summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/block-group.c17
-rw-r--r--fs/btrfs/block-group.h2
-rw-r--r--fs/btrfs/disk-io.c13
-rw-r--r--fs/btrfs/extent-tree.c5
-rw-r--r--fs/btrfs/extent_io.c13
-rw-r--r--fs/btrfs/inode.c10
-rw-r--r--fs/btrfs/relocation.c45
-rw-r--r--fs/btrfs/tree-checker.c14
-rw-r--r--fs/inode.c3
-rw-r--r--fs/nilfs2/inode.c8
-rw-r--r--fs/nilfs2/segment.c2
-rw-r--r--fs/nilfs2/the_nilfs.h2
-rw-r--r--fs/proc/kcore.c30
-rw-r--r--fs/smb/client/cifs_debug.c10
-rw-r--r--fs/smb/client/file.c25
-rw-r--r--fs/zonefs/file.c111
-rw-r--r--fs/zonefs/super.c9
-rw-r--r--fs/zonefs/zonefs.h2
18 files changed, 169 insertions, 152 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 030ab44fce18..82324c327a50 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -441,13 +441,23 @@ void btrfs_wait_block_group_cache_progress(struct btrfs_block_group *cache,
u64 num_bytes)
{
struct btrfs_caching_control *caching_ctl;
+ int progress;
caching_ctl = btrfs_get_caching_control(cache);
if (!caching_ctl)
return;
+ /*
+ * We've already failed to allocate from this block group, so even if
+ * there's enough space in the block group it isn't contiguous enough to
+ * allow for an allocation, so wait for at least the next wakeup tick,
+ * or for the thing to be done.
+ */
+ progress = atomic_read(&caching_ctl->progress);
+
wait_event(caching_ctl->wait, btrfs_block_group_done(cache) ||
- (cache->free_space_ctl->free_space >= num_bytes));
+ (progress != atomic_read(&caching_ctl->progress) &&
+ (cache->free_space_ctl->free_space >= num_bytes)));
btrfs_put_caching_control(caching_ctl);
}
@@ -802,8 +812,10 @@ next:
if (total_found > CACHING_CTL_WAKE_UP) {
total_found = 0;
- if (wakeup)
+ if (wakeup) {
+ atomic_inc(&caching_ctl->progress);
wake_up(&caching_ctl->wait);
+ }
}
}
path->slots[0]++;
@@ -910,6 +922,7 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait)
init_waitqueue_head(&caching_ctl->wait);
caching_ctl->block_group = cache;
refcount_set(&caching_ctl->count, 2);
+ atomic_set(&caching_ctl->progress, 0);
btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
spin_lock(&cache->lock);
diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h
index aba5dff66c19..74b61e663028 100644
--- a/fs/btrfs/block-group.h
+++ b/fs/btrfs/block-group.h
@@ -90,6 +90,8 @@ struct btrfs_caching_control {
wait_queue_head_t wait;
struct btrfs_work work;
struct btrfs_block_group *block_group;
+ /* Track progress of caching during allocation. */
+ atomic_t progress;
refcount_t count;
};
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9b9914e5f03d..a9a2c5446c18 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1103,7 +1103,8 @@ static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
btrfs_drew_lock_init(&root->snapshot_lock);
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
- !btrfs_is_data_reloc_root(root)) {
+ !btrfs_is_data_reloc_root(root) &&
+ is_fstree(root->root_key.objectid)) {
set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
btrfs_check_and_init_root_item(&root->root_item);
}
@@ -1300,6 +1301,16 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
root = btrfs_get_global_root(fs_info, objectid);
if (root)
return root;
+
+ /*
+ * If we're called for non-subvolume trees, and above function didn't
+ * find one, do not try to read it from disk.
+ *
+ * This is namely for free-space-tree and quota tree, which can change
+ * at runtime and should only be grabbed from fs_info.
+ */
+ if (!is_fstree(objectid) && objectid != BTRFS_DATA_RELOC_TREE_OBJECTID)
+ return ERR_PTR(-ENOENT);
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 911908ea5f6f..f396a9afa403 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4310,8 +4310,11 @@ have_block_group:
ret = 0;
}
- if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
+ if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) {
+ if (!cache_block_group_error)
+ cache_block_group_error = -EIO;
goto loop;
+ }
if (!find_free_extent_check_size_class(ffe_ctl, block_group))
goto loop;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a91d5ad27984..ca765d62324f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2145,6 +2145,12 @@ retry:
continue;
}
+ if (!folio_test_dirty(folio)) {
+ /* Someone wrote it for us. */
+ folio_unlock(folio);
+ continue;
+ }
+
if (wbc->sync_mode != WB_SYNC_NONE) {
if (folio_test_writeback(folio))
submit_write_bio(bio_ctrl, 0);
@@ -2164,11 +2170,12 @@ retry:
}
/*
- * the filesystem may choose to bump up nr_to_write.
+ * The filesystem may choose to bump up nr_to_write.
* We have to make sure to honor the new nr_to_write
- * at any time
+ * at any time.
*/
- nr_to_write_done = wbc->nr_to_write <= 0;
+ nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE &&
+ wbc->nr_to_write <= 0);
}
folio_batch_release(&fbatch);
cond_resched();
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 49cef61f6a39..9055e19b01ef 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1654,8 +1654,6 @@ out_unlock:
clear_bits,
page_ops);
start += cur_alloc_size;
- if (start >= end)
- return ret;
}
/*
@@ -1664,9 +1662,11 @@ out_unlock:
* space_info's bytes_may_use counter, reserved in
* btrfs_check_data_free_space().
*/
- extent_clear_unlock_delalloc(inode, start, end, locked_page,
- clear_bits | EXTENT_CLEAR_DATA_RESV,
- page_ops);
+ if (start < end) {
+ clear_bits |= EXTENT_CLEAR_DATA_RESV;
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ clear_bits, page_ops);
+ }
return ret;
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 25a3361caedc..46c3c1d57266 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1916,7 +1916,39 @@ again:
err = PTR_ERR(root);
break;
}
- ASSERT(root->reloc_root == reloc_root);
+
+ if (unlikely(root->reloc_root != reloc_root)) {
+ if (root->reloc_root) {
+ btrfs_err(fs_info,
+"reloc tree mismatch, root %lld has reloc root key (%lld %u %llu) gen %llu, expect reloc root key (%lld %u %llu) gen %llu",
+ root->root_key.objectid,
+ root->reloc_root->root_key.objectid,
+ root->reloc_root->root_key.type,
+ root->reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &root->reloc_root->root_item),
+ reloc_root->root_key.objectid,
+ reloc_root->root_key.type,
+ reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &reloc_root->root_item));
+ } else {
+ btrfs_err(fs_info,
+"reloc tree mismatch, root %lld has no reloc root, expect reloc root key (%lld %u %llu) gen %llu",
+ root->root_key.objectid,
+ reloc_root->root_key.objectid,
+ reloc_root->root_key.type,
+ reloc_root->root_key.offset,
+ btrfs_root_generation(
+ &reloc_root->root_item));
+ }
+ list_add(&reloc_root->root_list, &reloc_roots);
+ btrfs_put_root(root);
+ btrfs_abort_transaction(trans, -EUCLEAN);
+ if (!err)
+ err = -EUCLEAN;
+ break;
+ }
/*
* set reference count to 1, so btrfs_recover_relocation
@@ -1989,7 +2021,7 @@ again:
root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
false);
if (btrfs_root_refs(&reloc_root->root_item) > 0) {
- if (IS_ERR(root)) {
+ if (WARN_ON(IS_ERR(root))) {
/*
* For recovery we read the fs roots on mount,
* and if we didn't find the root then we marked
@@ -1998,17 +2030,14 @@ again:
* memory. However there's no reason we can't
* handle the error properly here just in case.
*/
- ASSERT(0);
ret = PTR_ERR(root);
goto out;
}
- if (root->reloc_root != reloc_root) {
+ if (WARN_ON(root->reloc_root != reloc_root)) {
/*
- * This is actually impossible without something
- * going really wrong (like weird race condition
- * or cosmic rays).
+ * This can happen if on-disk metadata has some
+ * corruption, e.g. bad reloc tree key offset.
*/
- ASSERT(0);
ret = -EINVAL;
goto out;
}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 038dfa8f1788..ab08a0b01311 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -446,6 +446,20 @@ static int check_root_key(struct extent_buffer *leaf, struct btrfs_key *key,
btrfs_item_key_to_cpu(leaf, &item_key, slot);
is_root_item = (item_key.type == BTRFS_ROOT_ITEM_KEY);
+ /*
+ * Bad rootid for reloc trees.
+ *
+ * Reloc trees are only for subvolume trees, other trees only need
+ * to be COWed to be relocated.
+ */
+ if (unlikely(is_root_item && key->objectid == BTRFS_TREE_RELOC_OBJECTID &&
+ !is_fstree(key->offset))) {
+ generic_err(leaf, slot,
+ "invalid reloc tree for root %lld, root id is not a subvolume tree",
+ key->offset);
+ return -EUCLEAN;
+ }
+
/* No such tree id */
if (unlikely(key->objectid == 0)) {
if (is_root_item)
diff --git a/fs/inode.c b/fs/inode.c
index 8fefb69e1f84..67611a360031 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -16,7 +16,6 @@
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/posix_acl.h>
-#include <linux/prefetch.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include <linux/ratelimit.h>
#include <linux/list_lru.h>
@@ -1041,8 +1040,6 @@ struct inode *new_inode(struct super_block *sb)
{
struct inode *inode;
- spin_lock_prefetch(&sb->s_inode_list_lock);
-
inode = new_inode_pseudo(sb);
if (inode)
inode_sb_list_add(inode);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index a8ce522ac747..35bc79305318 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -1101,9 +1101,17 @@ int nilfs_set_file_dirty(struct inode *inode, unsigned int nr_dirty)
int __nilfs_mark_inode_dirty(struct inode *inode, int flags)
{
+ struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
struct buffer_head *ibh;
int err;
+ /*
+ * Do not dirty inodes after the log writer has been detached
+ * and its nilfs_root struct has been freed.
+ */
+ if (unlikely(nilfs_purging(nilfs)))
+ return 0;
+
err = nilfs_load_inode_block(inode, &ibh);
if (unlikely(err)) {
nilfs_warn(inode->i_sb,
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index c2553024bd25..581691e4be49 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -2845,6 +2845,7 @@ void nilfs_detach_log_writer(struct super_block *sb)
nilfs_segctor_destroy(nilfs->ns_writer);
nilfs->ns_writer = NULL;
}
+ set_nilfs_purging(nilfs);
/* Force to free the list of dirty files */
spin_lock(&nilfs->ns_inode_lock);
@@ -2857,4 +2858,5 @@ void nilfs_detach_log_writer(struct super_block *sb)
up_write(&nilfs->ns_segctor_sem);
nilfs_dispose_list(nilfs, &garbage_list, 1);
+ clear_nilfs_purging(nilfs);
}
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 47c7dfbb7ea5..cd4ae1b8ae16 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -29,6 +29,7 @@ enum {
THE_NILFS_DISCONTINUED, /* 'next' pointer chain has broken */
THE_NILFS_GC_RUNNING, /* gc process is running */
THE_NILFS_SB_DIRTY, /* super block is dirty */
+ THE_NILFS_PURGING, /* disposing dirty files for cleanup */
};
/**
@@ -208,6 +209,7 @@ THE_NILFS_FNS(INIT, init)
THE_NILFS_FNS(DISCONTINUED, discontinued)
THE_NILFS_FNS(GC_RUNNING, gc_running)
THE_NILFS_FNS(SB_DIRTY, sb_dirty)
+THE_NILFS_FNS(PURGING, purging)
/*
* Mount option operations
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 9cb32e1a78a0..23fc24d16b31 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -309,6 +309,8 @@ static void append_kcore_note(char *notes, size_t *i, const char *name,
static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
{
+ struct file *file = iocb->ki_filp;
+ char *buf = file->private_data;
loff_t *fpos = &iocb->ki_pos;
size_t phdrs_offset, notes_offset, data_offset;
size_t page_offline_frozen = 1;
@@ -555,10 +557,21 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
case KCORE_VMEMMAP:
case KCORE_TEXT:
/*
- * We use _copy_to_iter() to bypass usermode hardening
- * which would otherwise prevent this operation.
+ * Sadly we must use a bounce buffer here to be able to
+ * make use of copy_from_kernel_nofault(), as these
+ * memory regions might not always be mapped on all
+ * architectures.
*/
- if (_copy_to_iter((char *)start, tsz, iter) != tsz) {
+ if (copy_from_kernel_nofault(buf, (void *)start, tsz)) {
+ if (iov_iter_zero(tsz, iter) != tsz) {
+ ret = -EFAULT;
+ goto out;
+ }
+ /*
+ * We know the bounce buffer is safe to copy from, so
+ * use _copy_to_iter() directly.
+ */
+ } else if (_copy_to_iter(buf, tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
}
@@ -595,6 +608,10 @@ static int open_kcore(struct inode *inode, struct file *filp)
if (ret)
return ret;
+ filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!filp->private_data)
+ return -ENOMEM;
+
if (kcore_need_update)
kcore_update_ram();
if (i_size_read(inode) != proc_root_kcore->size) {
@@ -605,9 +622,16 @@ static int open_kcore(struct inode *inode, struct file *filp)
return 0;
}
+static int release_kcore(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
+
static const struct proc_ops kcore_proc_ops = {
.proc_read_iter = read_kcore_iter,
.proc_open = open_kcore,
+ .proc_release = release_kcore,
.proc_lseek = default_llseek,
};
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index fb4162a52844..aec6e9137474 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -153,6 +153,11 @@ cifs_dump_channel(struct seq_file *m, int i, struct cifs_chan *chan)
in_flight(server),
atomic_read(&server->in_send),
atomic_read(&server->num_waiters));
+#ifdef CONFIG_NET_NS
+ if (server->net)
+ seq_printf(m, " Net namespace: %u ", server->net->ns.inum);
+#endif /* NET_NS */
+
}
static inline const char *smb_speed_to_str(size_t bps)
@@ -430,10 +435,15 @@ skip_rdma:
server->reconnect_instance,
server->srv_count,
server->sec_mode, in_flight(server));
+#ifdef CONFIG_NET_NS
+ if (server->net)
+ seq_printf(m, " Net namespace: %u ", server->net->ns.inum);
+#endif /* NET_NS */
seq_printf(m, "\nIn Send: %d In MaxReq Wait: %d",
atomic_read(&server->in_send),
atomic_read(&server->num_waiters));
+
if (server->leaf_fullpath) {
seq_printf(m, "\nDFS leaf full path: %s",
server->leaf_fullpath);
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index fc5acc95cd13..6bc44f79d2e9 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -4681,9 +4681,9 @@ static int cifs_readpage_worker(struct file *file, struct page *page,
io_error:
kunmap(page);
- unlock_page(page);
read_complete:
+ unlock_page(page);
return rc;
}
@@ -4878,9 +4878,11 @@ void cifs_oplock_break(struct work_struct *work)
struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
oplock_break);
struct inode *inode = d_inode(cfile->dentry);
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifsInodeInfo *cinode = CIFS_I(inode);
- struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
- struct TCP_Server_Info *server = tcon->ses->server;
+ struct cifs_tcon *tcon;
+ struct TCP_Server_Info *server;
+ struct tcon_link *tlink;
int rc = 0;
bool purge_cache = false, oplock_break_cancelled;
__u64 persistent_fid, volatile_fid;
@@ -4889,6 +4891,12 @@ void cifs_oplock_break(struct work_struct *work)
wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS,
TASK_UNINTERRUPTIBLE);
+ tlink = cifs_sb_tlink(cifs_sb);
+ if (IS_ERR(tlink))
+ goto out;
+ tcon = tlink_tcon(tlink);
+ server = tcon->ses->server;
+
server->ops->downgrade_oplock(server, cinode, cfile->oplock_level,
cfile->oplock_epoch, &purge_cache);
@@ -4938,18 +4946,19 @@ oplock_break_ack:
/*
* MS-SMB2 3.2.5.19.1 and 3.2.5.19.2 (and MS-CIFS 3.2.5.42) do not require
* an acknowledgment to be sent when the file has already been closed.
- * check for server null, since can race with kill_sb calling tree disconnect.
*/
spin_lock(&cinode->open_file_lock);
- if (tcon->ses && tcon->ses->server && !oplock_break_cancelled &&
- !list_empty(&cinode->openFileList)) {
+ /* check list empty since can race with kill_sb calling tree disconnect */
+ if (!oplock_break_cancelled && !list_empty(&cinode->openFileList)) {
spin_unlock(&cinode->open_file_lock);
- rc = tcon->ses->server->ops->oplock_response(tcon, persistent_fid,
- volatile_fid, net_fid, cinode);
+ rc = server->ops->oplock_response(tcon, persistent_fid,
+ volatile_fid, net_fid, cinode);
cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
} else
spin_unlock(&cinode->open_file_lock);
+ cifs_put_tlink(tlink);
+out:
cifs_done_oplock_break(cinode);
}
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index 92c9aaae3663..789cfb74c146 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -341,77 +341,6 @@ static loff_t zonefs_file_llseek(struct file *file, loff_t offset, int whence)
return generic_file_llseek_size(file, offset, whence, isize, isize);
}
-struct zonefs_zone_append_bio {
- /* The target inode of the BIO */
- struct inode *inode;
-
- /* For sync writes, the target append write offset */
- u64 append_offset;
-
- /*
- * This member must come last, bio_alloc_bioset will allocate enough
- * bytes for entire zonefs_bio but relies on bio being last.
- */
- struct bio bio;
-};
-
-static inline struct zonefs_zone_append_bio *
-zonefs_zone_append_bio(struct bio *bio)
-{
- return container_of(bio, struct zonefs_zone_append_bio, bio);
-}
-
-static void zonefs_file_zone_append_dio_bio_end_io(struct bio *bio)
-{
- struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio);
- struct zonefs_zone *z = zonefs_inode_zone(za_bio->inode);
- sector_t za_sector;
-
- if (bio->bi_status != BLK_STS_OK)
- goto bio_end;
-
- /*
- * If the file zone was written underneath the file system, the zone
- * append operation can still succedd (if the zone is not full) but
- * the write append location will not be where we expect it to be.
- * Check that we wrote where we intended to, that is, at z->z_wpoffset.
- */
- za_sector = z->z_sector + (za_bio->append_offset >> SECTOR_SHIFT);
- if (bio->bi_iter.bi_sector != za_sector) {
- zonefs_warn(za_bio->inode->i_sb,
- "Invalid write sector %llu for zone at %llu\n",
- bio->bi_iter.bi_sector, z->z_sector);
- bio->bi_status = BLK_STS_IOERR;
- }
-
-bio_end:
- iomap_dio_bio_end_io(bio);
-}
-
-static void zonefs_file_zone_append_dio_submit_io(const struct iomap_iter *iter,
- struct bio *bio,
- loff_t file_offset)
-{
- struct zonefs_zone_append_bio *za_bio = zonefs_zone_append_bio(bio);
- struct inode *inode = iter->inode;
- struct zonefs_zone *z = zonefs_inode_zone(inode);
-
- /*
- * Issue a zone append BIO to process sync dio writes. The append
- * file offset is saved to check the zone append write location
- * on completion of the BIO.
- */
- za_bio->inode = inode;
- za_bio->append_offset = file_offset;
-
- bio->bi_opf &= ~REQ_OP_WRITE;
- bio->bi_opf |= REQ_OP_ZONE_APPEND;
- bio->bi_iter.bi_sector = z->z_sector;
- bio->bi_end_io = zonefs_file_zone_append_dio_bio_end_io;
-
- submit_bio(bio);
-}
-
static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
int error, unsigned int flags)
{
@@ -442,14 +371,6 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size,
return 0;
}
-static struct bio_set zonefs_zone_append_bio_set;
-
-static const struct iomap_dio_ops zonefs_zone_append_dio_ops = {
- .submit_io = zonefs_file_zone_append_dio_submit_io,
- .end_io = zonefs_file_write_dio_end_io,
- .bio_set = &zonefs_zone_append_bio_set,
-};
-
static const struct iomap_dio_ops zonefs_write_dio_ops = {
.end_io = zonefs_file_write_dio_end_io,
};
@@ -533,9 +454,6 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
struct zonefs_inode_info *zi = ZONEFS_I(inode);
struct zonefs_zone *z = zonefs_inode_zone(inode);
struct super_block *sb = inode->i_sb;
- const struct iomap_dio_ops *dio_ops;
- bool sync = is_sync_kiocb(iocb);
- bool append = false;
ssize_t ret, count;
/*
@@ -543,7 +461,8 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
* as this can cause write reordering (e.g. the first aio gets EAGAIN
* on the inode lock but the second goes through but is now unaligned).
*/
- if (zonefs_zone_is_seq(z) && !sync && (iocb->ki_flags & IOCB_NOWAIT))
+ if (zonefs_zone_is_seq(z) && !is_sync_kiocb(iocb) &&
+ (iocb->ki_flags & IOCB_NOWAIT))
return -EOPNOTSUPP;
if (iocb->ki_flags & IOCB_NOWAIT) {
@@ -573,18 +492,6 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
goto inode_unlock;
}
mutex_unlock(&zi->i_truncate_mutex);
- append = sync;
- }
-
- if (append) {
- unsigned int max = bdev_max_zone_append_sectors(sb->s_bdev);
-
- max = ALIGN_DOWN(max << SECTOR_SHIFT, sb->s_blocksize);
- iov_iter_truncate(from, max);
-
- dio_ops = &zonefs_zone_append_dio_ops;
- } else {
- dio_ops = &zonefs_write_dio_ops;
}
/*
@@ -593,7 +500,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
* the user can make sense of the error.
*/
ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops,
- dio_ops, 0, NULL, 0);
+ &zonefs_write_dio_ops, 0, NULL, 0);
if (ret == -ENOTBLK)
ret = -EBUSY;
@@ -938,15 +845,3 @@ const struct file_operations zonefs_file_operations = {
.splice_write = iter_file_splice_write,
.iopoll = iocb_bio_iopoll,
};
-
-int zonefs_file_bioset_init(void)
-{
- return bioset_init(&zonefs_zone_append_bio_set, BIO_POOL_SIZE,
- offsetof(struct zonefs_zone_append_bio, bio),
- BIOSET_NEED_BVECS);
-}
-
-void zonefs_file_bioset_exit(void)
-{
- bioset_exit(&zonefs_zone_append_bio_set);
-}
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index bbe44a26a8e5..9350221abfc5 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -1412,13 +1412,9 @@ static int __init zonefs_init(void)
BUILD_BUG_ON(sizeof(struct zonefs_super) != ZONEFS_SUPER_SIZE);
- ret = zonefs_file_bioset_init();
- if (ret)
- return ret;
-
ret = zonefs_init_inodecache();
if (ret)
- goto destroy_bioset;
+ return ret;
ret = zonefs_sysfs_init();
if (ret)
@@ -1434,8 +1430,6 @@ sysfs_exit:
zonefs_sysfs_exit();
destroy_inodecache:
zonefs_destroy_inodecache();
-destroy_bioset:
- zonefs_file_bioset_exit();
return ret;
}
@@ -1445,7 +1439,6 @@ static void __exit zonefs_exit(void)
unregister_filesystem(&zonefs_type);
zonefs_sysfs_exit();
zonefs_destroy_inodecache();
- zonefs_file_bioset_exit();
}
MODULE_AUTHOR("Damien Le Moal");
diff --git a/fs/zonefs/zonefs.h b/fs/zonefs/zonefs.h
index f663b8ebc2cb..8175652241b5 100644
--- a/fs/zonefs/zonefs.h
+++ b/fs/zonefs/zonefs.h
@@ -279,8 +279,6 @@ extern const struct file_operations zonefs_dir_operations;
extern const struct address_space_operations zonefs_file_aops;
extern const struct file_operations zonefs_file_operations;
int zonefs_file_truncate(struct inode *inode, loff_t isize);
-int zonefs_file_bioset_init(void);
-void zonefs_file_bioset_exit(void);
/* In sysfs.c */
int zonefs_sysfs_register(struct super_block *sb);