aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/inode.c')
-rw-r--r--fs/btrfs/inode.c217
1 files changed, 120 insertions, 97 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 35bfa0533f23..4af336008b12 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -102,6 +102,7 @@ static void __endio_write_update_ordered(struct btrfs_inode *inode,
* BTRFS_ILOCK_SHARED - acquire a shared lock on the inode
* BTRFS_ILOCK_TRY - try to acquire the lock, if fails on first attempt
* return -EAGAIN
+ * BTRFS_ILOCK_MMAP - acquire a write lock on the i_mmap_lock
*/
int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags)
{
@@ -122,6 +123,8 @@ int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags)
}
inode_lock(inode);
}
+ if (ilock_flags & BTRFS_ILOCK_MMAP)
+ down_write(&BTRFS_I(inode)->i_mmap_lock);
return 0;
}
@@ -133,6 +136,8 @@ int btrfs_inode_lock(struct inode *inode, unsigned int ilock_flags)
*/
void btrfs_inode_unlock(struct inode *inode, unsigned int ilock_flags)
{
+ if (ilock_flags & BTRFS_ILOCK_MMAP)
+ up_write(&BTRFS_I(inode)->i_mmap_lock);
if (ilock_flags & BTRFS_ILOCK_SHARED)
inode_unlock_shared(inode);
else
@@ -641,17 +646,12 @@ again:
if (!ret) {
unsigned long offset = offset_in_page(total_compressed);
struct page *page = pages[nr_pages - 1];
- char *kaddr;
/* zero the tail end of the last page, we might be
* sending it down to disk
*/
- if (offset) {
- kaddr = kmap_atomic(page);
- memset(kaddr + offset, 0,
- PAGE_SIZE - offset);
- kunmap_atomic(kaddr);
- }
+ if (offset)
+ memzero_page(page, offset, PAGE_SIZE - offset);
will_compress = 1;
}
}
@@ -1516,7 +1516,7 @@ static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
struct page *locked_page,
const u64 start, const u64 end,
- int *page_started, int force,
+ int *page_started,
unsigned long *nr_written)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
@@ -1530,6 +1530,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
u64 ino = btrfs_ino(inode);
bool nocow = false;
u64 disk_bytenr = 0;
+ const bool force = inode->flags & BTRFS_INODE_NODATACOW;
path = btrfs_alloc_path();
if (!path) {
@@ -1863,23 +1864,16 @@ error:
return ret;
}
-static inline int need_force_cow(struct btrfs_inode *inode, u64 start, u64 end)
+static bool should_nocow(struct btrfs_inode *inode, u64 start, u64 end)
{
-
- if (!(inode->flags & BTRFS_INODE_NODATACOW) &&
- !(inode->flags & BTRFS_INODE_PREALLOC))
- return 0;
-
- /*
- * @defrag_bytes is a hint value, no spinlock held here,
- * if is not zero, it means the file is defragging.
- * Force cow if given extent needs to be defragged.
- */
- if (inode->defrag_bytes &&
- test_range_bit(&inode->io_tree, start, end, EXTENT_DEFRAG, 0, NULL))
- return 1;
-
- return 0;
+ if (inode->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) {
+ if (inode->defrag_bytes &&
+ test_range_bit(&inode->io_tree, start, end, EXTENT_DEFRAG,
+ 0, NULL))
+ return false;
+ return true;
+ }
+ return false;
}
/*
@@ -1891,17 +1885,12 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
struct writeback_control *wbc)
{
int ret;
- int force_cow = need_force_cow(inode, start, end);
const bool zoned = btrfs_is_zoned(inode->root->fs_info);
- if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) {
- ASSERT(!zoned);
- ret = run_delalloc_nocow(inode, locked_page, start, end,
- page_started, 1, nr_written);
- } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) {
+ if (should_nocow(inode, start, end)) {
ASSERT(!zoned);
ret = run_delalloc_nocow(inode, locked_page, start, end,
- page_started, 0, nr_written);
+ page_started, nr_written);
} else if (!inode_can_compress(inode) ||
!inode_need_compress(inode, start, end)) {
if (zoned)
@@ -3099,11 +3088,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
* @bio_offset: offset to the beginning of the bio (in bytes)
* @page: page where is the data to be verified
* @pgoff: offset inside the page
+ * @start: logical offset in the file
*
* The length of such check is always one sector size.
*/
static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
- u32 bio_offset, struct page *page, u32 pgoff)
+ u32 bio_offset, struct page *page, u32 pgoff,
+ u64 start)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
@@ -3130,8 +3121,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
kunmap_atomic(kaddr);
return 0;
zeroit:
- btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff,
- csum, csum_expected, io_bio->mirror_num);
+ btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+ io_bio->mirror_num);
if (io_bio->device)
btrfs_dev_stat_inc_and_print(io_bio->device,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
@@ -3149,10 +3140,9 @@ zeroit:
* @bio_offset: offset to the beginning of the bio (in bytes)
* @start: file offset of the range start
* @end: file offset of the range end (inclusive)
- * @mirror: mirror number
*/
int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
- struct page *page, u64 start, u64 end, int mirror)
+ struct page *page, u64 start, u64 end)
{
struct inode *inode = page->mapping->host;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -3184,7 +3174,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset,
pg_off += sectorsize, bio_offset += sectorsize) {
int ret;
- ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off);
+ ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off,
+ page_offset(page) + pg_off);
if (ret < 0)
return -EIO;
}
@@ -3390,15 +3381,19 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
int is_dead_root = 0;
/*
- * this is an orphan in the tree root. Currently these
+ * This is an orphan in the tree root. Currently these
* could come from 2 sources:
- * a) a snapshot deletion in progress
+ * a) a root (snapshot/subvolume) deletion in progress
* b) a free space cache inode
- * We need to distinguish those two, as the snapshot
- * orphan must not get deleted.
- * find_dead_roots already ran before us, so if this
- * is a snapshot deletion, we should find the root
- * in the fs_roots radix tree.
+ * We need to distinguish those two, as the orphan item
+ * for a root must not get deleted before the deletion
+ * of the snapshot/subvolume's tree completes.
+ *
+ * btrfs_find_orphan_roots() ran before us, which has
+ * found all deleted roots and loaded them into
+ * fs_info->fs_roots_radix. So here we can find if an
+ * orphan item corresponds to a deleted root by looking
+ * up the root from that radix tree.
*/
spin_lock(&fs_info->fs_roots_radix_lock);
@@ -4329,7 +4324,11 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
goto out_end_trans;
}
- btrfs_record_root_in_trans(trans, dest);
+ ret = btrfs_record_root_in_trans(trans, dest);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_end_trans;
+ }
memset(&dest->root_item.drop_progress, 0,
sizeof(dest->root_item.drop_progress));
@@ -4829,7 +4828,6 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
- char *kaddr;
bool only_release_metadata = false;
u32 blocksize = fs_info->sectorsize;
pgoff_t index = from >> PAGE_SHIFT;
@@ -4921,15 +4919,13 @@ again:
if (offset != blocksize) {
if (!len)
len = blocksize - offset;
- kaddr = kmap(page);
if (front)
- memset(kaddr + (block_start - page_offset(page)),
- 0, offset);
+ memzero_page(page, (block_start - page_offset(page)),
+ offset);
else
- memset(kaddr + (block_start - page_offset(page)) + offset,
- 0, len);
+ memzero_page(page, (block_start - page_offset(page)) + offset,
+ len);
flush_dcache_page(page);
- kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
@@ -6828,11 +6824,9 @@ static noinline int uncompress_inline(struct btrfs_path *path,
* cover that region here.
*/
- if (max_size + pg_offset < PAGE_SIZE) {
- char *map = kmap(page);
- memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset);
- kunmap(page);
- }
+ if (max_size + pg_offset < PAGE_SIZE)
+ memzero_page(page, pg_offset + max_size,
+ PAGE_SIZE - max_size - pg_offset);
kfree(tmp);
return ret;
}
@@ -7023,7 +7017,7 @@ next:
if (ret)
goto out;
} else {
- map = kmap(page);
+ map = kmap_local_page(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
copy_size);
if (pg_offset + copy_size < PAGE_SIZE) {
@@ -7031,7 +7025,7 @@ next:
PAGE_SIZE - pg_offset -
copy_size);
}
- kunmap(page);
+ kunmap_local(map);
}
flush_dcache_page(page);
}
@@ -7259,6 +7253,19 @@ static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
return em;
}
+static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+ struct btrfs_block_group *block_group;
+ bool readonly = false;
+
+ block_group = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!block_group || block_group->ro)
+ readonly = true;
+ if (block_group)
+ btrfs_put_block_group(block_group);
+ return readonly;
+}
+
/*
* Check if we can do nocow write into the range [@offset, @offset + @len)
*
@@ -7910,7 +7917,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode,
ASSERT(pgoff < PAGE_SIZE);
if (uptodate &&
(!csum || !check_data_csum(inode, io_bio,
- bio_offset, bvec.bv_page, pgoff))) {
+ bio_offset, bvec.bv_page,
+ pgoff, start))) {
clean_io_failure(fs_info, failure_tree, io_tree,
start, bvec.bv_page,
btrfs_ino(BTRFS_I(inode)),
@@ -8169,10 +8177,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap,
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
- WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) &&
- fs_info->max_zone_append_size &&
- bio_op(bio) != REQ_OP_ZONE_APPEND);
-
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
status = extract_ordered_extent(BTRFS_I(inode), bio,
file_offset);
@@ -8403,17 +8407,11 @@ again:
* for the finish_ordered_io
*/
if (TestClearPagePrivate2(page)) {
- struct btrfs_ordered_inode_tree *tree;
- u64 new_len;
-
- tree = &inode->ordered_tree;
-
- spin_lock_irq(&tree->lock);
+ spin_lock_irq(&inode->ordered_tree.lock);
set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
- new_len = start - ordered->file_offset;
- if (new_len < ordered->truncated_len)
- ordered->truncated_len = new_len;
- spin_unlock_irq(&tree->lock);
+ ordered->truncated_len = min(ordered->truncated_len,
+ start - ordered->file_offset);
+ spin_unlock_irq(&inode->ordered_tree.lock);
if (btrfs_dec_test_ordered_pending(inode, &ordered,
start,
@@ -8498,7 +8496,6 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
- char *kaddr;
unsigned long zero_start;
loff_t size;
vm_fault_t ret;
@@ -8539,6 +8536,7 @@ vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
again:
+ down_read(&BTRFS_I(inode)->i_mmap_lock);
lock_page(page);
size = i_size_read(inode);
@@ -8567,6 +8565,7 @@ again:
unlock_extent_cached(io_tree, page_start, page_end,
&cached_state);
unlock_page(page);
+ up_read(&BTRFS_I(inode)->i_mmap_lock);
btrfs_start_ordered_extent(ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
@@ -8610,20 +8609,17 @@ again:
zero_start = PAGE_SIZE;
if (zero_start != PAGE_SIZE) {
- kaddr = kmap(page);
- memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start);
+ memzero_page(page, zero_start, PAGE_SIZE - zero_start);
flush_dcache_page(page);
- kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
SetPageUptodate(page);
- BTRFS_I(inode)->last_trans = fs_info->generation;
- BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
- BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit;
+ btrfs_set_inode_last_sub_trans(BTRFS_I(inode));
unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
+ up_read(&BTRFS_I(inode)->i_mmap_lock);
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
sb_end_pagefault(inode->i_sb);
@@ -8632,6 +8628,7 @@ again:
out_unlock:
unlock_page(page);
+ up_read(&BTRFS_I(inode)->i_mmap_lock);
out:
btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, page_start,
@@ -8883,6 +8880,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&ei->delalloc_inodes);
INIT_LIST_HEAD(&ei->delayed_iput);
RB_CLEAR_NODE(&ei->rb_node);
+ init_rwsem(&ei->i_mmap_lock);
return inode;
}
@@ -9008,7 +9006,7 @@ int __init btrfs_init_cachep(void)
btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap",
PAGE_SIZE, PAGE_SIZE,
- SLAB_RED_ZONE, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!btrfs_free_space_bitmap_cachep)
goto fail;
@@ -9101,8 +9099,11 @@ static int btrfs_rename_exchange(struct inode *old_dir,
goto out_notrans;
}
- if (dest != root)
- btrfs_record_root_in_trans(trans, dest);
+ if (dest != root) {
+ ret = btrfs_record_root_in_trans(trans, dest);
+ if (ret)
+ goto out_fail;
+ }
/*
* We need to find a free sequence number both in the source and
@@ -9406,8 +9407,11 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_notrans;
}
- if (dest != root)
- btrfs_record_root_in_trans(trans, dest);
+ if (dest != root) {
+ ret = btrfs_record_root_in_trans(trans, dest);
+ if (ret)
+ goto out_fail;
+ }
ret = btrfs_set_inode_index(BTRFS_I(new_dir), &index);
if (ret)
@@ -9877,6 +9881,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
struct btrfs_path *path;
u64 start = ins->objectid;
u64 len = ins->offset;
+ int qgroup_released;
int ret;
memset(&stack_fi, 0, sizeof(stack_fi));
@@ -9889,16 +9894,16 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
/* Encryption and other encoding is reserved and all 0 */
- ret = btrfs_qgroup_release_data(inode, file_offset, len);
- if (ret < 0)
- return ERR_PTR(ret);
+ qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
+ if (qgroup_released < 0)
+ return ERR_PTR(qgroup_released);
if (trans) {
ret = insert_reserved_file_extent(trans, inode,
file_offset, &stack_fi,
- true, ret);
+ true, qgroup_released);
if (ret)
- return ERR_PTR(ret);
+ goto free_qgroup;
return trans;
}
@@ -9909,21 +9914,35 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
extent_info.file_offset = file_offset;
extent_info.extent_buf = (char *)&stack_fi;
extent_info.is_new_extent = true;
- extent_info.qgroup_reserved = ret;
+ extent_info.qgroup_reserved = qgroup_released;
extent_info.insertions = 0;
path = btrfs_alloc_path();
- if (!path)
- return ERR_PTR(-ENOMEM);
+ if (!path) {
+ ret = -ENOMEM;
+ goto free_qgroup;
+ }
- ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset,
+ ret = btrfs_replace_file_extents(inode, path, file_offset,
file_offset + len - 1, &extent_info,
&trans);
btrfs_free_path(path);
if (ret)
- return ERR_PTR(ret);
-
+ goto free_qgroup;
return trans;
+
+free_qgroup:
+ /*
+ * We have released qgroup data range at the beginning of the function,
+ * and normally qgroup_released bytes will be freed when committing
+ * transaction.
+ * But if we error out early, we have to free what we have released
+ * or we leak qgroup data reservation.
+ */
+ btrfs_qgroup_free_refroot(inode->root->fs_info,
+ inode->root->root_key.objectid, qgroup_released,
+ BTRFS_QGROUP_RSV_DATA);
+ return ERR_PTR(ret);
}
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -10588,6 +10607,8 @@ static const struct inode_operations btrfs_dir_inode_operations = {
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
.tmpfile = btrfs_tmpfile,
+ .fileattr_get = btrfs_fileattr_get,
+ .fileattr_set = btrfs_fileattr_set,
};
static const struct file_operations btrfs_dir_file_operations = {
@@ -10641,6 +10662,8 @@ static const struct inode_operations btrfs_file_inode_operations = {
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
+ .fileattr_get = btrfs_fileattr_get,
+ .fileattr_set = btrfs_fileattr_set,
};
static const struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
Powered by cgit, Gruvboxed by Blaster4385.