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.c27
-rw-r--r--fs/btrfs/ioctl.c12
-rw-r--r--fs/btrfs/qgroup.c4
-rw-r--r--fs/btrfs/relocation.c9
-rw-r--r--fs/btrfs/space-info.c21
-rw-r--r--fs/btrfs/tree-checker.c8
-rw-r--r--fs/btrfs/volumes.c1
-rw-r--r--fs/ceph/caps.c10
-rw-r--r--fs/ceph/dir.c15
-rw-r--r--fs/ceph/file.c15
-rw-r--r--fs/ceph/inode.c1
-rw-r--r--fs/ceph/super.c11
-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/smb2ops.c3
-rw-r--r--fs/cifs/smb2pdu.h1
-rw-r--r--fs/cifs/transport.c42
-rw-r--r--fs/configfs/symlink.c2
-rw-r--r--fs/dax.c5
-rw-r--r--fs/fs-writeback.c9
-rw-r--r--fs/fuse/Makefile3
-rw-r--r--fs/fuse/dev.c4
-rw-r--r--fs/fuse/dir.c16
-rw-r--r--fs/fuse/file.c14
-rw-r--r--fs/fuse/fuse_i.h4
-rw-r--r--fs/fuse/inode.c4
-rw-r--r--fs/fuse/virtio_fs.c169
-rw-r--r--fs/gfs2/ops_fstype.c21
-rw-r--r--fs/io_uring.c221
-rw-r--r--fs/nfs/delegation.c12
-rw-r--r--fs/nfs/delegation.h1
-rw-r--r--fs/nfs/nfs4proc.c7
-rw-r--r--fs/ocfs2/file.c134
45 files changed, 592 insertions, 350 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..c6dc4dd16cf7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -474,6 +474,7 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
u64 start = async_chunk->start;
u64 end = async_chunk->end;
u64 actual_end;
+ u64 i_size;
int ret = 0;
struct page **pages = NULL;
unsigned long nr_pages;
@@ -488,7 +489,19 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
SZ_16K);
- actual_end = min_t(u64, i_size_read(inode), end + 1);
+ /*
+ * We need to save i_size before now because it could change in between
+ * us evaluating the size and assigning it. This is because we lock and
+ * unlock the page in truncate and fallocate, and then modify the i_size
+ * later on.
+ *
+ * The barriers are to emulate READ_ONCE, remove that once i_size_read
+ * does that for us.
+ */
+ barrier();
+ i_size = i_size_read(inode);
+ barrier();
+ actual_end = min_t(u64, i_size, end + 1);
again:
will_compress = 0;
nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
@@ -2206,7 +2219,7 @@ 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 +4964,7 @@ 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 +5031,7 @@ 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 +8722,7 @@ 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 +9072,7 @@ 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 +9081,7 @@ 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..23272d9154f3 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;
@@ -4197,9 +4195,6 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root,
u64 transid;
int ret;
- btrfs_warn(root->fs_info,
- "START_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT)
@@ -4227,9 +4222,6 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info,
{
u64 transid;
- btrfs_warn(fs_info,
- "WAIT_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
if (argp) {
if (copy_from_user(&transid, argp, sizeof(transid)))
return -EFAULT;
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/btrfs/space-info.c b/fs/btrfs/space-info.c
index 98dc092a905e..e8a4b0ebe97f 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -893,6 +893,15 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info,
while (ticket->bytes > 0 && ticket->error == 0) {
ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
if (ret) {
+ /*
+ * Delete us from the list. After we unlock the space
+ * info, we don't want the async reclaim job to reserve
+ * space for this ticket. If that would happen, then the
+ * ticket's task would not known that space was reserved
+ * despite getting an error, resulting in a space leak
+ * (bytes_may_use counter of our space_info).
+ */
+ list_del_init(&ticket->list);
ticket->error = -EINTR;
break;
}
@@ -945,12 +954,24 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
spin_lock(&space_info->lock);
ret = ticket->error;
if (ticket->bytes || ticket->error) {
+ /*
+ * Need to delete here for priority tickets. For regular tickets
+ * either the async reclaim job deletes the ticket from the list
+ * or we delete it ourselves at wait_reserve_ticket().
+ */
list_del_init(&ticket->list);
if (!ret)
ret = -ENOSPC;
}
spin_unlock(&space_info->lock);
ASSERT(list_empty(&ticket->list));
+ /*
+ * Check that we can't have an error set if the reservation succeeded,
+ * as that would confuse tasks and lead them to error out without
+ * releasing reserved space (if an error happens the expectation is that
+ * space wasn't reserved at all).
+ */
+ ASSERT(!(ticket->bytes == 0 && ticket->error));
return ret;
}
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 43e488f5d063..076d5b8014fb 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -686,9 +686,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot,
static int check_dev_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot)
{
- struct btrfs_fs_info *fs_info = leaf->fs_info;
struct btrfs_dev_item *ditem;
- u64 max_devid = max(BTRFS_MAX_DEVS(fs_info), BTRFS_MAX_DEVS_SYS_CHUNK);
if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) {
dev_item_err(leaf, slot,
@@ -696,12 +694,6 @@ static int check_dev_item(struct extent_buffer *leaf,
key->objectid, BTRFS_DEV_ITEMS_OBJECTID);
return -EUCLEAN;
}
- if (key->offset > max_devid) {
- dev_item_err(leaf, slot,
- "invalid devid: has=%llu expect=[0, %llu]",
- key->offset, max_devid);
- return -EUCLEAN;
- }
ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item);
if (btrfs_device_id(leaf, ditem) != key->offset) {
dev_item_err(leaf, slot,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bdfe4493e43a..e04409f85063 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4967,6 +4967,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
max_stripe_size = SZ_32M;
max_chunk_size = 2 * max_stripe_size;
+ devs_max = min_t(int, devs_max, BTRFS_MAX_DEVS_SYS_CHUNK);
} else {
btrfs_err(info, "invalid chunk type 0x%llx requested",
type);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d3b9c9d5c1bd..f5a38910a82b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1058,6 +1058,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
+ /* remove from inode's cap rbtree, and clear auth cap */
+ rb_erase(&cap->ci_node, &ci->i_caps);
+ if (ci->i_auth_cap == cap)
+ ci->i_auth_cap = NULL;
+
/* remove from session list */
spin_lock(&session->s_cap_lock);
if (session->s_cap_iterator == cap) {
@@ -1091,11 +1096,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
spin_unlock(&session->s_cap_lock);
- /* remove from inode list */
- rb_erase(&cap->ci_node, &ci->i_caps);
- if (ci->i_auth_cap == cap)
- ci->i_auth_cap = NULL;
-
if (removed)
ceph_put_cap(mdsc, cap);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4ca0b8ff9a72..d17a789fd856 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1553,36 +1553,37 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int valid = 0;
struct dentry *parent;
- struct inode *dir;
+ struct inode *dir, *inode;
if (flags & LOOKUP_RCU) {
parent = READ_ONCE(dentry->d_parent);
dir = d_inode_rcu(parent);
if (!dir)
return -ECHILD;
+ inode = d_inode_rcu(dentry);
} else {
parent = dget_parent(dentry);
dir = d_inode(parent);
+ inode = d_inode(dentry);
}
dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
- dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
+ dentry, inode, ceph_dentry(dentry)->offset);
/* always trust cached snapped dentries, snapdir dentry */
if (ceph_snap(dir) != CEPH_NOSNAP) {
dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
- dentry, d_inode(dentry));
+ dentry, inode);
valid = 1;
- } else if (d_really_is_positive(dentry) &&
- ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
+ } else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
valid = 1;
} else {
valid = dentry_lease_is_valid(dentry, flags);
if (valid == -ECHILD)
return valid;
if (valid || dir_lease_is_valid(dir, dentry)) {
- if (d_really_is_positive(dentry))
- valid = ceph_is_any_caps(d_inode(dentry));
+ if (inode)
+ valid = ceph_is_any_caps(inode);
else
valid = 1;
}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d277f71abe0b..bd77adb64bfd 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -462,6 +462,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
err = ceph_security_init_secctx(dentry, mode, &as_ctx);
if (err < 0)
goto out_ctx;
+ } else if (!d_in_lookup(dentry)) {
+ /* If it's not being looked up, it's negative */
+ return -ENOENT;
}
/* do the open */
@@ -1956,10 +1959,18 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
return -EOPNOTSUPP;
+ /*
+ * Striped file layouts require that we copy partial objects, but the
+ * OSD copy-from operation only supports full-object copies. Limit
+ * this to non-striped file layouts for now.
+ */
if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) ||
- (src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) ||
- (src_ci->i_layout.object_size != dst_ci->i_layout.object_size))
+ (src_ci->i_layout.stripe_count != 1) ||
+ (dst_ci->i_layout.stripe_count != 1) ||
+ (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) {
+ dout("Invalid src/dst files layout\n");
return -EOPNOTSUPP;
+ }
if (len < src_ci->i_layout.object_size)
return -EOPNOTSUPP; /* no remote copy will be done */
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9f135624ae47..c07407586ce8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1434,6 +1434,7 @@ retry_lookup:
dout(" final dn %p\n", dn);
} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
req->r_op == CEPH_MDS_OP_MKSNAP) &&
+ test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
struct inode *dir = req->r_parent;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index edfd643a8205..b47f43fc2d68 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -268,6 +268,7 @@ static int parse_fsopt_token(char *c, void *private)
}
break;
case Opt_fscache_uniq:
+#ifdef CONFIG_CEPH_FSCACHE
kfree(fsopt->fscache_uniq);
fsopt->fscache_uniq = kstrndup(argstr[0].from,
argstr[0].to-argstr[0].from,
@@ -276,7 +277,10 @@ static int parse_fsopt_token(char *c, void *private)
return -ENOMEM;
fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
break;
- /* misc */
+#else
+ pr_err("fscache support is disabled\n");
+ return -EINVAL;
+#endif
case Opt_wsize:
if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE)
return -EINVAL;
@@ -353,10 +357,15 @@ static int parse_fsopt_token(char *c, void *private)
fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
break;
case Opt_fscache:
+#ifdef CONFIG_CEPH_FSCACHE
fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
kfree(fsopt->fscache_uniq);
fsopt->fscache_uniq = NULL;
break;
+#else
+ pr_err("fscache support is disabled\n");
+ return -EINVAL;
+#endif
case Opt_nofscache:
fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
kfree(fsopt->fscache_uniq);
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/smb2ops.c b/fs/cifs/smb2ops.c
index 4c0922596467..cd55af9b7cc5 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4084,6 +4084,7 @@ free_pages:
kfree(dw->ppages);
cifs_small_buf_release(dw->buf);
+ kfree(dw);
}
@@ -4157,7 +4158,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid,
dw->server = server;
dw->ppages = pages;
dw->len = len;
- queue_work(cifsiod_wq, &dw->decrypt);
+ queue_work(decrypt_wq, &dw->decrypt);
*num_mids = 0; /* worker thread takes care of finding mid */
return -1;
}
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index ea735d59c36e..0abfde6d0b05 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -838,6 +838,7 @@ struct create_durable_handle_reconnect_v2 {
struct create_context ccontext;
__u8 Name[8];
struct durable_reconnect_context_v2 dcontext;
+ __u8 Pad[4];
} __packed;
/* See MS-SMB2 2.2.13.2.5 */
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/configfs/symlink.c b/fs/configfs/symlink.c
index dc5dbf6a81d7..cb61467478ca 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -101,7 +101,7 @@ static int create_link(struct config_item *parent_item,
}
target_sd->s_links++;
spin_unlock(&configfs_dirent_lock);
- ret = configfs_get_target_path(item, item, body);
+ ret = configfs_get_target_path(parent_item, item, body);
if (!ret)
ret = configfs_create_link(target_sd, parent_item->ci_dentry,
dentry, body);
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/fs-writeback.c b/fs/fs-writeback.c
index 8461a6322039..335607b8c5c0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -576,10 +576,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
spin_unlock(&inode->i_lock);
/*
- * A dying wb indicates that the memcg-blkcg mapping has changed
- * and a new wb is already serving the memcg. Switch immediately.
+ * A dying wb indicates that either the blkcg associated with the
+ * memcg changed or the associated memcg is dying. In the first
+ * case, a replacement wb should already be available and we should
+ * refresh the wb immediately. In the second case, trying to
+ * refresh will keep failing.
*/
- if (unlikely(wb_dying(wbc->wb)))
+ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css)))
inode_switch_wbs(inode, wbc->wb_id);
}
EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode);
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 6419a2b3510d..3e8cebfb59b7 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -5,6 +5,7 @@
obj-$(CONFIG_FUSE_FS) += fuse.o
obj-$(CONFIG_CUSE) += cuse.o
-obj-$(CONFIG_VIRTIO_FS) += virtio_fs.o
+obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
+virtiofs-y += virtio_fs.o
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index dadd617d826c..ed1abc9e33cf 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -276,10 +276,12 @@ static void flush_bg_queue(struct fuse_conn *fc)
void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
{
struct fuse_iqueue *fiq = &fc->iq;
- bool async = req->args->end;
+ bool async;
if (test_and_set_bit(FR_FINISHED, &req->flags))
goto put_request;
+
+ async = req->args->end;
/*
* test_and_set_bit() implies smp_mb() between bit
* changing and below intr_entry check. Pairs with
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index d572c900bb0f..54d638f9ba1c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -405,7 +405,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
else
fuse_invalidate_entry_cache(entry);
- fuse_advise_use_readdirplus(dir);
+ if (inode)
+ fuse_advise_use_readdirplus(dir);
return newent;
out_iput:
@@ -1521,6 +1522,19 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
is_truncate = true;
}
+ /* Flush dirty data/metadata before non-truncate SETATTR */
+ if (is_wb && S_ISREG(inode->i_mode) &&
+ attr->ia_valid &
+ (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME_SET |
+ ATTR_TIMES_SET)) {
+ err = write_inode_now(inode, true);
+ if (err)
+ return err;
+
+ fuse_set_nowrite(inode);
+ fuse_release_nowrite(inode);
+ }
+
if (is_truncate) {
fuse_set_nowrite(inode);
set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 0f0225686aee..db48a5cf8620 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -217,7 +217,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
{
struct fuse_conn *fc = get_fuse_conn(inode);
int err;
- bool lock_inode = (file->f_flags & O_TRUNC) &&
+ bool is_wb_truncate = (file->f_flags & O_TRUNC) &&
fc->atomic_o_trunc &&
fc->writeback_cache;
@@ -225,16 +225,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
if (err)
return err;
- if (lock_inode)
+ if (is_wb_truncate) {
inode_lock(inode);
+ fuse_set_nowrite(inode);
+ }
err = fuse_do_open(fc, get_node_id(inode), file, isdir);
if (!err)
fuse_finish_open(inode, file);
- if (lock_inode)
+ if (is_wb_truncate) {
+ fuse_release_nowrite(inode);
inode_unlock(inode);
+ }
return err;
}
@@ -1997,7 +2001,7 @@ static int fuse_writepages_fill(struct page *page,
if (!data->ff) {
err = -EIO;
- data->ff = fuse_write_file_get(fc, get_fuse_inode(inode));
+ data->ff = fuse_write_file_get(fc, fi);
if (!data->ff)
goto out_unlock;
}
@@ -2042,8 +2046,6 @@ static int fuse_writepages_fill(struct page *page,
* under writeback, so we can release the page lock.
*/
if (data->wpa == NULL) {
- struct fuse_inode *fi = get_fuse_inode(inode);
-
err = -ENOMEM;
wpa = fuse_writepage_args_alloc();
if (!wpa) {
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 956aeaf961ae..d148188cfca4 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -479,6 +479,7 @@ struct fuse_fs_context {
bool destroy:1;
bool no_control:1;
bool no_force_umount:1;
+ bool no_mount_options:1;
unsigned int max_read;
unsigned int blksize;
const char *subtype;
@@ -713,6 +714,9 @@ struct fuse_conn {
/** Do not allow MNT_FORCE umount */
unsigned int no_force_umount:1;
+ /* Do not show mount options */
+ unsigned int no_mount_options:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e040e2a2b621..16aec32f7f3d 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -558,6 +558,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
struct super_block *sb = root->d_sb;
struct fuse_conn *fc = get_fuse_conn_super(sb);
+ if (fc->no_mount_options)
+ return 0;
+
seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id));
seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id));
if (fc->default_permissions)
@@ -1180,6 +1183,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
fc->destroy = ctx->destroy;
fc->no_control = ctx->no_control;
fc->no_force_umount = ctx->no_force_umount;
+ fc->no_mount_options = ctx->no_mount_options;
err = -ENOMEM;
root = fuse_get_root_inode(sb, ctx->rootmode);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 6af3f131e468..a5c86048b96e 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -30,6 +30,7 @@ struct virtio_fs_vq {
struct virtqueue *vq; /* protected by ->lock */
struct work_struct done_work;
struct list_head queued_reqs;
+ struct list_head end_reqs; /* End these requests */
struct delayed_work dispatch_work;
struct fuse_dev *fud;
bool connected;
@@ -54,6 +55,9 @@ struct virtio_fs_forget {
struct list_head list;
};
+static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
+ struct fuse_req *req, bool in_flight);
+
static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
{
struct virtio_fs *fs = vq->vdev->priv;
@@ -66,6 +70,19 @@ static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq)
return &vq_to_fsvq(vq)->fud->pq;
}
+/* Should be called with fsvq->lock held. */
+static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+ fsvq->in_flight++;
+}
+
+/* Should be called with fsvq->lock held. */
+static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+ WARN_ON(fsvq->in_flight <= 0);
+ fsvq->in_flight--;
+}
+
static void release_virtio_fs_obj(struct kref *ref)
{
struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);
@@ -109,22 +126,6 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
flush_delayed_work(&fsvq->dispatch_work);
}
-static inline void drain_hiprio_queued_reqs(struct virtio_fs_vq *fsvq)
-{
- struct virtio_fs_forget *forget;
-
- spin_lock(&fsvq->lock);
- while (1) {
- forget = list_first_entry_or_null(&fsvq->queued_reqs,
- struct virtio_fs_forget, list);
- if (!forget)
- break;
- list_del(&forget->list);
- kfree(forget);
- }
- spin_unlock(&fsvq->lock);
-}
-
static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
{
struct virtio_fs_vq *fsvq;
@@ -132,9 +133,6 @@ static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
for (i = 0; i < fs->nvqs; i++) {
fsvq = &fs->vqs[i];
- if (i == VQ_HIPRIO)
- drain_hiprio_queued_reqs(fsvq);
-
virtio_fs_drain_queue(fsvq);
}
}
@@ -253,14 +251,66 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work)
while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
kfree(req);
- fsvq->in_flight--;
+ dec_in_flight_req(fsvq);
}
} while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
spin_unlock(&fsvq->lock);
}
-static void virtio_fs_dummy_dispatch_work(struct work_struct *work)
+static void virtio_fs_request_dispatch_work(struct work_struct *work)
{
+ struct fuse_req *req;
+ struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
+ dispatch_work.work);
+ struct fuse_conn *fc = fsvq->fud->fc;
+ int ret;
+
+ pr_debug("virtio-fs: worker %s called.\n", __func__);
+ while (1) {
+ spin_lock(&fsvq->lock);
+ req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req,
+ list);
+ if (!req) {
+ spin_unlock(&fsvq->lock);
+ break;
+ }
+
+ list_del_init(&req->list);
+ spin_unlock(&fsvq->lock);
+ fuse_request_end(fc, req);
+ }
+
+ /* Dispatch pending requests */
+ while (1) {
+ spin_lock(&fsvq->lock);
+ req = list_first_entry_or_null(&fsvq->queued_reqs,
+ struct fuse_req, list);
+ if (!req) {
+ spin_unlock(&fsvq->lock);
+ return;
+ }
+ list_del_init(&req->list);
+ spin_unlock(&fsvq->lock);
+
+ ret = virtio_fs_enqueue_req(fsvq, req, true);
+ if (ret < 0) {
+ if (ret == -ENOMEM || ret == -ENOSPC) {
+ spin_lock(&fsvq->lock);
+ list_add_tail(&req->list, &fsvq->queued_reqs);
+ schedule_delayed_work(&fsvq->dispatch_work,
+ msecs_to_jiffies(1));
+ spin_unlock(&fsvq->lock);
+ return;
+ }
+ req->out.h.error = ret;
+ spin_lock(&fsvq->lock);
+ dec_in_flight_req(fsvq);
+ spin_unlock(&fsvq->lock);
+ pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n",
+ ret);
+ fuse_request_end(fc, req);
+ }
+ }
}
static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
@@ -286,6 +336,7 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
list_del(&forget->list);
if (!fsvq->connected) {
+ dec_in_flight_req(fsvq);
spin_unlock(&fsvq->lock);
kfree(forget);
continue;
@@ -307,13 +358,13 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
} else {
pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
ret);
+ dec_in_flight_req(fsvq);
kfree(forget);
}
spin_unlock(&fsvq->lock);
return;
}
- fsvq->in_flight++;
notify = virtqueue_kick_prepare(vq);
spin_unlock(&fsvq->lock);
@@ -452,7 +503,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
fuse_request_end(fc, req);
spin_lock(&fsvq->lock);
- fsvq->in_flight--;
+ dec_in_flight_req(fsvq);
spin_unlock(&fsvq->lock);
}
}
@@ -502,6 +553,7 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
names[VQ_HIPRIO] = fs->vqs[VQ_HIPRIO].name;
INIT_WORK(&fs->vqs[VQ_HIPRIO].done_work, virtio_fs_hiprio_done_work);
INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].queued_reqs);
+ INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].end_reqs);
INIT_DELAYED_WORK(&fs->vqs[VQ_HIPRIO].dispatch_work,
virtio_fs_hiprio_dispatch_work);
spin_lock_init(&fs->vqs[VQ_HIPRIO].lock);
@@ -511,8 +563,9 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
spin_lock_init(&fs->vqs[i].lock);
INIT_WORK(&fs->vqs[i].done_work, virtio_fs_requests_done_work);
INIT_DELAYED_WORK(&fs->vqs[i].dispatch_work,
- virtio_fs_dummy_dispatch_work);
+ virtio_fs_request_dispatch_work);
INIT_LIST_HEAD(&fs->vqs[i].queued_reqs);
+ INIT_LIST_HEAD(&fs->vqs[i].end_reqs);
snprintf(fs->vqs[i].name, sizeof(fs->vqs[i].name),
"requests.%u", i - VQ_REQUEST);
callbacks[i] = virtio_fs_vq_done;
@@ -708,6 +761,7 @@ __releases(fiq->lock)
list_add_tail(&forget->list, &fsvq->queued_reqs);
schedule_delayed_work(&fsvq->dispatch_work,
msecs_to_jiffies(1));
+ inc_in_flight_req(fsvq);
} else {
pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
ret);
@@ -717,7 +771,7 @@ __releases(fiq->lock)
goto out;
}
- fsvq->in_flight++;
+ inc_in_flight_req(fsvq);
notify = virtqueue_kick_prepare(vq);
spin_unlock(&fsvq->lock);
@@ -819,7 +873,7 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg,
/* Add a request to a virtqueue and kick the device */
static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
- struct fuse_req *req)
+ struct fuse_req *req, bool in_flight)
{
/* requests need at least 4 elements */
struct scatterlist *stack_sgs[6];
@@ -835,6 +889,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
unsigned int i;
int ret;
bool notify;
+ struct fuse_pqueue *fpq;
/* Does the sglist fit on the stack? */
total_sgs = sg_count_fuse_req(req);
@@ -889,7 +944,17 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
goto out;
}
- fsvq->in_flight++;
+ /* Request successfully sent. */
+ fpq = &fsvq->fud->pq;
+ spin_lock(&fpq->lock);
+ list_add_tail(&req->list, fpq->processing);
+ spin_unlock(&fpq->lock);
+ set_bit(FR_SENT, &req->flags);
+ /* matches barrier in request_wait_answer() */
+ smp_mb__after_atomic();
+
+ if (!in_flight)
+ inc_in_flight_req(fsvq);
notify = virtqueue_kick_prepare(vq);
spin_unlock(&fsvq->lock);
@@ -915,9 +980,8 @@ __releases(fiq->lock)
{
unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */
struct virtio_fs *fs;
- struct fuse_conn *fc;
struct fuse_req *req;
- struct fuse_pqueue *fpq;
+ struct virtio_fs_vq *fsvq;
int ret;
WARN_ON(list_empty(&fiq->pending));
@@ -928,44 +992,36 @@ __releases(fiq->lock)
spin_unlock(&fiq->lock);
fs = fiq->priv;
- fc = fs->vqs[queue_id].fud->fc;
pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n",
__func__, req->in.h.opcode, req->in.h.unique,
req->in.h.nodeid, req->in.h.len,
fuse_len_args(req->args->out_numargs, req->args->out_args));
- fpq = &fs->vqs[queue_id].fud->pq;
- spin_lock(&fpq->lock);
- if (!fpq->connected) {
- spin_unlock(&fpq->lock);
- req->out.h.error = -ENODEV;
- pr_err("virtio-fs: %s disconnected\n", __func__);
- fuse_request_end(fc, req);
- return;
- }
- list_add_tail(&req->list, fpq->processing);
- spin_unlock(&fpq->lock);
- set_bit(FR_SENT, &req->flags);
- /* matches barrier in request_wait_answer() */
- smp_mb__after_atomic();
-
-retry:
- ret = virtio_fs_enqueue_req(&fs->vqs[queue_id], req);
+ fsvq = &fs->vqs[queue_id];
+ ret = virtio_fs_enqueue_req(fsvq, req, false);
if (ret < 0) {
if (ret == -ENOMEM || ret == -ENOSPC) {
- /* Virtqueue full. Retry submission */
- /* TODO use completion instead of timeout */
- usleep_range(20, 30);
- goto retry;
+ /*
+ * Virtqueue full. Retry submission from worker
+ * context as we might be holding fc->bg_lock.
+ */
+ spin_lock(&fsvq->lock);
+ list_add_tail(&req->list, &fsvq->queued_reqs);
+ inc_in_flight_req(fsvq);
+ schedule_delayed_work(&fsvq->dispatch_work,
+ msecs_to_jiffies(1));
+ spin_unlock(&fsvq->lock);
+ return;
}
req->out.h.error = ret;
pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret);
- spin_lock(&fpq->lock);
- clear_bit(FR_SENT, &req->flags);
- list_del_init(&req->list);
- spin_unlock(&fpq->lock);
- fuse_request_end(fc, req);
+
+ /* Can't end request in submission context. Use a worker */
+ spin_lock(&fsvq->lock);
+ list_add_tail(&req->list, &fsvq->end_reqs);
+ schedule_delayed_work(&fsvq->dispatch_work, 0);
+ spin_unlock(&fsvq->lock);
return;
}
}
@@ -992,6 +1048,7 @@ static int virtio_fs_fill_super(struct super_block *sb)
.destroy = true,
.no_control = true,
.no_force_umount = true,
+ .no_mount_options = true,
};
mutex_lock(&virtio_fs_mutex);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 681b44682b0d..18daf494abab 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1540,17 +1540,23 @@ static int gfs2_init_fs_context(struct fs_context *fc)
{
struct gfs2_args *args;
- args = kzalloc(sizeof(*args), GFP_KERNEL);
+ args = kmalloc(sizeof(*args), GFP_KERNEL);
if (args == NULL)
return -ENOMEM;
- args->ar_quota = GFS2_QUOTA_DEFAULT;
- args->ar_data = GFS2_DATA_DEFAULT;
- args->ar_commit = 30;
- args->ar_statfs_quantum = 30;
- args->ar_quota_quantum = 60;
- args->ar_errors = GFS2_ERRORS_DEFAULT;
+ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ struct gfs2_sbd *sdp = fc->root->d_sb->s_fs_info;
+ *args = sdp->sd_args;
+ } else {
+ memset(args, 0, sizeof(*args));
+ args->ar_quota = GFS2_QUOTA_DEFAULT;
+ args->ar_data = GFS2_DATA_DEFAULT;
+ args->ar_commit = 30;
+ args->ar_statfs_quantum = 30;
+ args->ar_quota_quantum = 60;
+ args->ar_errors = GFS2_ERRORS_DEFAULT;
+ }
fc->fs_private = args;
fc->ops = &gfs2_context_ops;
return 0;
@@ -1600,6 +1606,7 @@ 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 67dbe0201e0d..f9a38998f2fc 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;
@@ -420,7 +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,
@@ -567,9 +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));
}
}
@@ -735,6 +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
*/
@@ -864,19 +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;
@@ -912,6 +914,21 @@ 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;
}
@@ -1107,6 +1124,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
kiocb->ki_flags |= IOCB_HIPRI;
kiocb->ki_complete = io_complete_rw_iopoll;
+ req->result = 0;
} else {
if (kiocb->ki_flags & IOCB_HIPRI)
return -EINVAL;
@@ -1877,7 +1895,7 @@ 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);
@@ -1885,6 +1903,15 @@ 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);
@@ -1903,6 +1930,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
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;
@@ -1951,9 +1979,17 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (ctx->cached_sq_head < nxt_sq_head)
tmp += UINT_MAX;
- if (tmp >= tmp_nxt)
+ 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);
@@ -2292,11 +2328,11 @@ 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);
+ ret = __io_submit_sqe(ctx, req, s, true);
/*
* We async punt it if the file wasn't marked NOWAIT, or if the file
@@ -2343,7 +2379,7 @@ 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;
@@ -2356,18 +2392,17 @@ 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
@@ -2379,6 +2414,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
if (ret) {
if (ret != -EIOCBQUEUED) {
io_free_req(req);
+ __io_free_req(shadow);
io_cqring_add_event(ctx, s->sqe->user_data, ret);
return 0;
}
@@ -2396,7 +2432,7 @@ 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;
}
@@ -2404,8 +2440,7 @@ 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;
@@ -2432,6 +2467,8 @@ 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
@@ -2458,7 +2495,7 @@ err:
INIT_LIST_HEAD(&req->link_list);
*link = req;
} else {
- io_queue_sqe(ctx, req, s, force_nonblock);
+ io_queue_sqe(ctx, req, s);
}
}
@@ -2538,12 +2575,13 @@ 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;
@@ -2557,19 +2595,23 @@ 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))
@@ -2577,24 +2619,24 @@ 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);
@@ -2603,7 +2645,6 @@ 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;
@@ -2618,14 +2659,27 @@ 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.
@@ -2639,7 +2693,8 @@ 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
@@ -2670,7 +2725,8 @@ 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;
@@ -2688,19 +2744,8 @@ 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);
@@ -2708,8 +2753,9 @@ 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);
@@ -2726,8 +2772,7 @@ 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;
@@ -2741,7 +2786,6 @@ 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))
@@ -2752,8 +2796,7 @@ 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;
}
@@ -2775,27 +2818,16 @@ 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;
}
@@ -3636,21 +3668,10 @@ 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) {
@@ -3809,10 +3830,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
if (ret)
goto err;
- ret = io_uring_get_fd(ctx);
- if (ret < 0)
- goto err;
-
memset(&p->sq_off, 0, sizeof(p->sq_off));
p->sq_off.head = offsetof(struct io_rings, sq.head);
p->sq_off.tail = offsetof(struct io_rings, sq.tail);
@@ -3830,6 +3847,14 @@ 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);
+ /*
+ * Install ring fd as the very last thing, so we don't risk someone
+ * having closed it before we finish setup
+ */
+ ret = io_uring_get_fd(ctx);
+ if (ret < 0)
+ goto err;
+
p->features = IORING_FEAT_SINGLE_MMAP;
return ret;
err:
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 071b90a45933..af549d70ec50 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -53,6 +53,16 @@ nfs4_is_valid_delegation(const struct nfs_delegation *delegation,
return false;
}
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode)
+{
+ struct nfs_delegation *delegation;
+
+ delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (nfs4_is_valid_delegation(delegation, 0))
+ return delegation;
+ return NULL;
+}
+
static int
nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
{
@@ -1181,7 +1191,7 @@ bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
if (delegation != NULL &&
nfs4_stateid_match_other(dst, &delegation->stateid)) {
dst->seqid = delegation->stateid.seqid;
- return ret;
+ ret = true;
}
rcu_read_unlock();
out:
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9eb87ae4c982..8b14d441e699 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -68,6 +68,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred);
bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode);
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
int nfs4_have_delegation(struct inode *inode, fmode_t flags);
int nfs4_check_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ab8ca20fd579..caacf5e7f5e1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1440,8 +1440,6 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode,
return 0;
if ((delegation->type & fmode) != fmode)
return 0;
- if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
- return 0;
switch (claim) {
case NFS4_OPEN_CLAIM_NULL:
case NFS4_OPEN_CLAIM_FH:
@@ -1810,7 +1808,6 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
{
struct nfs4_state *state = opendata->state;
- struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs_delegation *delegation;
int open_mode = opendata->o_arg.open_flags;
fmode_t fmode = opendata->o_arg.fmode;
@@ -1827,7 +1824,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
}
spin_unlock(&state->owner->so_lock);
rcu_read_lock();
- delegation = rcu_dereference(nfsi->delegation);
+ delegation = nfs4_get_valid_delegation(state->inode);
if (!can_open_delegated(delegation, fmode, claim)) {
rcu_read_unlock();
break;
@@ -2371,7 +2368,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
data->o_arg.open_flags, claim))
goto out_no_action;
rcu_read_lock();
- delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
+ delegation = nfs4_get_valid_delegation(data->state->inode);
if (can_open_delegated(delegation, data->o_arg.fmode, claim))
goto unlock_no_action;
rcu_read_unlock();
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 53939bf9d7d2..9876db52913a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2098,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
return 0;
}
-static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
- struct file *file,
- loff_t pos, size_t count,
- int *meta_level)
+static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
+ struct buffer_head **di_bh,
+ int meta_level,
+ int overwrite_io,
+ int write_sem,
+ int wait)
{
- int ret;
- struct buffer_head *di_bh = NULL;
- u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
- u32 clusters =
- ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+ int ret = 0;
- ret = ocfs2_inode_lock(inode, &di_bh, 1);
- if (ret) {
- mlog_errno(ret);
+ if (wait)
+ ret = ocfs2_inode_lock(inode, NULL, meta_level);
+ else
+ ret = ocfs2_try_inode_lock(inode,
+ overwrite_io ? NULL : di_bh, meta_level);
+ if (ret < 0)
goto out;
+
+ if (wait) {
+ if (write_sem)
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
+ else
+ down_read(&OCFS2_I(inode)->ip_alloc_sem);
+ } else {
+ if (write_sem)
+ ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+ else
+ ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+
+ if (!ret) {
+ ret = -EAGAIN;
+ goto out_unlock;
+ }
}
- *meta_level = 1;
+ return ret;
- ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
- if (ret)
- mlog_errno(ret);
+out_unlock:
+ brelse(*di_bh);
+ ocfs2_inode_unlock(inode, meta_level);
out:
- brelse(di_bh);
return ret;
}
+static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode,
+ struct buffer_head **di_bh,
+ int meta_level,
+ int write_sem)
+{
+ if (write_sem)
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
+ else
+ up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+ brelse(*di_bh);
+ *di_bh = NULL;
+
+ if (meta_level >= 0)
+ ocfs2_inode_unlock(inode, meta_level);
+}
+
static int ocfs2_prepare_inode_for_write(struct file *file,
loff_t pos, size_t count, int wait)
{
int ret = 0, meta_level = 0, overwrite_io = 0;
+ int write_sem = 0;
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = d_inode(dentry);
struct buffer_head *di_bh = NULL;
+ u32 cpos;
+ u32 clusters;
/*
* We start with a read level meta lock and only jump to an ex
* if we need to make modifications here.
*/
for(;;) {
- if (wait)
- ret = ocfs2_inode_lock(inode, NULL, meta_level);
- else
- ret = ocfs2_try_inode_lock(inode,
- overwrite_io ? NULL : &di_bh, meta_level);
+ ret = ocfs2_inode_lock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ overwrite_io,
+ write_sem,
+ wait);
if (ret < 0) {
- meta_level = -1;
if (ret != -EAGAIN)
mlog_errno(ret);
goto out;
@@ -2156,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
*/
if (!wait && !overwrite_io) {
overwrite_io = 1;
- if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
- ret = -EAGAIN;
- goto out_unlock;
- }
ret = ocfs2_overwrite_io(inode, di_bh, pos, count);
- brelse(di_bh);
- di_bh = NULL;
- up_read(&OCFS2_I(inode)->ip_alloc_sem);
if (ret < 0) {
if (ret != -EAGAIN)
mlog_errno(ret);
@@ -2183,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
* set inode->i_size at the end of a write. */
if (should_remove_suid(dentry)) {
if (meta_level == 0) {
- ocfs2_inode_unlock(inode, meta_level);
+ ocfs2_inode_unlock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ write_sem);
meta_level = 1;
continue;
}
@@ -2197,18 +2229,32 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
ret = ocfs2_check_range_for_refcount(inode, pos, count);
if (ret == 1) {
- ocfs2_inode_unlock(inode, meta_level);
- meta_level = -1;
-
- ret = ocfs2_prepare_inode_for_refcount(inode,
- file,
- pos,
- count,
- &meta_level);
+ ocfs2_inode_unlock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ write_sem);
+ ret = ocfs2_inode_lock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ overwrite_io,
+ 1,
+ wait);
+ write_sem = 1;
+ if (ret < 0) {
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
+ goto out;
+ }
+
+ cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+ clusters =
+ ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+ ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
}
if (ret < 0) {
- mlog_errno(ret);
+ if (ret != -EAGAIN)
+ mlog_errno(ret);
goto out_unlock;
}
@@ -2219,10 +2265,10 @@ out_unlock:
trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
pos, count, wait);
- brelse(di_bh);
-
- if (meta_level >= 0)
- ocfs2_inode_unlock(inode, meta_level);
+ ocfs2_inode_unlock_for_extent_tree(inode,
+ &di_bh,
+ meta_level,
+ write_sem);
out:
return ret;