/ext4/sysfs.c8
-rw-r--r--fs/ext4/xattr.c6
-rw-r--r--fs/f2fs/dir.c10
-rw-r--r--fs/f2fs/f2fs.h2
-rw-r--r--fs/f2fs/hash.c2
-rw-r--r--fs/f2fs/namei.c4
-rw-r--r--fs/f2fs/recovery.c4
-rw-r--r--fs/f2fs/super.c10
-rw-r--r--fs/f2fs/sysfs.c10
-rw-r--r--fs/file_table.c2
-rw-r--r--fs/iomap/buffered-io.c52
-rw-r--r--fs/jbd2/commit.c21
-rw-r--r--fs/jbd2/journal.c8
-rw-r--r--fs/jbd2/transaction.c53
-rw-r--r--fs/ksmbd/auth.c27
-rw-r--r--fs/ksmbd/smb2pdu.c45
-rw-r--r--fs/ksmbd/smb_common.c5
-rw-r--r--fs/ksmbd/transport_rdma.c2
-rw-r--r--fs/ksmbd/vfs.h1
-rw-r--r--fs/libfs.c10
-rw-r--r--fs/lockd/svcsubs.c18
-rw-r--r--fs/namei.c10
-rw-r--r--fs/nfs/callback.h2
-rw-r--r--fs/nfs/callback_proc.c2
-rw-r--r--fs/nfs/callback_xdr.c18
-rw-r--r--fs/nfs/client.c9
-rw-r--r--fs/nfs/dir.c170
-rw-r--r--fs/nfs/filelayout/filelayout.h2
-rw-r--r--fs/nfs/filelayout/filelayoutdev.c4
-rw-r--r--fs/nfs/internal.h1
-rw-r--r--fs/nfs/nfs3proc.c5
-rw-r--r--fs/nfs/nfs42proc.c13
-rw-r--r--fs/nfs/nfs4_fs.h14
-rw-r--r--fs/nfs/nfs4client.c5
-rw-r--r--fs/nfs/nfs4namespace.c19
-rw-r--r--fs/nfs/nfs4proc.c200
-rw-r--r--fs/nfs/nfs4state.c6
-rw-r--r--fs/nfs/nfs4xdr.c49
-rw-r--r--fs/nfs/sysfs.c3
-rw-r--r--fs/nfsd/nfs3proc.c19
-rw-r--r--fs/nfsd/nfs3xdr.c4
-rw-r--r--fs/nfsd/nfs4proc.c13
-rw-r--r--fs/nfsd/nfs4state.c4
-rw-r--r--fs/nfsd/nfs4xdr.c10
-rw-r--r--fs/nfsd/nfsctl.c5
-rw-r--r--fs/nfsd/trace.h14
-rw-r--r--fs/nfsd/vfs.c57
-rw-r--r--fs/nfsd/vfs.h4
-rw-r--r--fs/notify/fanotify/fanotify_user.c9
-rw-r--r--fs/ocfs2/stackglue.c13
-rw-r--r--fs/ocfs2/suballoc.c25
-rw-r--r--fs/overlayfs/copy_up.c16
-rw-r--r--fs/quota/dquot.c11
-rw-r--r--fs/super.c19
-rw-r--r--fs/sync.c18
-rw-r--r--fs/udf/inode.c9
-rw-r--r--fs/unicode/Kconfig18
-rw-r--r--fs/unicode/Makefile6
-rw-r--r--fs/xfs/xfs_aops.c16
-rw-r--r--fs/xfs/xfs_bmap_util.c9
-rw-r--r--fs/xfs/xfs_file.c86
-rw-r--r--fs/xfs/xfs_inode.h9
-rw-r--r--fs/xfs/xfs_ioctl.c2
-rw-r--r--fs/xfs/xfs_pnfs.c42
-rw-r--r--fs/xfs/xfs_super.c6
106 files changed, 1674 insertions, 867 deletions
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 6aab046c98e2..79df61fe0e59 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -96,12 +96,8 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
dentry, dentry, from_kuid(&init_user_ns, uid),
any);
ret = NULL;
-
- if (d_inode(dentry))
- ret = v9fs_fid_find_inode(d_inode(dentry), uid);
-
/* we'll recheck under lock if there's anything to look in */
- if (!ret && dentry->d_fsdata) {
+ if (dentry->d_fsdata) {
struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata;
spin_lock(&dentry->d_lock);
@@ -113,6 +109,9 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
}
}
spin_unlock(&dentry->d_lock);
+ } else {
+ if (dentry->d_inode)
+ ret = v9fs_fid_find_inode(dentry->d_inode, uid);
}
return ret;
diff --git a/fs/Kconfig b/fs/Kconfig
index 7a2b11c0b803..6c7dc1387beb 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -369,8 +369,8 @@ source "fs/ksmbd/Kconfig"
config SMBFS_COMMON
tristate
- default y if CIFS=y
- default m if CIFS=m
+ default y if CIFS=y || SMB_SERVER=y
+ default m if CIFS=m || SMB_SERVER=m
source "fs/coda/Kconfig"
source "fs/afs/Kconfig"
diff --git a/fs/Makefile b/fs/Makefile
index dab324aea08f..208a74e0b00e 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -96,7 +96,7 @@ obj-$(CONFIG_EXPORTFS) += exportfs/
obj-$(CONFIG_NFSD) += nfsd/
obj-$(CONFIG_LOCKD) += lockd/
obj-$(CONFIG_NLS) += nls/
-obj-$(CONFIG_UNICODE) += unicode/
+obj-y += unicode/
obj-$(CONFIG_SYSV_FS) += sysv/
obj-$(CONFIG_SMBFS_COMMON) += smbfs_common/
obj-$(CONFIG_CIFS) += cifs/
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index ddea6acbddde..e1eae7ea823a 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -822,11 +822,7 @@ static int __init init_misc_binfmt(void)
int err = register_filesystem(&bm_fs_type);
if (!err)
insert_binfmt(&misc_format);
- if (!register_sysctl_mount_point("fs/binfmt_misc")) {
- pr_warn("Failed to create fs/binfmt_misc sysctl mount point");
- return -ENOMEM;
- }
- return 0;
+ return err;
}
static void __exit exit_misc_binfmt(void)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 1db24e6d6d90..8202ad6aa131 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -124,7 +124,16 @@ void btrfs_put_block_group(struct btrfs_block_group *cache)
{
if (refcount_dec_and_test(&cache->refs)) {
WARN_ON(cache->pinned > 0);
- WARN_ON(cache->reserved > 0);
+ /*
+ * If there was a failure to cleanup a log tree, very likely due
+ * to an IO failure on a writeback attempt of one or more of its
+ * extent buffers, we could not do proper (and cheap) unaccounting
+ * of their reserved space, so don't warn on reserved > 0 in that
+ * case.
+ */
+ if (!(cache->flags & BTRFS_BLOCK_GROUP_METADATA) ||
+ !BTRFS_FS_LOG_CLEANUP_ERROR(cache->fs_info))
+ WARN_ON(cache->reserved > 0);
/*
* A block_group shouldn't be on the discard_list anymore.
@@ -2544,6 +2553,19 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
int ret;
bool dirty_bg_running;
+ /*
+ * This can only happen when we are doing read-only scrub on read-only
+ * mount.
+ * In that case we should not start a new transaction on read-only fs.
+ * Thus here we skip all chunk allocations.
+ */
+ if (sb_rdonly(fs_info->sb)) {
+ mutex_lock(&fs_info->ro_block_group_mutex);
+ ret = inc_block_group_ro(cache, 0);
+ mutex_unlock(&fs_info->ro_block_group_mutex);
+ return ret;
+ }
+
do {
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
@@ -3974,9 +3996,22 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
* important and indicates a real bug if this happens.
*/
if (WARN_ON(space_info->bytes_pinned > 0 ||
- space_info->bytes_reserved > 0 ||
space_info->bytes_may_use > 0))
btrfs_dump_space_info(info, space_info, 0, 0);
+
+ /*
+ * If there was a failure to cleanup a log tree, very likely due
+ * to an IO failure on a writeback attempt of one or more of its
+ * extent buffers, we could not do proper (and cheap) unaccounting
+ * of their reserved space, so don't warn on bytes_reserved > 0 in
+ * that case.
+ */
+ if (!(space_info->flags & BTRFS_BLOCK_GROUP_METADATA) ||
+ !BTRFS_FS_LOG_CLEANUP_ERROR(info)) {
+ if (WARN_ON(space_info->bytes_reserved > 0))
+ btrfs_dump_space_info(info, space_info, 0, 0);
+ }
+
WARN_ON(space_info->reclaim_size > 0);
list_del(&space_info->list);
btrfs_sysfs_remove_space_info(space_info);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b4a9b1c58d22..8992e0096163 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -145,6 +145,9 @@ enum {
BTRFS_FS_STATE_DUMMY_FS_INFO,
BTRFS_FS_STATE_NO_CSUMS,
+
+ /* Indicates there was an error cleaning up a log tree. */
+ BTRFS_FS_STATE_LOG_CLEANUP_ERROR,
};
#define BTRFS_BACKREF_REV_MAX 256
@@ -3593,6 +3596,9 @@ do { \
#define BTRFS_FS_ERROR(fs_info) (unlikely(test_bit(BTRFS_FS_STATE_ERROR, \
&(fs_info)->fs_state)))
+#define BTRFS_FS_LOG_CLEANUP_ERROR(fs_info) \
+ (unlikely(test_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, \
+ &(fs_info)->fs_state)))
__printf(5, 6)
__cold
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a5bd6926f7ff..33eda39df685 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -805,10 +805,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
goto fail;
}
- spin_lock(&fs_info->trans_lock);
- list_add(&pending_snapshot->list,
- &trans->transaction->pending_snapshots);
- spin_unlock(&fs_info->trans_lock);
+ trans->pending_snapshot = pending_snapshot;
ret = btrfs_commit_transaction(trans);
if (ret)
@@ -1214,6 +1211,35 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
goto next;
/*
+ * Our start offset might be in the middle of an existing extent
+ * map, so take that into account.
+ */
+ range_len = em->len - (cur - em->start);
+ /*
+ * If this range of the extent map is already flagged for delalloc,
+ * skip it, because:
+ *
+ * 1) We could deadlock later, when trying to reserve space for
+ * delalloc, because in case we can't immediately reserve space
+ * the flusher can start delalloc and wait for the respective
+ * ordered extents to complete. The deadlock would happen
+ * because we do the space reservation while holding the range
+ * locked, and starting writeback, or finishing an ordered
+ * extent, requires locking the range;
+ *
+ * 2) If there's delalloc there, it means there's dirty pages for
+ * which writeback has not started yet (we clean the delalloc
+ * flag when starting writeback and after creating an ordered
+ * extent). If we mark pages in an adjacent range for defrag,
+ * then we will have a larger contiguous range for delalloc,
+ * very likely resulting in a larger extent after writeback is
+ * triggered (except in a case of free space fragmentation).
+ */
+ if (test_range_bit(&inode->io_tree, cur, cur + range_len - 1,
+ EXTENT_DELALLOC, 0, NULL))
+ goto next;
+
+ /*
* For do_compress case, we want to compress all valid file
* extents, thus no @extent_thresh or mergeable check.
*/
@@ -1221,7 +1247,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode,
goto add;
/* Skip too large extent */
- if (em->len >= extent_thresh)
+ if (range_len >= extent_thresh)
goto next;
next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em,
@@ -1442,9 +1468,11 @@ static int defrag_one_cluster(struct btrfs_inode *inode,
list_for_each_entry(entry, &target_list, list) {
u32 range_len = entry->len;
- /* Reached the limit */
- if (max_sectors && max_sectors == *sectors_defragged)
+ /* Reached or beyond the limit */
+ if (max_sectors && *sectors_defragged >= max_sectors) {
+ ret = 1;
break;
+ }
if (max_sectors)
range_len = min_t(u32, range_len,
@@ -1465,7 +1493,8 @@ static int defrag_one_cluster(struct btrfs_inode *inode,
extent_thresh, newer_than, do_compress);
if (ret < 0)
break;
- *sectors_defragged += range_len;
+ *sectors_defragged += range_len >>
+ inode->root->fs_info->sectorsize_bits;
}
out:
list_for_each_entry_safe(entry, tmp, &target_list, list) {
@@ -1484,6 +1513,12 @@ out:
* @newer_than: minimum transid to defrag
* @max_to_defrag: max number of sectors to be defragged, if 0, the whole inode
* will be defragged.
+ *
+ * Return <0 for error.
+ * Return >=0 for the number of sectors defragged, and range->start will be updated
+ * to indicate the file offset where next defrag should be started at.
+ * (Mostly for autodefrag, which sets @max_to_defrag thus we may exit early without
+ * defragging all the range).
*/
int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
struct btrfs_ioctl_defrag_range_args *range,
@@ -1499,6 +1534,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
int compress_type = BTRFS_COMPRESS_ZLIB;
int ret = 0;
u32 extent_thresh = range->extent_thresh;
+ pgoff_t start_index;
if (isize == 0)
return 0;
@@ -1518,12 +1554,16 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
if (range->start + range->len > range->start) {
/* Got a specific range */
- last_byte = min(isize, range->start + range->len) - 1;
+ last_byte = min(isize, range->start + range->len);
} else {
/* Defrag until file end */
- last_byte = isize - 1;
+ last_byte = isize;
}
+ /* Align the range */
+ cur = round_down(range->start, fs_info->sectorsize);
+ last_byte = round_up(last_byte, fs_info->sectorsize) - 1;
+
/*
* If we were not given a ra, allocate a readahead context. As
* readahead is just an optimization, defrag will work without it so
@@ -1536,16 +1576,26 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
file_ra_state_init(ra, inode->i_mapping);
}
- /* Align the range */
- cur = round_down(range->start, fs_info->sectorsize);
- last_byte = round_up(last_byte, fs_info->sectorsize) - 1;
+ /*
+ * Make writeback start from the beginning of the range, so that the
+ * defrag range can be written sequentially.
+ */
+ start_index = cur >> PAGE_SHIFT;
+ if (start_index < inode->i_mapping->writeback_index)
+ inode->i_mapping->writeback_index = start_index;
while (cur < last_byte) {
+ const unsigned long prev_sectors_defragged = sectors_defragged;
u64 cluster_end;
/* The cluster size 256K should always be page aligned */
BUILD_BUG_ON(!IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE));
+ if (btrfs_defrag_cancelled(fs_info)) {
+ ret = -EAGAIN;
+ break;
+ }
+
/* We want the cluster end at page boundary when possible */
cluster_end = (((cur >> PAGE_SHIFT) +
(SZ_256K >> PAGE_SHIFT)) << PAGE_SHIFT) - 1;
@@ -1567,14 +1617,27 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
cluster_end + 1 - cur, extent_thresh,
newer_than, do_compress,
&sectors_defragged, max_to_defrag);
+
+ if (sectors_defragged > prev_sectors_defragged)
+ balance_dirty_pages_ratelimited(inode->i_mapping);
+
btrfs_inode_unlock(inode, 0);
if (ret < 0)
break;
cur = cluster_end + 1;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
}
if (ra_allocated)
kfree(ra);
+ /*
+ * Update range.start for autodefrag, this will indicate where to start
+ * in next run.
+ */
+ range->start = cur;
if (sectors_defragged) {
/*
* We have defragged some sectors, for compression case they
@@ -3086,10 +3149,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
btrfs_inode_lock(inode, 0);
err = btrfs_delete_subvolume(dir, dentry);
btrfs_inode_unlock(inode, 0);
- if (!err) {
- fsnotify_rmdir(dir, dentry);
- d_delete(dentry);
- }
+ if (!err)
+ d_delete_notify(dir, dentry);
out_dput:
dput(dentry);
@@ -3290,7 +3351,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
struct block_device *bdev = NULL;
fmode_t mode;
int ret;
- bool cancel;
+ bool cancel = false;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 8928275823a1..f12dc687350c 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1185,9 +1185,24 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
struct btrfs_trans_handle *trans = NULL;
int ret = 0;
+ /*
+ * We need to have subvol_sem write locked, to prevent races between
+ * concurrent tasks trying to disable quotas, because we will unlock
+ * and relock qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes.
+ */
+ lockdep_assert_held_write(&fs_info->subvol_sem);
+
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root)
goto out;
+
+ /*
+ * Request qgroup rescan worker to complete and wait for it. This wait
+ * must be done before transaction start for quota disable since it may
+ * deadlock with transaction by the qgroup rescan worker.
+ */
+ clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
mutex_unlock(&fs_info->qgroup_ioctl_lock);
/*
@@ -1205,14 +1220,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
+ set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
goto out;
}
if (!fs_info->quota_root)
goto out;
- clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
- btrfs_qgroup_wait_for_completion(fs_info, false);
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
@@ -3383,6 +3397,9 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
btrfs_warn(fs_info,
"qgroup rescan init failed, qgroup is not enabled");
ret = -EINVAL;
+ } else if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
+ /* Quota disable is in progress */
+ ret = -EBUSY;
}
if (ret) {
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 03de89b45f27..c43bbc7f623e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2000,6 +2000,27 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
}
+/*
+ * Add a pending snapshot associated with the given transaction handle to the
+ * respective handle. This must be called after the transaction commit started
+ * and while holding fs_info->trans_lock.
+ * This serves to guarantee a caller of btrfs_commit_transaction() that it can
+ * safely free the pending snapshot pointer in case btrfs_commit_transaction()
+ * returns an error.
+ */
+static void add_pending_snapshot(struct btrfs_trans_handle *trans)
+{
+ struct btrfs_transaction *cur_trans = trans->transaction;
+
+ if (!trans->pending_snapshot)
+ return;
+
+ lockdep_assert_held(&trans->fs_info->trans_lock);
+ ASSERT(cur_trans->state >= TRANS_STATE_COMMIT_START);
+
+ list_add(&trans->pending_snapshot->list, &cur_trans->pending_snapshots);
+}
+
int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
@@ -2073,6 +2094,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED;
+ add_pending_snapshot(trans);
+
spin_unlock(&fs_info->trans_lock);
refcount_inc(&cur_trans->use_count);
@@ -2163,6 +2186,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
* COMMIT_DOING so make sure to wait for num_writers to == 1 again.
*/
spin_lock(&fs_info->trans_lock);
+ add_pending_snapshot(trans);
cur_trans->state = TRANS_STATE_COMMIT_DOING;
spin_unlock(&fs_info->trans_lock);
wait_event(cur_trans->writer_wait,
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 1852ed9de7fd..9402d8d94484 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -123,6 +123,8 @@ struct btrfs_trans_handle {
struct btrfs_transaction *transaction;
struct btrfs_block_rsv *block_rsv;
struct btrfs_block_rsv *orig_rsv;
+ /* Set by a task that wants to create a snapshot. */
+ struct btrfs_pending_snapshot *pending_snapshot;
refcount_t use_count;
unsigned int type;
/*
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 72e1c942197d..9fd145f1c4bc 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -965,6 +965,7 @@ static int check_dev_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
struct btrfs_dev_item *ditem;
+ const u32 item_size = btrfs_item_size(leaf, slot);
if (unlikely(key->objectid != BTRFS_DEV_ITEMS_OBJECTID)) {
dev_item_err(leaf, slot,
@@ -972,6 +973,13 @@ static int check_dev_item(struct extent_buffer *leaf,
key->objectid, BTRFS_DEV_ITEMS_OBJECTID);
return -EUCLEAN;
}
+
+ if (unlikely(item_size != sizeof(*ditem))) {
+ dev_item_err(leaf, slot, "invalid item size: has %u expect %zu",
+ item_size, sizeof(*ditem));
+ return -EUCLEAN;
+ }
+
ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item);
if (unlikely(btrfs_device_id(leaf, ditem) != key->offset)) {
dev_item_err(leaf, slot,
@@ -1007,6 +1015,7 @@ static int check_inode_item(struct extent_buffer *leaf,
struct btrfs_inode_item *iitem;
u64 super_gen = btrfs_super_generation(fs_info->super_copy);
u32 valid_mask = (S_IFMT | S_ISUID | S_ISGID | S_ISVTX | 0777);
+ const u32 item_size = btrfs_item_size(leaf, slot);
u32 mode;
int ret;
u32 flags;
@@ -1016,6 +1025,12 @@ static int check_inode_item(struct extent_buffer *leaf,
if (unlikely(ret < 0))
return ret;
+ if (unlikely(item_size != sizeof(*iitem))) {
+ generic_err(leaf, slot, "invalid item size: has %u expect %zu",
+ item_size, sizeof(*iitem));
+ return -EUCLEAN;
+ }
+
iitem = btrfs_item_ptr(leaf, slot, struct btrfs_inode_item);
/* Here we use super block generation + 1 to handle log tree */
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index c1ddbe800897..3ee014c06b82 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3414,6 +3414,29 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
if (log->node) {
ret = walk_log_tree(trans, log, &wc);
if (ret) {
+ /*
+ * We weren't able to traverse the entire log tree, the
+ * typical scenario is getting an -EIO when reading an
+ * extent buffer of the tree, due to a previous writeback
+ * failure of it.
+ */
+ set_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR,
+ &log->fs_info->fs_state);
+
+ /*
+ * Some extent buffers of the log tree may still be dirty
+ * and not yet written back to storage, because we may
+ * have updates to a log tree without syncing a log tree,
+ * such as during rename and link operations. So flush
+ * them out and wait for their writeback to complete, so
+ * that we properly cleanup their state and pages.
+ */
+ btrfs_write_marked_extents(log->fs_info,
+ &log->dirty_log_pages,
+ EXTENT_DIRTY | EXTENT_NEW);
+ btrfs_wait_tree_log_extents(log,
+ EXTENT_DIRTY | EXTENT_NEW);
+
if (trans)
btrfs_abort_transaction(trans, ret);
else
diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
index 04eb52736990..753986ea1583 100644
--- a/fs/cachefiles/io.c
+++ b/fs/cachefiles/io.c
@@ -192,6 +192,64 @@ presubmission_error:
}
/*
+ * Query the occupancy of the cache in a region, returning where the next chunk
+ * of data starts and how long it is.
+ */
+static int cachefiles_query_occupancy(struct netfs_cache_resources *cres,
+ loff_t start, size_t len, size_t granularity,
+ loff_t *_data_start, size_t *_data_len)
+{
+ struct cachefiles_object *object;
+ struct file *file;
+ loff_t off, off2;
+
+ *_data_start = -1;
+ *_data_len = 0;
+
+ if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ))
+ return -ENOBUFS;
+
+ object = cachefiles_cres_object(cres);
+ file = cachefiles_cres_file(cres);
+ granularity = max_t(size_t, object->volume->cache->bsize, granularity);
+
+ _enter("%pD,%li,%llx,%zx/%llx",
+ file, file_inode(file)->i_ino, start, len,
+ i_size_read(file_inode(file)));
+
+ off = cachefiles_inject_read_error();
+ if (off == 0)
+ off = vfs_llseek(file, start, SEEK_DATA);
+ if (off == -ENXIO)
+ return -ENODATA; /* Beyond EOF */
+ if (off < 0 && off >= (loff_t)-MAX_ERRNO)
+ return -ENOBUFS; /* Error. */
+ if (round_up(off, granularity) >= start + len)
+ return -ENODATA; /* No data in range */
+
+ off2 = cachefiles_inject_read_error();
+ if (off2 == 0)
+ off2 = vfs_llseek(file, off, SEEK_HOLE);
+ if (off2 == -ENXIO)
+ return -ENODATA; /* Beyond EOF */
+ if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO)
+ return -ENOBUFS; /* Error. */
+
+ /* Round away partial blocks */
+ off = round_up(off, granularity);
+ off2 = round_down(off2, granularity);
+ if (off2 <= off)
+ return -ENODATA;
+
+ *_data_start = off;
+ if (off2 > start + len)
+ *_data_len = len;
+ else
+ *_data_len = off2 - off;
+ return 0;
+}
+
+/*
* Handle completion of a write to the cache.
*/
static void cachefiles_write_complete(struct kiocb *iocb, long ret)
@@ -545,6 +603,7 @@ static const struct netfs_cache_ops cachefiles_netfs_cache_ops = {
.write = cachefiles_write,
.prepare_read = cachefiles_prepare_read,
.prepare_write = cachefiles_prepare_write,
+ .query_occupancy = cachefiles_query_occupancy,
};
/*
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 7d305b974824..b472cd066d1c 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2218,6 +2218,7 @@ static int unsafe_request_wait(struct inode *inode)
struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
struct ceph_inode_info *ci = ceph_inode(inode);
struct ceph_mds_request *req1 = NULL, *req2 = NULL;
+ unsigned int max_sessions;
int ret, err = 0;
spin_lock(&ci->i_unsafe_lock);
@@ -2236,36 +2237,44 @@ static int unsafe_request_wait(struct inode *inode)
spin_unlock(&ci->i_unsafe_lock);
/*
+ * The mdsc->max_sessions is unlikely to be changed
+ * mostly, here we will retry it by reallocating the
+ * sessions array memory to get rid of the mdsc->mutex
+ * lock.
+ */
+retry:
+ max_sessions = mdsc->max_sessions;
+
+ /*
* Trigger to flush the journal logs in all the relevant MDSes
* manually, or in the worst case we must wait at most 5 seconds
* to wait the journal logs to be flushed by the MDSes periodically.
*/
- if (req1 || req2) {
+ if ((req1 || req2) && likely(max_sessions)) {
struct ceph_mds_session **sessions = NULL;
struct ceph_mds_session *s;
struct ceph_mds_request *req;
- unsigned int max;
int i;
- /*
- * The mdsc->max_sessions is unlikely to be changed
- * mostly, here we will retry it by reallocating the
- * sessions arrary memory to get rid of the mdsc->mutex
- * lock.
- */
-retry:
- max = mdsc->max_sessions;
- sessions = krealloc(sessions, max * sizeof(s), __GFP_ZERO);
- if (!sessions)
- return -ENOMEM;
+ sessions = kzalloc(max_sessions * sizeof(s), GFP_KERNEL);
+ if (!sessions) {
+ err = -ENOMEM;
+ goto out;
+ }
spin_lock(&ci->i_unsafe_lock);
if (req1) {
list_for_each_entry(req, &ci->i_unsafe_dirops,
r_unsafe_dir_item) {
s = req->r_session;
- if (unlikely(s->s_mds >= max)) {
+ if (unlikely(s->s_mds >= max_sessions)) {
spin_unlock(&ci->i_unsafe_lock);
+ for (i = 0; i < max_sessions; i++) {
+ s = sessions[i];
+ if (s)
+ ceph_put_mds_session(s);
+ }
+ kfree(sessions);
goto retry;
}
if (!sessions[s->s_mds]) {
@@ -2278,8 +2287,14 @@ retry:
list_for_each_entry(req, &ci->i_unsafe_iops,
r_unsafe_target_item) {
s = req->r_session;
- if (unlikely(s->s_mds >= max)) {
+ if (unlikely(s->s_mds >= max_sessions)) {
spin_unlock(&ci->i_unsafe_lock);
+ for (i = 0; i < max_sessions; i++) {
+ s = sessions[i];
+ if (s)
+ ceph_put_mds_session(s);
+ }
+ kfree(sessions);
goto retry;
}
if (!sessions[s->s_mds]) {
@@ -2300,7 +2315,7 @@ retry:
spin_unlock(&ci->i_ceph_lock);
/* send flush mdlog request to MDSes */
- for (i = 0; i < max; i++) {
+ for (i = 0; i < max_sessions; i++) {
s = sessions[i];
if (s) {
send_flush_mdlog(s);
@@ -2317,15 +2332,19 @@ retry:
ceph_timeout_jiffies(req1->r_timeout));
if (ret)
err = -EIO;
- ceph_mdsc_put_request(req1);
}
if (req2) {
ret = !wait_for_completion_timeout(&req2->r_safe_completion,
ceph_timeout_jiffies(req2->r_timeout));
if (ret)
err = -EIO;
- ceph_mdsc_put_request(req2);
}
+
+out:
+ if (req1)
+ ceph_mdsc_put_request(req1);
+ if (req2)
+ ceph_mdsc_put_request(req2);
return err;
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 5b9104b8e453..bbed3224ad68 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -583,6 +583,7 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
struct ceph_inode_info *ci = ceph_inode(dir);
struct inode *inode;
struct timespec64 now;
+ struct ceph_string *pool_ns;
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(dir->i_sb);
struct ceph_vino vino = { .ino = req->r_deleg_ino,
.snap = CEPH_NOSNAP };
@@ -632,6 +633,12 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry,
in.max_size = cpu_to_le64(lo->stripe_unit);
ceph_file_layout_to_legacy(lo, &in.layout);
+ /* lo is private, so pool_ns can't change */
+ pool_ns = rcu_dereference_raw(lo->pool_ns);
+ if (pool_ns) {
+ iinfo.pool_ns_len = pool_ns->len;
+ iinfo.pool_ns_data = pool_ns->str;
+ }
down_read(&mdsc->snap_rwsem);
ret = ceph_fill_inode(inode, NULL, &iinfo, NULL, req->r_session,
@@ -750,8 +757,10 @@ retry:
restore_deleg_ino(dir, req->r_deleg_ino);
ceph_mdsc_put_request(req);
try_async = false;
+ ceph_put_string(rcu_dereference_raw(lo.pool_ns));
goto retry;
}
+ ceph_put_string(rcu_dereference_raw(lo.pool_ns));
goto out_req;
}
}
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 11a22a30ee14..0b742bd50642 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -162,7 +162,7 @@ static void cifs_resolve_server(struct work_struct *work)
mutex_unlock(&server->srv_mutex);
}
-/**
+/*
* Mark all sessions and tcons for reconnect.
*
* @server needs to be previously set to CifsNeedReconnect.
@@ -1831,13 +1831,9 @@ void cifs_put_smb_ses(struct cifs_ses *ses)
int i;
for (i = 1; i < chan_count; i++) {
- /*
- * note: for now, we're okay accessing ses->chans
- * without chan_lock. But when chans can go away, we'll
- * need to introduce ref counting to make sure that chan
- * is not freed from under us.
- */
+ spin_unlock(&ses->chan_lock);
cifs_put_tcp_session(ses->chans[i].server, 0);
+ spin_lock(&ses->chan_lock);
ses->chans[i].server = NULL;
}
}
@@ -1981,6 +1977,19 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
}
}
+ ctx->workstation_name = kstrdup(ses->workstation_name, GFP_KERNEL);
+ if (!ctx->workstation_name) {
+ cifs_dbg(FYI, "Unable to allocate memory for workstation_name\n");
+ rc = -ENOMEM;
+ kfree(ctx->username);
+ ctx->username = NULL;
+ kfree_sensitive(ctx->password);
+ ctx->password = NULL;
+ kfree(ctx->domainname);
+ ctx->domainname = NULL;
+ goto out_key_put;
+ }
+
out_key_put:
up_read(&key->sem);
key_put(key);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 59334be9ed3b..e7af802dcfa6 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4269,8 +4269,6 @@ cifs_readv_complete(struct work_struct *work)
for (i = 0; i < rdata->nr_pages; i++) {
struct page *page = rdata->pages[i];
- lru_cache_add(page);
-
if (rdata->result == 0 ||
(rdata->result == -EAGAIN && got_bytes)) {
flush_dcache_page(page);
@@ -4278,12 +4276,12 @@ cifs_readv_complete(struct work_struct *work)
} else
SetPageError(page);
- unlock_page(page);
-
if (rdata->result == 0 ||
(rdata->result == -EAGAIN && got_bytes))
cifs_readpage_to_fscache(rdata->mapping->host, page);
+ unlock_page(page);
+
got_bytes -= min_t(unsigned int, PAGE_SIZE, got_bytes);
put_page(page);
@@ -4340,7 +4338,6 @@ readpages_fill_pages(struct TCP_Server_Info *server,
* fill them until the writes are flushed.
*/
zero_user(page, 0, PAGE_SIZE);
- lru_cache_add(page);
flush_dcache_page(page);
SetPageUptodate(page);
unlock_page(page);
@@ -4350,7 +4347,6 @@ readpages_fill_pages(struct TCP_Server_Info *server,
continue;
} else {
/* no need to hold page hostage */
- lru_cache_add(page);
unlock_page(page);
put_page(page);
rdata->pages[i] = NULL;
@@ -4393,92 +4389,20 @@ cifs_readpages_copy_into_pages(struct TCP_Server_Info *server,
return readpages_fill_pages(server, rdata, iter, iter->count);
}
-static int
-readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
- unsigned int rsize, struct list_head *tmplist,
- unsigned int *nr_pages, loff_t *offset, unsigned int *bytes)
-{
- struct page *page, *tpage;
- unsigned int expected_index;
- int rc;
- gfp_t gfp = readahead_gfp_mask(mapping);
-
- INIT_LIST_HEAD(tmplist);
-
- page = lru_to_page(page_list);
-
- /*
- * Lock the page and put it in the cache. Since no one else
- * should have access to this page, we're safe to simply set
- * PG_locked without checking it first.
- */
- __SetPageLocked(page);
- rc = add_to_page_cache_locked(page, mapping,
- page->index, gfp);
-
- /* give up if we can't stick it in the cache */
- if (rc) {
- __ClearPageLocked(page);
- return rc;
- }
-
- /* move first page to the tmplist */
- *offset = (loff_t)page->index << PAGE_SHIFT;
- *bytes = PAGE_SIZE;
- *nr_pages = 1;
- list_move_tail(&page->lru, tmplist);
-
- /* now try and add more pages onto the request */
- expected_index = page->index + 1;
- list_for_each_entry_safe_reverse(page, tpage, page_list, lru) {
- /* discontinuity ? */
- if (page->index != expected_index)
- break;
-
- /* would this page push the read over the rsize? */
- if (*bytes + PAGE_SIZE > rsize)
- break;
-
- __SetPageLocked(page);
- rc = add_to_page_cache_locked(page, mapping, page->index, gfp);
- if (rc) {
- __ClearPageLocked(page);
- break;
- }
- list_move_tail(&page->lru, tmplist);
- (*bytes) += PAGE_SIZE;
- expected_index++;
- (*nr_pages)++;
- }
- return rc;
-}
-
-static int cifs_readpages(struct file *file, struct address_space *mapping,
- struct list_head *page_list, unsigned num_pages)
+static void cifs_readahead(struct readahead_control *ractl)
{
int rc;
- int err = 0;
- struct list_head tmplist;
- struct cifsFileInfo *open_file = file->private_data;
- struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file);
+ struct cifsFileInfo *open_file = ractl->file->private_data;
+ struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(ractl->file);
struct TCP_Server_Info *server;
pid_t pid;
- unsigned int xid;
+ unsigned int xid, nr_pages, last_batch_size = 0, cache_nr_pages = 0;
+ pgoff_t next_cached = ULONG_MAX;
+ bool caching = fscache_cookie_enabled(cifs_inode_cookie(ractl->mapping->host)) &&
+ cifs_inode_cookie(ractl->mapping->host)->cache_priv;
+ bool check_cache = caching;
xid = get_xid();
- /*
- * Reads as many pages as possible from fscache. Returns -ENOBUFS
- * immediately if the cookie is negative
- *
- * After this point, every page in the list might have PG_fscache set,
- * so we will need to clean that up off of every page we don't use.
- */
- rc = cifs_readpages_from_fscache(mapping->host, mapping, page_list,
- &num_pages);
- if (rc == 0) {
- free_xid(xid);
- return rc;
- }
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
pid = open_file->pid;
@@ -4489,39 +4413,73 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
cifs_dbg(FYI, "%s: file=%p mapping=%p num_pages=%u\n",
- __func__, file, mapping, num_pages);
+ __func__, ractl->file, ractl->mapping, readahead_count(ractl));
/*
- * Start with the page at end of list and move it to private
- * list. Do the same with any following pages until we hit
- * the rsize limit, hit an index discontinuity, or run out of
- * pages. Issue the async read and then start the loop again
- * until the list is empty.
- *
- * Note that list order is important. The page_list is in
- * the order of declining indexes. When we put the pages in
- * the rdata->pages, then we want them in increasing order.
+ * Chop the readahead request up into rsize-sized read requests.
*/
- while (!list_empty(page_list) && !err) {
- unsigned int i, nr_pages, bytes, rsize;
- loff_t offset;
- struct page *page, *tpage;
+ while ((nr_pages = readahead_count(ractl) - last_batch_size)) {
+ unsigned int i, got, rsize;
+ struct page *page;
struct cifs_readdata *rdata;
struct cifs_credits credits_on_stack;
struct cifs_credits *credits = &credits_on_stack;
+ pgoff_t index = readahead_index(ractl) + last_batch_size;
+
+ /*
+ * Find out if we have anything cached in the range of
+ * interest, and if so, where the next chunk of cached data is.
+ */
+ if (caching) {
+ if (check_cache) {
+ rc = cifs_fscache_query_occupancy(
+ ractl->mapping->host, index, nr_pages,
+ &next_cached, &cache_nr_pages);
+ if (rc < 0)
+ caching = false;
+ check_cache = false;
+ }
+
+ if (index == next_cached) {
+ /*
+ * TODO: Send a whole batch of pages to be read
+ * by the cache.
+ */
+ page = readahead_page(ractl);
+ last_batch_size = 1 << thp_order(page);
+ if (cifs_readpage_from_fscache(ractl->mapping->host,
+ page) < 0) {
+ /*
+ * TODO: Deal with cache read failure
+ * here, but for the moment, delegate
+ * that to readpage.
+ */
+ caching = false;
+ }
+ unlock_page(page);
+ next_cached++;
+ cache_nr_pages--;
+ if (cache_nr_pages == 0)
+ check_cache = true;
+ continue;
+ }
+ }
if (open_file->invalidHandle) {
rc = cifs_reopen_file(open_file, true);
- if (rc == -EAGAIN)
- continue;
- else if (rc)
+ if (rc) {
+ if (rc == -EAGAIN)
+ continue;
break;
+ }
}
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
&rsize, credits);
if (rc)
break;
+ nr_pages = min_t(size_t, rsize / PAGE_SIZE, readahead_count(ractl));
+ nr_pages = min_t(size_t, nr_pages, next_cached - index);
/*
* Give up immediately if rsize is too small to read an entire
@@ -4529,16 +4487,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
* reach this point however since we set ra_pages to 0 when the
* rsize is smaller than a cache page.
*/
- if (unlikely(rsize < PAGE_SIZE)) {
- add_credits_and_wake_if(server, credits, 0);
- free_xid(xid);
- return 0;
- }
-
- nr_pages = 0;
- err = readpages_get_pages(mapping, page_list, rsize, &tmplist,
- &nr_pages, &offset, &bytes);
- if (!nr_pages) {
+ if (unlikely(!nr_pages)) {
add_credits_and_wake_if(server, credits, 0);
break;
}
@@ -4546,36 +4495,31 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
rdata = cifs_readdata_alloc(nr_pages, cifs_readv_complete);
if (!rdata) {
/* best to give up if we're out of mem */
- list_for_each_entry_safe(page, tpage, &tmplist, lru) {
- list_del(&page->lru);
- lru_cache_add(page);
- unlock_page(page);
- put_page(page);
- }
- rc = -ENOMEM;
add_credits_and_wake_if(server, credits, 0);
break;
}
- rdata->cfile = cifsFileInfo_get(open_file);
- rdata->server = server;
- rdata->mapping = mapping;
- rdata->offset = offset;
- rdata->bytes = bytes;
- rdata->pid = pid;
- rdata->pagesz = PAGE_SIZE;
- rdata->tailsz = PAGE_SIZE;
+ got = __readahead_batch(ractl, rdata->pages, nr_pages);
+ if (got != nr_pages) {
+ pr_warn("__readahead_batch() returned %u/%u\n",
+ got, nr_pages);
+ nr_pages = got;
+ }
+
+ rdata->nr_pages = nr_pages;
+ rdata->bytes = readahead_batch_length(ractl);
+ rdata->cfile = cifsFileInfo_get(open_file);
+ rdata->server = server;
+ rdata->mapping = ractl->mapping;
+ rdata->offset = readahead_pos(ractl);
+ rdata->pid = pid;
+ rdata->pagesz = PAGE_SIZE;
+ rdata->tailsz = PAGE_SIZE;
rdata->read_into_pages = cifs_readpages_read_into_pages;
rdata->copy_into_pages = cifs_readpages_copy_into_pages;
- rdata->credits = credits_on_stack;
-
- list_for_each_entry_safe(page, tpage, &tmplist, lru) {
- list_del(&page->lru);
- rdata->pages[rdata->nr_pages++] = page;
- }
+ rdata->credits = credits_on_stack;
rc = adjust_credits(server, &rdata->credits, rdata->bytes);
-
if (!rc) {
if (rdata->cfile->invalidHandle)
rc = -EAGAIN;
@@ -4587,7 +4531,6 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
add_credits_and_wake_if(server, &rdata->credits, 0);
for (i = 0; i < rdata->nr_pages; i++) {
page = rdata->pages[i];
- lru_cache_add(page);
unlock_page(page);
put_page(page);
}
@@ -4597,10 +4540,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
}
kref_put(&rdata->refcount, cifs_readdata_release);
+ last_batch_size = nr_pages;
}
free_xid(xid);
- return rc;
}
/*
@@ -4924,7 +4867,7 @@ oplock_break_done:
* In the non-cached mode (mount with cache=none), we shunt off direct read and write requests
* so this method should never be called.
*
- * Direct IO is not yet supported in the cached mode.
+ * Direct IO is not yet supported in the cached mode.
*/
static ssize_t
cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter)
@@ -5006,7 +4949,7 @@ static int cifs_set_page_dirty(struct page *page)
const struct address_space_operations cifs_addr_ops = {
.readpage = cifs_readpage,
- .readpages = cifs_readpages,
+ .readahead = cifs_readahead,
.writepage = cifs_writepage,
.writepages = cifs_writepages,
.write_begin = cifs_write_begin,
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index efaac4d5ff55..33af72e0ac0c 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -134,37 +134,127 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
}
}
+static inline void fscache_end_operation(struct netfs_cache_resources *cres)
+{
+ const struct netfs_cache_ops *ops = fscache_operation_valid(cres);
+
+ if (ops)
+ ops->end_operation(cres);
+}
+
/*
- * Retrieve a page from FS-Cache
+ * Fallback page reading interface.
*/
-int __cifs_readpage_from_fscache(struct inode *inode, struct page *page)
+static int fscache_fallback_read_page(struct inode *inode, struct page *page)
{
- cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n",
- __func__, CIFS_I(inode)->fscache, page, inode);
- return -ENOBUFS; // Needs conversion to using netfslib
+ struct netfs_cache_resources cres;
+ struct fscache_cookie *cookie = cifs_inode_cookie(inode);
+ struct iov_iter iter;
+ struct bio_vec bvec[1];
+ int ret;
+
+ memset(&cres, 0, sizeof(cres));
+ bvec[0].bv_page = page;
+ bvec[0].bv_offset = 0;
+ bvec[0].bv_len = PAGE_SIZE;
+ iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
+
+ ret = fscache_begin_read_operation(&cres, cookie);
+ if (ret < 0)
+ return ret;
+
+ ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL,
+ NULL, NULL);
+ fscache_end_operation(&cres);
+ return ret;
}
/*
- * Retrieve a set of pages from FS-Cache
+ * Fallback page writing interface.
*/
-int __cifs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
+static int fscache_fallback_write_page(struct inode *inode, struct page *page,
+ bool no_space_allocated_yet)
{
- cifs_dbg(FYI, "%s: (0x%p/%u/0x%p)\n",
- __func__, CIFS_I(inode)->fscache, *nr_pages, inode);
- return -ENOBUFS; // Needs conversion to using netfslib
+ struct netfs_cache_resources cres;
+ struct fscache_cookie *cookie = cifs_inode_cookie(inode);
+ struct iov_iter iter;
+ struct bio_vec bvec[1];
+ loff_t start = page_offset(page);
+ size_t len = PAGE_SIZE;
+ int ret;
+
+ memset(&cres, 0, sizeof(cres));
+ bvec[0].bv_page = page;
+ bvec[0].bv_offset = 0;
+ bvec[0].bv_len = PAGE_SIZE;
+ iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE);
+
+ ret = fscache_begin_write_operation(&cres, cookie);
+ if (ret < 0)
+ return ret;
+
+ ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode),
+ no_space_allocated_yet);
+ if (ret == 0)
+ ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL);
+ fscache_end_operation(&cres);
+ return ret;
}
-void __cifs_readpage_to_fscache(struct inode *inode, struct page *page)
+/*
+ * Retrieve a page from FS-Cache
+ */
+int __cifs_readpage_from_fscache(struct inode *inode, struct page *page)
{
- struct cifsInodeInfo *cifsi = CIFS_I(inode);
+ int ret;
- WARN_ON(!cifsi->fscache);
+ cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n",
+ __func__, cifs_inode_cookie(inode), page, inode);
+ ret = fscache_fallback_read_page(inode, page);
+ if (ret < 0)
+ return ret;
+
+ /* Read completed synchronously */
+ SetPageUptodate(page);
+ return 0;
+}
+
+void __cifs_readpage_to_fscache(struct inode *inode, struct page *page)
+{
cifs_dbg(FYI, "%s: (fsc: %p, p: %p, i: %p)\n",
- __func__, cifsi->fscache, page, inode);
+ __func__, cifs_inode_cookie(inode), page, inode);
+
+ fscache_fallback_write_page(inode, page, true);
+}
+
+/*
+ * Query the cache occupancy.
+ */
+int __cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages)
+{
+ struct netfs_cache_resources cres;
+ struct fscache_cookie *cookie = cifs_inode_cookie(inode);
+ loff_t start, data_start;
+ size_t len, data_len;
+ int ret;
- // Needs conversion to using netfslib
+ ret = fscache_begin_read_operation(&cres, cookie);
+ if (ret < 0)
+ return ret;
+
+ start = first * PAGE_SIZE;
+ len = nr_pages * PAGE_SIZE;
+ ret = cres.ops->query_occupancy(&cres, start, len, PAGE_SIZE,
+ &data_start, &data_len);
+ if (ret == 0) {
+ *_data_first = data_start / PAGE_SIZE;
+ *_data_nr_pages = len / PAGE_SIZE;
+ }
+
+ fscache_end_operation(&cres);
+ return ret;
}
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index c6ca49ac33d4..55129908e2c1 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -9,6 +9,7 @@
#ifndef _CIFS_FSCACHE_H
#define _CIFS_FSCACHE_H
+#include <linux/swap.h>
#include <linux/fscache.h>
#include "cifsglob.h"
@@ -58,14 +59,6 @@ void cifs_fscache_fill_coherency(struct inode *inode,
}
-extern int cifs_fscache_release_page(struct page *page, gfp_t gfp);
-extern int __cifs_readpage_from_fscache(struct inode *, struct page *);
-extern int __cifs_readpages_from_fscache(struct inode *,
- struct address_space *,
- struct list_head *,
- unsigned *);
-extern void __cifs_readpage_to_fscache(struct inode *, struct page *);
-
static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode)
{
return CIFS_I(inode)->fscache;
@@ -80,33 +73,52 @@ static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags
i_size_read(inode), flags);
}
-static inline int cifs_readpage_from_fscache(struct inode *inode,
- struct page *page)
-{
- if (CIFS_I(inode)->fscache)
- return __cifs_readpage_from_fscache(inode, page);
+extern int __cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages);
- return -ENOBUFS;
+static inline int cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages)
+{
+ if (!cifs_inode_cookie(inode))
+ return -ENOBUFS;
+ return __cifs_fscache_query_occupancy(inode, first, nr_pages,
+ _data_first, _data_nr_pages);
}
-static inline int cifs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
+extern int __cifs_readpage_from_fscache(struct inode *pinode, struct page *ppage);
+extern void __cifs_readpage_to_fscache(struct inode *pinode, struct page *ppage);
+
+
+static inline int cifs_readpage_from_fscache(struct inode *inode,
+ struct page *page)
{
- if (CIFS_I(inode)->fscache)
- return __cifs_readpages_from_fscache(inode, mapping, pages,
- nr_pages);
+ if (cifs_inode_cookie(inode))
+ return __cifs_readpage_from_fscache(inode, page);
return -ENOBUFS;
}
static inline void cifs_readpage_to_fscache(struct inode *inode,
struct page *page)
{
- if (PageFsCache(page))
+ if (cifs_inode_cookie(inode))
__cifs_readpage_to_fscache(inode, page);
}
+static inline int cifs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+ if (PageFsCache(page)) {
+ if (current_is_kswapd() || !(gfp & __GFP_FS))
+ return false;
+ wait_on_page_fscache(page);
+ fscache_note_page_release(cifs_inode_cookie(page->mapping->host));
+ }
+ return true;
+}
+
#else /* CONFIG_CIFS_FSCACHE */
static inline
void cifs_fscache_fill_coherency(struct inode *inode,
@@ -123,22 +135,29 @@ static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool upd
static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; }
static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {}
-static inline int
-cifs_readpage_from_fscache(struct inode *inode, struct page *page)
+static inline int cifs_fscache_query_occupancy(struct inode *inode,
+ pgoff_t first, unsigned int nr_pages,
+ pgoff_t *_data_first,
+ unsigned int *_data_nr_pages)
{
+ *_data_first = ULONG_MAX;
+ *_data_nr_pages = 0;
return -ENOBUFS;
}
-static inline int cifs_readpages_from_fscache(struct inode *inode,
- struct address_space *mapping,
- struct list_head *pages,
- unsigned *nr_pages)
+static inline int
+cifs_readpage_from_fscache(struct inode *inode, struct page *page)
{
return -ENOBUFS;
}
-static inline void cifs_readpage_to_fscache(struct inode *inode,
- struct page *page) {}
+static inline
+void cifs_readpage_to_fscache(struct inode *inode, struct page *page) {}
+
+static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+ return true; /* May release page */
+}
#endif /* CONFIG_CIFS_FSCACHE */
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7d8b3ceb2af3..60d853c92f6a 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -83,6 +83,7 @@ static void cifs_set_ops(struct inode *inode)
static void
cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
{
+ struct cifs_fscache_inode_coherency_data cd;
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
cifs_dbg(FYI, "%s: revalidating inode %llu\n",
@@ -113,6 +114,9 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
cifs_dbg(FYI, "%s: invalidating inode %llu mapping\n",
__func__, cifs_i->uniqueid);
set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags);
+ /* Invalidate fscache cookie */
+ cifs_fscache_fill_coherency(&cifs_i->vfs_inode, &cd);
+ fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0);
}
/*
@@ -2261,8 +2265,6 @@ cifs_dentry_needs_reval(struct dentry *dentry)
int
cifs_invalidate_mapping(struct inode *inode)
{
- struct cifs_fscache_inode_coherency_data cd;
- struct cifsInodeInfo *cifsi = CIFS_I(inode);
int rc = 0;
if (inode->i_mapping && inode->i_mapping->nrpages != 0) {
@@ -2272,8 +2274,6 @@ cifs_invalidate_mapping(struct inode *inode)
__func__, inode);
}
- cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd);
- fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0);
return rc;
}
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index dc3b16d1be09..5723d50340e5 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -713,7 +713,11 @@ static int size_of_ntlmssp_blob(struct cifs_ses *ses, int base_size)
else
sz += sizeof(__le16);
- sz += sizeof(__le16) * strnlen(ses->workstation_name, CIFS_MAX_WORKSTATION_LEN);
+ if (ses->workstation_name)
+ sz += sizeof(__le16) * strnlen(ses->workstation_name,
+ CIFS_MAX_WORKSTATION_LEN);
+ else
+ sz += sizeof(__le16);
return sz;
}
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 1466b5d01cbb..d3cd2a94d1e8 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1780,8 +1780,8 @@ void configfs_unregister_group(struct config_group *group)
configfs_detach_group(&group->cg_item);
d_inode(dentry)->i_flags |= S_DEAD;
dont_mount(dentry);
+ d_drop(dentry);
fsnotify_rmdir(d_inode(parent), dentry);
- d_delete(dentry);
inode_unlock(d_inode(parent));
dput(dentry);
@@ -1922,10 +1922,10 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys)
configfs_detach_group(&group->cg_item);
d_inode(dentry)->i_flags |= S_DEAD;
dont_mount(dentry);
- fsnotify_rmdir(d_inode(root), dentry);
inode_unlock(d_inode(dentry));
- d_delete(dentry);
+ d_drop(dentry);
+ fsnotify_rmdir(d_inode(root), dentry);
inode_unlock(d_inode(root));
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 42e5a766d33c..4f25015aa534 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -621,8 +621,8 @@ void devpts_pty_kill(struct dentry *dentry)
dentry->d_fsdata = NULL;
drop_nlink(dentry->d_inode);
- fsnotify_unlink(d_inode(dentry->d_parent), dentry);
d_drop(dentry);
+ fsnotify_unlink(d_inode(dentry->d_parent), dentry);
dput(dentry); /* d_alloc_name() in devpts_pty_new() */
}
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index fa7ddb7ad980..226a57c57ee6 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -252,12 +252,10 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
return ret;
iomap->offset = map.m_la;
- if (flags & IOMAP_DAX) {
+ if (flags & IOMAP_DAX)
iomap->dax_dev = mdev.m_daxdev;
- iomap->offset += mdev.m_dax_part_off;
- } else {
+ else
iomap->bdev = mdev.m_bdev;
- }
iomap->length = map.m_llen;
iomap->flags = 0;
iomap->private = NULL;
@@ -284,6 +282,8 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
} else {
iomap->type = IOMAP_MAPPED;
iomap->addr = mdev.m_pa;
+ if (flags & IOMAP_DAX)
+ iomap->addr += mdev.m_dax_part_off;
}
return 0;
}
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 498b7666efe8..423bc1a61da5 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -810,68 +810,11 @@ static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi,
return false;
}
-static void z_erofs_decompressqueue_work(struct work_struct *work);
-static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
- bool sync, int bios)
-{
- struct erofs_sb_info *const sbi = EROFS_SB(io->sb);
-
- /* wake up the caller thread for sync decompression */
- if (sync) {
- unsigned long flags;
-
- spin_lock_irqsave(&io->u.wait.lock, flags);
- if (!atomic_add_return(bios, &io->pending_bios))
- wake_up_locked(&io->u.wait);
- spin_unlock_irqrestore(&io->u.wait.lock, flags);
- return;
- }
-
- if (atomic_add_return(bios, &io->pending_bios))
- return;
- /* Use workqueue and sync decompression for atomic contexts only */
- if (in_atomic() || irqs_disabled()) {
- queue_work(z_erofs_workqueue, &io->u.work);
- /* enable sync decompression for readahead */
- if (sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO)
- sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON;
- return;
- }
- z_erofs_decompressqueue_work(&io->u.work);
-}
-
static bool z_erofs_page_is_invalidated(struct page *page)
{
return !page->mapping && !z_erofs_is_shortlived_page(page);
}
-static void z_erofs_decompressqueue_endio(struct bio *bio)
-{
- tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private);
- struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t);
- blk_status_t err = bio->bi_status;
- struct bio_vec *bvec;
- struct bvec_iter_all iter_all;
-
- bio_for_each_segment_all(bvec, bio, iter_all) {
- struct page *page = bvec->bv_page;
-
- DBG_BUGON(PageUptodate(page));
- DBG_BUGON(z_erofs_page_is_invalidated(page));
-
- if (err)
- SetPageError(page);
-
- if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
- if (!err)
- SetPageUptodate(page);
- unlock_page(page);
- }
- }
- z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1);
- bio_put(bio);
-}
-
static int z_erofs_decompress_pcluster(struct super_block *sb,
struct z_erofs_pcluster *pcl,
struct page **pagepool)
@@ -1123,6 +1066,35 @@ static void z_erofs_decompressqueue_work(struct work_struct *work)
kvfree(bgq);
}
+static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
+ bool sync, int bios)
+{
+ struct erofs_sb_info *const sbi = EROFS_SB(io->sb);
+
+ /* wake up the caller thread for sync decompression */
+ if (sync) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&io->u.wait.lock, flags);
+ if (!atomic_add_return(bios, &io->pending_bios))
+ wake_up_locked(&io->u.wait);
+ spin_unlock_irqrestore(&io->u.wait.lock, flags);
+ return;
+ }
+
+ if (atomic_add_return(bios, &io->pending_bios))
+ return;
+ /* Use workqueue and sync decompression for atomic contexts only */
+ if (in_atomic() || irqs_disabled()) {
+ queue_work(z_erofs_workqueue, &io->u.work);
+ /* enable sync decompression for readahead */
+ if (sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO)
+ sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON;
+ return;
+ }
+ z_erofs_decompressqueue_work(&io->u.work);
+}
+
static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl,
unsigned int nr,
struct page **pagepool,
@@ -1300,6 +1272,33 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl,
qtail[JQ_BYPASS] = &pcl->next;
}
+static void z_erofs_decompressqueue_endio(struct bio *bio)
+{
+ tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private);
+ struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t);
+ blk_status_t err = bio->bi_status;
+ struct bio_vec *bvec;
+ struct bvec_iter_all iter_all;
+
+ bio_for_each_segment_all(bvec, bio, iter_all) {
+ struct page *page = bvec->bv_page;
+
+ DBG_BUGON(PageUptodate(page));
+ DBG_BUGON(z_erofs_page_is_invalidated(page));
+
+ if (err)
+ SetPageError(page);
+
+ if (erofs_page_is_managed(EROFS_SB(q->sb), page)) {
+ if (!err)
+ SetPageUptodate(page);
+ unlock_page(page);
+ }
+ }
+ z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1);
+ bio_put(bio);
+}
+
static void z_erofs_submit_queue(struct super_block *sb,
struct z_erofs_decompress_frontend *f,
struct page **pagepool,
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 18d7fd1a5064..361b1d6e4bf9 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -630,6 +630,13 @@ static int z_erofs_do_map_blocks(struct inode *inode,
if (endoff >= m.clusterofs) {
m.headtype = m.type;
map->m_la = (m.lcn << lclusterbits) | m.clusterofs;
+ /*
+ * For ztailpacking files, in order to inline data more
+ * effectively, special EOF lclusters are now supported
+ * which can have three parts at most.
+ */
+ if (ztailpacking && end > inode->i_size)
+ end = inode->i_size;
break;
}
/* m.lcn should be >= 1 if endoff < m.clusterofs */
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 5a35768d6149..57e82e25f8e2 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -139,7 +139,7 @@ fail:
/*
* Inode operation get_posix_acl().
*
- * inode->i_mutex: don't care
+ * inode->i_rwsem: don't care
*/
struct posix_acl *
ext4_get_acl(struct inode *inode, int type, bool rcu)
@@ -183,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type, bool rcu)
/*
* Set the access or default ACL of an inode.
*
- * inode->i_mutex: down unless called from ext4_new_inode
+ * inode->i_rwsem: down unless called from ext4_new_inode
*/
static int
__ext4_set_acl(handle_t *handle, struct inode *inode, int type,
@@ -271,8 +271,8 @@ out_stop:
/*
* Initialize the ACLs of a new inode. Called from ext4_new_inode.
*
- * dir->i_mutex: down
- * inode->i_mutex: up (access to inode is still exclusive)
+ * dir->i_rwsem: down
+ * inode->i_rwsem: up (access to inode is still exclusive)
*/
int
ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 71a3cdceaa03..bcd3b9bf8069 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1028,7 +1028,7 @@ struct ext4_inode_info {
/*
* Extended attributes can be read independently of the main file
- * data. Taking i_mutex even when reading would cause contention
+ * data. Taking i_rwsem even when reading would cause contention
* between readers of EAs and writers of regular file data, so
* instead we synchronize on xattr_sem when reading or changing
* EAs.
@@ -1750,6 +1750,7 @@ struct ext4_sb_info {
spinlock_t s_fc_lock;
struct buffer_head *s_fc_bh;
struct ext4_fc_stats s_fc_stats;
+ tid_t s_fc_ineligible_tid;
#ifdef CONFIG_EXT4_DEBUG
int s_fc_debug_max_replay;
#endif
@@ -1795,10 +1796,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
enum {
EXT4_MF_MNTDIR_SAMPLED,
EXT4_MF_FS_ABORTED, /* Fatal error detected */
- EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */
- EXT4_MF_FC_COMMITTING /* File system underoing a fast
- * commit.
- */
+ EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */
};
static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
@@ -2485,7 +2483,7 @@ struct ext4_filename {
#ifdef CONFIG_FS_ENCRYPTION
struct fscrypt_str crypto_buf;
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
struct fscrypt_str cf_name;
#endif
};
@@ -2721,7 +2719,7 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb,
struct ext4_group_desc *gdp);
ext4_fsblk_t ext4_inode_to_goal_block(struct inode *);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
extern int ext4_fname_setup_ci_filename(struct inode *dir,
const struct qstr *iname,
struct ext4_filename *fname);
@@ -2754,7 +2752,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
ext4_fname_from_fscrypt_name(fname, &name);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
return err;
@@ -2773,7 +2771,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
ext4_fname_from_fscrypt_name(fname, &name);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
#endif
return err;
@@ -2790,7 +2788,7 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname)
fname->usr_fname = NULL;
fname->disk_name.name = NULL;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
kfree(fname->cf_name.name);
fname->cf_name.name = NULL;
#endif
@@ -2806,7 +2804,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
fname->disk_name.name = (unsigned char *) iname->name;
fname->disk_name.len = iname->len;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, iname, fname);
#endif
@@ -2822,7 +2820,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir,
static inline void ext4_fname_free_filename(struct ext4_filename *fname)
{
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
kfree(fname->cf_name.name);
fname->cf_name.name = NULL;
#endif
@@ -2926,7 +2924,7 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
struct dentry *dentry);
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
-void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
void ext4_fc_start_update(struct inode *inode);
void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
@@ -2935,6 +2933,9 @@ void ext4_fc_replay_cleanup(struct super_block *sb);
int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
int __init ext4_fc_init_dentry_cache(void);
void ext4_fc_destroy_dentry_cache(void);
+int ext4_fc_record_regions(struct super_block *sb, int ino,
+ ext4_lblk_t lblk, ext4_fsblk_t pblk,
+ int len, int replay);
/* mballoc.c */
extern const struct seq_operations ext4_mb_seq_groups_ops;
@@ -3407,7 +3408,7 @@ do { \
#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
-/* Update i_disksize. Requires i_mutex to avoid races with truncate */
+/* Update i_disksize. Requires i_rwsem to avoid races with truncate */
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
@@ -3418,7 +3419,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
up_write(&EXT4_I(inode)->i_data_sem);
}
-/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
+/* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */
static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
{
int changed = 0;
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 0e4fa644df01..db2ae4a2b38d 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -491,7 +491,7 @@ static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks)
/*
* This function controls whether or not we should try to go down the
* dioread_nolock code paths, which makes it safe to avoid taking
- * i_mutex for direct I/O reads. This only works for extent-based
+ * i_rwsem for direct I/O reads. This only works for extent-based
* files, and it doesn't work if data journaling is enabled, since the
* dioread_nolock code uses b_private to pass information back to the
* I/O completion handler, and this conflicts with the jbd's use of
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 74c91da585d7..c0f3f83e0c1b 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -97,7 +97,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
* Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
* moment, get_block can be called only for blocks inside i_size since
* page cache has been already dropped and writes are blocked by
- * i_mutex. So we can safely drop the i_data_sem here.
+ * i_rwsem. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
ext4_discard_preallocations(inode, 0);
@@ -4572,7 +4572,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT;
- /* Wait all existing dio workers, newcomers will block on i_mutex */
+ /* Wait all existing dio workers, newcomers will block on i_rwsem */
inode_dio_wait(inode);
/* Preallocate the range including the unaligned edges */
@@ -4738,7 +4738,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
goto out;
}
- /* Wait all existing dio workers, newcomers will block on i_mutex */
+ /* Wait all existing dio workers, newcomers will block on i_rwsem */
inode_dio_wait(inode);
ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags);
@@ -5334,7 +5334,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
ret = PTR_ERR(handle);
goto out_mmap;
}
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode, 0);
@@ -5474,7 +5474,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
ret = PTR_ERR(handle);
goto out_mmap;
}
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
/* Expand file to avoid data loss if there is error while shifting */
inode->i_size += len;
@@ -5571,7 +5571,7 @@ out_mutex:
* stuff such as page-cache locking consistency, bh mapping consistency or
* extent's data copying must be performed by caller.
* Locking:
- * i_mutex is held for both inodes
+ * i_rwsem is held for both inodes
* i_data_sem is locked for write for both inodes
* Assumptions:
* All pages from requested range are locked for both inodes
@@ -6091,11 +6091,15 @@ int ext4_ext_clear_bb(struct inode *inode)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 0);
+ ext4_fc_record_regions(inode->i_sb, inode->i_ino,
+ 0, path[j].p_block, 1, 1);
}
ext4_ext_drop_refs(path);
kfree(path);
}
ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+ ext4_fc_record_regions(inode->i_sb, inode->i_ino,
+ map.m_lblk, map.m_pblk, map.m_len, 1);
}
cur = cur + map.m_len;
}
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 5ae8026a0c56..7964ee34e322 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -300,18 +300,32 @@ restart:
}
/*
- * Mark file system as fast commit ineligible. This means that next commit
- * operation would result in a full jbd2 commit.
+ * Mark file system as fast commit ineligible, and record latest
+ * ineligible transaction tid. This means until the recorded
+ * transaction, commit operation would result in a full jbd2 commit.
*/
-void ext4_fc_mark_ineligible(struct super_block *sb, int reason)
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
+ tid_t tid;
if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
return;
ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ if (handle && !IS_ERR(handle))
+ tid = handle->h_transaction->t_tid;
+ else {
+ read_lock(&sbi->s_journal->j_state_lock);
+ tid = sbi->s_journal->j_running_transaction ?
+ sbi->s_journal->j_running_transaction->t_tid : 0;
+ read_unlock(&sbi->s_journal->j_state_lock);
+ }
+ spin_lock(&sbi->s_fc_lock);
+ if (sbi->s_fc_ineligible_tid < tid)
+ sbi->s_fc_ineligible_tid = tid;
+ spin_unlock(&sbi->s_fc_lock);
WARN_ON(reason >= EXT4_FC_REASON_MAX);
sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
}
@@ -361,7 +375,8 @@ static int ext4_fc_track_template(
spin_lock(&sbi->s_fc_lock);
if (list_empty(&EXT4_I(inode)->i_fc_list))
list_add_tail(&EXT4_I(inode)->i_fc_list,
- (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
+ (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+ sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ?
&sbi->s_fc_q[FC_Q_STAGING] :
&sbi->s_fc_q[FC_Q_MAIN]);
spin_unlock(&sbi->s_fc_lock);
@@ -387,7 +402,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
mutex_unlock(&ei->i_fc_lock);
node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
if (!node) {
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -400,7 +415,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
if (!node->fcd_name.name) {
kmem_cache_free(ext4_fc_dentry_cachep, node);
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_NOMEM);
+ EXT4_FC_REASON_NOMEM, NULL);
mutex_lock(&ei->i_fc_lock);
return -ENOMEM;
}
@@ -414,7 +429,8 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
node->fcd_name.len = dentry->d_name.len;
spin_lock(&sbi->s_fc_lock);
- if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
+ if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+ sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING)
list_add_tail(&node->fcd_list,
&sbi->s_fc_dentry_q[FC_Q_STAGING]);
else
@@ -502,7 +518,7 @@ void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
if (ext4_should_journal_data(inode)) {
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_INODE_JOURNAL_DATA);
+ EXT4_FC_REASON_INODE_JOURNAL_DATA, handle);
return;
}
@@ -879,7 +895,6 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
int ret = 0;
spin_lock(&sbi->s_fc_lock);
- ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
while (atomic_read(&ei->i_fc_updates)) {
@@ -1179,7 +1194,7 @@ fallback:
* Fast commit cleanup routine. This is called after every fast commit and
* full commit. full is true if we are called after a full commit.
*/
-static void ext4_fc_cleanup(journal_t *journal, int full)
+static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
{
struct super_block *sb = journal->j_private;
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -1197,7 +1212,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_del_init(&iter->i_fc_list);
ext4_clear_inode_state(&iter->vfs_inode,
EXT4_STATE_FC_COMMITTING);
- ext4_fc_reset_inode(&iter->vfs_inode);
+ if (iter->i_sync_tid <= tid)
+ ext4_fc_reset_inode(&iter->vfs_inode);
/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
smp_mb();
#if (BITS_PER_LONG < 64)
@@ -1226,8 +1242,10 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
&sbi->s_fc_q[FC_Q_MAIN]);
- ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
- ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ if (tid >= sbi->s_fc_ineligible_tid) {
+ sbi->s_fc_ineligible_tid = 0;
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ }
if (full)
sbi->s_fc_bytes = 0;
@@ -1392,14 +1410,15 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
if (state->fc_modified_inodes[i] == ino)
return 0;
if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) {
- state->fc_modified_inodes_size +=
- EXT4_FC_REPLAY_REALLOC_INCREMENT;
state->fc_modified_inodes = krealloc(
- state->fc_modified_inodes, sizeof(int) *
- state->fc_modified_inodes_size,
- GFP_KERNEL);
+ state->fc_modified_inodes,
+ sizeof(int) * (state->fc_modified_inodes_size +
+ EXT4_FC_REPLAY_REALLOC_INCREMENT),
+ GFP_KERNEL);
if (!state->fc_modified_inodes)
return -ENOMEM;
+ state->fc_modified_inodes_size +=
+ EXT4_FC_REPLAY_REALLOC_INCREMENT;
}
state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino;
return 0;
@@ -1431,7 +1450,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
}
inode = NULL;
- ext4_fc_record_modified_inode(sb, ino);
+ ret = ext4_fc_record_modified_inode(sb, ino);
+ if (ret)
+ goto out;
raw_fc_inode = (struct ext4_inode *)
(val + offsetof(struct ext4_fc_inode, fc_raw_inode));
@@ -1563,16 +1584,23 @@ out:
}
/*
- * Record physical disk regions which are in use as per fast commit area. Our
- * simple replay phase allocator excludes these regions from allocation.
+ * Record physical disk regions which are in use as per fast commit area,
+ * and used by inodes during replay phase. Our simple replay phase
+ * allocator excludes these regions from allocation.
*/
-static int ext4_fc_record_regions(struct super_block *sb, int ino,
- ext4_lblk_t lblk, ext4_fsblk_t pblk, int len)
+int ext4_fc_record_regions(struct super_block *sb, int ino,
+ ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay)
{
struct ext4_fc_replay_state *state;
struct ext4_fc_alloc_region *region;
state = &EXT4_SB(sb)->s_fc_replay_state;
+ /*
+ * during replay phase, the fc_regions_valid may not same as
+ * fc_regions_used, update it when do new additions.
+ */
+ if (replay && state->fc_regions_used != state->fc_regions_valid)
+ state->fc_regions_used = state->fc_regions_valid;
if (state->fc_regions_used == state->fc_regions_size) {
state->fc_regions_size +=
EXT4_FC_REPLAY_REALLOC_INCREMENT;
@@ -1590,6 +1618,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino,
region->pblk = pblk;
region->len = len;
+ if (replay)
+ state->fc_regions_valid++;
+
return 0;
}
@@ -1621,6 +1652,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
}
ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+ if (ret)
+ goto out;
start = le32_to_cpu(ex->ee_block);
start_pblk = ext4_ext_pblock(ex);
@@ -1638,18 +1671,14 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
map.m_pblk = 0;
ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0) {
- iput(inode);
- return 0;
- }
+ if (ret < 0)
+ goto out;
if (ret == 0) {
/* Range is not mapped */
path = ext4_find_extent(inode, cur, NULL, 0);
- if (IS_ERR(path)) {
- iput(inode);
- return 0;
- }
+ if (IS_ERR(path))
+ goto out;
memset(&newex, 0, sizeof(newex));
newex.ee_block = cpu_to_le32(cur);
ext4_ext_store_pblock(
@@ -1663,10 +1692,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
up_write((&EXT4_I(inode)->i_data_sem));
ext4_ext_drop_refs(path);
kfree(path);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
goto next;
}
@@ -1679,10 +1706,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
ext4_ext_is_unwritten(ex),
start_pblk + cur - start);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
/*
* Mark the old blocks as free since they aren't used
* anymore. We maintain an array of all the modified
@@ -1702,10 +1727,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
ext4_ext_is_unwritten(ex), map.m_pblk);
ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
ext4_ext_is_unwritten(ex), map.m_pblk);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
/*
* We may have split the extent tree while toggling the state.
* Try to shrink the extent tree now.
@@ -1717,6 +1740,7 @@ next:
}
ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >>
sb->s_blocksize_bits);
+out:
iput(inode);
return 0;
}
@@ -1746,6 +1770,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
}
ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+ if (ret)
+ goto out;
jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n",
inode->i_ino, le32_to_cpu(lrange.fc_lblk),
@@ -1755,10 +1781,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
map.m_len = remaining;
ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0) {
- iput(inode);
- return 0;
- }
+ if (ret < 0)
+ goto out;
if (ret > 0) {
remaining -= ret;
cur += ret;
@@ -1770,18 +1794,17 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl,
}
down_write(&EXT4_I(inode)->i_data_sem);
- ret = ext4_ext_remove_space(inode, lrange.fc_lblk,
- lrange.fc_lblk + lrange.fc_len - 1);
+ ret = ext4_ext_remove_space(inode, le32_to_cpu(lrange.fc_lblk),
+ le32_to_cpu(lrange.fc_lblk) +
+ le32_to_cpu(lrange.fc_len) - 1);
up_write(&EXT4_I(inode)->i_data_sem);
- if (ret) {
- iput(inode);
- return 0;
- }
+ if (ret)
+ goto out;
ext4_ext_replay_shrink_inode(inode,
i_size_read(inode) >> sb->s_blocksize_bits);
ext4_mark_inode_dirty(NULL, inode);
+out:
iput(inode);
-
return 0;
}
@@ -1937,7 +1960,7 @@ static int ext4_fc_replay_scan(journal_t *journal,
ret = ext4_fc_record_regions(sb,
le32_to_cpu(ext.fc_ino),
le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex),
- ext4_ext_get_actual_len(ex));
+ ext4_ext_get_actual_len(ex), 0);
if (ret < 0)
break;
ret = JBD2_FC_REPLAY_CONTINUE;
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index f34f4176c1e7..147b5241dd94 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -290,7 +290,7 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len,
int ext4fs_dirhash(const struct inode *dir, const char *name, int len,
struct dx_hash_info *hinfo)
{
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
const struct unicode_map *um = dir->i_sb->s_encoding;
int r, dlen;
unsigned char *buff;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 89efa78ed4b2..07a8c75b65ed 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
* Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
* moment, get_block can be called only for blocks inside i_size since
* page cache has been already dropped and writes are blocked by
- * i_mutex. So we can safely drop the i_data_sem here.
+ * i_rwsem. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
ext4_discard_preallocations(inode, 0);
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 635bcf68a67e..e42941803605 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -911,7 +911,7 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping,
struct page **pagep,
void **fsdata)
{
- int ret, inline_size;
+ int ret;
handle_t *handle;
struct page *page;
struct ext4_iloc iloc;
@@ -928,14 +928,9 @@ retry_journal:
goto out;
}
- inline_size = ext4_get_max_inline_size(inode);
-
- ret = -ENOSPC;
- if (inline_size >= pos + len) {
- ret = ext4_prepare_inline_data(handle, inode, pos + len);
- if (ret && ret != -ENOSPC)
- goto out_journal;
- }
+ ret = ext4_prepare_inline_data(handle, inode, pos + len);
+ if (ret && ret != -ENOSPC)
+ goto out_journal;
/*
* We cannot recurse into the filesystem as the transaction
@@ -1133,7 +1128,15 @@ static void ext4_restore_inline_data(handle_t *handle, struct inode *inode,
struct ext4_iloc *iloc,
void *buf, int inline_size)
{
- ext4_create_inline_data(handle, inode, inline_size);
+ int ret;
+
+ ret = ext4_create_inline_data(handle, inode, inline_size);
+ if (ret) {
+ ext4_msg(inode->i_sb, KERN_EMERG,
+ "error restoring inline_data for inode -- potential data loss! (inode %lu, error %d)",
+ inode->i_ino, ret);
+ return;
+ }
ext4_write_inline_data(inode, iloc, buf, 0, inline_size);
ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5f79d265d06a..01c9e4f743ba 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -338,7 +338,7 @@ stop_handle:
return;
no_delete:
if (!list_empty(&EXT4_I(inode)->i_fc_list))
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL);
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
@@ -1224,7 +1224,7 @@ retry_journal:
/*
* __block_write_begin may have instantiated a few blocks
* outside i_size. Trim these off again. Don't need
- * i_size_read because we hold i_mutex.
+ * i_size_read because we hold i_rwsem.
*
* Add inode to orphan list in case we crash before
* truncate finishes
@@ -3979,7 +3979,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
}
- /* Wait all existing dio workers, newcomers will block on i_mutex */
+ /* Wait all existing dio workers, newcomers will block on i_rwsem */
inode_dio_wait(inode);
/*
@@ -4129,7 +4129,7 @@ int ext4_truncate(struct inode *inode)
/*
* There is a possibility that we're either freeing the inode
* or it's a completely new inode. In those cases we might not
- * have i_mutex locked because it's not necessary.
+ * have i_rwsem locked because it's not necessary.
*/
if (!(inode->i_state & (I_NEW|I_FREEING)))
WARN_ON(!inode_is_locked(inode));
@@ -5271,7 +5271,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
* transaction are already on disk (truncate waits for pages under
* writeback).
*
- * Called with inode->i_mutex down.
+ * Called with inode->i_rwsem down.
*/
int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry,
struct iattr *attr)
@@ -5983,7 +5983,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val)
return PTR_ERR(handle);
ext4_fc_mark_ineligible(inode->i_sb,
- EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
+ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle);
err = ext4_mark_inode_dirty(handle, inode);
ext4_handle_sync(handle);
ext4_journal_stop(handle);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bbbedf27b71c..a8022c2c6a58 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -411,7 +411,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
err = -EINVAL;
goto err_out;
}
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle);
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
@@ -1373,7 +1373,7 @@ mext_out:
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
- ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
+ ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL);
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 9f86dd947032..67ac95c4cd9b 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -5753,7 +5753,8 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
struct super_block *sb = ar->inode->i_sb;
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i = sb->s_blocksize;
+ ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb);
+ ext4_grpblk_t i = 0;
ext4_fsblk_t goal, block;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
@@ -5775,19 +5776,26 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
ext4_get_group_no_and_offset(sb,
max(ext4_group_first_block_no(sb, group), goal),
NULL, &blkoff);
- i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize,
+ while (1) {
+ i = mb_find_next_zero_bit(bitmap_bh->b_data, max,
blkoff);
+ if (i >= max)
+ break;
+ if (ext4_fc_replay_check_excluded(sb,
+ ext4_group_first_block_no(sb, group) + i)) {
+ blkoff = i + 1;
+ } else
+ break;
+ }
brelse(bitmap_bh);
- if (i >= sb->s_blocksize)
- continue;
- if (ext4_fc_replay_check_excluded(sb,
- ext4_group_first_block_no(sb, group) + i))
- continue;
- break;
+ if (i < max)
+ break;
}
- if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize)
+ if (group >= ext4_get_groups_count(sb) || i >= max) {
+ *errp = -ENOSPC;
return 0;
+ }
block = ext4_group_first_block_no(sb, group) + i;
ext4_mb_mark_bb(sb, block, 1, 1);
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index ff8916e1d38e..7a5353a8cfd7 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -485,7 +485,7 @@ int ext4_ext_migrate(struct inode *inode)
* when we add extents we extent the journal
*/
/*
- * Even though we take i_mutex we can still cause block
+ * Even though we take i_rwsem we can still cause block
* allocation via mmap write to holes. If we have allocated
* new blocks we fail migrate. New block allocation will
* clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 52c9bd154122..8cf0a924a49b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1317,7 +1317,7 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
dx_set_count(entries, count + 1);
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/*
* Test whether a case-insensitive directory entry matches the filename
* being searched for. If quick is set, assume the name being looked up
@@ -1428,7 +1428,7 @@ static bool ext4_match(struct inode *parent,
f.crypto_buf = fname->crypto_buf;
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) &&
(!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
if (fname->cf_name.name) {
@@ -1800,7 +1800,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
}
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (!inode && IS_CASEFOLDED(dir)) {
/* Eventually we want to call d_add_ci(dentry, NULL)
* for negative dentries in the encoding case as
@@ -2308,7 +2308,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
if (fscrypt_is_nokey_name(dentry))
return -ENOKEY;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
return -EINVAL;
@@ -3126,7 +3126,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
ext4_fc_track_unlink(handle, dentry);
retval = ext4_mark_inode_dirty(handle, dir);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
@@ -3231,7 +3231,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
if (!retval)
ext4_fc_track_unlink(handle, dentry);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
@@ -3889,7 +3889,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
* dirents in directories.
*/
ext4_fc_mark_ineligible(old.inode->i_sb,
- EXT4_FC_REASON_RENAME_DIR);
+ EXT4_FC_REASON_RENAME_DIR, handle);
} else {
if (new.inode)
ext4_fc_track_unlink(handle, new.dentry);
@@ -4049,7 +4049,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
if (unlikely(retval))
goto end_rename;
ext4_fc_mark_ineligible(new.inode->i_sb,
- EXT4_FC_REASON_CROSS_RENAME);
+ EXT4_FC_REASON_CROSS_RENAME, handle);
if (old.dir_bh) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
if (retval)
diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c
index 53adc8f570a3..7de0612eb42d 100644
--- a/fs/ext4/orphan.c
+++ b/fs/ext4/orphan.c
@@ -93,7 +93,7 @@ static int ext4_orphan_file_add(handle_t *handle, struct inode *inode)
* At filesystem recovery time, we walk this list deleting unlinked
* inodes and truncating linked inodes in ext4_orphan_cleanup().
*
- * Orphan list manipulation functions must be called under i_mutex unless
+ * Orphan list manipulation functions must be called under i_rwsem unless
* we are just creating the inode or deleting it.
*/
int ext4_orphan_add(handle_t *handle, struct inode *inode)
@@ -119,7 +119,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
/*
* Orphan handling is only valid for files with data blocks
* being truncated, or files being unlinked. Note that we either
- * hold i_mutex, or the inode can not be referenced from outside,
+ * hold i_rwsem, or the inode can not be referenced from outside,
* so i_nlink should not be bumped due to race
*/
ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index eee0d9ebfa6c..c5021ca0a28a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1301,7 +1301,7 @@ static void ext4_put_super(struct super_block *sb)
kfree(sbi->s_blockgroup_lock);
fs_put_dax(sbi->s_daxdev);
fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
utf8_unload(sb->s_encoding);
#endif
kfree(sbi);
@@ -1961,7 +1961,7 @@ static const struct mount_opts {
{Opt_err, 0, 0}
};
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
static const struct ext4_sb_encodings {
__u16 magic;
char *name;
@@ -3606,7 +3606,7 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly)
return 0;
}
-#ifndef CONFIG_UNICODE
+#if !IS_ENABLED(CONFIG_UNICODE)
if (ext4_has_feature_casefold(sb)) {
ext4_msg(sb, KERN_ERR,
"Filesystem with casefold feature cannot be "
@@ -4610,7 +4610,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
if (err < 0)
goto failed_mount;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (ext4_has_feature_casefold(sb) && !sb->s_encoding) {
const struct ext4_sb_encodings *encoding_info;
struct unicode_map *encoding;
@@ -5082,7 +5082,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
sbi->s_fc_bytes = 0;
ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
- ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+ sbi->s_fc_ineligible_tid = 0;
spin_lock_init(&sbi->s_fc_lock);
memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
sbi->s_fc_replay_state.fc_regions = NULL;
@@ -5514,7 +5514,7 @@ failed_mount:
if (sbi->s_chksum_driver)
crypto_free_shash(sbi->s_chksum_driver);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
utf8_unload(sb->s_encoding);
#endif
@@ -5540,7 +5540,7 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc)
sbi = ext4_alloc_sbi(sb);
if (!sbi)
- ret = -ENOMEM;
+ return -ENOMEM;
fc->s_fs_info = sbi;
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index f61e65ae27d8..d233c24ea342 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -309,7 +309,7 @@ EXT4_ATTR_FEATURE(meta_bg_resize);
EXT4_ATTR_FEATURE(encryption);
EXT4_ATTR_FEATURE(test_dummy_encryption_v2);
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
EXT4_ATTR_FEATURE(casefold);
#endif
#ifdef CONFIG_FS_VERITY
@@ -317,7 +317,7 @@ EXT4_ATTR_FEATURE(verity);
#endif
EXT4_ATTR_FEATURE(metadata_csum_seed);
EXT4_ATTR_FEATURE(fast_commit);
-#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
+#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
EXT4_ATTR_FEATURE(encrypted_casefold);
#endif
@@ -329,7 +329,7 @@ static struct attribute *ext4_feat_attrs[] = {
ATTR_LIST(encryption),
ATTR_LIST(test_dummy_encryption_v2),
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
ATTR_LIST(casefold),
#endif
#ifdef CONFIG_FS_VERITY
@@ -337,7 +337,7 @@ static struct attribute *ext4_feat_attrs[] = {
#endif
ATTR_LIST(metadata_csum_seed),
ATTR_LIST(fast_commit),
-#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
+#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION)
ATTR_LIST(encrypted_casefold),
#endif
NULL,
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 1e0fc1ed845b..042325349098 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2408,7 +2408,7 @@ retry_inode:
if (IS_SYNC(inode))
ext4_handle_sync(handle);
}
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle);
cleanup:
brelse(is.iloc.bh);
@@ -2486,7 +2486,7 @@ retry:
if (error == 0)
error = error2;
}
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL);
return error;
}
@@ -2920,7 +2920,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
error);
goto cleanup;
}
- ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle);
}
error = 0;
cleanup:
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 1820e9c106f7..166f08623362 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -16,7 +16,7 @@
#include "xattr.h"
#include <trace/events/f2fs.h>
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
extern struct kmem_cache *f2fs_cf_name_slab;
#endif
@@ -79,7 +79,7 @@ unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de)
int f2fs_init_casefolded_name(const struct inode *dir,
struct f2fs_filename *fname)
{
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
struct super_block *sb = dir->i_sb;
if (IS_CASEFOLDED(dir)) {
@@ -174,7 +174,7 @@ void f2fs_free_filename(struct f2fs_filename *fname)
kfree(fname->crypto_buf.name);
fname->crypto_buf.name = NULL;
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (fname->cf_name.name) {
kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
fname->cf_name.name = NULL;
@@ -208,7 +208,7 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir,
return f2fs_find_target_dentry(&d, fname, max_slots);
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/*
* Test whether a case-insensitive directory entry matches the filename
* being searched for.
@@ -266,7 +266,7 @@ static inline int f2fs_match_name(const struct inode *dir,
{
struct fscrypt_name f;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (fname->cf_name.name) {
struct qstr cf = FSTR_TO_QSTR(&fname->cf_name);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index eb22fa91c2b2..68b44015514f 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -488,7 +488,7 @@ struct f2fs_filename {
*/
struct fscrypt_str crypto_buf;
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/*
* For casefolded directories: the casefolded name, but it's left NULL
* if the original name is not valid Unicode, if the directory is both
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index e3beac546c63..3cb1e7a24740 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -105,7 +105,7 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname)
return;
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (IS_CASEFOLDED(dir)) {
/*
* If the casefolded name is provided, hash it instead of the
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a728a0af9ce0..5f213f05556d 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -561,7 +561,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
goto out_iput;
}
out_splice:
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (!inode && IS_CASEFOLDED(dir)) {
/* Eventually we want to call d_add_ci(dentry, NULL)
* for negative dentries in the encoding case as
@@ -622,7 +622,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
goto fail;
}
f2fs_delete_entry(de, page, dir, inode);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/* VFS negative dentries are incompatible with Encoding and
* Case-insensitiveness. Eventually we'll want avoid
* invalidating the dentries here, alongside with returning the
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 9683c80ff8c2..79773d322c47 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -46,7 +46,7 @@
static struct kmem_cache *fsync_entry_slab;
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
extern struct kmem_cache *f2fs_cf_name_slab;
#endif
@@ -149,7 +149,7 @@ static int init_recovered_filename(const struct inode *dir,
if (err)
return err;
f2fs_hash_filename(dir, fname);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/* Case-sensitive match is fine for recovery */
kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name);
fname->cf_name.name = NULL;
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 76e6a3df9aba..baefd398ec1a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -257,7 +257,7 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
va_end(args);
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
static const struct f2fs_sb_encodings {
__u16 magic;
char *name;
@@ -1259,7 +1259,7 @@ default_check:
return -EINVAL;
}
#endif
-#ifndef CONFIG_UNICODE
+#if !IS_ENABLED(CONFIG_UNICODE)
if (f2fs_sb_has_casefold(sbi)) {
f2fs_err(sbi,
"Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE");
@@ -1619,7 +1619,7 @@ static void f2fs_put_super(struct super_block *sb)
f2fs_destroy_iostat(sbi);
for (i = 0; i < NR_PAGE_TYPE; i++)
kvfree(sbi->write_io[i]);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
utf8_unload(sb->s_encoding);
#endif
kfree(sbi);
@@ -3903,7 +3903,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
{
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) {
const struct f2fs_sb_encodings *encoding_info;
struct unicode_map *encoding;
@@ -4458,7 +4458,7 @@ free_bio_info:
for (i = 0; i < NR_PAGE_TYPE; i++)
kvfree(sbi->write_io[i]);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
utf8_unload(sb->s_encoding);
sb->s_encoding = NULL;
#endif
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
index df406c16b2eb..8ac506671245 100644
--- a/fs/f2fs/sysfs.c
+++ b/fs/f2fs/sysfs.c
@@ -201,7 +201,7 @@ static ssize_t unusable_show(struct f2fs_attr *a,
static ssize_t encoding_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
struct super_block *sb = sbi->sb;
if (f2fs_sb_has_casefold(sbi))
@@ -778,7 +778,7 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks);
#ifdef CONFIG_FS_ENCRYPTION
F2FS_FEATURE_RO_ATTR(encryption);
F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
F2FS_FEATURE_RO_ATTR(encrypted_casefold);
#endif
#endif /* CONFIG_FS_ENCRYPTION */
@@ -797,7 +797,7 @@ F2FS_FEATURE_RO_ATTR(lost_found);
F2FS_FEATURE_RO_ATTR(verity);
#endif
F2FS_FEATURE_RO_ATTR(sb_checksum);
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
F2FS_FEATURE_RO_ATTR(casefold);
#endif
F2FS_FEATURE_RO_ATTR(readonly);
@@ -910,7 +910,7 @@ static struct attribute *f2fs_feat_attrs[] = {
#ifdef CONFIG_FS_ENCRYPTION
ATTR_LIST(encryption),
ATTR_LIST(test_dummy_encryption_v2),
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
ATTR_LIST(encrypted_casefold),
#endif
#endif /* CONFIG_FS_ENCRYPTION */
@@ -929,7 +929,7 @@ static struct attribute *f2fs_feat_attrs[] = {
ATTR_LIST(verity),
#endif
ATTR_LIST(sb_checksum),
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
ATTR_LIST(casefold),
#endif
ATTR_LIST(readonly),
diff --git a/fs/file_table.c b/fs/file_table.c
index 57edef16dce4..4969021fa676 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -119,6 +119,8 @@ static struct ctl_table fs_stat_sysctls[] = {
static int __init init_fs_stat_sysctls(void)
{
register_sysctl_init("fs", fs_stat_sysctls);
+ if (IS_ENABLED(CONFIG_BINFMT_MISC))
+ register_sysctl_mount_point("fs/binfmt_misc");
return 0;
}
fs_initcall(init_fs_stat_sysctls);
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index c938bbad075e..6c51a75d0be6 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -21,6 +21,8 @@
#include "../internal.h"
+#define IOEND_BATCH_SIZE 4096
+
/*
* Structure allocated for each folio when block size < folio size
* to track sub-folio uptodate status and I/O completions.
@@ -1039,7 +1041,7 @@ static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
* state, release holds on bios, and finally free up memory. Do not use the
* ioend after this.
*/
-static void
+static u32
iomap_finish_ioend(struct iomap_ioend *ioend, int error)
{
struct inode *inode = ioend->io_inode;
@@ -1048,6 +1050,7 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
u64 start = bio->bi_iter.bi_sector;
loff_t offset = ioend->io_offset;
bool quiet = bio_flagged(bio, BIO_QUIET);
+ u32 folio_count = 0;
for (bio = &ioend->io_inline_bio; bio; bio = next) {
struct folio_iter fi;
@@ -1062,9 +1065,11 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
next = bio->bi_private;
/* walk all folios in bio, ending page IO on them */
- bio_for_each_folio_all(fi, bio)
+ bio_for_each_folio_all(fi, bio) {
iomap_finish_folio_write(inode, fi.folio, fi.length,
error);
+ folio_count++;
+ }
bio_put(bio);
}
/* The ioend has been freed by bio_put() */
@@ -1074,20 +1079,36 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
"%s: writeback error on inode %lu, offset %lld, sector %llu",
inode->i_sb->s_id, inode->i_ino, offset, start);
}
+ return folio_count;
}
+/*
+ * Ioend completion routine for merged bios. This can only be called from task
+ * contexts as merged ioends can be of unbound length. Hence we have to break up
+ * the writeback completions into manageable chunks to avoid long scheduler
+ * holdoffs. We aim to keep scheduler holdoffs down below 10ms so that we get
+ * good batch processing throughput without creating adverse scheduler latency
+ * conditions.
+ */
void
iomap_finish_ioends(struct iomap_ioend *ioend, int error)
{
struct list_head tmp;
+ u32 completions;
+
+ might_sleep();
list_replace_init(&ioend->io_list, &tmp);
- iomap_finish_ioend(ioend, error);
+ completions = iomap_finish_ioend(ioend, error);
while (!list_empty(&tmp)) {
+ if (completions > IOEND_BATCH_SIZE * 8) {
+ cond_resched();
+ completions = 0;
+ }
ioend = list_first_entry(&tmp, struct iomap_ioend, io_list);
list_del_init(&ioend->io_list);
- iomap_finish_ioend(ioend, error);
+ completions += iomap_finish_ioend(ioend, error);
}
}
EXPORT_SYMBOL_GPL(iomap_finish_ioends);
@@ -1108,6 +1129,18 @@ iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
return false;
if (ioend->io_offset + ioend->io_size != next->io_offset)
return false;
+ /*
+ * Do not merge physically discontiguous ioends. The filesystem
+ * completion functions will have to iterate the physical
+ * discontiguities even if we merge the ioends at a logical level, so
+ * we don't gain anything by merging physical discontiguities here.
+ *
+ * We cannot use bio->bi_iter.bi_sector here as it is modified during
+ * submission so does not point to the start sector of the bio at
+ * completion.
+ */
+ if (ioend->io_sector + (ioend->io_size >> 9) != next->io_sector)
+ return false;
return true;
}
@@ -1209,8 +1242,10 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
ioend->io_flags = wpc->iomap.flags;
ioend->io_inode = inode;
ioend->io_size = 0;
+ ioend->io_folios = 0;
ioend->io_offset = offset;
ioend->io_bio = bio;
+ ioend->io_sector = sector;
return ioend;
}
@@ -1251,6 +1286,13 @@ iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
return false;
if (sector != bio_end_sector(wpc->ioend->io_bio))
return false;
+ /*
+ * Limit ioend bio chain lengths to minimise IO completion latency. This
+ * also prevents long tight loops ending page writeback on all the
+ * folios in the ioend.
+ */
+ if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE)
+ return false;
return true;
}
@@ -1335,6 +1377,8 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
&submit_list);
count++;
}
+ if (count)
+ wpc->ioend->io_folios++;
WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
WARN_ON_ONCE(!folio_test_locked(folio));
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 3cc4ab2ba7f4..5b9408e3b370 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -484,22 +484,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
stats.run.rs_locked);
- spin_lock(&commit_transaction->t_handle_lock);
- while (atomic_read(&commit_transaction->t_updates)) {
- DEFINE_WAIT(wait);
+ // waits for any t_updates to finish
+ jbd2_journal_wait_updates(journal);
- prepare_to_wait(&journal->j_wait_updates, &wait,
- TASK_UNINTERRUPTIBLE);
- if (atomic_read(&commit_transaction->t_updates)) {
- spin_unlock(&commit_transaction->t_handle_lock);
- write_unlock(&journal->j_state_lock);
- schedule();
- write_lock(&journal->j_state_lock);
- spin_lock(&commit_transaction->t_handle_lock);
- }
- finish_wait(&journal->j_wait_updates, &wait);
- }
- spin_unlock(&commit_transaction->t_handle_lock);
commit_transaction->t_state = T_SWITCH;
write_unlock(&journal->j_state_lock);
@@ -817,7 +804,7 @@ start_journal_io:
commit_transaction->t_state = T_COMMIT_DFLUSH;
write_unlock(&journal->j_state_lock);
- /*
+ /*
* If the journal is not located on the file system device,
* then we must flush the file system device before we issue
* the commit record
@@ -1170,7 +1157,7 @@ restart_loop:
if (journal->j_commit_callback)
journal->j_commit_callback(journal, commit_transaction);
if (journal->j_fc_cleanup_callback)
- journal->j_fc_cleanup_callback(journal, 1);
+ journal->j_fc_cleanup_callback(journal, 1, commit_transaction->t_tid);
trace_jbd2_end_commit(journal, commit_transaction);
jbd_debug(1, "JBD2: commit %d complete, head %d\n",
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index f13d548e4a7f..c2cf74b01ddb 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -771,7 +771,7 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
{
jbd2_journal_unlock_updates(journal);
if (journal->j_fc_cleanup_callback)
- journal->j_fc_cleanup_callback(journal, 0);
+ journal->j_fc_cleanup_callback(journal, 0, tid);
write_lock(&journal->j_state_lock);
journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
if (fallback)
@@ -1287,6 +1287,8 @@ static int jbd2_min_tag_size(void)
/**
* jbd2_journal_shrink_scan()
+ * @shrink: shrinker to work on
+ * @sc: reclaim request to process
*
* Scan the checkpointed buffer on the checkpoint list and release the
* journal_head.
@@ -1312,6 +1314,8 @@ static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink,
/**
* jbd2_journal_shrink_count()
+ * @shrink: shrinker to work on
+ * @sc: reclaim request to process
*
* Count the number of checkpoint buffers on the checkpoint list.
*/
@@ -2972,6 +2976,7 @@ struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh)
jbd_unlock_bh_journal_head(bh);
return jh;
}
+EXPORT_SYMBOL(jbd2_journal_grab_journal_head);
static void __journal_remove_journal_head(struct buffer_head *bh)
{
@@ -3024,6 +3029,7 @@ void jbd2_journal_put_journal_head(struct journal_head *jh)
jbd_unlock_bh_journal_head(bh);
}
}
+EXPORT_SYMBOL(jbd2_journal_put_journal_head);
/*
* Initialize jbd inode head
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 6a3caedd2285..8e2f8275a253 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -449,7 +449,7 @@ repeat:
}
/* OK, account for the buffers that this operation expects to
- * use and add the handle to the running transaction.
+ * use and add the handle to the running transaction.
*/
update_t_max_wait(transaction, ts);
handle->h_transaction = transaction;
@@ -836,6 +836,35 @@ int jbd2_journal_restart(handle_t *handle, int nblocks)
}
EXPORT_SYMBOL(jbd2_journal_restart);
+/*
+ * Waits for any outstanding t_updates to finish.
+ * This is called with write j_state_lock held.
+ */
+void jbd2_journal_wait_updates(journal_t *journal)
+{
+ transaction_t *commit_transaction = journal->j_running_transaction;
+
+ if (!commit_transaction)
+ return;
+
+ spin_lock(&commit_transaction->t_handle_lock);
+ while (atomic_read(&commit_transaction->t_updates)) {
+ DEFINE_WAIT(wait);
+
+ prepare_to_wait(&journal->j_wait_updates, &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (atomic_read(&commit_transaction->t_updates)) {
+ spin_unlock(&commit_transaction->t_handle_lock);
+ write_unlock(&journal->j_state_lock);
+ schedule();
+ write_lock(&journal->j_state_lock);
+ spin_lock(&commit_transaction->t_handle_lock);
+ }
+ finish_wait(&journal->j_wait_updates, &wait);
+ }
+ spin_unlock(&commit_transaction->t_handle_lock);
+}
+
/**
* jbd2_journal_lock_updates () - establish a transaction barrier.
* @journal: Journal to establish a barrier on.
@@ -863,27 +892,9 @@ void jbd2_journal_lock_updates(journal_t *journal)
write_lock(&journal->j_state_lock);
}
- /* Wait until there are no running updates */
- while (1) {
- transaction_t *transaction = journal->j_running_transaction;
-
- if (!transaction)
- break;
+ /* Wait until there are no running t_updates */
+ jbd2_journal_wait_updates(journal);
- spin_lock(&transaction->t_handle_lock);
- prepare_to_wait(&journal->j_wait_updates, &wait,
- TASK_UNINTERRUPTIBLE);
- if (!atomic_read(&transaction->t_updates)) {
- spin_unlock(&transaction->t_handle_lock);
- finish_wait(&journal->j_wait_updates, &wait);
- break;
- }
- spin_unlock(&transaction->t_handle_lock);
- write_unlock(&journal->j_state_lock);
- schedule();
- finish_wait(&journal->j_wait_updates, &wait);
- write_lock(&journal->j_state_lock);
- }
write_unlock(&journal->j_state_lock);
/*
diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c
index dc3d061edda9..911444d21267 100644
--- a/fs/ksmbd/auth.c
+++ b/fs/ksmbd/auth.c
@@ -29,6 +29,7 @@
#include "mgmt/user_config.h"
#include "crypto_ctx.h"
#include "transport_ipc.h"
+#include "../smbfs_common/arc4.h"
/*
* Fixed format data defining GSS header and fixed string
@@ -336,6 +337,29 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
nt_len - CIFS_ENCPWD_SIZE,
domain_name, conn->ntlmssp.cryptkey);
kfree(domain_name);
+
+ /* The recovered secondary session key */
+ if (conn->ntlmssp.client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) {
+ struct arc4_ctx *ctx_arc4;
+ unsigned int sess_key_off, sess_key_len;
+
+ sess_key_off = le32_to_cpu(authblob->SessionKey.BufferOffset);
+ sess_key_len = le16_to_cpu(authblob->SessionKey.Length);
+
+ if (blob_len < (u64)sess_key_off + sess_key_len)
+ return -EINVAL;
+
+ ctx_arc4 = kmalloc(sizeof(*ctx_arc4), GFP_KERNEL);
+ if (!ctx_arc4)
+ return -ENOMEM;
+
+ cifs_arc4_setkey(ctx_arc4, sess->sess_key,
+ SMB2_NTLMV2_SESSKEY_SIZE);
+ cifs_arc4_crypt(ctx_arc4, sess->sess_key,
+ (char *)authblob + sess_key_off, sess_key_len);
+ kfree_sensitive(ctx_arc4);
+ }
+
return ret;
}
@@ -408,6 +432,9 @@ ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob,
(cflags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
flags |= NTLMSSP_NEGOTIATE_EXTENDED_SEC;
+ if (cflags & NTLMSSP_NEGOTIATE_KEY_XCH)
+ flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
+
chgblob->NegotiateFlags = cpu_to_le32(flags);
len = strlen(ksmbd_netbios_name());
name = kmalloc(2 + UNICODE_LEN(len), GFP_KERNEL);
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 1866c81c5c99..67e8e28e3fc3 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -2688,7 +2688,7 @@ int smb2_open(struct ksmbd_work *work)
(struct create_posix *)context;
if (le16_to_cpu(context->DataOffset) +
le32_to_cpu(context->DataLength) <
- sizeof(struct create_posix)) {
+ sizeof(struct create_posix) - 4) {
rc = -EINVAL;
goto err_out1;
}
@@ -3422,9 +3422,9 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level,
goto free_conv_name;
}
- struct_sz = readdir_info_level_struct_sz(info_level);
- next_entry_offset = ALIGN(struct_sz - 1 + conv_len,
- KSMBD_DIR_INFO_ALIGNMENT);
+ struct_sz = readdir_info_level_struct_sz(info_level) - 1 + conv_len;
+ next_entry_offset = ALIGN(struct_sz, KSMBD_DIR_INFO_ALIGNMENT);
+ d_info->last_entry_off_align = next_entry_offset - struct_sz;
if (next_entry_offset > d_info->out_buf_len) {
d_info->out_buf_len = 0;
@@ -3976,6 +3976,7 @@ int smb2_query_dir(struct ksmbd_work *work)
((struct file_directory_info *)
((char *)rsp->Buffer + d_info.last_entry_offset))
->NextEntryOffset = 0;
+ d_info.data_count -= d_info.last_entry_off_align;
rsp->StructureSize = cpu_to_le16(9);
rsp->OutputBufferOffset = cpu_to_le16(72);
@@ -6126,13 +6127,26 @@ static int smb2_set_remote_key_for_rdma(struct ksmbd_work *work,
__le16 ChannelInfoOffset,
__le16 ChannelInfoLength)
{
+ unsigned int i, ch_count;
+
if (work->conn->dialect == SMB30_PROT_ID &&
Channel != SMB2_CHANNEL_RDMA_V1)
return -EINVAL;
- if (ChannelInfoOffset == 0 ||
- le16_to_cpu(ChannelInfoLength) < sizeof(*desc))
+ ch_count = le16_to_cpu(ChannelInfoLength) / sizeof(*desc);
+ if (ksmbd_debug_types & KSMBD_DEBUG_RDMA) {
+ for (i = 0; i < ch_count; i++) {
+ pr_info("RDMA r/w request %#x: token %#x, length %#x\n",
+ i,
+ le32_to_cpu(desc[i].token),
+ le32_to_cpu(desc[i].length));
+ }
+ }
+ if (ch_count != 1) {
+ ksmbd_debug(RDMA, "RDMA multiple buffer descriptors %d are not supported yet\n",
+ ch_count);
return -EINVAL;
+ }
work->need_invalidate_rkey =
(Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE);
@@ -6185,9 +6199,15 @@ int smb2_read(struct ksmbd_work *work)
if (req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE ||
req->Channel == SMB2_CHANNEL_RDMA_V1) {
+ unsigned int ch_offset = le16_to_cpu(req->ReadChannelInfoOffset);
+
+ if (ch_offset < offsetof(struct smb2_read_req, Buffer)) {
+ err = -EINVAL;
+ goto out;
+ }
err = smb2_set_remote_key_for_rdma(work,
(struct smb2_buffer_desc_v1 *)
- &req->Buffer[0],
+ ((char *)req + ch_offset),
req->Channel,
req->ReadChannelInfoOffset,
req->ReadChannelInfoLength);
@@ -6428,11 +6448,16 @@ int smb2_write(struct ksmbd_work *work)
if (req->Channel == SMB2_CHANNEL_RDMA_V1 ||
req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE) {
- if (req->Length != 0 || req->DataOffset != 0)
- return -EINVAL;
+ unsigned int ch_offset = le16_to_cpu(req->WriteChannelInfoOffset);
+
+ if (req->Length != 0 || req->DataOffset != 0 ||
+ ch_offset < offsetof(struct smb2_write_req, Buffer)) {
+ err = -EINVAL;
+ goto out;
+ }
err = smb2_set_remote_key_for_rdma(work,
(struct smb2_buffer_desc_v1 *)
- &req->Buffer[0],
+ ((char *)req + ch_offset),
req->Channel,
req->WriteChannelInfoOffset,
req->WriteChannelInfoLength);
diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c
index ef7f42b0290a..9a7e211dbf4f 100644
--- a/fs/ksmbd/smb_common.c
+++ b/fs/ksmbd/smb_common.c
@@ -308,14 +308,17 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level,
for (i = 0; i < 2; i++) {
struct kstat kstat;
struct ksmbd_kstat ksmbd_kstat;
+ struct dentry *dentry;
if (!dir->dot_dotdot[i]) { /* fill dot entry info */
if (i == 0) {
d_info->name = ".";
d_info->name_len = 1;
+ dentry = dir->filp->f_path.dentry;
} else {
d_info->name = "..";
d_info->name_len = 2;
+ dentry = dir->filp->f_path.dentry->d_parent;
}
if (!match_pattern(d_info->name, d_info->name_len,
@@ -327,7 +330,7 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level,
ksmbd_kstat.kstat = &kstat;
ksmbd_vfs_fill_dentry_attrs(work,
user_ns,
- dir->filp->f_path.dentry->d_parent,
+ dentry,
&ksmbd_kstat);
rc = fn(conn, info_level, d_info, &ksmbd_kstat);
if (rc)
diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c
index 3c1ec1ac0b27..ba5a22bc2e6d 100644
--- a/fs/ksmbd/transport_rdma.c
+++ b/fs/ksmbd/transport_rdma.c
@@ -80,7 +80,7 @@ static int smb_direct_max_fragmented_recv_size = 1024 * 1024;
/* The maximum single-message size which can be received */
static int smb_direct_max_receive_size = 8192;
-static int smb_direct_max_read_write_size = 1048512;
+static int smb_direct_max_read_write_size = 524224;
static int smb_direct_max_outstanding_rw_ops = 8;
diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h
index adf94a4f22fa..8c37aaf936ab 100644
--- a/fs/ksmbd/vfs.h
+++ b/fs/ksmbd/vfs.h
@@ -47,6 +47,7 @@ struct ksmbd_dir_info {
int last_entry_offset;
bool hide_dot_file;
int flags;
+ int last_entry_off_align;
};
struct ksmbd_readdir_data {
diff --git a/fs/libfs.c b/fs/libfs.c
index ba7438ab9371..974125270a42 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -1379,7 +1379,7 @@ bool is_empty_dir_inode(struct inode *inode)
(inode->i_op == &empty_dir_inode_operations);
}
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
/*
* Determine if the name of a dentry should be casefolded.
*
@@ -1473,7 +1473,7 @@ static const struct dentry_operations generic_encrypted_dentry_ops = {
};
#endif
-#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE)
+#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
static const struct dentry_operations generic_encrypted_ci_dentry_ops = {
.d_hash = generic_ci_d_hash,
.d_compare = generic_ci_d_compare,
@@ -1508,10 +1508,10 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
#ifdef CONFIG_FS_ENCRYPTION
bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME;
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
bool needs_ci_ops = dentry->d_sb->s_encoding;
#endif
-#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE)
+#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE)
if (needs_encrypt_ops && needs_ci_ops) {
d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops);
return;
@@ -1523,7 +1523,7 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry)
return;
}
#endif
-#ifdef CONFIG_UNICODE
+#if IS_ENABLED(CONFIG_UNICODE)
if (needs_ci_ops) {
d_set_d_op(dentry, &generic_ci_dentry_ops);
return;
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index cb3a7512c33e..0a22a2faf552 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -179,19 +179,21 @@ nlm_delete_file(struct nlm_file *file)
static int nlm_unlock_files(struct nlm_file *file)
{
struct file_lock lock;
- struct file *f;
+ locks_init_lock(&lock);
lock.fl_type = F_UNLCK;
lock.fl_start = 0;
lock.fl_end = OFFSET_MAX;
- for (f = file->f_file[0]; f <= file->f_file[1]; f++) {
- if (f && vfs_lock_file(f, F_SETLK, &lock, NULL) < 0) {
- pr_warn("lockd: unlock failure in %s:%d\n",
- __FILE__, __LINE__);
- return 1;
- }
- }
+ if (file->f_file[O_RDONLY] &&
+ vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, &lock, NULL))
+ goto out_err;
+ if (file->f_file[O_WRONLY] &&
+ vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, &lock, NULL))
+ goto out_err;
return 0;
+out_err:
+ pr_warn("lockd: unlock failure in %s:%d\n", __FILE__, __LINE__);
+ return 1;
}
/*
diff --git a/fs/namei.c b/fs/namei.c
index b867a92c078e..3f1829b3ab5b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4024,13 +4024,12 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir,
dentry->d_inode->i_flags |= S_DEAD;
dont_mount(dentry);
detach_mounts(dentry);
- fsnotify_rmdir(dir, dentry);
out:
inode_unlock(dentry->d_inode);
dput(dentry);
if (!error)
- d_delete(dentry);
+ d_delete_notify(dir, dentry);
return error;
}
EXPORT_SYMBOL(vfs_rmdir);
@@ -4152,7 +4151,6 @@ int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir,
if (!error) {
dont_mount(dentry);
detach_mounts(dentry);
- fsnotify_unlink(dir, dentry);
}
}
}
@@ -4160,9 +4158,11 @@ out:
inode_unlock(target);
/* We don't d_delete() NFS sillyrenamed files--they still exist. */
- if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
+ if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) {
+ fsnotify_unlink(dir, dentry);
+ } else if (!error) {
fsnotify_link_count(target);
- d_delete(dentry);
+ d_delete_notify(dir, dentry);
}
return error;
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 6a2033131c06..ccd4f245cae2 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -170,7 +170,7 @@ struct cb_devicenotifyitem {
};
struct cb_devicenotifyargs {
- int ndevs;
+ uint32_t ndevs;
struct cb_devicenotifyitem *devs;
};
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 09c5b1cb3e07..c343666d9a42 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -358,7 +358,7 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp,
struct cb_process_state *cps)
{
struct cb_devicenotifyargs *args = argp;
- int i;
+ uint32_t i;
__be32 res = 0;
struct nfs_client *clp = cps->clp;
struct nfs_server *server = NULL;
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index a67c41ec545f..f90de8043b0f 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -258,11 +258,9 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp,
void *argp)
{
struct cb_devicenotifyargs *args = argp;
+ uint32_t tmp, n, i;
__be32 *p;
__be32 status = 0;
- u32 tmp;
- int n, i;
- args->ndevs = 0;
/* Num of device notifications */
p = xdr_inline_decode(xdr, sizeof(uint32_t));
@@ -271,7 +269,7 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp,
goto out;
}
n = ntohl(*p++);
- if (n <= 0)
+ if (n == 0)
goto out;
if (n > ULONG_MAX / sizeof(*args->devs)) {
status = htonl(NFS4ERR_BADXDR);
@@ -330,19 +328,21 @@ __be32 decode_devicenotify_args(struct svc_rqst *rqstp,
dev->cbd_immediate = 0;
}
- args->ndevs++;
-
dprintk("%s: type %d layout 0x%x immediate %d\n",
__func__, dev->cbd_notify_type, dev->cbd_layout_type,
dev->cbd_immediate);
}
+ args->ndevs = n;
+ dprintk("%s: ndevs %d\n", __func__, args->ndevs);
+ return 0;
+err:
+ kfree(args->devs);
out:
+ args->devs = NULL;
+ args->ndevs = 0;
dprintk("%s: status %d ndevs %d\n",
__func__, ntohl(status), args->ndevs);
return status;
-err:
- kfree(args->devs);
- goto out;
}
static __be32 decode_sessionid(struct xdr_stream *xdr,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8d8b85b5a641..d1f34229e11a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -177,6 +177,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init)
INIT_LIST_HEAD(&clp->cl_superblocks);
clp->cl_rpcclient = ERR_PTR(-EINVAL);
+ clp->cl_flags = cl_init->init_flags;
clp->cl_proto = cl_init->proto;
clp->cl_nconnect = cl_init->nconnect;
clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1;
@@ -423,7 +424,6 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
list_add_tail(&new->cl_share_link,
&nn->nfs_client_list);
spin_unlock(&nn->nfs_client_lock);
- new->cl_flags = cl_init->init_flags;
return rpc_ops->init_client(new, cl_init);
}
@@ -856,6 +856,13 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str
server->namelen = pathinfo.max_namelen;
}
+ if (clp->rpc_ops->discover_trunking != NULL &&
+ (server->caps & NFS_CAP_FS_LOCATIONS)) {
+ error = clp->rpc_ops->discover_trunking(server, mntfh);
+ if (error < 0)
+ return error;
+ }
+
return 0;
}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 347793626f19..7bc7cf6b26f0 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -80,6 +80,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir
ctx->dir_cookie = 0;
ctx->dup_cookie = 0;
ctx->page_index = 0;
+ ctx->eof = false;
spin_lock(&dir->i_lock);
if (list_empty(&nfsi->open_files) &&
(nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
@@ -168,6 +169,7 @@ struct nfs_readdir_descriptor {
unsigned int cache_entry_index;
signed char duped;
bool plus;
+ bool eob;
bool eof;
};
@@ -867,7 +869,8 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
status = nfs_readdir_page_filler(desc, entry, pages, pglen,
arrays, narrays);
- } while (!status && nfs_readdir_page_needs_filling(page));
+ } while (!status && nfs_readdir_page_needs_filling(page) &&
+ page_mapping(page));
nfs_readdir_free_pages(pages, array_size);
out:
@@ -988,7 +991,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
ent = &array->array[i];
if (!dir_emit(desc->ctx, ent->name, ent->name_len,
nfs_compat_user_ino64(ent->ino), ent->d_type)) {
- desc->eof = true;
+ desc->eob = true;
break;
}
memcpy(desc->verf, verf, sizeof(desc->verf));
@@ -1004,7 +1007,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
desc->duped = 1;
}
if (array->page_is_eof)
- desc->eof = true;
+ desc->eof = !desc->eob;
kunmap(desc->page);
dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n",
@@ -1041,12 +1044,13 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
goto out;
desc->page_index = 0;
+ desc->cache_entry_index = 0;
desc->last_cookie = desc->dir_cookie;
desc->duped = 0;
status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz);
- for (i = 0; !desc->eof && i < sz && arrays[i]; i++) {
+ for (i = 0; !desc->eob && i < sz && arrays[i]; i++) {
desc->page = arrays[i];
nfs_do_filldir(desc, verf);
}
@@ -1105,9 +1109,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
desc->duped = dir_ctx->duped;
page_index = dir_ctx->page_index;
desc->attr_gencount = dir_ctx->attr_gencount;
+ desc->eof = dir_ctx->eof;
memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
spin_unlock(&file->f_lock);
+ if (desc->eof) {
+ res = 0;
+ goto out_free;
+ }
+
if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) &&
list_is_singular(&nfsi->open_files))
invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
@@ -1141,7 +1151,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
nfs_do_filldir(desc, nfsi->cookieverf);
nfs_readdir_page_unlock_and_put_cached(desc);
- } while (!desc->eof);
+ } while (!desc->eob && !desc->eof);
spin_lock(&file->f_lock);
dir_ctx->dir_cookie = desc->dir_cookie;
@@ -1149,9 +1159,10 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
dir_ctx->duped = desc->duped;
dir_ctx->attr_gencount = desc->attr_gencount;
dir_ctx->page_index = desc->page_index;
+ dir_ctx->eof = desc->eof;
memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
spin_unlock(&file->f_lock);
-
+out_free:
kfree(desc);
out:
@@ -1193,6 +1204,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
if (offset == 0)
memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
dir_ctx->duped = 0;
+ dir_ctx->eof = false;
}
spin_unlock(&filp->f_lock);
return offset;
@@ -1325,6 +1337,14 @@ void nfs_clear_verifier_delegated(struct inode *inode)
EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated);
#endif /* IS_ENABLED(CONFIG_NFS_V4) */
+static int nfs_dentry_verify_change(struct inode *dir, struct dentry *dentry)
+{
+ if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE) &&
+ d_really_is_negative(dentry))
+ return dentry->d_time == inode_peek_iversion_raw(dir);
+ return nfs_verify_change_attribute(dir, dentry->d_time);
+}
+
/*
* A check for whether or not the parent directory has changed.
* In the case it has, we assume that the dentries are untrustworthy
@@ -1338,7 +1358,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry,
return 1;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
return 0;
- if (!nfs_verify_change_attribute(dir, dentry->d_time))
+ if (!nfs_dentry_verify_change(dir, dentry))
return 0;
/* Revalidate nfsi->cache_change_attribute before we declare a match */
if (nfs_mapping_need_revalidate_inode(dir)) {
@@ -1347,7 +1367,7 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry,
if (__nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0)
return 0;
}
- if (!nfs_verify_change_attribute(dir, dentry->d_time))
+ if (!nfs_dentry_verify_change(dir, dentry))
return 0;
return 1;
}
@@ -1437,6 +1457,9 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
return 0;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
return 1;
+ /* Case insensitive server? Revalidate negative dentries */
+ if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
+ return 1;
return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU);
}
@@ -1537,7 +1560,7 @@ out:
* If the lookup failed despite the dentry change attribute being
* a match, then we should revalidate the directory cache.
*/
- if (!ret && nfs_verify_change_attribute(dir, dentry->d_time))
+ if (!ret && nfs_dentry_verify_change(dir, dentry))
nfs_mark_dir_for_revalidate(dir);
return nfs_lookup_revalidate_done(dir, dentry, inode, ret);
}
@@ -1776,8 +1799,11 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
dir_verifier = nfs_save_change_attribute(dir);
trace_nfs_lookup_enter(dir, dentry, flags);
error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
- if (error == -ENOENT)
+ if (error == -ENOENT) {
+ if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
+ dir_verifier = inode_peek_iversion_raw(dir);
goto no_entry;
+ }
if (error < 0) {
res = ERR_PTR(error);
goto out;
@@ -1806,6 +1832,14 @@ out:
}
EXPORT_SYMBOL_GPL(nfs_lookup);
+void nfs_d_prune_case_insensitive_aliases(struct inode *inode)
+{
+ /* Case insensitive server? Revalidate dentries */
+ if (inode && nfs_server_capable(inode, NFS_CAP_CASE_INSENSITIVE))
+ d_prune_aliases(inode);
+}
+EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases);
+
#if IS_ENABLED(CONFIG_NFS_V4)
static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
@@ -1867,6 +1901,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
struct iattr attr = { .ia_valid = ATTR_OPEN };
struct inode *inode;
unsigned int lookup_flags = 0;
+ unsigned long dir_verifier;
bool switched = false;
int created = 0;
int err;
@@ -1940,7 +1975,11 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
switch (err) {
case -ENOENT:
d_splice_alias(NULL, dentry);
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+ if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
+ dir_verifier = inode_peek_iversion_raw(dir);
+ else
+ dir_verifier = nfs_save_change_attribute(dir);
+ nfs_set_verifier(dentry, dir_verifier);
break;
case -EISDIR:
case -ENOTDIR:
@@ -1968,6 +2007,24 @@ out:
no_open:
res = nfs_lookup(dir, dentry, lookup_flags);
+ if (!res) {
+ inode = d_inode(dentry);
+ if ((lookup_flags & LOOKUP_DIRECTORY) && inode &&
+ !S_ISDIR(inode->i_mode))
+ res = ERR_PTR(-ENOTDIR);
+ else if (inode && S_ISREG(inode->i_mode))
+ res = ERR_PTR(-EOPENSTALE);
+ } else if (!IS_ERR(res)) {
+ inode = d_inode(res);
+ if ((lookup_flags & LOOKUP_DIRECTORY) && inode &&
+ !S_ISDIR(inode->i_mode)) {
+ dput(res);
+ res = ERR_PTR(-ENOTDIR);
+ } else if (inode && S_ISREG(inode->i_mode)) {
+ dput(res);
+ res = ERR_PTR(-EOPENSTALE);
+ }
+ }
if (switched) {
d_lookup_done(dentry);
if (!res)
@@ -2186,8 +2243,10 @@ static void nfs_dentry_remove_handle_error(struct inode *dir,
switch (error) {
case -ENOENT:
d_delete(dentry);
- fallthrough;
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
+ break;
case 0:
+ nfs_d_prune_case_insensitive_aliases(d_inode(dentry));
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
}
}
@@ -2380,6 +2439,8 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
trace_nfs_link_enter(inode, dir, dentry);
d_drop(dentry);
+ if (S_ISREG(inode->i_mode))
+ nfs_sync_inode(inode);
error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
if (error == 0) {
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
@@ -2469,6 +2530,8 @@ int nfs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
}
}
+ if (S_ISREG(old_inode->i_mode))
+ nfs_sync_inode(old_inode);
task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry, NULL);
if (IS_ERR(task)) {
error = PTR_ERR(task);
@@ -2529,7 +2592,7 @@ MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache lengt
static void nfs_access_free_entry(struct nfs_access_entry *entry)
{
- put_cred(entry->cred);
+ put_group_info(entry->group_info);
kfree_rcu(entry, rcu_head);
smp_mb__before_atomic();
atomic_long_dec(&nfs_access_nr_entries);
@@ -2655,6 +2718,43 @@ void nfs_access_zap_cache(struct inode *inode)
}
EXPORT_SYMBOL_GPL(nfs_access_zap_cache);
+static int access_cmp(const struct cred *a, const struct nfs_access_entry *b)
+{
+ struct group_info *ga, *gb;
+ int g;
+
+ if (uid_lt(a->fsuid, b->fsuid))
+ return -1;
+ if (uid_gt(a->fsuid, b->fsuid))
+ return 1;
+
+ if (gid_lt(a->fsgid, b->fsgid))
+ return -1;
+ if (gid_gt(a->fsgid, b->fsgid))
+ return 1;
+
+ ga = a->group_info;
+ gb = b->group_info;
+ if (ga == gb)
+ return 0;
+ if (ga == NULL)
+ return -1;
+ if (gb == NULL)
+ return 1;
+ if (ga->ngroups < gb->ngroups)
+ return -1;
+ if (ga->ngroups > gb->ngroups)
+ return 1;
+
+ for (g = 0; g < ga->ngroups; g++) {
+ if (gid_lt(ga->gid[g], gb->gid[g]))
+ return -1;
+ if (gid_gt(ga->gid[g], gb->gid[g]))
+ return 1;
+ }
+ return 0;
+}
+
static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred)
{
struct rb_node *n = NFS_I(inode)->access_cache.rb_node;
@@ -2662,7 +2762,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co
while (n != NULL) {
struct nfs_access_entry *entry =
rb_entry(n, struct nfs_access_entry, rb_node);
- int cmp = cred_fscmp(cred, entry->cred);
+ int cmp = access_cmp(cred, entry);
if (cmp < 0)
n = n->rb_left;
@@ -2674,7 +2774,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co
return NULL;
}
-static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block)
+static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_access_entry *cache;
@@ -2704,8 +2804,7 @@ static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *
spin_lock(&inode->i_lock);
retry = false;
}
- res->cred = cache->cred;
- res->mask = cache->mask;
+ *mask = cache->mask;
list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru);
err = 0;
out:
@@ -2717,7 +2816,7 @@ out_zap:
return -ENOENT;
}
-static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res)
+static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, u32 *mask)
{
/* Only check the most recently returned cache entry,
* but do it without locking.
@@ -2733,35 +2832,36 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre
lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru));
cache = list_entry(lh, struct nfs_access_entry, lru);
if (lh == &nfsi->access_cache_entry_lru ||
- cred_fscmp(cred, cache->cred) != 0)
+ access_cmp(cred, cache) != 0)
cache = NULL;
if (cache == NULL)
goto out;
if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
goto out;
- res->cred = cache->cred;
- res->mask = cache->mask;
+ *mask = cache->mask;
err = 0;
out:
rcu_read_unlock();
return err;
}
-int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct
-nfs_access_entry *res, bool may_block)
+int nfs_access_get_cached(struct inode *inode, const struct cred *cred,
+ u32 *mask, bool may_block)
{
int status;
- status = nfs_access_get_cached_rcu(inode, cred, res);
+ status = nfs_access_get_cached_rcu(inode, cred, mask);
if (status != 0)
- status = nfs_access_get_cached_locked(inode, cred, res,
+ status = nfs_access_get_cached_locked(inode, cred, mask,
may_block);
return status;
}
EXPORT_SYMBOL_GPL(nfs_access_get_cached);
-static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set)
+static void nfs_access_add_rbtree(struct inode *inode,
+ struct nfs_access_entry *set,
+ const struct cred *cred)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct rb_root *root_node = &nfsi->access_cache;
@@ -2774,7 +2874,7 @@ static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *
while (*p != NULL) {
parent = *p;
entry = rb_entry(parent, struct nfs_access_entry, rb_node);
- cmp = cred_fscmp(set->cred, entry->cred);
+ cmp = access_cmp(cred, entry);
if (cmp < 0)
p = &parent->rb_left;
@@ -2796,13 +2896,16 @@ found:
nfs_access_free_entry(entry);
}
-void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
+void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set,
+ const struct cred *cred)
{
struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL);
if (cache == NULL)
return;
RB_CLEAR_NODE(&cache->rb_node);
- cache->cred = get_cred(set->cred);
+ cache->fsuid = cred->fsuid;
+ cache->fsgid = cred->fsgid;
+ cache->group_info = get_group_info(cred->group_info);
cache->mask = set->mask;
/* The above field assignments must be visible
@@ -2810,7 +2913,7 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
* use rcu_assign_pointer, so just force the memory barrier.
*/
smp_wmb();
- nfs_access_add_rbtree(inode, cache);
+ nfs_access_add_rbtree(inode, cache, cred);
/* Update accounting */
smp_mb__before_atomic();
@@ -2875,7 +2978,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
trace_nfs_access_enter(inode);
- status = nfs_access_get_cached(inode, cred, &cache, may_block);
+ status = nfs_access_get_cached(inode, cred, &cache.mask, may_block);
if (status == 0)
goto out_cached;
@@ -2895,8 +2998,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP;
else
cache.mask |= NFS_ACCESS_EXECUTE;
- cache.cred = cred;
- status = NFS_PROTO(inode)->access(inode, &cache);
+ status = NFS_PROTO(inode)->access(inode, &cache, cred);
if (status != 0) {
if (status == -ESTALE) {
if (!S_ISDIR(inode->i_mode))
@@ -2906,7 +3008,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
}
goto out;
}
- nfs_access_add_cache(inode, &cache);
+ nfs_access_add_cache(inode, &cache, cred);
out_cached:
cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode);
if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
index 79323b5dab0c..aed0748fd6ec 100644
--- a/fs/nfs/filelayout/filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -51,7 +51,7 @@ struct nfs4_file_layout_dsaddr {
u32 stripe_count;
u8 *stripe_indices;
u32 ds_num;
- struct nfs4_pnfs_ds *ds_list[1];
+ struct nfs4_pnfs_ds *ds_list[];
};
struct nfs4_filelayout_segment {
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index 86c3f7e69ec4..acf4b88889dc 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -136,9 +136,7 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
goto out_err_free_stripe_indices;
}
- dsaddr = kzalloc(sizeof(*dsaddr) +
- (sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
- gfp_flags);
+ dsaddr = kzalloc(struct_size(dsaddr, ds_list, num), gfp_flags);
if (!dsaddr)
goto out_err_free_stripe_indices;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 12f6acb483bb..2de7c56a1fbe 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -373,6 +373,7 @@ extern unsigned long nfs_access_cache_count(struct shrinker *shrink,
extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
struct shrink_control *sc);
struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
+void nfs_d_prune_case_insensitive_aliases(struct inode *inode);
int nfs_create(struct user_namespace *, struct inode *, struct dentry *,
umode_t, bool);
int nfs_mkdir(struct user_namespace *, struct inode *, struct dentry *,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 7100514d306b..1597eef40d54 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -220,7 +220,8 @@ static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle,
task_flags);
}
-static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
+static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry,
+ const struct cred *cred)
{
struct nfs3_accessargs arg = {
.fh = NFS_FH(inode),
@@ -231,7 +232,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
.rpc_proc = &nfs3_procedures[NFS3PROC_ACCESS],
.rpc_argp = &arg,
.rpc_resp = &res,
- .rpc_cred = entry->cred,
+ .rpc_cred = cred,
};
int status = -ENOMEM;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 8b21ff1be717..32129446beca 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -46,7 +46,7 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
{
struct inode *inode = file_inode(filep);
struct nfs_server *server = NFS_SERVER(inode);
- u32 bitmask[3];
+ u32 bitmask[NFS_BITMASK_SZ];
struct nfs42_falloc_args args = {
.falloc_fh = NFS_FH(inode),
.falloc_offset = offset,
@@ -69,9 +69,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep,
return status;
}
- memcpy(bitmask, server->cache_consistency_bitmask, sizeof(bitmask));
- if (server->attr_bitmask[1] & FATTR4_WORD1_SPACE_USED)
- bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+ nfs4_bitmask_set(bitmask, server->cache_consistency_bitmask, inode,
+ NFS_INO_INVALID_BLOCKS);
res.falloc_fattr = nfs_alloc_fattr();
if (!res.falloc_fattr)
@@ -1044,13 +1043,14 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
struct inode *src_inode = file_inode(src_f);
struct inode *dst_inode = file_inode(dst_f);
struct nfs_server *server = NFS_SERVER(dst_inode);
+ __u32 dst_bitmask[NFS_BITMASK_SZ];
struct nfs42_clone_args args = {
.src_fh = NFS_FH(src_inode),
.dst_fh = NFS_FH(dst_inode),
.src_offset = src_offset,
.dst_offset = dst_offset,
.count = count,
- .dst_bitmask = server->cache_consistency_bitmask,
+ .dst_bitmask = dst_bitmask,
};
struct nfs42_clone_res res = {
.server = server,
@@ -1079,6 +1079,9 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
if (!res.dst_fattr)
return -ENOMEM;
+ nfs4_bitmask_set(dst_bitmask, server->cache_consistency_bitmask,
+ dst_inode, NFS_INO_INVALID_BLOCKS);
+
status = nfs4_call_sync(server->client, server, msg,
&args.seq_args, &res.seq_res, 0);
trace_nfs4_clone(src_inode, dst_inode, &args, status);
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index ed5eaca6801e..84f39b6f1b1e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -260,8 +260,8 @@ struct nfs4_state_maintenance_ops {
};
struct nfs4_mig_recovery_ops {
- int (*get_locations)(struct inode *, struct nfs4_fs_locations *,
- struct page *, const struct cred *);
+ int (*get_locations)(struct nfs_server *, struct nfs_fh *,
+ struct nfs4_fs_locations *, struct page *, const struct cred *);
int (*fsid_present)(struct inode *, const struct cred *);
};
@@ -280,7 +280,8 @@ struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *,
int nfs4_submount(struct fs_context *, struct nfs_server *);
int nfs4_replace_transport(struct nfs_server *server,
const struct nfs4_fs_locations *locations);
-
+size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa,
+ size_t salen, struct net *net, int port);
/* nfs4proc.c */
extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *);
extern int nfs4_async_handle_error(struct rpc_task *task,
@@ -302,8 +303,9 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait);
extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle);
extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *,
struct nfs4_fs_locations *, struct page *);
-extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *,
- struct page *page, const struct cred *);
+extern int nfs4_proc_get_locations(struct nfs_server *, struct nfs_fh *,
+ struct nfs4_fs_locations *,
+ struct page *page, const struct cred *);
extern int nfs4_proc_fsid_present(struct inode *, const struct cred *);
extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *,
struct dentry *,
@@ -315,6 +317,8 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid,
const struct nfs_open_context *ctx,
const struct nfs_lock_context *l_ctx,
fmode_t fmode);
+extern void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[],
+ struct inode *inode, unsigned long cache_validity);
extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fattr *fattr, struct inode *inode);
extern int update_open_stateid(struct nfs4_state *state,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index d8b5a250ca05..47a6cf892c95 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1343,8 +1343,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
}
nfs_put_client(clp);
- if (server->nfs_client->cl_hostname == NULL)
+ if (server->nfs_client->cl_hostname == NULL) {
server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL);
+ if (server->nfs_client->cl_hostname == NULL)
+ return -ENOMEM;
+ }
nfs_server_insert_lists(server);
return nfs_probe_server(server, NFS_FH(d_inode(server->super->s_root)));
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 873342308dc0..3680c8da510c 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -164,16 +164,21 @@ static int nfs4_validate_fspath(struct dentry *dentry,
return 0;
}
-static size_t nfs_parse_server_name(char *string, size_t len,
- struct sockaddr *sa, size_t salen, struct net *net)
+size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa,
+ size_t salen, struct net *net, int port)
{
ssize_t ret;
ret = rpc_pton(net, string, len, sa, salen);
if (ret == 0) {
- ret = nfs_dns_resolve_name(net, string, len, sa, salen);
- if (ret < 0)
- ret = 0;
+ ret = rpc_uaddr2sockaddr(net, string, len, sa, salen);
+ if (ret == 0) {
+ ret = nfs_dns_resolve_name(net, string, len, sa, salen);
+ if (ret < 0)
+ ret = 0;
+ }
+ } else if (port) {
+ rpc_set_port(sa, port);
}
return ret;
}
@@ -328,7 +333,7 @@ static int try_location(struct fs_context *fc,
nfs_parse_server_name(buf->data, buf->len,
&ctx->nfs_server.address,
sizeof(ctx->nfs_server._address),
- fc->net_ns);
+ fc->net_ns, 0);
if (ctx->nfs_server.addrlen == 0)
continue;
@@ -496,7 +501,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
continue;
salen = nfs_parse_server_name(buf->data, buf->len,
- sap, addr_bufsize, net);
+ sap, addr_bufsize, net, 0);
if (salen == 0)
continue;
rpc_set_port(sap, NFS_PORT);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ee3bc79f6ca3..f5020828ab65 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -108,10 +108,6 @@ static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
const struct cred *, bool);
#endif
-static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ],
- const __u32 *src, struct inode *inode,
- struct nfs_server *server,
- struct nfs4_label *label);
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
static inline struct nfs4_label *
@@ -2653,9 +2649,8 @@ static int nfs4_opendata_access(const struct cred *cred,
} else if ((fmode & FMODE_READ) && !opendata->file_created)
mask = NFS4_ACCESS_READ;
- cache.cred = cred;
nfs_access_set_mask(&cache, opendata->o_res.access_result);
- nfs_access_add_cache(state->inode, &cache);
+ nfs_access_add_cache(state->inode, &cache, cred);
flags = NFS4_ACCESS_READ | NFS4_ACCESS_EXECUTE | NFS4_ACCESS_LOOKUP;
if ((mask & ~cache.mask & flags) == 0)
@@ -3670,7 +3665,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
if (!nfs4_have_delegation(inode, FMODE_READ)) {
nfs4_bitmask_set(calldata->arg.bitmask_store,
server->cache_consistency_bitmask,
- inode, server, NULL);
+ inode, 0);
calldata->arg.bitmask = calldata->arg.bitmask_store;
} else
calldata->arg.bitmask = NULL;
@@ -3841,7 +3836,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
FATTR4_WORD0_FH_EXPIRE_TYPE |
FATTR4_WORD0_LINK_SUPPORT |
FATTR4_WORD0_SYMLINK_SUPPORT |
- FATTR4_WORD0_ACLSUPPORT;
+ FATTR4_WORD0_ACLSUPPORT |
+ FATTR4_WORD0_CASE_INSENSITIVE |
+ FATTR4_WORD0_CASE_PRESERVING;
if (minorversion)
bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT;
@@ -3870,10 +3867,16 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
server->caps |= NFS_CAP_HARDLINKS;
if (res.has_symlinks != 0)
server->caps |= NFS_CAP_SYMLINKS;
+ if (res.case_insensitive)
+ server->caps |= NFS_CAP_CASE_INSENSITIVE;
+ if (res.case_preserving)
+ server->caps |= NFS_CAP_CASE_PRESERVING;
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL)
server->caps |= NFS_CAP_SECURITY_LABEL;
#endif
+ if (res.attr_bitmask[0] & FATTR4_WORD0_FS_LOCATIONS)
+ server->caps |= NFS_CAP_FS_LOCATIONS;
if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID))
server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID;
if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE))
@@ -3932,6 +3935,114 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
return err;
}
+static void test_fs_location_for_trunking(struct nfs4_fs_location *location,
+ struct nfs_client *clp,
+ struct nfs_server *server)
+{
+ int i;
+
+ for (i = 0; i < location->nservers; i++) {
+ struct nfs4_string *srv_loc = &location->servers[i];
+ struct sockaddr addr;
+ size_t addrlen;
+ struct xprt_create xprt_args = {
+ .ident = 0,
+ .net = clp->cl_net,
+ };
+ struct nfs4_add_xprt_data xprtdata = {
+ .clp = clp,
+ };
+ struct rpc_add_xprt_test rpcdata = {
+ .add_xprt_test = clp->cl_mvops->session_trunk,
+ .data = &xprtdata,
+ };
+ char *servername = NULL;
+
+ if (!srv_loc->len)
+ continue;
+
+ addrlen = nfs_parse_server_name(srv_loc->data, srv_loc->len,
+ &addr, sizeof(addr),
+ clp->cl_net, server->port);
+ if (!addrlen)
+ return;
+ xprt_args.dstaddr = &addr;
+ xprt_args.addrlen = addrlen;
+ servername = kmalloc(srv_loc->len + 1, GFP_KERNEL);
+ if (!servername)
+ return;
+ memcpy(servername, srv_loc->data, srv_loc->len);
+ servername[srv_loc->len] = '\0';
+ xprt_args.servername = servername;
+
+ xprtdata.cred = nfs4_get_clid_cred(clp);
+ rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
+ rpc_clnt_setup_test_and_add_xprt,
+ &rpcdata);
+ if (xprtdata.cred)
+ put_cred(xprtdata.cred);
+ kfree(servername);
+ }
+}
+
+static int _nfs4_discover_trunking(struct nfs_server *server,
+ struct nfs_fh *fhandle)
+{
+ struct nfs4_fs_locations *locations = NULL;
+ struct page *page;
+ const struct cred *cred;
+ struct nfs_client *clp = server->nfs_client;
+ const struct nfs4_state_maintenance_ops *ops =
+ clp->cl_mvops->state_renewal_ops;
+ int status = -ENOMEM, i;
+
+ cred = ops->get_state_renewal_cred(clp);
+ if (cred == NULL) {
+ cred = nfs4_get_clid_cred(clp);
+ if (cred == NULL)
+ return -ENOKEY;
+ }
+
+ page = alloc_page(GFP_KERNEL);
+ locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
+ if (page == NULL || locations == NULL)
+ goto out;
+
+ status = nfs4_proc_get_locations(server, fhandle, locations, page,
+ cred);
+ if (status)
+ goto out;
+
+ for (i = 0; i < locations->nlocations; i++)
+ test_fs_location_for_trunking(&locations->locations[i], clp,
+ server);
+out:
+ if (page)
+ __free_page(page);
+ kfree(locations);
+ return status;
+}
+
+static int nfs4_discover_trunking(struct nfs_server *server,
+ struct nfs_fh *fhandle)
+{
+ struct nfs4_exception exception = {
+ .interruptible = true,
+ };
+ struct nfs_client *clp = server->nfs_client;
+ int err = 0;
+
+ if (!nfs4_has_session(clp))
+ goto out;
+ do {
+ err = nfs4_handle_exception(server,
+ _nfs4_discover_trunking(server, fhandle),
+ &exception);
+ } while (exception.retry);
+out:
+ return err;
+}
+
static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
@@ -4441,7 +4552,8 @@ static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle,
return err;
}
-static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
+static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry,
+ const struct cred *cred)
{
struct nfs_server *server = NFS_SERVER(inode);
struct nfs4_accessargs args = {
@@ -4455,7 +4567,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ACCESS],
.rpc_argp = &args,
.rpc_resp = &res,
- .rpc_cred = entry->cred,
+ .rpc_cred = cred,
};
int status = 0;
@@ -4475,14 +4587,15 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry
return status;
}
-static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
+static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry,
+ const struct cred *cred)
{
struct nfs4_exception exception = {
.interruptible = true,
};
int err;
do {
- err = _nfs4_proc_access(inode, entry);
+ err = _nfs4_proc_access(inode, entry, cred);
trace_nfs4_access(inode, err);
err = nfs4_handle_exception(NFS_SERVER(inode), err,
&exception);
@@ -4663,8 +4776,10 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg,
nfs_fattr_init(res->dir_attr);
- if (inode)
+ if (inode) {
nfs4_inode_return_delegation(inode);
+ nfs_d_prune_case_insensitive_aliases(inode);
+ }
}
static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
@@ -4730,6 +4845,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
return 0;
if (task->tk_status == 0) {
+ nfs_d_prune_case_insensitive_aliases(d_inode(data->old_dentry));
if (new_dir != old_dir) {
/* Note: If we moved a directory, nlink will change */
nfs4_update_changeattr(old_dir, &res->old_cinfo,
@@ -5422,14 +5538,14 @@ bool nfs4_write_need_cache_consistency_data(struct nfs_pgio_header *hdr)
return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0;
}
-static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src,
- struct inode *inode, struct nfs_server *server,
- struct nfs4_label *label)
+void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[],
+ struct inode *inode, unsigned long cache_validity)
{
- unsigned long cache_validity = READ_ONCE(NFS_I(inode)->cache_validity);
+ struct nfs_server *server = NFS_SERVER(inode);
unsigned int i;
memcpy(bitmask, src, sizeof(*bitmask) * NFS4_BITMASK_SZ);
+ cache_validity |= READ_ONCE(NFS_I(inode)->cache_validity);
if (cache_validity & NFS_INO_INVALID_CHANGE)
bitmask[0] |= FATTR4_WORD0_CHANGE;
@@ -5441,8 +5557,6 @@ static void nfs4_bitmask_set(__u32 bitmask[NFS4_BITMASK_SZ], const __u32 *src,
bitmask[1] |= FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP;
if (cache_validity & NFS_INO_INVALID_NLINK)
bitmask[1] |= FATTR4_WORD1_NUMLINKS;
- if (label && label->len && cache_validity & NFS_INO_INVALID_LABEL)
- bitmask[2] |= FATTR4_WORD2_SECURITY_LABEL;
if (cache_validity & NFS_INO_INVALID_CTIME)
bitmask[1] |= FATTR4_WORD1_TIME_METADATA;
if (cache_validity & NFS_INO_INVALID_MTIME)
@@ -5469,7 +5583,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
} else {
nfs4_bitmask_set(hdr->args.bitmask_store,
server->cache_consistency_bitmask,
- hdr->inode, server, NULL);
+ hdr->inode, NFS_INO_INVALID_BLOCKS);
hdr->args.bitmask = hdr->args.bitmask_store;
}
@@ -6507,8 +6621,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
data->args.fhandle = &data->fh;
data->args.stateid = &data->stateid;
nfs4_bitmask_set(data->args.bitmask_store,
- server->cache_consistency_bitmask, inode, server,
- NULL);
+ server->cache_consistency_bitmask, inode, 0);
data->args.bitmask = data->args.bitmask_store;
nfs_copy_fh(&data->fh, NFS_FH(inode));
nfs4_stateid_copy(&data->stateid, stateid);
@@ -7611,7 +7724,7 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler,
const char *key, const void *buf,
size_t buflen, int flags)
{
- struct nfs_access_entry cache;
+ u32 mask;
int ret;
if (!nfs_server_capable(inode, NFS_CAP_XATTR))
@@ -7626,8 +7739,8 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler,
* do a cached access check for the XA* flags to possibly avoid
* doing an RPC and getting EACCES back.
*/
- if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) {
- if (!(cache.mask & NFS_ACCESS_XAWRITE))
+ if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) {
+ if (!(mask & NFS_ACCESS_XAWRITE))
return -EACCES;
}
@@ -7648,14 +7761,14 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler,
struct dentry *unused, struct inode *inode,
const char *key, void *buf, size_t buflen)
{
- struct nfs_access_entry cache;
+ u32 mask;
ssize_t ret;
if (!nfs_server_capable(inode, NFS_CAP_XATTR))
return -EOPNOTSUPP;
- if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) {
- if (!(cache.mask & NFS_ACCESS_XAREAD))
+ if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) {
+ if (!(mask & NFS_ACCESS_XAREAD))
return -EACCES;
}
@@ -7680,13 +7793,13 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len)
ssize_t ret, size;
char *buf;
size_t buflen;
- struct nfs_access_entry cache;
+ u32 mask;
if (!nfs_server_capable(inode, NFS_CAP_XATTR))
return 0;
- if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) {
- if (!(cache.mask & NFS_ACCESS_XALIST))
+ if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) {
+ if (!(mask & NFS_ACCESS_XALIST))
return 0;
}
@@ -7818,18 +7931,18 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir,
* appended to this compound to identify the client ID which is
* performing recovery.
*/
-static int _nfs40_proc_get_locations(struct inode *inode,
+static int _nfs40_proc_get_locations(struct nfs_server *server,
+ struct nfs_fh *fhandle,
struct nfs4_fs_locations *locations,
struct page *page, const struct cred *cred)
{
- struct nfs_server *server = NFS_SERVER(inode);
struct rpc_clnt *clnt = server->client;
u32 bitmask[2] = {
[0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
};
struct nfs4_fs_locations_arg args = {
.clientid = server->nfs_client->cl_clientid,
- .fh = NFS_FH(inode),
+ .fh = fhandle,
.page = page,
.bitmask = bitmask,
.migration = 1, /* skip LOOKUP */
@@ -7875,17 +7988,17 @@ static int _nfs40_proc_get_locations(struct inode *inode,
* When the client supports GETATTR(fs_locations_info), it can
* be plumbed in here.
*/
-static int _nfs41_proc_get_locations(struct inode *inode,
+static int _nfs41_proc_get_locations(struct nfs_server *server,
+ struct nfs_fh *fhandle,
struct nfs4_fs_locations *locations,
struct page *page, const struct cred *cred)
{
- struct nfs_server *server = NFS_SERVER(inode);
struct rpc_clnt *clnt = server->client;
u32 bitmask[2] = {
[0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS,
};
struct nfs4_fs_locations_arg args = {
- .fh = NFS_FH(inode),
+ .fh = fhandle,
.page = page,
.bitmask = bitmask,
.migration = 1, /* skip LOOKUP */
@@ -7919,7 +8032,8 @@ static int _nfs41_proc_get_locations(struct inode *inode,
/**
* nfs4_proc_get_locations - discover locations for a migrated FSID
- * @inode: inode on FSID that is migrating
+ * @server: pointer to nfs_server to process
+ * @fhandle: pointer to the kernel NFS client file handle
* @locations: result of query
* @page: buffer
* @cred: credential to use for this operation
@@ -7934,11 +8048,11 @@ static int _nfs41_proc_get_locations(struct inode *inode,
* -NFS4ERR_LEASE_MOVED is returned if the server still has leases
* from this client that require migration recovery.
*/
-int nfs4_proc_get_locations(struct inode *inode,
+int nfs4_proc_get_locations(struct nfs_server *server,
+ struct nfs_fh *fhandle,
struct nfs4_fs_locations *locations,
struct page *page, const struct cred *cred)
{
- struct nfs_server *server = NFS_SERVER(inode);
struct nfs_client *clp = server->nfs_client;
const struct nfs4_mig_recovery_ops *ops =
clp->cl_mvops->mig_recovery_ops;
@@ -7951,10 +8065,11 @@ int nfs4_proc_get_locations(struct inode *inode,
(unsigned long long)server->fsid.major,
(unsigned long long)server->fsid.minor,
clp->cl_hostname);
- nfs_display_fhandle(NFS_FH(inode), __func__);
+ nfs_display_fhandle(fhandle, __func__);
do {
- status = ops->get_locations(inode, locations, page, cred);
+ status = ops->get_locations(server, fhandle, locations, page,
+ cred);
if (status != -NFS4ERR_DELAY)
break;
nfs4_handle_exception(server, status, &exception);
@@ -10423,6 +10538,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
.free_client = nfs4_free_client,
.create_server = nfs4_create_server,
.clone_server = nfs_clone_server,
+ .discover_trunking = nfs4_discover_trunking,
};
static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index d88b779f9dd0..f5a62c0d999b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2098,7 +2098,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
}
inode = d_inode(server->super->s_root);
- result = nfs4_proc_get_locations(inode, locations, page, cred);
+ result = nfs4_proc_get_locations(server, NFS_FH(inode), locations,
+ page, cred);
if (result) {
dprintk("<-- %s: failed to retrieve fs_locations: %d\n",
__func__, result);
@@ -2106,6 +2107,9 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred
}
result = -NFS4ERR_NXIO;
+ if (!locations->nlocations)
+ goto out;
+
if (!(locations->fattr.valid & NFS_ATTR_FATTR_V4_LOCATIONS)) {
dprintk("<-- %s: No fs_locations data, migration skipped\n",
__func__);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 69862bf6db00..8e70b92df4cc 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3533,6 +3533,42 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint
return 0;
}
+static int decode_attr_case_insensitive(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
+{
+ __be32 *p;
+
+ *res = 0;
+ if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_INSENSITIVE - 1U)))
+ return -EIO;
+ if (likely(bitmap[0] & FATTR4_WORD0_CASE_INSENSITIVE)) {
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ return -EIO;
+ *res = be32_to_cpup(p);
+ bitmap[0] &= ~FATTR4_WORD0_CASE_INSENSITIVE;
+ }
+ dprintk("%s: case_insensitive=%s\n", __func__, *res == 0 ? "false" : "true");
+ return 0;
+}
+
+static int decode_attr_case_preserving(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res)
+{
+ __be32 *p;
+
+ *res = 0;
+ if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_PRESERVING - 1U)))
+ return -EIO;
+ if (likely(bitmap[0] & FATTR4_WORD0_CASE_PRESERVING)) {
+ p = xdr_inline_decode(xdr, 4);
+ if (unlikely(!p))
+ return -EIO;
+ *res = be32_to_cpup(p);
+ bitmap[0] &= ~FATTR4_WORD0_CASE_PRESERVING;
+ }
+ dprintk("%s: case_preserving=%s\n", __func__, *res == 0 ? "false" : "true");
+ return 0;
+}
+
static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid)
{
__be32 *p;
@@ -3696,8 +3732,6 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
if (unlikely(!p))
goto out_eio;
n = be32_to_cpup(p);
- if (n <= 0)
- goto out_eio;
for (res->nlocations = 0; res->nlocations < n; res->nlocations++) {
u32 m;
struct nfs4_fs_location *loc;
@@ -4200,10 +4234,11 @@ static int decode_attr_security_label(struct xdr_stream *xdr, uint32_t *bitmap,
} else
printk(KERN_WARNING "%s: label too long (%u)!\n",
__func__, len);
+ if (label && label->label)
+ dprintk("%s: label=%.*s, len=%d, PI=%d, LFS=%d\n",
+ __func__, label->len, (char *)label->label,
+ label->len, label->pi, label->lfs);
}
- if (label && label->label)
- dprintk("%s: label=%s, len=%d, PI=%d, LFS=%d\n", __func__,
- (char *)label->label, label->len, label->pi, label->lfs);
return status;
}
@@ -4412,6 +4447,10 @@ static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_re
goto xdr_error;
if ((status = decode_attr_aclsupport(xdr, bitmap, &res->acl_bitmask)) != 0)
goto xdr_error;
+ if ((status = decode_attr_case_insensitive(xdr, bitmap, &res->case_insensitive)) != 0)
+ goto xdr_error;
+ if ((status = decode_attr_case_preserving(xdr, bitmap, &res->case_preserving)) != 0)
+ goto xdr_error;
if ((status = decode_attr_exclcreat_supported(xdr, bitmap,
res->exclcreat_bitmask)) != 0)
goto xdr_error;
diff --git a/fs/nfs/sysfs.c b/fs/nfs/sysfs.c
index 8cb70755e3c9..a6f740366963 100644
--- a/fs/nfs/sysfs.c
+++ b/fs/nfs/sysfs.c
@@ -142,10 +142,11 @@ static struct attribute *nfs_netns_client_attrs[] = {
&nfs_netns_client_id.attr,
NULL,
};
+ATTRIBUTE_GROUPS(nfs_netns_client);
static struct kobj_type nfs_netns_client_type = {
.release = nfs_netns_client_release,
- .default_attrs = nfs_netns_client_attrs,
+ .default_groups = nfs_netns_client_groups,
.sysfs_ops = &kobj_sysfs_ops,
.namespace = nfs_netns_client_namespace,
};
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 8ef53f6726ec..936eebd4c56d 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -150,13 +150,17 @@ nfsd3_proc_read(struct svc_rqst *rqstp)
unsigned int len;
int v;
- argp->count = min_t(u32, argp->count, max_blocksize);
-
dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n",
SVCFH_fmt(&argp->fh),
(unsigned long) argp->count,
(unsigned long long) argp->offset);
+ argp->count = min_t(u32, argp->count, max_blocksize);
+ if (argp->offset > (u64)OFFSET_MAX)
+ argp->offset = (u64)OFFSET_MAX;
+ if (argp->offset + argp->count > (u64)OFFSET_MAX)
+ argp->count = (u64)OFFSET_MAX - argp->offset;
+
v = 0;
len = argp->count;
resp->pages = rqstp->rq_next_page;
@@ -199,6 +203,11 @@ nfsd3_proc_write(struct svc_rqst *rqstp)
(unsigned long long) argp->offset,
argp->stable? " stable" : "");
+ resp->status = nfserr_fbig;
+ if (argp->offset > (u64)OFFSET_MAX ||
+ argp->offset + argp->len > (u64)OFFSET_MAX)
+ return rpc_success;
+
fh_copy(&resp->fh, &argp->fh);
resp->committed = argp->stable;
nvecs = svc_fill_write_vector(rqstp, &argp->payload);
@@ -651,15 +660,9 @@ nfsd3_proc_commit(struct svc_rqst *rqstp)
argp->count,
(unsigned long long) argp->offset);
- if (argp->offset > NFS_OFFSET_MAX) {
- resp->status = nfserr_inval;
- goto out;
- }
-
fh_copy(&resp->fh, &argp->fh);
resp->status = nfsd_commit(rqstp, &resp->fh, argp->offset,
argp->count, resp->verf);
-out:
return rpc_success;
}
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 7c45ba4db61b..0293b8d65f10 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -254,7 +254,7 @@ svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
if (xdr_stream_decode_u64(xdr, &newsize) < 0)
return false;
iap->ia_valid |= ATTR_SIZE;
- iap->ia_size = min_t(u64, newsize, NFS_OFFSET_MAX);
+ iap->ia_size = newsize;
}
if (xdr_stream_decode_u32(xdr, &set_it) < 0)
return false;
@@ -1060,7 +1060,7 @@ svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name,
return false;
/* cookie */
resp->cookie_offset = dirlist->len;
- if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0)
+ if (xdr_stream_encode_u64(xdr, OFFSET_MAX) < 0)
return false;
return true;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index ed1ee25647be..b207c76a873f 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -782,12 +782,16 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
read->rd_nf = NULL;
- if (read->rd_offset >= OFFSET_MAX)
- return nfserr_inval;
trace_nfsd_read_start(rqstp, &cstate->current_fh,
read->rd_offset, read->rd_length);
+ read->rd_length = min_t(u32, read->rd_length, svc_max_payload(rqstp));
+ if (read->rd_offset > (u64)OFFSET_MAX)
+ read->rd_offset = (u64)OFFSET_MAX;
+ if (read->rd_offset + read->rd_length > (u64)OFFSET_MAX)
+ read->rd_length = (u64)OFFSET_MAX - read->rd_offset;
+
/*
* If we do a zero copy read, then a client will see read data
* that reflects the state of the file *after* performing the
@@ -1018,8 +1022,9 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
unsigned long cnt;
int nvecs;
- if (write->wr_offset >= OFFSET_MAX)
- return nfserr_inval;
+ if (write->wr_offset > (u64)OFFSET_MAX ||
+ write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX)
+ return nfserr_fbig;
cnt = write->wr_buflen;
trace_nfsd_write_start(rqstp, &cstate->current_fh,
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 72900b89cf84..32063733443d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4130,8 +4130,10 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
status = nfserr_clid_inuse;
if (client_has_state(old)
&& !same_creds(&unconf->cl_cred,
- &old->cl_cred))
+ &old->cl_cred)) {
+ old = NULL;
goto out;
+ }
status = mark_client_expired_locked(old);
if (status) {
old = NULL;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 899de438e529..714a3a3bd50c 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3495,7 +3495,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen,
p = xdr_reserve_space(xdr, 3*4 + namlen);
if (!p)
goto fail;
- p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */
+ p = xdr_encode_hyper(p, OFFSET_MAX); /* offset of next entry */
p = xdr_encode_array(p, name, namlen); /* name length & name */
nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen);
@@ -3986,10 +3986,8 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
}
xdr_commit_encode(xdr);
- maxcount = svc_max_payload(resp->rqstp);
- maxcount = min_t(unsigned long, maxcount,
+ maxcount = min_t(unsigned long, read->rd_length,
(xdr->buf->buflen - xdr->buf->len));
- maxcount = min_t(unsigned long, maxcount, read->rd_length);
if (file->f_op->splice_read &&
test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags))
@@ -4826,10 +4824,8 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr,
return nfserr_resource;
xdr_commit_encode(xdr);
- maxcount = svc_max_payload(resp->rqstp);
- maxcount = min_t(unsigned long, maxcount,
+ maxcount = min_t(unsigned long, read->rd_length,
(xdr->buf->buflen - xdr->buf->len));
- maxcount = min_t(unsigned long, maxcount, read->rd_length);
count = maxcount;
eof = read->rd_offset >= i_size_read(file_inode(file));
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index b9f27fbcd768..68b020f2002b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1247,7 +1247,8 @@ static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry)
clear_ncl(d_inode(dentry));
dget(dentry);
ret = simple_unlink(dir, dentry);
- d_delete(dentry);
+ d_drop(dentry);
+ fsnotify_unlink(dir, dentry);
dput(dentry);
WARN_ON_ONCE(ret);
}
@@ -1338,8 +1339,8 @@ void nfsd_client_rmdir(struct dentry *dentry)
dget(dentry);
ret = simple_rmdir(dir, dentry);
WARN_ON_ONCE(ret);
+ d_drop(dentry);
fsnotify_rmdir(dir, dentry);
- d_delete(dentry);
dput(dentry);
inode_unlock(dir);
}
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index c4cf56327843..5889db66409d 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -306,14 +306,14 @@ TRACE_EVENT(nfsd_export_update,
DECLARE_EVENT_CLASS(nfsd_io_class,
TP_PROTO(struct svc_rqst *rqstp,
struct svc_fh *fhp,
- loff_t offset,
- unsigned long len),
+ u64 offset,
+ u32 len),
TP_ARGS(rqstp, fhp, offset, len),
TP_STRUCT__entry(
__field(u32, xid)
__field(u32, fh_hash)
- __field(loff_t, offset)
- __field(unsigned long, len)
+ __field(u64, offset)
+ __field(u32, len)
),
TP_fast_assign(
__entry->xid = be32_to_cpu(rqstp->rq_xid);
@@ -321,7 +321,7 @@ DECLARE_EVENT_CLASS(nfsd_io_class,
__entry->offset = offset;
__entry->len = len;
),
- TP_printk("xid=0x%08x fh_hash=0x%08x offset=%lld len=%lu",
+ TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu len=%u",
__entry->xid, __entry->fh_hash,
__entry->offset, __entry->len)
)
@@ -330,8 +330,8 @@ DECLARE_EVENT_CLASS(nfsd_io_class,
DEFINE_EVENT(nfsd_io_class, nfsd_##name, \
TP_PROTO(struct svc_rqst *rqstp, \
struct svc_fh *fhp, \
- loff_t offset, \
- unsigned long len), \
+ u64 offset, \
+ u32 len), \
TP_ARGS(rqstp, fhp, offset, len))
DEFINE_NFSD_IO_EVENT(read_start);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 99c2b9dfbb10..91600e71be19 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -435,6 +435,10 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
.ia_size = iap->ia_size,
};
+ host_err = -EFBIG;
+ if (iap->ia_size < 0)
+ goto out_unlock;
+
host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL);
if (host_err)
goto out_unlock;
@@ -1110,42 +1114,61 @@ out:
}
#ifdef CONFIG_NFSD_V3
-/*
- * Commit all pending writes to stable storage.
+/**
+ * nfsd_commit - Commit pending writes to stable storage
+ * @rqstp: RPC request being processed
+ * @fhp: NFS filehandle
+ * @offset: raw offset from beginning of file
+ * @count: raw count of bytes to sync
+ * @verf: filled in with the server's current write verifier
*
- * Note: we only guarantee that data that lies within the range specified
- * by the 'offset' and 'count' parameters will be synced.
+ * Note: we guarantee that data that lies within the range specified
+ * by the 'offset' and 'count' parameters will be synced. The server
+ * is permitted to sync data that lies outside this range at the
+ * same time.
*
* Unfortunately we cannot lock the file to make sure we return full WCC
* data to the client, as locking happens lower down in the filesystem.
+ *
+ * Return values:
+ * An nfsstat value in network byte order.
*/
__be32
-nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
- loff_t offset, unsigned long count, __be32 *verf)
+nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset,
+ u32 count, __be32 *verf)
{
+ u64 maxbytes;
+ loff_t start, end;
struct nfsd_net *nn;
struct nfsd_file *nf;
- loff_t end = LLONG_MAX;
- __be32 err = nfserr_inval;
-
- if (offset < 0)
- goto out;
- if (count != 0) {
- end = offset + (loff_t)count - 1;
- if (end < offset)
- goto out;
- }
+ __be32 err;
err = nfsd_file_acquire(rqstp, fhp,
NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf);
if (err)
goto out;
+
+ /*
+ * Convert the client-provided (offset, count) range to a
+ * (start, end) range. If the client-provided range falls
+ * outside the maximum file size of the underlying FS,
+ * clamp the sync range appropriately.
+ */
+ start = 0;
+ end = LLONG_MAX;
+ maxbytes = (u64)fhp->fh_dentry->d_sb->s_maxbytes;
+ if (offset < maxbytes) {
+ start = offset;
+ if (count && (offset + count - 1 < maxbytes))
+ end = offset + count - 1;
+ }
+
nn = net_generic(nf->nf_net, nfsd_net_id);
if (EX_ISSYNC(fhp->fh_export)) {
errseq_t since = READ_ONCE(nf->nf_file->f_wb_err);
int err2;
- err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
+ err2 = vfs_fsync_range(nf->nf_file, start, end, 0);
switch (err2) {
case 0:
nfsd_copy_write_verifier(verf, nn);
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 9f56dcb22ff7..2c43d10e3cab 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -74,8 +74,8 @@ __be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *,
char *name, int len, struct iattr *attrs,
struct svc_fh *res, int createmode,
u32 *verifier, bool *truncp, bool *created);
-__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *,
- loff_t, unsigned long, __be32 *verf);
+__be32 nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp,
+ u64 offset, u32 count, __be32 *verf);
#endif /* CONFIG_NFSD_V3 */
#ifdef CONFIG_NFSD_V4
__be32 nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 73b1615f9d96..2ff6bd85ba8f 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -158,7 +158,6 @@ static size_t fanotify_event_len(unsigned int info_mode,
struct fanotify_event *event)
{
size_t event_len = FAN_EVENT_METADATA_LEN;
- struct fanotify_info *info;
int fh_len;
int dot_len = 0;
@@ -168,8 +167,6 @@ static size_t fanotify_event_len(unsigned int info_mode,
if (fanotify_is_error_event(event->mask))
event_len += FANOTIFY_ERROR_INFO_LEN;
- info = fanotify_event_info(event);
-
if (fanotify_event_has_any_dir_fh(event)) {
event_len += fanotify_dir_name_info_len(event);
} else if ((info_mode & FAN_REPORT_NAME) &&
@@ -704,9 +701,6 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
if (fanotify_is_perm_event(event->mask))
FANOTIFY_PERM(event)->fd = fd;
- if (f)
- fd_install(fd, f);
-
if (info_mode) {
ret = copy_info_records_to_user(event, info, info_mode, pidfd,
buf, count);
@@ -714,6 +708,9 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
goto out_close_fd;
}
+ if (f)
+ fd_install(fd, f);
+
return metadata.event_len;
out_close_fd:
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 731558a6f27d..dd77b7aaabf5 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -661,17 +661,6 @@ static struct ctl_table ocfs2_nm_table[] = {
{ }
};
-static struct ctl_table ocfs2_mod_table[] = {
- {
- .procname = "nm",
- .data = NULL,
- .maxlen = 0,
- .mode = 0555,
- .child = ocfs2_nm_table
- },
- { }
-};
-
static struct ctl_table_header *ocfs2_table_header;
/*
@@ -682,7 +671,7 @@ static int __init ocfs2_stack_glue_init(void)
{
strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB);
- ocfs2_table_header = register_sysctl("fs/ocfs2", ocfs2_mod_table);
+ ocfs2_table_header = register_sysctl("fs/ocfs2/nm", ocfs2_nm_table);
if (!ocfs2_table_header) {
printk(KERN_ERR
"ocfs2 stack glue: unable to register sysctl\n");
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 481017e1dac5..166c8918c825 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1251,26 +1251,23 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
{
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
struct journal_head *jh;
- int ret = 1;
+ int ret;
if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
return 0;
- if (!buffer_jbd(bg_bh))
+ jh = jbd2_journal_grab_journal_head(bg_bh);
+ if (!jh)
return 1;
- jbd_lock_bh_journal_head(bg_bh);
- if (buffer_jbd(bg_bh)) {
- jh = bh2jh(bg_bh);
- spin_lock(&jh->b_state_lock);
- bg = (struct ocfs2_group_desc *) jh->b_committed_data;
- if (bg)
- ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
- else
- ret = 1;
- spin_unlock(&jh->b_state_lock);
- }
- jbd_unlock_bh_journal_head(bg_bh);
+ spin_lock(&jh->b_state_lock);
+ bg = (struct ocfs2_group_desc *) jh->b_committed_data;
+ if (bg)
+ ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
+ else
+ ret = 1;
+ spin_unlock(&jh->b_state_lock);
+ jbd2_journal_put_journal_head(jh);
return ret;
}
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index b193d08a3dc3..e040970408d4 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -145,7 +145,7 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
if (err == -ENOTTY || err == -EINVAL)
return 0;
pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n",
- old, err);
+ old->dentry, err);
return err;
}
@@ -157,7 +157,9 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
*/
if (oldfa.flags & OVL_PROT_FS_FLAGS_MASK) {
err = ovl_set_protattr(inode, new->dentry, &oldfa);
- if (err)
+ if (err == -EPERM)
+ pr_warn_once("copying fileattr: no xattr on upper\n");
+ else if (err)
return err;
}
@@ -167,8 +169,16 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old,
err = ovl_real_fileattr_get(new, &newfa);
if (err) {
+ /*
+ * Returning an error if upper doesn't support fileattr will
+ * result in a regression, so revert to the old behavior.
+ */
+ if (err == -ENOTTY || err == -EINVAL) {
+ pr_warn_once("copying fileattr: no support on upper\n");
+ return 0;
+ }
pr_warn("failed to retrieve upper fileattr (%pd2, err=%i)\n",
- new, err);
+ new->dentry, err);
return err;
}
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 22d904bde6ab..a74aef99bd3d 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -690,9 +690,14 @@ int dquot_quota_sync(struct super_block *sb, int type)
/* This is not very clever (and fast) but currently I don't know about
* any other simple way of getting quota data to disk and we must get
* them there for userspace to be visible... */
- if (sb->s_op->sync_fs)
- sb->s_op->sync_fs(sb, 1);
- sync_blockdev(sb->s_bdev);
+ if (sb->s_op->sync_fs) {
+ ret = sb->s_op->sync_fs(sb, 1);
+ if (ret)
+ return ret;
+ }
+ ret = sync_blockdev(sb->s_bdev);
+ if (ret)
+ return ret;
/*
* Now when everything is written we can discard the pagecache so
diff --git a/fs/super.c b/fs/super.c
index 7af820ba5ad5..f1d4a193602d 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1616,11 +1616,9 @@ static void lockdep_sb_freeze_acquire(struct super_block *sb)
percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
}
-static void sb_freeze_unlock(struct super_block *sb)
+static void sb_freeze_unlock(struct super_block *sb, int level)
{
- int level;
-
- for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
+ for (level--; level >= 0; level--)
percpu_up_write(sb->s_writers.rw_sem + level);
}
@@ -1691,7 +1689,14 @@ int freeze_super(struct super_block *sb)
sb_wait_write(sb, SB_FREEZE_PAGEFAULT);
/* All writers are done so after syncing there won't be dirty data */
- sync_filesystem(sb);
+ ret = sync_filesystem(sb);
+ if (ret) {
+ sb->s_writers.frozen = SB_UNFROZEN;
+ sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT);
+ wake_up(&sb->s_writers.wait_unfrozen);
+ deactivate_locked_super(sb);
+ return ret;
+ }
/* Now wait for internal filesystem counter */
sb->s_writers.frozen = SB_FREEZE_FS;
@@ -1703,7 +1708,7 @@ int freeze_super(struct super_block *sb)
printk(KERN_ERR
"VFS:Filesystem freeze failed\n");
sb->s_writers.frozen = SB_UNFROZEN;
- sb_freeze_unlock(sb);
+ sb_freeze_unlock(sb, SB_FREEZE_FS);
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return ret;
@@ -1748,7 +1753,7 @@ static int thaw_super_locked(struct super_block *sb)
}
sb->s_writers.frozen = SB_UNFROZEN;
- sb_freeze_unlock(sb);
+ sb_freeze_unlock(sb, SB_FREEZE_FS);
out:
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
diff --git a/fs/sync.c b/fs/sync.c
index 3ce8e2137f31..c7690016453e 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -29,7 +29,7 @@
*/
int sync_filesystem(struct super_block *sb)
{
- int ret;
+ int ret = 0;
/*
* We need to be protected against the filesystem going from
@@ -52,15 +52,21 @@ int sync_filesystem(struct super_block *sb)
* at a time.
*/
writeback_inodes_sb(sb, WB_REASON_SYNC);
- if (sb->s_op->sync_fs)
- sb->s_op->sync_fs(sb, 0);
+ if (sb->s_op->sync_fs) {
+ ret = sb->s_op->sync_fs(sb, 0);
+ if (ret)
+ return ret;
+ }
ret = sync_blockdev_nowait(sb->s_bdev);
- if (ret < 0)
+ if (ret)
return ret;
sync_inodes_sb(sb);
- if (sb->s_op->sync_fs)
- sb->s_op->sync_fs(sb, 1);
+ if (sb->s_op->sync_fs) {
+ ret = sb->s_op->sync_fs(sb, 1);
+ if (ret)
+ return ret;
+ }
return sync_blockdev(sb->s_bdev);
}
EXPORT_SYMBOL(sync_filesystem);
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 1d6b7a50736b..ea8f6cd01f50 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -258,10 +258,6 @@ int udf_expand_file_adinicb(struct inode *inode)
char *kaddr;
struct udf_inode_info *iinfo = UDF_I(inode);
int err;
- struct writeback_control udf_wbc = {
- .sync_mode = WB_SYNC_NONE,
- .nr_to_write = 1,
- };
WARN_ON_ONCE(!inode_is_locked(inode));
if (!iinfo->i_lenAlloc) {
@@ -305,8 +301,10 @@ int udf_expand_file_adinicb(struct inode *inode)
iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG;
/* from now on we have normal address_space methods */
inode->i_data.a_ops = &udf_aops;
+ set_page_dirty(page);
+ unlock_page(page);
up_write(&iinfo->i_data_sem);
- err = inode->i_data.a_ops->writepage(page, &udf_wbc);
+ err = filemap_fdatawrite(inode->i_mapping);
if (err) {
/* Restore everything back so that we don't lose data... */
lock_page(page);
@@ -317,6 +315,7 @@ int udf_expand_file_adinicb(struct inode *inode)
unlock_page(page);
iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
inode->i_data.a_ops = &udf_adinicb_aops;
+ iinfo->i_lenAlloc = inode->i_size;
up_write(&iinfo->i_data_sem);
}
put_page(page);
diff --git a/fs/unicode/Kconfig b/fs/unicode/Kconfig
index 610d7bc05d6e..da786a687fdc 100644
--- a/fs/unicode/Kconfig
+++ b/fs/unicode/Kconfig
@@ -3,21 +3,13 @@
# UTF-8 normalization
#
config UNICODE
- bool "UTF-8 normalization and casefolding support"
+ tristate "UTF-8 normalization and casefolding support"
help
Say Y here to enable UTF-8 NFD normalization and NFD+CF casefolding
- support.
-
-config UNICODE_UTF8_DATA
- tristate "UTF-8 normalization and casefolding tables"
- depends on UNICODE
- default UNICODE
- help
- This contains a large table of case foldings, which can be loaded as
- a separate module if you say M here. To be on the safe side stick
- to the default of Y. Saying N here makes no sense, if you do not want
- utf8 casefolding support, disable CONFIG_UNICODE instead.
+ support. If you say M here the large table of case foldings will
+ be a separate loadable module that gets requested only when a file
+ system actually use it.
config UNICODE_NORMALIZATION_SELFTEST
tristate "Test UTF-8 normalization support"
- depends on UNICODE_UTF8_DATA
+ depends on UNICODE
diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile
index 2f9d9188852b..0cc87423de82 100644
--- a/fs/unicode/Makefile
+++ b/fs/unicode/Makefile
@@ -1,8 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_UNICODE) += unicode.o
+ifneq ($(CONFIG_UNICODE),)
+obj-y += unicode.o
+endif
+obj-$(CONFIG_UNICODE) += utf8data.o
obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o
-obj-$(CONFIG_UNICODE_UTF8_DATA) += utf8data.o
unicode-y := utf8-norm.o utf8-core.o
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 2705f91bdd0d..9d6a67c7d227 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -136,7 +136,20 @@ done:
memalloc_nofs_restore(nofs_flag);
}
-/* Finish all pending io completions. */
+/*
+ * Finish all pending IO completions that require transactional modifications.
+ *
+ * We try to merge physical and logically contiguous ioends before completion to
+ * minimise the number of transactions we need to perform during IO completion.
+ * Both unwritten extent conversion and COW remapping need to iterate and modify
+ * one physical extent at a time, so we gain nothing by merging physically
+ * discontiguous extents here.
+ *
+ * The ioend chain length that we can be processing here is largely unbound in
+ * length and we may have to perform significant amounts of work on each ioend
+ * to complete it. Hence we have to be careful about holding the CPU for too
+ * long in this loop.
+ */
void
xfs_end_io(
struct work_struct *work)
@@ -157,6 +170,7 @@ xfs_end_io(
list_del_init(&ioend->io_list);
iomap_ioend_try_merge(ioend, &tmp);
xfs_end_ioend(ioend);
+ cond_resched();
}
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d4a387d3d0ce..eb2e387ba528 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -850,9 +850,6 @@ xfs_alloc_file_space(
rblocks = 0;
}
- /*
- * Allocate and setup the transaction.
- */
error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write,
dblocks, rblocks, false, &tp);
if (error)
@@ -869,9 +866,9 @@ xfs_alloc_file_space(
if (error)
goto error;
- /*
- * Complete the transaction
- */
+ ip->i_diflags |= XFS_DIFLAG_PREALLOC;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
error = xfs_trans_commit(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 22ad207bedf4..5bddb1e9e0b3 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -66,40 +66,6 @@ xfs_is_falloc_aligned(
return !((pos | len) & mask);
}
-int
-xfs_update_prealloc_flags(
- struct xfs_inode *ip,
- enum xfs_prealloc_flags flags)
-{
- struct xfs_trans *tp;
- int error;
-
- error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
- 0, 0, 0, &tp);
- if (error)
- return error;
-
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-
- if (!(flags & XFS_PREALLOC_INVISIBLE)) {
- VFS_I(ip)->i_mode &= ~S_ISUID;
- if (VFS_I(ip)->i_mode & S_IXGRP)
- VFS_I(ip)->i_mode &= ~S_ISGID;
- xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- }
-
- if (flags & XFS_PREALLOC_SET)
- ip->i_diflags |= XFS_DIFLAG_PREALLOC;
- if (flags & XFS_PREALLOC_CLEAR)
- ip->i_diflags &= ~XFS_DIFLAG_PREALLOC;
-
- xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- if (flags & XFS_PREALLOC_SYNC)
- xfs_trans_set_sync(tp);
- return xfs_trans_commit(tp);
-}
-
/*
* Fsync operations on directories are much simpler than on regular files,
* as there is no file data to flush, and thus also no need for explicit
@@ -895,6 +861,21 @@ xfs_break_layouts(
return error;
}
+/* Does this file, inode, or mount want synchronous writes? */
+static inline bool xfs_file_sync_writes(struct file *filp)
+{
+ struct xfs_inode *ip = XFS_I(file_inode(filp));
+
+ if (xfs_has_wsync(ip->i_mount))
+ return true;
+ if (filp->f_flags & (__O_SYNC | O_DSYNC))
+ return true;
+ if (IS_SYNC(file_inode(filp)))
+ return true;
+
+ return false;
+}
+
#define XFS_FALLOC_FL_SUPPORTED \
(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \
@@ -910,7 +891,6 @@ xfs_file_fallocate(
struct inode *inode = file_inode(file);
struct xfs_inode *ip = XFS_I(inode);
long error;
- enum xfs_prealloc_flags flags = 0;
uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
loff_t new_size = 0;
bool do_file_insert = false;
@@ -955,6 +935,10 @@ xfs_file_fallocate(
goto out_unlock;
}
+ error = file_modified(file);
+ if (error)
+ goto out_unlock;
+
if (mode & FALLOC_FL_PUNCH_HOLE) {
error = xfs_free_file_space(ip, offset, len);
if (error)
@@ -1004,8 +988,6 @@ xfs_file_fallocate(
}
do_file_insert = true;
} else {
- flags |= XFS_PREALLOC_SET;
-
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
offset + len > i_size_read(inode)) {
new_size = offset + len;
@@ -1057,13 +1039,6 @@ xfs_file_fallocate(
}
}
- if (file->f_flags & O_DSYNC)
- flags |= XFS_PREALLOC_SYNC;
-
- error = xfs_update_prealloc_flags(ip, flags);
- if (error)
- goto out_unlock;
-
/* Change file size if needed */
if (new_size) {
struct iattr iattr;
@@ -1082,8 +1057,14 @@ xfs_file_fallocate(
* leave shifted extents past EOF and hence losing access to
* the data that is contained within them.
*/
- if (do_file_insert)
+ if (do_file_insert) {
error = xfs_insert_file_space(ip, offset, len);
+ if (error)
+ goto out_unlock;
+ }
+
+ if (xfs_file_sync_writes(file))
+ error = xfs_log_force_inode(ip);
out_unlock:
xfs_iunlock(ip, iolock);
@@ -1115,21 +1096,6 @@ xfs_file_fadvise(
return ret;
}
-/* Does this file, inode, or mount want synchronous writes? */
-static inline bool xfs_file_sync_writes(struct file *filp)
-{
- struct xfs_inode *ip = XFS_I(file_inode(filp));
-
- if (xfs_has_wsync(ip->i_mount))
- return true;
- if (filp->f_flags & (__O_SYNC | O_DSYNC))
- return true;
- if (IS_SYNC(file_inode(filp)))
- return true;
-
- return false;
-}
-
STATIC loff_t
xfs_file_remap_range(
struct file *file_in,
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index c447bf04205a..b7e8f14d9fca 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -462,15 +462,6 @@ xfs_itruncate_extents(
}
/* from xfs_file.c */
-enum xfs_prealloc_flags {
- XFS_PREALLOC_SET = (1 << 1),
- XFS_PREALLOC_CLEAR = (1 << 2),
- XFS_PREALLOC_SYNC = (1 << 3),
- XFS_PREALLOC_INVISIBLE = (1 << 4),
-};
-
-int xfs_update_prealloc_flags(struct xfs_inode *ip,
- enum xfs_prealloc_flags flags);
int xfs_break_layouts(struct inode *inode, uint *iolock,
enum layout_break_reason reason);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 03a6198c97f6..2515fe8299e1 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1464,7 +1464,7 @@ xfs_ioc_getbmap(
if (bmx.bmv_count < 2)
return -EINVAL;
- if (bmx.bmv_count > ULONG_MAX / recsize)
+ if (bmx.bmv_count >= INT_MAX / recsize)
return -ENOMEM;
buf = kvcalloc(bmx.bmv_count, sizeof(*buf), GFP_KERNEL);
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index d6334abbc0b3..4abe17312c2b 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -71,6 +71,40 @@ xfs_fs_get_uuid(
}
/*
+ * We cannot use file based VFS helpers such as file_modified() to update
+ * inode state as we modify the data/metadata in the inode here. Hence we have
+ * to open code the timestamp updates and SUID/SGID stripping. We also need
+ * to set the inode prealloc flag to ensure that the extents we allocate are not
+ * removed if the inode is reclaimed from memory before xfs_fs_block_commit()
+ * is from the client to indicate that data has been written and the file size
+ * can be extended.
+ */
+static int
+xfs_fs_map_update_inode(
+ struct xfs_inode *ip)
+{
+ struct xfs_trans *tp;
+ int error;
+
+ error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid,
+ 0, 0, 0, &tp);
+ if (error)
+ return error;
+
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+ VFS_I(ip)->i_mode &= ~S_ISUID;
+ if (VFS_I(ip)->i_mode & S_IXGRP)
+ VFS_I(ip)->i_mode &= ~S_ISGID;
+ xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ ip->i_diflags |= XFS_DIFLAG_PREALLOC;
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ return xfs_trans_commit(tp);
+}
+
+/*
* Get a layout for the pNFS client.
*/
int
@@ -164,10 +198,12 @@ xfs_fs_map_blocks(
* that the blocks allocated and handed out to the client are
* guaranteed to be present even after a server crash.
*/
- error = xfs_update_prealloc_flags(ip,
- XFS_PREALLOC_SET | XFS_PREALLOC_SYNC);
+ error = xfs_fs_map_update_inode(ip);
+ if (!error)
+ error = xfs_log_force_inode(ip);
if (error)
goto out_unlock;
+
} else {
xfs_iunlock(ip, lock_flags);
}
@@ -255,7 +291,7 @@ xfs_fs_commit_blocks(
length = end - start;
if (!length)
continue;
-
+
/*
* Make sure reads through the pagecache see the new data.
*/
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e8f37bdc8354..4c0dee78b2f8 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -735,6 +735,7 @@ xfs_fs_sync_fs(
int wait)
{
struct xfs_mount *mp = XFS_M(sb);
+ int error;
trace_xfs_fs_sync_fs(mp, __return_address);
@@ -744,7 +745,10 @@ xfs_fs_sync_fs(
if (!wait)
return 0;
- xfs_log_force(mp, XFS_LOG_SYNC);
+ error = xfs_log_force(mp, XFS_LOG_SYNC);
+ if (error)
+ return error;
+
if (laptop_mode) {
/*
* The disk must be active because we're syncing.