Merge branch 'cleanup/blocksize-diet-part1' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux into for-linus
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7a7521c..8a42adb 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -44,6 +44,17 @@
#define BTRFS_INODE_IN_DELALLOC_LIST 9
#define BTRFS_INODE_READDIO_NEED_LOCK 10
#define BTRFS_INODE_HAS_PROPS 11
+/*
+ * The following 3 bits are meant only for the btree inode.
+ * When any of them is set, it means an error happened while writing an
+ * extent buffer belonging to:
+ * 1) a non-log btree
+ * 2) a log btree and first log sub-transaction
+ * 3) a log btree and second log sub-transaction
+ */
+#define BTRFS_INODE_BTREE_ERR 12
+#define BTRFS_INODE_BTREE_LOG1_ERR 13
+#define BTRFS_INODE_BTREE_LOG2_ERR 14
/* in memory btrfs inode */
struct btrfs_inode {
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index eeee138..d3220d3 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -388,7 +388,8 @@
* freed before we're done setting it up
*/
atomic_inc(&cb->pending_bios);
- ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
+ ret = btrfs_bio_wq_end_io(root->fs_info, bio,
+ BTRFS_WQ_ENDIO_DATA);
BUG_ON(ret); /* -ENOMEM */
if (!skip_sum) {
@@ -419,7 +420,7 @@
}
bio_get(bio);
- ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
+ ret = btrfs_bio_wq_end_io(root->fs_info, bio, BTRFS_WQ_ENDIO_DATA);
BUG_ON(ret); /* -ENOMEM */
if (!skip_sum) {
@@ -668,7 +669,8 @@
PAGE_CACHE_SIZE) {
bio_get(comp_bio);
- ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
+ ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio,
+ BTRFS_WQ_ENDIO_DATA);
BUG_ON(ret); /* -ENOMEM */
/*
@@ -706,7 +708,8 @@
}
bio_get(comp_bio);
- ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio, 0);
+ ret = btrfs_bio_wq_end_io(root->fs_info, comp_bio,
+ BTRFS_WQ_ENDIO_DATA);
BUG_ON(ret); /* -ENOMEM */
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index d498982..19bc616 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1503,10 +1503,9 @@
struct btrfs_root *root,
struct extent_buffer *buf)
{
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+ if (btrfs_test_is_dummy_root(root))
return 0;
-#endif
+
/* ensure we can see the force_cow */
smp_rmb();
@@ -4615,8 +4614,7 @@
ptr = btrfs_item_ptr_offset(leaf, slot);
memmove_extent_buffer(leaf, ptr,
(unsigned long)fi,
- offsetof(struct btrfs_file_extent_item,
- disk_bytenr));
+ BTRFS_FILE_EXTENT_INLINE_DATA_START);
}
}
@@ -5512,18 +5510,18 @@
goto out;
advance_right = ADVANCE;
} else {
- enum btrfs_compare_tree_result cmp;
+ enum btrfs_compare_tree_result result;
WARN_ON(!extent_buffer_uptodate(left_path->nodes[0]));
ret = tree_compare_item(left_root, left_path,
right_path, tmp_buf);
if (ret)
- cmp = BTRFS_COMPARE_TREE_CHANGED;
+ result = BTRFS_COMPARE_TREE_CHANGED;
else
- cmp = BTRFS_COMPARE_TREE_SAME;
+ result = BTRFS_COMPARE_TREE_SAME;
ret = changed_cb(left_root, right_root,
left_path, right_path,
- &left_key, cmp, ctx);
+ &left_key, result, ctx);
if (ret < 0)
goto out;
advance_left = ADVANCE;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 3073b88..f7555e2 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -385,9 +385,11 @@
sizeof(struct btrfs_key_ptr))
#define __BTRFS_LEAF_DATA_SIZE(bs) ((bs) - sizeof(struct btrfs_header))
#define BTRFS_LEAF_DATA_SIZE(r) (__BTRFS_LEAF_DATA_SIZE(r->nodesize))
+#define BTRFS_FILE_EXTENT_INLINE_DATA_START \
+ (offsetof(struct btrfs_file_extent_item, disk_bytenr))
#define BTRFS_MAX_INLINE_DATA_SIZE(r) (BTRFS_LEAF_DATA_SIZE(r) - \
sizeof(struct btrfs_item) - \
- offsetof(struct btrfs_file_extent_item, disk_bytenr))
+ BTRFS_FILE_EXTENT_INLINE_DATA_START)
#define BTRFS_MAX_XATTR_SIZE(r) (BTRFS_LEAF_DATA_SIZE(r) - \
sizeof(struct btrfs_item) -\
sizeof(struct btrfs_dir_item))
@@ -896,6 +898,8 @@
/*
* disk space consumed by the extent, checksum blocks are included
* in these numbers
+ *
+ * At this offset in the structure, the inline extent data start.
*/
__le64 disk_bytenr;
__le64 disk_num_bytes;
@@ -2089,6 +2093,7 @@
#define BTRFS_MOUNT_CHANGE_INODE_CACHE (1 << 24)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
+#define BTRFS_DEFAULT_MAX_INLINE (8192)
#define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt)
#define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt)
@@ -3042,14 +3047,12 @@
static inline unsigned long
btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e)
{
- unsigned long offset = (unsigned long)e;
- offset += offsetof(struct btrfs_file_extent_item, disk_bytenr);
- return offset;
+ return (unsigned long)e + BTRFS_FILE_EXTENT_INLINE_DATA_START;
}
static inline u32 btrfs_file_extent_calc_inline_size(u32 datasize)
{
- return offsetof(struct btrfs_file_extent_item, disk_bytenr) + datasize;
+ return BTRFS_FILE_EXTENT_INLINE_DATA_START + datasize;
}
BTRFS_SETGET_FUNCS(file_extent_disk_bytenr, struct btrfs_file_extent_item,
@@ -3079,9 +3082,7 @@
static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb,
struct btrfs_item *e)
{
- unsigned long offset;
- offset = offsetof(struct btrfs_file_extent_item, disk_bytenr);
- return btrfs_item_size(eb, e) - offset;
+ return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
}
/* this returns the number of file bytes represented by the inline item.
@@ -4126,8 +4127,15 @@
/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_destroy_inode(struct inode *inode);
-int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
- u64 rfer, u64 excl);
#endif
+static inline int btrfs_test_is_dummy_root(struct btrfs_root *root)
+{
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+ return 1;
+#endif
+ return 0;
+}
+
#endif
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2e5d460..2409718 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -72,21 +72,41 @@
static void btrfs_error_commit_super(struct btrfs_root *root);
/*
- * end_io_wq structs are used to do processing in task context when an IO is
- * complete. This is used during reads to verify checksums, and it is used
+ * 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 end_io_wq {
+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_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+ NULL);
+ if (!btrfs_end_io_wq_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void btrfs_end_io_wq_exit(void)
+{
+ if (btrfs_end_io_wq_cache)
+ 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
@@ -327,8 +347,7 @@
{
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;
@@ -607,7 +626,7 @@
goto err;
eb->read_mirror = mirror;
- if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+ if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
ret = -EIO;
goto err;
}
@@ -680,7 +699,7 @@
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
eb = (struct extent_buffer *)page->private;
- set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+ 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))
@@ -690,7 +709,7 @@
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;
@@ -733,20 +752,12 @@
btrfs_queue_work(wq, &end_io_wq->work);
}
-/*
- * For the metadata arg you want
- *
- * 0 - if data
- * 1 - if normal metadta
- * 2 - if writing to the free space cache area
- * 3 - raid parity work
- */
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;
+ struct btrfs_end_io_wq *end_io_wq;
- end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS);
+ end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
if (!end_io_wq)
return -ENOMEM;
@@ -930,7 +941,7 @@
* 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,
@@ -1116,11 +1127,9 @@
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
u64 bytenr, u32 blocksize)
{
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+ if (btrfs_test_is_dummy_root(root))
return alloc_test_extent_buffer(root->fs_info, bytenr,
blocksize);
-#endif
return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
}
@@ -1724,16 +1733,16 @@
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_nodec(bio, error);
}
@@ -2252,7 +2261,7 @@
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic64_set(&fs_info->tree_mod_seq, 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;
@@ -3805,10 +3814,73 @@
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int read_only)
{
+ struct btrfs_super_block *sb = fs_info->super_copy;
+ int ret = 0;
+
+ if (sb->root_level > BTRFS_MAX_LEVEL) {
+ printk(KERN_ERR "BTRFS: tree_root level too big: %d > %d\n",
+ sb->root_level, BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+ if (sb->chunk_root_level > BTRFS_MAX_LEVEL) {
+ printk(KERN_ERR "BTRFS: chunk_root level too big: %d > %d\n",
+ sb->chunk_root_level, BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+ if (sb->log_root_level > BTRFS_MAX_LEVEL) {
+ printk(KERN_ERR "BTRFS: log_root level too big: %d > %d\n",
+ sb->log_root_level, BTRFS_MAX_LEVEL);
+ ret = -EINVAL;
+ }
+
/*
- * Placeholder for checks
+ * The common minimum, we don't know if we can trust the nodesize/sectorsize
+ * items yet, they'll be verified later. Issue just a warning.
*/
- return 0;
+ if (!IS_ALIGNED(sb->root, 4096))
+ printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+ sb->root);
+ if (!IS_ALIGNED(sb->chunk_root, 4096))
+ printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+ sb->chunk_root);
+ if (!IS_ALIGNED(sb->log_root, 4096))
+ printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+ sb->log_root);
+
+ 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 (sb->num_devices > (1UL << 31))
+ printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
+ sb->num_devices);
+
+ if (sb->bytenr != BTRFS_SUPER_INFO_OFFSET) {
+ printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
+ sb->bytenr, BTRFS_SUPER_INFO_OFFSET);
+ 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 (sb->generation < sb->chunk_root_generation)
+ printk(KERN_WARNING
+ "BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n",
+ sb->generation, sb->chunk_root_generation);
+ if (sb->generation < sb->cache_generation && sb->cache_generation != (u64)-1)
+ printk(KERN_WARNING
+ "BTRFS: suspicious: generation < cache_generation: %llu < %llu\n",
+ sb->generation, sb->cache_generation);
+
+ return ret;
}
static void btrfs_error_commit_super(struct btrfs_root *root)
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index ae04dae..4146518 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -25,7 +25,7 @@
#define BTRFS_SUPER_MIRROR_MAX 3
#define BTRFS_SUPER_MIRROR_SHIFT 12
-enum {
+enum btrfs_wq_endio_type {
BTRFS_WQ_ENDIO_DATA = 0,
BTRFS_WQ_ENDIO_METADATA = 1,
BTRFS_WQ_ENDIO_FREE_SPACE = 2,
@@ -119,7 +119,7 @@
u32 btrfs_csum_data(char *data, u32 seed, size_t len);
void btrfs_csum_final(u32 crc, char *result);
int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
- int metadata);
+ enum btrfs_wq_endio_type metadata);
int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
int rw, struct bio *bio, int mirror_num,
unsigned long bio_flags, u64 bio_offset,
@@ -141,6 +141,8 @@
void (*flush_fn)(void *));
int btrfs_calc_num_tolerated_disk_barrier_failures(
struct btrfs_fs_info *fs_info);
+int __init btrfs_end_io_wq_init(void);
+void btrfs_end_io_wq_exit(void);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
void btrfs_init_lockdep(void);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0ba42eb..9a5effa 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3073,10 +3073,10 @@
int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *,
u64, u64, u64, u64, u64, u64, int);
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+
+ if (btrfs_test_is_dummy_root(root))
return 0;
-#endif
+
ref_root = btrfs_header_owner(buf);
nritems = btrfs_header_nritems(buf);
level = btrfs_header_level(buf);
@@ -6264,10 +6264,9 @@
int ret;
struct btrfs_fs_info *fs_info = root->fs_info;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+ if (btrfs_test_is_dummy_root(root))
return 0;
-#endif
+
add_pinned_bytes(root->fs_info, num_bytes, owner, root_objectid);
/*
@@ -7235,17 +7234,19 @@
btrfs_set_buffer_uptodate(buf);
if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+ buf->log_index = root->log_transid % 2;
/*
* we allow two log transactions at a time, use different
* EXENT bit to differentiate dirty pages.
*/
- if (root->log_transid % 2 == 0)
+ if (buf->log_index == 0)
set_extent_dirty(&root->dirty_log_pages, buf->start,
buf->start + buf->len - 1, GFP_NOFS);
else
set_extent_new(&root->dirty_log_pages, buf->start,
buf->start + buf->len - 1, GFP_NOFS);
} else {
+ buf->log_index = -1;
set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
buf->start + buf->len - 1, GFP_NOFS);
}
@@ -7337,15 +7338,14 @@
bool skinny_metadata = btrfs_fs_incompat(root->fs_info,
SKINNY_METADATA);
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state))) {
+ if (btrfs_test_is_dummy_root(root)) {
buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
blocksize, level);
if (!IS_ERR(buf))
root->alloc_bytenr += blocksize;
return buf;
}
-#endif
+
block_rsv = use_block_rsv(trans, root, blocksize);
if (IS_ERR(block_rsv))
return ERR_CAST(block_rsv);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 7822900..bf3f424 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2064,7 +2064,7 @@
return -EROFS;
for (i = 0; i < num_pages; i++) {
- struct page *p = extent_buffer_page(eb, i);
+ struct page *p = eb->pages[i];
ret = repair_io_failure(root->fs_info->btree_inode, start,
PAGE_CACHE_SIZE, start, p,
@@ -3580,7 +3580,7 @@
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- struct page *p = extent_buffer_page(eb, i);
+ struct page *p = eb->pages[i];
if (!trylock_page(p)) {
if (!flush) {
@@ -3601,6 +3601,68 @@
wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
}
+static void set_btree_ioerr(struct page *page)
+{
+ struct extent_buffer *eb = (struct extent_buffer *)page->private;
+ struct btrfs_inode *btree_ino = BTRFS_I(eb->fs_info->btree_inode);
+
+ SetPageError(page);
+ if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
+ return;
+
+ /*
+ * If writeback for a btree extent that doesn't belong to a log tree
+ * failed, increment the counter transaction->eb_write_errors.
+ * We do this because while the transaction is running and before it's
+ * committing (when we call filemap_fdata[write|wait]_range against
+ * the btree inode), we might have
+ * btree_inode->i_mapping->a_ops->writepages() called by the VM - if it
+ * returns an error or an error happens during writeback, when we're
+ * committing the transaction we wouldn't know about it, since the pages
+ * can be no longer dirty nor marked anymore for writeback (if a
+ * subsequent modification to the extent buffer didn't happen before the
+ * transaction commit), which makes filemap_fdata[write|wait]_range not
+ * able to find the pages tagged with SetPageError at transaction
+ * commit time. So if this happens we must abort the transaction,
+ * otherwise we commit a super block with btree roots that point to
+ * btree nodes/leafs whose content on disk is invalid - either garbage
+ * or the content of some node/leaf from a past generation that got
+ * cowed or deleted and is no longer valid.
+ *
+ * Note: setting AS_EIO/AS_ENOSPC in the btree inode's i_mapping would
+ * not be enough - we need to distinguish between log tree extents vs
+ * non-log tree extents, and the next filemap_fdatawait_range() call
+ * will catch and clear such errors in the mapping - and that call might
+ * be from a log sync and not from a transaction commit. Also, checking
+ * for the eb flag EXTENT_BUFFER_WRITE_ERR at transaction commit time is
+ * not done and would not be reliable - the eb might have been released
+ * from memory and reading it back again means that flag would not be
+ * set (since it's a runtime flag, not persisted on disk).
+ *
+ * Using the flags below in the btree inode also makes us achieve the
+ * goal of AS_EIO/AS_ENOSPC when writepages() returns success, started
+ * writeback for all dirty pages and before filemap_fdatawait_range()
+ * is called, the writeback for all dirty pages had already finished
+ * with errors - because we were not using AS_EIO/AS_ENOSPC,
+ * filemap_fdatawait_range() would return success, as it could not know
+ * that writeback errors happened (the pages were no longer tagged for
+ * writeback).
+ */
+ switch (eb->log_index) {
+ case -1:
+ set_bit(BTRFS_INODE_BTREE_ERR, &btree_ino->runtime_flags);
+ break;
+ case 0:
+ set_bit(BTRFS_INODE_BTREE_LOG1_ERR, &btree_ino->runtime_flags);
+ break;
+ case 1:
+ set_bit(BTRFS_INODE_BTREE_LOG2_ERR, &btree_ino->runtime_flags);
+ break;
+ default:
+ BUG(); /* unexpected, logic error */
+ }
+}
+
static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
{
struct bio_vec *bvec;
@@ -3614,10 +3676,9 @@
BUG_ON(!eb);
done = atomic_dec_and_test(&eb->io_pages);
- if (err || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
- set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+ if (err || test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
ClearPageUptodate(page);
- SetPageError(page);
+ set_btree_ioerr(page);
}
end_page_writeback(page);
@@ -3644,14 +3705,14 @@
int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
int ret = 0;
- clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
num_pages = num_extent_pages(eb->start, eb->len);
atomic_set(&eb->io_pages, num_pages);
if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
bio_flags = EXTENT_BIO_TREE_LOG;
for (i = 0; i < num_pages; i++) {
- struct page *p = extent_buffer_page(eb, i);
+ struct page *p = eb->pages[i];
clear_page_dirty_for_io(p);
set_page_writeback(p);
@@ -3661,8 +3722,8 @@
0, epd->bio_flags, bio_flags);
epd->bio_flags = bio_flags;
if (ret) {
- set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
- SetPageError(p);
+ set_btree_ioerr(p);
+ end_page_writeback(p);
if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
end_extent_buffer_writeback(eb);
ret = -EIO;
@@ -3675,7 +3736,8 @@
if (unlikely(ret)) {
for (; i < num_pages; i++) {
- struct page *p = extent_buffer_page(eb, i);
+ struct page *p = eb->pages[i];
+ clear_page_dirty_for_io(p);
unlock_page(p);
}
}
@@ -4450,24 +4512,21 @@
/*
* Helper for releasing extent buffer page.
*/
-static void btrfs_release_extent_buffer_page(struct extent_buffer *eb,
- unsigned long start_idx)
+static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
{
unsigned long index;
- unsigned long num_pages;
struct page *page;
int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
BUG_ON(extent_buffer_under_io(eb));
- num_pages = num_extent_pages(eb->start, eb->len);
- index = start_idx + num_pages;
- if (start_idx >= index)
+ index = num_extent_pages(eb->start, eb->len);
+ if (index == 0)
return;
do {
index--;
- page = extent_buffer_page(eb, index);
+ page = eb->pages[index];
if (page && mapped) {
spin_lock(&page->mapping->private_lock);
/*
@@ -4498,7 +4557,7 @@
/* One for when we alloced the page */
page_cache_release(page);
}
- } while (index != start_idx);
+ } while (index != 0);
}
/*
@@ -4506,7 +4565,7 @@
*/
static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
{
- btrfs_release_extent_buffer_page(eb, 0);
+ btrfs_release_extent_buffer_page(eb);
__free_extent_buffer(eb);
}
@@ -4649,7 +4708,8 @@
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- struct page *p = extent_buffer_page(eb, i);
+ struct page *p = eb->pages[i];
+
if (p != accessed)
mark_page_accessed(p);
}
@@ -4818,7 +4878,7 @@
*/
SetPageChecked(eb->pages[0]);
for (i = 1; i < num_pages; i++) {
- p = extent_buffer_page(eb, i);
+ p = eb->pages[i];
ClearPageChecked(p);
unlock_page(p);
}
@@ -4863,7 +4923,7 @@
}
/* Should be safe to release our pages at this point */
- btrfs_release_extent_buffer_page(eb, 0);
+ btrfs_release_extent_buffer_page(eb);
call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
return 1;
}
@@ -4929,7 +4989,7 @@
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
if (!PageDirty(page))
continue;
@@ -4965,7 +5025,7 @@
WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
for (i = 0; i < num_pages; i++)
- set_page_dirty(extent_buffer_page(eb, i));
+ set_page_dirty(eb->pages[i]);
return was_dirty;
}
@@ -4978,7 +5038,7 @@
clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
if (page)
ClearPageUptodate(page);
}
@@ -4994,7 +5054,7 @@
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
SetPageUptodate(page);
}
return 0;
@@ -5034,7 +5094,7 @@
num_pages = num_extent_pages(eb->start, eb->len);
for (i = start_i; i < num_pages; i++) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
if (wait == WAIT_NONE) {
if (!trylock_page(page))
goto unlock_exit;
@@ -5053,11 +5113,11 @@
goto unlock_exit;
}
- clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
eb->read_mirror = 0;
atomic_set(&eb->io_pages, num_reads);
for (i = start_i; i < num_pages; i++) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
if (!PageUptodate(page)) {
ClearPageError(page);
err = __extent_read_full_page(tree, page,
@@ -5082,7 +5142,7 @@
return ret;
for (i = start_i; i < num_pages; i++) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
wait_on_page_locked(page);
if (!PageUptodate(page))
ret = -EIO;
@@ -5093,7 +5153,7 @@
unlock_exit:
i = start_i;
while (locked_pages > 0) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
i++;
unlock_page(page);
locked_pages--;
@@ -5119,7 +5179,7 @@
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
cur = min(len, (PAGE_CACHE_SIZE - offset));
kaddr = page_address(page);
@@ -5151,7 +5211,7 @@
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
cur = min(len, (PAGE_CACHE_SIZE - offset));
kaddr = page_address(page);
@@ -5200,7 +5260,7 @@
return -EINVAL;
}
- p = extent_buffer_page(eb, i);
+ p = eb->pages[i];
kaddr = page_address(p);
*map = kaddr + offset;
*map_len = PAGE_CACHE_SIZE - offset;
@@ -5226,7 +5286,7 @@
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
cur = min(len, (PAGE_CACHE_SIZE - offset));
@@ -5260,7 +5320,7 @@
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
WARN_ON(!PageUptodate(page));
cur = min(len, PAGE_CACHE_SIZE - offset);
@@ -5290,7 +5350,7 @@
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = extent_buffer_page(eb, i);
+ page = eb->pages[i];
WARN_ON(!PageUptodate(page));
cur = min(len, PAGE_CACHE_SIZE - offset);
@@ -5321,7 +5381,7 @@
(PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = extent_buffer_page(dst, i);
+ page = dst->pages[i];
WARN_ON(!PageUptodate(page));
cur = min(len, (unsigned long)(PAGE_CACHE_SIZE - offset));
@@ -5399,8 +5459,7 @@
cur = min_t(unsigned long, cur,
(unsigned long)(PAGE_CACHE_SIZE - dst_off_in_page));
- copy_pages(extent_buffer_page(dst, dst_i),
- extent_buffer_page(dst, src_i),
+ copy_pages(dst->pages[dst_i], dst->pages[src_i],
dst_off_in_page, src_off_in_page, cur);
src_offset += cur;
@@ -5446,8 +5505,7 @@
cur = min_t(unsigned long, len, src_off_in_page + 1);
cur = min(cur, dst_off_in_page + 1);
- copy_pages(extent_buffer_page(dst, dst_i),
- extent_buffer_page(dst, src_i),
+ copy_pages(dst->pages[dst_i], dst->pages[src_i],
dst_off_in_page - cur + 1,
src_off_in_page - cur + 1, cur);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 5e91fb9..f40d67f 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -11,8 +11,6 @@
#define EXTENT_NEW (1 << 4)
#define EXTENT_DELALLOC (1 << 5)
#define EXTENT_DEFRAG (1 << 6)
-#define EXTENT_DEFRAG_DONE (1 << 7)
-#define EXTENT_BUFFER_FILLED (1 << 8)
#define EXTENT_BOUNDARY (1 << 9)
#define EXTENT_NODATASUM (1 << 10)
#define EXTENT_DO_ACCOUNTING (1 << 11)
@@ -34,16 +32,16 @@
/* these are bit numbers for test/set bit */
#define EXTENT_BUFFER_UPTODATE 0
-#define EXTENT_BUFFER_BLOCKING 1
#define EXTENT_BUFFER_DIRTY 2
#define EXTENT_BUFFER_CORRUPT 3
#define EXTENT_BUFFER_READAHEAD 4 /* this got triggered by readahead */
#define EXTENT_BUFFER_TREE_REF 5
#define EXTENT_BUFFER_STALE 6
#define EXTENT_BUFFER_WRITEBACK 7
-#define EXTENT_BUFFER_IOERR 8
+#define EXTENT_BUFFER_READ_ERR 8 /* read IO error */
#define EXTENT_BUFFER_DUMMY 9
#define EXTENT_BUFFER_IN_TREE 10
+#define EXTENT_BUFFER_WRITE_ERR 11 /* write IO error */
/* these are flags for extent_clear_unlock_delalloc */
#define PAGE_UNLOCK (1 << 0)
@@ -57,7 +55,6 @@
* map has page->private set to one.
*/
#define EXTENT_PAGE_PRIVATE 1
-#define EXTENT_PAGE_PRIVATE_FIRST_PAGE 3
struct extent_state;
struct btrfs_root;
@@ -141,7 +138,9 @@
atomic_t blocking_readers;
atomic_t spinning_readers;
atomic_t spinning_writers;
- int lock_nested;
+ short lock_nested;
+ /* >= 0 if eb belongs to a log tree, -1 otherwise */
+ short log_index;
/* protects write locks */
rwlock_t lock;
@@ -283,12 +282,6 @@
(start >> PAGE_CACHE_SHIFT);
}
-static inline struct page *extent_buffer_page(struct extent_buffer *eb,
- unsigned long i)
-{
- return eb->pages[i];
-}
-
static inline void extent_buffer_get(struct extent_buffer *eb)
{
atomic_inc(&eb->refs);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 344a322..6c4da844 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6586,7 +6586,7 @@
* extent causing the -EEXIST.
*/
if (start >= extent_map_end(existing) ||
- start + len <= existing->start) {
+ start <= existing->start) {
/*
* The existing extent map is the one nearest to
* the [start, start + len) range which overlaps
@@ -7721,7 +7721,8 @@
bio_get(bio);
if (!write) {
- ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0);
+ ret = btrfs_bio_wq_end_io(root->fs_info, bio,
+ BTRFS_WQ_ENDIO_DATA);
if (ret)
goto err;
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2fc4890..fd9d190 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -884,7 +884,7 @@
* file you want to defrag, we return 0 to let you know to skip this
* part of the file
*/
-static int check_defrag_in_cache(struct inode *inode, u64 offset, int thresh)
+static int check_defrag_in_cache(struct inode *inode, u64 offset, u32 thresh)
{
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_map *em = NULL;
@@ -919,7 +919,7 @@
*/
static int find_new_extents(struct btrfs_root *root,
struct inode *inode, u64 newer_than,
- u64 *off, int thresh)
+ u64 *off, u32 thresh)
{
struct btrfs_path *path;
struct btrfs_key min_key;
@@ -1028,7 +1028,7 @@
return ret;
}
-static int should_defrag_range(struct inode *inode, u64 start, int thresh,
+static int should_defrag_range(struct inode *inode, u64 start, u32 thresh,
u64 *last_len, u64 *skip, u64 *defrag_end,
int compress)
{
@@ -1258,7 +1258,7 @@
int ret;
int defrag_count = 0;
int compress_type = BTRFS_COMPRESS_ZLIB;
- int extent_thresh = range->extent_thresh;
+ u32 extent_thresh = range->extent_thresh;
unsigned long max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
unsigned long cluster = max_cluster;
u64 new_align = ~((u64)128 * 1024 - 1);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index cd9717e..48b60db 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -539,10 +539,9 @@
struct extent_buffer *leaf;
struct btrfs_key key;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, "a_root->state)))
+ if (btrfs_test_is_dummy_root(quota_root))
return 0;
-#endif
+
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
@@ -698,10 +697,9 @@
int ret;
int slot;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+ if (btrfs_test_is_dummy_root(root))
return 0;
-#endif
+
key.objectid = 0;
key.type = BTRFS_QGROUP_INFO_KEY;
key.offset = qgroup->qgroupid;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 95bc40a..74257d6 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -736,7 +736,8 @@
err = ret;
goto out;
}
- BUG_ON(!ret || !path1->slots[0]);
+ ASSERT(ret);
+ ASSERT(path1->slots[0]);
path1->slots[0]--;
@@ -746,10 +747,10 @@
* the backref was added previously when processing
* backref of type BTRFS_TREE_BLOCK_REF_KEY
*/
- BUG_ON(!list_is_singular(&cur->upper));
+ ASSERT(list_is_singular(&cur->upper));
edge = list_entry(cur->upper.next, struct backref_edge,
list[LOWER]);
- BUG_ON(!list_empty(&edge->list[UPPER]));
+ ASSERT(list_empty(&edge->list[UPPER]));
exist = edge->node[UPPER];
/*
* add the upper level block to pending list if we need
@@ -831,7 +832,7 @@
cur->cowonly = 1;
}
#else
- BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
+ ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
#endif
if (key.objectid == key.offset) {
@@ -840,7 +841,7 @@
* backref of this type.
*/
root = find_reloc_root(rc, cur->bytenr);
- BUG_ON(!root);
+ ASSERT(root);
cur->root = root;
break;
}
@@ -868,7 +869,7 @@
} else {
upper = rb_entry(rb_node, struct backref_node,
rb_node);
- BUG_ON(!upper->checked);
+ ASSERT(upper->checked);
INIT_LIST_HEAD(&edge->list[UPPER]);
}
list_add_tail(&edge->list[LOWER], &cur->upper);
@@ -892,7 +893,7 @@
if (btrfs_root_level(&root->root_item) == cur->level) {
/* tree root */
- BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+ ASSERT(btrfs_root_bytenr(&root->root_item) ==
cur->bytenr);
if (should_ignore_root(root))
list_add(&cur->list, &useless);
@@ -927,7 +928,7 @@
need_check = true;
for (; level < BTRFS_MAX_LEVEL; level++) {
if (!path2->nodes[level]) {
- BUG_ON(btrfs_root_bytenr(&root->root_item) !=
+ ASSERT(btrfs_root_bytenr(&root->root_item) ==
lower->bytenr);
if (should_ignore_root(root))
list_add(&lower->list, &useless);
@@ -977,12 +978,15 @@
need_check = false;
list_add_tail(&edge->list[UPPER],
&list);
- } else
+ } else {
+ if (upper->checked)
+ need_check = true;
INIT_LIST_HEAD(&edge->list[UPPER]);
+ }
} else {
upper = rb_entry(rb_node, struct backref_node,
rb_node);
- BUG_ON(!upper->checked);
+ ASSERT(upper->checked);
INIT_LIST_HEAD(&edge->list[UPPER]);
if (!upper->owner)
upper->owner = btrfs_header_owner(eb);
@@ -1026,7 +1030,7 @@
* everything goes well, connect backref nodes and insert backref nodes
* into the cache.
*/
- BUG_ON(!node->checked);
+ ASSERT(node->checked);
cowonly = node->cowonly;
if (!cowonly) {
rb_node = tree_insert(&cache->rb_root, node->bytenr,
@@ -1062,8 +1066,21 @@
continue;
}
- BUG_ON(!upper->checked);
- BUG_ON(cowonly != upper->cowonly);
+ if (!upper->checked) {
+ /*
+ * Still want to blow up for developers since this is a
+ * logic bug.
+ */
+ ASSERT(0);
+ err = -EINVAL;
+ goto out;
+ }
+ if (cowonly != upper->cowonly) {
+ ASSERT(0);
+ err = -EINVAL;
+ goto out;
+ }
+
if (!cowonly) {
rb_node = tree_insert(&cache->rb_root, upper->bytenr,
&upper->rb_node);
@@ -1086,7 +1103,7 @@
while (!list_empty(&useless)) {
upper = list_entry(useless.next, struct backref_node, list);
list_del_init(&upper->list);
- BUG_ON(!list_empty(&upper->upper));
+ ASSERT(list_empty(&upper->upper));
if (upper == node)
node = NULL;
if (upper->lowest) {
@@ -1119,29 +1136,45 @@
if (err) {
while (!list_empty(&useless)) {
lower = list_entry(useless.next,
- struct backref_node, upper);
- list_del_init(&lower->upper);
+ struct backref_node, list);
+ list_del_init(&lower->list);
}
- upper = node;
- INIT_LIST_HEAD(&list);
- while (upper) {
- if (RB_EMPTY_NODE(&upper->rb_node)) {
- list_splice_tail(&upper->upper, &list);
- free_backref_node(cache, upper);
- }
-
- if (list_empty(&list))
- break;
-
- edge = list_entry(list.next, struct backref_edge,
- list[LOWER]);
+ while (!list_empty(&list)) {
+ edge = list_first_entry(&list, struct backref_edge,
+ list[UPPER]);
+ list_del(&edge->list[UPPER]);
list_del(&edge->list[LOWER]);
+ lower = edge->node[LOWER];
upper = edge->node[UPPER];
free_backref_edge(cache, edge);
+
+ /*
+ * Lower is no longer linked to any upper backref nodes
+ * and isn't in the cache, we can free it ourselves.
+ */
+ if (list_empty(&lower->upper) &&
+ RB_EMPTY_NODE(&lower->rb_node))
+ list_add(&lower->list, &useless);
+
+ if (!RB_EMPTY_NODE(&upper->rb_node))
+ continue;
+
+ /* Add this guy's upper edges to the list to proces */
+ list_for_each_entry(edge, &upper->upper, list[LOWER])
+ list_add_tail(&edge->list[UPPER], &list);
+ if (list_empty(&upper->upper))
+ list_add(&upper->list, &useless);
+ }
+
+ while (!list_empty(&useless)) {
+ lower = list_entry(useless.next,
+ struct backref_node, list);
+ list_del_init(&lower->list);
+ free_backref_node(cache, lower);
}
return ERR_PTR(err);
}
- BUG_ON(node && node->detached);
+ ASSERT(!node || !node->detached);
return node;
}
@@ -2313,7 +2346,7 @@
}
static noinline_for_stack
-int merge_reloc_roots(struct reloc_control *rc)
+void merge_reloc_roots(struct reloc_control *rc)
{
struct btrfs_root *root;
struct btrfs_root *reloc_root;
@@ -2394,7 +2427,6 @@
}
BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
- return ret;
}
static void free_block_list(struct rb_root *blocks)
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index b9c37ac..efa0831 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -177,17 +177,12 @@
struct scrub_warning {
struct btrfs_path *path;
u64 extent_item_size;
- char *scratch_buf;
- char *msg_buf;
const char *errstr;
sector_t sector;
u64 logical;
struct btrfs_device *dev;
- int msg_bufsize;
- int scratch_bufsize;
};
-
static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
@@ -551,7 +546,6 @@
u64 ref_root;
u32 item_size;
u8 ref_level;
- const int bufsize = 4096;
int ret;
WARN_ON(sblock->page_count < 1);
@@ -559,18 +553,13 @@
fs_info = sblock->sctx->dev_root->fs_info;
path = btrfs_alloc_path();
+ if (!path)
+ return;
- swarn.scratch_buf = kmalloc(bufsize, GFP_NOFS);
- swarn.msg_buf = kmalloc(bufsize, GFP_NOFS);
swarn.sector = (sblock->pagev[0]->physical) >> 9;
swarn.logical = sblock->pagev[0]->logical;
swarn.errstr = errstr;
swarn.dev = NULL;
- swarn.msg_bufsize = bufsize;
- swarn.scratch_bufsize = bufsize;
-
- if (!path || !swarn.scratch_buf || !swarn.msg_buf)
- goto out;
ret = extent_from_logical(fs_info, swarn.logical, path, &found_key,
&flags);
@@ -611,8 +600,6 @@
out:
btrfs_free_path(path);
- kfree(swarn.scratch_buf);
- kfree(swarn.msg_buf);
}
static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 7edfc7c..874828d 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3327,7 +3327,7 @@
if (ret < 0 && ret != -ENOENT) {
goto out;
} else if (ret == -ENOENT) {
- ret = 1;
+ ret = 0;
break;
}
@@ -5728,7 +5728,7 @@
NULL);
sort_clone_roots = 1;
- current->journal_info = (void *)BTRFS_SEND_TRANS_STUB;
+ current->journal_info = BTRFS_SEND_TRANS_STUB;
ret = send_subvol(sctx);
current->journal_info = NULL;
if (ret < 0)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2375f94..4685b97 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -395,7 +395,6 @@
int ret = 0;
char *compress_type;
bool compress_force = false;
- bool compress = false;
cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
if (cache_gen)
@@ -473,7 +472,6 @@
/* Fallthrough */
case Opt_compress:
case Opt_compress_type:
- compress = true;
if (token == Opt_compress ||
token == Opt_compress_force ||
strcmp(args[0].from, "zlib") == 0) {
@@ -503,7 +501,7 @@
btrfs_set_and_info(root, FORCE_COMPRESS,
"force %s compression",
compress_type);
- } else if (compress) {
+ } else {
if (!btrfs_test_opt(root, COMPRESS))
btrfs_info(root->fs_info,
"btrfs: use %s compression",
@@ -1016,7 +1014,7 @@
seq_puts(seq, ",nodatacow");
if (btrfs_test_opt(root, NOBARRIER))
seq_puts(seq, ",nobarrier");
- if (info->max_inline != 8192 * 1024)
+ if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE)
seq_printf(seq, ",max_inline=%llu", info->max_inline);
if (info->alloc_start != 0)
seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
@@ -2001,11 +1999,15 @@
err = btrfs_prelim_ref_init();
if (err)
+ goto free_delayed_ref;
+
+ err = btrfs_end_io_wq_init();
+ if (err)
goto free_prelim_ref;
err = btrfs_interface_init();
if (err)
- goto free_delayed_ref;
+ goto free_end_io_wq;
btrfs_init_lockdep();
@@ -2023,6 +2025,8 @@
unregister_ioctl:
btrfs_interface_exit();
+free_end_io_wq:
+ btrfs_end_io_wq_exit();
free_prelim_ref:
btrfs_prelim_ref_exit();
free_delayed_ref:
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 16d0c1b..0bcdcc6 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -386,7 +386,7 @@
int ret;
/* Send isn't supposed to start transactions. */
- ASSERT(current->journal_info != (void *)BTRFS_SEND_TRANS_STUB);
+ ASSERT(current->journal_info != BTRFS_SEND_TRANS_STUB);
if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
return ERR_PTR(-EROFS);
@@ -609,7 +609,6 @@
if (transid <= root->fs_info->last_trans_committed)
goto out;
- ret = -EINVAL;
/* find specified transaction */
spin_lock(&root->fs_info->trans_lock);
list_for_each_entry(t, &root->fs_info->trans_list, list) {
@@ -625,9 +624,16 @@
}
}
spin_unlock(&root->fs_info->trans_lock);
- /* The specified transaction doesn't exist */
- if (!cur_trans)
+
+ /*
+ * The specified transaction doesn't exist, or we
+ * raced with btrfs_commit_transaction
+ */
+ if (!cur_trans) {
+ if (transid > root->fs_info->last_trans_committed)
+ ret = -EINVAL;
goto out;
+ }
} else {
/* find newest transaction that is committing | committed */
spin_lock(&root->fs_info->trans_lock);
@@ -851,6 +857,8 @@
struct extent_state *cached_state = NULL;
u64 start = 0;
u64 end;
+ struct btrfs_inode *btree_ino = BTRFS_I(root->fs_info->btree_inode);
+ bool errors = false;
while (!find_first_extent_bit(dirty_pages, start, &start, &end,
EXTENT_NEED_WAIT, &cached_state)) {
@@ -864,6 +872,26 @@
}
if (err)
werr = err;
+
+ if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
+ if ((mark & EXTENT_DIRTY) &&
+ test_and_clear_bit(BTRFS_INODE_BTREE_LOG1_ERR,
+ &btree_ino->runtime_flags))
+ errors = true;
+
+ if ((mark & EXTENT_NEW) &&
+ test_and_clear_bit(BTRFS_INODE_BTREE_LOG2_ERR,
+ &btree_ino->runtime_flags))
+ errors = true;
+ } else {
+ if (test_and_clear_bit(BTRFS_INODE_BTREE_ERR,
+ &btree_ino->runtime_flags))
+ errors = true;
+ }
+
+ if (errors && !werr)
+ werr = -EIO;
+
return werr;
}
@@ -1629,6 +1657,7 @@
{
struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_transaction *prev_trans = NULL;
+ struct btrfs_inode *btree_ino = BTRFS_I(root->fs_info->btree_inode);
int ret;
/* Stop the commit early if ->aborted is set */
@@ -1871,6 +1900,9 @@
btrfs_update_commit_device_size(root->fs_info);
btrfs_update_commit_device_bytes_used(root, cur_trans);
+ clear_bit(BTRFS_INODE_BTREE_LOG1_ERR, &btree_ino->runtime_flags);
+ clear_bit(BTRFS_INODE_BTREE_LOG2_ERR, &btree_ino->runtime_flags);
+
spin_lock(&root->fs_info->trans_lock);
cur_trans->state = TRANS_STATE_UNBLOCKED;
root->fs_info->running_transaction = NULL;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 579be51..d8f40e1 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -79,7 +79,7 @@
#define TRANS_EXTWRITERS (__TRANS_USERSPACE | __TRANS_START | \
__TRANS_ATTACH)
-#define BTRFS_SEND_TRANS_STUB 1
+#define BTRFS_SEND_TRANS_STUB ((void *)1)
struct btrfs_trans_handle {
u64 transid;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f27c0f7..f61278f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5709,8 +5709,8 @@
name = rcu_dereference(dev->name);
pr_debug("btrfs_map_bio: rw %d, sector=%llu, dev=%lu "
"(%s id %llu), size=%u\n", rw,
- (u64)bio->bi_sector, (u_long)dev->bdev->bd_dev,
- name->str, dev->devid, bio->bi_size);
+ (u64)bio->bi_iter.bi_sector, (u_long)dev->bdev->bd_dev,
+ name->str, dev->devid, bio->bi_iter.bi_size);
rcu_read_unlock();
}
#endif