/*
* Copyright (C) 2007 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
#include <linux/swap.h>
#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/crc32c.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <linux/uuid.h>
#include <asm/unaligned.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
#include "async-thread.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
#include "inode-map.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
#endif
static struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void free_fs_root(struct btrfs_root *root);
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int read_only);
static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
struct btrfs_root *root);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
struct btrfs_root *root);
static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t);
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_root *root,
struct extent_io_tree *dirty_pages,
int mark);
static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
struct extent_io_tree *pinned_extents);
static int btrfs_cleanup_transaction(struct btrfs_root *root);
static void btrfs_error_commit_super(struct btrfs_root *root);
/*
* end_io_wq structs are used to do processing in task context when an IO is
* complete. This is used during reads to verify checksums, and it is used
* by writes to insert metadata for new file extents after IO is complete.
*/
struct end_io_wq {
struct bio *bio;
bio_end_io_t *end_io;
void *private;
struct btrfs_fs_info *info;
int error;
int metadata;
struct list_head list;
struct btrfs_work work;
};
/*
* async submit bios are used to offload expensive checksumming
* onto the worker threads. They checksum file and metadata bios
* just before they are sent down the IO stack.
*/
struct async_submit_bio {
struct inode *inode;
struct bio *bio;
struct list_head list;
extent_submit_bio_hook_t *submit_bio_start;
extent_submit_bio_hook_t *submit_bio_done;
int rw;
int mirror_num;
unsigned long bio_flags;
/*
* bio_offset is optional, can be used if the pages in the bio
* can't tell us where in the file the bio should go
*/
u64 bio_offset;
struct btrfs_work work;
int error;
};
/*
* Lockdep class keys for extent_buffer->lock's in this root. For a given
* eb, the lockdep key is determined by the btrfs_root it belongs to and
* the level the eb occupies in the tree.
*
* Different roots are used for different purposes and may nest inside each
* other and they require separate keysets. As lockdep keys should be
* static, assign keysets according to the purpose of the root as indicated
* by btrfs_root->objectid. This ensures that all special purpose roots
* have separate keysets.
*
* Lock-nesting across peer nodes is always done with the immediate parent
* node locked thus preventing deadlock. As lockdep doesn't know this, use
* subclass to avoid triggering lockdep warning in such cases.
*
* The key is set by the readpage_end_io_hook after the buffer has passed
* csum validation but before the pages are unlocked. It is also set by
* btrfs_init_new_buffer on freshly allocated blocks.
*
* We also add a check to make sure the highest level of the tree is the
* same as our lockdep setup here. If BTRFS_MAX_LEVEL changes, this code
* needs update as well.
*/
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# if BTRFS_MAX_LEVEL != 8
# error
# endif
static struct btrfs_lockdep_keyset {
u64 id; /* root objectid */
const char *name_stem; /* lock name stem */
char names[BTRFS_MAX_LEVEL + 1][20];
struct lock_class_key keys[BTRFS_MAX_LEVEL + 1];
} btrfs_lockdep_keysets[] = {
{ .id = BTRFS_ROOT_TREE_OBJECTID, .name_stem = "root" },
{ .id = BTRFS_EXTENT_TREE_OBJECTID, .name_stem = "extent" },
{ .id = BTRFS_CHUNK_TREE_OBJECTID, .name_stem = "chunk" },
{ .id = BTRFS_DEV_TREE_OBJECTID, .name_stem = "dev" },
{ .id = BTRFS_FS_TREE_OBJECTID, .name_stem = "fs" },
{ .id = BTRFS_CSUM_TREE_OBJECTID, .name_stem = "csum" },
{ .id = BTRFS_QUOTA_TREE_OBJECTID, .name_stem = "quota" },
{ .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" },
{ .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" },
{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" },
{ .id = 0, .name_stem = "tree" },
};
void __init btrfs_init_lockdep(void)
{
int i, j;
/* initialize lockdep class names */
for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) {
struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i];
for (j = 0; j < ARRAY_SIZE(ks->names); j++)
snprintf(ks->names[j], sizeof(ks->names[j]),
"btrfs-%s-%02d", ks->name_stem, j);
}
}
void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
int level)
{
struct btrfs_lockdep_keyset *ks;
BUG_ON(level >= ARRAY_SIZE(ks->keys));
/* find the matching keyset, id 0 is the default entry */
for (ks = btrfs_lockdep_keysets; ks->id; ks++)
if (ks->id == objectid)
break;
lockdep_set_class_and_name(&eb->lock,
&ks->keys[level], ks->names[level]);
}
#endif
/*
* extents on the btree inode are pretty simple, there's one extent
* that covers the entire device
*/
static struct extent_map *btree_get_extent(struct inode *inode,
struct page *page, size_t pg_offset, u64 start, u64 len,
int create)
{
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_map *em;
int ret;
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
if (em) {
em->bdev =
BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
read_unlock(&em_tree->lock);
goto out;
}
read_unlock(&em_tree->lock);
em = alloc_extent_map();
if (!em) {
em = ERR_PTR(-ENOMEM);
goto out;
}
em->start = 0;
em->len = (u64)-1;
em->block_len = (u64)-1;
em->block_start = 0;
em->bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
write_lock(&em_tree->lock);
ret = add_extent_mapping(em_tree, em, 0);
if (ret == -EEXIST) {
free_extent_map(em);
em = lookup_extent_mapping(em_tree, start, len);
if (!em)
em = ERR_PTR(-EIO);
} else if (ret) {
free_extent_map(em);
em = ERR_PTR(ret);
}
write_unlock(&em_tree->lock);
out:
return em;
}
u32 btrfs_csum_data(char *data, u32 seed, size_t len)
{
return crc32c(seed, data, len);
}
void btrfs_csum_final(u32 crc, char *result)
{
put_unaligned_le32(~crc, result);
}
/*
* compute the csum for a btree block, and either verify it or write it
* into the csum field of the block.
*/
static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
int verify)
{
u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
char *result = NULL;
unsigned long len;
unsigned long cur_len;
unsigned long offset = BTRFS_CSUM_SIZE;
char *kaddr;
unsigned long map_start;
unsigned long map_len;
int err;
u32 crc = ~(u32)0;
unsigned long inline_result;
len = buf->len - offset;
while (len > 0) {
err = map_private_extent_buffer(buf, offset, 32,
&kaddr, &map_start, &map_len);
if (err)
return 1;
cur_len = min(len, map_len - (offset - map_start));
crc = btrfs_csum_data(kaddr + offset - map_start,
crc, cur_len);
len -= cur_len;
offset += cur_len;
}
if (csum_size > sizeof(inline_result)) {
result = kzalloc(csum_size * sizeof(char), GFP_NOFS);
if (!result)
return 1;
} else {
result = (char *)&inline_result;
}
btrfs_csum_final(crc, result);
if (verify) {
if (memcmp_extent_buffer(buf, result, 0, csum_size)) {
u32 val;
u32 found = 0;
memcpy(&found, result, csum_size);
read_extent_buffer(buf, &val, 0, csum_size);
printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
"failed on %llu wanted %X found %X "
"level %d\n",
root->fs_info->sb->s_id,
(unsigned long long)buf->start, val, found,
btrfs_header_level(buf));
if (result != (char *)&inline_result)
kfree(result);
return 1;
}
} else {
write_extent_buffer(buf, result, 0, csum_size);
}
if (result != (char *)&inline_result)
kfree(result);
return 0;
}
/*
* we can't consider a given block up to date unless the transid of the
* block matches the transid in the parent node's pointer. This is how we
* detect blocks that either didn't get written at all or got written
* in the wrong place.
*/
static int verify_parent_transid(struct extent_io_tree *io_tree,
struct extent_buffer *eb, u64 parent_transid,
int atomic)
{
struct extent_state *cached_state = NULL;
int ret;
if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
return 0;
if (atomic)
return -EAGAIN;
lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
0, &cached_state);
if (extent_buffer_uptodate(eb) &&
btrfs_header_generation(eb) == parent_transid) {
ret = 0;
goto out;
}
printk_ratelimited("parent transid verify failed on %llu wanted %llu "
"found %llu\n",
(unsigned long long)eb->start,
(unsigned long long)parent_transid,
(unsigned long long)btrfs_header_generation(eb));
ret = 1;
clear_extent_buffer_uptodate(eb);
out:
unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
&cached_state, GFP_NOFS);
return ret;
}
/*
* Return 0 if the superblock checksum type matches the checksum value of that
* algorithm. Pass the raw disk superblock data.
*/
static int btrfs_check_super_csum(char *raw_disk_sb)
{
struct btrfs_super_block *disk_sb =
(struct btrfs_super_block *)raw_disk_sb;
u16 csum_type = btrfs_super_csum_type(disk_sb);
int ret = 0;
if (csum_type == BTRFS_CSUM_TYPE_CRC32) {
u32 crc = ~(u32)0;
const int csum_size = sizeof(crc);
char result[csum_size];
/*
* The super_block structure does not span the whole
* BTRFS_SUPER_INFO_SIZE range, we expect that the unused space
* is filled with zeros and is included in the checkum.
*/
crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE,
crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
btrfs_csum_final(crc, result);
if (memcmp(raw_disk_sb, result, csum_size))
ret = 1;
if (ret && btrfs_super_generation(disk_sb) < 10) {
printk(KERN_WARNING "btrfs: super block crcs don't match, older mkfs detected\n");
ret = 0;
}
}
if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) {
printk(KERN_ERR "btrfs: unsupported checksum algorithm %u\n",
csum_type);
ret = 1;
}
return ret;
}
/*
* helper to read a given tree block, doing retries as required when
* the checksums don't match and we have alternate mirrors to try.
*/
static int btree_read_extent_buffer_pages(struct btrfs_root *root,
struct extent_buffer *eb,
u64 start, u64 parent_transid)
{
struct extent_io_tree *io_tree;
int failed = 0;
int ret;
int num_copies = 0;
int mirror_num = 0;
int failed_mirror = 0;
|