while (!list_empty(&states)) {
state = list_entry(states.next, struct extent_state, leak_list);
- printk(KERN_ERR "btrfs state leak: start %llu end %llu "
+ printk(KERN_ERR "BTRFS: state leak: start %llu end %llu "
"state %lu in tree %p refs %d\n",
state->start, state->end, state->state, state->tree,
atomic_read(&state->refs));
while (!list_empty(&buffers)) {
eb = list_entry(buffers.next, struct extent_buffer, leak_list);
- printk(KERN_ERR "btrfs buffer leak start %llu len %lu "
+ printk(KERN_ERR "BTRFS: buffer leak start %llu len %lu "
"refs %d\n",
eb->start, eb->len, atomic_read(&eb->refs));
list_del(&eb->leak_list);
}
}
-#define btrfs_debug_check_extent_io_range(inode, start, end) \
- __btrfs_debug_check_extent_io_range(__func__, (inode), (start), (end))
+#define btrfs_debug_check_extent_io_range(tree, start, end) \
+ __btrfs_debug_check_extent_io_range(__func__, (tree), (start), (end))
static inline void __btrfs_debug_check_extent_io_range(const char *caller,
- struct inode *inode, u64 start, u64 end)
+ struct extent_io_tree *tree, u64 start, u64 end)
{
- u64 isize = i_size_read(inode);
+ struct inode *inode;
+ u64 isize;
+
+ if (!tree->mapping)
+ return;
+ inode = tree->mapping->host;
+ isize = i_size_read(inode);
if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
printk_ratelimited(KERN_DEBUG
- "btrfs: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
+ "BTRFS: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
caller, btrfs_ino(inode), isize, start, end);
}
}
static inline struct btrfs_fs_info *
tree_fs_info(struct extent_io_tree *tree)
{
+ if (!tree->mapping)
+ return NULL;
return btrfs_sb(tree->mapping->host->i_sb);
}
struct address_space *mapping)
{
tree->state = RB_ROOT;
- INIT_RADIX_TREE(&tree->buffer, GFP_ATOMIC);
tree->ops = NULL;
tree->dirty_bytes = 0;
spin_lock_init(&tree->lock);
- spin_lock_init(&tree->buffer_lock);
tree->mapping = mapping;
}
}
static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
- struct rb_node *node)
+ struct rb_node *node,
+ struct rb_node ***p_in,
+ struct rb_node **parent_in)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct tree_entry *entry;
+ if (p_in && parent_in) {
+ p = *p_in;
+ parent = *parent_in;
+ goto do_insert;
+ }
+
while (*p) {
parent = *p;
entry = rb_entry(parent, struct tree_entry, rb_node);
return parent;
}
+do_insert:
rb_link_node(node, parent, p);
rb_insert_color(node, root);
return NULL;
}
static struct rb_node *__etree_search(struct extent_io_tree *tree, u64 offset,
- struct rb_node **prev_ret,
- struct rb_node **next_ret)
+ struct rb_node **prev_ret,
+ struct rb_node **next_ret,
+ struct rb_node ***p_ret,
+ struct rb_node **parent_ret)
{
struct rb_root *root = &tree->state;
- struct rb_node *n = root->rb_node;
+ struct rb_node **n = &root->rb_node;
struct rb_node *prev = NULL;
struct rb_node *orig_prev = NULL;
struct tree_entry *entry;
struct tree_entry *prev_entry = NULL;
- while (n) {
- entry = rb_entry(n, struct tree_entry, rb_node);
- prev = n;
+ while (*n) {
+ prev = *n;
+ entry = rb_entry(prev, struct tree_entry, rb_node);
prev_entry = entry;
if (offset < entry->start)
- n = n->rb_left;
+ n = &(*n)->rb_left;
else if (offset > entry->end)
- n = n->rb_right;
+ n = &(*n)->rb_right;
else
- return n;
+ return *n;
}
+ if (p_ret)
+ *p_ret = n;
+ if (parent_ret)
+ *parent_ret = prev;
+
if (prev_ret) {
orig_prev = prev;
while (prev && offset > prev_entry->end) {
return NULL;
}
-static inline struct rb_node *tree_search(struct extent_io_tree *tree,
- u64 offset)
+static inline struct rb_node *
+tree_search_for_insert(struct extent_io_tree *tree,
+ u64 offset,
+ struct rb_node ***p_ret,
+ struct rb_node **parent_ret)
{
struct rb_node *prev = NULL;
struct rb_node *ret;
- ret = __etree_search(tree, offset, &prev, NULL);
+ ret = __etree_search(tree, offset, &prev, NULL, p_ret, parent_ret);
if (!ret)
return prev;
return ret;
}
+static inline struct rb_node *tree_search(struct extent_io_tree *tree,
+ u64 offset)
+{
+ return tree_search_for_insert(tree, offset, NULL, NULL);
+}
+
static void merge_cb(struct extent_io_tree *tree, struct extent_state *new,
struct extent_state *other)
{
*/
static int insert_state(struct extent_io_tree *tree,
struct extent_state *state, u64 start, u64 end,
+ struct rb_node ***p,
+ struct rb_node **parent,
unsigned long *bits)
{
struct rb_node *node;
if (end < start)
- WARN(1, KERN_ERR "btrfs end < start %llu %llu\n",
+ WARN(1, KERN_ERR "BTRFS: end < start %llu %llu\n",
end, start);
state->start = start;
state->end = end;
set_state_bits(tree, state, bits);
- node = tree_insert(&tree->state, end, &state->rb_node);
+ node = tree_insert(&tree->state, end, &state->rb_node, p, parent);
if (node) {
struct extent_state *found;
found = rb_entry(node, struct extent_state, rb_node);
- printk(KERN_ERR "btrfs found node %llu %llu on insert of "
+ printk(KERN_ERR "BTRFS: found node %llu %llu on insert of "
"%llu %llu\n",
found->start, found->end, start, end);
return -EEXIST;
prealloc->state = orig->state;
orig->start = split;
- node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node);
+ node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node,
+ NULL, NULL);
if (node) {
free_extent_state(prealloc);
return -EEXIST;
int err;
int clear = 0;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
if (bits & EXTENT_DELALLOC)
bits |= EXTENT_NORESERVE;
struct extent_state *state;
struct rb_node *node;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
spin_lock(&tree->lock);
again:
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct rb_node *node;
+ struct rb_node **p;
+ struct rb_node *parent;
int err = 0;
u64 last_start;
u64 last_end;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
bits |= EXTENT_FIRST_DELALLOC;
again:
* this search will find all the extents that end after
* our range starts.
*/
- node = tree_search(tree, start);
+ node = tree_search_for_insert(tree, start, &p, &parent);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
BUG_ON(!prealloc);
- err = insert_state(tree, prealloc, start, end, &bits);
+ err = insert_state(tree, prealloc, start, end,
+ &p, &parent, &bits);
if (err)
extent_io_tree_panic(tree, err);
+ cache_state(prealloc, cached_state);
prealloc = NULL;
goto out;
}
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- &bits);
+ NULL, NULL, &bits);
if (err)
extent_io_tree_panic(tree, err);
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct rb_node *node;
+ struct rb_node **p;
+ struct rb_node *parent;
int err = 0;
u64 last_start;
u64 last_end;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
again:
if (!prealloc && (mask & __GFP_WAIT)) {
* this search will find all the extents that end after
* our range starts.
*/
- node = tree_search(tree, start);
+ node = tree_search_for_insert(tree, start, &p, &parent);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
if (!prealloc) {
err = -ENOMEM;
goto out;
}
- err = insert_state(tree, prealloc, start, end, &bits);
- prealloc = NULL;
+ err = insert_state(tree, prealloc, start, end,
+ &p, &parent, &bits);
if (err)
extent_io_tree_panic(tree, err);
+ cache_state(prealloc, cached_state);
+ prealloc = NULL;
goto out;
}
state = rb_entry(node, struct extent_state, rb_node);
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- &bits);
+ NULL, NULL, &bits);
if (err)
extent_io_tree_panic(tree, err);
cache_state(prealloc, cached_state);
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
if (!bio)
return -EIO;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
map_length = length;
ret = btrfs_map_block(fs_info, WRITE, logical,
}
BUG_ON(mirror_num != bbio->mirror_num);
sector = bbio->stripes[mirror_num-1].physical >> 9;
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
dev = bbio->stripes[mirror_num-1].dev;
kfree(bbio);
if (!dev || !dev->bdev || !dev->writeable) {
return -EIO;
}
- printk_ratelimited_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu "
- "(dev %s sector %llu)\n", page->mapping->host->i_ino,
- start, rcu_str_deref(dev->name), sector);
+ printk_ratelimited_in_rcu(KERN_INFO
+ "BTRFS: read error corrected: ino %lu off %llu "
+ "(dev %s sector %llu)\n", page->mapping->host->i_ino,
+ start, rcu_str_deref(dev->name), sector);
bio_put(bio);
return 0;
return -EIO;
}
- if (em->start > start || em->start + em->len < start) {
+ if (em->start > start || em->start + em->len <= start) {
free_extent_map(em);
em = NULL;
}
return -EIO;
}
bio->bi_end_io = failed_bio->bi_end_io;
- bio->bi_sector = failrec->logical >> 9;
+ bio->bi_iter.bi_sector = failrec->logical >> 9;
bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
btrfs_failed_bio = btrfs_io_bio(failed_bio);
if (btrfs_failed_bio->csum) {
*/
static void end_bio_extent_writepage(struct bio *bio, int err)
{
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct extent_io_tree *tree;
+ struct bio_vec *bvec;
u64 start;
u64 end;
+ int i;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
/* We always issue full-page reads, but if some block
* in a page fails to read, blk_update_request() will
* advance bv_offset and adjust bv_len to compensate.
* Print a warning for nonzero offsets, and an error
* if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE)
- printk("%s page write in btrfs with offset %u and length %u\n",
- bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE
- ? KERN_ERR "partial" : KERN_INFO "incomplete",
- bvec->bv_offset, bvec->bv_len);
+ if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
+ "partial page write in btrfs with offset %u and length %u",
+ bvec->bv_offset, bvec->bv_len);
+ else
+ btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
+ "incomplete page write in btrfs with offset %u and "
+ "length %u",
+ bvec->bv_offset, bvec->bv_len);
+ }
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
if (end_extent_writepage(page, err, start, end))
continue;
end_page_writeback(page);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
}
*/
static void end_bio_extent_readpage(struct bio *bio, int err)
{
+ struct bio_vec *bvec;
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct bio_vec *bvec = bio->bi_io_vec;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct extent_io_tree *tree;
u64 offset = 0;
u64 extent_len = 0;
int mirror;
int ret;
+ int i;
if (err)
uptodate = 0;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
struct inode *inode = page->mapping->host;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
- "mirror=%lu\n", (u64)bio->bi_sector, err,
+ "mirror=%lu\n", (u64)bio->bi_iter.bi_sector, err,
io_bio->mirror_num);
tree = &BTRFS_I(inode)->io_tree;
* advance bv_offset and adjust bv_len to compensate.
* Print a warning for nonzero offsets, and an error
* if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE)
- printk("%s page read in btrfs with offset %u and length %u\n",
- bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE
- ? KERN_ERR "partial" : KERN_INFO "incomplete",
- bvec->bv_offset, bvec->bv_len);
+ if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
+ "partial page read in btrfs with offset %u and length %u",
+ bvec->bv_offset, bvec->bv_len);
+ else
+ btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
+ "incomplete page read in btrfs with offset %u and "
+ "length %u",
+ bvec->bv_offset, bvec->bv_len);
+ }
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
len = bvec->bv_len;
- if (++bvec <= bvec_end)
- prefetchw(&bvec->bv_page->flags);
-
mirror = io_bio->mirror_num;
if (likely(uptodate && tree->ops &&
tree->ops->readpage_end_io_hook)) {
extent_start = start;
extent_len = end + 1 - start;
}
- } while (bvec <= bvec_end);
+ }
if (extent_len)
endio_readpage_release_extent(tree, extent_start, extent_len,
}
if (bio) {
- bio->bi_size = 0;
bio->bi_bdev = bdev;
- bio->bi_sector = first_sector;
+ bio->bi_iter.bi_sector = first_sector;
btrfs_bio = btrfs_io_bio(bio);
btrfs_bio->csum = NULL;
btrfs_bio->csum_allocated = NULL;
if (bio_ret && *bio_ret) {
bio = *bio_ret;
if (old_compressed)
- contig = bio->bi_sector == sector;
+ contig = bio->bi_iter.bi_sector == sector;
else
contig = bio_end_sector(bio) == sector;
set_range_writeback(tree, cur, cur + iosize - 1);
if (!PageWriteback(page)) {
- printk(KERN_ERR "btrfs warning page %lu not "
- "writeback, cur %llu end %llu\n",
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "page %lu not writeback, cur %llu end %llu",
page->index, cur, end);
}
static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
{
- int uptodate = err == 0;
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
struct extent_buffer *eb;
- int done;
+ int i, done;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- bvec--;
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
done = atomic_dec_and_test(&eb->io_pages);
- if (!uptodate || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+ if (err || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
ClearPageUptodate(page);
SetPageError(page);
continue;
end_extent_buffer_writeback(eb);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
-
}
static int write_one_eb(struct extent_buffer *eb,
struct extent_page_data *epd)
{
struct block_device *bdev = fs_info->fs_devices->latest_bdev;
+ struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
u64 offset = eb->start;
unsigned long i, num_pages;
unsigned long bio_flags = 0;
clear_page_dirty_for_io(p);
set_page_writeback(p);
- ret = submit_extent_page(rw, eb->tree, p, offset >> 9,
+ ret = submit_extent_page(rw, tree, p, offset >> 9,
PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
-1, end_bio_extent_buffer_writepage,
0, epd->bio_flags, bio_flags);
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
struct btrfs_path *path;
- struct btrfs_file_extent_item *item;
int end = 0;
u64 em_start = 0;
u64 em_len = 0;
u64 em_end = 0;
- unsigned long emflags;
if (len == 0)
return -EINVAL;
}
WARN_ON(!ret);
path->slots[0]--;
- item = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
offset_in_extent = em_start - em->start;
em_end = extent_map_end(em);
em_len = em_end - em_start;
- emflags = em->flags;
disko = 0;
flags = 0;
__free_extent_buffer(eb);
}
-static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
- u64 start,
- unsigned long len,
- gfp_t mask)
+static struct extent_buffer *
+__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
+ unsigned long len, gfp_t mask)
{
struct extent_buffer *eb = NULL;
return NULL;
eb->start = start;
eb->len = len;
- eb->tree = tree;
+ eb->fs_info = fs_info;
eb->bflags = 0;
rwlock_init(&eb->lock);
atomic_set(&eb->write_locks, 0);
}
}
-struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
- u64 start)
+struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
+ u64 start)
{
struct extent_buffer *eb;
rcu_read_lock();
- eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> PAGE_CACHE_SHIFT);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
mark_extent_buffer_accessed(eb);
return NULL;
}
-struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
+struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, unsigned long len)
{
unsigned long num_pages = num_extent_pages(start, len);
struct extent_buffer *eb;
struct extent_buffer *exists = NULL;
struct page *p;
- struct address_space *mapping = tree->mapping;
+ struct address_space *mapping = fs_info->btree_inode->i_mapping;
int uptodate = 1;
int ret;
-
- eb = find_extent_buffer(tree, start);
+ eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
- eb = __alloc_extent_buffer(tree, start, len, GFP_NOFS);
+ eb = __alloc_extent_buffer(fs_info, start, len, GFP_NOFS);
if (!eb)
return NULL;
if (ret)
goto free_eb;
- spin_lock(&tree->buffer_lock);
- ret = radix_tree_insert(&tree->buffer, start >> PAGE_CACHE_SHIFT, eb);
- spin_unlock(&tree->buffer_lock);
+ spin_lock(&fs_info->buffer_lock);
+ ret = radix_tree_insert(&fs_info->buffer_radix,
+ start >> PAGE_CACHE_SHIFT, eb);
+ spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
- exists = find_extent_buffer(tree, start);
+ exists = find_extent_buffer(fs_info, start);
if (exists)
goto free_eb;
else
}
/* add one reference for the tree */
check_buffer_tree_ref(eb);
+ set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
/*
* there is a race where release page may have
{
WARN_ON(atomic_read(&eb->refs) == 0);
if (atomic_dec_and_test(&eb->refs)) {
- if (test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags)) {
- spin_unlock(&eb->refs_lock);
- } else {
- struct extent_io_tree *tree = eb->tree;
+ if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
+ struct btrfs_fs_info *fs_info = eb->fs_info;
spin_unlock(&eb->refs_lock);
- spin_lock(&tree->buffer_lock);
- radix_tree_delete(&tree->buffer,
+ spin_lock(&fs_info->buffer_lock);
+ radix_tree_delete(&fs_info->buffer_radix,
eb->start >> PAGE_CACHE_SHIFT);
- spin_unlock(&tree->buffer_lock);
+ spin_unlock(&fs_info->buffer_lock);
+ } else {
+ spin_unlock(&eb->refs_lock);
}
/* Should be safe to release our pages at this point */
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus src_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
"len %lu dst len %lu\n", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus dst_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
"len %lu dst len %lu\n", dst_offset, len, dst->len);
BUG_ON(1);
}
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus src_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
"len %lu len %lu\n", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus dst_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
"len %lu len %lu\n", dst_offset, len, dst->len);
BUG_ON(1);
}