aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig6
-rw-r--r--fs/block_dev.c18
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/ctree.h4
-rw-r--r--fs/btrfs/extent-tree.c123
-rw-r--r--fs/btrfs/file.c10
-rw-r--r--fs/btrfs/inode.c24
-rw-r--r--fs/btrfs/qgroup.c5
-rw-r--r--fs/btrfs/scrub.c62
-rw-r--r--fs/btrfs/tests/free-space-tests.c4
-rw-r--r--fs/btrfs/transaction.c32
-rw-r--r--fs/btrfs/transaction.h4
-rw-r--r--fs/btrfs/volumes.c13
-rw-r--r--fs/btrfs/volumes.h2
-rw-r--r--fs/cachefiles/rdwr.c2
-rw-r--r--fs/configfs/dir.c110
-rw-r--r--fs/dax.c4
-rw-r--r--fs/direct-io.c10
-rw-r--r--fs/dlm/lowcomms.c4
-rw-r--r--fs/ext2/super.c2
-rw-r--r--fs/ext4/super.c6
-rw-r--r--fs/fat/dir.c16
-rw-r--r--fs/hugetlbfs/inode.c65
-rw-r--r--fs/ncpfs/ioctl.c2
-rw-r--r--fs/nfs/callback_xdr.c7
-rw-r--r--fs/nfs/inode.c11
-rw-r--r--fs/nfs/nfs42proc.c3
-rw-r--r--fs/nfs/nfs4client.c2
-rw-r--r--fs/nfs/nfs4file.c59
-rw-r--r--fs/nfs/nfs4proc.c2
-rw-r--r--fs/nfs/nfs4xdr.c1
-rw-r--r--fs/nfs/pnfs.c56
-rw-r--r--fs/ocfs2/namei.c2
-rw-r--r--fs/splice.c8
-rw-r--r--fs/sysv/inode.c11
35 files changed, 508 insertions, 184 deletions
diff --git a/fs/Kconfig b/fs/Kconfig
index da3f32f1a4e4..6ce72d8d1ee1 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -46,6 +46,12 @@ config FS_DAX
or if unsure, say N. Saying Y will increase the size of the kernel
by about 5kB.
+config FS_DAX_PMD
+ bool
+ default FS_DAX
+ depends on FS_DAX
+ depends on BROKEN
+
endif # BLOCK
# Posix ACL utility routines
diff --git a/fs/block_dev.c b/fs/block_dev.c
index bb0dfb1c7af1..c25639e907bd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -390,9 +390,17 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
struct page *page)
{
const struct block_device_operations *ops = bdev->bd_disk->fops;
+ int result = -EOPNOTSUPP;
+
if (!ops->rw_page || bdev_get_integrity(bdev))
- return -EOPNOTSUPP;
- return ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+ return result;
+
+ result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL);
+ if (result)
+ return result;
+ result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, READ);
+ blk_queue_exit(bdev->bd_queue);
+ return result;
}
EXPORT_SYMBOL_GPL(bdev_read_page);
@@ -421,14 +429,20 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
int result;
int rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE;
const struct block_device_operations *ops = bdev->bd_disk->fops;
+
if (!ops->rw_page || bdev_get_integrity(bdev))
return -EOPNOTSUPP;
+ result = blk_queue_enter(bdev->bd_queue, GFP_KERNEL);
+ if (result)
+ return result;
+
set_page_writeback(page);
result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, rw);
if (result)
end_page_writeback(page);
else
unlock_page(page);
+ blk_queue_exit(bdev->bd_queue);
return result;
}
EXPORT_SYMBOL_GPL(bdev_write_page);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 6dcdb2ec9211..d453d62ab0c6 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -355,7 +355,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
index = srcu_read_lock(&fs_info->subvol_srcu);
- root = btrfs_read_fs_root_no_name(fs_info, &root_key);
+ root = btrfs_get_fs_root(fs_info, &root_key, false);
if (IS_ERR(root)) {
srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = PTR_ERR(root);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8c58191249cc..35489e7129a7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3416,6 +3416,7 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
struct btrfs_block_group_cache *btrfs_lookup_block_group(
struct btrfs_fs_info *info,
u64 bytenr);
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int get_block_group_index(struct btrfs_block_group_cache *cache);
struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
@@ -3479,6 +3480,9 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytes_used,
u64 type, u64 chunk_objectid, u64 chunk_offset,
u64 size);
+struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
+ struct btrfs_fs_info *fs_info,
+ const u64 chunk_offset);
int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 group_start,
struct extent_map *em);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index acf3ed11cfb6..4b89680a1923 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -124,7 +124,7 @@ static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
return (cache->flags & bits) == bits;
}
-static void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
{
atomic_inc(&cache->count);
}
@@ -5915,19 +5915,6 @@ static int update_block_group(struct btrfs_trans_handle *trans,
set_extent_dirty(info->pinned_extents,
bytenr, bytenr + num_bytes - 1,
GFP_NOFS | __GFP_NOFAIL);
- /*
- * No longer have used bytes in this block group, queue
- * it for deletion.
- */
- if (old_val == 0) {
- spin_lock(&info->unused_bgs_lock);
- if (list_empty(&cache->bg_list)) {
- btrfs_get_block_group(cache);
- list_add_tail(&cache->bg_list,
- &info->unused_bgs);
- }
- spin_unlock(&info->unused_bgs_lock);
- }
}
spin_lock(&trans->transaction->dirty_bgs_lock);
@@ -5939,6 +5926,22 @@ static int update_block_group(struct btrfs_trans_handle *trans,
}
spin_unlock(&trans->transaction->dirty_bgs_lock);
+ /*
+ * No longer have used bytes in this block group, queue it for
+ * deletion. We do this after adding the block group to the
+ * dirty list to avoid races between cleaner kthread and space
+ * cache writeout.
+ */
+ if (!alloc && old_val == 0) {
+ spin_lock(&info->unused_bgs_lock);
+ if (list_empty(&cache->bg_list)) {
+ btrfs_get_block_group(cache);
+ list_add_tail(&cache->bg_list,
+ &info->unused_bgs);
+ }
+ spin_unlock(&info->unused_bgs_lock);
+ }
+
btrfs_put_block_group(cache);
total -= num_bytes;
bytenr += num_bytes;
@@ -8105,21 +8108,47 @@ reada:
}
/*
- * TODO: Modify related function to add related node/leaf to dirty_extent_root,
- * for later qgroup accounting.
- *
- * Current, this function does nothing.
+ * These may not be seen by the usual inc/dec ref code so we have to
+ * add them here.
*/
+static int record_one_subtree_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 bytenr,
+ u64 num_bytes)
+{
+ struct btrfs_qgroup_extent_record *qrecord;
+ struct btrfs_delayed_ref_root *delayed_refs;
+
+ qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS);
+ if (!qrecord)
+ return -ENOMEM;
+
+ qrecord->bytenr = bytenr;
+ qrecord->num_bytes = num_bytes;
+ qrecord->old_roots = NULL;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+ spin_lock(&delayed_refs->lock);
+ if (btrfs_qgroup_insert_dirty_extent(delayed_refs, qrecord))
+ kfree(qrecord);
+ spin_unlock(&delayed_refs->lock);
+
+ return 0;
+}
+
static int account_leaf_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *eb)
{
int nr = btrfs_header_nritems(eb);
- int i, extent_type;
+ int i, extent_type, ret;
struct btrfs_key key;
struct btrfs_file_extent_item *fi;
u64 bytenr, num_bytes;
+ /* We can be called directly from walk_up_proc() */
+ if (!root->fs_info->quota_enabled)
+ return 0;
+
for (i = 0; i < nr; i++) {
btrfs_item_key_to_cpu(eb, &key, i);
@@ -8138,6 +8167,10 @@ static int account_leaf_items(struct btrfs_trans_handle *trans,
continue;
num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+
+ ret = record_one_subtree_extent(trans, root, bytenr, num_bytes);
+ if (ret)
+ return ret;
}
return 0;
}
@@ -8206,8 +8239,6 @@ static int adjust_slots_upwards(struct btrfs_root *root,
/*
* root_eb is the subtree root and is locked before this function is called.
- * TODO: Modify this function to mark all (including complete shared node)
- * to dirty_extent_root to allow it get accounted in qgroup.
*/
static int account_shared_subtree(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
@@ -8285,6 +8316,11 @@ walk_down:
btrfs_tree_read_lock(eb);
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+
+ ret = record_one_subtree_extent(trans, root, child_bytenr,
+ root->nodesize);
+ if (ret)
+ goto out;
}
if (level == 0) {
@@ -10256,6 +10292,47 @@ out:
return ret;
}
+struct btrfs_trans_handle *
+btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
+ const u64 chunk_offset)
+{
+ struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+ struct extent_map *em;
+ struct map_lookup *map;
+ unsigned int num_items;
+
+ read_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, chunk_offset, 1);
+ read_unlock(&em_tree->lock);
+ ASSERT(em && em->start == chunk_offset);
+
+ /*
+ * We need to reserve 3 + N units from the metadata space info in order
+ * to remove a block group (done at btrfs_remove_chunk() and at
+ * btrfs_remove_block_group()), which are used for:
+ *
+ * 1 unit for adding the free space inode's orphan (located in the tree
+ * of tree roots).
+ * 1 unit for deleting the block group item (located in the extent
+ * tree).
+ * 1 unit for deleting the free space item (located in tree of tree
+ * roots).
+ * N units for deleting N device extent items corresponding to each
+ * stripe (located in the device tree).
+ *
+ * In order to remove a block group we also need to reserve units in the
+ * system space info in order to update the chunk tree (update one or
+ * more device items and remove one chunk item), but this is done at
+ * btrfs_remove_chunk() through a call to check_system_chunk().
+ */
+ map = (struct map_lookup *)em->bdev;
+ num_items = 3 + map->num_stripes;
+ free_extent_map(em);
+
+ return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root,
+ num_items, 1);
+}
+
/*
* Process the unused_bgs list and remove any that don't have any allocated
* space inside of them.
@@ -10322,8 +10399,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
* Want to do this before we do anything else so we can recover
* properly if we fail to join the transaction.
*/
- /* 1 for btrfs_orphan_reserve_metadata() */
- trans = btrfs_start_transaction(root, 1);
+ trans = btrfs_start_trans_remove_block_group(fs_info,
+ block_group->key.objectid);
if (IS_ERR(trans)) {
btrfs_dec_block_group_ro(root, block_group);
ret = PTR_ERR(trans);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 977e715f0bf2..72e73461c064 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1882,8 +1882,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
struct btrfs_log_ctx ctx;
int ret = 0;
bool full_sync = 0;
- const u64 len = end - start + 1;
+ u64 len;
+ /*
+ * 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);
/*
@@ -2071,8 +2076,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
}
}
if (!full_sync) {
- ret = btrfs_wait_ordered_range(inode, start,
- end - start + 1);
+ ret = btrfs_wait_ordered_range(inode, start, len);
if (ret) {
btrfs_end_transaction(trans, root);
goto out;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 994490d5fa64..a70c5790f8f5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4046,9 +4046,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
*/
static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
{
- struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
- int ret;
/*
* 1 for the possible orphan item
@@ -4057,27 +4055,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
* 1 for the inode ref
* 1 for the inode
*/
- trans = btrfs_start_transaction(root, 5);
- if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
- return trans;
-
- if (PTR_ERR(trans) == -ENOSPC) {
- u64 num_bytes = btrfs_calc_trans_metadata_size(root, 5);
-
- trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
- return trans;
- ret = btrfs_cond_migrate_bytes(root->fs_info,
- &root->fs_info->trans_block_rsv,
- num_bytes, 5);
- if (ret) {
- btrfs_end_transaction(trans, root);
- return ERR_PTR(ret);
- }
- trans->block_rsv = &root->fs_info->trans_block_rsv;
- trans->bytes_reserved = num_bytes;
- }
- return trans;
+ return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
}
static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 93e12c18ffd7..5279fdae7142 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -993,9 +993,10 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root)
goto out;
- spin_lock(&fs_info->qgroup_lock);
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
+ btrfs_qgroup_wait_for_completion(fs_info);
+ spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
@@ -1461,6 +1462,8 @@ struct btrfs_qgroup_extent_record
struct btrfs_qgroup_extent_record *entry;
u64 bytenr = record->bytenr;
+ assert_spin_locked(&delayed_refs->lock);
+
while (*p) {
parent_node = *p;
entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 2907a77fb1f6..b091d94ceef6 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3432,7 +3432,9 @@ out:
static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
struct btrfs_device *scrub_dev,
u64 chunk_offset, u64 length,
- u64 dev_offset, int is_dev_replace)
+ u64 dev_offset,
+ struct btrfs_block_group_cache *cache,
+ int is_dev_replace)
{
struct btrfs_mapping_tree *map_tree =
&sctx->dev_root->fs_info->mapping_tree;
@@ -3445,8 +3447,18 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1);
read_unlock(&map_tree->map_tree.lock);
- if (!em)
- return -EINVAL;
+ if (!em) {
+ /*
+ * Might have been an unused block group deleted by the cleaner
+ * kthread or relocation.
+ */
+ spin_lock(&cache->lock);
+ if (!cache->removed)
+ ret = -EINVAL;
+ spin_unlock(&cache->lock);
+
+ return ret;
+ }
map = (struct map_lookup *)em->bdev;
if (em->start != chunk_offset)
@@ -3483,6 +3495,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
u64 length;
u64 chunk_offset;
int ret = 0;
+ int ro_set;
int slot;
struct extent_buffer *l;
struct btrfs_key key;
@@ -3568,7 +3581,21 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
scrub_pause_on(fs_info);
ret = btrfs_inc_block_group_ro(root, cache);
scrub_pause_off(fs_info);
- if (ret) {
+
+ if (ret == 0) {
+ ro_set = 1;
+ } else if (ret == -ENOSPC) {
+ /*
+ * btrfs_inc_block_group_ro return -ENOSPC when it
+ * failed in creating new chunk for metadata.
+ * It is not a problem for scrub/replace, because
+ * metadata are always cowed, and our scrub paused
+ * commit_transactions.
+ */
+ ro_set = 0;
+ } else {
+ btrfs_warn(fs_info, "failed setting block group ro, ret=%d\n",
+ ret);
btrfs_put_block_group(cache);
break;
}
@@ -3577,7 +3604,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
dev_replace->cursor_left = found_key.offset;
dev_replace->item_needs_writeback = 1;
ret = scrub_chunk(sctx, scrub_dev, chunk_offset, length,
- found_key.offset, is_dev_replace);
+ found_key.offset, cache, is_dev_replace);
/*
* flush, submit all pending read and write bios, afterwards
@@ -3611,7 +3638,30 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
scrub_pause_off(fs_info);
- btrfs_dec_block_group_ro(root, cache);
+ if (ro_set)
+ btrfs_dec_block_group_ro(root, cache);
+
+ /*
+ * We might have prevented the cleaner kthread from deleting
+ * this block group if it was already unused because we raced
+ * and set it to RO mode first. So add it back to the unused
+ * list, otherwise it might not ever be deleted unless a manual
+ * balance is triggered or it becomes used and unused again.
+ */
+ spin_lock(&cache->lock);
+ if (!cache->removed && !cache->ro && cache->reserved == 0 &&
+ btrfs_block_group_used(&cache->item) == 0) {
+ spin_unlock(&cache->lock);
+ spin_lock(&fs_info->unused_bgs_lock);
+ if (list_empty(&cache->bg_list)) {
+ btrfs_get_block_group(cache);
+ list_add_tail(&cache->bg_list,
+ &fs_info->unused_bgs);
+ }
+ spin_unlock(&fs_info->unused_bgs_lock);
+ } else {
+ spin_unlock(&cache->lock);
+ }
btrfs_put_block_group(cache);
if (ret)
diff --git a/fs/btrfs/tests/free-space-tests.c b/fs/btrfs/tests/free-space-tests.c
index c8c3d70c31ff..8b72b005bfb9 100644
--- a/fs/btrfs/tests/free-space-tests.c
+++ b/fs/btrfs/tests/free-space-tests.c
@@ -898,8 +898,10 @@ int btrfs_test_free_space_cache(void)
}
root = btrfs_alloc_dummy_root();
- if (!root)
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
goto out;
+ }
root->fs_info = btrfs_alloc_dummy_fs_info();
if (!root->fs_info)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 418c6a2ad7d8..3367a3c6f214 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -592,6 +592,38 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
return start_transaction(root, num_items, TRANS_START,
BTRFS_RESERVE_FLUSH_ALL);
}
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+ struct btrfs_root *root,
+ unsigned int num_items,
+ int min_factor)
+{
+ struct btrfs_trans_handle *trans;
+ u64 num_bytes;
+ int ret;
+
+ trans = btrfs_start_transaction(root, num_items);
+ if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
+ return trans;
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return trans;
+
+ num_bytes = btrfs_calc_trans_metadata_size(root, num_items);
+ ret = btrfs_cond_migrate_bytes(root->fs_info,
+ &root->fs_info->trans_block_rsv,
+ num_bytes,
+ min_factor);
+ if (ret) {
+ btrfs_end_transaction(trans, root);
+ return ERR_PTR(ret);
+ }
+
+ trans->block_rsv = &root->fs_info->trans_block_rsv;
+ trans->bytes_reserved = num_bytes;
+
+ return trans;
+}
struct btrfs_trans_handle *btrfs_start_transaction_lflush(
struct btrfs_root *root,
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index b05b2f64d913..0da21ca9b3fb 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -185,6 +185,10 @@ int btrfs_end_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
unsigned int num_items);
+struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
+ struct btrfs_root *root,
+ unsigned int num_items,
+ int min_factor);
struct btrfs_trans_handle *btrfs_start_transaction_lflush(
struct btrfs_root *root,
unsigned int num_items);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a6df8fdc1312..456452206609 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1973,8 +1973,7 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
if (srcdev->writeable) {
fs_devices->rw_devices--;
/* zero out the old super if it is writable */
- btrfs_scratch_superblocks(srcdev->bdev,
- rcu_str_deref(srcdev->name));
+ btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
}
if (srcdev->bdev)
@@ -2024,8 +2023,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
btrfs_sysfs_rm_device_link(fs_info->fs_devices, tgtdev);
if (tgtdev->bdev) {
- btrfs_scratch_superblocks(tgtdev->bdev,
- rcu_str_deref(tgtdev->name));
+ btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
fs_info->fs_devices->open_devices--;
}
fs_info->fs_devices->num_devices--;
@@ -2853,7 +2851,8 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, u64 chunk_offset)
if (ret)
return ret;
- trans = btrfs_start_transaction(root, 0);
+ trans = btrfs_start_trans_remove_block_group(root->fs_info,
+ chunk_offset);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_std_error(root->fs_info, ret, NULL);
@@ -3123,7 +3122,7 @@ static int chunk_profiles_filter(u64 chunk_type,
return 1;
}
-static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
+static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
struct btrfs_balance_args *bargs)
{
struct btrfs_block_group_cache *cache;
@@ -3156,7 +3155,7 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset,
return ret;
}
-static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info,
+static int chunk_usage_filter(struct btrfs_fs_info *fs_info,
u64 chunk_offset, struct btrfs_balance_args *bargs)
{
struct btrfs_block_group_cache *cache;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ec5712372732..d5c84f6b1353 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -382,7 +382,7 @@ struct map_lookup {
#define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5)
#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6)
#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7)
-#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 8)
+#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 10)
#define BTRFS_BALANCE_ARGS_MASK \
(BTRFS_BALANCE_ARGS_PROFILES | \
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 7a6b02f72787..c0f3da3926a0 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -879,7 +879,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
loff_t pos, eof;
size_t len;
void *data;
- int ret;
+ int ret = -ENOBUFS;
ASSERT(op != NULL);
ASSERT(page != NULL);
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index c81ce7f200a6..a7a1b218f308 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1636,6 +1636,116 @@ const struct file_operations configfs_dir_operations = {
.iterate = configfs_readdir,
};
+/**
+ * configfs_register_group - creates a parent-child relation between two groups
+ * @parent_group: parent group
+ * @group: child group
+ *
+ * link groups, creates dentry for the child and attaches it to the
+ * parent dentry.
+ *
+ * Return: 0 on success, negative errno code on error
+ */
+int configfs_register_group(struct config_group *parent_group,
+ struct config_group *group)
+{
+ struct configfs_subsystem *subsys = parent_group->cg_subsys;
+ struct dentry *parent;
+ int ret;
+
+ mutex_lock(&subsys->su_mutex);
+ link_group(parent_group, group);
+ mutex_unlock(&subsys->su_mutex);
+
+ parent = parent_group->cg_item.ci_dentry;
+
+ mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT);
+ ret = create_default_group(parent_group, group);
+ if (!ret) {
+ spin_lock(&configfs_dirent_lock);
+ configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata);
+ spin_unlock(&configfs_dirent_lock);
+ }
+ mutex_unlock(&d_inode(parent)->i_mutex);
+ return ret;
+}
+EXPORT_SYMBOL(configfs_register_group);
+
+/**
+ * configfs_unregister_group() - unregisters a child group from its parent
+ * @group: parent group to be unregistered
+ *
+ * Undoes configfs_register_group()
+ */
+void configfs_unregister_group(struct config_group *group)
+{
+ struct configfs_subsystem *subsys = group->cg_subsys;
+ struct dentry *dentry = group->cg_item.ci_dentry;
+ struct dentry *parent = group->cg_item.ci_parent->ci_dentry;
+
+ mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT);
+ spin_lock(&configfs_dirent_lock);
+ configfs_detach_prep(dentry, NULL);
+ spin_unlock(&configfs_dirent_lock);
+
+ configfs_detach_group(&group->cg_item);
+ d_inode(dentry)->i_flags |= S_DEAD;
+ dont_mount(dentry);
+ d_delete(dentry);
+ mutex_unlock(&d_inode(parent)->i_mutex);
+
+ dput(dentry);
+
+ mutex_lock(&subsys->su_mutex);
+ unlink_group(group);
+ mutex_unlock(&subsys->su_mutex);
+}
+EXPORT_SYMBOL(configfs_unregister_group);
+
+/**
+ * configfs_register_default_group() - allocates and registers a child group
+ * @parent_group: parent group
+ * @name: child group name
+ * @item_type: child item type description
+ *
+ * boilerplate to allocate and register a child group with its parent. We need
+ * kzalloc'ed memory because child's default_group is initially empty.
+ *
+ * Return: allocated config group or ERR_PTR() on error
+ */
+struct config_group *
+configfs_register_default_group(struct config_group *parent_group,
+ const char *name,
+ struct config_item_type *item_type)
+{
+ int ret;
+ struct config_group *group;
+
+ group = kzalloc(sizeof(*group), GFP_KERNEL);
+ if (!group)
+ return ERR_PTR(-ENOMEM);
+ config_group_init_type_name(group, name, item_type);
+
+ ret = configfs_register_group(parent_group, group);
+ if (ret) {
+ kfree(group);
+ return ERR_PTR(ret);
+ }
+ return group;
+}
+EXPORT_SYMBOL(configfs_register_default_group);
+
+/**
+ * configfs_unregister_default_group() - unregisters and frees a child group
+ * @group: the group to act on
+ */
+void configfs_unregister_default_group(struct config_group *group)
+{
+ configfs_unregister_group(group);
+ kfree(group);
+}
+EXPORT_SYMBOL(configfs_unregister_default_group);
+
int configfs_register_subsystem(struct configfs_subsystem *subsys)
{
int err;
diff --git a/fs/dax.c b/fs/dax.c
index d1e5cb7311a1..43671b68220e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -541,6 +541,10 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
unsigned long pfn;
int result = 0;
+ /* dax pmd mappings are broken wrt gup and fork */
+ if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+ return VM_FAULT_FALLBACK;
+
/* Fall back to PTEs if we're going to COW */
if (write && !(vma->vm_flags & VM_SHARED))
return VM_FAULT_FALLBACK;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index cb5337d8c273..1c75a3a07f8f 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1169,6 +1169,15 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
}
}
+ /* Once we sampled i_size check for reads beyond EOF */
+ dio->i_size = i_size_read(inode);
+ if (iov_iter_rw(iter) == READ && offset >= dio->i_size) {
+ if (dio->flags & DIO_LOCKING)
+ mutex_unlock(&inode->i_mutex);
+ kmem_cache_free(dio_cache, dio);
+ goto out;
+ }
+
/*
* For file extending writes updating i_size before data writeouts
* complete can expose uninitialized blocks in dumb filesystems.
@@ -1222,7 +1231,6 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
sdio.next_block_for_io = -1;
dio->iocb = iocb;
- dio->i_size = i_size_read(inode);
spin_lock_init(&dio->bio_lock);
dio->refcount = 1;
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 87e9d796cf7d..3a37bd3f9637 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -421,7 +421,7 @@ static void lowcomms_write_space(struct sock *sk)
if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) {
con->sock->sk->sk_write_pending--;
- clear_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags);
+ clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags);
}
if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
@@ -1448,7 +1448,7 @@ static void send_to_sock(struct connection *con)
msg_flags);
if (ret == -EAGAIN || ret == 0) {
if (ret == -EAGAIN &&
- test_bit(SOCK_ASYNC_NOSPACE, &con->sock->flags) &&
+ test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) &&
!test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
/* Notify TCP that we're limited by the
* application window size.
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 3a71cea68420..748d35afc902 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -569,6 +569,8 @@ static int parse_options(char *options, struct super_block *sb)
/* Fall through */
case Opt_dax:
#ifdef CONFIG_FS_DAX
+ ext2_msg(sb, KERN_WARNING,
+ "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
set_opt(sbi->s_mount_opt, DAX);
#else
ext2_msg(sb, KERN_INFO, "dax option not supported");
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 753f4e68b820..c9ab67da6e5a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1664,8 +1664,12 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
}
sbi->s_jquota_fmt = m->mount_opt;
#endif
-#ifndef CONFIG_FS_DAX
} else if (token == Opt_dax) {
+#ifdef CONFIG_FS_DAX
+ ext4_msg(sb, KERN_WARNING,
+ "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+ sbi->s_mount_opt |= m->mount_opt;
+#else
ext4_msg(sb, KERN_INFO, "dax option not supported");
return -1;
#endif
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 4afc4d9d2e41..8b2127ffb226 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -610,9 +610,9 @@ parse_record:
int status = fat_parse_long(inode, &cpos, &bh, &de,
&unicode, &nr_slots);
if (status < 0) {
- ctx->pos = cpos;
+ bh = NULL;
ret = status;
- goto out;
+ goto end_of_dir;
} else if (status == PARSE_INVALID)
goto record_end;
else if (status == PARSE_NOT_LONGNAME)
@@ -654,8 +654,9 @@ parse_record:
fill_len = short_len;
start_filldir:
- if (!fake_offset)
- ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry);
+ ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry);
+ if (fake_offset && ctx->pos < 2)
+ ctx->pos = 2;
if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) {
if (!dir_emit_dot(file, ctx))
@@ -681,14 +682,19 @@ record_end:
fake_offset = 0;
ctx->pos = cpos;
goto get_new;
+
end_of_dir:
- ctx->pos = cpos;
+ if (fake_offset && cpos < 2)
+ ctx->pos = 2;
+ else
+ ctx->pos = cpos;
fill_failed:
brelse(bh);
if (unicode)
__putname(unicode);
out:
mutex_unlock(&sbi->s_lock);
+
return ret;
}
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 316adb968b65..de4bdfac0cec 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -332,12 +332,17 @@ static void remove_huge_page(struct page *page)
* truncation is indicated by end of range being LLONG_MAX
* In this case, we first scan the range and release found pages.
* After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
- * maps and global counts.
+ * maps and global counts. Page faults can not race with truncation
+ * in this routine. hugetlb_no_page() prevents page faults in the
+ * truncated range. It checks i_size before allocation, and again after
+ * with the page table lock for the page held. The same lock must be
+ * acquired to unmap a page.
* hole punch is indicated if end is not LLONG_MAX
* In the hole punch case we scan the range and release found pages.
* Only when releasing a page is the associated region/reserv map
* deleted. The region/reserv map for ranges without associated
- * pages are not modified.
+ * pages are not modified. Page faults can race with hole punch.
+ * This is indicated if we find a mapped page.
* Note: If the passed end of range value is beyond the end of file, but
* not LLONG_MAX this routine still performs a hole punch operation.
*/
@@ -361,46 +366,37 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
next = start;
while (next < end) {
/*
- * Make sure to never grab more pages that we
- * might possibly need.
+ * Don't grab more pages than the number left in the range.
*/
if (end - next < lookup_nr)
lookup_nr = end - next;
/*
- * This pagevec_lookup() may return pages past 'end',
- * so we must check for page->index > end.
+ * When no more pages are found, we are done.
*/
- if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) {
- if (next == start)
- break;
- next = start;
- continue;
- }
+ if (!pagevec_lookup(&pvec, mapping, next, lookup_nr))
+ break;
for (i = 0; i < pagevec_count(&pvec); ++i) {
struct page *page = pvec.pages[i];
u32 hash;
+ /*
+ * The page (index) could be beyond end. This is
+ * only possible in the punch hole case as end is
+ * max page offset in the truncate case.
+ */
+ next = page->index;
+ if (next >= end)
+ break;
+
hash = hugetlb_fault_mutex_hash(h, current->mm,
&pseudo_vma,
mapping, next, 0);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
lock_page(page);
- if (page->index >= end) {
- unlock_page(page);
- mutex_unlock(&hugetlb_fault_mutex_table[hash]);
- next = end; /* we are done */
- break;
- }
-
- /*
- * If page is mapped, it was faulted in after being
- * unmapped. Do nothing in this race case. In the
- * normal case page is not mapped.
- */
- if (!page_mapped(page)) {
+ if (likely(!page_mapped(page))) {
bool rsv_on_error = !PagePrivate(page);
/*
* We must free the huge page and remove
@@ -421,17 +417,23 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
hugetlb_fix_reserve_counts(
inode, rsv_on_error);
}
+ } else {
+ /*
+ * If page is mapped, it was faulted in after
+ * being unmapped. It indicates a race between
+ * hole punch and page fault. Do nothing in
+ * this case. Getting here in a truncate
+ * operation is a bug.
+ */
+ BUG_ON(truncate_op);
}
- if (page->index > next)
- next = page->index;
-
- ++next;
unlock_page(page);
-
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
}
+ ++next;
huge_pagevec_release(&pvec);
+ cond_resched();
}
if (truncate_op)
@@ -647,9 +649,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
i_size_write(inode, offset + len);
inode->i_ctime = CURRENT_TIME;
- spin_lock(&inode->i_lock);
- inode->i_private = NULL;
- spin_unlock(&inode->i_lock);
out:
mutex_unlock(&inode->i_mutex);
return error;
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 79b113048eac..0a3f9b594602 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -525,6 +525,8 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
switch (rqdata.cmd) {
case NCP_LOCK_EX:
case NCP_LOCK_SH:
+ if (rqdata.timeout < 0)
+ return -EINVAL;
if (rqdata.timeout == 0)
rqdata.timeout = NCP_LOCK_DEFAULT_TIMEOUT;
else if (rqdata.timeout > NCP_LOCK_MAX_TIMEOUT)
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 646cdac73488..beac58b0e09c 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -78,7 +78,8 @@ static __be32 *read_buf(struct xdr_stream *xdr, int nbytes)
p = xdr_inline_decode(xdr, nbytes);
if (unlikely(p == NULL))
- printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed!\n");
+ printk(KERN_WARNING "NFS: NFSv4 callback reply buffer overflowed "
+ "or truncated request.\n");
return p;
}
@@ -889,6 +890,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
struct cb_compound_hdr_arg hdr_arg = { 0 };
struct cb_compound_hdr_res hdr_res = { NULL };
struct xdr_stream xdr_in, xdr_out;
+ struct xdr_buf *rq_arg = &rqstp->rq_arg;
__be32 *p, status;
struct cb_process_state cps = {
.drc_status = 0,
@@ -900,7 +902,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
dprintk("%s: start\n", __func__);
- xdr_init_decode(&xdr_in, &rqstp->rq_arg, rqstp->rq_arg.head[0].iov_base);
+ rq_arg->len = rq_arg->head[0].iov_len + rq_arg->page_len;
+ xdr_init_decode(&xdr_in, rq_arg, rq_arg->head[0].iov_base);
p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len);
xdr_init_encode(&xdr_out, &rqstp->rq_res, p);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 326d9e10d833..31b0a52223a7 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -618,7 +618,10 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
nfs_vmtruncate(inode, attr->ia_size);
}
- nfs_update_inode(inode, fattr);
+ if (fattr->valid)
+ nfs_update_inode(inode, fattr);
+ else
+ NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR;
spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
@@ -1824,7 +1827,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
if ((long)fattr->gencount - (long)nfsi->attr_gencount > 0)
nfsi->attr_gencount = fattr->gencount;
}
- invalid &= ~NFS_INO_INVALID_ATTR;
+
+ /* Don't declare attrcache up to date if there were no attrs! */
+ if (fattr->valid != 0)
+ invalid &= ~NFS_INO_INVALID_ATTR;
+
/* Don't invalidate the data if we were to blame */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
|| S_ISLNK(inode->i_mode)))
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 3e92a3cde15d..6b1ce9825430 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -14,7 +14,7 @@
#include "pnfs.h"
#include "internal.h"
-#define NFSDBG_FACILITY NFSDBG_PNFS
+#define NFSDBG_FACILITY NFSDBG_PROC
static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file,
fmode_t fmode)
@@ -284,6 +284,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
.dst_fh = NFS_FH(dst_inode),
.src_offset = src_offset,
.dst_offset = dst_offset,
+ .count = count,
.dst_bitmask = server->cache_consistency_bitmask,
};
struct nfs42_clone_res res = {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 223bedda64ae..10410e8b5853 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -33,7 +33,7 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
return ret;
idr_preload(GFP_KERNEL);
spin_lock(&nn->nfs_client_lock);
- ret = idr_alloc(&nn->cb_ident_idr, clp, 0, 0, GFP_NOWAIT);
+ ret = idr_alloc(&nn->cb_ident_idr, clp, 1, 0, GFP_NOWAIT);
if (ret >= 0)
clp->cl_cb_ident = ret;
spin_unlock(&nn->nfs_client_lock);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 4aa571956cd6..db9b5fea5b3e 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -7,6 +7,7 @@
#include <linux/file.h>
#include <linux/falloc.h>
#include <linux/nfs_fs.h>
+#include <uapi/linux/btrfs.h> /* BTRFS_IOC_CLONE/BTRFS_IOC_CLONE_RANGE */
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
@@ -203,6 +204,7 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
struct fd src_file;
struct inode *src_inode;
unsigned int bs = server->clone_blksize;
+ bool same_inode = false;
int ret;
/* dst file must be opened for writing */
@@ -221,10 +223,8 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
src_inode = file_inode(src_file.file);
- /* src and dst must be different files */
- ret = -EINVAL;
if (src_inode == dst_inode)
- goto out_fput;
+ same_inode = true;
/* src file must be opened for reading */
if (!(src_file.file->f_mode & FMODE_READ))
@@ -249,8 +249,16 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
goto out_fput;
}
+ /* verify if ranges are overlapped within the same file */
+ if (same_inode) {
+ if (dst_off + count > src_off && dst_off < src_off + count)
+ goto out_fput;
+ }
+
/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
- if (dst_inode < src_inode) {
+ if (same_inode) {
+ mutex_lock(&src_inode->i_mutex);
+ } else if (dst_inode < src_inode) {
mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD);
} else {
@@ -275,7 +283,9 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
out_unlock:
- if (dst_inode < src_inode) {
+ if (same_inode) {
+ mutex_unlock(&src_inode->i_mutex);
+ } else if (dst_inode < src_inode) {
mutex_unlock(&src_inode->i_mutex);
mutex_unlock(&dst_inode->i_mutex);
} else {
@@ -291,46 +301,31 @@ out_drop_write:
static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
{
- struct nfs_ioctl_clone_range_args args;
+ struct btrfs_ioctl_clone_range_args args;
if (copy_from_user(&args, argp, sizeof(args)))
return -EFAULT;
- return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_off, args.dst_off, args.count);
-}
-#else
-static long nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
- u64 src_off, u64 dst_off, u64 count)
-{
- return -ENOTTY;
-}
-
-static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
-{
- return -ENOTTY;
+ return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_offset,
+ args.dest_offset, args.src_length);
}
-#endif /* CONFIG_NFS_V4_2 */
long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
switch (cmd) {
- case NFS_IOC_CLONE:
+ case BTRFS_IOC_CLONE:
return nfs42_ioctl_clone(file, arg, 0, 0, 0);
- case NFS_IOC_CLONE_RANGE:
+ case BTRFS_IOC_CLONE_RANGE:
return nfs42_ioctl_clone_range(file, argp);
}
return -ENOTTY;
}
+#endif /* CONFIG_NFS_V4_2 */
const struct file_operations nfs4_file_operations = {
-#ifdef CONFIG_NFS_V4_2
- .llseek = nfs4_file_llseek,
-#else
- .llseek = nfs_file_llseek,
-#endif
.read_iter = nfs_file_read,
.write_iter = nfs_file_write,
.mmap = nfs_file_mmap,
@@ -342,14 +337,14 @@ const struct file_operations nfs4_file_operations = {
.flock = nfs_flock,
.splice_read = nfs_file_splice_read,
.splice_write = iter_file_splice_write,
-#ifdef CONFIG_NFS_V4_2
- .fallocate = nfs42_fallocate,
-#endif /* CONFIG_NFS_V4_2 */
.check_flags = nfs_check_flags,
.setlease = simple_nosetlease,
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_NFS_V4_2
+ .llseek = nfs4_file_llseek,
+ .fallocate = nfs42_fallocate,
.unlocked_ioctl = nfs4_ioctl,
-#else
.compat_ioctl = nfs4_ioctl,
-#endif /* CONFIG_COMPAT */
+#else
+ .llseek = nfs_file_llseek,
+#endif
};
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 765a03559363..89818036f035 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7866,7 +7866,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
spin_unlock(&inode->i_lock);
goto out_restart;
}
- if (nfs4_async_handle_error(task, server, state, NULL) == -EAGAIN)
+ if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN)
goto out_restart;
out:
dprintk("<-- %s\n", __func__);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index dfed4f5c8fcc..4e4441216804 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3615,6 +3615,7 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
status = 0;
if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS)))
goto out;
+ bitmap[0] &= ~FATTR4_WORD0_FS_LOCATIONS;
status = -EIO;
/* Ignore borken servers that return unrequested attrs */
if (unlikely(res == NULL))
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 93496c059837..5a8ae2125b50 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -872,33 +872,38 @@ send_layoutget(struct pnfs_layout_hdr *lo,
dprintk("--> %s\n", __func__);
- lgp = kzalloc(sizeof(*lgp), gfp_flags);
- if (lgp == NULL)
- return NULL;
+ /*
+ * Synchronously retrieve layout information from server and
+ * store in lseg. If we race with a concurrent seqid morphing
+ * op, then re-send the LAYOUTGET.
+ */
+ do {
+ lgp = kzalloc(sizeof(*lgp), gfp_flags);
+ if (lgp == NULL)
+ return NULL;
+
+ i_size = i_size_read(ino);
+
+ lgp->args.minlength = PAGE_CACHE_SIZE;
+ if (lgp->args.minlength > range->length)
+ lgp->args.minlength = range->length;
+ if (range->iomode == IOMODE_READ) {
+ if (range->offset >= i_size)
+ lgp->args.minlength = 0;
+ else if (i_size - range->offset < lgp->args.minlength)
+ lgp->args.minlength = i_size - range->offset;
+ }
+ lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
+ lgp->args.range = *range;
+ lgp->args.type = server->pnfs_curr_ld->id;
+ lgp->args.inode = ino;
+ lgp->args.ctx = get_nfs_open_context(ctx);
+ lgp->gfp_flags = gfp_flags;
+ lgp->cred = lo->plh_lc_cred;
- i_size = i_size_read(ino);
+ lseg = nfs4_proc_layoutget(lgp, gfp_flags);
+ } while (lseg == ERR_PTR(-EAGAIN));
- lgp->args.minlength = PAGE_CACHE_SIZE;
- if (lgp->args.minlength > range->length)
- lgp->args.minlength = range->length;
- if (range->iomode == IOMODE_READ) {
- if (range->offset >= i_size)
- lgp->args.minlength = 0;
- else if (i_size - range->offset < lgp->args.minlength)
- lgp->args.minlength = i_size - range->offset;
- }
- lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
- lgp->args.range = *range;
- lgp->args.type = server->pnfs_curr_ld->id;
- lgp->args.inode = ino;
- lgp->args.ctx = get_nfs_open_context(ctx);
- lgp->gfp_flags = gfp_flags;
- lgp->cred = lo->plh_lc_cred;
-
- /* Synchronously retrieve layout information from server and
- * store in lseg.
- */
- lseg = nfs4_proc_layoutget(lgp, gfp_flags);
if (IS_ERR(lseg)) {
switch (PTR_ERR(lseg)) {
case -ENOMEM:
@@ -1687,6 +1692,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
/* existing state ID, make sure the sequence number matches. */
if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
dprintk("%s forget reply due to sequence\n", __func__);
+ status = -EAGAIN;
goto out_forget_reply;
}
pnfs_set_layout_stateid(lo, &res->stateid, false);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 3b48ac25d8a7..a03f6f433075 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -372,6 +372,8 @@ static int ocfs2_mknod(struct inode *dir,
mlog_errno(status);
goto leave;
}
+ /* update inode->i_mode after mask with "umask". */
+ inode->i_mode = mode;
handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb,
S_ISDIR(mode),
diff --git a/fs/splice.c b/fs/splice.c
index 801c21cd77fe..4cf700d50b40 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -809,6 +809,13 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des
*/
static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd)
{
+ /*
+ * Check for signal early to make process killable when there are
+ * always buffers available
+ */
+ if (signal_pending(current))
+ return -ERESTARTSYS;
+
while (!pipe->nrbufs) {
if (!pipe->writers)
return 0;
@@ -884,6 +891,7 @@ ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
splice_from_pipe_begin(sd);
do {
+ cond_resched();
ret = splice_from_pipe_next(pipe, sd);
if (ret > 0)
ret = splice_from_pipe_feed(pipe, sd, actor);
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 590ad9206e3f..02fa1dcc5969 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -162,15 +162,8 @@ void sysv_set_inode(struct inode *inode, dev_t rdev)
inode->i_fop = &sysv_dir_operations;
inode->i_mapping->a_ops = &sysv_aops;
} else if (S_ISLNK(inode->i_mode)) {
- if (inode->i_blocks) {
- inode->i_op = &sysv_symlink_inode_operations;
- inode->i_mapping->a_ops = &sysv_aops;
- } else {
- inode->i_op = &simple_symlink_inode_operations;
- inode->i_link = (char *)SYSV_I(inode)->i_data;
- nd_terminate_link(inode->i_link, inode->i_size,
- sizeof(SYSV_I(inode)->i_data) - 1);
- }
+ inode->i_op = &sysv_symlink_inode_operations;
+ inode->i_mapping->a_ops = &sysv_aops;
} else
init_special_inode(inode, inode->i_mode, rdev);
}