summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/block-group.c20
-rw-r--r--fs/btrfs/discard.h2
-rw-r--r--fs/btrfs/disk-io.c36
-rw-r--r--fs/btrfs/relocation.c1
-rw-r--r--fs/btrfs/transaction.c13
-rw-r--r--fs/btrfs/tree-log.c43
-rw-r--r--fs/cachefiles/rdwr.c12
-rw-r--r--fs/ceph/caps.c3
-rw-r--r--fs/ceph/debugfs.c2
-rw-r--r--fs/ceph/mds_client.c8
-rw-r--r--fs/ceph/quota.c4
-rw-r--r--fs/cifs/cifssmb.c2
-rw-r--r--fs/cifs/file.c2
-rw-r--r--fs/cifs/inode.c2
-rw-r--r--fs/configfs/dir.c1
-rw-r--r--fs/coredump.c8
-rw-r--r--fs/eventpoll.c107
-rw-r--r--fs/gfs2/bmap.c16
-rw-r--r--fs/gfs2/glock.c6
-rw-r--r--fs/gfs2/inode.c7
-rw-r--r--fs/gfs2/log.c11
-rw-r--r--fs/gfs2/lops.c19
-rw-r--r--fs/gfs2/meta_io.c2
-rw-r--r--fs/gfs2/quota.c13
-rw-r--r--fs/gfs2/quota.h3
-rw-r--r--fs/gfs2/super.c1
-rw-r--r--fs/gfs2/util.c10
-rw-r--r--fs/io_uring.c140
-rw-r--r--fs/ioctl.c8
-rw-r--r--fs/iomap/fiemap.c5
-rw-r--r--fs/nfs/fscache.c39
-rw-r--r--fs/nfs/mount_clnt.c3
-rw-r--r--fs/nfs/nfs3acl.c22
-rw-r--r--fs/nfs/nfs4proc.c13
-rw-r--r--fs/nfs/nfs4state.c2
-rw-r--r--fs/nfs/pagelist.c5
-rw-r--r--fs/nfs/pnfs.c11
-rw-r--r--fs/nfs/pnfs_nfs.c3
-rw-r--r--fs/nfs/super.c3
-rw-r--r--fs/nfs/write.c4
-rw-r--r--fs/ocfs2/dlmfs/dlmfs.c27
-rw-r--r--fs/pnode.c9
-rw-r--r--fs/splice.c45
-rw-r--r--fs/super.c2
-rw-r--r--fs/vboxsf/super.c2
46 files changed, 400 insertions, 299 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 9c380e7edf62..0cc02577577b 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -391,7 +391,7 @@ static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr)
struct rb_node **p = &preftrees->direct.root.rb_root.rb_node;
struct rb_node *parent = NULL;
struct prelim_ref *ref = NULL;
- struct prelim_ref target = {0};
+ struct prelim_ref target = {};
int result;
target.parent = bytenr;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 47f66c6a7d7f..696f47103cfc 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -916,7 +916,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
- goto out;
+ goto out_put_group;
}
/*
@@ -954,7 +954,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
ret = btrfs_orphan_add(trans, BTRFS_I(inode));
if (ret) {
btrfs_add_delayed_iput(inode);
- goto out;
+ goto out_put_group;
}
clear_nlink(inode);
/* One for the block groups ref */
@@ -977,13 +977,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
if (ret < 0)
- goto out;
+ goto out_put_group;
if (ret > 0)
btrfs_release_path(path);
if (ret == 0) {
ret = btrfs_del_item(trans, tree_root, path);
if (ret)
- goto out;
+ goto out_put_group;
btrfs_release_path(path);
}
@@ -1102,9 +1102,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
ret = remove_block_group_free_space(trans, block_group);
if (ret)
- goto out;
+ goto out_put_group;
- btrfs_put_block_group(block_group);
+ /* Once for the block groups rbtree */
btrfs_put_block_group(block_group);
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
@@ -1127,6 +1127,10 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
/* once for the tree */
free_extent_map(em);
}
+
+out_put_group:
+ /* Once for the lookup reference */
+ btrfs_put_block_group(block_group);
out:
if (remove_rsv)
btrfs_delayed_refs_rsv_release(fs_info, 1);
@@ -1288,11 +1292,15 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
if (ret)
goto err;
mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+ if (prev_trans)
+ btrfs_put_transaction(prev_trans);
return true;
err:
mutex_unlock(&fs_info->unused_bg_unpin_mutex);
+ if (prev_trans)
+ btrfs_put_transaction(prev_trans);
btrfs_dec_block_group_ro(bg);
return false;
}
diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h
index 21a15776dac4..353228d62f5a 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef BTRFS_DISCARD_H
#define BTRFS_DISCARD_H
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a6cb5cbbdb9f..d10c7be10f3b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2036,9 +2036,6 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
for (i = 0; i < ret; i++)
btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
-
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
- btrfs_free_log_root_tree(NULL, fs_info);
}
static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
@@ -3888,7 +3885,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
spin_unlock(&fs_info->fs_roots_radix_lock);
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
- btrfs_free_log(NULL, root);
+ ASSERT(root->log_root == NULL);
if (root->reloc_root) {
btrfs_put_root(root->reloc_root);
root->reloc_root = NULL;
@@ -4211,6 +4208,36 @@ static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
up_write(&fs_info->cleanup_work_sem);
}
+static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_root *gang[8];
+ u64 root_objectid = 0;
+ int ret;
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ while ((ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)gang, root_objectid,
+ ARRAY_SIZE(gang))) != 0) {
+ int i;
+
+ for (i = 0; i < ret; i++)
+ gang[i] = btrfs_grab_root(gang[i]);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
+ continue;
+ root_objectid = gang[i]->root_key.objectid;
+ btrfs_free_log(NULL, gang[i]);
+ btrfs_put_root(gang[i]);
+ }
+ root_objectid++;
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ }
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ btrfs_free_log_root_tree(NULL, fs_info);
+}
+
static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
{
struct btrfs_ordered_extent *ordered;
@@ -4603,6 +4630,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
btrfs_destroy_delayed_inodes(fs_info);
btrfs_assert_delayed_root_empty(fs_info);
btrfs_destroy_all_delalloc_inodes(fs_info);
+ btrfs_drop_all_logs(fs_info);
mutex_unlock(&fs_info->transaction_kthread_mutex);
return 0;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index d35936c934ab..03bc7134e8cb 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4559,6 +4559,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
if (IS_ERR(fs_root)) {
err = PTR_ERR(fs_root);
list_add_tail(&reloc_root->root_list, &reloc_roots);
+ btrfs_end_transaction(trans);
goto out_unset;
}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 8cede6eb9843..2d5498136e5e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -662,10 +662,19 @@ again:
}
got_it:
- btrfs_record_root_in_trans(h, root);
-
if (!current->journal_info)
current->journal_info = h;
+
+ /*
+ * btrfs_record_root_in_trans() needs to alloc new extents, and may
+ * call btrfs_join_transaction() while we're also starting a
+ * transaction.
+ *
+ * Thus it need to be called after current->journal_info initialized,
+ * or we can deadlock.
+ */
+ btrfs_record_root_in_trans(h, root);
+
return h;
join_fail:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ec36a7c6ba3d..02ebdd9edc19 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4226,6 +4226,9 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
const u64 ino = btrfs_ino(inode);
struct btrfs_path *dst_path = NULL;
bool dropped_extents = false;
+ u64 truncate_offset = i_size;
+ struct extent_buffer *leaf;
+ int slot;
int ins_nr = 0;
int start_slot;
int ret;
@@ -4240,9 +4243,43 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
if (ret < 0)
goto out;
+ /*
+ * We must check if there is a prealloc extent that starts before the
+ * i_size and crosses the i_size boundary. This is to ensure later we
+ * truncate down to the end of that extent and not to the i_size, as
+ * otherwise we end up losing part of the prealloc extent after a log
+ * replay and with an implicit hole if there is another prealloc extent
+ * that starts at an offset beyond i_size.
+ */
+ ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY);
+ if (ret < 0)
+ goto out;
+
+ if (ret == 0) {
+ struct btrfs_file_extent_item *ei;
+
+ leaf = path->nodes[0];
+ slot = path->slots[0];
+ ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+
+ if (btrfs_file_extent_type(leaf, ei) ==
+ BTRFS_FILE_EXTENT_PREALLOC) {
+ u64 extent_end;
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ extent_end = key.offset +
+ btrfs_file_extent_num_bytes(leaf, ei);
+
+ if (extent_end > i_size)
+ truncate_offset = extent_end;
+ }
+ } else {
+ ret = 0;
+ }
+
while (true) {
- struct extent_buffer *leaf = path->nodes[0];
- int slot = path->slots[0];
+ leaf = path->nodes[0];
+ slot = path->slots[0];
if (slot >= btrfs_header_nritems(leaf)) {
if (ins_nr > 0) {
@@ -4280,7 +4317,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
ret = btrfs_truncate_inode_items(trans,
root->log_root,
&inode->vfs_inode,
- i_size,
+ truncate_offset,
BTRFS_EXTENT_DATA_KEY);
} while (ret == -EAGAIN);
if (ret)
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 1dc97f2d6201..e7726f5f1241 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -60,9 +60,9 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
object = container_of(op->op.object, struct cachefiles_object, fscache);
spin_lock(&object->work_lock);
list_add_tail(&monitor->op_link, &op->to_do);
+ fscache_enqueue_retrieval(op);
spin_unlock(&object->work_lock);
- fscache_enqueue_retrieval(op);
fscache_put_retrieval(op);
return 0;
}
@@ -398,7 +398,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
struct inode *inode;
sector_t block;
unsigned shift;
- int ret;
+ int ret, ret2;
object = container_of(op->op.object,
struct cachefiles_object, fscache);
@@ -430,8 +430,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
block = page->index;
block <<= shift;
- ret = bmap(inode, &block);
- ASSERT(ret < 0);
+ ret2 = bmap(inode, &block);
+ ASSERT(ret2 == 0);
_debug("%llx -> %llx",
(unsigned long long) (page->index << shift),
@@ -739,8 +739,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
block = page->index;
block <<= shift;
- ret = bmap(inode, &block);
- ASSERT(!ret);
+ ret2 = bmap(inode, &block);
+ ASSERT(ret2 == 0);
_debug("%llx -> %llx",
(unsigned long long) (page->index << shift),
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 185db76300b3..5f3aa4d607de 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2749,7 +2749,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want,
ret = try_get_cap_refs(inode, need, want, 0, flags, got);
/* three special error codes */
- if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN)
+ if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE)
ret = 0;
return ret;
}
@@ -3746,6 +3746,7 @@ retry:
WARN_ON(1);
tsession = NULL;
target = -1;
+ mutex_lock(&session->s_mutex);
}
goto retry;
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 481ac97b4d25..dcaed75de9e6 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -271,7 +271,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
&congestion_kb_fops);
snprintf(name, sizeof(name), "../../bdi/%s",
- dev_name(fsc->sb->s_bdi->dev));
+ bdi_dev_name(fsc->sb->s_bdi));
fsc->debugfs_bdi =
debugfs_create_symlink("bdi",
fsc->client->debugfs_dir,
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 486f91f9685b..7c63abf5bea9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -3251,8 +3251,7 @@ static void handle_session(struct ceph_mds_session *session,
void *end = p + msg->front.iov_len;
struct ceph_mds_session_head *h;
u32 op;
- u64 seq;
- unsigned long features = 0;
+ u64 seq, features = 0;
int wake = 0;
bool blacklisted = false;
@@ -3271,9 +3270,8 @@ static void handle_session(struct ceph_mds_session *session,
goto bad;
/* version >= 3, feature bits */
ceph_decode_32_safe(&p, end, len, bad);
- ceph_decode_need(&p, end, len, bad);
- memcpy(&features, p, min_t(size_t, len, sizeof(features)));
- p += len;
+ ceph_decode_64_safe(&p, end, features, bad);
+ p += len - sizeof(features);
}
mutex_lock(&mdsc->mutex);
diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c
index de56dee60540..19507e2fdb57 100644
--- a/fs/ceph/quota.c
+++ b/fs/ceph/quota.c
@@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc,
}
if (IS_ERR(in)) {
- pr_warn("Can't lookup inode %llx (err: %ld)\n",
- realm->ino, PTR_ERR(in));
+ dout("Can't lookup inode %llx (err: %ld)\n",
+ realm->ino, PTR_ERR(in));
qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */
} else {
qri->timeout = 0;
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 182b864b3075..5014a82391ff 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2152,8 +2152,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
}
}
+ kref_put(&wdata2->refcount, cifs_writedata_release);
if (rc) {
- kref_put(&wdata2->refcount, cifs_writedata_release);
if (is_retryable_error(rc))
continue;
i += nr_pages;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0b1528edebcf..75ddce8ef456 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4060,7 +4060,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
* than it negotiated since it will refuse the read
* then.
*/
- if ((tcon->ses) && !(tcon->ses->capabilities &
+ if (!(tcon->ses->capabilities &
tcon->ses->server->vals->cap_large_files)) {
current_read_size = min_t(uint,
current_read_size, CIFSMaxBufSize);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 390d2b15ef6e..5d2965a23730 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -730,7 +730,7 @@ static __u64 simple_hashstr(const char *str)
* cifs_backup_query_path_info - SMB1 fallback code to get ino
*
* Fallback code to get file metadata when we don't have access to
- * @full_path (EACCESS) and have backup creds.
+ * @full_path (EACCES) and have backup creds.
*
* @data will be set to search info result buffer
* @resp_buf will be set to cifs resp buf and needs to be freed with
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index cf7b7e1d5bd7..cb733652ecca 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1519,6 +1519,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
spin_lock(&configfs_dirent_lock);
configfs_detach_rollback(dentry);
spin_unlock(&configfs_dirent_lock);
+ config_item_put(parent_item);
return -EINTR;
}
frag->frag_dead = true;
diff --git a/fs/coredump.c b/fs/coredump.c
index 408418e6aa13..478a0d810136 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -788,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo)
if (displaced)
put_files_struct(displaced);
if (!dump_interrupted()) {
+ /*
+ * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would
+ * have this set to NULL.
+ */
+ if (!cprm.file) {
+ pr_info("Core dump to |%s disabled\n", cn.corename);
+ goto close_fail;
+ }
file_start_write(cprm.file);
core_dumped = binfmt->core_dump(&cprm);
file_end_write(cprm.file);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 8c596641a72b..12eebcdea9c8 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1171,6 +1171,10 @@ static inline bool chain_epi_lockless(struct epitem *epi)
{
struct eventpoll *ep = epi->ep;
+ /* Fast preliminary check */
+ if (epi->next != EP_UNACTIVE_PTR)
+ return false;
+
/* Check that the same epi has not been just chained from another CPU */
if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR)
return false;
@@ -1237,16 +1241,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v
* chained in ep->ovflist and requeued later on.
*/
if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) {
- if (epi->next == EP_UNACTIVE_PTR &&
- chain_epi_lockless(epi))
+ if (chain_epi_lockless(epi))
+ ep_pm_stay_awake_rcu(epi);
+ } else if (!ep_is_linked(epi)) {
+ /* In the usual case, add event to ready list. */
+ if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist))
ep_pm_stay_awake_rcu(epi);
- goto out_unlock;
- }
-
- /* If this file is already in the ready list we exit soon */
- if (!ep_is_linked(epi) &&
- list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) {
- ep_pm_stay_awake_rcu(epi);
}
/*
@@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
{
int res = 0, eavail, timed_out = 0;
u64 slack = 0;
- bool waiter = false;
wait_queue_entry_t wait;
ktime_t expires, *to = NULL;
@@ -1867,55 +1866,75 @@ fetch_events:
*/
ep_reset_busy_poll_napi_id(ep);
- /*
- * We don't have any available event to return to the caller. We need
- * to sleep here, and we will be woken by ep_poll_callback() when events
- * become available.
- */
- if (!waiter) {
- waiter = true;
- init_waitqueue_entry(&wait, current);
+ do {
+ /*
+ * Internally init_wait() uses autoremove_wake_function(),
+ * thus wait entry is removed from the wait queue on each
+ * wakeup. Why it is important? In case of several waiters
+ * each new wakeup will hit the next waiter, giving it the
+ * chance to harvest new event. Otherwise wakeup can be
+ * lost. This is also good performance-wise, because on
+ * normal wakeup path no need to call __remove_wait_queue()
+ * explicitly, thus ep->lock is not taken, which halts the
+ * event delivery.
+ */
+ init_wait(&wait);
write_lock_irq(&ep->lock);
- __add_wait_queue_exclusive(&ep->wq, &wait);
- write_unlock_irq(&ep->lock);
- }
-
- for (;;) {
/*
- * We don't want to sleep if the ep_poll_callback() sends us
- * a wakeup in between. That's why we set the task state
- * to TASK_INTERRUPTIBLE before doing the checks.
+ * Barrierless variant, waitqueue_active() is called under
+ * the same lock on wakeup ep_poll_callback() side, so it
+ * is safe to avoid an explicit barrier.
*/
- set_current_state(TASK_INTERRUPTIBLE);
+ __set_current_state(TASK_INTERRUPTIBLE);
+
/*
- * Always short-circuit for fatal signals to allow
- * threads to make a timely exit without the chance of
- * finding more events available and fetching
- * repeatedly.
+ * Do the final check under the lock. ep_scan_ready_list()
+ * plays with two lists (->rdllist and ->ovflist) and there
+ * is always a race when both lists are empty for short
+ * period of time although events are pending, so lock is
+ * important.
*/
- if (fatal_signal_pending(current)) {
- res = -EINTR;
- break;
+ eavail = ep_events_available(ep);
+ if (!eavail) {
+ if (signal_pending(current))
+ res = -EINTR;
+ else
+ __add_wait_queue_exclusive(&ep->wq, &wait);
}
+ write_unlock_irq(&ep->lock);
- eavail = ep_events_available(ep);
- if (eavail)
+ if (eavail || res)
break;
- if (signal_pending(current)) {
- res = -EINTR;
- break;
- }
if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) {
timed_out = 1;
break;
}
- }
+
+ /* We were woken up, thus go and try to harvest some events */
+ eavail = 1;
+
+ } while (0);
__set_current_state(TASK_RUNNING);
+ if (!list_empty_careful(&wait.entry)) {
+ write_lock_irq(&ep->lock);
+ __remove_wait_queue(&ep->wq, &wait);
+ write_unlock_irq(&ep->lock);
+ }
+
send_events:
+ if (fatal_signal_pending(current)) {
+ /*
+ * Always short-circuit for fatal signals to allow
+ * threads to make a timely exit without the chance of
+ * finding more events available and fetching
+ * repeatedly.
+ */
+ res = -EINTR;
+ }
/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
@@ -1925,12 +1944,6 @@ send_events:
!(res = ep_send_events(ep, events, maxevents)) && !timed_out)
goto fetch_events;
- if (waiter) {
- write_lock_irq(&ep->lock);
- __remove_wait_queue(&ep->wq, &wait);
- write_unlock_irq(&ep->lock);
- }
-
return res;
}
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 936a8ec6b48e..6306eaae378b 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -528,10 +528,12 @@ lower_metapath:
/* Advance in metadata tree. */
(mp->mp_list[hgt])++;
- if (mp->mp_list[hgt] >= sdp->sd_inptrs) {
- if (!hgt)
+ if (hgt) {
+ if (mp->mp_list[hgt] >= sdp->sd_inptrs)
+ goto lower_metapath;
+ } else {
+ if (mp->mp_list[hgt] >= sdp->sd_diptrs)
break;
- goto lower_metapath;
}
fill_up_metapath:
@@ -876,10 +878,9 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
ret = -ENOENT;
goto unlock;
} else {
- /* report a hole */
iomap->offset = pos;
iomap->length = length;
- goto do_alloc;
+ goto hole_found;
}
}
iomap->length = size;
@@ -933,8 +934,6 @@ unlock:
return ret;
do_alloc:
- iomap->addr = IOMAP_NULL_ADDR;
- iomap->type = IOMAP_HOLE;
if (flags & IOMAP_REPORT) {
if (pos >= size)
ret = -ENOENT;
@@ -956,6 +955,9 @@ do_alloc:
if (pos < size && height == ip->i_height)
ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
}
+hole_found:
+ iomap->addr = IOMAP_NULL_ADDR;
+ iomap->type = IOMAP_HOLE;
goto out;
}
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 29f9b6684b74..bf70e3b14938 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -613,7 +613,7 @@ __acquires(&gl->gl_lockref.lock)
fs_err(sdp, "Error %d syncing glock \n", ret);
gfs2_dump_glock(NULL, gl, true);
}
- return;
+ goto skip_inval;
}
}
if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) {
@@ -633,6 +633,7 @@ __acquires(&gl->gl_lockref.lock)
clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
}
+skip_inval:
gfs2_glock_hold(gl);
/*
* Check for an error encountered since we called go_sync and go_inval.
@@ -722,9 +723,6 @@ __acquires(&gl->gl_lockref.lock)
goto out_unlock;
if (nonblock)
goto out_sched;
- smp_mb();
- if (atomic_read(&gl->gl_revokes) != 0)
- goto out_sched;
set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags);
GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE);
gl->gl_target = gl->gl_demote_state;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 70b2d3a1e866..5acd3ce30759 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -622,7 +622,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
error = finish_no_open(file, NULL);
}
gfs2_glock_dq_uninit(ghs);
- return error;
+ goto fail;
} else if (error != -ENOENT) {
goto fail_gunlock;
}
@@ -764,9 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
error = finish_open(file, dentry, gfs2_open_common);
}
gfs2_glock_dq_uninit(ghs);
+ gfs2_qa_put(ip);
gfs2_glock_dq_uninit(ghs + 1);
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
gfs2_glock_put(io_gl);
+ gfs2_qa_put(dip);
return error;
fail_gunlock3:
@@ -776,7 +778,6 @@ fail_gunlock2:
clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
gfs2_glock_put(io_gl);
fail_free_inode:
- gfs2_qa_put(ip);
if (ip->i_gl) {
glock_clear_object(ip->i_gl, ip);
gfs2_glock_put(ip->i_gl);
@@ -1005,7 +1006,7 @@ out_gunlock:
out_child:
gfs2_glock_dq(ghs);
out_parent:
- gfs2_qa_put(ip);
+ gfs2_qa_put(dip);
gfs2_holder_uninit(ghs);
gfs2_holder_uninit(ghs + 1);
return error;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 3a75843ae580..0644e58c6191 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -669,13 +669,13 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
struct buffer_head *bh = bd->bd_bh;
struct gfs2_glock *gl = bd->bd_gl;
+ sdp->sd_log_num_revoke++;
+ if (atomic_inc_return(&gl->gl_revokes) == 1)
+ gfs2_glock_hold(gl);
bh->b_private = NULL;
bd->bd_blkno = bh->b_blocknr;
gfs2_remove_from_ail(bd); /* drops ref on bh */
bd->bd_bh = NULL;
- sdp->sd_log_num_revoke++;
- if (atomic_inc_return(&gl->gl_revokes) == 1)
- gfs2_glock_hold(gl);
set_bit(GLF_LFLUSH, &gl->gl_flags);
list_add(&bd->bd_list, &sdp->sd_log_revokes);
}
@@ -1131,6 +1131,10 @@ int gfs2_logd(void *data)
while (!kthread_should_stop()) {
+ if (gfs2_withdrawn(sdp)) {
+ msleep_interruptible(HZ);
+ continue;
+ }
/* Check for errors writing to the journal */
if (sdp->sd_log_error) {
gfs2_lm(sdp,
@@ -1139,6 +1143,7 @@ int gfs2_logd(void *data)
"prevent further damage.\n",
sdp->sd_fsname, sdp->sd_log_error);
gfs2_withdraw(sdp);
+ continue;
}
did_flush = false;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 5ea96757afc4..48b54ec1c793 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -263,7 +263,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno,
struct super_block *sb = sdp->sd_vfs;
struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
- bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9);
+ bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift;
bio_set_dev(bio, sb->s_bdev);
bio->bi_end_io = end_io;
bio->bi_private = sdp;
@@ -509,7 +509,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
unsigned int bsize = sdp->sd_sb.sb_bsize, off;
unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift;
unsigned int shift = PAGE_SHIFT - bsize_shift;
- unsigned int readahead_blocks = BIO_MAX_PAGES << shift;
+ unsigned int max_bio_size = 2 * 1024 * 1024;
struct gfs2_journal_extent *je;
int sz, ret = 0;
struct bio *bio = NULL;
@@ -537,12 +537,17 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head,
off = 0;
}
- if (!bio || (bio_chained && !off)) {
+ if (!bio || (bio_chained && !off) ||
+ bio->bi_iter.bi_size >= max_bio_size) {
/* start new bio */
} else {
- sz = bio_add_page(bio, page, bsize, off);
- if (sz == bsize)
- goto block_added;
+ sector_t sector = dblock << sdp->sd_fsb2bb_shift;
+
+ if (bio_end_sector(bio) == sector) {
+ sz = bio_add_page(bio, page, bsize, off);
+ if (sz == bsize)
+ goto block_added;
+ }
if (off) {
unsigned int blocks =
(PAGE_SIZE - off) >> bsize_shift;
@@ -568,7 +573,7 @@ block_added:
off += bsize;
if (off == PAGE_SIZE)
page = NULL;
- if (blocks_submitted < blocks_read + readahead_blocks) {
+ if (blocks_submitted < 2 * max_bio_size >> bsize_shift) {
/* Keep at least one bio in flight */
continue;
}
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 4b72abcf83b2..9856cc2e0795 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -252,7 +252,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
int num = 0;
if (unlikely(gfs2_withdrawn(sdp)) &&
- (!sdp->sd_jdesc || (blkno != sdp->sd_jdesc->jd_no_addr))) {
+ (!sdp->sd_jdesc || gl != sdp->sd_jinode_gl)) {
*bhp = NULL;
return -EIO;
}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index cc0c4b5800be..8259fef3f986 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1051,8 +1051,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
u32 x;
int error = 0;
- if (capable(CAP_SYS_RESOURCE) ||
- sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
+ if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
return 0;
error = gfs2_quota_hold(ip, uid, gid);
@@ -1125,7 +1124,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
int found;
if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
- goto out;
+ return;
for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
struct gfs2_quota_data *qd;
@@ -1162,7 +1161,6 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
qd_unlock(qda[x]);
}
-out:
gfs2_quota_unhold(ip);
}
@@ -1210,9 +1208,6 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid,
if (!test_bit(GIF_QD_LOCKED, &ip->i_flags))
return 0;
- if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
- return 0;
-
for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
qd = ip->i_qadata->qa_qd[x];
@@ -1270,7 +1265,9 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
if (ip->i_diskflags & GFS2_DIF_SYSTEM)
return;
- BUG_ON(ip->i_qadata->qa_ref <= 0);
+ if (gfs2_assert_withdraw(sdp, ip->i_qadata &&
+ ip->i_qadata->qa_ref > 0))
+ return;
for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
qd = ip->i_qadata->qa_qd[x];
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 7f9ca8ef40fc..21ada332d555 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -44,7 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip,
int ret;
ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
- if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+ if (capable(CAP_SYS_RESOURCE) ||
+ sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
if (ret)
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 37fc41632aa2..956fced0a8ec 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1404,7 +1404,6 @@ out:
if (ip->i_qadata)
gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0);
gfs2_rs_delete(ip, NULL);
- gfs2_qa_put(ip);
gfs2_ordered_del_inode(ip);
clear_inode(inode);
gfs2_dir_hash_inval(ip);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 9b64d40ab379..aa087a5675af 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -119,6 +119,12 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
if (!sb_rdonly(sdp->sd_vfs))
ret = gfs2_make_fs_ro(sdp);
+ if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
+ if (!ret)
+ ret = -EIO;
+ clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
+ goto skip_recovery;
+ }
/*
* Drop the glock for our journal so another node can recover it.
*/
@@ -159,10 +165,6 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
wait_on_bit(&gl->gl_flags, GLF_FREEING, TASK_UNINTERRUPTIBLE);
}
- if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
- clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
- goto skip_recovery;
- }
/*
* Dequeue the "live" glock, but keep a reference so it's never freed.
*/
diff --git a/fs/io_uring.c b/fs/io_uring.c
index c687f57fb651..70ae7e840c85 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -524,6 +524,7 @@ enum {
REQ_F_OVERFLOW_BIT,
REQ_F_POLLED_BIT,
REQ_F_BUFFER_SELECTED_BIT,
+ REQ_F_NO_FILE_TABLE_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
@@ -577,6 +578,8 @@ enum {
REQ_F_POLLED = BIT(REQ_F_POLLED_BIT),
/* buffer already selected */
REQ_F_BUFFER_SELECTED = BIT(REQ_F_BUFFER_SELECTED_BIT),
+ /* doesn't need file table for this request */
+ REQ_F_NO_FILE_TABLE = BIT(REQ_F_NO_FILE_TABLE_BIT),
};
struct async_poll {
@@ -677,8 +680,6 @@ struct io_op_def {
unsigned needs_mm : 1;
/* needs req->file assigned */
unsigned needs_file : 1;
- /* needs req->file assigned IFF fd is >= 0 */
- unsigned fd_non_neg : 1;
/* hash wq insertion if file is a regular file */
unsigned hash_reg_file : 1;
/* unbound wq insertion if file is a non-regular file */
@@ -781,8 +782,6 @@ static const struct io_op_def io_op_defs[] = {
.needs_file = 1,
},
[IORING_OP_OPENAT] = {
- .needs_file = 1,
- .fd_non_neg = 1,
.file_table = 1,
.needs_fs = 1,
},
@@ -796,9 +795,8 @@ static const struct io_op_def io_op_defs[] = {
},
[IORING_OP_STATX] = {
.needs_mm = 1,
- .needs_file = 1,
- .fd_non_neg = 1,
.needs_fs = 1,
+ .file_table = 1,
},
[IORING_OP_READ] = {
.needs_mm = 1,
@@ -833,8 +831,6 @@ static const struct io_op_def io_op_defs[] = {
.buffer_select = 1,
},
[IORING_OP_OPENAT2] = {
- .needs_file = 1,
- .fd_non_neg = 1,
.file_table = 1,
.needs_fs = 1,
},
@@ -1291,7 +1287,7 @@ static struct io_kiocb *io_get_fallback_req(struct io_ring_ctx *ctx)
struct io_kiocb *req;
req = ctx->fallback_req;
- if (!test_and_set_bit_lock(0, (unsigned long *) ctx->fallback_req))
+ if (!test_and_set_bit_lock(0, (unsigned long *) &ctx->fallback_req))
return req;
return NULL;
@@ -1378,7 +1374,7 @@ static void __io_free_req(struct io_kiocb *req)
if (likely(!io_is_fallback_req(req)))
kmem_cache_free(req_cachep, req);
else
- clear_bit_unlock(0, (unsigned long *) req->ctx->fallback_req);
+ clear_bit_unlock(0, (unsigned long *) &req->ctx->fallback_req);
}
struct req_batch {
@@ -1398,10 +1394,6 @@ static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
for (i = 0; i < rb->to_free; i++) {
struct io_kiocb *req = rb->reqs[i];
- if (req->flags & REQ_F_FIXED_FILE) {
- req->file = NULL;
- percpu_ref_put(req->fixed_file_refs);
- }
if (req->flags & REQ_F_INFLIGHT)
inflight++;
__io_req_aux_free(req);
@@ -1674,7 +1666,7 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req))
return false;
- if (!(req->flags & REQ_F_FIXED_FILE) || req->io)
+ if (req->file || req->io)
rb->need_iter++;
rb->reqs[rb->to_free++] = req;
@@ -2034,7 +2026,7 @@ static struct file *__io_file_get(struct io_submit_state *state, int fd)
* any file. For now, just ensure that anything potentially problematic is done
* inline.
*/
-static bool io_file_supports_async(struct file *file)
+static bool io_file_supports_async(struct file *file, int rw)
{
umode_t mode = file_inode(file)->i_mode;
@@ -2043,7 +2035,13 @@ static bool io_file_supports_async(struct file *file)
if (S_ISREG(mode) && file->f_op != &io_uring_fops)
return true;
- return false;
+ if (!(file->f_mode & FMODE_NOWAIT))
+ return false;
+
+ if (rw == READ)
+ return file->f_op->read_iter != NULL;
+
+ return file->f_op->write_iter != NULL;
}
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
@@ -2571,7 +2569,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock)
* If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
* we know to async punt it even if it was opened O_NONBLOCK
*/
- if (force_nonblock && !io_file_supports_async(req->file))
+ if (force_nonblock && !io_file_supports_async(req->file, READ))
goto copy_iov;
iov_count = iov_iter_count(&iter);
@@ -2594,7 +2592,8 @@ copy_iov:
if (ret)
goto out_free;
/* any defer here is final, must blocking retry */
- if (!(req->flags & REQ_F_NOWAIT))
+ if (!(req->flags & REQ_F_NOWAIT) &&
+ !file_can_poll(req->file))
req->flags |= REQ_F_MUST_PUNT;
return -EAGAIN;
}
@@ -2662,7 +2661,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock)
* If the file doesn't support async, mark it as REQ_F_MUST_PUNT so
* we know to async punt it even if it was opened O_NONBLOCK
*/
- if (force_nonblock && !io_file_supports_async(req->file))
+ if (force_nonblock && !io_file_supports_async(req->file, WRITE))
goto copy_iov;
/* file path doesn't support NOWAIT for non-direct_IO */
@@ -2716,7 +2715,8 @@ copy_iov:
if (ret)
goto out_free;
/* any defer here is final, must blocking retry */
- req->flags |= REQ_F_MUST_PUNT;
+ if (!file_can_poll(req->file))
+ req->flags |= REQ_F_MUST_PUNT;
return -EAGAIN;
}
}
@@ -2756,15 +2756,6 @@ static int io_splice_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
return 0;
}
-static bool io_splice_punt(struct file *file)
-{
- if (get_pipe_info(file))
- return false;
- if (!io_file_supports_async(file))
- return true;
- return !(file->f_flags & O_NONBLOCK);
-}
-
static int io_splice(struct io_kiocb *req, bool force_nonblock)
{
struct io_splice *sp = &req->splice;
@@ -2772,19 +2763,19 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock)
struct file *out = sp->file_out;
unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED;
loff_t *poff_in, *poff_out;
- long ret;
+ long ret = 0;
- if (force_nonblock) {
- if (io_splice_punt(in) || io_splice_punt(out))
- return -EAGAIN;
- flags |= SPLICE_F_NONBLOCK;
- }
+ if (force_nonblock)
+ return -EAGAIN;
poff_in = (sp->off_in == -1) ? NULL : &sp->off_in;
poff_out = (sp->off_out == -1) ? NULL : &sp->off_out;
- ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
- if (force_nonblock && ret == -EAGAIN)
- return -EAGAIN;
+
+ if (sp->len) {
+ ret = do_splice(in, poff_in, out, poff_out, sp->len, flags);
+ if (force_nonblock && ret == -EAGAIN)
+ return -EAGAIN;
+ }
io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED));
req->flags &= ~REQ_F_NEED_CLEANUP;
@@ -3355,8 +3346,12 @@ static int io_statx(struct io_kiocb *req, bool force_nonblock)
struct kstat stat;
int ret;
- if (force_nonblock)
+ if (force_nonblock) {
+ /* only need file table for an actual valid fd */
+ if (ctx->dfd == -1 || ctx->dfd == AT_FDCWD)
+ req->flags |= REQ_F_NO_FILE_TABLE;
return -EAGAIN;
+ }
if (vfs_stat_set_lookup_flags(&lookup_flags, ctx->how.flags))
return -EINVAL;
@@ -3502,7 +3497,7 @@ static void io_sync_file_range_finish(struct io_wq_work **workptr)
if (io_req_cancelled(req))
return;
__io_sync_file_range(req);
- io_put_req(req); /* put submission ref */
+ io_steal_work(req, workptr);
}
static int io_sync_file_range(struct io_kiocb *req, bool force_nonblock)
@@ -5015,7 +5010,7 @@ static int io_req_defer(struct io_kiocb *req, const struct io_uring_sqe *sqe)
int ret;
/* Still need defer if there is pending req in defer list. */
- if (!req_need_defer(req) && list_empty(&ctx->defer_list))
+ if (!req_need_defer(req) && list_empty_careful(&ctx->defer_list))
return 0;
if (!req->io && io_alloc_async_ctx(req))
@@ -5364,15 +5359,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr)
io_steal_work(req, workptr);
}
-static int io_req_needs_file(struct io_kiocb *req, int fd)
-{
- if (!io_op_defs[req->opcode].needs_file)
- return 0;
- if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg)
- return 0;
- return 1;
-}
-
static inline struct file *io_file_from_index(struct io_ring_ctx *ctx,
int index)
{
@@ -5410,14 +5396,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req,
}
static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req,
- int fd, unsigned int flags)
+ int fd)
{
bool fixed;
- if (!io_req_needs_file(req, fd))
- return 0;
-
- fixed = (flags & IOSQE_FIXED_FILE);
+ fixed = (req->flags & REQ_F_FIXED_FILE) != 0;
if (unlikely(!fixed && req->needs_fixed_file))
return -EBADF;
@@ -5429,7 +5412,7 @@ static int io_grab_files(struct io_kiocb *req)
int ret = -EBADF;
struct io_ring_ctx *ctx = req->ctx;
- if (req->work.files)
+ if (req->work.files || (req->flags & REQ_F_NO_FILE_TABLE))
return 0;
if (!ctx->ring_file)
return -EBADF;
@@ -5794,7 +5777,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
struct io_submit_state *state, bool async)
{
unsigned int sqe_flags;
- int id, fd;
+ int id;
/*
* All io need record the previous position, if LINK vs DARIN,
@@ -5846,8 +5829,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
IOSQE_ASYNC | IOSQE_FIXED_FILE |
IOSQE_BUFFER_SELECT | IOSQE_IO_LINK);
- fd = READ_ONCE(sqe->fd);
- return io_req_set_file(state, req, fd, sqe_flags);
+ if (!io_op_defs[req->opcode].needs_file)
+ return 0;
+
+ return io_req_set_file(state, req, READ_ONCE(sqe->fd));
}
static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
@@ -7327,7 +7312,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
* it could cause shutdown to hang.
*/
while (ctx->sqo_thread && !wq_has_sleeper(&ctx->sqo_wait))
- cpu_relax();
+ cond_resched();
io_kill_timeouts(ctx);
io_poll_remove_all(ctx);
@@ -7356,11 +7341,9 @@ static int io_uring_release(struct inode *inode, struct file *file)
static void io_uring_cancel_files(struct io_ring_ctx *ctx,
struct files_struct *files)
{
- struct io_kiocb *req;
- DEFINE_WAIT(wait);
-
while (!list_empty_careful(&ctx->inflight_list)) {
- struct io_kiocb *cancel_req = NULL;
+ struct io_kiocb *cancel_req = NULL, *req;
+ DEFINE_WAIT(wait);
spin_lock_irq(&ctx->inflight_lock);
list_for_each_entry(req, &ctx->inflight_list, inflight_entry) {
@@ -7400,6 +7383,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
*/
if (refcount_sub_and_test(2, &cancel_req->refs)) {
io_put_req(cancel_req);
+ finish_wait(&ctx->inflight_wait, &wait);
continue;
}
}
@@ -7407,8 +7391,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx,
io_wq_cancel_work(ctx->io_wq, &cancel_req->work);
io_put_req(cancel_req);
schedule();
+ finish_wait(&ctx->inflight_wait, &wait);
}
- finish_wait(&ctx->inflight_wait, &wait);
}
static int io_uring_flush(struct file *file, void *data)
@@ -7757,7 +7741,8 @@ err:
return ret;
}
-static int io_uring_create(unsigned entries, struct io_uring_params *p)
+static int io_uring_create(unsigned entries, struct io_uring_params *p,
+ struct io_uring_params __user *params)
{
struct user_struct *user = NULL;
struct io_ring_ctx *ctx;
@@ -7849,6 +7834,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
p->cq_off.cqes = offsetof(struct io_rings, cqes);
+ p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
+ IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
+ IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
+
+ if (copy_to_user(params, p, sizeof(*p))) {
+ ret = -EFAULT;
+ goto err;
+ }
/*
* Install ring fd as the very last thing, so we don't risk someone
* having closed it before we finish setup
@@ -7857,9 +7850,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
if (ret < 0)
goto err;
- p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP |
- IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS |
- IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL;
trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags);
return ret;
err:
@@ -7875,7 +7865,6 @@ err:
static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
{
struct io_uring_params p;
- long ret;
int i;
if (copy_from_user(&p, params, sizeof(p)))
@@ -7890,14 +7879,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ))
return -EINVAL;
- ret = io_uring_create(entries, &p);
- if (ret < 0)
- return ret;
-
- if (copy_to_user(params, &p, sizeof(p)))
- return -EFAULT;
-
- return ret;
+ return io_uring_create(entries, &p, params);
}
SYSCALL_DEFINE2(io_uring_setup, u32, entries,
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 282d45be6f45..5e80b40bc1b5 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -55,6 +55,7 @@ EXPORT_SYMBOL(vfs_ioctl);
static int ioctl_fibmap(struct file *filp, int __user *p)
{
struct inode *inode = file_inode(filp);
+ struct super_block *sb = inode->i_sb;
int error, ur_block;
sector_t block;
@@ -71,6 +72,13 @@ static int ioctl_fibmap(struct file *filp, int __user *p)
block = ur_block;
error = bmap(inode, &block);
+ if (block > INT_MAX) {
+ error = -ERANGE;
+ pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n",
+ current->comm, task_pid_nr(current),
+ sb->s_id, filp);
+ }
+
if (error)
ur_block = 0;
else
diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c
index bccf305ea9ce..d55e8f491a5e 100644
--- a/fs/iomap/fiemap.c
+++ b/fs/iomap/fiemap.c
@@ -117,10 +117,7 @@ iomap_bmap_actor(struct inode *inode, loff_t pos, loff_t length,
if (iomap->type == IOMAP_MAPPED) {
addr = (pos - iomap->offset + iomap->addr) >> inode->i_blkbits;
- if (addr > INT_MAX)
- WARN(1, "would truncate bmap result\n");
- else
- *bno = addr;
+ *bno = addr;
}
return 0;
}
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 1abf126c2df4..a60df88efc40 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -118,8 +118,6 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
nfss->fscache_key = NULL;
nfss->fscache = NULL;
- if (!(nfss->options & NFS_OPTION_FSCACHE))
- return;
if (!uniq) {
uniq = "";
ulen = 1;
@@ -188,7 +186,8 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int
/* create a cache index for looking up filehandles */
nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
&nfs_fscache_super_index_def,
- key, sizeof(*key) + ulen,
+ &key->key,
+ sizeof(key->key) + ulen,
NULL, 0,
nfss, 0, true);
dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
@@ -226,6 +225,19 @@ void nfs_fscache_release_super_cookie(struct super_block *sb)
}
}
+static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata,
+ struct nfs_inode *nfsi)
+{
+ memset(auxdata, 0, sizeof(*auxdata));
+ auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
+ auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
+ auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
+ auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+
+ if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+ auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+}
+
/*
* Initialise the per-inode cache cookie pointer for an NFS inode.
*/
@@ -239,14 +251,7 @@ void nfs_fscache_init_inode(struct inode *inode)
if (!(nfss->fscache && S_ISREG(inode->i_mode)))
return;
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
- auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
- auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
- auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
-
- if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
- auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode);
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache,
&nfs_fscache_inode_object_def,
@@ -266,11 +271,7 @@ void nfs_fscache_clear_inode(struct inode *inode)
dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie);
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
- auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
- auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
- auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
fscache_relinquish_cookie(cookie, &auxdata, false);
nfsi->fscache = NULL;
}
@@ -310,11 +311,7 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp)
if (!fscache_cookie_valid(cookie))
return;
- memset(&auxdata, 0, sizeof(auxdata));
- auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec;
- auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec;
- auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec;
- auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec;
+ nfs_fscache_update_auxdata(&auxdata, nfsi);
if (inode_is_open_for_write(inode)) {
dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi);
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 35c8cb2d7637..dda5c3e65d8d 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -30,6 +30,7 @@
#define encode_dirpath_sz (1 + XDR_QUADLEN(MNTPATHLEN))
#define MNT_status_sz (1)
#define MNT_fhandle_sz XDR_QUADLEN(NFS2_FHSIZE)
+#define MNT_fhandlev3_sz XDR_QUADLEN(NFS3_FHSIZE)
#define MNT_authflav3_sz (1 + NFS_MAX_SECFLAVORS)
/*
@@ -37,7 +38,7 @@
*/
#define MNT_enc_dirpath_sz encode_dirpath_sz
#define MNT_dec_mountres_sz (MNT_status_sz + MNT_fhandle_sz)
-#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandle_sz + \
+#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandlev3_sz + \
MNT_authflav3_sz)
/*
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index c5c3fc6e6c60..26c94b32d6f4 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -253,37 +253,45 @@ int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
- struct posix_acl *alloc = NULL, *dfacl = NULL;
+ struct posix_acl *orig = acl, *dfacl = NULL, *alloc;
int status;
if (S_ISDIR(inode->i_mode)) {
switch(type) {
case ACL_TYPE_ACCESS:
- alloc = dfacl = get_acl(inode, ACL_TYPE_DEFAULT);
+ alloc = get_acl(inode, ACL_TYPE_DEFAULT);
if (IS_ERR(alloc))
goto fail;
+ dfacl = alloc;
break;
case ACL_TYPE_DEFAULT:
- dfacl = acl;
- alloc = acl = get_acl(inode, ACL_TYPE_ACCESS);
+ alloc = get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(alloc))
goto fail;
+ dfacl = acl;
+ acl = alloc;
break;
}
}
if (acl == NULL) {
- alloc = acl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+ alloc = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
if (IS_ERR(alloc))
goto fail;
+ acl = alloc;
}
status = __nfs3_proc_setacls(inode, acl, dfacl);
- posix_acl_release(alloc);
+out:
+ if (acl != orig)
+ posix_acl_release(acl);
+ if (dfacl != orig)
+ posix_acl_release(dfacl);
return status;
fail:
- return PTR_ERR(alloc);
+ status = PTR_ERR(alloc);
+ goto out;
}
const struct xattr_handler *nfs3_xattr_handlers[] = {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 512afb1c7867..9056f3dd380e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -6347,7 +6347,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred,
.rpc_client = server->client,
.rpc_message = &msg,
.callback_ops = &nfs4_delegreturn_ops,
- .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | RPC_TASK_TIMEOUT,
+ .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
};
int status = 0;
@@ -7891,6 +7891,7 @@ static void
nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
{
struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+ struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp;
struct nfs_client *clp = args->client;
switch (task->tk_status) {
@@ -7899,6 +7900,12 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
nfs4_schedule_session_recovery(clp->cl_session,
task->tk_status);
}
+ if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
+ res->dir != NFS4_CDFS4_BOTH) {
+ rpc_task_close_connection(task);
+ if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES)
+ rpc_restart_call(task);
+ }
}
static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
@@ -7921,6 +7928,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
struct nfs41_bind_conn_to_session_args args = {
.client = clp,
.dir = NFS4_CDFC4_FORE_OR_BOTH,
+ .retries = 0,
};
struct nfs41_bind_conn_to_session_res res;
struct rpc_message msg = {
@@ -9191,8 +9199,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout)
nfs4_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0, 0);
task = rpc_run_task(&task_setup_data);
- if (IS_ERR(task))
- return ERR_CAST(task);
+
status = rpc_wait_for_completion_task(task);
if (status != 0)
goto out;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index ac93715c05a4..a8dc25ce48bb 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -734,9 +734,9 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner)
state = new;
state->owner = owner;
atomic_inc(&owner->so_count);
- list_add_rcu(&state->inode_states, &nfsi->open_states);
ihold(inode);
state->inode = inode;
+ list_add_rcu(&state->inode_states, &nfsi->open_states);
spin_unlock(&inode->i_lock);
/* Note: The reclaim code dictates that we add stateless
* and read-only stateids to the end of the list */
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index f61f96603df7..6ca421cbe19c 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -752,7 +752,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
.callback_ops = call_ops,
.callback_data = hdr,
.workqueue = nfsiod_workqueue,
- .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags,
+ .flags = RPC_TASK_ASYNC | flags,
};
hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
@@ -950,7 +950,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
hdr->cred,
NFS_PROTO(hdr->inode),
desc->pg_rpc_callops,
- desc->pg_ioflags, 0);
+ desc->pg_ioflags,
+ RPC_TASK_CRED_NOREF);
return ret;
}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index b8d78f393365..dd2e14f5875d 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1332,13 +1332,15 @@ _pnfs_return_layout(struct inode *ino)
!valid_layout) {
spin_unlock(&ino->i_lock);
dprintk("NFS: %s no layout segments to return\n", __func__);
- goto out_put_layout_hdr;
+ goto out_wait_layoutreturn;
}
send = pnfs_prepare_layoutreturn(lo, &stateid, &cred, NULL);
spin_unlock(&ino->i_lock);
if (send)
status = pnfs_send_layoutreturn(lo, &stateid, &cred, IOMODE_ANY, true);
+out_wait_layoutreturn:
+ wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, TASK_UNINTERRUPTIBLE);
out_put_layout_hdr:
pnfs_free_lseg_list(&tmp_list);
pnfs_put_layout_hdr(lo);
@@ -1456,18 +1458,15 @@ retry:
/* lo ref dropped in pnfs_roc_release() */
layoutreturn = pnfs_prepare_layoutreturn(lo, &stateid, &lc_cred, &iomode);
/* If the creds don't match, we can't compound the layoutreturn */
- if (!layoutreturn)
+ if (!layoutreturn || cred_fscmp(cred, lc_cred) != 0)
goto out_noroc;
- if (cred_fscmp(cred, lc_cred) != 0)
- goto out_noroc_put_cred;
roc = layoutreturn;
pnfs_init_layoutreturn_args(args, lo, &stateid, iomode);
res->lrs_present = 0;
layoutreturn = false;
-
-out_noroc_put_cred:
put_cred(lc_cred);
+
out_noroc:
spin_unlock(&ino->i_lock);
rcu_read_unlock();
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index e7ddbce48321..679767ac258d 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -536,7 +536,8 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
nfs_init_commit(data, NULL, NULL, cinfo);
nfs_initiate_commit(NFS_CLIENT(inode), data,
NFS_PROTO(data->inode),
- data->mds_ops, how, 0);
+ data->mds_ops, how,
+ RPC_TASK_CRED_NOREF);
} else {
nfs_init_commit(data, NULL, data->lseg, cinfo);
initiate_commit(data, how);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 59ef3b13ccca..7a70287f21a2 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -185,7 +185,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
rcu_read_lock();
list_for_each_entry_rcu(server, head, client_link) {
- if (!nfs_sb_active(server->super))
+ if (!(server->super && nfs_sb_active(server->super)))
continue;
rcu_read_unlock();
if (last)
@@ -1189,7 +1189,6 @@ static void nfs_get_cache_cookie(struct super_block *sb,
uniq = ctx->fscache_uniq;
ulen = strlen(ctx->fscache_uniq);
}
- return;
}
nfs_fscache_get_super_cookie(sb, uniq, ulen);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index df4b87c30ac9..1e767f779c49 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1695,7 +1695,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
.callback_ops = call_ops,
.callback_data = data,
.workqueue = nfsiod_workqueue,
- .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags,
+ .flags = RPC_TASK_ASYNC | flags,
.priority = priority,
};
/* Set up the initial task struct. */
@@ -1813,7 +1813,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
nfs_init_commit(data, head, NULL, cinfo);
atomic_inc(&cinfo->mds->rpcs_out);
return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
- data->mds_ops, how, 0);
+ data->mds_ops, how, RPC_TASK_CRED_NOREF);
}
/*
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 8e4f1ace467c..1de77f1a600b 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -275,7 +275,6 @@ static ssize_t dlmfs_file_write(struct file *filp,
loff_t *ppos)
{
int bytes_left;
- ssize_t writelen;
char *lvb_buf;
struct inode *inode = file_inode(filp);
@@ -285,32 +284,30 @@ static ssize_t dlmfs_file_write(struct file *filp,
if (*ppos >= i_size_read(inode))
return -ENOSPC;
+ /* don't write past the lvb */
+ if (count > i_size_read(inode) - *ppos)
+ count = i_size_read(inode) - *ppos;
+
if (!count)
return 0;
if (!access_ok(buf, count))
return -EFAULT;
- /* don't write past the lvb */
- if ((count + *ppos) > i_size_read(inode))
- writelen = i_size_read(inode) - *ppos;
- else
- writelen = count - *ppos;
-
- lvb_buf = kmalloc(writelen, GFP_NOFS);
+ lvb_buf = kmalloc(count, GFP_NOFS);
if (!lvb_buf)
return -ENOMEM;
- bytes_left = copy_from_user(lvb_buf, buf, writelen);
- writelen -= bytes_left;
- if (writelen)
- user_dlm_write_lvb(inode, lvb_buf, writelen);
+ bytes_left = copy_from_user(lvb_buf, buf, count);
+ count -= bytes_left;
+ if (count)
+ user_dlm_write_lvb(inode, lvb_buf, count);
kfree(lvb_buf);
- *ppos = *ppos + writelen;
- mlog(0, "wrote %zd bytes\n", writelen);
- return writelen;
+ *ppos = *ppos + count;
+ mlog(0, "wrote %zu bytes\n", count);
+ return count;
}
static void dlmfs_init_once(void *foo)
diff --git a/fs/pnode.c b/fs/pnode.c
index 49f6d7ff2139..1106137c747a 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -261,14 +261,13 @@ static int propagate_one(struct mount *m)
child = copy_tree(last_source, last_source->mnt.mnt_root, type);
if (IS_ERR(child))
return PTR_ERR(child);
+ read_seqlock_excl(&mount_lock);
mnt_set_mountpoint(m, mp, child);
+ if (m->mnt_master != dest_master)
+ SET_MNT_MARK(m->mnt_master);
+ read_sequnlock_excl(&mount_lock);
last_dest = m;
last_source = child;
- if (m->mnt_master != dest_master) {
- read_seqlock_excl(&mount_lock);
- SET_MNT_MARK(m->mnt_master);
- read_sequnlock_excl(&mount_lock);
- }
hlist_add_head(&child->mnt_hash, list);
return count_mounts(m->mnt_ns, child);
}
diff --git a/fs/splice.c b/fs/splice.c
index 4735defc46ee..fd0a1e7e5959 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in,
loff_t offset;
long ret;
+ if (unlikely(!(in->f_mode & FMODE_READ) ||
+ !(out->f_mode & FMODE_WRITE)))
+ return -EBADF;
+
ipipe = get_pipe_info(in);
opipe = get_pipe_info(out);
@@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
if (off_in || off_out)
return -ESPIPE;
- if (!(in->f_mode & FMODE_READ))
- return -EBADF;
-
- if (!(out->f_mode & FMODE_WRITE))
- return -EBADF;
-
/* Splicing to self would be fun, but... */
if (ipipe == opipe)
return -EINVAL;
@@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in,
offset = out->f_pos;
}
- if (unlikely(!(out->f_mode & FMODE_WRITE)))
- return -EBADF;
-
if (unlikely(out->f_flags & O_APPEND))
return -EINVAL;
@@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
error = -EBADF;
in = fdget(fd_in);
if (in.file) {
- if (in.file->f_mode & FMODE_READ) {
- out = fdget(fd_out);
- if (out.file) {
- if (out.file->f_mode & FMODE_WRITE)
- error = do_splice(in.file, off_in,
- out.file, off_out,
- len, flags);
- fdput(out);
- }
+ out = fdget(fd_out);
+ if (out.file) {
+ error = do_splice(in.file, off_in, out.file, off_out,
+ len, flags);
+ fdput(out);
}
fdput(in);
}
@@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len,
struct pipe_inode_info *opipe = get_pipe_info(out);
int ret = -EINVAL;
+ if (unlikely(!(in->f_mode & FMODE_READ) ||
+ !(out->f_mode & FMODE_WRITE)))
+ return -EBADF;
+
/*
* Duplicate the contents of ipipe to opipe without actually
* copying the data.
@@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len,
SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
{
- struct fd in;
+ struct fd in, out;
int error;
if (unlikely(flags & ~SPLICE_F_ALL))
@@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
error = -EBADF;
in = fdget(fdin);
if (in.file) {
- if (in.file->f_mode & FMODE_READ) {
- struct fd out = fdget(fdout);
- if (out.file) {
- if (out.file->f_mode & FMODE_WRITE)
- error = do_tee(in.file, out.file,
- len, flags);
- fdput(out);
- }
+ out = fdget(fdout);
+ if (out.file) {
+ error = do_tee(in.file, out.file, len, flags);
+ fdput(out);
}
fdput(in);
}
diff --git a/fs/super.c b/fs/super.c
index cd352530eca9..a288cd60d2ae 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1302,8 +1302,8 @@ int get_tree_bdev(struct fs_context *fc,
mutex_lock(&bdev->bd_fsfreeze_mutex);
if (bdev->bd_fsfreeze_count > 0) {
mutex_unlock(&bdev->bd_fsfreeze_mutex);
- blkdev_put(bdev, mode);
warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
+ blkdev_put(bdev, mode);
return -EBUSY;
}
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 675e26989376..8fe03b4a0d2b 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -164,7 +164,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
goto fail_free;
}
- err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id);
+ err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id);
if (err)
goto fail_free;