Skip to content

Instantly share code, notes, and snippets.

@barcharcraz

barcharcraz/gist:f088f28ff7a160f144e34dd60405abe1

Created April 12, 2018 16:18
Show Gist options
  • Save barcharcraz/f088f28ff7a160f144e34dd60405abe1 to your computer and use it in GitHub Desktop.
Save barcharcraz/f088f28ff7a160f144e34dd60405abe1 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
gistfile1.txt
--- /home/bartoc/Downloads/linux-3.10.x/fs/btrfs/disk-io.c 2017-10-30 17:07:19.000000000 -0400
+++ /home/bartoc/rpmbuild/BUILD/kernel-3.10.0-693.el7/linux-3.10.0-693.fc28.x86_64/fs/btrfs/disk-io.c 2017-07-06 19:37:46.000000000 -0400
@@ -1,6 +1,20 @@
-#ifndef MY_ABC_HERE
-#define MY_ABC_HERE
-#endif
+/*
+ * 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>
@@ -11,7 +25,6 @@
#include <linux/buffer_head.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
-#include <linux/freezer.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
@@ -36,12 +49,19 @@
#include "raid56.h"
#include "sysfs.h"
#include "qgroup.h"
+#include "compression.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
#endif
-static struct extent_io_ops btree_extent_io_ops;
+#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\
+ BTRFS_HEADER_FLAG_RELOC |\
+ BTRFS_SUPER_FLAG_ERROR |\
+ BTRFS_SUPER_FLAG_SEEDING |\
+ BTRFS_SUPER_FLAG_METADUMP)
+
+static const 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,
@@ -58,17 +78,46 @@
static int btrfs_cleanup_transaction(struct btrfs_root *root);
static void btrfs_error_commit_super(struct btrfs_root *root);
-struct end_io_wq {
+/*
+ * btrfs_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 btrfs_end_io_wq {
struct bio *bio;
bio_end_io_t *end_io;
void *private;
struct btrfs_fs_info *info;
int error;
- int metadata;
+ enum btrfs_wq_endio_type metadata;
struct list_head list;
struct btrfs_work work;
};
+static struct kmem_cache *btrfs_end_io_wq_cache;
+
+int __init btrfs_end_io_wq_init(void)
+{
+ btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
+ sizeof(struct btrfs_end_io_wq),
+ 0,
+ SLAB_MEM_SPREAD,
+ NULL);
+ if (!btrfs_end_io_wq_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void btrfs_end_io_wq_exit(void)
+{
+ kmem_cache_destroy(btrfs_end_io_wq_cache);
+}
+
+/*
+ * 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;
@@ -78,20 +127,46 @@
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;
- const char *name_stem;
+ 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[] = {
@@ -107,9 +182,6 @@
{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" },
{ .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" },
{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" },
-#ifdef MY_DEF_HERE
- { .id = BTRFS_BLOCK_GROUP_HINT_TREE_OBJECTID, .name_stem = "block-group-hint" },
-#endif
{ .id = 0, .name_stem = "tree" },
};
@@ -117,6 +189,7 @@
{
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];
@@ -133,6 +206,7 @@
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;
@@ -143,6 +217,10 @@
#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)
@@ -199,10 +277,15 @@
put_unaligned_le32(~crc, result);
}
-static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
+/*
+ * 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_fs_info *fs_info,
+ struct extent_buffer *buf,
int verify)
{
- u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
+ u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
char *result = NULL;
unsigned long len;
unsigned long cur_len;
@@ -219,7 +302,7 @@
err = map_private_extent_buffer(buf, offset, 32,
&kaddr, &map_start, &map_len);
if (err)
- return 1;
+ return err;
cur_len = min(len, map_len - (offset - map_start));
crc = btrfs_csum_data(kaddr + offset - map_start,
crc, cur_len);
@@ -227,9 +310,9 @@
offset += cur_len;
}
if (csum_size > sizeof(inline_result)) {
- result = kzalloc(csum_size * sizeof(char), GFP_NOFS);
+ result = kzalloc(csum_size, GFP_NOFS);
if (!result)
- return 1;
+ return -ENOMEM;
} else {
result = (char *)&inline_result;
}
@@ -243,14 +326,13 @@
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, buf->start,
+ btrfs_warn_rl(fs_info,
+ "%s checksum verify failed on %llu wanted %X found %X level %d",
+ fs_info->sb->s_id, buf->start,
val, found, btrfs_header_level(buf));
if (result != (char *)&inline_result)
kfree(result);
- return 1;
+ return -EUCLEAN;
}
} else {
write_extent_buffer(buf, result, 0, csum_size);
@@ -260,14 +342,19 @@
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;
- bool need_lock = (current->journal_info ==
- (void *)BTRFS_SEND_TRANS_STUB);
+ bool need_lock = (current->journal_info == BTRFS_SEND_TRANS_STUB);
if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
return 0;
@@ -281,17 +368,26 @@
}
lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
- 0, &cached_state);
+ &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",
- eb->start, parent_transid, btrfs_header_generation(eb));
+ btrfs_err_rl(eb->fs_info,
+ "parent transid verify failed on %llu wanted %llu found %llu",
+ eb->start,
+ parent_transid, btrfs_header_generation(eb));
ret = 1;
+ /*
+ * Things reading via commit roots that don't have normal protection,
+ * like send, can have a really old block in cache that may point at a
+ * block that has been free'd and re-allocated. So don't clear uptodate
+ * if we find an eb that is under IO (dirty/writeback) because we could
+ * end up reading in the stale data and then writing it back out and
+ * making everybody very sad.
+ */
if (!extent_buffer_under_io(eb))
clear_extent_buffer_uptodate(eb);
out:
@@ -302,6 +398,10 @@
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 =
@@ -314,18 +414,17 @@
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)) {
@@ -337,9 +436,13 @@
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)
+ u64 parent_transid)
{
struct extent_io_tree *io_tree;
int failed = 0;
@@ -351,8 +454,7 @@
clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
while (1) {
- ret = read_extent_buffer_pages(io_tree, eb, start,
- WAIT_COMPLETE,
+ ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
btree_get_extent, mirror_num);
if (!ret) {
if (!verify_parent_transid(io_tree, eb,
@@ -362,6 +464,11 @@
ret = -EIO;
}
+ /*
+ * This buffer's crc is fine, but its contents are corrupted, so
+ * there is no reason to read the other copies, they won't be
+ * any less wrong.
+ */
if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
break;
@@ -385,15 +492,16 @@
if (failed && !ret && failed_mirror)
repair_eb_io_failure(root, eb, failed_mirror);
-#ifdef MY_DEF_HERE
- if (unlikely(test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags) && !ret))
- repair_eb_io_failure(root, eb, 1);
-#endif
return ret;
}
-static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
+/*
+ * checksum a dirty tree block before IO. This has extra checks to make sure
+ * we only fill in the checksum field in the first page of a multi-page block
+ */
+
+static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
{
u64 start = page_offset(page);
u64 found_start;
@@ -402,17 +510,27 @@
eb = (struct extent_buffer *)page->private;
if (page != eb->pages[0])
return 0;
+
found_start = btrfs_header_bytenr(eb);
- if (WARN_ON(found_start != start || !PageUptodate(page)))
- return 0;
- csum_tree_block(root, eb, 0);
- return 0;
+ /*
+ * Please do not consolidate these warnings into a single if.
+ * It is useful to know what went wrong.
+ */
+ if (WARN_ON(found_start != start))
+ return -EUCLEAN;
+ if (WARN_ON(!PageUptodate(page)))
+ return -EUCLEAN;
+
+ ASSERT(memcmp_extent_buffer(eb, fs_info->fsid,
+ btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
+
+ return csum_tree_block(fs_info, eb, 0);
}
-static int check_tree_block_fsid(struct btrfs_root *root,
+static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb)
{
- struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
+ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
u8 fsid[BTRFS_UUID_SIZE];
int ret = 1;
@@ -433,203 +551,98 @@
btrfs_header_level(eb) == 0 ? "leaf" : "node",\
reason, btrfs_header_bytenr(eb), root->objectid, slot)
-#ifdef MY_DEF_HERE
-
-static int fix_item_offset_size(struct btrfs_root *root, struct extent_buffer *leaf, int slot)
+static noinline int check_leaf(struct btrfs_root *root,
+ struct extent_buffer *leaf)
{
- u32 offset, size;
- struct btrfs_item *item = btrfs_item_nr(slot);
+ struct btrfs_key key;
+ struct btrfs_key leaf_key;
+ u32 nritems = btrfs_header_nritems(leaf);
+ int slot;
- if (slot >= btrfs_header_nritems(leaf) - 1)
- return -EIO;
+ /*
+ * Extent buffers from a relocation tree have a owner field that
+ * corresponds to the subvolume tree they are based on. So just from an
+ * extent buffer alone we can not find out what is the id of the
+ * corresponding subvolume tree, so we can not figure out if the extent
+ * buffer corresponds to the root of the relocation tree or not. So skip
+ * this check for relocation trees.
+ */
+ if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
+ struct btrfs_root *check_root;
- if (btrfs_item_offset_nr(leaf, slot + 1) > BTRFS_LEAF_DATA_SIZE(root) ||
- btrfs_item_size_nr(leaf, slot + 1) > BTRFS_LEAF_DATA_SIZE(root))
- return -EIO;
-
- if (slot + 2 < btrfs_header_nritems(leaf) &&
- btrfs_item_offset_nr(leaf, slot + 1) != btrfs_item_end_nr(leaf, slot + 2))
- return -EIO;
+ key.objectid = btrfs_header_owner(leaf);
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
- offset = btrfs_item_end_nr(leaf, slot + 1);
+ check_root = btrfs_get_fs_root(root->fs_info, &key, false);
+ /*
+ * The only reason we also check NULL here is that during
+ * open_ctree() some roots has not yet been set up.
+ */
+ if (!IS_ERR_OR_NULL(check_root)) {
+ struct extent_buffer *eb;
- if (slot != 0) {
- if (offset >= btrfs_item_offset_nr(leaf, slot - 1))
- return -EIO;
- size = btrfs_item_offset_nr(leaf, slot - 1) - offset;
- } else {
- if (offset >= BTRFS_LEAF_DATA_SIZE(root))
+ eb = btrfs_root_node(check_root);
+ /* if leaf is the root, then it's fine */
+ if (leaf != eb) {
+ CORRUPT("non-root leaf's nritems is 0",
+ leaf, check_root, 0);
+ free_extent_buffer(eb);
return -EIO;
- size = BTRFS_LEAF_DATA_SIZE(root) - offset;
}
-
- btrfs_set_item_offset(leaf, item, offset);
- btrfs_set_item_size(leaf, item, size);
-
- return 0;
+ free_extent_buffer(eb);
}
-
-static void fix_item_key(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, int slot, struct btrfs_key bad_key)
-{
- struct btrfs_extent_item *ei;
- struct btrfs_extent_inline_ref *iref;
- struct btrfs_extent_data_ref *dref;
- struct btrfs_root *root;
- struct btrfs_key key;
- struct btrfs_path *path = NULL;
- struct extent_buffer *buf;
- struct btrfs_file_extent_item *item;
- struct btrfs_disk_key disk_key;
- u64 flags;
- int type;
- int ret;
-
- if (btrfs_header_owner(leaf) != 2)
- return;
-
- if (bad_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY)
- return;
-
- ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
- flags = btrfs_extent_flags(leaf, ei);
-
- if (flags != BTRFS_EXTENT_FLAG_DATA)
- return;
-
- iref = (struct btrfs_extent_inline_ref *)(ei + 1);
- type = btrfs_extent_inline_ref_type(leaf, iref);
-
- if (type != BTRFS_EXTENT_DATA_REF_KEY)
- return;
-
- if (cmpxchg(&fs_info->can_fix_meta_key, CAN_FIX_META_KEY, DOING_FIX_META_KEY) != CAN_FIX_META_KEY)
- return;
-
- dref = (struct btrfs_extent_data_ref *)(&iref->offset);
- key.objectid = btrfs_extent_data_ref_root(leaf, dref);
- key.type = BTRFS_ROOT_ITEM_KEY;
- key.offset = 0;
- root = btrfs_read_fs_root_no_name(fs_info, &key);
- if (IS_ERR(root))
- goto err;
-
- path = btrfs_alloc_path();
- if (!path)
- goto err;
-
- key.objectid = btrfs_extent_data_ref_objectid(leaf, dref);
- key.offset = btrfs_extent_data_ref_offset(leaf, dref);
- key.type = BTRFS_EXTENT_DATA_KEY;
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
- if (ret)
- goto err;
-
- buf = path->nodes[0];
- item = btrfs_item_ptr(buf, path->slots[0], struct btrfs_file_extent_item);
- type = btrfs_file_extent_type(buf, item);
- if (type != BTRFS_FILE_EXTENT_REG && type != BTRFS_FILE_EXTENT_PREALLOC)
- goto err;
-
- key.objectid = btrfs_file_extent_disk_bytenr(buf, item);
- key.type = BTRFS_EXTENT_ITEM_KEY;
- key.offset = btrfs_file_extent_disk_num_bytes(buf, item);
- btrfs_cpu_key_to_disk(&disk_key, &key);
- btrfs_set_item_key(leaf, &disk_key, slot);
-
-err:
- fs_info->can_fix_meta_key = CAN_FIX_META_KEY;
- btrfs_free_path(path);
- return;
+ return 0;
}
-#endif
-
-static noinline int check_leaf(struct btrfs_root *root,
- struct extent_buffer *leaf)
-{
- struct btrfs_key key;
- struct btrfs_key leaf_key;
- u32 nritems = btrfs_header_nritems(leaf);
- int slot;
if (nritems == 0)
return 0;
+ /* Check the 0 item */
if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
BTRFS_LEAF_DATA_SIZE(root)) {
-#ifdef MY_DEF_HERE
- if (fix_item_offset_size(root, leaf, 0)) {
- btrfs_crit(root->fs_info, "invalid leaf item offset size pair, "
- "block=%llu, root=%llu, slot=%d", btrfs_header_bytenr(leaf), btrfs_header_owner(leaf), 0);
- return -EIO;
- }
- btrfs_warn(root->fs_info, "corrupt leaf fixed, invalid item offset size pair, "
- "block=%llu, root=%llu, slot=%d", btrfs_header_bytenr(leaf), btrfs_header_owner(leaf), 0);
- set_bit(EXTENT_BUFFER_CORRUPT, &leaf->bflags);
-#else
CORRUPT("invalid item offset size pair", leaf, root, 0);
return -EIO;
-#endif
}
+ /*
+ * Check to make sure each items keys are in the correct order and their
+ * offsets make sense. We only have to loop through nritems-1 because
+ * we check the current slot against the next slot, which verifies the
+ * next slot's offset+size makes sense and that the current's slot
+ * offset is correct.
+ */
for (slot = 0; slot < nritems - 1; slot++) {
btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
btrfs_item_key_to_cpu(leaf, &key, slot + 1);
-#ifdef MY_DEF_HERE
-
-#else
-
+ /* Make sure the keys are in the right order */
if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
CORRUPT("bad key order", leaf, root, slot);
return -EIO;
}
-#endif
+ /*
+ * Make sure the offset and ends are right, remember that the
+ * item data starts at the end of the leaf and grows towards the
+ * front.
+ */
if (btrfs_item_offset_nr(leaf, slot) !=
btrfs_item_end_nr(leaf, slot + 1)) {
-#ifdef MY_DEF_HERE
- if (fix_item_offset_size(root, leaf, slot + 1)) {
- btrfs_crit(root->fs_info, "leaf slot offset bad, "
- "block=%llu, root=%llu, slot=%d", btrfs_header_bytenr(leaf), btrfs_header_owner(leaf), slot + 1);
- return -EIO;
- }
- btrfs_warn(root->fs_info, "corrupt leaf fixed, slot offset bad, "
- "block=%llu, root=%llu, slot=%d", btrfs_header_bytenr(leaf), btrfs_header_owner(leaf), slot + 1);
- set_bit(EXTENT_BUFFER_CORRUPT, &leaf->bflags);
-#else
CORRUPT("slot offset bad", leaf, root, slot);
return -EIO;
-#endif
- }
-
-#ifdef MY_DEF_HERE
-
- if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
-
- fix_item_key(root->fs_info, leaf, slot, leaf_key);
- fix_item_key(root->fs_info, leaf, slot + 1, key);
-
- btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
- btrfs_item_key_to_cpu(leaf, &key, slot + 1);
-
- if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
- btrfs_crit(root->fs_info, "leaf bad key order, "
- "block=%llu, root=%llu, slot=%d", btrfs_header_bytenr(leaf), btrfs_header_owner(leaf), slot);
- return -EIO;
- }
- btrfs_warn(root->fs_info, "corrupt leaf fixed, bad key order, "
- "block=%llu, root=%llu, slot=%d", btrfs_header_bytenr(leaf), btrfs_header_owner(leaf), slot);
- set_bit(EXTENT_BUFFER_CORRUPT, &leaf->bflags);
}
-#else
-
+ /*
+ * Check to make sure that we don't point outside of the leaf,
+ * just incase all the items are consistent to eachother, but
+ * all point outside of the leaf.
+ */
if (btrfs_item_end_nr(leaf, slot) >
BTRFS_LEAF_DATA_SIZE(root)) {
CORRUPT("slot end outside of leaf", leaf, root, slot);
return -EIO;
}
-#endif
}
return 0;
@@ -679,6 +692,7 @@
int found_level;
struct extent_buffer *eb;
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
int ret = 0;
int reads_done;
@@ -687,6 +701,9 @@
eb = (struct extent_buffer *)page->private;
+ /* the pending IO might have been the only thing that kept this buffer
+ * in memory. Make sure we have a ref for all this other checks
+ */
extent_buffer_get(eb);
reads_done = atomic_dec_and_test(&eb->io_pages);
@@ -694,7 +711,6 @@
goto err;
eb->read_mirror = mirror;
-
if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
ret = -EIO;
goto err;
@@ -702,21 +718,20 @@
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
- printk_ratelimited(KERN_INFO "BTRFS: bad tree block start "
- "%llu %llu\n",
+ btrfs_err_rl(fs_info, "bad tree block start %llu %llu",
found_start, eb->start);
ret = -EIO;
goto err;
}
- if (check_tree_block_fsid(root, eb)) {
- printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n",
+ if (check_tree_block_fsid(fs_info, eb)) {
+ btrfs_err_rl(fs_info, "bad fsid on block %llu",
eb->start);
ret = -EIO;
goto err;
}
found_level = btrfs_header_level(eb);
if (found_level >= BTRFS_MAX_LEVEL) {
- btrfs_info(root->fs_info, "bad tree block level %d",
+ btrfs_err(fs_info, "bad tree block level %d",
(int)btrfs_header_level(eb));
ret = -EIO;
goto err;
@@ -725,12 +740,15 @@
btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
eb, found_level);
- ret = csum_tree_block(root, eb, 1);
- if (ret) {
- ret = -EIO;
+ ret = csum_tree_block(fs_info, eb, 1);
+ if (ret)
goto err;
- }
+ /*
+ * If this is a leaf block and it is corrupt, set the corrupt bit so
+ * that we don't try and read the other copies of this block, just
+ * return -EIO.
+ */
if (found_level == 0 && check_leaf(root, eb)) {
set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
ret = -EIO;
@@ -744,10 +762,14 @@
err:
if (reads_done &&
test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
- btree_readahead_hook(root, eb, eb->start, ret);
+ btree_readahead_hook(fs_info, eb, eb->start, ret);
if (ret) {
-
+ /*
+ * our io error hook is going to dec the io pages
+ * again, we have to make sure it has something
+ * to decrement
+ */
atomic_inc(&eb->io_pages);
clear_extent_buffer_uptodate(eb);
}
@@ -759,20 +781,19 @@
static int btree_io_failed_hook(struct page *page, int failed_mirror)
{
struct extent_buffer *eb;
- struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
eb = (struct extent_buffer *)page->private;
set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
eb->read_mirror = failed_mirror;
atomic_dec(&eb->io_pages);
if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
- btree_readahead_hook(root, eb, eb->start, -EIO);
- return -EIO;
+ btree_readahead_hook(eb->fs_info, eb, eb->start, -EIO);
+ return -EIO; /* we fixed nothing */
}
static void end_workqueue_bio(struct bio *bio, int err)
{
- struct end_io_wq *end_io_wq = bio->bi_private;
+ struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
struct btrfs_fs_info *fs_info;
struct btrfs_workqueue *wq;
btrfs_work_func_t func;
@@ -795,22 +816,16 @@
func = btrfs_endio_write_helper;
}
} else {
- if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+ if (unlikely(end_io_wq->metadata ==
+ BTRFS_WQ_ENDIO_DIO_REPAIR)) {
+ wq = fs_info->endio_repair_workers;
+ func = btrfs_endio_repair_helper;
+ } else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
wq = fs_info->endio_raid56_workers;
func = btrfs_endio_raid56_helper;
} else if (end_io_wq->metadata) {
-#ifdef MY_DEF_HERE
- if (unlikely(fs_info->can_fix_meta_key == DOING_FIX_META_KEY)) {
- wq = fs_info->endio_meta_fix_workers;
- func = btrfs_endio_meta_fix_helper;
- } else {
- wq = fs_info->endio_meta_workers;
- func = btrfs_endio_meta_helper;
- }
-#else
wq = fs_info->endio_meta_workers;
func = btrfs_endio_meta_helper;
-#endif
} else {
wq = fs_info->endio_workers;
func = btrfs_endio_helper;
@@ -822,10 +837,11 @@
}
int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
- int metadata)
+ enum btrfs_wq_endio_type metadata)
{
- struct end_io_wq *end_io_wq;
- end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS);
+ struct btrfs_end_io_wq *end_io_wq;
+
+ end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
if (!end_io_wq)
return -ENOMEM;
@@ -874,10 +890,14 @@
limit = btrfs_async_submit_limit(fs_info);
limit = limit * 2 / 3;
+ /*
+ * atomic_dec_return implies a barrier for waitqueue_active
+ */
if (atomic_dec_return(&fs_info->nr_async_submits) < limit &&
waitqueue_active(&fs_info->async_submit_wait))
wake_up(&fs_info->async_submit_wait);
+ /* If an error occurred we just want to clean up the bio and move on */
if (async->error) {
bio_endio(async->bio, async->error);
return;
@@ -942,20 +962,17 @@
static int btree_csum_one_bio(struct bio *bio)
{
- struct bio_vec *bvec = bio->bi_io_vec;
- int bio_index = 0;
+ struct bio_vec *bvec;
struct btrfs_root *root;
- int ret = 0;
+ int i, ret = 0;
- WARN_ON(bio->bi_vcnt <= 0);
- while (bio_index < bio->bi_vcnt) {
+ bio_for_each_segment_all(bvec, bio, i) {
root = BTRFS_I(bvec->bv_page->mapping->host)->root;
- ret = csum_dirty_buffer(root, bvec->bv_page);
+ ret = csum_dirty_buffer(root->fs_info, bvec->bv_page);
if (ret)
break;
- bio_index++;
- bvec++;
}
+
return ret;
}
@@ -964,7 +981,10 @@
unsigned long bio_flags,
u64 bio_offset)
{
-
+ /*
+ * when we're called for a write, we're already in the async
+ * submission context. Just jump into btrfs_map_bio
+ */
return btree_csum_one_bio(bio);
}
@@ -974,6 +994,10 @@
{
int ret;
+ /*
+ * when we're called for a write, we're already in the async
+ * submission context. Just jump into btrfs_map_bio
+ */
ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
if (ret)
bio_endio(bio, ret);
@@ -999,9 +1023,12 @@
int ret;
if (!(rw & REQ_WRITE)) {
-
+ /*
+ * called for a read, do the setup so that checksum validation
+ * can happen in the async kernel threads
+ */
ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info,
- bio, 1);
+ bio, BTRFS_WQ_ENDIO_METADATA);
if (ret)
goto out_w_error;
ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
@@ -1013,7 +1040,10 @@
ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
mirror_num, 0);
} else {
-
+ /*
+ * kthread helpers are used to submit writes so that
+ * checksumming can happen in parallel across all CPUs
+ */
ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
inode, rw, bio, mirror_num, 0,
bio_offset,
@@ -1033,10 +1063,16 @@
struct page *newpage, struct page *page,
enum migrate_mode mode)
{
-
+ /*
+ * we can't safely write a btree page from here,
+ * we haven't done the locking hook
+ */
if (PageDirty(page))
return -EAGAIN;
-
+ /*
+ * Buffers may be managed in a filesystem specific way.
+ * We must have no buffers or drop them.
+ */
if (page_has_private(page) &&
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
@@ -1044,6 +1080,7 @@
}
#endif
+
static int btree_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -1056,7 +1093,7 @@
return 0;
fs_info = BTRFS_I(mapping->host)->root->fs_info;
-
+ /* this is a bit racy, but that's ok */
ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
BTRFS_DIRTY_METADATA_THRESH);
if (ret < 0)
@@ -1122,23 +1159,20 @@
.set_page_dirty = btree_set_page_dirty,
};
-int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
- u64 parent_transid)
+void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
{
struct extent_buffer *buf = NULL;
struct inode *btree_inode = root->fs_info->btree_inode;
- int ret = 0;
- buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
- if (!buf)
- return 0;
+ buf = btrfs_find_create_tree_block(root, bytenr);
+ if (IS_ERR(buf))
+ return;
read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
- buf, 0, WAIT_NONE, btree_get_extent, 0);
+ buf, WAIT_NONE, btree_get_extent, 0);
free_extent_buffer(buf);
- return ret;
}
-int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
+int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
int mirror_num, struct extent_buffer **eb)
{
struct extent_buffer *buf = NULL;
@@ -1146,13 +1180,13 @@
struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree;
int ret;
- buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
- if (!buf)
+ buf = btrfs_find_create_tree_block(root, bytenr);
+ if (IS_ERR(buf))
return 0;
set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
- ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK,
+ ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK,
btree_get_extent, mirror_num);
if (ret) {
free_extent_buffer(buf);
@@ -1170,20 +1204,22 @@
return 0;
}
-struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
- u64 bytenr, u32 blocksize)
+struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info,
+ u64 bytenr)
{
- return find_extent_buffer(root->fs_info, bytenr);
+ return find_extent_buffer(fs_info, bytenr);
}
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
- u64 bytenr, u32 blocksize)
+ u64 bytenr)
{
- if (btrfs_test_is_dummy_root(root))
- return alloc_test_extent_buffer(root->fs_info, bytenr);
+ if (btrfs_is_testing(root->fs_info))
+ return alloc_test_extent_buffer(root->fs_info, bytenr,
+ root->nodesize);
return alloc_extent_buffer(root->fs_info, bytenr);
}
+
int btrfs_write_tree_block(struct extent_buffer *buf)
{
return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
@@ -1197,29 +1233,28 @@
}
struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
- u32 blocksize, u64 parent_transid)
+ u64 parent_transid)
{
struct extent_buffer *buf = NULL;
int ret;
- buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
- if (!buf)
- return NULL;
+ buf = btrfs_find_create_tree_block(root, bytenr);
+ if (IS_ERR(buf))
+ return buf;
- ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
+ ret = btree_read_extent_buffer_pages(root, buf, parent_transid);
if (ret) {
free_extent_buffer(buf);
- return NULL;
+ return ERR_PTR(ret);
}
return buf;
}
-void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+void clean_tree_block(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info,
struct extent_buffer *buf)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
-
if (btrfs_header_generation(buf) ==
fs_info->running_transaction->transid) {
btrfs_assert_tree_locked(buf);
@@ -1228,7 +1263,7 @@
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-buf->len,
fs_info->dirty_metadata_batch);
-
+ /* ugh, clear_extent_buffer_dirty needs to lock the page */
btrfs_set_lock_blocking(buf);
clear_extent_buffer_dirty(buf);
}
@@ -1244,7 +1279,7 @@
if (!writers)
return ERR_PTR(-ENOMEM);
- ret = percpu_counter_init(&writers->counter, 0);
+ ret = percpu_counter_init(&writers->counter, 0, GFP_KERNEL);
if (ret < 0) {
kfree(writers);
return ERR_PTR(ret);
@@ -1261,16 +1296,15 @@
kfree(writers);
}
-static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
- u32 stripesize, struct btrfs_root *root,
- struct btrfs_fs_info *fs_info,
+static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
+ struct btrfs_root *root, struct btrfs_fs_info *fs_info,
u64 objectid)
{
+ bool dummy = test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
root->node = NULL;
root->commit_root = NULL;
root->sectorsize = sectorsize;
root->nodesize = nodesize;
- root->leafsize = leafsize;
root->stripesize = stripesize;
root->state = 0;
root->orphan_cleanup_state = 0;
@@ -1304,9 +1338,6 @@
mutex_init(&root->objectid_mutex);
mutex_init(&root->log_mutex);
mutex_init(&root->ordered_extent_mutex);
-#ifdef MY_DEF_HERE
- mutex_init(&root->ordered_extent_worker_mutex);
-#endif
mutex_init(&root->delalloc_mutex);
init_waitqueue_head(&root->log_writer_wait);
init_waitqueue_head(&root->log_commit_wait[0]);
@@ -1320,50 +1351,52 @@
atomic_set(&root->orphan_inodes, 0);
atomic_set(&root->refs, 1);
atomic_set(&root->will_be_snapshoted, 0);
+ atomic_set(&root->qgroup_meta_rsv, 0);
root->log_transid = 0;
-#ifdef MY_DEF_HERE
-#else
root->log_transid_committed = -1;
-#endif
root->last_log_commit = 0;
- if (fs_info)
+ if (!dummy)
extent_io_tree_init(&root->dirty_log_pages,
fs_info->btree_inode->i_mapping);
memset(&root->root_key, 0, sizeof(root->root_key));
memset(&root->root_item, 0, sizeof(root->root_item));
memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
- memset(&root->root_kobj, 0, sizeof(root->root_kobj));
- if (fs_info)
+ if (!dummy)
root->defrag_trans_start = fs_info->generation;
else
root->defrag_trans_start = 0;
- init_completion(&root->kobj_unregister);
root->root_key.objectid = objectid;
root->anon_dev = 0;
spin_lock_init(&root->root_item_lock);
}
-static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info)
+static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
+ gfp_t flags)
{
- struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS);
+ struct btrfs_root *root = kzalloc(sizeof(*root), flags);
if (root)
root->fs_info = fs_info;
return root;
}
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-
-struct btrfs_root *btrfs_alloc_dummy_root(void)
+/* Should only be used by the testing infrastructure */
+struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info,
+ u32 sectorsize, u32 nodesize)
{
struct btrfs_root *root;
- root = btrfs_alloc_root(NULL);
+ if (!fs_info)
+ return ERR_PTR(-EINVAL);
+
+ root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!root)
return ERR_PTR(-ENOMEM);
- __setup_root(4096, 4096, 4096, 4096, root, NULL, 1);
- set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
+ /* We don't use the stripesize in selftest, set it as sectorsize */
+ __setup_root(nodesize, sectorsize, sectorsize, root, fs_info,
+ BTRFS_ROOT_TREE_OBJECTID);
root->alloc_bytenr = 0;
return root;
@@ -1381,19 +1414,17 @@
int ret = 0;
uuid_le uuid;
- root = btrfs_alloc_root(fs_info);
+ root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!root)
return ERR_PTR(-ENOMEM);
- __setup_root(tree_root->nodesize, tree_root->leafsize,
- tree_root->sectorsize, tree_root->stripesize,
- root, fs_info, objectid);
+ __setup_root(tree_root->nodesize, tree_root->sectorsize,
+ tree_root->stripesize, root, fs_info, objectid);
root->root_key.objectid = objectid;
root->root_key.type = BTRFS_ROOT_ITEM_KEY;
root->root_key.offset = 0;
- leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
- 0, objectid, NULL, 0, 0, 0);
+ leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
leaf = NULL;
@@ -1459,21 +1490,29 @@
struct btrfs_root *tree_root = fs_info->tree_root;
struct extent_buffer *leaf;
- root = btrfs_alloc_root(fs_info);
+ root = btrfs_alloc_root(fs_info, GFP_NOFS);
if (!root)
return ERR_PTR(-ENOMEM);
- __setup_root(tree_root->nodesize, tree_root->leafsize,
- tree_root->sectorsize, tree_root->stripesize,
- root, fs_info, BTRFS_TREE_LOG_OBJECTID);
+ __setup_root(tree_root->nodesize, tree_root->sectorsize,
+ tree_root->stripesize, root, fs_info,
+ BTRFS_TREE_LOG_OBJECTID);
root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
root->root_key.type = BTRFS_ROOT_ITEM_KEY;
root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
- leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
- BTRFS_TREE_LOG_OBJECTID, NULL,
- 0, 0, 0);
+ /*
+ * DON'T set REF_COWS for log trees
+ *
+ * log trees do not get reference counted because they go away
+ * before a real commit is actually done. They do store pointers
+ * to file data extents, and those reference counts still get
+ * updated (along with back refs to the log tree).
+ */
+
+ leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
+ NULL, 0, 0, 0);
if (IS_ERR(leaf)) {
kfree(root);
return ERR_CAST(leaf);
@@ -1523,7 +1562,7 @@
btrfs_set_stack_inode_generation(inode_item, 1);
btrfs_set_stack_inode_size(inode_item, 3);
btrfs_set_stack_inode_nlink(inode_item, 1);
- btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
+ btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
btrfs_set_root_node(&log_root->root_item, log_root->node);
@@ -1531,10 +1570,7 @@
WARN_ON(root->log_root);
root->log_root = log_root;
root->log_transid = 0;
-#ifdef MY_DEF_HERE
-#else
root->log_transid_committed = -1;
-#endif
root->last_log_commit = 0;
return 0;
}
@@ -1546,22 +1582,20 @@
struct btrfs_fs_info *fs_info = tree_root->fs_info;
struct btrfs_path *path;
u64 generation;
- u32 blocksize;
int ret;
path = btrfs_alloc_path();
if (!path)
return ERR_PTR(-ENOMEM);
- root = btrfs_alloc_root(fs_info);
+ root = btrfs_alloc_root(fs_info, GFP_NOFS);
if (!root) {
ret = -ENOMEM;
goto alloc_fail;
}
- __setup_root(tree_root->nodesize, tree_root->leafsize,
- tree_root->sectorsize, tree_root->stripesize,
- root, fs_info, key->objectid);
+ __setup_root(tree_root->nodesize, tree_root->sectorsize,
+ tree_root->stripesize, root, fs_info, key->objectid);
ret = btrfs_find_root(tree_root, key, path,
&root->root_item, &root->root_key);
@@ -1572,23 +1606,21 @@
}
generation = btrfs_root_generation(&root->root_item);
- blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
- blocksize, generation);
- if (!root->node) {
- ret = -ENOMEM;
+ generation);
+ if (IS_ERR(root->node)) {
+ ret = PTR_ERR(root->node);
goto find_fail;
} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
ret = -EIO;
- goto read_fail;
+ free_extent_buffer(root->node);
+ goto find_fail;
}
root->commit_root = btrfs_root_node(root);
out:
btrfs_free_path(path);
return root;
-read_fail:
- free_extent_buffer(root->node);
find_fail:
kfree(root);
alloc_fail:
@@ -1634,23 +1666,32 @@
root->subv_writers = writers;
btrfs_init_free_ino_ctl(root);
- spin_lock_init(&root->cache_lock);
- init_waitqueue_head(&root->cache_wait);
+ spin_lock_init(&root->ino_cache_lock);
+ init_waitqueue_head(&root->ino_cache_wait);
ret = get_anon_bdev(&root->anon_dev);
if (ret)
- goto free_writers;
- return 0;
+ goto fail;
-free_writers:
- btrfs_free_subvolume_writers(root->subv_writers);
+ mutex_lock(&root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(root,
+ &root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&root->objectid_mutex);
+ goto fail;
+ }
+
+ ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ mutex_unlock(&root->objectid_mutex);
+
+ return 0;
fail:
- kfree(root->free_ino_ctl);
- kfree(root->free_ino_pinned);
+ /* the caller is responsible to call free_fs_root */
return ret;
}
-static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
u64 root_id)
{
struct btrfs_root *root;
@@ -1667,7 +1708,7 @@
{
int ret;
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ ret = radix_tree_preload(GFP_NOFS);
if (ret)
return ret;
@@ -1688,6 +1729,8 @@
bool check_ref)
{
struct btrfs_root *root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
int ret;
if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
@@ -1709,12 +1752,6 @@
if (location->objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
return fs_info->free_space_root ? fs_info->free_space_root :
ERR_PTR(-ENOENT);
-#ifdef MY_DEF_HERE
- if (location->objectid == BTRFS_BLOCK_GROUP_HINT_TREE_OBJECTID)
- return fs_info->block_group_hint_root ? fs_info->block_group_hint_root :
- ERR_PTR(-ENOENT);
-#endif
-
again:
root = btrfs_lookup_fs_root(fs_info, location->objectid);
if (root) {
@@ -1736,8 +1773,17 @@
if (ret)
goto fail;
- ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID,
- location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL);
+ path = btrfs_alloc_path();
+ if (!path) {
+ ret = -ENOMEM;
+ goto fail;
+ }
+ key.objectid = BTRFS_ORPHAN_OBJECTID;
+ key.type = BTRFS_ORPHAN_ITEM_KEY;
+ key.offset = location->objectid;
+
+ ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
+ btrfs_free_path(path);
if (ret < 0)
goto fail;
if (ret == 0)
@@ -1769,7 +1815,7 @@
if (!device->bdev)
continue;
bdi = blk_get_backing_dev_info(device->bdev);
- if (bdi && bdi_congested(bdi, bdi_bits)) {
+ if (bdi_congested(bdi, bdi_bits)) {
ret = 1;
break;
}
@@ -1793,19 +1839,23 @@
return 0;
}
+/*
+ * called by the kthread helper functions to finally call the bio end_io
+ * functions. This is where read checksum verification actually happens
+ */
static void end_workqueue_fn(struct btrfs_work *work)
{
struct bio *bio;
- struct end_io_wq *end_io_wq;
+ struct btrfs_end_io_wq *end_io_wq;
int error;
- end_io_wq = container_of(work, struct end_io_wq, work);
+ end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
bio = end_io_wq->bio;
error = end_io_wq->error;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
- kfree(end_io_wq);
+ kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
bio_endio(bio, error);
}
@@ -1818,25 +1868,53 @@
do {
again = 0;
+ /* Make the cleaner go to sleep early. */
if (btrfs_need_cleaner_sleep(root))
goto sleep;
+ /*
+ * Do not do anything if we might cause open_ctree() to block
+ * before we have finished mounting the filesystem.
+ */
+ if (!test_bit(BTRFS_FS_OPEN, &root->fs_info->flags))
+ goto sleep;
+
if (!mutex_trylock(&root->fs_info->cleaner_mutex))
goto sleep;
+ /*
+ * Avoid the problem that we change the status of the fs
+ * during the above check and trylock.
+ */
if (btrfs_need_cleaner_sleep(root)) {
mutex_unlock(&root->fs_info->cleaner_mutex);
goto sleep;
}
+ mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(root);
- btrfs_delete_unused_bgs(root->fs_info);
+ mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
+
again = btrfs_clean_one_deleted_snapshot(root);
mutex_unlock(&root->fs_info->cleaner_mutex);
+ /*
+ * The defragger has dealt with the R/O remount and umount,
+ * needn't do anything special here.
+ */
btrfs_run_defrag_inodes(root->fs_info);
+
+ /*
+ * Acquires fs_info->delete_unused_bgs_mutex to avoid racing
+ * with relocation (btrfs_relocate_chunk) and relocation
+ * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
+ * after acquiring fs_info->delete_unused_bgs_mutex. So we
+ * can't hold, nor need to, fs_info->cleaner_mutex when deleting
+ * unused block groups.
+ */
+ btrfs_delete_unused_bgs(root->fs_info);
sleep:
- if (!try_to_freeze() && !again) {
+ if (!again) {
set_current_state(TASK_INTERRUPTIBLE);
if (!kthread_should_stop())
schedule();
@@ -1844,6 +1922,17 @@
}
} while (!kthread_should_stop());
+ /*
+ * Transaction kthread is stopped before us and wakes us up.
+ * However we might have started a new transaction and COWed some
+ * tree blocks when deleting unused block groups for example. So
+ * make sure we commit the transaction we started to have a clean
+ * shutdown when evicting the btree inode - if it has dirty pages
+ * when we do the final iput() on it, eviction will trigger a
+ * writeback for it which will fail with null pointer dereferences
+ * since work queues and other resources were already released and
+ * destroyed by the time the iput/eviction/writeback is made.
+ */
trans = btrfs_attach_transaction(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT)
@@ -1890,18 +1979,13 @@
(now < cur->start_time ||
now - cur->start_time < root->fs_info->commit_interval)) {
spin_unlock(&root->fs_info->trans_lock);
-#ifdef MY_DEF_HERE
-
- if (root->fs_info->commit_interval <= 5)
- delay = HZ * 1;
- else
-#endif
delay = HZ * 5;
goto sleep;
}
transid = cur->transid;
spin_unlock(&root->fs_info->trans_lock);
+ /* If the file system is aborted, this will always fail. */
trans = btrfs_attach_transaction(root);
if (IS_ERR(trans)) {
if (PTR_ERR(trans) != -ENOENT)
@@ -1920,18 +2004,25 @@
if (unlikely(test_bit(BTRFS_FS_STATE_ERROR,
&root->fs_info->fs_state)))
btrfs_cleanup_transaction(root);
- if (!try_to_freeze()) {
set_current_state(TASK_INTERRUPTIBLE);
if (!kthread_should_stop() &&
(!btrfs_transaction_blocked(root->fs_info) ||
cannot_commit))
schedule_timeout(delay);
__set_current_state(TASK_RUNNING);
- }
} while (!kthread_should_stop());
return 0;
}
+/*
+ * this will find the highest generation in the array of
+ * root backups. The index of the highest array is returned,
+ * or -1 if we can't find anything.
+ *
+ * We check to make sure the array is valid by comparing the
+ * generation of the latest root in the array with the generation
+ * in the super block. If they don't match we pitch it.
+ */
static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
{
u64 cur;
@@ -1946,6 +2037,7 @@
newest_index = i;
}
+ /* check to see if we actually wrapped around */
if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) {
root_backup = info->super_copy->super_roots;
cur = btrfs_backup_tree_root_gen(root_backup);
@@ -1955,13 +2047,19 @@
return newest_index;
}
+
+/*
+ * find the oldest backup so we know where to store new entries
+ * in the backup array. This will set the backup_root_index
+ * field in the fs_info struct
+ */
static void find_oldest_super_backup(struct btrfs_fs_info *info,
u64 newest_gen)
{
int newest_index = -1;
newest_index = find_newest_super_backup(info, newest_gen);
-
+ /* if there was garbage in there, just move along */
if (newest_index == -1) {
info->backup_root_index = 0;
} else {
@@ -1969,6 +2067,11 @@
}
}
+/*
+ * copy all the root pointers into the super backup array.
+ * this will bump the backup pointer by one when it is
+ * done
+ */
static void backup_super_roots(struct btrfs_fs_info *info)
{
int next_backup;
@@ -1979,6 +2082,10 @@
last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) %
BTRFS_NUM_BACKUP_ROOTS;
+ /*
+ * just overwrite the last backup if we're at the same generation
+ * this happens only at umount
+ */
root_backup = info->super_for_commit->super_roots + last_backup;
if (btrfs_backup_tree_root_gen(root_backup) ==
btrfs_header_generation(info->tree_root->node))
@@ -1986,6 +2093,10 @@
root_backup = info->super_for_commit->super_roots + next_backup;
+ /*
+ * make sure all of our padding and empty slots get zero filled
+ * regardless of which ones we use today
+ */
memset(root_backup, 0, sizeof(*root_backup));
info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS;
@@ -2009,6 +2120,10 @@
btrfs_set_backup_extent_root_level(root_backup,
btrfs_header_level(info->extent_root->node));
+ /*
+ * we might commit during log recovery, which happens before we set
+ * the fs_root. Make sure it is valid before we fill it in.
+ */
if (info->fs_root && info->fs_root->node) {
btrfs_set_backup_fs_root(root_backup,
info->fs_root->node->start);
@@ -2037,11 +2152,23 @@
btrfs_set_backup_num_devices(root_backup,
btrfs_super_num_devices(info->super_copy));
+ /*
+ * if we don't copy this out to the super_copy, it won't get remembered
+ * for the next commit
+ */
memcpy(&info->super_copy->super_roots,
&info->super_for_commit->super_roots,
sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS);
}
+/*
+ * this copies info out of the root backup array and back into
+ * the in-memory super block. It is meant to help iterate through
+ * the array, so you send it the number of backups you've already
+ * tried and the last backup index you used.
+ *
+ * this returns -1 when it has tried all the backups
+ */
static noinline int next_root_backup(struct btrfs_fs_info *info,
struct btrfs_super_block *super,
int *num_backups_tried, int *backup_index)
@@ -2059,10 +2186,10 @@
*backup_index = newest;
*num_backups_tried = 1;
} else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) {
-
+ /* we've tried all the backups, all done */
return -1;
} else {
-
+ /* jump to the next oldest backup */
newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) %
BTRFS_NUM_BACKUP_ROOTS;
*backup_index = newest;
@@ -2077,11 +2204,16 @@
btrfs_backup_tree_root_level(root_backup));
btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));
+ /*
+ * fixme: the total bytes and num_devices need to match or we should
+ * need a fsck
+ */
btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));
return 0;
}
+/* helper to cleanup workers */
static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
btrfs_destroy_workqueue(fs_info->fixup_workers);
@@ -2089,10 +2221,8 @@
btrfs_destroy_workqueue(fs_info->workers);
btrfs_destroy_workqueue(fs_info->endio_workers);
btrfs_destroy_workqueue(fs_info->endio_meta_workers);
-#ifdef MY_DEF_HERE
- btrfs_destroy_workqueue(fs_info->endio_meta_fix_workers);
-#endif
btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
+ btrfs_destroy_workqueue(fs_info->endio_repair_workers);
btrfs_destroy_workqueue(fs_info->rmw_workers);
btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
btrfs_destroy_workqueue(fs_info->endio_write_workers);
@@ -2101,9 +2231,6 @@
btrfs_destroy_workqueue(fs_info->delayed_workers);
btrfs_destroy_workqueue(fs_info->caching_workers);
btrfs_destroy_workqueue(fs_info->readahead_workers);
-#ifdef MY_DEF_HERE
- btrfs_destroy_workqueue(fs_info->reada_path_workers);
-#endif
btrfs_destroy_workqueue(fs_info->flush_workers);
btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
btrfs_destroy_workqueue(fs_info->extent_workers);
@@ -2119,6 +2246,7 @@
}
}
+/* helper to cleanup tree roots */
static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
{
free_root_extent_buffers(info->tree_root);
@@ -2128,9 +2256,6 @@
free_root_extent_buffers(info->csum_root);
free_root_extent_buffers(info->quota_root);
free_root_extent_buffers(info->uuid_root);
-#ifdef MY_DEF_HERE
- free_root_extent_buffers(info->block_group_hint_root);
-#endif
if (chunk_root)
free_root_extent_buffers(info->chunk_root);
free_root_extent_buffers(info->free_space_root);
@@ -2173,14 +2298,295 @@
}
}
+static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
+{
+ mutex_init(&fs_info->scrub_lock);
+ atomic_set(&fs_info->scrubs_running, 0);
+ atomic_set(&fs_info->scrub_pause_req, 0);
+ atomic_set(&fs_info->scrubs_paused, 0);
+ atomic_set(&fs_info->scrub_cancel_req, 0);
+ init_waitqueue_head(&fs_info->scrub_pause_wait);
+ fs_info->scrub_workers_refcnt = 0;
+}
+
+static void btrfs_init_balance(struct btrfs_fs_info *fs_info)
+{
+ spin_lock_init(&fs_info->balance_lock);
+ mutex_init(&fs_info->balance_mutex);
+ atomic_set(&fs_info->balance_running, 0);
+ atomic_set(&fs_info->balance_pause_req, 0);
+ atomic_set(&fs_info->balance_cancel_req, 0);
+ fs_info->balance_ctl = NULL;
+ init_waitqueue_head(&fs_info->balance_wait_q);
+}
+
+static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info,
+ struct btrfs_root *tree_root)
+{
+ fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
+ set_nlink(fs_info->btree_inode, 1);
+ /*
+ * we set the i_size on the btree inode to the max possible int.
+ * the real end of the address space is determined by all of
+ * the devices in the system
+ */
+ fs_info->btree_inode->i_size = OFFSET_MAX;
+ fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
+ fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
+
+ RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
+ extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
+ fs_info->btree_inode->i_mapping);
+ BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0;
+ extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree);
+
+ BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops;
+
+ BTRFS_I(fs_info->btree_inode)->root = tree_root;
+ memset(&BTRFS_I(fs_info->btree_inode)->location, 0,
+ sizeof(struct btrfs_key));
+ set_bit(BTRFS_INODE_DUMMY,
+ &BTRFS_I(fs_info->btree_inode)->runtime_flags);
+ btrfs_insert_inode_hash(fs_info->btree_inode);
+}
+
+static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
+{
+ fs_info->dev_replace.lock_owner = 0;
+ atomic_set(&fs_info->dev_replace.nesting_level, 0);
+ mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
+ rwlock_init(&fs_info->dev_replace.lock);
+ atomic_set(&fs_info->dev_replace.read_locks, 0);
+ atomic_set(&fs_info->dev_replace.blocking_readers, 0);
+ init_waitqueue_head(&fs_info->replace_wait);
+ init_waitqueue_head(&fs_info->dev_replace.read_lock_wq);
+}
+
+static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
+{
+ spin_lock_init(&fs_info->qgroup_lock);
+ mutex_init(&fs_info->qgroup_ioctl_lock);
+ fs_info->qgroup_tree = RB_ROOT;
+ fs_info->qgroup_op_tree = RB_ROOT;
+ INIT_LIST_HEAD(&fs_info->dirty_qgroups);
+ fs_info->qgroup_seq = 1;
+ fs_info->qgroup_ulist = NULL;
+ fs_info->qgroup_rescan_running = false;
+ mutex_init(&fs_info->qgroup_rescan_lock);
+}
+
+static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
+ struct btrfs_fs_devices *fs_devices)
+{
+ int max_active = fs_info->thread_pool_size;
+ unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
+
+ fs_info->workers =
+ btrfs_alloc_workqueue(fs_info, "worker",
+ flags | WQ_HIGHPRI, max_active, 16);
+
+ fs_info->delalloc_workers =
+ btrfs_alloc_workqueue(fs_info, "delalloc",
+ flags, max_active, 2);
+
+ fs_info->flush_workers =
+ btrfs_alloc_workqueue(fs_info, "flush_delalloc",
+ flags, max_active, 0);
+
+ fs_info->caching_workers =
+ btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);
+
+ /*
+ * a higher idle thresh on the submit workers makes it much more
+ * likely that bios will be send down in a sane order to the
+ * devices
+ */
+ fs_info->submit_workers =
+ btrfs_alloc_workqueue(fs_info, "submit", flags,
+ min_t(u64, fs_devices->num_devices,
+ max_active), 64);
+
+ fs_info->fixup_workers =
+ btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
+
+ /*
+ * endios are largely parallel and should have a very
+ * low idle thresh
+ */
+ fs_info->endio_workers =
+ btrfs_alloc_workqueue(fs_info, "endio", flags, max_active, 4);
+ fs_info->endio_meta_workers =
+ btrfs_alloc_workqueue(fs_info, "endio-meta", flags,
+ max_active, 4);
+ fs_info->endio_meta_write_workers =
+ btrfs_alloc_workqueue(fs_info, "endio-meta-write", flags,
+ max_active, 2);
+ fs_info->endio_raid56_workers =
+ btrfs_alloc_workqueue(fs_info, "endio-raid56", flags,
+ max_active, 4);
+ fs_info->endio_repair_workers =
+ btrfs_alloc_workqueue(fs_info, "endio-repair", flags, 1, 0);
+ fs_info->rmw_workers =
+ btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2);
+ fs_info->endio_write_workers =
+ btrfs_alloc_workqueue(fs_info, "endio-write", flags,
+ max_active, 2);
+ fs_info->endio_freespace_worker =
+ btrfs_alloc_workqueue(fs_info, "freespace-write", flags,
+ max_active, 0);
+ fs_info->delayed_workers =
+ btrfs_alloc_workqueue(fs_info, "delayed-meta", flags,
+ max_active, 0);
+ fs_info->readahead_workers =
+ btrfs_alloc_workqueue(fs_info, "readahead", flags,
+ 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 &&
+ fs_info->endio_workers && fs_info->endio_meta_workers &&
+ fs_info->endio_meta_write_workers &&
+ fs_info->endio_repair_workers &&
+ fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
+ 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;
+ }
+
+ return 0;
+}
+
+static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
+ struct btrfs_fs_devices *fs_devices)
+{
+ int ret;
+ struct btrfs_root *tree_root = fs_info->tree_root;
+ struct btrfs_root *log_tree_root;
+ struct btrfs_super_block *disk_super = fs_info->super_copy;
+ u64 bytenr = btrfs_super_log_root(disk_super);
+
+ if (fs_devices->rw_devices == 0) {
+ btrfs_warn(fs_info, "log replay required on RO media");
+ return -EIO;
+ }
+
+ log_tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
+ if (!log_tree_root)
+ return -ENOMEM;
+
+ __setup_root(tree_root->nodesize, tree_root->sectorsize,
+ tree_root->stripesize, log_tree_root, fs_info,
+ BTRFS_TREE_LOG_OBJECTID);
+
+ log_tree_root->node = read_tree_block(tree_root, bytenr,
+ fs_info->generation + 1);
+ if (IS_ERR(log_tree_root->node)) {
+ btrfs_warn(fs_info, "failed to read log tree");
+ ret = PTR_ERR(log_tree_root->node);
+ kfree(log_tree_root);
+ return ret;
+ } else if (!extent_buffer_uptodate(log_tree_root->node)) {
+ btrfs_err(fs_info, "failed to read log tree");
+ free_extent_buffer(log_tree_root->node);
+ kfree(log_tree_root);
+ return -EIO;
+ }
+ /* returns with log_tree_root freed on success */
+ ret = btrfs_recover_log_trees(log_tree_root);
+ if (ret) {
+ btrfs_handle_fs_error(tree_root->fs_info, ret,
+ "Failed to recover log tree");
+ free_extent_buffer(log_tree_root->node);
+ kfree(log_tree_root);
+ return ret;
+ }
+
+ if (fs_info->sb->s_flags & MS_RDONLY) {
+ ret = btrfs_commit_super(tree_root);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static int btrfs_read_roots(struct btrfs_fs_info *fs_info,
+ struct btrfs_root *tree_root)
+{
+ struct btrfs_root *root;
+ struct btrfs_key location;
+ int ret;
+
+ location.objectid = BTRFS_EXTENT_TREE_OBJECTID;
+ location.type = BTRFS_ROOT_ITEM_KEY;
+ location.offset = 0;
+
+ root = btrfs_read_tree_root(tree_root, &location);
+ if (IS_ERR(root))
+ return PTR_ERR(root);
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+ fs_info->extent_root = root;
+
+ location.objectid = BTRFS_DEV_TREE_OBJECTID;
+ root = btrfs_read_tree_root(tree_root, &location);
+ if (IS_ERR(root))
+ return PTR_ERR(root);
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+ fs_info->dev_root = root;
+ btrfs_init_devices_late(fs_info);
+
+ location.objectid = BTRFS_CSUM_TREE_OBJECTID;
+ root = btrfs_read_tree_root(tree_root, &location);
+ if (IS_ERR(root))
+ return PTR_ERR(root);
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+ fs_info->csum_root = root;
+
+ location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
+ root = btrfs_read_tree_root(tree_root, &location);
+ if (!IS_ERR(root)) {
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+ set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+ fs_info->quota_root = root;
+ }
+
+ location.objectid = BTRFS_UUID_TREE_OBJECTID;
+ root = btrfs_read_tree_root(tree_root, &location);
+ if (IS_ERR(root)) {
+ ret = PTR_ERR(root);
+ if (ret != -ENOENT)
+ return ret;
+ } else {
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+ fs_info->uuid_root = root;
+ }
+
+ if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
+ location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID;
+ root = btrfs_read_tree_root(tree_root, &location);
+ if (IS_ERR(root))
+ return PTR_ERR(root);
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+ fs_info->free_space_root = root;
+ }
+
+ return 0;
+}
+
int open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options)
{
u32 sectorsize;
u32 nodesize;
- u32 leafsize;
- u32 blocksize;
u32 stripesize;
u64 generation;
u64 features;
@@ -2189,30 +2595,16 @@
struct btrfs_super_block *disk_super;
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
struct btrfs_root *tree_root;
- struct btrfs_root *extent_root;
- struct btrfs_root *csum_root;
struct btrfs_root *chunk_root;
- struct btrfs_root *dev_root;
- struct btrfs_root *quota_root;
- struct btrfs_root *uuid_root;
- struct btrfs_root *log_tree_root;
- struct btrfs_root *free_space_tree_root;
-#ifdef MY_DEF_HERE
- struct btrfs_root *block_group_hint_root;
-#endif
-
int ret;
int err = -EINVAL;
int num_backups_tried = 0;
int backup_index = 0;
int max_active;
- int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
- bool create_uuid_tree;
- bool check_uuid_tree;
int clear_free_space_tree = 0;
- tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info);
- chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info);
+ tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
+ chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!tree_root || !chunk_root) {
err = -ENOMEM;
goto fail;
@@ -2230,7 +2622,7 @@
goto fail_srcu;
}
- ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0);
+ ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_bdi;
@@ -2238,30 +2630,22 @@
fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE *
(1 + ilog2(nr_cpu_ids));
- ret = percpu_counter_init(&fs_info->delalloc_bytes, 0);
+ ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_dirty_metadata_bytes;
}
-#ifdef MY_DEF_HERE
-#else
- ret = percpu_counter_init(&fs_info->bio_counter, 0);
-
+ ret = percpu_counter_init(&fs_info->bio_counter, 0, GFP_KERNEL);
if (ret) {
err = ret;
goto fail_delalloc_bytes;
}
-#endif
fs_info->btree_inode = new_inode(sb);
if (!fs_info->btree_inode) {
err = -ENOMEM;
-#ifdef MY_DEF_HERE
- goto fail_delalloc_bytes;
-#else
goto fail_bio_counter;
-#endif
}
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
@@ -2286,22 +2670,17 @@
spin_lock_init(&fs_info->unused_bgs_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->unused_bg_unpin_mutex);
+ mutex_init(&fs_info->delete_unused_bgs_mutex);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
+ mutex_init(&fs_info->cleaner_delayed_iput_mutex);
seqlock_init(&fs_info->profiles_lock);
- init_rwsem(&fs_info->delayed_iput_sem);
- init_completion(&fs_info->kobj_unregister);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
INIT_LIST_HEAD(&fs_info->unused_bgs);
btrfs_mapping_init(&fs_info->mapping_tree);
-#ifdef MY_DEF_HERE
- atomic_set(&fs_info->nr_extent_maps, 0);
- INIT_LIST_HEAD(&fs_info->extent_map_inode_list);
- spin_lock_init(&fs_info->extent_map_inode_list_lock);
-#endif
btrfs_init_block_rsv(&fs_info->global_block_rsv,
BTRFS_BLOCK_RSV_GLOBAL);
btrfs_init_block_rsv(&fs_info->delalloc_block_rsv,
@@ -2317,16 +2696,18 @@
atomic_set(&fs_info->nr_async_bios, 0);
atomic_set(&fs_info->defrag_running, 0);
atomic_set(&fs_info->qgroup_op_seq, 0);
+ atomic_set(&fs_info->reada_works_cnt, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
+ fs_info->fs_frozen = 0;
fs_info->sb = sb;
- fs_info->max_inline = 8192 * 1024;
+ fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
fs_info->metadata_ratio = 0;
fs_info->defrag_inodes = RB_ROOT;
fs_info->free_chunk_space = 0;
fs_info->tree_mod_log = RB_ROOT;
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
- fs_info->avg_delayed_ref_runtime = div64_u64(NSEC_PER_SEC, 64);
-
+ fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
+ /* readahead state */
INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
spin_lock_init(&fs_info->reada_lock);
@@ -2336,62 +2717,25 @@
INIT_LIST_HEAD(&fs_info->ordered_roots);
spin_lock_init(&fs_info->ordered_root_lock);
fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
- GFP_NOFS);
+ GFP_KERNEL);
if (!fs_info->delayed_root) {
err = -ENOMEM;
goto fail_iput;
}
btrfs_init_delayed_root(fs_info->delayed_root);
- mutex_init(&fs_info->scrub_lock);
- atomic_set(&fs_info->scrubs_running, 0);
- atomic_set(&fs_info->scrub_pause_req, 0);
- atomic_set(&fs_info->scrubs_paused, 0);
- atomic_set(&fs_info->scrub_cancel_req, 0);
-#ifdef MY_DEF_HERE
-#else
- init_waitqueue_head(&fs_info->replace_wait);
-#endif
- init_waitqueue_head(&fs_info->scrub_pause_wait);
- fs_info->scrub_workers_refcnt = 0;
+ btrfs_init_scrub(fs_info);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
fs_info->check_integrity_print_mask = 0;
#endif
-
- spin_lock_init(&fs_info->balance_lock);
- mutex_init(&fs_info->balance_mutex);
- atomic_set(&fs_info->balance_running, 0);
- atomic_set(&fs_info->balance_pause_req, 0);
- atomic_set(&fs_info->balance_cancel_req, 0);
- fs_info->balance_ctl = NULL;
- init_waitqueue_head(&fs_info->balance_wait_q);
+ btrfs_init_balance(fs_info);
btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
sb->s_blocksize = 4096;
sb->s_blocksize_bits = blksize_bits(4096);
sb->s_bdi = &fs_info->bdi;
- fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
- set_nlink(fs_info->btree_inode, 1);
-
- fs_info->btree_inode->i_size = OFFSET_MAX;
- fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
- fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
-
- RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
- extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
- fs_info->btree_inode->i_mapping);
- BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0;
- extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree);
-
- BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops;
-
- BTRFS_I(fs_info->btree_inode)->root = tree_root;
- memset(&BTRFS_I(fs_info->btree_inode)->location, 0,
- sizeof(struct btrfs_key));
- set_bit(BTRFS_INODE_DUMMY,
- &BTRFS_I(fs_info->btree_inode)->runtime_flags);
- btrfs_insert_inode_hash(fs_info->btree_inode);
+ btrfs_init_btree_inode(fs_info, tree_root);
spin_lock_init(&fs_info->block_group_cache_lock);
fs_info->block_group_cache_tree = RB_ROOT;
@@ -2402,10 +2746,9 @@
extent_io_tree_init(&fs_info->freed_extents[1],
fs_info->btree_inode->i_mapping);
fs_info->pinned_extents = &fs_info->freed_extents[0];
- fs_info->do_barriers = 1;
+ set_bit(BTRFS_FS_BARRIER, &fs_info->flags);
mutex_init(&fs_info->ordered_operations_mutex);
- mutex_init(&fs_info->ordered_extent_flush_mutex);
mutex_init(&fs_info->tree_log_mutex);
mutex_init(&fs_info->chunk_mutex);
mutex_init(&fs_info->transaction_kthread_mutex);
@@ -2416,34 +2759,9 @@
init_rwsem(&fs_info->cleanup_work_sem);
init_rwsem(&fs_info->subvol_sem);
sema_init(&fs_info->uuid_tree_rescan_sem, 1);
- fs_info->dev_replace.lock_owner = 0;
- atomic_set(&fs_info->dev_replace.nesting_level, 0);
- mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
- mutex_init(&fs_info->dev_replace.lock_management_lock);
- mutex_init(&fs_info->dev_replace.lock);
-#ifdef MY_DEF_HERE
- fs_info->metadata_ratio = 50;
-#endif
-#ifdef MY_DEF_HERE
- fs_info->ordered_extent_nr = 0;
- fs_info->delalloc_inodes_nr = 0;
- if (totalram_pages > ((2ULL*1024*1024*1024)/PAGE_SIZE))
- fs_info->flushoncommit_threshold = 0;
- else
- fs_info->flushoncommit_threshold = 1000;
-#endif
-
- spin_lock_init(&fs_info->qgroup_lock);
- mutex_init(&fs_info->qgroup_ioctl_lock);
- fs_info->qgroup_tree = RB_ROOT;
- fs_info->qgroup_op_tree = RB_ROOT;
- INIT_LIST_HEAD(&fs_info->dirty_qgroups);
- fs_info->qgroup_seq = 1;
- fs_info->quota_enabled = 0;
- fs_info->pending_quota_state = 0;
- fs_info->qgroup_ulist = NULL;
- mutex_init(&fs_info->qgroup_rescan_lock);
+ btrfs_init_dev_replace_locks(fs_info);
+ btrfs_init_qgroup(fs_info);
btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
btrfs_init_free_cluster(&fs_info->data_alloc_cluster);
@@ -2461,24 +2779,36 @@
goto fail_alloc;
}
- __setup_root(4096, 4096, 4096, 4096, tree_root,
+ __setup_root(4096, 4096, 4096, tree_root,
fs_info, BTRFS_ROOT_TREE_OBJECTID);
invalidate_bdev(fs_devices->latest_bdev);
+ /*
+ * Read super block and check the signature bytes only
+ */
bh = btrfs_read_dev_super(fs_devices->latest_bdev);
- if (!bh) {
- err = -EINVAL;
+ if (IS_ERR(bh)) {
+ err = PTR_ERR(bh);
goto fail_alloc;
}
+ /*
+ * We want to check superblock checksum, the type is stored inside.
+ * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
+ */
if (btrfs_check_super_csum(bh->b_data)) {
- printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
+ btrfs_err(fs_info, "superblock checksum mismatch");
err = -EINVAL;
brelse(bh);
goto fail_alloc;
}
+ /*
+ * super_copy is zeroed at allocation time and we never touch the
+ * following bytes up to INFO_SIZE, the checksum is calculated from
+ * the whole block of INFO_SIZE
+ */
memcpy(fs_info->super_copy, bh->b_data, sizeof(*fs_info->super_copy));
memcpy(fs_info->super_for_commit, fs_info->super_copy,
sizeof(*fs_info->super_for_commit));
@@ -2488,7 +2818,7 @@
ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
if (ret) {
- printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
+ btrfs_err(fs_info, "superblock contains fatal errors");
err = -EINVAL;
goto fail_alloc;
}
@@ -2497,19 +2827,24 @@
if (!btrfs_super_root(disk_super))
goto fail_alloc;
+ /* check FS state, whether FS is broken. */
if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR)
set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
+ /*
+ * run through our array of backup supers and setup
+ * our ring pointer to the oldest one
+ */
generation = btrfs_super_generation(disk_super);
find_oldest_super_backup(fs_info, generation);
-#ifdef MY_DEF_HERE
- fs_info->compress_type = BTRFS_COMPRESS_DEFAULT;
-#else
+ /*
+ * In the long term, we'll store the compression type in the super
+ * block, and it'll be used for per file compression control.
+ */
fs_info->compress_type = BTRFS_COMPRESS_ZLIB;
-#endif
- ret = btrfs_parse_options(tree_root, options);
+ ret = btrfs_parse_options(tree_root, options, sb->s_flags);
if (ret) {
err = ret;
goto fail_alloc;
@@ -2518,66 +2853,61 @@
features = btrfs_super_incompat_flags(disk_super) &
~BTRFS_FEATURE_INCOMPAT_SUPP;
if (features) {
- printk(KERN_ERR "BTRFS: couldn't mount because of "
- "unsupported optional features (%Lx).\n",
+ btrfs_err(fs_info,
+ "cannot mount because of unsupported optional features (%llx)",
features);
err = -EINVAL;
goto fail_alloc;
}
- if (btrfs_super_leafsize(disk_super) !=
- btrfs_super_nodesize(disk_super)) {
- printk(KERN_ERR "BTRFS: couldn't mount because metadata "
- "blocksizes don't match. node %d leaf %d\n",
- btrfs_super_nodesize(disk_super),
- btrfs_super_leafsize(disk_super));
- err = -EINVAL;
- goto fail_alloc;
- }
- if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
- printk(KERN_ERR "BTRFS: couldn't mount because metadata "
- "blocksize (%d) was too large\n",
- btrfs_super_leafsize(disk_super));
- err = -EINVAL;
- goto fail_alloc;
- }
-
features = btrfs_super_incompat_flags(disk_super);
features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
- printk(KERN_ERR "BTRFS: has skinny extents\n");
+ btrfs_info(fs_info, "has skinny extents");
- if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
+ /*
+ * flag our filesystem as having big metadata blocks if
+ * they are bigger than the page size
+ */
+ if (btrfs_super_nodesize(disk_super) > PAGE_CACHE_SIZE) {
if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
+ btrfs_info(fs_info,
+ "flagging fs with big metadata feature");
features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
}
nodesize = btrfs_super_nodesize(disk_super);
- leafsize = btrfs_super_leafsize(disk_super);
sectorsize = btrfs_super_sectorsize(disk_super);
- stripesize = btrfs_super_stripesize(disk_super);
- fs_info->dirty_metadata_batch = leafsize * (1 + ilog2(nr_cpu_ids));
+ stripesize = sectorsize;
+ fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
+ /*
+ * mixed block groups end up with duplicate but slightly offset
+ * extent buffers for the same range. It leads to corruptions
+ */
if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
- (sectorsize != leafsize)) {
- printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
- "are not allowed for mixed block groups on %s\n",
- sb->s_id);
+ (sectorsize != nodesize)) {
+ btrfs_err(fs_info,
+"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups",
+ nodesize, sectorsize);
goto fail_alloc;
}
+ /*
+ * Needn't use the lock because there is no other task which will
+ * update the flag.
+ */
btrfs_set_super_incompat_flags(disk_super, features);
features = btrfs_super_compat_ro_flags(disk_super) &
~BTRFS_FEATURE_COMPAT_RO_SUPP;
if (!(sb->s_flags & MS_RDONLY) && features) {
- printk(KERN_ERR "BTRFS: couldn't mount RDWR because of "
- "unsupported option features (%Lx).\n",
+ btrfs_err(fs_info,
+ "cannot mount read-write because of unsupported optional features (%llx)",
features);
err = -EINVAL;
goto fail_alloc;
@@ -2585,124 +2915,45 @@
max_active = fs_info->thread_pool_size;
- fs_info->workers =
- btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI,
- max_active, 16);
-
- fs_info->delalloc_workers =
- btrfs_alloc_workqueue("delalloc", flags, max_active, 2);
-
- fs_info->flush_workers =
- btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0);
-
- fs_info->caching_workers =
- btrfs_alloc_workqueue("cache", flags, max_active, 0);
-
- fs_info->submit_workers =
- btrfs_alloc_workqueue("submit", flags,
- min_t(u64, fs_devices->num_devices,
- max_active), 64);
-
- fs_info->fixup_workers =
- btrfs_alloc_workqueue("fixup", flags, 1, 0);
-
- fs_info->endio_workers =
- btrfs_alloc_workqueue("endio", flags, max_active, 4);
- fs_info->endio_meta_workers =
- btrfs_alloc_workqueue("endio-meta", flags, max_active, 4);
-#ifdef MY_DEF_HERE
- fs_info->endio_meta_fix_workers =
- btrfs_alloc_workqueue("endio-meta-fix", flags, max_active, 4);
-#endif
- fs_info->endio_meta_write_workers =
- btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
- fs_info->endio_raid56_workers =
- btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
- fs_info->rmw_workers =
- btrfs_alloc_workqueue("rmw", flags, max_active, 2);
- fs_info->endio_write_workers =
-#ifdef MY_DEF_HERE
- btrfs_alloc_workqueue("endio-write", flags, min_t(unsigned long, 4, max_active), 2);
-#else
- btrfs_alloc_workqueue("endio-write", flags, max_active, 2);
-#endif
- fs_info->endio_freespace_worker =
- btrfs_alloc_workqueue("freespace-write", flags, max_active, 0);
- fs_info->delayed_workers =
- btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0);
- fs_info->readahead_workers =
- btrfs_alloc_workqueue("readahead", flags, max_active, 2);
-#ifdef MY_DEF_HERE
- fs_info->reada_path_workers =
- btrfs_alloc_workqueue("reada-path", flags, max_active, 2);
-#endif
- fs_info->qgroup_rescan_workers =
- btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0);
- fs_info->extent_workers =
- btrfs_alloc_workqueue("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 &&
- fs_info->endio_workers && fs_info->endio_meta_workers &&
- fs_info->endio_meta_write_workers &&
- fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
- 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->fixup_workers && fs_info->extent_workers &&
- fs_info->qgroup_rescan_workers)) {
- err = -ENOMEM;
+ ret = btrfs_init_workqueues(fs_info, fs_devices);
+ if (ret) {
+ err = ret;
goto fail_sb_buffer;
}
fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
- 4 * 1024 * 1024 / PAGE_CACHE_SIZE);
+ SZ_4M / PAGE_CACHE_SIZE);
tree_root->nodesize = nodesize;
- tree_root->leafsize = leafsize;
tree_root->sectorsize = sectorsize;
tree_root->stripesize = stripesize;
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
- if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
- printk(KERN_INFO "BTRFS: valid FS not found on %s\n", sb->s_id);
- goto fail_sb_buffer;
- }
-
- if (sectorsize != PAGE_SIZE) {
- printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) "
- "found on %s\n", (unsigned long)sectorsize, sb->s_id);
- goto fail_sb_buffer;
- }
-
mutex_lock(&fs_info->chunk_mutex);
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
- printk(KERN_WARNING "BTRFS: failed to read the system "
- "array on %s\n", sb->s_id);
+ btrfs_err(fs_info, "failed to read the system array: %d", ret);
goto fail_sb_buffer;
}
- blocksize = btrfs_level_size(tree_root,
- btrfs_super_chunk_root_level(disk_super));
generation = btrfs_super_chunk_root_generation(disk_super);
- __setup_root(nodesize, leafsize, sectorsize, stripesize,
- chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID);
+ __setup_root(nodesize, sectorsize, stripesize, chunk_root,
+ fs_info, BTRFS_CHUNK_TREE_OBJECTID);
chunk_root->node = read_tree_block(chunk_root,
btrfs_super_chunk_root(disk_super),
- blocksize, generation);
- if (!chunk_root->node ||
- !test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
- printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
- sb->s_id);
+ generation);
+ if (IS_ERR(chunk_root->node) ||
+ !extent_buffer_uptodate(chunk_root->node)) {
+ btrfs_err(fs_info, "failed to read chunk root");
+ if (!IS_ERR(chunk_root->node))
+ free_extent_buffer(chunk_root->node);
+ chunk_root->node = NULL;
goto fail_tree_roots;
}
btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
@@ -2713,32 +2964,33 @@
ret = btrfs_read_chunk_tree(chunk_root);
if (ret) {
- printk(KERN_WARNING "BTRFS: failed to read chunk tree on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read chunk tree: %d", ret);
goto fail_tree_roots;
}
- btrfs_close_extra_devices(fs_info, fs_devices, 0);
+ /*
+ * keep the device that is marked to be the target device for the
+ * dev_replace procedure
+ */
+ btrfs_close_extra_devices(fs_devices, 0);
if (!fs_devices->latest_bdev) {
- printk(KERN_CRIT "BTRFS: failed to read devices on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read devices");
goto fail_tree_roots;
}
retry_root_backup:
- blocksize = btrfs_level_size(tree_root,
- btrfs_super_root_level(disk_super));
generation = btrfs_super_generation(disk_super);
tree_root->node = read_tree_block(tree_root,
btrfs_super_root(disk_super),
- blocksize, generation);
- if (!tree_root->node ||
- !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) {
- printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
- sb->s_id);
-
+ generation);
+ if (IS_ERR(tree_root->node) ||
+ !extent_buffer_uptodate(tree_root->node)) {
+ btrfs_warn(fs_info, "failed to read tree root");
+ if (!IS_ERR(tree_root->node))
+ free_extent_buffer(tree_root->node);
+ tree_root->node = NULL;
goto recovery_tree_root;
}
@@ -2746,141 +2998,74 @@
tree_root->commit_root = btrfs_root_node(tree_root);
btrfs_set_root_refs(&tree_root->root_item, 1);
- location.objectid = BTRFS_EXTENT_TREE_OBJECTID;
- location.type = BTRFS_ROOT_ITEM_KEY;
- location.offset = 0;
-
- extent_root = btrfs_read_tree_root(tree_root, &location);
- if (IS_ERR(extent_root)) {
- ret = PTR_ERR(extent_root);
- goto recovery_tree_root;
- }
- set_bit(BTRFS_ROOT_TRACK_DIRTY, &extent_root->state);
- fs_info->extent_root = extent_root;
-
- location.objectid = BTRFS_DEV_TREE_OBJECTID;
- dev_root = btrfs_read_tree_root(tree_root, &location);
- if (IS_ERR(dev_root)) {
- ret = PTR_ERR(dev_root);
- goto recovery_tree_root;
- }
- set_bit(BTRFS_ROOT_TRACK_DIRTY, &dev_root->state);
- fs_info->dev_root = dev_root;
- btrfs_init_devices_late(fs_info);
-
- location.objectid = BTRFS_CSUM_TREE_OBJECTID;
- csum_root = btrfs_read_tree_root(tree_root, &location);
- if (IS_ERR(csum_root)) {
- ret = PTR_ERR(csum_root);
+ mutex_lock(&tree_root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(tree_root,
+ &tree_root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&tree_root->objectid_mutex);
goto recovery_tree_root;
}
- set_bit(BTRFS_ROOT_TRACK_DIRTY, &csum_root->state);
- fs_info->csum_root = csum_root;
- location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
- quota_root = btrfs_read_tree_root(tree_root, &location);
- if (!IS_ERR(quota_root)) {
- set_bit(BTRFS_ROOT_TRACK_DIRTY, &quota_root->state);
- fs_info->quota_enabled = 1;
- fs_info->pending_quota_state = 1;
- fs_info->quota_root = quota_root;
- }
+ ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
- location.objectid = BTRFS_UUID_TREE_OBJECTID;
- uuid_root = btrfs_read_tree_root(tree_root, &location);
- if (IS_ERR(uuid_root)) {
- ret = PTR_ERR(uuid_root);
- if (ret != -ENOENT)
- goto recovery_tree_root;
- create_uuid_tree = true;
- check_uuid_tree = false;
- } else {
- set_bit(BTRFS_ROOT_TRACK_DIRTY, &uuid_root->state);
- fs_info->uuid_root = uuid_root;
- create_uuid_tree = false;
- check_uuid_tree =
- generation != btrfs_super_uuid_tree_generation(disk_super);
- }
-
-#ifdef MY_DEF_HERE
- if (!fs_info->no_block_group_hint) {
- spin_lock_init(&fs_info->block_group_hint_tree_lock);
- location.objectid = BTRFS_BLOCK_GROUP_HINT_TREE_OBJECTID;
- block_group_hint_root = btrfs_read_tree_root(tree_root, &location);
- if (IS_ERR_OR_NULL(block_group_hint_root))
- fs_info->block_group_hint_root = NULL;
- else {
- set_bit(BTRFS_ROOT_TRACK_DIRTY, &block_group_hint_root->state);
- fs_info->block_group_hint_root = block_group_hint_root;
- }
- }
-#endif
+ mutex_unlock(&tree_root->objectid_mutex);
- if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
- location.objectid = BTRFS_FREE_SPACE_TREE_OBJECTID;
- free_space_tree_root = btrfs_read_tree_root(tree_root, &location);
- if (IS_ERR(free_space_tree_root)) {
- ret = PTR_ERR(free_space_tree_root);
+ ret = btrfs_read_roots(fs_info, tree_root);
+ if (ret)
goto recovery_tree_root;
- }
- set_bit(BTRFS_ROOT_TRACK_DIRTY, &free_space_tree_root->state);
- fs_info->free_space_root = free_space_tree_root;
- }
fs_info->generation = generation;
fs_info->last_trans_committed = generation;
ret = btrfs_recover_balance(fs_info);
if (ret) {
- printk(KERN_WARNING "BTRFS: failed to recover balance\n");
+ btrfs_err(fs_info, "failed to recover balance: %d", ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_stats(fs_info);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
- ret);
+ btrfs_err(fs_info, "failed to init dev_stats: %d", ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_replace(fs_info);
if (ret) {
- pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
+ btrfs_err(fs_info, "failed to init dev_replace: %d", ret);
goto fail_block_groups;
}
- btrfs_close_extra_devices(fs_info, fs_devices, 1);
+ btrfs_close_extra_devices(fs_devices, 1);
- ret = btrfs_sysfs_add_one(fs_info);
+ ret = btrfs_sysfs_add_fsid(fs_devices, NULL);
if (ret) {
- pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
+ btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
+ ret);
goto fail_block_groups;
}
- ret = btrfs_init_space_info(fs_info);
+ ret = btrfs_sysfs_add_device(fs_devices);
if (ret) {
- printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
- goto fail_sysfs;
+ btrfs_err(fs_info, "failed to init sysfs device interface: %d",
+ ret);
+ goto fail_fsdev_sysfs;
}
-#ifdef MY_DEF_HERE
- fs_info->can_fix_meta_key = CAN_FIX_META_KEY;
-#endif
-
- ret = btrfs_read_block_groups(extent_root);
+ ret = btrfs_sysfs_add_mounted(fs_info);
+ if (ret) {
+ btrfs_err(fs_info, "failed to init sysfs interface: %d", ret);
+ goto fail_fsdev_sysfs;
+ }
-#ifdef MY_DEF_HERE
- btrfs_destroy_workqueue(fs_info->reada_path_workers);
- fs_info->reada_path_workers = NULL;
-#endif
-#ifdef MY_DEF_HERE
- fs_info->can_fix_meta_key = STOP_FIX_META_KEY;
- btrfs_destroy_workqueue(fs_info->endio_meta_fix_workers);
- fs_info->endio_meta_fix_workers = NULL;
-#endif
+ ret = btrfs_init_space_info(fs_info);
+ if (ret) {
+ btrfs_err(fs_info, "failed to initialize space info: %d", ret);
+ goto fail_sysfs;
+ }
+ ret = btrfs_read_block_groups(fs_info->extent_root);
if (ret) {
- printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
+ btrfs_err(fs_info, "failed to read block groups: %d", ret);
goto fail_sysfs;
}
fs_info->num_tolerated_disk_barrier_failures =
@@ -2888,8 +3073,10 @@
if (fs_info->fs_devices->missing_devices >
fs_info->num_tolerated_disk_barrier_failures &&
!(sb->s_flags & MS_RDONLY)) {
- printk(KERN_WARNING "BTRFS: "
- "too many missing devices, writeable mount is not allowed\n");
+ btrfs_warn(fs_info,
+"missing devices (%llu) exceeds the limit (%d), writeable mount is not allowed",
+ fs_info->fs_devices->missing_devices,
+ fs_info->num_tolerated_disk_barrier_failures);
goto fail_sysfs;
}
@@ -2904,78 +3091,42 @@
if (IS_ERR(fs_info->transaction_kthread))
goto fail_cleaner;
- if (!btrfs_test_opt(tree_root, SSD) &&
- !btrfs_test_opt(tree_root, NOSSD) &&
+ if (!btrfs_test_opt(tree_root->fs_info, SSD) &&
+ !btrfs_test_opt(tree_root->fs_info, NOSSD) &&
!fs_info->fs_devices->rotating) {
- printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
- "mode\n");
+ btrfs_info(fs_info, "detected SSD devices, enabling SSD mode");
btrfs_set_opt(fs_info->mount_opt, SSD);
}
- if (btrfs_test_opt(tree_root, CHANGE_INODE_CACHE))
- btrfs_set_opt(tree_root->fs_info->mount_opt, INODE_MAP_CACHE);
+ /*
+ * Mount does not set all options immediatelly, we can do it now and do
+ * not have to wait for transaction commit
+ */
+ btrfs_apply_pending_changes(fs_info);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
- if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
+ if (btrfs_test_opt(tree_root->fs_info, CHECK_INTEGRITY)) {
ret = btrfsic_mount(tree_root, fs_devices,
- btrfs_test_opt(tree_root,
+ btrfs_test_opt(tree_root->fs_info,
CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ?
1 : 0,
fs_info->check_integrity_print_mask);
if (ret)
- printk(KERN_WARNING "BTRFS: failed to initialize"
- " integrity check module %s\n", sb->s_id);
+ btrfs_warn(fs_info,
+ "failed to initialize integrity check module: %d",
+ ret);
}
#endif
ret = btrfs_read_qgroup_config(fs_info);
if (ret)
goto fail_trans_kthread;
- if (btrfs_super_log_root(disk_super) != 0) {
- u64 bytenr = btrfs_super_log_root(disk_super);
-
- if (fs_devices->rw_devices == 0) {
- printk(KERN_WARNING "BTRFS: log replay required "
- "on RO media\n");
- err = -EIO;
- goto fail_qgroup;
- }
- blocksize =
- btrfs_level_size(tree_root,
- btrfs_super_log_root_level(disk_super));
-
- log_tree_root = btrfs_alloc_root(fs_info);
- if (!log_tree_root) {
- err = -ENOMEM;
- goto fail_qgroup;
- }
-
- __setup_root(nodesize, leafsize, sectorsize, stripesize,
- log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID);
-
- log_tree_root->node = read_tree_block(tree_root, bytenr,
- blocksize,
- generation + 1);
- if (!log_tree_root->node ||
- !extent_buffer_uptodate(log_tree_root->node)) {
- printk(KERN_ERR "BTRFS: failed to read log tree\n");
- free_extent_buffer(log_tree_root->node);
- kfree(log_tree_root);
- goto fail_qgroup;
- }
-
- ret = btrfs_recover_log_trees(log_tree_root);
+ /* do not make disk changes in broken FS or nologreplay is given */
+ if (btrfs_super_log_root(disk_super) != 0 &&
+ !btrfs_test_opt(tree_root->fs_info, NOLOGREPLAY)) {
+ ret = btrfs_replay_log(fs_info, fs_devices);
if (ret) {
- btrfs_error(tree_root->fs_info, ret,
- "Failed to recover log tree");
- free_extent_buffer(log_tree_root->node);
- kfree(log_tree_root);
- goto fail_qgroup;
- }
-
- if (sb->s_flags & MS_RDONLY) {
- ret = btrfs_commit_super(tree_root);
- if (ret)
+ err = ret;
goto fail_qgroup;
}
}
@@ -2993,8 +3144,8 @@
ret = btrfs_recover_relocation(tree_root);
mutex_unlock(&fs_info->cleaner_mutex);
if (ret < 0) {
- printk(KERN_WARNING
- "BTRFS: failed to recover relocation\n");
+ btrfs_warn(fs_info, "failed to recover relocation: %d",
+ ret);
err = -EINVAL;
goto fail_qgroup;
}
@@ -3013,7 +3164,7 @@
if (sb->s_flags & MS_RDONLY)
return 0;
- if (btrfs_test_opt(tree_root, CLEAR_CACHE) &&
+ if (btrfs_test_opt(fs_info, CLEAR_CACHE) &&
btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
clear_free_space_tree = 1;
} else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
@@ -3033,13 +3184,13 @@
}
}
- if (btrfs_test_opt(tree_root, FREE_SPACE_TREE) &&
+ if (btrfs_test_opt(tree_root->fs_info, FREE_SPACE_TREE) &&
!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
- pr_info("BTRFS: creating free space tree\n");
+ btrfs_info(fs_info, "creating free space tree");
ret = btrfs_create_free_space_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to create free space tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to create free space tree: %d", ret);
close_ctree(tree_root);
return ret;
}
@@ -3056,44 +3207,50 @@
ret = btrfs_resume_balance_async(fs_info);
if (ret) {
- printk(KERN_WARNING "BTRFS: failed to resume balance\n");
+ btrfs_warn(fs_info, "failed to resume balance: %d", ret);
close_ctree(tree_root);
return ret;
}
ret = btrfs_resume_dev_replace_async(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to resume dev_replace\n");
+ btrfs_warn(fs_info, "failed to resume device replace: %d", ret);
close_ctree(tree_root);
return ret;
}
btrfs_qgroup_rescan_resume(fs_info);
- if (create_uuid_tree) {
- pr_info("BTRFS: creating UUID tree\n");
+ if (!fs_info->uuid_root) {
+ btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to create the UUID tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to create the UUID tree: %d", ret);
close_ctree(tree_root);
return ret;
}
- } else if (check_uuid_tree ||
- btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) {
- pr_info("BTRFS: checking UUID tree\n");
+ } else if (btrfs_test_opt(tree_root->fs_info, RESCAN_UUID_TREE) ||
+ fs_info->generation !=
+ btrfs_super_uuid_tree_generation(disk_super)) {
+ btrfs_info(fs_info, "checking UUID tree");
ret = btrfs_check_uuid_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to check the UUID tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to check the UUID tree: %d", ret);
close_ctree(tree_root);
return ret;
}
} else {
- fs_info->update_uuid_tree_gen = 1;
+ set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
}
+ set_bit(BTRFS_FS_OPEN, &fs_info->flags);
- fs_info->open = 1;
+ /*
+ * backuproot only affect mount behavior, and if open_ctree succeeded,
+ * no need to keep the flag
+ */
+ btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
return 0;
@@ -3106,10 +3263,17 @@
fail_cleaner:
kthread_stop(fs_info->cleaner_kthread);
+ /*
+ * make sure we're done with the btree inode before we stop our
+ * kthreads
+ */
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
fail_sysfs:
- btrfs_sysfs_remove_one(fs_info);
+ btrfs_sysfs_remove_mounted(fs_info);
+
+fail_fsdev_sysfs:
+ btrfs_sysfs_remove_fsid(fs_info->fs_devices);
fail_block_groups:
btrfs_put_block_group_cache(fs_info);
@@ -3126,11 +3290,8 @@
btrfs_mapping_tree_free(&fs_info->mapping_tree);
iput(fs_info->btree_inode);
-#ifdef MY_DEF_HERE
-#else
fail_bio_counter:
percpu_counter_destroy(&fs_info->bio_counter);
-#endif
fail_delalloc_bytes:
percpu_counter_destroy(&fs_info->delalloc_bytes);
fail_dirty_metadata_bytes:
@@ -3142,17 +3303,18 @@
fail:
btrfs_free_stripe_hash_table(fs_info);
btrfs_close_devices(fs_info->fs_devices);
-
return err;
recovery_tree_root:
- if (!btrfs_test_opt(tree_root, RECOVERY))
+ if (!btrfs_test_opt(tree_root->fs_info, USEBACKUPROOT))
goto fail_tree_roots;
free_root_pointers(fs_info, 0);
+ /* don't use the log in recovery mode, it won't be valid */
btrfs_set_super_log_root(disk_super, 0);
+ /* we can't trust the free space cache either */
btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);
ret = next_root_backup(fs_info, fs_info->super_copy,
@@ -3170,10 +3332,12 @@
struct btrfs_device *device = (struct btrfs_device *)
bh->b_private;
- printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to "
- "I/O error on %s\n",
+ btrfs_warn_rl_in_rcu(device->dev_root->fs_info,
+ "lost page write due to IO error on %s",
rcu_str_deref(device->name));
-
+ /* note, we dont' set_buffer_write_io_error because we have
+ * our own ways of dealing with the IO errors
+ */
clear_buffer_uptodate(bh);
btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS);
}
@@ -3181,32 +3345,58 @@
put_bh(bh);
}
-struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
+int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
+ struct buffer_head **bh_ret)
{
struct buffer_head *bh;
- struct buffer_head *latest = NULL;
struct btrfs_super_block *super;
- int i;
- u64 transid = 0;
u64 bytenr;
- for (i = 0; i < 1; i++) {
- bytenr = btrfs_sb_offset(i);
- if (bytenr + BTRFS_SUPER_INFO_SIZE >=
- i_size_read(bdev->bd_inode))
- break;
- bh = __bread(bdev, bytenr / 4096,
- BTRFS_SUPER_INFO_SIZE);
+ bytenr = btrfs_sb_offset(copy_num);
+ if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode))
+ return -EINVAL;
+
+ bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE);
+ /*
+ * If we fail to read from the underlying devices, as of now
+ * the best option we have is to mark it EIO.
+ */
if (!bh)
- continue;
+ return -EIO;
super = (struct btrfs_super_block *)bh->b_data;
if (btrfs_super_bytenr(super) != bytenr ||
btrfs_super_magic(super) != BTRFS_MAGIC) {
brelse(bh);
- continue;
+ return -EINVAL;
}
+ *bh_ret = bh;
+ return 0;
+}
+
+
+struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
+{
+ struct buffer_head *bh;
+ struct buffer_head *latest = NULL;
+ struct btrfs_super_block *super;
+ int i;
+ u64 transid = 0;
+ int ret = -EINVAL;
+
+ /* we would like to check all the supers, but that would make
+ * a btrfs mount succeed after a mkfs from a different FS.
+ * So, we need to add a special mount option to scan for
+ * later supers, using BTRFS_SUPER_MIRROR_MAX instead
+ */
+ for (i = 0; i < 1; i++) {
+ ret = btrfs_read_dev_one_super(bdev, i, &bh);
+ if (ret)
+ continue;
+
+ super = (struct btrfs_super_block *)bh->b_data;
+
if (!latest || btrfs_super_generation(super) > transid) {
brelse(latest);
latest = bh;
@@ -3215,9 +3405,24 @@
brelse(bh);
}
}
+
+ if (!latest)
+ return ERR_PTR(ret);
+
return latest;
}
+/*
+ * this should be called twice, once with wait == 0 and
+ * once with wait == 1. When wait == 0 is done, all the buffer heads
+ * we write are pinned.
+ *
+ * They are released when wait == 1 is done.
+ * max_mirrors must be the same for both runs, and it indicates how
+ * many supers on this one device should be written.
+ *
+ * max_mirrors == 0 means to write them all.
+ */
static int write_dev_supers(struct btrfs_device *device,
struct btrfs_super_block *sb,
int do_barriers, int wait, int max_mirrors)
@@ -3234,7 +3439,8 @@
for (i = 0; i < max_mirrors; i++) {
bytenr = btrfs_sb_offset(i);
- if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
+ if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+ device->commit_total_bytes)
break;
if (wait) {
@@ -3248,8 +3454,10 @@
if (!buffer_uptodate(bh))
errors++;
+ /* drop our reference */
brelse(bh);
+ /* drop the reference from the wait == 0 run */
brelse(bh);
continue;
} else {
@@ -3262,17 +3470,23 @@
BTRFS_CSUM_SIZE);
btrfs_csum_final(crc, sb->csum);
+ /*
+ * one reference for us, and we leave it for the
+ * caller
+ */
bh = __getblk(device->bdev, bytenr / 4096,
BTRFS_SUPER_INFO_SIZE);
if (!bh) {
- printk(KERN_ERR "BTRFS: couldn't get super "
- "buffer head for bytenr %Lu\n", bytenr);
+ btrfs_err(device->dev_root->fs_info,
+ "couldn't get super buffer head for bytenr %llu",
+ bytenr);
errors++;
continue;
}
memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE);
+ /* one reference for submit_bh */
get_bh(bh);
set_buffer_uptodate(bh);
@@ -3281,6 +3495,10 @@
bh->b_private = device;
}
+ /*
+ * we fua the first super. The others we allow
+ * to go down lazy.
+ */
if (i == 0)
ret = btrfsic_submit_bh(WRITE_FUA, bh);
else
@@ -3291,6 +3509,10 @@
return errors < i ? 0 : -1;
}
+/*
+ * endio for the write_dev_flush, this will wake anyone waiting
+ * for the barrier when it is done
+ */
static void btrfs_end_empty_barrier(struct bio *bio, int err)
{
if (err) {
@@ -3303,6 +3525,13 @@
bio_put(bio);
}
+/*
+ * trigger flushes for one the devices. If you pass wait == 0, the flushes are
+ * sent down. With wait == 1, it waits for the previous flush.
+ *
+ * any device where the flush fails with eopnotsupp are flagged as not-barrier
+ * capable
+ */
static int write_dev_flush(struct btrfs_device *device, int wait)
{
struct bio *bio;
@@ -3328,12 +3557,17 @@
BTRFS_DEV_STAT_FLUSH_ERRS);
}
+ /* drop the reference from the wait == 0 run */
bio_put(bio);
device->flush_bio = NULL;
return ret;
}
+ /*
+ * one reference for us, and we leave it for the
+ * caller
+ */
device->flush_bio = NULL;
bio = btrfs_io_bio_alloc(GFP_NOFS, 0);
if (!bio)
@@ -3351,6 +3585,10 @@
return 0;
}
+/*
+ * send an empty flush down to each device in parallel,
+ * then wait for them
+ */
static int barrier_all_devices(struct btrfs_fs_info *info)
{
struct list_head *head;
@@ -3359,6 +3597,7 @@
int errors_wait = 0;
int ret;
+ /* send down all the barriers */
head = &info->fs_devices->devices;
list_for_each_entry_rcu(dev, head, dev_list) {
if (dev->missing)
@@ -3375,6 +3614,7 @@
errors_send++;
}
+ /* wait for all the barriers */
list_for_each_entry_rcu(dev, head, dev_list) {
if (dev->missing)
continue;
@@ -3395,6 +3635,35 @@
return 0;
}
+int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
+{
+ int raid_type;
+ int min_tolerated = INT_MAX;
+
+ if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 ||
+ (flags & BTRFS_AVAIL_ALLOC_BIT_SINGLE))
+ min_tolerated = min(min_tolerated,
+ btrfs_raid_array[BTRFS_RAID_SINGLE].
+ tolerated_failures);
+
+ for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
+ if (raid_type == BTRFS_RAID_SINGLE)
+ continue;
+ if (!(flags & btrfs_raid_group[raid_type]))
+ continue;
+ min_tolerated = min(min_tolerated,
+ btrfs_raid_array[raid_type].
+ tolerated_failures);
+ }
+
+ if (min_tolerated == INT_MAX) {
+ pr_warn("BTRFS: unknown raid flag: %llu\n", flags);
+ min_tolerated = 0;
+ }
+
+ return min_tolerated;
+}
+
int btrfs_calc_num_tolerated_disk_barrier_failures(
struct btrfs_fs_info *fs_info)
{
@@ -3404,13 +3673,12 @@
BTRFS_BLOCK_GROUP_SYSTEM,
BTRFS_BLOCK_GROUP_METADATA,
BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
- int num_types = 4;
int i;
int c;
int num_tolerated_disk_barrier_failures =
(int)fs_info->fs_devices->num_devices;
- for (i = 0; i < num_types; i++) {
+ for (i = 0; i < ARRAY_SIZE(types); i++) {
struct btrfs_space_info *tmp;
sinfo = NULL;
@@ -3428,33 +3696,21 @@
down_read(&sinfo->groups_sem);
for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
- if (!list_empty(&sinfo->block_groups[c])) {
u64 flags;
- btrfs_get_block_group_info(
- &sinfo->block_groups[c], &space);
- if (space.total_bytes == 0 ||
- space.used_bytes == 0)
+ if (list_empty(&sinfo->block_groups[c]))
+ continue;
+
+ btrfs_get_block_group_info(&sinfo->block_groups[c],
+ &space);
+ if (space.total_bytes == 0 || space.used_bytes == 0)
continue;
flags = space.flags;
- if (num_tolerated_disk_barrier_failures > 0 &&
- ((flags & (BTRFS_BLOCK_GROUP_DUP |
- BTRFS_BLOCK_GROUP_RAID0)) ||
- ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK)
- == 0)))
- num_tolerated_disk_barrier_failures = 0;
- else if (num_tolerated_disk_barrier_failures > 1) {
- if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID5 |
- BTRFS_BLOCK_GROUP_RAID10)) {
- num_tolerated_disk_barrier_failures = 1;
- } else if (flags &
- BTRFS_BLOCK_GROUP_RAID6) {
- num_tolerated_disk_barrier_failures = 2;
- }
- }
- }
+ num_tolerated_disk_barrier_failures = min(
+ num_tolerated_disk_barrier_failures,
+ btrfs_get_num_tolerated_disk_barrier_failures(
+ flags));
}
up_read(&sinfo->groups_sem);
}
@@ -3474,7 +3730,7 @@
int total_errors = 0;
u64 flags;
- do_barriers = !btrfs_test_opt(root, NOBARRIER);
+ do_barriers = !btrfs_test_opt(root->fs_info, NOBARRIER);
backup_super_roots(root->fs_info);
sb = root->fs_info->super_for_commit;
@@ -3489,7 +3745,7 @@
if (ret) {
mutex_unlock(
&root->fs_info->fs_devices->device_list_mutex);
- btrfs_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"errors while submitting device barriers.");
return ret;
}
@@ -3506,8 +3762,10 @@
btrfs_set_stack_device_generation(dev_item, 0);
btrfs_set_stack_device_type(dev_item, dev->type);
btrfs_set_stack_device_id(dev_item, dev->devid);
- btrfs_set_stack_device_total_bytes(dev_item, dev->total_bytes);
- btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used);
+ btrfs_set_stack_device_total_bytes(dev_item,
+ dev->commit_total_bytes);
+ btrfs_set_stack_device_bytes_used(dev_item,
+ dev->commit_bytes_used);
btrfs_set_stack_device_io_align(dev_item, dev->io_align);
btrfs_set_stack_device_io_width(dev_item, dev->io_width);
btrfs_set_stack_device_sector_size(dev_item, dev->sector_size);
@@ -3526,7 +3784,8 @@
total_errors);
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
- btrfs_error(root->fs_info, -EIO,
+ /* FUA is masked off if unsupported and can't be the reason */
+ btrfs_handle_fs_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
@@ -3544,7 +3803,7 @@
}
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
if (total_errors > max_errors) {
- btrfs_error(root->fs_info, -EIO,
+ btrfs_handle_fs_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
@@ -3557,6 +3816,7 @@
return write_all_supers(root, max_mirrors);
}
+/* Drop a fs root from the radix tree and free it. */
void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root)
{
@@ -3568,8 +3828,15 @@
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
btrfs_free_log(NULL, root);
+ if (root->reloc_root) {
+ free_extent_buffer(root->reloc_root->node);
+ free_extent_buffer(root->reloc_root->commit_root);
+ btrfs_put_fs_root(root->reloc_root);
+ root->reloc_root = NULL;
+ }
+ }
if (root->free_ino_pinned)
__btrfs_remove_free_space_cache(root->free_ino_pinned);
@@ -3580,7 +3847,7 @@
static void free_fs_root(struct btrfs_root *root)
{
- iput(root->cache_inode);
+ iput(root->ino_cache_inode);
WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
btrfs_free_block_rsv(root, root->orphan_block_rsv);
root->orphan_block_rsv = NULL;
@@ -3622,12 +3889,12 @@
root_objectid = gang[ret - 1]->root_key.objectid + 1;
for (i = 0; i < ret; i++) {
-
+ /* Avoid to grab roots in dead_roots */
if (btrfs_root_refs(&gang[i]->root_item) == 0) {
gang[i] = NULL;
continue;
}
-
+ /* grab all the search result for later use */
gang[i] = btrfs_grab_fs_root(gang[i]);
}
srcu_read_unlock(&fs_info->subvol_srcu, index);
@@ -3644,6 +3911,7 @@
root_objectid++;
}
+ /* release the uncleaned roots due to error */
for (; i < ret; i++) {
if (gang[i])
btrfs_put_fs_root(gang[i]);
@@ -3660,6 +3928,7 @@
mutex_unlock(&root->fs_info->cleaner_mutex);
wake_up_process(root->fs_info->cleaner_kthread);
+ /* wait until ongoing cleanup work done */
down_write(&root->fs_info->cleanup_work_sem);
up_write(&root->fs_info->cleanup_work_sem);
@@ -3669,35 +3938,48 @@
return btrfs_commit_transaction(trans, root);
}
-int close_ctree(struct btrfs_root *root)
+void close_ctree(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
- fs_info->closing = 1;
- smp_mb();
+ set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
- down(&fs_info->uuid_tree_rescan_sem);
+ /* wait for the qgroup rescan worker to stop */
+ btrfs_qgroup_wait_for_completion(fs_info, false);
+ /* wait for the uuid_scan task to finish */
+ down(&fs_info->uuid_tree_rescan_sem);
+ /* avoid complains from lockdep et al., set sem back to initial state */
up(&fs_info->uuid_tree_rescan_sem);
+ /* pause restriper - we want to resume on mount */
btrfs_pause_balance(fs_info);
btrfs_dev_replace_suspend_for_unmount(fs_info);
btrfs_scrub_cancel(fs_info);
+ /* wait for any defraggers to finish */
wait_event(fs_info->transaction_wait,
(atomic_read(&fs_info->defrag_running) == 0));
+ /* clear out the rbtree of defraggable inodes */
btrfs_cleanup_defrag_inodes(fs_info);
cancel_work_sync(&fs_info->async_reclaim_work);
if (!(fs_info->sb->s_flags & MS_RDONLY)) {
+ /*
+ * If the cleaner thread is stopped and there are
+ * block groups queued for removal, the deletion will be
+ * skipped when we quit the cleaner thread.
+ */
+ btrfs_delete_unused_bgs(root->fs_info);
+
ret = btrfs_commit_super(root);
if (ret)
- btrfs_err(root->fs_info, "commit super ret %d", ret);
+ btrfs_err(fs_info, "commit super ret %d", ret);
}
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
@@ -3706,17 +3988,17 @@
kthread_stop(fs_info->transaction_kthread);
kthread_stop(fs_info->cleaner_kthread);
- fs_info->closing = 2;
- smp_mb();
+ set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
- btrfs_free_qgroup_config(root->fs_info);
+ btrfs_free_qgroup_config(fs_info);
if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
- btrfs_info(root->fs_info, "at unmount delalloc count %lld",
+ btrfs_info(fs_info, "at unmount delalloc count %lld",
percpu_counter_sum(&fs_info->delalloc_bytes));
}
- btrfs_sysfs_remove_one(fs_info);
+ btrfs_sysfs_remove_mounted(fs_info);
+ btrfs_sysfs_remove_fsid(fs_info->fs_devices);
btrfs_free_fs_roots(fs_info);
@@ -3724,16 +4006,20 @@
btrfs_free_block_groups(fs_info);
+ /*
+ * we must make sure there is not any read request to
+ * submit after we stopping all workers.
+ */
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
btrfs_stop_all_workers(fs_info);
- fs_info->open = 0;
+ clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
free_root_pointers(fs_info, 1);
iput(fs_info->btree_inode);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
- if (btrfs_test_opt(root, CHECK_INTEGRITY))
+ if (btrfs_test_opt(root->fs_info, CHECK_INTEGRITY))
btrfsic_unmount(root, fs_info->fs_devices);
#endif
@@ -3742,16 +4028,13 @@
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
percpu_counter_destroy(&fs_info->delalloc_bytes);
-#ifdef MY_DEF_HERE
-#else
percpu_counter_destroy(&fs_info->bio_counter);
-#endif
bdi_destroy(&fs_info->bdi);
cleanup_srcu_struct(&fs_info->subvol_srcu);
btrfs_free_stripe_hash_table(fs_info);
- btrfs_free_block_rsv(root, root->orphan_block_rsv);
+ __btrfs_free_block_rsv(root->orphan_block_rsv);
root->orphan_block_rsv = NULL;
lock_chunks(root);
@@ -3764,7 +4047,6 @@
free_extent_map(em);
}
unlock_chunks(root);
- return 0;
}
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
@@ -3784,11 +4066,6 @@
return !ret;
}
-int btrfs_set_buffer_uptodate(struct extent_buffer *buf)
-{
- return set_extent_buffer_uptodate(buf);
-}
-
void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
{
struct btrfs_root *root;
@@ -3796,22 +4073,24 @@
int was_dirty;
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-
+ /*
+ * This is a fast path so only do this check if we have sanity tests
+ * enabled. Normal people shouldn't be marking dummy buffers as dirty
+ * outside of the sanity tests.
+ */
if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags)))
return;
#endif
root = BTRFS_I(buf->pages[0]->mapping->host)->root;
btrfs_assert_tree_locked(buf);
if (transid != root->fs_info->generation)
- WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, "
- "found %llu running %llu\n",
+ WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n",
buf->start, transid, root->fs_info->generation);
was_dirty = set_extent_buffer_dirty(buf);
if (!was_dirty)
__percpu_counter_add(&root->fs_info->dirty_metadata_bytes,
buf->len,
root->fs_info->dirty_metadata_batch);
-
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) {
btrfs_print_leaf(root, buf);
@@ -3823,7 +4102,10 @@
static void __btrfs_btree_balance_dirty(struct btrfs_root *root,
int flush_delayed)
{
-
+ /*
+ * looks as though older kernels can get into trouble with
+ * this code, they end up stuck in balance_dirty_pages forever
+ */
int ret;
if (current->flags & PF_MEMALLOC)
@@ -3838,7 +4120,6 @@
balance_dirty_pages_ratelimited(
root->fs_info->btree_inode->i_mapping);
}
- return;
}
void btrfs_btree_balance_dirty(struct btrfs_root *root)
@@ -3854,14 +4135,152 @@
int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
{
struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
- return btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
+ return btree_read_extent_buffer_pages(root, buf, parent_transid);
}
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int read_only)
{
+ struct btrfs_super_block *sb = fs_info->super_copy;
+ u64 nodesize = btrfs_super_nodesize(sb);
+ u64 sectorsize = btrfs_super_sectorsize(sb);
+ int ret = 0;
- return 0;
+ if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
+ printk(KERN_ERR "BTRFS: no valid FS found\n");
+ ret = -EINVAL;
+ }
+ if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)
+ printk(KERN_WARNING "BTRFS: unrecognized super flag: %llu\n",
+ btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
+ if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
+ printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
+ btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+ if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
+ printk(KERN_ERR "BTRFS: chunk_root level too big: %d >= %d\n",
+ btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+ if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
+ printk(KERN_ERR "BTRFS: log_root level too big: %d >= %d\n",
+ btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+
+ /*
+ * Check sectorsize and nodesize first, other check will need it.
+ * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
+ */
+ if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+ sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize);
+ ret = -EINVAL;
+ }
+ /* Only PAGE SIZE is supported yet */
+ if (sectorsize != PAGE_CACHE_SIZE) {
+ printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n",
+ sectorsize, PAGE_CACHE_SIZE);
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
+ nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize);
+ ret = -EINVAL;
+ }
+ if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
+ printk(KERN_ERR "BTRFS: invalid leafsize %u, should be %llu\n",
+ le32_to_cpu(sb->__unused_leafsize),
+ nodesize);
+ ret = -EINVAL;
+ }
+
+ /* Root alignment check */
+ if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
+ printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+ btrfs_super_root(sb));
+ ret = -EINVAL;
+ }
+ if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
+ printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n",
+ btrfs_super_chunk_root(sb));
+ ret = -EINVAL;
+ }
+ if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
+ printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
+ btrfs_super_log_root(sb));
+ ret = -EINVAL;
+ }
+
+ if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
+ printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n",
+ fs_info->fsid, sb->dev_item.fsid);
+ ret = -EINVAL;
+ }
+
+ /*
+ * Hint to catch really bogus numbers, bitflips or so, more exact checks are
+ * done later
+ */
+ if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+ btrfs_err(fs_info, "bytes_used is too small %llu",
+ btrfs_super_bytes_used(sb));
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+ btrfs_err(fs_info, "invalid stripesize %u",
+ btrfs_super_stripesize(sb));
+ ret = -EINVAL;
+ }
+ if (btrfs_super_num_devices(sb) > (1UL << 31))
+ printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
+ btrfs_super_num_devices(sb));
+ if (btrfs_super_num_devices(sb) == 0) {
+ printk(KERN_ERR "BTRFS: number of devices is 0\n");
+ ret = -EINVAL;
+ }
+
+ if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
+ printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
+ btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
+ ret = -EINVAL;
+ }
+
+ /*
+ * Obvious sys_chunk_array corruptions, it must hold at least one key
+ * and one chunk
+ */
+ if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
+ printk(KERN_ERR "BTRFS: system chunk array too big %u > %u\n",
+ btrfs_super_sys_array_size(sb),
+ BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
+ ret = -EINVAL;
+ }
+ if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+ + sizeof(struct btrfs_chunk)) {
+ printk(KERN_ERR "BTRFS: system chunk array too small %u < %zu\n",
+ btrfs_super_sys_array_size(sb),
+ sizeof(struct btrfs_disk_key)
+ + sizeof(struct btrfs_chunk));
+ ret = -EINVAL;
+ }
+
+ /*
+ * The generation is a global counter, we'll trust it more than the others
+ * but it's still possible that it's the one that's wrong.
+ */
+ if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
+ printk(KERN_WARNING
+ "BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n",
+ btrfs_super_generation(sb), btrfs_super_chunk_root_generation(sb));
+ if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
+ && btrfs_super_cache_generation(sb) != (u64)-1)
+ printk(KERN_WARNING
+ "BTRFS: suspicious: generation < cache_generation: %llu < %llu\n",
+ btrfs_super_generation(sb), btrfs_super_cache_generation(sb));
+
+ return ret;
}
static void btrfs_error_commit_super(struct btrfs_root *root)
@@ -3873,6 +4292,7 @@
down_write(&root->fs_info->cleanup_work_sem);
up_write(&root->fs_info->cleanup_work_sem);
+ /* cleanup FS via transaction */
btrfs_cleanup_transaction(root);
}
@@ -3881,7 +4301,10 @@
struct btrfs_ordered_extent *ordered;
spin_lock(&root->ordered_extent_lock);
-
+ /*
+ * This will just short circuit the ordered completion stuff which will
+ * make sure the ordered extent gets properly cleaned up.
+ */
list_for_each_entry(ordered, &root->ordered_extents,
root_extent_list)
set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
@@ -3931,6 +4354,7 @@
while ((node = rb_first(&delayed_refs->href_root)) != NULL) {
struct btrfs_delayed_ref_head *head;
+ struct btrfs_delayed_ref_node *tmp;
bool pin_bytes = false;
head = rb_entry(node, struct btrfs_delayed_ref_head,
@@ -3946,11 +4370,12 @@
continue;
}
spin_lock(&head->lock);
- while ((node = rb_first(&head->ref_root)) != NULL) {
- ref = rb_entry(node, struct btrfs_delayed_ref_node,
- rb_node);
+ list_for_each_entry_safe_reverse(ref, tmp, &head->ref_list,
+ list) {
ref->in_tree = 0;
- rb_erase(&ref->rb_node, &head->ref_root);
+ list_del(&ref->list);
+ if (!list_empty(&ref->add_list))
+ list_del(&ref->add_list);
atomic_dec(&delayed_refs->num_entries);
btrfs_put_delayed_ref(ref);
}
@@ -4047,11 +4472,10 @@
if (ret)
break;
- clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
+ clear_extent_bits(dirty_pages, start, end, mark);
while (start <= end) {
- eb = btrfs_find_tree_block(root, start,
- root->leafsize);
- start += root->leafsize;
+ eb = btrfs_find_tree_block(root->fs_info, start);
+ start += root->nodesize;
if (!eb)
continue;
wait_on_extent_buffer_writeback(eb);
@@ -4083,7 +4507,7 @@
if (ret)
break;
- clear_extent_dirty(unpin, start, end, GFP_NOFS);
+ clear_extent_dirty(unpin, start, end);
btrfs_error_unpin_extent_range(root, start, end);
cond_resched();
}
@@ -4100,9 +4524,80 @@
return 0;
}
+static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
+{
+ struct inode *inode;
+
+ inode = cache->io_ctl.inode;
+ if (inode) {
+ invalidate_inode_pages2(inode->i_mapping);
+ BTRFS_I(inode)->generation = 0;
+ cache->io_ctl.inode = NULL;
+ iput(inode);
+ }
+ btrfs_put_block_group(cache);
+}
+
+void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
+ struct btrfs_root *root)
+{
+ struct btrfs_block_group_cache *cache;
+
+ spin_lock(&cur_trans->dirty_bgs_lock);
+ while (!list_empty(&cur_trans->dirty_bgs)) {
+ cache = list_first_entry(&cur_trans->dirty_bgs,
+ struct btrfs_block_group_cache,
+ dirty_list);
+ if (!cache) {
+ btrfs_err(root->fs_info,
+ "orphan block group dirty_bgs list");
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+ return;
+ }
+
+ if (!list_empty(&cache->io_list)) {
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+ list_del_init(&cache->io_list);
+ btrfs_cleanup_bg_io(cache);
+ spin_lock(&cur_trans->dirty_bgs_lock);
+ }
+
+ list_del_init(&cache->dirty_list);
+ spin_lock(&cache->lock);
+ cache->disk_cache_state = BTRFS_DC_ERROR;
+ spin_unlock(&cache->lock);
+
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+ btrfs_put_block_group(cache);
+ spin_lock(&cur_trans->dirty_bgs_lock);
+ }
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+
+ while (!list_empty(&cur_trans->io_bgs)) {
+ cache = list_first_entry(&cur_trans->io_bgs,
+ struct btrfs_block_group_cache,
+ io_list);
+ if (!cache) {
+ btrfs_err(root->fs_info,
+ "orphan block group on io_bgs list");
+ return;
+ }
+
+ list_del_init(&cache->io_list);
+ spin_lock(&cache->lock);
+ cache->disk_cache_state = BTRFS_DC_ERROR;
+ spin_unlock(&cache->lock);
+ btrfs_cleanup_bg_io(cache);
+ }
+}
+
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_root *root)
{
+ btrfs_cleanup_dirty_bgs(cur_trans, root);
+ ASSERT(list_empty(&cur_trans->dirty_bgs));
+ ASSERT(list_empty(&cur_trans->io_bgs));
+
btrfs_destroy_delayed_refs(cur_trans, root);
cur_trans->state = TRANS_STATE_COMMIT_START;
@@ -4122,6 +4617,10 @@
cur_trans->state =TRANS_STATE_COMPLETED;
wake_up(&cur_trans->commit_wait);
+ /*
+ memset(cur_trans, 0, sizeof(*cur_trans));
+ kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+ */
}
static int btrfs_cleanup_transaction(struct btrfs_root *root)
@@ -4145,7 +4644,10 @@
if (t == root->fs_info->running_transaction) {
t->state = TRANS_STATE_COMMIT_DOING;
spin_unlock(&root->fs_info->trans_lock);
-
+ /*
+ * We wait for 0 num_writers since we don't hold a trans
+ * handle open currently for this transaction.
+ */
wait_event(t->writer_wait,
atomic_read(&t->num_writers) == 0);
} else {
@@ -4174,10 +4676,10 @@
return 0;
}
-static struct extent_io_ops btree_extent_io_ops = {
+static const struct extent_io_ops btree_extent_io_ops = {
.readpage_end_io_hook = btree_readpage_end_io_hook,
.readpage_io_failed_hook = btree_io_failed_hook,
.submit_bio_hook = btree_submit_bio_hook,
-
+ /* note we're sharing with inode.c for the merge bio hook */
.merge_bio_hook = btrfs_merge_bio_hook,
};
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment