summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/inode.c4
-rw-r--r--fs/btrfs/bio.c4
-rw-r--r--fs/btrfs/block-group.c20
-rw-r--r--fs/btrfs/extent_io.c2
-rw-r--r--fs/btrfs/free-space-cache.c2
-rw-r--r--fs/btrfs/inode.c2
-rw-r--r--fs/btrfs/qgroup.c14
-rw-r--r--fs/btrfs/ref-verify.c9
-rw-r--r--fs/btrfs/scrub.c24
-rw-r--r--fs/btrfs/space-info.c24
-rw-r--r--fs/btrfs/tree-log.c43
-rw-r--r--fs/dcache.c31
-rw-r--r--fs/erofs/super.c2
-rw-r--r--fs/erofs/zmap.c2
-rw-r--r--fs/erofs/zutil.c8
-rw-r--r--fs/locks.c9
-rw-r--r--fs/namei.c10
-rw-r--r--fs/netfs/buffered_write.c12
-rw-r--r--fs/netfs/direct_write.c3
-rw-r--r--fs/netfs/internal.h9
-rw-r--r--fs/netfs/misc.c81
-rw-r--r--fs/netfs/write_issue.c2
-rw-r--r--fs/nfs/direct.c2
-rw-r--r--fs/nfsd/netlink.c2
-rw-r--r--fs/nfsd/netlink.h3
-rw-r--r--fs/nfsd/nfsctl.c50
-rw-r--r--fs/nfsd/nfssvc.c1
-rw-r--r--fs/nilfs2/alloc.c19
-rw-r--r--fs/nilfs2/alloc.h4
-rw-r--r--fs/nilfs2/dat.c2
-rw-r--r--fs/nilfs2/dir.c6
-rw-r--r--fs/nilfs2/ifile.c7
-rw-r--r--fs/nilfs2/nilfs.h10
-rw-r--r--fs/nilfs2/the_nilfs.c6
-rw-r--r--fs/nilfs2/the_nilfs.h2
-rw-r--r--fs/ocfs2/aops.c5
-rw-r--r--fs/ocfs2/journal.c209
-rw-r--r--fs/ocfs2/journal.h2
-rw-r--r--fs/ocfs2/ocfs2.h27
-rw-r--r--fs/ocfs2/ocfs2_trace.h2
-rw-r--r--fs/ocfs2/super.c4
-rw-r--r--fs/open.c26
-rw-r--r--fs/overlayfs/dir.c8
-rw-r--r--fs/overlayfs/export.c6
-rw-r--r--fs/proc/task_mmu.c3
-rw-r--r--fs/smb/client/cifsfs.c2
-rw-r--r--fs/smb/client/cifsglob.h3
-rw-r--r--fs/smb/client/cifssmb.c8
-rw-r--r--fs/smb/client/file.c57
-rw-r--r--fs/smb/client/smb2pdu.c19
-rw-r--r--fs/smb/common/smb2pdu.h34
-rw-r--r--fs/smb/server/smb2pdu.c22
-rw-r--r--fs/super.c11
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c31
-rw-r--r--fs/xfs/libxfs/xfs_fs.h2
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c23
-rw-r--r--fs/xfs/xfs_bmap_util.c30
-rw-r--r--fs/xfs/xfs_bmap_util.h2
-rw-r--r--fs/xfs/xfs_icache.c2
-rw-r--r--fs/xfs/xfs_inode.c47
-rw-r--r--fs/xfs/xfs_iomap.c34
61 files changed, 600 insertions, 450 deletions
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 15bb7989c387..3acf5e050072 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -512,7 +512,7 @@ static int afs_iget5_set_root(struct inode *inode, void *opaque)
struct afs_vnode *vnode = AFS_FS_I(inode);
vnode->volume = as->volume;
- vnode->fid.vid = as->volume->vid,
+ vnode->fid.vid = as->volume->vid;
vnode->fid.vnode = 1;
vnode->fid.unique = 1;
inode->i_ino = 1;
@@ -545,7 +545,7 @@ struct inode *afs_root_iget(struct super_block *sb, struct key *key)
BUG_ON(!(inode->i_state & I_NEW));
vnode = AFS_FS_I(inode);
- vnode->cb_v_check = atomic_read(&as->volume->cb_v_break),
+ vnode->cb_v_check = atomic_read(&as->volume->cb_v_break);
afs_set_netfs_context(vnode);
op = afs_alloc_operation(key, as->volume);
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 477f350a8bd0..e3a57196b0ee 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -741,7 +741,9 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
ret = btrfs_bio_csum(bbio);
if (ret)
goto fail_put_bio;
- } else if (use_append) {
+ } else if (use_append ||
+ (btrfs_is_zoned(fs_info) && inode &&
+ inode->flags & BTRFS_INODE_NODATASUM)) {
ret = btrfs_alloc_dummy_sum(bbio);
if (ret)
goto fail_put_bio;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 1e09aeea69c2..60066822b532 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1785,6 +1785,7 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
container_of(work, struct btrfs_fs_info, reclaim_bgs_work);
struct btrfs_block_group *bg;
struct btrfs_space_info *space_info;
+ LIST_HEAD(retry_list);
if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
return;
@@ -1921,8 +1922,20 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
}
next:
- if (ret)
- btrfs_mark_bg_to_reclaim(bg);
+ if (ret) {
+ /* Refcount held by the reclaim_bgs list after splice. */
+ spin_lock(&fs_info->unused_bgs_lock);
+ /*
+ * This block group might be added to the unused list
+ * during the above process. Move it back to the
+ * reclaim list otherwise.
+ */
+ if (list_empty(&bg->bg_list)) {
+ btrfs_get_block_group(bg);
+ list_add_tail(&bg->bg_list, &retry_list);
+ }
+ spin_unlock(&fs_info->unused_bgs_lock);
+ }
btrfs_put_block_group(bg);
mutex_unlock(&fs_info->reclaim_bgs_lock);
@@ -1942,6 +1955,9 @@ next:
spin_unlock(&fs_info->unused_bgs_lock);
mutex_unlock(&fs_info->reclaim_bgs_lock);
end:
+ spin_lock(&fs_info->unused_bgs_lock);
+ list_splice_tail(&retry_list, &fs_info->reclaim_bgs);
+ spin_unlock(&fs_info->unused_bgs_lock);
btrfs_exclop_finish(fs_info);
sb_end_write(fs_info->sb);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f688fab55251..958155cc43a8 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3553,7 +3553,7 @@ err:
for (int i = 0; i < num_folios; i++) {
if (eb->folios[i]) {
detach_extent_buffer_folio(eb, eb->folios[i]);
- __folio_put(eb->folios[i]);
+ folio_put(eb->folios[i]);
}
}
__free_extent_buffer(eb);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 3ab8dea5036b..dabc3d0793cf 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2697,7 +2697,7 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
u64 offset = bytenr - block_group->start;
u64 to_free, to_unusable;
int bg_reclaim_threshold = 0;
- bool initial = (size == block_group->length);
+ bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
u64 reclaimable_unusable;
WARN_ON(!initial && offset + size > block_group->zone_capacity);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 753db965f7c0..3a2b902b2d1f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10385,7 +10385,7 @@ out_unlock:
out_folios:
for (i = 0; i < nr_folios; i++) {
if (folios[i])
- __folio_put(folios[i]);
+ folio_put(folios[i]);
}
kvfree(folios);
out:
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index fc2a7ea26354..39a15cca58ca 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1351,7 +1351,7 @@ static int flush_reservations(struct btrfs_fs_info *fs_info)
int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
{
- struct btrfs_root *quota_root;
+ struct btrfs_root *quota_root = NULL;
struct btrfs_trans_handle *trans = NULL;
int ret = 0;
@@ -1449,9 +1449,9 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
quota_root->node, 0, 1);
- btrfs_put_root(quota_root);
out:
+ btrfs_put_root(quota_root);
mutex_unlock(&fs_info->qgroup_ioctl_lock);
if (ret && trans)
btrfs_end_transaction(trans);
@@ -3062,8 +3062,6 @@ int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
struct btrfs_qgroup_inherit *inherit,
size_t size)
{
- if (!btrfs_qgroup_enabled(fs_info))
- return 0;
if (inherit->flags & ~BTRFS_QGROUP_INHERIT_FLAGS_SUPP)
return -EOPNOTSUPP;
if (size < sizeof(*inherit) || size > PAGE_SIZE)
@@ -3085,6 +3083,14 @@ int btrfs_qgroup_check_inherit(struct btrfs_fs_info *fs_info,
return -EINVAL;
/*
+ * Skip the inherit source qgroups check if qgroup is not enabled.
+ * Qgroup can still be later enabled causing problems, but in that case
+ * btrfs_qgroup_inherit() would just ignore those invalid ones.
+ */
+ if (!btrfs_qgroup_enabled(fs_info))
+ return 0;
+
+ /*
* Now check all the remaining qgroups, they should all:
*
* - Exist
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index cf531255ab76..9522a8b79d22 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -441,7 +441,8 @@ static int process_extent_item(struct btrfs_fs_info *fs_info,
u32 item_size = btrfs_item_size(leaf, slot);
unsigned long end, ptr;
u64 offset, flags, count;
- int type, ret;
+ int type;
+ int ret = 0;
ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
flags = btrfs_extent_flags(leaf, ei);
@@ -486,7 +487,11 @@ static int process_extent_item(struct btrfs_fs_info *fs_info,
key->objectid, key->offset);
break;
case BTRFS_EXTENT_OWNER_REF_KEY:
- WARN_ON(!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA));
+ if (!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)) {
+ btrfs_err(fs_info,
+ "found extent owner ref without simple quotas enabled");
+ ret = -EINVAL;
+ }
break;
default:
btrfs_err(fs_info, "invalid key type in iref");
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index afd6932f5e89..d7caa3732f07 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1688,20 +1688,24 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
(i << fs_info->sectorsize_bits);
int err;
- bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
- fs_info, scrub_read_endio, stripe);
- bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT;
-
io_stripe.is_scrub = true;
+ stripe_len = (nr_sectors - i) << fs_info->sectorsize_bits;
+ /*
+ * For RST cases, we need to manually split the bbio to
+ * follow the RST boundary.
+ */
err = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
- &stripe_len, &bioc, &io_stripe,
- &mirror);
+ &stripe_len, &bioc, &io_stripe, &mirror);
btrfs_put_bioc(bioc);
- if (err) {
- btrfs_bio_end_io(bbio,
- errno_to_blk_status(err));
- return;
+ if (err < 0) {
+ set_bit(i, &stripe->io_error_bitmap);
+ set_bit(i, &stripe->error_bitmap);
+ continue;
}
+
+ bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
+ fs_info, scrub_read_endio, stripe);
+ bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT;
}
__bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d620323d08ea..ae8c56442549 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -373,11 +373,18 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info,
* "optimal" chunk size based on the fs size. However when we actually
* allocate the chunk we will strip this down further, making it no more
* than 10% of the disk or 1G, whichever is smaller.
+ *
+ * On the zoned mode, we need to use zone_size (=
+ * data_sinfo->chunk_size) as it is.
*/
data_sinfo = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA);
- data_chunk_size = min(data_sinfo->chunk_size,
- mult_perc(fs_info->fs_devices->total_rw_bytes, 10));
- data_chunk_size = min_t(u64, data_chunk_size, SZ_1G);
+ if (!btrfs_is_zoned(fs_info)) {
+ data_chunk_size = min(data_sinfo->chunk_size,
+ mult_perc(fs_info->fs_devices->total_rw_bytes, 10));
+ data_chunk_size = min_t(u64, data_chunk_size, SZ_1G);
+ } else {
+ data_chunk_size = data_sinfo->chunk_size;
+ }
/*
* Since data allocations immediately use block groups as part of the
@@ -405,6 +412,17 @@ static u64 calc_available_free_space(struct btrfs_fs_info *fs_info,
avail >>= 3;
else
avail >>= 1;
+
+ /*
+ * On the zoned mode, we always allocate one zone as one chunk.
+ * Returning non-zone size alingned bytes here will result in
+ * less pressure for the async metadata reclaim process, and it
+ * will over-commit too much leading to ENOSPC. Align down to the
+ * zone size to avoid that.
+ */
+ if (btrfs_is_zoned(fs_info))
+ avail = ALIGN_DOWN(avail, fs_info->zone_size);
+
return avail;
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 26a2e5aa08e9..0bce1d45e252 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -138,6 +138,25 @@ static void wait_log_commit(struct btrfs_root *root, int transid);
* and once to do all the other items.
*/
+static struct inode *btrfs_iget_logging(u64 objectid, struct btrfs_root *root)
+{
+ unsigned int nofs_flag;
+ struct inode *inode;
+
+ /*
+ * We're holding a transaction handle whether we are logging or
+ * replaying a log tree, so we must make sure NOFS semantics apply
+ * because btrfs_alloc_inode() may be triggered and it uses GFP_KERNEL
+ * to allocate an inode, which can recurse back into the filesystem and
+ * attempt a transaction commit, resulting in a deadlock.
+ */
+ nofs_flag = memalloc_nofs_save();
+ inode = btrfs_iget(root->fs_info->sb, objectid, root);
+ memalloc_nofs_restore(nofs_flag);
+
+ return inode;
+}
+
/*
* start a sub transaction and setup the log tree
* this increments the log tree writer count to make the people
@@ -600,7 +619,7 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root,
{
struct inode *inode;
- inode = btrfs_iget(root->fs_info->sb, objectid, root);
+ inode = btrfs_iget_logging(objectid, root);
if (IS_ERR(inode))
inode = NULL;
return inode;
@@ -5438,7 +5457,6 @@ static int log_new_dir_dentries(struct btrfs_trans_handle *trans,
struct btrfs_log_ctx *ctx)
{
struct btrfs_root *root = start_inode->root;
- struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_path *path;
LIST_HEAD(dir_list);
struct btrfs_dir_list *dir_elem;
@@ -5499,7 +5517,7 @@ again:
continue;
btrfs_release_path(path);
- di_inode = btrfs_iget(fs_info->sb, di_key.objectid, root);
+ di_inode = btrfs_iget_logging(di_key.objectid, root);
if (IS_ERR(di_inode)) {
ret = PTR_ERR(di_inode);
goto out;
@@ -5559,7 +5577,7 @@ again:
btrfs_add_delayed_iput(curr_inode);
curr_inode = NULL;
- vfs_inode = btrfs_iget(fs_info->sb, ino, root);
+ vfs_inode = btrfs_iget_logging(ino, root);
if (IS_ERR(vfs_inode)) {
ret = PTR_ERR(vfs_inode);
break;
@@ -5654,7 +5672,7 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans,
if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES)
return BTRFS_LOG_FORCE_COMMIT;
- inode = btrfs_iget(root->fs_info->sb, ino, root);
+ inode = btrfs_iget_logging(ino, root);
/*
* If the other inode that had a conflicting dir entry was deleted in
* the current transaction then we either:
@@ -5755,7 +5773,6 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_log_ctx *ctx)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
int ret = 0;
/*
@@ -5786,7 +5803,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
list_del(&curr->list);
kfree(curr);
- inode = btrfs_iget(fs_info->sb, ino, root);
+ inode = btrfs_iget_logging(ino, root);
/*
* If the other inode that had a conflicting dir entry was
* deleted in the current transaction, we need to log its parent
@@ -5797,7 +5814,7 @@ static int log_conflicting_inodes(struct btrfs_trans_handle *trans,
if (ret != -ENOENT)
break;
- inode = btrfs_iget(fs_info->sb, parent, root);
+ inode = btrfs_iget_logging(parent, root);
if (IS_ERR(inode)) {
ret = PTR_ERR(inode);
break;
@@ -6319,7 +6336,6 @@ static int log_new_delayed_dentries(struct btrfs_trans_handle *trans,
struct btrfs_log_ctx *ctx)
{
const bool orig_log_new_dentries = ctx->log_new_dentries;
- struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_delayed_item *item;
int ret = 0;
@@ -6345,7 +6361,7 @@ static int log_new_delayed_dentries(struct btrfs_trans_handle *trans,
if (key.type == BTRFS_ROOT_ITEM_KEY)
continue;
- di_inode = btrfs_iget(fs_info->sb, key.objectid, inode->root);
+ di_inode = btrfs_iget_logging(key.objectid, inode->root);
if (IS_ERR(di_inode)) {
ret = PTR_ERR(di_inode);
break;
@@ -6729,7 +6745,6 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode,
struct btrfs_log_ctx *ctx)
{
- struct btrfs_fs_info *fs_info = trans->fs_info;
int ret;
struct btrfs_path *path;
struct btrfs_key key;
@@ -6794,8 +6809,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
cur_offset = item_size;
}
- dir_inode = btrfs_iget(fs_info->sb, inode_key.objectid,
- root);
+ dir_inode = btrfs_iget_logging(inode_key.objectid, root);
/*
* If the parent inode was deleted, return an error to
* fallback to a transaction commit. This is to prevent
@@ -6857,7 +6871,6 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
while (true) {
- struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_buffer *leaf;
int slot;
struct btrfs_key search_key;
@@ -6872,7 +6885,7 @@ static int log_new_ancestors(struct btrfs_trans_handle *trans,
search_key.objectid = found_key.offset;
search_key.type = BTRFS_INODE_ITEM_KEY;
search_key.offset = 0;
- inode = btrfs_iget(fs_info->sb, ino, root);
+ inode = btrfs_iget_logging(ino, root);
if (IS_ERR(inode))
return PTR_ERR(inode);
diff --git a/fs/dcache.c b/fs/dcache.c
index 407095188f83..d58dc9e58f3b 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3029,28 +3029,25 @@ EXPORT_SYMBOL(d_splice_alias);
bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
{
- bool result;
+ bool subdir;
unsigned seq;
if (new_dentry == old_dentry)
return true;
- do {
- /* for restarting inner loop in case of seq retry */
- seq = read_seqbegin(&rename_lock);
- /*
- * Need rcu_readlock to protect against the d_parent trashing
- * due to d_move
- */
- rcu_read_lock();
- if (d_ancestor(old_dentry, new_dentry))
- result = true;
- else
- result = false;
- rcu_read_unlock();
- } while (read_seqretry(&rename_lock, seq));
-
- return result;
+ /* Access d_parent under rcu as d_move() may change it. */
+ rcu_read_lock();
+ seq = read_seqbegin(&rename_lock);
+ subdir = d_ancestor(old_dentry, new_dentry);
+ /* Try lockless once... */
+ if (read_seqretry(&rename_lock, seq)) {
+ /* ...else acquire lock for progress even on deep chains. */
+ read_seqlock_excl(&rename_lock);
+ subdir = d_ancestor(old_dentry, new_dentry);
+ read_sequnlock_excl(&rename_lock);
+ }
+ rcu_read_unlock();
+ return subdir;
}
EXPORT_SYMBOL(is_subdir);
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index c93bd24d2771..1b91d9513013 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -343,7 +343,7 @@ static int erofs_read_superblock(struct super_block *sb)
sbi->build_time = le64_to_cpu(dsb->build_time);
sbi->build_time_nsec = le32_to_cpu(dsb->build_time_nsec);
- memcpy(&sb->s_uuid, dsb->uuid, sizeof(dsb->uuid));
+ super_set_uuid(sb, (void *)dsb->uuid, sizeof(dsb->uuid));
ret = strscpy(sbi->volume_name, dsb->volume_name,
sizeof(dsb->volume_name));
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 9b248ee5fef2..74d3d7bffcf3 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -711,6 +711,8 @@ int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map,
err = z_erofs_do_map_blocks(inode, map, flags);
out:
+ if (err)
+ map->m_llen = 0;
trace_z_erofs_map_blocks_iter_exit(inode, map, flags, err);
return err;
}
diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c
index 036024bce9f7..b80f612867c2 100644
--- a/fs/erofs/zutil.c
+++ b/fs/erofs/zutil.c
@@ -148,7 +148,7 @@ int __init z_erofs_gbuf_init(void)
void z_erofs_gbuf_exit(void)
{
- int i;
+ int i, j;
for (i = 0; i < z_erofs_gbuf_count + (!!z_erofs_rsvbuf); ++i) {
struct z_erofs_gbuf *gbuf = &z_erofs_gbufpool[i];
@@ -161,9 +161,9 @@ void z_erofs_gbuf_exit(void)
if (!gbuf->pages)
continue;
- for (i = 0; i < gbuf->nrpages; ++i)
- if (gbuf->pages[i])
- put_page(gbuf->pages[i]);
+ for (j = 0; j < gbuf->nrpages; ++j)
+ if (gbuf->pages[j])
+ put_page(gbuf->pages[j]);
kfree(gbuf->pages);
gbuf->pages = NULL;
}
diff --git a/fs/locks.c b/fs/locks.c
index 90c8746874de..c360d1992d21 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2448,8 +2448,9 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
error = do_lock_file_wait(filp, cmd, file_lock);
/*
- * Attempt to detect a close/fcntl race and recover by releasing the
- * lock that was just acquired. There is no need to do that when we're
+ * Detect close/fcntl races and recover by zapping all POSIX locks
+ * associated with this file and our files_struct, just like on
+ * filp_flush(). There is no need to do that when we're
* unlocking though, or for OFD locks.
*/
if (!error && file_lock->c.flc_type != F_UNLCK &&
@@ -2464,9 +2465,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
f = files_lookup_fd_locked(files, fd);
spin_unlock(&files->file_lock);
if (f != filp) {
- file_lock->c.flc_type = F_UNLCK;
- error = do_lock_file_wait(filp, cmd, file_lock);
- WARN_ON_ONCE(error);
+ locks_remove_posix(filp, files);
error = -EBADF;
}
}
diff --git a/fs/namei.c b/fs/namei.c
index 37fb0a8aa09a..1e05a0f3f04d 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3572,8 +3572,12 @@ static const char *open_last_lookups(struct nameidata *nd,
else
inode_lock_shared(dir->d_inode);
dentry = lookup_open(nd, file, op, got_write);
- if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED))
- fsnotify_create(dir->d_inode, dentry);
+ if (!IS_ERR(dentry)) {
+ if (file->f_mode & FMODE_CREATED)
+ fsnotify_create(dir->d_inode, dentry);
+ if (file->f_mode & FMODE_OPENED)
+ fsnotify_open(file);
+ }
if (open_flag & O_CREAT)
inode_unlock(dir->d_inode);
else
@@ -3700,6 +3704,8 @@ int vfs_tmpfile(struct mnt_idmap *idmap,
mode = vfs_prepare_mode(idmap, dir, mode, mode, mode);
error = dir->i_op->tmpfile(idmap, dir, file, mode);
dput(child);
+ if (file->f_mode & FMODE_OPENED)
+ fsnotify_open(file);
if (error)
return error;
/* Don't check for other permissions, the inode was just created */
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 07bc1fd43530..d583af7a2209 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -523,6 +523,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
struct netfs_group *group;
struct folio *folio = page_folio(vmf->page);
struct file *file = vmf->vma->vm_file;
+ struct address_space *mapping = file->f_mapping;
struct inode *inode = file_inode(file);
struct netfs_inode *ictx = netfs_inode(inode);
vm_fault_t ret = VM_FAULT_RETRY;
@@ -534,6 +535,11 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
if (folio_lock_killable(folio) < 0)
goto out;
+ if (folio->mapping != mapping) {
+ folio_unlock(folio);
+ ret = VM_FAULT_NOPAGE;
+ goto out;
+ }
if (folio_wait_writeback_killable(folio)) {
ret = VM_FAULT_LOCKED;
@@ -549,9 +555,9 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr
group = netfs_folio_group(folio);
if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE) {
folio_unlock(folio);
- err = filemap_fdatawait_range(inode->i_mapping,
- folio_pos(folio),
- folio_pos(folio) + folio_size(folio));
+ err = filemap_fdatawrite_range(mapping,
+ folio_pos(folio),
+ folio_pos(folio) + folio_size(folio));
switch (err) {
case 0:
ret = VM_FAULT_RETRY;
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index e14cd53ac9fd..88f2adfab75e 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -92,8 +92,9 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
__set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
if (async)
wreq->iocb = iocb;
+ wreq->len = iov_iter_count(&wreq->io_iter);
wreq->cleanup = netfs_cleanup_dio_write;
- ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), iov_iter_count(&wreq->io_iter));
+ ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
if (ret < 0) {
_debug("begin = %zd", ret);
goto out;
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index 95e281a8af78..acd9ca14e264 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -63,15 +63,6 @@ static inline void netfs_proc_del_rreq(struct netfs_io_request *rreq) {}
/*
* misc.c
*/
-#define NETFS_FLAG_PUT_MARK BIT(0)
-#define NETFS_FLAG_PAGECACHE_MARK BIT(1)
-int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
- struct folio *folio, unsigned int flags,
- gfp_t gfp_mask);
-int netfs_add_folios_to_buffer(struct xarray *buffer,
- struct address_space *mapping,
- pgoff_t index, pgoff_t to, gfp_t gfp_mask);
-void netfs_clear_buffer(struct xarray *buffer);
/*
* objects.c
diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
index bc1fc54fb724..83e644bd518f 100644
--- a/fs/netfs/misc.c
+++ b/fs/netfs/misc.c
@@ -8,87 +8,6 @@
#include <linux/swap.h>
#include "internal.h"
-/*
- * Attach a folio to the buffer and maybe set marks on it to say that we need
- * to put the folio later and twiddle the pagecache flags.
- */
-int netfs_xa_store_and_mark(struct xarray *xa, unsigned long index,
- struct folio *folio, unsigned int flags,
- gfp_t gfp_mask)
-{
- XA_STATE_ORDER(xas, xa, index, folio_order(folio));
-
-retry:
- xas_lock(&xas);
- for (;;) {
- xas_store(&xas, folio);
- if (!xas_error(&xas))
- break;
- xas_unlock(&xas);
- if (!xas_nomem(&xas, gfp_mask))
- return xas_error(&xas);
- goto retry;
- }
-
- if (flags & NETFS_FLAG_PUT_MARK)
- xas_set_mark(&xas, NETFS_BUF_PUT_MARK);
- if (flags & NETFS_FLAG_PAGECACHE_MARK)
- xas_set_mark(&xas, NETFS_BUF_PAGECACHE_MARK);
- xas_unlock(&xas);
- return xas_error(&xas);
-}
-
-/*
- * Create the specified range of folios in the buffer attached to the read
- * request. The folios are marked with NETFS_BUF_PUT_MARK so that we know that
- * these need freeing later.
- */
-int netfs_add_folios_to_buffer(struct xarray *buffer,
- struct address_space *mapping,
- pgoff_t index, pgoff_t to, gfp_t gfp_mask)
-{
- struct folio *folio;
- int ret;
-
- if (to + 1 == index) /* Page range is inclusive */
- return 0;
-
- do {
- /* TODO: Figure out what order folio can be allocated here */
- folio = filemap_alloc_folio(readahead_gfp_mask(mapping), 0);
- if (!folio)
- return -ENOMEM;
- folio->index = index;
- ret = netfs_xa_store_and_mark(buffer, index, folio,
- NETFS_FLAG_PUT_MARK, gfp_mask);
- if (ret < 0) {
- folio_put(folio);
- return ret;
- }
-
- index += folio_nr_pages(folio);
- } while (index <= to && index != 0);
-
- return 0;
-}
-
-/*
- * Clear an xarray buffer, putting a ref on the folios that have
- * NETFS_BUF_PUT_MARK set.
- */
-void netfs_clear_buffer(struct xarray *buffer)
-{
- struct folio *folio;
- XA_STATE(xas, buffer, 0);
-
- rcu_read_lock();
- xas_for_each_marked(&xas, folio, ULONG_MAX, NETFS_BUF_PUT_MARK) {
- folio_put(folio);
- }
- rcu_read_unlock();
- xa_destroy(buffer);
-}
-
/**
* netfs_dirty_folio - Mark folio dirty and pin a cache object for writeback
* @mapping: The mapping the folio belongs to.
diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 3aa86e268f40..ec6cf8707fb0 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -483,7 +483,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
if (!debug)
kdebug("R=%x: No submit", wreq->debug_id);
- if (flen < fsize)
+ if (foff + flen < fsize)
for (int s = 0; s < NR_IO_STREAMS; s++)
netfs_issue_write(wreq, &wreq->io_streams[s]);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index bb2f583eb28b..90079ca134dd 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -141,8 +141,6 @@ int nfs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
{
ssize_t ret;
- VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
-
if (iov_iter_rw(iter) == READ)
ret = nfs_file_direct_read(iocb, iter, true);
else
diff --git a/fs/nfsd/netlink.c b/fs/nfsd/netlink.c
index 62d2586d9902..529a75ecf22e 100644
--- a/fs/nfsd/netlink.c
+++ b/fs/nfsd/netlink.c
@@ -44,9 +44,7 @@ static const struct nla_policy nfsd_listener_set_nl_policy[NFSD_A_SERVER_SOCK_AD
static const struct genl_split_ops nfsd_nl_ops[] = {
{
.cmd = NFSD_CMD_RPC_STATUS_GET,
- .start = nfsd_nl_rpc_status_get_start,
.dumpit = nfsd_nl_rpc_status_get_dumpit,
- .done = nfsd_nl_rpc_status_get_done,
.flags = GENL_CMD_CAP_DUMP,
},
{
diff --git a/fs/nfsd/netlink.h b/fs/nfsd/netlink.h
index e3724637d64d..2e132ef328f8 100644
--- a/fs/nfsd/netlink.h
+++ b/fs/nfsd/netlink.h
@@ -15,9 +15,6 @@
extern const struct nla_policy nfsd_sock_nl_policy[NFSD_A_SOCK_TRANSPORT_NAME + 1];
extern const struct nla_policy nfsd_version_nl_policy[NFSD_A_VERSION_ENABLED + 1];
-int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb);
-int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb);
-
int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
struct netlink_callback *cb);
int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 202140df8f82..c848ebe5d08f 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1460,28 +1460,6 @@ static int create_proc_exports_entry(void)
unsigned int nfsd_net_id;
-/**
- * nfsd_nl_rpc_status_get_start - Prepare rpc_status_get dumpit
- * @cb: netlink metadata and command arguments
- *
- * Return values:
- * %0: The rpc_status_get command may proceed
- * %-ENODEV: There is no NFSD running in this namespace
- */
-int nfsd_nl_rpc_status_get_start(struct netlink_callback *cb)
-{
- struct nfsd_net *nn = net_generic(sock_net(cb->skb->sk), nfsd_net_id);
- int ret = -ENODEV;
-
- mutex_lock(&nfsd_mutex);
- if (nn->nfsd_serv)
- ret = 0;
- else
- mutex_unlock(&nfsd_mutex);
-
- return ret;
-}
-
static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb,
struct netlink_callback *cb,
struct nfsd_genl_rqstp *rqstp)
@@ -1558,8 +1536,16 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb,
int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
struct netlink_callback *cb)
{
- struct nfsd_net *nn = net_generic(sock_net(skb->sk), nfsd_net_id);
int i, ret, rqstp_index = 0;
+ struct nfsd_net *nn;
+
+ mutex_lock(&nfsd_mutex);
+
+ nn = net_generic(sock_net(skb->sk), nfsd_net_id);
+ if (!nn->nfsd_serv) {
+ ret = -ENODEV;
+ goto out_unlock;
+ }
rcu_read_lock();
@@ -1636,22 +1622,10 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
ret = skb->len;
out:
rcu_read_unlock();
-
- return ret;
-}
-
-/**
- * nfsd_nl_rpc_status_get_done - rpc_status_get dumpit post-processing
- * @cb: netlink metadata and command arguments
- *
- * Return values:
- * %0: Success
- */
-int nfsd_nl_rpc_status_get_done(struct netlink_callback *cb)
-{
+out_unlock:
mutex_unlock(&nfsd_mutex);
- return 0;
+ return ret;
}
/**
@@ -2195,6 +2169,8 @@ static __net_init int nfsd_net_init(struct net *net)
nn->nfsd_svcstats.program = &nfsd_program;
nn->nfsd_versions = NULL;
nn->nfsd4_minorversions = NULL;
+ nn->nfsd_info.mutex = &nfsd_mutex;
+ nn->nfsd_serv = NULL;
nfsd4_init_leases_net(nn);
get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
seqlock_init(&nn->writeverf_lock);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index cd9a6a1a9fc8..89d7918de7b1 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -672,7 +672,6 @@ int nfsd_create_serv(struct net *net)
return error;
}
spin_lock(&nfsd_notifier_lock);
- nn->nfsd_info.mutex = &nfsd_mutex;
nn->nfsd_serv = serv;
spin_unlock(&nfsd_notifier_lock);
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 89caef7513db..ba50388ee4bf 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -377,11 +377,12 @@ void *nilfs_palloc_block_get_entry(const struct inode *inode, __u64 nr,
* @target: offset number of an entry in the group (start point)
* @bsize: size in bits
* @lock: spin lock protecting @bitmap
+ * @wrap: whether to wrap around
*/
static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
unsigned long target,
unsigned int bsize,
- spinlock_t *lock)
+ spinlock_t *lock, bool wrap)
{
int pos, end = bsize;
@@ -397,6 +398,8 @@ static int nilfs_palloc_find_available_slot(unsigned char *bitmap,
end = target;
}
+ if (!wrap)
+ return -ENOSPC;
/* wrap around */
for (pos = 0; pos < end; pos++) {
@@ -495,9 +498,10 @@ int nilfs_palloc_count_max_entries(struct inode *inode, u64 nused, u64 *nmaxp)
* nilfs_palloc_prepare_alloc_entry - prepare to allocate a persistent object
* @inode: inode of metadata file using this allocator
* @req: nilfs_palloc_req structure exchanged for the allocation
+ * @wrap: whether to wrap around
*/
int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
- struct nilfs_palloc_req *req)
+ struct nilfs_palloc_req *req, bool wrap)
{
struct buffer_head *desc_bh, *bitmap_bh;
struct nilfs_palloc_group_desc *desc;
@@ -516,7 +520,7 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
entries_per_group = nilfs_palloc_entries_per_group(inode);
for (i = 0; i < ngroups; i += n) {
- if (group >= ngroups) {
+ if (group >= ngroups && wrap) {
/* wrap around */
group = 0;
maxgroup = nilfs_palloc_group(inode, req->pr_entry_nr,
@@ -550,7 +554,14 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
pos = nilfs_palloc_find_available_slot(
- bitmap, group_offset, entries_per_group, lock);
+ bitmap, group_offset, entries_per_group, lock,
+ wrap);
+ /*
+ * Since the search for a free slot in the second and
+ * subsequent bitmap blocks always starts from the
+ * beginning, the wrap flag only has an effect on the
+ * first search.
+ */
kunmap_local(bitmap_kaddr);
if (pos >= 0)
goto found;
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index b667e869ac07..d825a9faca6d 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -50,8 +50,8 @@ struct nilfs_palloc_req {
struct buffer_head *pr_entry_bh;
};
-int nilfs_palloc_prepare_alloc_entry(struct inode *,
- struct nilfs_palloc_req *);
+int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
+ struct nilfs_palloc_req *req, bool wrap);
void nilfs_palloc_commit_alloc_entry(struct inode *,
struct nilfs_palloc_req *);
void nilfs_palloc_abort_alloc_entry(struct inode *, struct nilfs_palloc_req *);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 180fc8d36213..fc1caf63a42a 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -75,7 +75,7 @@ int nilfs_dat_prepare_alloc(struct inode *dat, struct nilfs_palloc_req *req)
{
int ret;
- ret = nilfs_palloc_prepare_alloc_entry(dat, req);
+ ret = nilfs_palloc_prepare_alloc_entry(dat, req, true);
if (ret < 0)
return ret;
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 52e50b1b7f22..dddfa604491a 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -135,6 +135,9 @@ static bool nilfs_check_folio(struct folio *folio, char *kaddr)
goto Enamelen;
if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
goto Espan;
+ if (unlikely(p->inode &&
+ NILFS_PRIVATE_INODE(le64_to_cpu(p->inode))))
+ goto Einumber;
}
if (offs != limit)
goto Eend;
@@ -160,6 +163,9 @@ Enamelen:
goto bad_entry;
Espan:
error = "directory entry across blocks";
+ goto bad_entry;
+Einumber:
+ error = "disallowed inode number";
bad_entry:
nilfs_error(sb,
"bad entry in directory #%lu: %s - offset=%lu, inode=%lu, rec_len=%zd, name_len=%d",
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index 612e609158b5..1e86b9303b7c 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -56,13 +56,10 @@ int nilfs_ifile_create_inode(struct inode *ifile, ino_t *out_ino,
struct nilfs_palloc_req req;
int ret;
- req.pr_entry_nr = 0; /*
- * 0 says find free inode from beginning
- * of a group. dull code!!
- */
+ req.pr_entry_nr = NILFS_FIRST_INO(ifile->i_sb);
req.pr_entry_bh = NULL;
- ret = nilfs_palloc_prepare_alloc_entry(ifile, &req);
+ ret = nilfs_palloc_prepare_alloc_entry(ifile, &req, false);
if (!ret) {
ret = nilfs_palloc_get_entry_block(ifile, req.pr_entry_nr, 1,
&req.pr_entry_bh);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 728e90be3570..4017f7856440 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -116,9 +116,15 @@ enum {
#define NILFS_FIRST_INO(sb) (((struct the_nilfs *)sb->s_fs_info)->ns_first_ino)
#define NILFS_MDT_INODE(sb, ino) \
- ((ino) < NILFS_FIRST_INO(sb) && (NILFS_MDT_INO_BITS & BIT(ino)))
+ ((ino) < NILFS_USER_INO && (NILFS_MDT_INO_BITS & BIT(ino)))
#define NILFS_VALID_INODE(sb, ino) \
- ((ino) >= NILFS_FIRST_INO(sb) || (NILFS_SYS_INO_BITS & BIT(ino)))
+ ((ino) >= NILFS_FIRST_INO(sb) || \
+ ((ino) < NILFS_USER_INO && (NILFS_SYS_INO_BITS & BIT(ino))))
+
+#define NILFS_PRIVATE_INODE(ino) ({ \
+ ino_t __ino = (ino); \
+ ((__ino) < NILFS_USER_INO && (__ino) != NILFS_ROOT_INO && \
+ (__ino) != NILFS_SKETCH_INO); })
/**
* struct nilfs_transaction_info: context information for synchronization
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index f41d7b6d432c..e44dde57ab65 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -452,6 +452,12 @@ static int nilfs_store_disk_layout(struct the_nilfs *nilfs,
}
nilfs->ns_first_ino = le32_to_cpu(sbp->s_first_ino);
+ if (nilfs->ns_first_ino < NILFS_USER_INO) {
+ nilfs_err(nilfs->ns_sb,
+ "too small lower limit for non-reserved inode numbers: %u",
+ nilfs->ns_first_ino);
+ return -EINVAL;
+ }
nilfs->ns_blocks_per_segment = le32_to_cpu(sbp->s_blocks_per_segment);
if (nilfs->ns_blocks_per_segment < NILFS_SEG_MIN_BLOCKS) {
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 85da0629415d..1e829ed7b0ef 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -182,7 +182,7 @@ struct the_nilfs {
unsigned long ns_nrsvsegs;
unsigned long ns_first_data_block;
int ns_inode_size;
- int ns_first_ino;
+ unsigned int ns_first_ino;
u32 ns_crc_seed;
/* /sys/fs/<nilfs>/<device> */
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index f0467d3b3c88..6be175a1ab3c 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2366,6 +2366,11 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
}
list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
+ ret = ocfs2_assure_trans_credits(handle, credits);
+ if (ret < 0) {
+ mlog_errno(ret);
+ break;
+ }
ret = ocfs2_mark_extent_written(inode, &et, handle,
ue->ue_cpos, 1,
ue->ue_phys,
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 604fea3a26ff..530fba34f6d3 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -446,6 +446,23 @@ bail:
}
/*
+ * Make sure handle has at least 'nblocks' credits available. If it does not
+ * have that many credits available, we will try to extend the handle to have
+ * enough credits. If that fails, we will restart transaction to have enough
+ * credits. Similar notes regarding data consistency and locking implications
+ * as for ocfs2_extend_trans() apply here.
+ */
+int ocfs2_assure_trans_credits(handle_t *handle, int nblocks)
+{
+ int old_nblks = jbd2_handle_buffer_credits(handle);
+
+ trace_ocfs2_assure_trans_credits(old_nblks);
+ if (old_nblks >= nblocks)
+ return 0;
+ return ocfs2_extend_trans(handle, nblocks - old_nblks);
+}
+
+/*
* If we have fewer than thresh credits, extend by OCFS2_MAX_TRANS_DATA.
* If that fails, restart the transaction & regain write access for the
* buffer head which is used for metadata modifications.
@@ -479,12 +496,6 @@ bail:
return status;
}
-
-struct ocfs2_triggers {
- struct jbd2_buffer_trigger_type ot_triggers;
- int ot_offset;
-};
-
static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger_type *triggers)
{
return container_of(triggers, struct ocfs2_triggers, ot_triggers);
@@ -548,85 +559,76 @@ static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers,
static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers,
struct buffer_head *bh)
{
+ struct ocfs2_triggers *ot = to_ocfs2_trigger(triggers);
+
mlog(ML_ERROR,
"ocfs2_abort_trigger called by JBD2. bh = 0x%lx, "
"bh->b_blocknr = %llu\n",
(unsigned long)bh,
(unsigned long long)bh->b_blocknr);
- ocfs2_error(bh->b_assoc_map->host->i_sb,
+ ocfs2_error(ot->sb,
"JBD2 has aborted our journal, ocfs2 cannot continue\n");
}
-static struct ocfs2_triggers di_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
- .ot_offset = offsetof(struct ocfs2_dinode, i_check),
-};
-
-static struct ocfs2_triggers eb_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
- .ot_offset = offsetof(struct ocfs2_extent_block, h_check),
-};
-
-static struct ocfs2_triggers rb_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
- .ot_offset = offsetof(struct ocfs2_refcount_block, rf_check),
-};
-
-static struct ocfs2_triggers gd_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
- .ot_offset = offsetof(struct ocfs2_group_desc, bg_check),
-};
-
-static struct ocfs2_triggers db_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_db_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
-};
+static void ocfs2_setup_csum_triggers(struct super_block *sb,
+ enum ocfs2_journal_trigger_type type,
+ struct ocfs2_triggers *ot)
+{
+ BUG_ON(type >= OCFS2_JOURNAL_TRIGGER_COUNT);
-static struct ocfs2_triggers xb_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
- .ot_offset = offsetof(struct ocfs2_xattr_block, xb_check),
-};
+ switch (type) {
+ case OCFS2_JTR_DI:
+ ot->ot_triggers.t_frozen = ocfs2_frozen_trigger;
+ ot->ot_offset = offsetof(struct ocfs2_dinode, i_check);
+ break;
+ case OCFS2_JTR_EB:
+ ot->ot_triggers.t_frozen = ocfs2_frozen_trigger;
+ ot->ot_offset = offsetof(struct ocfs2_extent_block, h_check);
+ break;
+ case OCFS2_JTR_RB:
+ ot->ot_triggers.t_frozen = ocfs2_frozen_trigger;
+ ot->ot_offset = offsetof(struct ocfs2_refcount_block, rf_check);
+ break;
+ case OCFS2_JTR_GD:
+ ot->ot_triggers.t_frozen = ocfs2_frozen_trigger;
+ ot->ot_offset = offsetof(struct ocfs2_group_desc, bg_check);
+ break;
+ case OCFS2_JTR_DB:
+ ot->ot_triggers.t_frozen = ocfs2_db_frozen_trigger;
+ break;
+ case OCFS2_JTR_XB:
+ ot->ot_triggers.t_frozen = ocfs2_frozen_trigger;
+ ot->ot_offset = offsetof(struct ocfs2_xattr_block, xb_check);
+ break;
+ case OCFS2_JTR_DQ:
+ ot->ot_triggers.t_frozen = ocfs2_dq_frozen_trigger;
+ break;
+ case OCFS2_JTR_DR:
+ ot->ot_triggers.t_frozen = ocfs2_frozen_trigger;
+ ot->ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check);
+ break;
+ case OCFS2_JTR_DL:
+ ot->ot_triggers.t_frozen = ocfs2_frozen_trigger;
+ ot->ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check);
+ break;
+ case OCFS2_JTR_NONE:
+ /* To make compiler happy... */
+ return;
+ }
-static struct ocfs2_triggers dq_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_dq_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
-};
+ ot->ot_triggers.t_abort = ocfs2_abort_trigger;
+ ot->sb = sb;
+}
-static struct ocfs2_triggers dr_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
- .ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check),
-};
+void ocfs2_initialize_journal_triggers(struct super_block *sb,
+ struct ocfs2_triggers triggers[])
+{
+ enum ocfs2_journal_trigger_type type;
-static struct ocfs2_triggers dl_triggers = {
- .ot_triggers = {
- .t_frozen = ocfs2_frozen_trigger,
- .t_abort = ocfs2_abort_trigger,
- },
- .ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check),
-};
+ for (type = OCFS2_JTR_DI; type < OCFS2_JOURNAL_TRIGGER_COUNT; type++)
+ ocfs2_setup_csum_triggers(sb, type, &triggers[type]);
+}
static int __ocfs2_journal_access(handle_t *handle,
struct ocfs2_caching_info *ci,
@@ -708,56 +710,91 @@ static int __ocfs2_journal_access(handle_t *handle,
int ocfs2_journal_access_di(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &di_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_DI],
+ type);
}
int ocfs2_journal_access_eb(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &eb_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_EB],
+ type);
}
int ocfs2_journal_access_rb(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &rb_triggers,
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_RB],
type);
}
int ocfs2_journal_access_gd(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &gd_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_GD],
+ type);
}
int ocfs2_journal_access_db(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &db_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_DB],
+ type);
}
int ocfs2_journal_access_xb(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &xb_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_XB],
+ type);
}
int ocfs2_journal_access_dq(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &dq_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_DQ],
+ type);
}
int ocfs2_journal_access_dr(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &dr_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_DR],
+ type);
}
int ocfs2_journal_access_dl(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
- return __ocfs2_journal_access(handle, ci, bh, &dl_triggers, type);
+ struct ocfs2_super *osb = OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
+
+ return __ocfs2_journal_access(handle, ci, bh,
+ &osb->s_journal_triggers[OCFS2_JTR_DL],
+ type);
}
int ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci,
@@ -778,13 +815,15 @@ void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh)
if (!is_handle_aborted(handle)) {
journal_t *journal = handle->h_transaction->t_journal;
- mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed. "
- "Aborting transaction and journal.\n");
+ mlog(ML_ERROR, "jbd2_journal_dirty_metadata failed: "
+ "handle type %u started at line %u, credits %u/%u "
+ "errcode %d. Aborting transaction and journal.\n",
+ handle->h_type, handle->h_line_no,
+ handle->h_requested_credits,
+ jbd2_handle_buffer_credits(handle), status);
handle->h_err = status;
jbd2_journal_abort_handle(handle);
jbd2_journal_abort(journal, status);
- ocfs2_abort(bh->b_assoc_map->host->i_sb,
- "Journal already aborted.\n");
}
}
}
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 41c9fe7e62f9..e3c3a35dc5e0 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -243,6 +243,8 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb,
int ocfs2_commit_trans(struct ocfs2_super *osb,
handle_t *handle);
int ocfs2_extend_trans(handle_t *handle, int nblocks);
+int ocfs2_assure_trans_credits(handle_t *handle,
+ int nblocks);
int ocfs2_allocate_extend_trans(handle_t *handle,
int thresh);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index a503c553bab2..8fe826143d7b 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -284,6 +284,30 @@ enum ocfs2_mount_options
#define OCFS2_OSB_ERROR_FS 0x0004
#define OCFS2_DEFAULT_ATIME_QUANTUM 60
+struct ocfs2_triggers {
+ struct jbd2_buffer_trigger_type ot_triggers;
+ int ot_offset;
+ struct super_block *sb;
+};
+
+enum ocfs2_journal_trigger_type {
+ OCFS2_JTR_DI,
+ OCFS2_JTR_EB,
+ OCFS2_JTR_RB,
+ OCFS2_JTR_GD,
+ OCFS2_JTR_DB,
+ OCFS2_JTR_XB,
+ OCFS2_JTR_DQ,
+ OCFS2_JTR_DR,
+ OCFS2_JTR_DL,
+ OCFS2_JTR_NONE /* This must be the last entry */
+};
+
+#define OCFS2_JOURNAL_TRIGGER_COUNT OCFS2_JTR_NONE
+
+void ocfs2_initialize_journal_triggers(struct super_block *sb,
+ struct ocfs2_triggers triggers[]);
+
struct ocfs2_journal;
struct ocfs2_slot_info;
struct ocfs2_recovery_map;
@@ -351,6 +375,9 @@ struct ocfs2_super
struct ocfs2_journal *journal;
unsigned long osb_commit_interval;
+ /* Journal triggers for checksum */
+ struct ocfs2_triggers s_journal_triggers[OCFS2_JOURNAL_TRIGGER_COUNT];
+
struct delayed_work la_enable_wq;
/*
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 60e208b01c8d..0511c69c9fde 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2577,6 +2577,8 @@ DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_commit_cache_end);
DEFINE_OCFS2_INT_INT_EVENT(ocfs2_extend_trans);
+DEFINE_OCFS2_INT_EVENT(ocfs2_assure_trans_credits);
+
DEFINE_OCFS2_INT_EVENT(ocfs2_extend_trans_restart);
DEFINE_OCFS2_INT_INT_EVENT(ocfs2_allocate_extend_trans);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 8aabaed2c1cb..afee70125ae3 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1075,9 +1075,11 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
debugfs_create_file("fs_state", S_IFREG|S_IRUSR, osb->osb_debug_root,
osb, &ocfs2_osb_debug_fops);
- if (ocfs2_meta_ecc(osb))
+ if (ocfs2_meta_ecc(osb)) {
+ ocfs2_initialize_journal_triggers(sb, osb->s_journal_triggers);
ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats,
osb->osb_debug_root);
+ }
status = ocfs2_mount_volume(sb);
if (status < 0)
diff --git a/fs/open.c b/fs/open.c
index 89cafb572061..278b3edcda44 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -202,13 +202,13 @@ long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
return error;
}
-SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length)
+SYSCALL_DEFINE2(ftruncate, unsigned int, fd, off_t, length)
{
return do_sys_ftruncate(fd, length, 1);
}
#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length)
+COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_off_t, length)
{
return do_sys_ftruncate(fd, length, 1);
}
@@ -1004,11 +1004,6 @@ static int do_dentry_open(struct file *f,
}
}
- /*
- * Once we return a file with FMODE_OPENED, __fput() will call
- * fsnotify_close(), so we need fsnotify_open() here for symmetry.
- */
- fsnotify_open(f);
return 0;
cleanup_all:
@@ -1085,8 +1080,19 @@ EXPORT_SYMBOL(file_path);
*/
int vfs_open(const struct path *path, struct file *file)
{
+ int ret;
+
file->f_path = *path;
- return do_dentry_open(file, NULL);
+ ret = do_dentry_open(file, NULL);
+ if (!ret) {
+ /*
+ * Once we return a file with FMODE_OPENED, __fput() will call
+ * fsnotify_close(), so we need fsnotify_open() here for
+ * symmetry.
+ */
+ fsnotify_open(file);
+ }
+ return ret;
}
struct file *dentry_open(const struct path *path, int flags,
@@ -1177,8 +1183,10 @@ struct file *kernel_file_open(const struct path *path, int flags,
error = do_dentry_open(f, NULL);
if (error) {
fput(f);
- f = ERR_PTR(error);
+ return ERR_PTR(error);
}
+
+ fsnotify_open(f);
return f;
}
EXPORT_SYMBOL_GPL(kernel_file_open);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 116f542442dd..ab65e98a1def 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -1314,10 +1314,6 @@ static int ovl_create_tmpfile(struct file *file, struct dentry *dentry,
int flags = file->f_flags | OVL_OPEN_FLAGS;
int err;
- err = ovl_copy_up(dentry->d_parent);
- if (err)
- return err;
-
old_cred = ovl_override_creds(dentry->d_sb);
err = ovl_setup_cred_for_create(dentry, inode, mode, old_cred);
if (err)
@@ -1360,6 +1356,10 @@ static int ovl_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
if (!OVL_FS(dentry->d_sb)->tmpfile)
return -EOPNOTSUPP;
+ err = ovl_copy_up(dentry->d_parent);
+ if (err)
+ return err;
+
err = ovl_want_write(dentry);
if (err)
return err;
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
index 063409069f56..5868cb222955 100644
--- a/fs/overlayfs/export.c
+++ b/fs/overlayfs/export.c
@@ -181,6 +181,10 @@ static int ovl_check_encode_origin(struct dentry *dentry)
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
bool decodable = ofs->config.nfs_export;
+ /* No upper layer? */
+ if (!ovl_upper_mnt(ofs))
+ return 1;
+
/* Lower file handle for non-upper non-decodable */
if (!ovl_dentry_upper(dentry) && !decodable)
return 1;
@@ -209,7 +213,7 @@ static int ovl_check_encode_origin(struct dentry *dentry)
* ovl_connect_layer() will try to make origin's layer "connected" by
* copying up a "connectable" ancestor.
*/
- if (d_is_dir(dentry) && ovl_upper_mnt(ofs) && decodable)
+ if (d_is_dir(dentry) && decodable)
return ovl_connect_layer(dentry);
/* Lower file handle for indexed and non-upper dir/non-dir */
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f8d35f993fe5..71e5039d940d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -707,6 +707,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
#ifdef CONFIG_X86_USER_SHADOW_STACK
[ilog2(VM_SHADOW_STACK)] = "ss",
#endif
+#ifdef CONFIG_64BIT
+ [ilog2(VM_SEALED)] = "sl",
+#endif
};
size_t i;
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index bb86fc0641d8..6397fdefd876 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -134,7 +134,7 @@ module_param(enable_oplocks, bool, 0644);
MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1");
module_param(enable_gcm_256, bool, 0644);
-MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: n/N/0");
+MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/0");
module_param(require_gcm_256, bool, 0644);
MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0");
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 73482734a8d8..557b68e99d0a 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -1494,6 +1494,8 @@ struct cifs_aio_ctx {
struct cifs_io_request {
struct netfs_io_request rreq;
struct cifsFileInfo *cfile;
+ struct TCP_Server_Info *server;
+ pid_t pid;
};
/* asynchronous read support */
@@ -1504,7 +1506,6 @@ struct cifs_io_subrequest {
struct cifs_io_request *req;
};
ssize_t got_bytes;
- pid_t pid;
unsigned int xid;
int result;
bool have_xid;
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 25e9ab947c17..595c4b673707 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1345,8 +1345,8 @@ cifs_async_readv(struct cifs_io_subrequest *rdata)
if (rc)
return rc;
- smb->hdr.Pid = cpu_to_le16((__u16)rdata->pid);
- smb->hdr.PidHigh = cpu_to_le16((__u16)(rdata->pid >> 16));
+ smb->hdr.Pid = cpu_to_le16((__u16)rdata->req->pid);
+ smb->hdr.PidHigh = cpu_to_le16((__u16)(rdata->req->pid >> 16));
smb->AndXCommand = 0xFF; /* none */
smb->Fid = rdata->req->cfile->fid.netfid;
@@ -1689,8 +1689,8 @@ cifs_async_writev(struct cifs_io_subrequest *wdata)
if (rc)
goto async_writev_out;
- smb->hdr.Pid = cpu_to_le16((__u16)wdata->pid);
- smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->pid >> 16));
+ smb->hdr.Pid = cpu_to_le16((__u16)wdata->req->pid);
+ smb->hdr.PidHigh = cpu_to_le16((__u16)(wdata->req->pid >> 16));
smb->AndXCommand = 0xFF; /* none */
smb->Fid = wdata->req->cfile->fid.netfid;
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 9d5c2440abfc..1374635e89fa 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -134,17 +134,15 @@ fail:
static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
{
struct netfs_io_request *rreq = subreq->rreq;
- struct TCP_Server_Info *server;
struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq);
struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
+ struct TCP_Server_Info *server = req->server;
struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
size_t rsize = 0;
int rc;
rdata->xid = get_xid();
rdata->have_xid = true;
-
- server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses);
rdata->server = server;
if (cifs_sb->ctx->rsize == 0)
@@ -179,15 +177,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
struct netfs_io_request *rreq = subreq->rreq;
struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq);
struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
- struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
- pid_t pid;
int rc = 0;
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
- pid = req->cfile->pid;
- else
- pid = current->tgid; // Ummm... This may be a workqueue
-
cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n",
__func__, rreq->debug_id, subreq->debug_index, rreq->mapping,
subreq->transferred, subreq->len);
@@ -201,16 +192,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
}
__set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags);
- rdata->pid = pid;
-
- rc = adjust_credits(rdata->server, &rdata->credits, rdata->subreq.len);
- if (!rc) {
- if (rdata->req->cfile->invalidHandle)
- rc = -EAGAIN;
- else
- rc = rdata->server->ops->async_readv(rdata);
- }
+ rc = rdata->server->ops->async_readv(rdata);
out:
if (rc)
netfs_subreq_terminated(subreq, rc, false);
@@ -245,11 +228,15 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file)
rreq->rsize = cifs_sb->ctx->rsize;
rreq->wsize = cifs_sb->ctx->wsize;
+ req->pid = current->tgid; // Ummm... This may be a workqueue
if (file) {
open_file = file->private_data;
rreq->netfs_priv = file->private_data;
req->cfile = cifsFileInfo_get(open_file);
+ req->server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses);
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
+ req->pid = req->cfile->pid;
} else if (rreq->origin != NETFS_WRITEBACK) {
WARN_ON_ONCE(1);
return -EIO;
@@ -259,35 +246,6 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file)
}
/*
- * Expand the size of a readahead to the size of the rsize, if at least as
- * large as a page, allowing for the possibility that rsize is not pow-2
- * aligned.
- */
-static void cifs_expand_readahead(struct netfs_io_request *rreq)
-{
- unsigned int rsize = rreq->rsize;
- loff_t misalignment, i_size = i_size_read(rreq->inode);
-
- if (rsize < PAGE_SIZE)
- return;
-
- if (rsize < INT_MAX)
- rsize = roundup_pow_of_two(rsize);
- else
- rsize = ((unsigned int)INT_MAX + 1) / 2;
-
- misalignment = rreq->start & (rsize - 1);
- if (misalignment) {
- rreq->start -= misalignment;
- rreq->len += misalignment;
- }
-
- rreq->len = round_up(rreq->len, rsize);
- if (rreq->start < i_size && rreq->len > i_size - rreq->start)
- rreq->len = i_size - rreq->start;
-}
-
-/*
* Completion of a request operation.
*/
static void cifs_rreq_done(struct netfs_io_request *rreq)
@@ -342,7 +300,6 @@ const struct netfs_request_ops cifs_req_ops = {
.init_request = cifs_init_request,
.free_request = cifs_free_request,
.free_subrequest = cifs_free_subrequest,
- .expand_readahead = cifs_expand_readahead,
.clamp_length = cifs_clamp_length,
.issue_read = cifs_req_issue_read,
.done = cifs_rreq_done,
@@ -3200,8 +3157,6 @@ static int cifs_swap_rw(struct kiocb *iocb, struct iov_iter *iter)
{
ssize_t ret;
- WARN_ON_ONCE(iov_iter_count(iter) != PAGE_SIZE);
-
if (iov_iter_rw(iter) == READ)
ret = netfs_unbuffered_read_iter_locked(iocb, iter);
else
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 38a06e8a0f90..2ae2dbb6202b 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -4484,6 +4484,16 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
return rc;
}
+static void smb2_readv_worker(struct work_struct *work)
+{
+ struct cifs_io_subrequest *rdata =
+ container_of(work, struct cifs_io_subrequest, subreq.work);
+
+ netfs_subreq_terminated(&rdata->subreq,
+ (rdata->result == 0 || rdata->result == -EAGAIN) ?
+ rdata->got_bytes : rdata->result, true);
+}
+
static void
smb2_readv_callback(struct mid_q_entry *mid)
{
@@ -4578,9 +4588,8 @@ smb2_readv_callback(struct mid_q_entry *mid)
rdata->result = 0;
}
rdata->credits.value = 0;
- netfs_subreq_terminated(&rdata->subreq,
- (rdata->result == 0 || rdata->result == -EAGAIN) ?
- rdata->got_bytes : rdata->result, true);
+ INIT_WORK(&rdata->subreq.work, smb2_readv_worker);
+ queue_work(cifsiod_wq, &rdata->subreq.work);
release_mid(mid);
add_credits(server, &credits, 0);
}
@@ -4612,7 +4621,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
io_parms.length = rdata->subreq.len;
io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid;
io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid;
- io_parms.pid = rdata->pid;
+ io_parms.pid = rdata->req->pid;
rc = smb2_new_read_req(
(void **) &buf, &total_len, &io_parms, rdata, 0, 0);
@@ -4864,7 +4873,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
.length = wdata->subreq.len,
.persistent_fid = wdata->req->cfile->fid.persistent_fid,
.volatile_fid = wdata->req->cfile->fid.volatile_fid,
- .pid = wdata->pid,
+ .pid = wdata->req->pid,
};
io_parms = &_io_parms;
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index 8d10be1fe18a..c3ee42188d25 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -917,6 +917,40 @@ struct smb2_query_directory_rsp {
__u8 Buffer[];
} __packed;
+/* DeviceType Flags */
+#define FILE_DEVICE_CD_ROM 0x00000002
+#define FILE_DEVICE_CD_ROM_FILE_SYSTEM 0x00000003
+#define FILE_DEVICE_DFS 0x00000006
+#define FILE_DEVICE_DISK 0x00000007
+#define FILE_DEVICE_DISK_FILE_SYSTEM 0x00000008
+#define FILE_DEVICE_FILE_SYSTEM 0x00000009
+#define FILE_DEVICE_NAMED_PIPE 0x00000011
+#define FILE_DEVICE_NETWORK 0x00000012
+#define FILE_DEVICE_NETWORK_FILE_SYSTEM 0x00000014
+#define FILE_DEVICE_NULL 0x00000015
+#define FILE_DEVICE_PARALLEL_PORT 0x00000016
+#define FILE_DEVICE_PRINTER 0x00000018
+#define FILE_DEVICE_SERIAL_PORT 0x0000001b
+#define FILE_DEVICE_STREAMS 0x0000001e
+#define FILE_DEVICE_TAPE 0x0000001f
+#define FILE_DEVICE_TAPE_FILE_SYSTEM 0x00000020
+#define FILE_DEVICE_VIRTUAL_DISK 0x00000024
+#define FILE_DEVICE_NETWORK_REDIRECTOR 0x00000028
+
+/* Device Characteristics */
+#define FILE_REMOVABLE_MEDIA 0x00000001
+#define FILE_READ_ONLY_DEVICE 0x00000002
+#define FILE_FLOPPY_DISKETTE 0x00000004
+#define FILE_WRITE_ONCE_MEDIA 0x00000008
+#define FILE_REMOTE_DEVICE 0x00000010
+#define FILE_DEVICE_IS_MOUNTED 0x00000020
+#define FILE_VIRTUAL_VOLUME 0x00000040
+#define FILE_DEVICE_SECURE_OPEN 0x00000100
+#define FILE_CHARACTERISTIC_TS_DEVICE 0x00001000
+#define FILE_CHARACTERISTIC_WEBDAV_DEVICE 0x00002000
+#define FILE_PORTABLE_DEVICE 0x00004000
+#define FILE_DEVICE_ALLOW_APPCONTAINER_TRAVERSAL 0x00020000
+
/*
* Maximum number of iovs we need for a set-info request.
* The largest one is rename/hardlink
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index e7e07891781b..840c71c66b30 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -2051,15 +2051,22 @@ out_err1:
* @access: file access flags
* @disposition: file disposition flags
* @may_flags: set with MAY_ flags
+ * @is_dir: is creating open flags for directory
*
* Return: file open flags
*/
static int smb2_create_open_flags(bool file_present, __le32 access,
__le32 disposition,
- int *may_flags)
+ int *may_flags,
+ bool is_dir)
{
int oflags = O_NONBLOCK | O_LARGEFILE;
+ if (is_dir) {
+ access &= ~FILE_WRITE_DESIRE_ACCESS_LE;
+ ksmbd_debug(SMB, "Discard write access to a directory\n");
+ }
+
if (access & FILE_READ_DESIRED_ACCESS_LE &&
access & FILE_WRITE_DESIRE_ACCESS_LE) {
oflags |= O_RDWR;
@@ -3167,7 +3174,9 @@ int smb2_open(struct ksmbd_work *work)
open_flags = smb2_create_open_flags(file_present, daccess,
req->CreateDisposition,
- &may_flags);
+ &may_flags,
+ req->CreateOptions & FILE_DIRECTORY_FILE_LE ||
+ (file_present && S_ISDIR(d_inode(path.dentry)->i_mode)));
if (!test_tree_conn_flag(tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) {
if (open_flags & (O_CREAT | O_TRUNC)) {
@@ -5314,8 +5323,13 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work,
info = (struct filesystem_device_info *)rsp->Buffer;
- info->DeviceType = cpu_to_le32(stfs.f_type);
- info->DeviceCharacteristics = cpu_to_le32(0x00000020);
+ info->DeviceType = cpu_to_le32(FILE_DEVICE_DISK);
+ info->DeviceCharacteristics =
+ cpu_to_le32(FILE_DEVICE_IS_MOUNTED);
+ if (!test_tree_conn_flag(work->tcon,
+ KSMBD_TREE_CONN_FLAG_WRITABLE))
+ info->DeviceCharacteristics |=
+ cpu_to_le32(FILE_READ_ONLY_DEVICE);
rsp->OutputBufferLength = cpu_to_le32(8);
break;
}
diff --git a/fs/super.c b/fs/super.c
index b72f1d288e95..095ba793e10c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1502,8 +1502,17 @@ static int fs_bdev_thaw(struct block_device *bdev)
lockdep_assert_held(&bdev->bd_fsfreeze_mutex);
+ /*
+ * The block device may have been frozen before it was claimed by a
+ * filesystem. Concurrently another process might try to mount that
+ * frozen block device and has temporarily claimed the block device for
+ * that purpose causing a concurrent fs_bdev_thaw() to end up here. The
+ * mounter is already about to abort mounting because they still saw an
+ * elevanted bdev->bd_fsfreeze_count so get_bdev_super() will return
+ * NULL in that case.
+ */
sb = get_bdev_super(bdev);
- if (WARN_ON_ONCE(!sb))
+ if (!sb)
return -EINVAL;
if (sb->s_op->thaw_super)
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c101cf266bc4..6af6f744fdd6 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4058,20 +4058,32 @@ xfs_bmapi_reserve_delalloc(
xfs_extlen_t indlen;
uint64_t fdblocks;
int error;
- xfs_fileoff_t aoff = off;
+ xfs_fileoff_t aoff;
+ bool use_cowextszhint =
+ whichfork == XFS_COW_FORK && !prealloc;
+retry:
/*
* Cap the alloc length. Keep track of prealloc so we know whether to
* tag the inode before we return.
*/
+ aoff = off;
alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN);
if (!eof)
alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
if (prealloc && alen >= len)
prealloc = alen - len;
- /* Figure out the extent size, adjust alen */
- if (whichfork == XFS_COW_FORK) {
+ /*
+ * If we're targetting the COW fork but aren't creating a speculative
+ * posteof preallocation, try to expand the reservation to align with
+ * the COW extent size hint if there's sufficient free space.
+ *
+ * Unlike the data fork, the CoW cancellation functions will free all
+ * the reservations at inactivation, so we don't require that every
+ * delalloc reservation have a dirty pagecache.
+ */
+ if (use_cowextszhint) {
struct xfs_bmbt_irec prev;
xfs_extlen_t extsz = xfs_get_cowextsz_hint(ip);
@@ -4090,7 +4102,7 @@ xfs_bmapi_reserve_delalloc(
*/
error = xfs_quota_reserve_blkres(ip, alen);
if (error)
- return error;
+ goto out;
/*
* Split changing sb for alen and indlen since they could be coming
@@ -4140,6 +4152,17 @@ out_unreserve_frextents:
out_unreserve_quota:
if (XFS_IS_QUOTA_ON(mp))
xfs_quota_unreserve_blkres(ip, alen);
+out:
+ if (error == -ENOSPC || error == -EDQUOT) {
+ trace_xfs_delalloc_enospc(ip, off, len);
+
+ if (prealloc || use_cowextszhint) {
+ /* retry without any preallocation */
+ use_cowextszhint = false;
+ prealloc = 0;
+ goto retry;
+ }
+ }
return error;
}
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 97996cb79aaa..454b63ef7201 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -996,7 +996,7 @@ struct xfs_getparents_by_handle {
#define XFS_IOC_FSGEOMETRY _IOR ('X', 126, struct xfs_fsop_geom)
#define XFS_IOC_BULKSTAT _IOR ('X', 127, struct xfs_bulkstat_req)
#define XFS_IOC_INUMBERS _IOR ('X', 128, struct xfs_inumbers_req)
-#define XFS_IOC_EXCHANGE_RANGE _IOWR('X', 129, struct xfs_exchange_range)
+#define XFS_IOC_EXCHANGE_RANGE _IOW ('X', 129, struct xfs_exchange_range)
/* XFS_IOC_GETFSUUID ---------- deprecated 140 */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index e7a7bfbe75b4..513b50da6215 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -379,10 +379,13 @@ xfs_dinode_verify_fork(
/*
* A directory small enough to fit in the inode must be stored
* in local format. The directory sf <-> extents conversion
- * code updates the directory size accordingly.
+ * code updates the directory size accordingly. Directories
+ * being truncated have zero size and are not subject to this
+ * check.
*/
if (S_ISDIR(mode)) {
- if (be64_to_cpu(dip->di_size) <= fork_size &&
+ if (dip->di_size &&
+ be64_to_cpu(dip->di_size) <= fork_size &&
fork_format != XFS_DINODE_FMT_LOCAL)
return __this_address;
}
@@ -528,9 +531,19 @@ xfs_dinode_verify(
if (mode && xfs_mode_to_ftype(mode) == XFS_DIR3_FT_UNKNOWN)
return __this_address;
- /* No zero-length symlinks/dirs. */
- if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
- return __this_address;
+ /*
+ * No zero-length symlinks/dirs unless they're unlinked and hence being
+ * inactivated.
+ */
+ if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0) {
+ if (dip->di_version > 1) {
+ if (dip->di_nlink)
+ return __this_address;
+ } else {
+ if (dip->di_onlink)
+ return __this_address;
+ }
+ }
fa = xfs_dinode_verify_nrext64(mp, dip);
if (fa)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index ac2e77ebb54c..a4d9fbc21b83 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -486,13 +486,11 @@ out_unlock:
/*
* Test whether it is appropriate to check an inode for and free post EOF
- * blocks. The 'force' parameter determines whether we should also consider
- * regular files that are marked preallocated or append-only.
+ * blocks.
*/
bool
xfs_can_free_eofblocks(
- struct xfs_inode *ip,
- bool force)
+ struct xfs_inode *ip)
{
struct xfs_bmbt_irec imap;
struct xfs_mount *mp = ip->i_mount;
@@ -526,11 +524,11 @@ xfs_can_free_eofblocks(
return false;
/*
- * Do not free real preallocated or append-only files unless the file
- * has delalloc blocks and we are forced to remove them.
+ * Only free real extents for inodes with persistent preallocations or
+ * the append-only flag.
*/
if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
- if (!force || ip->i_delayed_blks == 0)
+ if (ip->i_delayed_blks == 0)
return false;
/*
@@ -584,6 +582,22 @@ xfs_free_eofblocks(
/* Wait on dio to ensure i_size has settled. */
inode_dio_wait(VFS_I(ip));
+ /*
+ * For preallocated files only free delayed allocations.
+ *
+ * Note that this means we also leave speculative preallocations in
+ * place for preallocated files.
+ */
+ if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) {
+ if (ip->i_delayed_blks) {
+ xfs_bmap_punch_delalloc_range(ip,
+ round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize),
+ LLONG_MAX);
+ }
+ xfs_inode_clear_eofblocks_tag(ip);
+ return 0;
+ }
+
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error) {
ASSERT(xfs_is_shutdown(mp));
@@ -891,7 +905,7 @@ xfs_prepare_shift(
* Trim eofblocks to avoid shifting uninitialized post-eof preallocation
* into the accessible region of the file.
*/
- if (xfs_can_free_eofblocks(ip, true)) {
+ if (xfs_can_free_eofblocks(ip)) {
error = xfs_free_eofblocks(ip);
if (error)
return error;
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 51f84d8ff372..eb0895bfb9da 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -63,7 +63,7 @@ int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset,
xfs_off_t len);
/* EOF block manipulation functions */
-bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
+bool xfs_can_free_eofblocks(struct xfs_inode *ip);
int xfs_free_eofblocks(struct xfs_inode *ip);
int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 0953163a2d84..9967334ea99f 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1155,7 +1155,7 @@ xfs_inode_free_eofblocks(
}
*lockflags |= XFS_IOLOCK_EXCL;
- if (xfs_can_free_eofblocks(ip, false))
+ if (xfs_can_free_eofblocks(ip))
return xfs_free_eofblocks(ip);
/* inode could be preallocated or append-only */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 58fb7a5062e1..a4e3cd8971fc 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -42,6 +42,7 @@
#include "xfs_pnfs.h"
#include "xfs_parent.h"
#include "xfs_xattr.h"
+#include "xfs_sb.h"
struct kmem_cache *xfs_inode_cache;
@@ -870,9 +871,16 @@ xfs_init_new_inode(
* this saves us from needing to run a separate transaction to set the
* fork offset in the immediate future.
*/
- if (init_xattrs && xfs_has_attr(mp)) {
+ if (init_xattrs) {
ip->i_forkoff = xfs_default_attroffset(ip) >> 3;
xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0);
+
+ if (!xfs_has_attr(mp)) {
+ spin_lock(&mp->m_sb_lock);
+ xfs_add_attr(mp);
+ spin_unlock(&mp->m_sb_lock);
+ xfs_log_sb(tp);
+ }
}
/*
@@ -1595,7 +1603,7 @@ xfs_release(
if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL))
return 0;
- if (xfs_can_free_eofblocks(ip, false)) {
+ if (xfs_can_free_eofblocks(ip)) {
/*
* Check if the inode is being opened, written and closed
* frequently and we have delayed allocation blocks outstanding
@@ -1856,15 +1864,13 @@ xfs_inode_needs_inactive(
/*
* This file isn't being freed, so check if there are post-eof blocks
- * to free. @force is true because we are evicting an inode from the
- * cache. Post-eof blocks must be freed, lest we end up with broken
- * free space accounting.
+ * to free.
*
* Note: don't bother with iolock here since lockdep complains about
* acquiring it in reclaim context. We have the only reference to the
* inode at this point anyways.
*/
- return xfs_can_free_eofblocks(ip, true);
+ return xfs_can_free_eofblocks(ip);
}
/*
@@ -1947,15 +1953,11 @@ xfs_inactive(
if (VFS_I(ip)->i_nlink != 0) {
/*
- * force is true because we are evicting an inode from the
- * cache. Post-eof blocks must be freed, lest we end up with
- * broken free space accounting.
- *
* Note: don't bother with iolock here since lockdep complains
* about acquiring it in reclaim context. We have the only
* reference to the inode at this point anyways.
*/
- if (xfs_can_free_eofblocks(ip, true))
+ if (xfs_can_free_eofblocks(ip))
error = xfs_free_eofblocks(ip);
goto out;
@@ -2548,11 +2550,26 @@ xfs_ifree_cluster(
* This buffer may not have been correctly initialised as we
* didn't read it from disk. That's not important because we are
* only using to mark the buffer as stale in the log, and to
- * attach stale cached inodes on it. That means it will never be
- * dispatched for IO. If it is, we want to know about it, and we
- * want it to fail. We can acheive this by adding a write
- * verifier to the buffer.
+ * attach stale cached inodes on it.
+ *
+ * For the inode that triggered the cluster freeing, this
+ * attachment may occur in xfs_inode_item_precommit() after we
+ * have marked this buffer stale. If this buffer was not in
+ * memory before xfs_ifree_cluster() started, it will not be
+ * marked XBF_DONE and this will cause problems later in
+ * xfs_inode_item_precommit() when we trip over a (stale, !done)
+ * buffer to attached to the transaction.
+ *
+ * Hence we have to mark the buffer as XFS_DONE here. This is
+ * safe because we are also marking the buffer as XBF_STALE and
+ * XFS_BLI_STALE. That means it will never be dispatched for
+ * IO and it won't be unlocked until the cluster freeing has
+ * been committed to the journal and the buffer unpinned. If it
+ * is written, we want to know about it, and we want it to
+ * fail. We can acheive this by adding a write verifier to the
+ * buffer.
*/
+ bp->b_flags |= XBF_DONE;
bp->b_ops = &xfs_inode_buf_ops;
/*
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 378342673925..414903885ab9 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1148,33 +1148,23 @@ xfs_buffered_write_iomap_begin(
}
}
-retry:
- error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
- end_fsb - offset_fsb, prealloc_blocks,
- allocfork == XFS_DATA_FORK ? &imap : &cmap,
- allocfork == XFS_DATA_FORK ? &icur : &ccur,
- allocfork == XFS_DATA_FORK ? eof : cow_eof);
- switch (error) {
- case 0:
- break;
- case -ENOSPC:
- case -EDQUOT:
- /* retry without any preallocation */
- trace_xfs_delalloc_enospc(ip, offset, count);
- if (prealloc_blocks) {
- prealloc_blocks = 0;
- goto retry;
- }
- fallthrough;
- default:
- goto out_unlock;
- }
-
if (allocfork == XFS_COW_FORK) {
+ error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
+ end_fsb - offset_fsb, prealloc_blocks, &cmap,
+ &ccur, cow_eof);
+ if (error)
+ goto out_unlock;
+
trace_xfs_iomap_alloc(ip, offset, count, allocfork, &cmap);
goto found_cow;
}
+ error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
+ end_fsb - offset_fsb, prealloc_blocks, &imap, &icur,
+ eof);
+ if (error)
+ goto out_unlock;
+
/*
* Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
* them out if the write happens to fail.