summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/block-group.c1
-rw-r--r--fs/btrfs/ctree.h5
-rw-r--r--fs/btrfs/delalloc-space.c7
-rw-r--r--fs/btrfs/disk-io.c6
-rw-r--r--fs/btrfs/file.c43
-rw-r--r--fs/btrfs/inode-map.c4
-rw-r--r--fs/btrfs/inode.c12
-rw-r--r--fs/btrfs/ioctl.c6
-rw-r--r--fs/btrfs/qgroup.c4
-rw-r--r--fs/btrfs/relocation.c9
-rw-r--r--fs/ceph/mds_client.c21
-rw-r--r--fs/cifs/cifsfs.c8
-rw-r--r--fs/cifs/cifsglob.h5
-rw-r--r--fs/cifs/cifsproto.h1
-rw-r--r--fs/cifs/connect.c18
-rw-r--r--fs/cifs/file.c29
-rw-r--r--fs/cifs/inode.c4
-rw-r--r--fs/cifs/smb1ops.c3
-rw-r--r--fs/cifs/smb2file.c2
-rw-r--r--fs/cifs/transport.c42
-rw-r--r--fs/dax.c5
-rw-r--r--fs/direct-io.c3
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--fs/gfs2/ops_fstype.c1
-rw-r--r--fs/io_uring.c289
-rw-r--r--fs/libfs.c3
-rw-r--r--fs/ocfs2/file.c2
-rw-r--r--fs/ocfs2/journal.c3
-rw-r--r--fs/ocfs2/localalloc.c3
-rw-r--r--fs/proc/meminfo.c4
-rw-r--r--fs/proc/page.c28
-rw-r--r--fs/readdir.c4
-rw-r--r--fs/xfs/libxfs/xfs_fs.h8
33 files changed, 336 insertions, 249 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index bf7e3f23bba7..670700cb1110 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1761,6 +1761,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
btrfs_err(info,
"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
cache->key.objectid);
+ btrfs_put_block_group(cache);
ret = -EINVAL;
goto error;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 19d669d12ca1..fe2b8765d9e6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -734,8 +734,6 @@ struct btrfs_fs_info {
struct btrfs_workqueue *fixup_workers;
struct btrfs_workqueue *delayed_workers;
- /* the extent workers do delayed refs on the extent allocation tree */
- struct btrfs_workqueue *extent_workers;
struct task_struct *transaction_kthread;
struct task_struct *cleaner_kthread;
u32 thread_pool_size;
@@ -2489,8 +2487,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
- bool qgroup_free);
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index d949d7d2abed..db9f2c58eb4a 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -381,7 +381,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
out_qgroup:
btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
out_fail:
- btrfs_inode_rsv_release(inode, true);
if (delalloc_lock)
mutex_unlock(&inode->delalloc_mutex);
return ret;
@@ -418,7 +417,6 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
* btrfs_delalloc_release_extents - release our outstanding_extents
* @inode: the inode to balance the reservation for.
* @num_bytes: the number of bytes we originally reserved with
- * @qgroup_free: do we need to free qgroup meta reservation or convert them.
*
* When we reserve space we increase outstanding_extents for the extents we may
* add. Once we've set the range as delalloc or created our ordered extents we
@@ -426,8 +424,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
* temporarily tracked outstanding_extents. This _must_ be used in conjunction
* with btrfs_delalloc_reserve_metadata.
*/
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
- bool qgroup_free)
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
unsigned num_extents;
@@ -441,7 +438,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
if (btrfs_is_testing(fs_info))
return;
- btrfs_inode_rsv_release(inode, qgroup_free);
+ btrfs_inode_rsv_release(inode, true);
}
/**
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 044981cf6df9..402b61bf345c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2008,7 +2008,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
btrfs_destroy_workqueue(fs_info->readahead_workers);
btrfs_destroy_workqueue(fs_info->flush_workers);
btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
- btrfs_destroy_workqueue(fs_info->extent_workers);
/*
* Now that all other work queues are destroyed, we can safely destroy
* the queues used for metadata I/O, since tasks from those other work
@@ -2214,10 +2213,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
max_active, 2);
fs_info->qgroup_rescan_workers =
btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
- fs_info->extent_workers =
- btrfs_alloc_workqueue(fs_info, "extent-refs", flags,
- min_t(u64, fs_devices->num_devices,
- max_active), 8);
if (!(fs_info->workers && fs_info->delalloc_workers &&
fs_info->submit_workers && fs_info->flush_workers &&
@@ -2228,7 +2223,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
fs_info->endio_freespace_worker && fs_info->rmw_workers &&
fs_info->caching_workers && fs_info->readahead_workers &&
fs_info->fixup_workers && fs_info->delayed_workers &&
- fs_info->extent_workers &&
fs_info->qgroup_rescan_workers)) {
return -ENOMEM;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 27e5b269e729..435a502a3226 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1692,7 +1692,7 @@ again:
force_page_uptodate);
if (ret) {
btrfs_delalloc_release_extents(BTRFS_I(inode),
- reserve_bytes, true);
+ reserve_bytes);
break;
}
@@ -1704,7 +1704,7 @@ again:
if (extents_locked == -EAGAIN)
goto again;
btrfs_delalloc_release_extents(BTRFS_I(inode),
- reserve_bytes, true);
+ reserve_bytes);
ret = extents_locked;
break;
}
@@ -1772,8 +1772,7 @@ again:
else
free_extent_state(cached_state);
- btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes,
- true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes);
if (ret) {
btrfs_drop_pages(pages, num_pages);
break;
@@ -2068,25 +2067,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
struct btrfs_trans_handle *trans;
struct btrfs_log_ctx ctx;
int ret = 0, err;
- u64 len;
- /*
- * If the inode needs a full sync, make sure we use a full range to
- * avoid log tree corruption, due to hole detection racing with ordered
- * extent completion for adjacent ranges, and assertion failures during
- * hole detection.
- */
- if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
- &BTRFS_I(inode)->runtime_flags)) {
- start = 0;
- end = LLONG_MAX;
- }
-
- /*
- * The range length can be represented by u64, we have to do the typecasts
- * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync()
- */
- len = (u64)end - (u64)start + 1;
trace_btrfs_sync_file(file, datasync);
btrfs_init_log_ctx(&ctx, inode);
@@ -2113,6 +2094,19 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
atomic_inc(&root->log_batch);
/*
+ * If the inode needs a full sync, make sure we use a full range to
+ * avoid log tree corruption, due to hole detection racing with ordered
+ * extent completion for adjacent ranges, and assertion failures during
+ * hole detection. Do this while holding the inode lock, to avoid races
+ * with other tasks.
+ */
+ if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+ &BTRFS_I(inode)->runtime_flags)) {
+ start = 0;
+ end = LLONG_MAX;
+ }
+
+ /*
* Before we acquired the inode's lock, someone may have dirtied more
* pages in the target range. We need to make sure that writeback for
* any such pages does not start while we are logging the inode, because
@@ -2139,8 +2133,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
/*
* We have to do this here to avoid the priority inversion of waiting on
* IO of a lower priority task while holding a transaction open.
+ *
+ * Also, the range length can be represented by u64, we have to do the
+ * typecasts to avoid signed overflow if it's [0, LLONG_MAX].
*/
- ret = btrfs_wait_ordered_range(inode, start, len);
+ ret = btrfs_wait_ordered_range(inode, start, (u64)end - (u64)start + 1);
if (ret) {
up_write(&BTRFS_I(inode)->dio_sem);
inode_unlock(inode);
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 63cad7865d75..37345fb6191d 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -501,13 +501,13 @@ again:
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
prealloc, prealloc, &alloc_hint);
if (ret) {
- btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true);
goto out_put;
}
ret = btrfs_write_out_ino_cache(root, trans, path, inode);
- btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
out_put:
iput(inode);
out_release:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0f2754eaa05b..c3f386b7cc0b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2206,7 +2206,7 @@ again:
ClearPageChecked(page);
set_page_dirty(page);
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
out:
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
&cached_state);
@@ -4951,7 +4951,7 @@ again:
if (!page) {
btrfs_delalloc_release_space(inode, data_reserved,
block_start, blocksize, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
ret = -ENOMEM;
goto out;
}
@@ -5018,7 +5018,7 @@ out_unlock:
if (ret)
btrfs_delalloc_release_space(inode, data_reserved, block_start,
blocksize, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, (ret != 0));
+ btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
unlock_page(page);
put_page(page);
out:
@@ -8709,7 +8709,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
} else if (ret >= 0 && (size_t)ret < count)
btrfs_delalloc_release_space(inode, data_reserved,
offset, count - (size_t)ret, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), count, false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), count);
}
out:
if (wakeup)
@@ -9059,7 +9059,7 @@ again:
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
if (!ret2) {
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
sb_end_pagefault(inode->i_sb);
extent_changeset_free(data_reserved);
return VM_FAULT_LOCKED;
@@ -9068,7 +9068,7 @@ again:
out_unlock:
unlock_page(page);
out:
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
btrfs_delalloc_release_space(inode, data_reserved, page_start,
reserved_space, (ret != 0));
out_noreserve:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index de730e56d3f5..7c145a41decd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1360,8 +1360,7 @@ again:
unlock_page(pages[i]);
put_page(pages[i]);
}
- btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT,
- false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return i_done;
out:
@@ -1372,8 +1371,7 @@ out:
btrfs_delalloc_release_space(inode, data_reserved,
start_index << PAGE_SHIFT,
page_cnt << PAGE_SHIFT, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT,
- true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
extent_changeset_free(data_reserved);
return ret;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c4bb69941c77..3ad151655eb8 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3629,7 +3629,7 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
return 0;
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
- trace_qgroup_meta_reserve(root, type, (s64)num_bytes);
+ trace_qgroup_meta_reserve(root, (s64)num_bytes, type);
ret = qgroup_reserve(root, num_bytes, enforce, type);
if (ret < 0)
return ret;
@@ -3676,7 +3676,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
*/
num_bytes = sub_root_meta_rsv(root, num_bytes, type);
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
- trace_qgroup_meta_reserve(root, type, -(s64)num_bytes);
+ trace_qgroup_meta_reserve(root, -(s64)num_bytes, type);
btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid,
num_bytes, type);
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 00504657b602..5cd42b66818c 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3277,6 +3277,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
if (!page) {
btrfs_delalloc_release_metadata(BTRFS_I(inode),
PAGE_SIZE, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode),
+ PAGE_SIZE);
ret = -ENOMEM;
goto out;
}
@@ -3297,7 +3299,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
btrfs_delalloc_release_metadata(BTRFS_I(inode),
PAGE_SIZE, true);
btrfs_delalloc_release_extents(BTRFS_I(inode),
- PAGE_SIZE, true);
+ PAGE_SIZE);
ret = -EIO;
goto out;
}
@@ -3326,7 +3328,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
btrfs_delalloc_release_metadata(BTRFS_I(inode),
PAGE_SIZE, true);
btrfs_delalloc_release_extents(BTRFS_I(inode),
- PAGE_SIZE, true);
+ PAGE_SIZE);
clear_extent_bits(&BTRFS_I(inode)->io_tree,
page_start, page_end,
@@ -3342,8 +3344,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
put_page(page);
index++;
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE,
- false);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
balance_dirty_pages_ratelimited(inode->i_mapping);
btrfs_throttle(fs_info);
}
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a8a8f84f3bbf..a5163296d9d9 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -384,8 +384,8 @@ static int parse_reply_info_readdir(void **p, void *end,
}
done:
- if (*p != end)
- goto bad;
+ /* Skip over any unrecognized fields */
+ *p = end;
return 0;
bad:
@@ -406,12 +406,10 @@ static int parse_reply_info_filelock(void **p, void *end,
goto bad;
info->filelock_reply = *p;
- *p += sizeof(*info->filelock_reply);
- if (unlikely(*p != end))
- goto bad;
+ /* Skip over any unrecognized fields */
+ *p = end;
return 0;
-
bad:
return -EIO;
}
@@ -425,18 +423,21 @@ static int parse_reply_info_create(void **p, void *end,
{
if (features == (u64)-1 ||
(features & CEPH_FEATURE_REPLY_CREATE_INODE)) {
+ /* Malformed reply? */
if (*p == end) {
info->has_create_ino = false;
} else {
info->has_create_ino = true;
- info->ino = ceph_decode_64(p);
+ ceph_decode_64_safe(p, end, info->ino, bad);
}
+ } else {
+ if (*p != end)
+ goto bad;
}
- if (unlikely(*p != end))
- goto bad;
+ /* Skip over any unrecognized fields */
+ *p = end;
return 0;
-
bad:
return -EIO;
}
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c049c7b3aa87..1a135d1b85bd 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -169,7 +169,13 @@ cifs_read_super(struct super_block *sb)
else
sb->s_maxbytes = MAX_NON_LFS;
- /* Some very old servers like DOS and OS/2 used 2 second granularity */
+ /*
+ * Some very old servers like DOS and OS/2 used 2 second granularity
+ * (while all current servers use 100ns granularity - see MS-DTYP)
+ * but 1 second is the maximum allowed granularity for the VFS
+ * so for old servers set time granularity to 1 second while for
+ * everything else (current servers) set it to 100ns.
+ */
if ((tcon->ses->server->vals->protocol_id == SMB10_PROT_ID) &&
((tcon->ses->capabilities &
tcon->ses->server->vals->cap_nt_find) == 0) &&
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 50dfd9049370..d78bfcc19156 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1391,6 +1391,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
struct cifsInodeInfo {
bool can_cache_brlcks;
struct list_head llist; /* locks helb by this inode */
+ /*
+ * NOTE: Some code paths call down_read(lock_sem) twice, so
+ * we must always use use cifs_down_write() instead of down_write()
+ * for this semaphore to avoid deadlocks.
+ */
struct rw_semaphore lock_sem; /* protect the fields above */
/* BB add in lists for dirty pages i.e. write caching info for oplock */
struct list_head openFileList;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index e53e9f62b87b..fe597d3d5208 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -170,6 +170,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile,
struct file_lock *flock, const unsigned int xid);
extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile);
+extern void cifs_down_write(struct rw_semaphore *sem);
extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid,
struct file *file,
struct tcon_link *tlink,
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a64dfa95a925..ccaa8bad336f 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -564,9 +564,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
spin_lock(&GlobalMid_Lock);
list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
+ kref_get(&mid_entry->refcount);
if (mid_entry->mid_state == MID_REQUEST_SUBMITTED)
mid_entry->mid_state = MID_RETRY_NEEDED;
list_move(&mid_entry->qhead, &retry_list);
+ mid_entry->mid_flags |= MID_DELETED;
}
spin_unlock(&GlobalMid_Lock);
mutex_unlock(&server->srv_mutex);
@@ -576,6 +578,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
list_del_init(&mid_entry->qhead);
mid_entry->callback(mid_entry);
+ cifs_mid_q_entry_release(mid_entry);
}
if (cifs_rdma_enabled(server)) {
@@ -895,8 +898,10 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed)
if (mid->mid_flags & MID_DELETED)
printk_once(KERN_WARNING
"trying to dequeue a deleted mid\n");
- else
+ else {
list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
+ }
spin_unlock(&GlobalMid_Lock);
}
@@ -966,8 +971,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
cifs_dbg(FYI, "Clearing mid 0x%llx\n", mid_entry->mid);
+ kref_get(&mid_entry->refcount);
mid_entry->mid_state = MID_SHUTDOWN;
list_move(&mid_entry->qhead, &dispose_list);
+ mid_entry->mid_flags |= MID_DELETED;
}
spin_unlock(&GlobalMid_Lock);
@@ -977,6 +984,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
cifs_dbg(FYI, "Callback mid 0x%llx\n", mid_entry->mid);
list_del_init(&mid_entry->qhead);
mid_entry->callback(mid_entry);
+ cifs_mid_q_entry_release(mid_entry);
}
/* 1/8th of sec is more than enough time for them to exit */
msleep(125);
@@ -3882,8 +3890,12 @@ generic_ip_connect(struct TCP_Server_Info *server)
rc = socket->ops->connect(socket, saddr, slen,
server->noblockcnt ? O_NONBLOCK : 0);
-
- if (rc == -EINPROGRESS)
+ /*
+ * When mounting SMB root file systems, we do not want to block in
+ * connect. Otherwise bail out and then let cifs_reconnect() perform
+ * reconnect failover - if possible.
+ */
+ if (server->noblockcnt && rc == -EINPROGRESS)
rc = 0;
if (rc < 0) {
cifs_dbg(FYI, "Error %d connecting to server\n", rc);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5ad15de2bb4f..fa7b0fa72bb3 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -281,6 +281,13 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode)
return has_locks;
}
+void
+cifs_down_write(struct rw_semaphore *sem)
+{
+ while (!down_write_trylock(sem))
+ msleep(10);
+}
+
struct cifsFileInfo *
cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock)
@@ -306,7 +313,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
INIT_LIST_HEAD(&fdlocks->locks);
fdlocks->cfile = cfile;
cfile->llist = fdlocks;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_add(&fdlocks->llist, &cinode->llist);
up_write(&cinode->lock_sem);
@@ -405,10 +412,11 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
bool oplock_break_cancelled;
spin_lock(&tcon->open_file_lock);
-
+ spin_lock(&cifsi->open_file_lock);
spin_lock(&cifs_file->file_info_lock);
if (--cifs_file->count > 0) {
spin_unlock(&cifs_file->file_info_lock);
+ spin_unlock(&cifsi->open_file_lock);
spin_unlock(&tcon->open_file_lock);
return;
}
@@ -421,9 +429,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
cifs_add_pending_open_locked(&fid, cifs_file->tlink, &open);
/* remove it from the lists */
- spin_lock(&cifsi->open_file_lock);
list_del(&cifs_file->flist);
- spin_unlock(&cifsi->open_file_lock);
list_del(&cifs_file->tlist);
atomic_dec(&tcon->num_local_opens);
@@ -440,6 +446,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
cifs_set_oplock_level(cifsi, 0);
}
+ spin_unlock(&cifsi->open_file_lock);
spin_unlock(&tcon->open_file_lock);
oplock_break_cancelled = wait_oplock_handler ?
@@ -464,7 +471,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
* Delete any outstanding lock records. We'll lose them when the file
* is closed anyway.
*/
- down_write(&cifsi->lock_sem);
+ cifs_down_write(&cifsi->lock_sem);
list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) {
list_del(&li->llist);
cifs_del_lock_waiters(li);
@@ -1027,7 +1034,7 @@ static void
cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
{
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_add_tail(&lock->llist, &cfile->llist->locks);
up_write(&cinode->lock_sem);
}
@@ -1049,7 +1056,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
try_again:
exist = false;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length,
lock->type, lock->flags, &conf_lock,
@@ -1072,7 +1079,7 @@ try_again:
(lock->blist.next == &lock->blist));
if (!rc)
goto try_again;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_del_init(&lock->blist);
}
@@ -1125,7 +1132,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
return rc;
try_again:
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
@@ -1331,7 +1338,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
int rc = 0;
/* we are going to update can_cache_brlcks here - need a write access */
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
@@ -1522,7 +1529,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
if (!buf)
return -ENOMEM;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
for (i = 0; i < 2; i++) {
cur = buf;
num = 0;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 5dcc95b38310..df9377828e2f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2475,9 +2475,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid);
cifsFileInfo_put(wfile);
if (rc)
- return rc;
+ goto cifs_setattr_exit;
} else if (rc != -EBADF)
- return rc;
+ goto cifs_setattr_exit;
else
rc = 0;
}
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index b7421a096319..514810694c0f 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -171,6 +171,9 @@ cifs_get_next_mid(struct TCP_Server_Info *server)
/* we do not want to loop forever */
last_mid = cur_mid;
cur_mid++;
+ /* avoid 0xFFFF MID */
+ if (cur_mid == 0xffff)
+ cur_mid++;
/*
* This nested loop looks more expensive than it is.
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index e6a1fc72018f..8b0b512c5792 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -145,7 +145,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
cur = buf;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) {
if (flock->fl_start > li->offset ||
(flock->fl_start + length) <
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 308ad0f495e1..ca3de62688d6 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -86,22 +86,8 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
static void _cifs_mid_q_entry_release(struct kref *refcount)
{
- struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry,
- refcount);
-
- mempool_free(mid, cifs_mid_poolp);
-}
-
-void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
-{
- spin_lock(&GlobalMid_Lock);
- kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
- spin_unlock(&GlobalMid_Lock);
-}
-
-void
-DeleteMidQEntry(struct mid_q_entry *midEntry)
-{
+ struct mid_q_entry *midEntry =
+ container_of(refcount, struct mid_q_entry, refcount);
#ifdef CONFIG_CIFS_STATS2
__le16 command = midEntry->server->vals->lock_cmd;
__u16 smb_cmd = le16_to_cpu(midEntry->command);
@@ -166,6 +152,19 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
}
}
#endif
+
+ mempool_free(midEntry, cifs_mid_poolp);
+}
+
+void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
+{
+ spin_lock(&GlobalMid_Lock);
+ kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
+ spin_unlock(&GlobalMid_Lock);
+}
+
+void DeleteMidQEntry(struct mid_q_entry *midEntry)
+{
cifs_mid_q_entry_release(midEntry);
}
@@ -173,8 +172,10 @@ void
cifs_delete_mid(struct mid_q_entry *mid)
{
spin_lock(&GlobalMid_Lock);
- list_del_init(&mid->qhead);
- mid->mid_flags |= MID_DELETED;
+ if (!(mid->mid_flags & MID_DELETED)) {
+ list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
+ }
spin_unlock(&GlobalMid_Lock);
DeleteMidQEntry(mid);
@@ -872,7 +873,10 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
rc = -EHOSTDOWN;
break;
default:
- list_del_init(&mid->qhead);
+ if (!(mid->mid_flags & MID_DELETED)) {
+ list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
+ }
cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n",
__func__, mid->mid, mid->mid_state);
rc = -EIO;
diff --git a/fs/dax.c b/fs/dax.c
index 6bf81f931de3..2cc43cd914eb 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -220,10 +220,11 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
for (;;) {
entry = xas_find_conflict(xas);
+ if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
+ return entry;
if (dax_entry_order(entry) < order)
return XA_RETRY_ENTRY;
- if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
- !dax_is_locked(entry))
+ if (!dax_is_locked(entry))
return entry;
wq = dax_entry_waitqueue(xas, entry, &ewait.key);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index ae196784f487..9329ced91f1d 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -241,9 +241,8 @@ void dio_warn_stale_pagecache(struct file *filp)
}
}
-/**
+/*
* dio_complete() - called when all DIO BIO I/O has been completed
- * @offset: the byte offset in the file of the completed operation
*
* This drops i_dio_count, lets interested parties know that a DIO operation
* has completed, and calculates the resulting return code for the operation.
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e88421d9a48d..8461a6322039 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -905,7 +905,7 @@ restart:
* cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs
* @bdi_id: target bdi id
* @memcg_id: target memcg css id
- * @nr_pages: number of pages to write, 0 for best-effort dirty flushing
+ * @nr: number of pages to write, 0 for best-effort dirty flushing
* @reason: reason why some writeback work initiated
* @done: target wb_completion
*
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 681b44682b0d..dc61af2c4d5e 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1600,6 +1600,7 @@ static int gfs2_meta_get_tree(struct fs_context *fc)
}
static const struct fs_context_operations gfs2_meta_context_ops = {
+ .free = gfs2_fc_free,
.get_tree = gfs2_meta_get_tree,
};
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 76fdbe84aff5..a30c4f622cb3 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -197,6 +197,7 @@ struct io_ring_ctx {
unsigned sq_entries;
unsigned sq_mask;
unsigned sq_thread_idle;
+ unsigned cached_sq_dropped;
struct io_uring_sqe *sq_sqes;
struct list_head defer_list;
@@ -212,6 +213,7 @@ struct io_ring_ctx {
struct {
unsigned cached_cq_tail;
+ atomic_t cached_cq_overflow;
unsigned cq_entries;
unsigned cq_mask;
struct wait_queue_head cq_wait;
@@ -322,6 +324,8 @@ struct io_kiocb {
#define REQ_F_FAIL_LINK 256 /* fail rest of links */
#define REQ_F_SHADOW_DRAIN 512 /* link-drain shadow req */
#define REQ_F_TIMEOUT 1024 /* timeout request */
+#define REQ_F_ISREG 2048 /* regular file */
+#define REQ_F_MUST_PUNT 4096 /* must be punted even for NONBLOCK */
u64 user_data;
u32 result;
u32 sequence;
@@ -418,7 +422,8 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
static inline bool __io_sequence_defer(struct io_ring_ctx *ctx,
struct io_kiocb *req)
{
- return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped;
+ return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped
+ + atomic_read(&ctx->cached_cq_overflow);
}
static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
@@ -565,9 +570,8 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, 0);
} else {
- unsigned overflow = READ_ONCE(ctx->rings->cq_overflow);
-
- WRITE_ONCE(ctx->rings->cq_overflow, overflow + 1);
+ WRITE_ONCE(ctx->rings->cq_overflow,
+ atomic_inc_return(&ctx->cached_cq_overflow));
}
}
@@ -733,6 +737,14 @@ static unsigned io_cqring_events(struct io_rings *rings)
return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
}
+static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
+{
+ struct io_rings *rings = ctx->rings;
+
+ /* make sure SQ entry isn't read before tail */
+ return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
+}
+
/*
* Find and free completed poll iocbs
*/
@@ -862,19 +874,11 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
mutex_unlock(&ctx->uring_lock);
}
-static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
- long min)
+static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+ long min)
{
- int iters, ret = 0;
+ int iters = 0, ret = 0;
- /*
- * We disallow the app entering submit/complete with polling, but we
- * still need to lock the ring to prevent racing with polled issue
- * that got punted to a workqueue.
- */
- mutex_lock(&ctx->uring_lock);
-
- iters = 0;
do {
int tmin = 0;
@@ -910,30 +914,45 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
ret = 0;
} while (min && !*nr_events && !need_resched());
+ return ret;
+}
+
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+ long min)
+{
+ int ret;
+
+ /*
+ * We disallow the app entering submit/complete with polling, but we
+ * still need to lock the ring to prevent racing with polled issue
+ * that got punted to a workqueue.
+ */
+ mutex_lock(&ctx->uring_lock);
+ ret = __io_iopoll_check(ctx, nr_events, min);
mutex_unlock(&ctx->uring_lock);
return ret;
}
-static void kiocb_end_write(struct kiocb *kiocb)
+static void kiocb_end_write(struct io_kiocb *req)
{
- if (kiocb->ki_flags & IOCB_WRITE) {
- struct inode *inode = file_inode(kiocb->ki_filp);
+ /*
+ * Tell lockdep we inherited freeze protection from submission
+ * thread.
+ */
+ if (req->flags & REQ_F_ISREG) {
+ struct inode *inode = file_inode(req->file);
- /*
- * Tell lockdep we inherited freeze protection from submission
- * thread.
- */
- if (S_ISREG(inode->i_mode))
- __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
- file_end_write(kiocb->ki_filp);
+ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
}
+ file_end_write(req->file);
}
static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
- kiocb_end_write(kiocb);
+ if (kiocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
if ((req->flags & REQ_F_LINK) && res != req->result)
req->flags |= REQ_F_FAIL_LINK;
@@ -945,7 +964,8 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
- kiocb_end_write(kiocb);
+ if (kiocb->ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
if ((req->flags & REQ_F_LINK) && res != req->result)
req->flags |= REQ_F_FAIL_LINK;
@@ -1059,8 +1079,17 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
if (!req->file)
return -EBADF;
- if (force_nonblock && !io_file_supports_async(req->file))
- force_nonblock = false;
+ if (S_ISREG(file_inode(req->file)->i_mode))
+ req->flags |= REQ_F_ISREG;
+
+ /*
+ * 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)) {
+ req->flags |= REQ_F_MUST_PUNT;
+ return -EAGAIN;
+ }
kiocb->ki_pos = READ_ONCE(sqe->off);
kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
@@ -1081,7 +1110,8 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
return ret;
/* don't allow async punt if RWF_NOWAIT was requested */
- if (kiocb->ki_flags & IOCB_NOWAIT)
+ if ((kiocb->ki_flags & IOCB_NOWAIT) ||
+ (req->file->f_flags & O_NONBLOCK))
req->flags |= REQ_F_NOWAIT;
if (force_nonblock)
@@ -1382,7 +1412,9 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
* need async punt anyway, so it's more efficient to do it
* here.
*/
- if (force_nonblock && ret2 > 0 && ret2 < read_size)
+ if (force_nonblock && !(req->flags & REQ_F_NOWAIT) &&
+ (req->flags & REQ_F_ISREG) &&
+ ret2 > 0 && ret2 < read_size)
ret2 = -EAGAIN;
/* Catch -EAGAIN return for forced non-blocking submission */
if (!force_nonblock || ret2 != -EAGAIN) {
@@ -1447,7 +1479,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
* released so that it doesn't complain about the held lock when
* we return to userspace.
*/
- if (S_ISREG(file_inode(file)->i_mode)) {
+ if (req->flags & REQ_F_ISREG) {
__sb_start_write(file_inode(file)->i_sb,
SB_FREEZE_WRITE, true);
__sb_writers_release(file_inode(file)->i_sb,
@@ -1862,7 +1894,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
{
struct io_ring_ctx *ctx;
- struct io_kiocb *req;
+ struct io_kiocb *req, *prev;
unsigned long flags;
req = container_of(timer, struct io_kiocb, timeout.timer);
@@ -1870,6 +1902,15 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
atomic_inc(&ctx->cq_timeouts);
spin_lock_irqsave(&ctx->completion_lock, flags);
+ /*
+ * Adjust the reqs sequence before the current one because it
+ * will consume a slot in the cq_ring and the the cq_tail pointer
+ * will be increased, otherwise other timeout reqs may return in
+ * advance without waiting for enough wait_nr.
+ */
+ prev = req;
+ list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list)
+ prev->sequence++;
list_del(&req->list);
io_cqring_fill_event(ctx, req->user_data, -ETIME);
@@ -1884,10 +1925,11 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
- unsigned count, req_dist, tail_index;
+ unsigned count;
struct io_ring_ctx *ctx = req->ctx;
struct list_head *entry;
struct timespec64 ts;
+ unsigned span = 0;
if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
@@ -1907,23 +1949,46 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
count = 1;
req->sequence = ctx->cached_sq_head + count - 1;
+ /* reuse it to store the count */
+ req->submit.sequence = count;
req->flags |= REQ_F_TIMEOUT;
/*
* Insertion sort, ensuring the first entry in the list is always
* the one we need first.
*/
- tail_index = ctx->cached_cq_tail - ctx->rings->sq_dropped;
- req_dist = req->sequence - tail_index;
spin_lock_irq(&ctx->completion_lock);
list_for_each_prev(entry, &ctx->timeout_list) {
struct io_kiocb *nxt = list_entry(entry, struct io_kiocb, list);
- unsigned dist;
+ unsigned nxt_sq_head;
+ long long tmp, tmp_nxt;
+
+ /*
+ * Since cached_sq_head + count - 1 can overflow, use type long
+ * long to store it.
+ */
+ tmp = (long long)ctx->cached_sq_head + count - 1;
+ nxt_sq_head = nxt->sequence - nxt->submit.sequence + 1;
+ tmp_nxt = (long long)nxt_sq_head + nxt->submit.sequence - 1;
- dist = nxt->sequence - tail_index;
- if (req_dist >= dist)
+ /*
+ * cached_sq_head may overflow, and it will never overflow twice
+ * once there is some timeout req still be valid.
+ */
+ if (ctx->cached_sq_head < nxt_sq_head)
+ tmp += UINT_MAX;
+
+ if (tmp > tmp_nxt)
break;
+
+ /*
+ * Sequence of reqs after the insert one and itself should
+ * be adjusted because each timeout req consumes a slot.
+ */
+ span++;
+ nxt->sequence++;
}
+ req->sequence -= span;
list_add(&req->list, entry);
spin_unlock_irq(&ctx->completion_lock);
@@ -2262,12 +2327,18 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
}
static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- struct sqe_submit *s, bool force_nonblock)
+ struct sqe_submit *s)
{
int ret;
- ret = __io_submit_sqe(ctx, req, s, force_nonblock);
- if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
+ ret = __io_submit_sqe(ctx, req, s, true);
+
+ /*
+ * We async punt it if the file wasn't marked NOWAIT, or if the file
+ * doesn't support non-blocking read/write attempts
+ */
+ if (ret == -EAGAIN && (!(req->flags & REQ_F_NOWAIT) ||
+ (req->flags & REQ_F_MUST_PUNT))) {
struct io_uring_sqe *sqe_copy;
sqe_copy = kmemdup(s->sqe, sizeof(*sqe_copy), GFP_KERNEL);
@@ -2307,7 +2378,7 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
}
static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- struct sqe_submit *s, bool force_nonblock)
+ struct sqe_submit *s)
{
int ret;
@@ -2320,18 +2391,17 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
return 0;
}
- return __io_queue_sqe(ctx, req, s, force_nonblock);
+ return __io_queue_sqe(ctx, req, s);
}
static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
- struct sqe_submit *s, struct io_kiocb *shadow,
- bool force_nonblock)
+ struct sqe_submit *s, struct io_kiocb *shadow)
{
int ret;
int need_submit = false;
if (!shadow)
- return io_queue_sqe(ctx, req, s, force_nonblock);
+ return io_queue_sqe(ctx, req, s);
/*
* Mark the first IO in link list as DRAIN, let all the following
@@ -2360,7 +2430,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
spin_unlock_irq(&ctx->completion_lock);
if (need_submit)
- return __io_queue_sqe(ctx, req, s, force_nonblock);
+ return __io_queue_sqe(ctx, req, s);
return 0;
}
@@ -2368,8 +2438,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK)
static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
- struct io_submit_state *state, struct io_kiocb **link,
- bool force_nonblock)
+ struct io_submit_state *state, struct io_kiocb **link)
{
struct io_uring_sqe *sqe_copy;
struct io_kiocb *req;
@@ -2396,6 +2465,8 @@ err:
return;
}
+ req->user_data = s->sqe->user_data;
+
/*
* If we already have a head request, queue this one for async
* submittal once the head completes. If we don't have a head but
@@ -2422,7 +2493,7 @@ err:
INIT_LIST_HEAD(&req->link_list);
*link = req;
} else {
- io_queue_sqe(ctx, req, s, force_nonblock);
+ io_queue_sqe(ctx, req, s);
}
}
@@ -2502,12 +2573,13 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
/* drop invalid entries */
ctx->cached_sq_head++;
- rings->sq_dropped++;
+ ctx->cached_sq_dropped++;
+ WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped);
return false;
}
-static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
- unsigned int nr, bool has_user, bool mm_fault)
+static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
+ bool has_user, bool mm_fault)
{
struct io_submit_state state, *statep = NULL;
struct io_kiocb *link = NULL;
@@ -2521,19 +2593,23 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
}
for (i = 0; i < nr; i++) {
+ struct sqe_submit s;
+
+ if (!io_get_sqring(ctx, &s))
+ break;
+
/*
* If previous wasn't linked and we have a linked command,
* that's the end of the chain. Submit the previous link.
*/
if (!prev_was_link && link) {
- io_queue_link_head(ctx, link, &link->submit, shadow_req,
- true);
+ io_queue_link_head(ctx, link, &link->submit, shadow_req);
link = NULL;
shadow_req = NULL;
}
- prev_was_link = (sqes[i].sqe->flags & IOSQE_IO_LINK) != 0;
+ prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0;
- if (link && (sqes[i].sqe->flags & IOSQE_IO_DRAIN)) {
+ if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) {
if (!shadow_req) {
shadow_req = io_get_req(ctx, NULL);
if (unlikely(!shadow_req))
@@ -2541,24 +2617,24 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN);
refcount_dec(&shadow_req->refs);
}
- shadow_req->sequence = sqes[i].sequence;
+ shadow_req->sequence = s.sequence;
}
out:
if (unlikely(mm_fault)) {
- io_cqring_add_event(ctx, sqes[i].sqe->user_data,
+ io_cqring_add_event(ctx, s.sqe->user_data,
-EFAULT);
} else {
- sqes[i].has_user = has_user;
- sqes[i].needs_lock = true;
- sqes[i].needs_fixed_file = true;
- io_submit_sqe(ctx, &sqes[i], statep, &link, true);
+ s.has_user = has_user;
+ s.needs_lock = true;
+ s.needs_fixed_file = true;
+ io_submit_sqe(ctx, &s, statep, &link);
submitted++;
}
}
if (link)
- io_queue_link_head(ctx, link, &link->submit, shadow_req, true);
+ io_queue_link_head(ctx, link, &link->submit, shadow_req);
if (statep)
io_submit_state_end(&state);
@@ -2567,7 +2643,6 @@ out:
static int io_sq_thread(void *data)
{
- struct sqe_submit sqes[IO_IOPOLL_BATCH];
struct io_ring_ctx *ctx = data;
struct mm_struct *cur_mm = NULL;
mm_segment_t old_fs;
@@ -2582,14 +2657,27 @@ static int io_sq_thread(void *data)
timeout = inflight = 0;
while (!kthread_should_park()) {
- bool all_fixed, mm_fault = false;
- int i;
+ bool mm_fault = false;
+ unsigned int to_submit;
if (inflight) {
unsigned nr_events = 0;
if (ctx->flags & IORING_SETUP_IOPOLL) {
- io_iopoll_check(ctx, &nr_events, 0);
+ /*
+ * inflight is the count of the maximum possible
+ * entries we submitted, but it can be smaller
+ * if we dropped some of them. If we don't have
+ * poll entries available, then we know that we
+ * have nothing left to poll for. Reset the
+ * inflight count to zero in that case.
+ */
+ mutex_lock(&ctx->uring_lock);
+ if (!list_empty(&ctx->poll_list))
+ __io_iopoll_check(ctx, &nr_events, 0);
+ else
+ inflight = 0;
+ mutex_unlock(&ctx->uring_lock);
} else {
/*
* Normal IO, just pretend everything completed.
@@ -2603,7 +2691,8 @@ static int io_sq_thread(void *data)
timeout = jiffies + ctx->sq_thread_idle;
}
- if (!io_get_sqring(ctx, &sqes[0])) {
+ to_submit = io_sqring_entries(ctx);
+ if (!to_submit) {
/*
* We're polling. If we're within the defined idle
* period, then let us spin without work before going
@@ -2634,7 +2723,8 @@ static int io_sq_thread(void *data)
/* make sure to read SQ tail after writing flags */
smp_mb();
- if (!io_get_sqring(ctx, &sqes[0])) {
+ to_submit = io_sqring_entries(ctx);
+ if (!to_submit) {
if (kthread_should_park()) {
finish_wait(&ctx->sqo_wait, &wait);
break;
@@ -2652,19 +2742,8 @@ static int io_sq_thread(void *data)
ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
}
- i = 0;
- all_fixed = true;
- do {
- if (all_fixed && io_sqe_needs_user(sqes[i].sqe))
- all_fixed = false;
-
- i++;
- if (i == ARRAY_SIZE(sqes))
- break;
- } while (io_get_sqring(ctx, &sqes[i]));
-
/* Unless all new commands are FIXED regions, grab mm */
- if (!all_fixed && !cur_mm) {
+ if (!cur_mm) {
mm_fault = !mmget_not_zero(ctx->sqo_mm);
if (!mm_fault) {
use_mm(ctx->sqo_mm);
@@ -2672,8 +2751,9 @@ static int io_sq_thread(void *data)
}
}
- inflight += io_submit_sqes(ctx, sqes, i, cur_mm != NULL,
- mm_fault);
+ to_submit = min(to_submit, ctx->sq_entries);
+ inflight += io_submit_sqes(ctx, to_submit, cur_mm != NULL,
+ mm_fault);
/* Commit SQ ring head once we've consumed all SQEs */
io_commit_sqring(ctx);
@@ -2690,8 +2770,7 @@ static int io_sq_thread(void *data)
return 0;
}
-static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
- bool block_for_last)
+static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
{
struct io_submit_state state, *statep = NULL;
struct io_kiocb *link = NULL;
@@ -2705,7 +2784,6 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
}
for (i = 0; i < to_submit; i++) {
- bool force_nonblock = true;
struct sqe_submit s;
if (!io_get_sqring(ctx, &s))
@@ -2716,8 +2794,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
* that's the end of the chain. Submit the previous link.
*/
if (!prev_was_link && link) {
- io_queue_link_head(ctx, link, &link->submit, shadow_req,
- force_nonblock);
+ io_queue_link_head(ctx, link, &link->submit, shadow_req);
link = NULL;
shadow_req = NULL;
}
@@ -2739,27 +2816,16 @@ out:
s.needs_lock = false;
s.needs_fixed_file = false;
submit++;
-
- /*
- * The caller will block for events after submit, submit the
- * last IO non-blocking. This is either the only IO it's
- * submitting, or it already submitted the previous ones. This
- * improves performance by avoiding an async punt that we don't
- * need to do.
- */
- if (block_for_last && submit == to_submit)
- force_nonblock = false;
-
- io_submit_sqe(ctx, &s, statep, &link, force_nonblock);
+ io_submit_sqe(ctx, &s, statep, &link);
}
- io_commit_sqring(ctx);
if (link)
- io_queue_link_head(ctx, link, &link->submit, shadow_req,
- !block_for_last);
+ io_queue_link_head(ctx, link, &link->submit, shadow_req);
if (statep)
io_submit_state_end(statep);
+ io_commit_sqring(ctx);
+
return submit;
}
@@ -3600,21 +3666,10 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
wake_up(&ctx->sqo_wait);
submitted = to_submit;
} else if (to_submit) {
- bool block_for_last = false;
-
to_submit = min(to_submit, ctx->sq_entries);
- /*
- * Allow last submission to block in a series, IFF the caller
- * asked to wait for events and we don't currently have
- * enough. This potentially avoids an async punt.
- */
- if (to_submit == min_complete &&
- io_cqring_events(ctx->rings) < min_complete)
- block_for_last = true;
-
mutex_lock(&ctx->uring_lock);
- submitted = io_ring_submit(ctx, to_submit, block_for_last);
+ submitted = io_ring_submit(ctx, to_submit);
mutex_unlock(&ctx->uring_lock);
}
if (flags & IORING_ENTER_GETEVENTS) {
diff --git a/fs/libfs.c b/fs/libfs.c
index 540611b99b9a..1463b038ffc4 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -473,8 +473,7 @@ EXPORT_SYMBOL(simple_write_begin);
/**
* simple_write_end - .write_end helper for non-block-device FSes
- * @available: See .write_end of address_space_operations
- * @file: "
+ * @file: See .write_end of address_space_operations
* @mapping: "
* @pos: "
* @len: "
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 2e982db3e1ae..53939bf9d7d2 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1230,6 +1230,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid));
if (IS_ERR(transfer_to[USRQUOTA])) {
status = PTR_ERR(transfer_to[USRQUOTA]);
+ transfer_to[USRQUOTA] = NULL;
goto bail_unlock;
}
}
@@ -1239,6 +1240,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid));
if (IS_ERR(transfer_to[GRPQUOTA])) {
status = PTR_ERR(transfer_to[GRPQUOTA]);
+ transfer_to[GRPQUOTA] = NULL;
goto bail_unlock;
}
}
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 930e3d388579..699a560efbb0 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -217,7 +217,8 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb)
/* At this point, we know that no more recovery threads can be
* launched, so wait for any recovery completion work to
* complete. */
- flush_workqueue(osb->ocfs2_wq);
+ if (osb->ocfs2_wq)
+ flush_workqueue(osb->ocfs2_wq);
/*
* Now that recovery is shut down, and the osb is about to be
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 158e5af767fd..720e9f94957e 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -377,7 +377,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
struct ocfs2_dinode *alloc = NULL;
cancel_delayed_work(&osb->la_enable_wq);
- flush_workqueue(osb->ocfs2_wq);
+ if (osb->ocfs2_wq)
+ flush_workqueue(osb->ocfs2_wq);
if (osb->local_alloc_state == OCFS2_LA_UNUSED)
goto out;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index ac9247371871..8c1f1bb1a5ce 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -132,9 +132,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR);
show_val_kb(m, "ShmemPmdMapped: ",
global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR);
- show_val_kb(m, "FileHugePages: ",
+ show_val_kb(m, "FileHugePages: ",
global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR);
- show_val_kb(m, "FilePmdMapped: ",
+ show_val_kb(m, "FilePmdMapped: ",
global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR);
#endif
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 544d1ee15aee..7c952ee732e6 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -42,10 +42,12 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
return -EINVAL;
while (count > 0) {
- if (pfn_valid(pfn))
- ppage = pfn_to_page(pfn);
- else
- ppage = NULL;
+ /*
+ * TODO: ZONE_DEVICE support requires to identify
+ * memmaps that were actually initialized.
+ */
+ ppage = pfn_to_online_page(pfn);
+
if (!ppage || PageSlab(ppage) || page_has_type(ppage))
pcount = 0;
else
@@ -216,10 +218,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
return -EINVAL;
while (count > 0) {
- if (pfn_valid(pfn))
- ppage = pfn_to_page(pfn);
- else
- ppage = NULL;
+ /*
+ * TODO: ZONE_DEVICE support requires to identify
+ * memmaps that were actually initialized.
+ */
+ ppage = pfn_to_online_page(pfn);
if (put_user(stable_page_flags(ppage), out)) {
ret = -EFAULT;
@@ -261,10 +264,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
return -EINVAL;
while (count > 0) {
- if (pfn_valid(pfn))
- ppage = pfn_to_page(pfn);
- else
- ppage = NULL;
+ /*
+ * TODO: ZONE_DEVICE support requires to identify
+ * memmaps that were actually initialized.
+ */
+ ppage = pfn_to_online_page(pfn);
if (ppage)
ino = page_cgroup_ino(ppage);
diff --git a/fs/readdir.c b/fs/readdir.c
index 6e2623e57b2e..d26d5ea4de7b 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -105,9 +105,9 @@ EXPORT_SYMBOL(iterate_dir);
*/
static int verify_dirent_name(const char *name, int len)
{
- if (WARN_ON_ONCE(!len))
+ if (!len)
return -EIO;
- if (WARN_ON_ONCE(memchr(name, '/', len)))
+ if (memchr(name, '/', len))
return -EIO;
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 39dd2b908106..e9371a8e0e26 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -366,11 +366,11 @@ struct xfs_bulkstat {
uint64_t bs_blocks; /* number of blocks */
uint64_t bs_xflags; /* extended flags */
- uint64_t bs_atime; /* access time, seconds */
- uint64_t bs_mtime; /* modify time, seconds */
+ int64_t bs_atime; /* access time, seconds */
+ int64_t bs_mtime; /* modify time, seconds */
- uint64_t bs_ctime; /* inode change time, seconds */
- uint64_t bs_btime; /* creation time, seconds */
+ int64_t bs_ctime; /* inode change time, seconds */
+ int64_t bs_btime; /* creation time, seconds */
uint32_t bs_gen; /* generation count */
uint32_t bs_uid; /* user id */
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-24 03:33:48 +0300