In order to handle multiple extent buffers per page, first we need to create a
way to handle all the extent buffers that are attached to a page.
This patch creates a new data structure 'struct extent_buffer_head', and moves
fields that are common to all extent buffers from 'struct extent buffer' to
'struct extent_buffer_head'
Also, this patch moves EXTENT_BUFFER_TREE_REF, EXTENT_BUFFER_DUMMY and
EXTENT_BUFFER_IN_TREE flags from extent_buffer->ebflags to
extent_buffer_head->bflags.
Reviewed-by: Liu Bo <bo.li....@oracle.com>
Signed-off-by: Chandan Rajendra <chan...@linux.vnet.ibm.com>
---
fs/btrfs/backref.c | 2 +-
fs/btrfs/ctree.c | 2 +-
fs/btrfs/ctree.h | 6 +-
fs/btrfs/disk-io.c | 78 +++---
fs/btrfs/extent-tree.c | 6 +-
fs/btrfs/extent_io.c | 588 ++++++++++++++++++++++++++++---------------
fs/btrfs/extent_io.h | 63 +++--
fs/btrfs/root-tree.c | 2 +-
fs/btrfs/volumes.c | 2 +-
include/trace/events/btrfs.h | 2 +-
10 files changed, 493 insertions(+), 258 deletions(-)
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index b90cd37..4d3d3e8 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1426,7 +1426,7 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root,
struct btrfs_path *path,
eb = path->nodes[0];
/* make sure we can use eb after releasing the path */
if (eb != eb_in) {
- atomic_inc(&eb->refs);
+ atomic_inc(&eb_head(eb)->refs);
btrfs_tree_read_lock(eb);
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
}
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index f5ef7d1..aa590a9 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -159,7 +159,7 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root
*root)
* the inc_not_zero dance and if it doesn't work then
* synchronize_rcu and try again.
*/
- if (atomic_inc_not_zero(&eb->refs)) {
+ if (atomic_inc_not_zero(&eb_head(eb)->refs)) {
rcu_read_unlock();
break;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 42ab582..34f53ac 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2433,14 +2433,16 @@ static inline void btrfs_set_token_##name(struct
extent_buffer *eb, \
#define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(struct extent_buffer *eb) \
{ \
- type *p = page_address(eb->pages[0]); \
+ type *p = page_address(eb_head(eb)->pages[0]) + \
+ (eb->start & (PAGE_CACHE_SIZE -1)); \
u##bits res = le##bits##_to_cpu(p->member); \
return res; \
} \
static inline void btrfs_set_##name(struct extent_buffer *eb, \
u##bits val) \
{ \
- type *p = page_address(eb->pages[0]); \
+ type *p = page_address(eb_head(eb)->pages[0]) + \
+ (eb->start & (PAGE_CACHE_SIZE -1)); \
p->member = cpu_to_le##bits(val); \
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 26ef141..9cfbcc3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -375,10 +375,9 @@ static int verify_parent_transid(struct extent_io_tree
*io_tree,
ret = 0;
goto out;
}
- btrfs_err_rl(eb->fs_info,
+ btrfs_err_rl(eb_head(eb)->fs_info,
"parent transid verify failed on %llu wanted %llu found %llu",
- eb->start,
- parent_transid, btrfs_header_generation(eb));
+ eb->start, parent_transid, btrfs_header_generation(eb));
ret = 1;
/*
@@ -452,7 +451,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root
*root,
int mirror_num = 0;
int failed_mirror = 0;
- clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags);
io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
while (1) {
ret = read_extent_buffer_pages(io_tree, eb, start,
@@ -471,7 +470,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root
*root,
* there is no reason to read the other copies, they won't be
* any less wrong.
*/
- if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
+ if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags))
break;
num_copies = btrfs_num_copies(root->fs_info,
@@ -510,7 +509,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info,
struct page *page)
struct extent_buffer *eb;
eb = (struct extent_buffer *)page->private;
- if (page != eb->pages[0])
+ if (page != eb_head(eb)->pages[0])
return 0;
found_start = btrfs_header_bytenr(eb);
if (WARN_ON(found_start != start || !PageUptodate(page)))
@@ -624,26 +623,26 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio
*io_bio,
*/
extent_buffer_get(eb);
- reads_done = atomic_dec_and_test(&eb->io_pages);
+ reads_done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
if (!reads_done)
goto err;
eb->read_mirror = mirror;
- if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
+ if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags)) {
ret = -EIO;
goto err;
}
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
- btrfs_err_rl(eb->fs_info, "bad tree block start %llu %llu",
- found_start, eb->start);
+ btrfs_err_rl(eb_head(eb)->fs_info, "bad tree block start %llu
%llu",
+ found_start, eb->start);
ret = -EIO;
goto err;
}
if (check_tree_block_fsid(root->fs_info, eb)) {
- btrfs_err_rl(eb->fs_info, "bad fsid on block %llu",
- eb->start);
+ btrfs_err_rl(eb_head(eb)->fs_info, "bad fsid on block %llu",
+ eb->start);
ret = -EIO;
goto err;
}
@@ -670,7 +669,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio
*io_bio,
* return -EIO.
*/
if (found_level == 0 && check_leaf(root, eb)) {
- set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
+ set_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags);
ret = -EIO;
}
@@ -678,7 +677,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio
*io_bio,
set_extent_buffer_uptodate(eb);
err:
if (reads_done &&
- test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
+ test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->ebflags))
btree_readahead_hook(root, eb, eb->start, ret);
if (ret) {
@@ -687,7 +686,7 @@ err:
* again, we have to make sure it has something
* to decrement
*/
- atomic_inc(&eb->io_pages);
+ atomic_inc(&eb_head(eb)->io_bvecs);
clear_extent_buffer_uptodate(eb);
}
free_extent_buffer(eb);
@@ -701,10 +700,10 @@ static int btree_io_failed_hook(struct page *page, int
failed_mirror)
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
eb = (struct extent_buffer *)page->private;
- set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
+ set_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags);
eb->read_mirror = failed_mirror;
- atomic_dec(&eb->io_pages);
- if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
+ atomic_dec(&eb_head(eb)->io_bvecs);
+ if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->ebflags))
btree_readahead_hook(root, eb, eb->start, -EIO);
return -EIO; /* we fixed nothing */
}
@@ -1062,13 +1061,24 @@ static int btree_set_page_dirty(struct page *page)
{
#ifdef DEBUG
struct extent_buffer *eb;
+ int i, dirty = 0;
BUG_ON(!PagePrivate(page));
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
- BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
- BUG_ON(!atomic_read(&eb->refs));
- btrfs_assert_tree_locked(eb);
+
+ do {
+ dirty = test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags);
+ if (dirty)
+ break;
+ } while ((eb = eb->eb_next) != NULL);
+
+ BUG_ON(!dirty);
+
+ eb = (struct extent_buffer *)page->private;
+ BUG_ON(!atomic_read(&(eb_head(eb)->refs)));
+
+ btrfs_assert_tree_locked(&ebh->eb);
#endif
return __set_page_dirty_nobuffers(page);
}
@@ -1109,7 +1119,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64
bytenr,
if (!buf)
return 0;
- set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
+ set_bit(EXTENT_BUFFER_READAHEAD, &buf->ebflags);
ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK,
btree_get_extent, mirror_num);
@@ -1118,7 +1128,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64
bytenr,
return ret;
}
- if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
+ if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->ebflags)) {
free_extent_buffer(buf);
return -EIO;
} else if (extent_buffer_uptodate(buf)) {
@@ -1146,14 +1156,16 @@ struct extent_buffer
*btrfs_find_create_tree_block(struct btrfs_root *root,
int btrfs_write_tree_block(struct extent_buffer *buf)
{
- return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
+ return filemap_fdatawrite_range(eb_head(buf)->pages[0]->mapping,
+ buf->start,
buf->start + buf->len - 1);
}
int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
{
- return filemap_fdatawait_range(buf->pages[0]->mapping,
- buf->start, buf->start + buf->len - 1);
+ return filemap_fdatawait_range(eb_head(buf)->pages[0]->mapping,
+ buf->start,
+ buf->start + buf->len - 1);
}
struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
@@ -1183,7 +1195,8 @@ void clean_tree_block(struct btrfs_trans_handle *trans,
fs_info->running_transaction->transid) {
btrfs_assert_tree_locked(buf);
- if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
+ if (test_and_clear_bit(EXTENT_BUFFER_DIRTY,
+ &buf->ebflags)) {
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-buf->len,
fs_info->dirty_metadata_batch);
@@ -3933,7 +3946,7 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64
parent_transid,
int atomic)
{
int ret;
- struct inode *btree_inode = buf->pages[0]->mapping->host;
+ struct inode *btree_inode = eb_head(buf)->pages[0]->mapping->host;
ret = extent_buffer_uptodate(buf);
if (!ret)
@@ -3958,10 +3971,10 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
* 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)))
+ if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY, &eb_head(buf)->bflags)))
return;
#endif
- root = BTRFS_I(buf->pages[0]->mapping->host)->root;
+ root = BTRFS_I(eb_head(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, "
@@ -4015,7 +4028,8 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_root
*root)
int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
{
- struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
+ struct btrfs_root *root =
+ BTRFS_I(eb_head(buf)->pages[0]->mapping->host)->root;
return btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
}
@@ -4350,7 +4364,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root
*root,
wait_on_extent_buffer_writeback(eb);
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY,
- &eb->bflags))
+ &eb->ebflags))
clear_extent_buffer_dirty(eb);
free_extent_buffer_stale(eb);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e2287c7..8cc71ba 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6843,7 +6843,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle
*trans,
goto out;
}
- WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
+ WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->ebflags));
btrfs_add_free_space(cache, buf->start, buf->len);
btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
@@ -6861,7 +6861,7 @@ out:
* Deleting the buffer, clear the corrupt flag since it doesn't matter
* anymore.
*/
- clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
+ clear_bit(EXTENT_BUFFER_CORRUPT, &buf->ebflags);
}
/* Can return -ENOMEM */
@@ -7901,7 +7901,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
btrfs_tree_lock(buf);
clean_tree_block(trans, root->fs_info, buf);
- clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
+ clear_bit(EXTENT_BUFFER_STALE, &buf->ebflags);
btrfs_set_lock_blocking(buf);
set_extent_buffer_uptodate(buf);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index da54e49..d5f0814 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -22,6 +22,7 @@
#include "backref.h"
static struct kmem_cache *extent_state_cache;
+static struct kmem_cache *extent_buffer_head_cache;
static struct kmem_cache *extent_buffer_cache;
static struct bio_set *btrfs_bioset;
@@ -61,6 +62,7 @@ void btrfs_leak_debug_check(void)
{
struct extent_state *state;
struct extent_buffer *eb;
+ struct extent_buffer_head *ebh;
while (!list_empty(&states)) {
state = list_entry(states.next, struct extent_state, leak_list);
@@ -73,12 +75,17 @@ void btrfs_leak_debug_check(void)
}
while (!list_empty(&buffers)) {
- eb = list_entry(buffers.next, struct extent_buffer, leak_list);
- 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);
- kmem_cache_free(extent_buffer_cache, eb);
+ ebh = list_entry(buffers.next, struct extent_buffer_head,
leak_list);
+ printk(KERN_ERR "btrfs buffer leak ");
+
+ eb = &ebh->eb;
+ do {
+ printk(KERN_ERR "eb %p %llu:%lu ", eb, eb->start,
eb->len);
+ } while ((eb = eb->eb_next) != NULL);
+
+ printk(KERN_ERR "refs %d\n", atomic_read(&ebh->refs));
+ list_del(&ebh->leak_list);
+ kmem_cache_free(extent_buffer_cache, ebh);
}
}
@@ -167,11 +174,17 @@ int __init extent_io_init(void)
if (!extent_state_cache)
return -ENOMEM;
+ extent_buffer_head_cache = kmem_cache_create("btrfs_extent_buffer_head",
+ sizeof(struct extent_buffer_head), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ if (!extent_buffer_head_cache)
+ goto free_state_cache;
+
extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
sizeof(struct extent_buffer), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
if (!extent_buffer_cache)
- goto free_state_cache;
+ goto free_buffer_head_cache;
btrfs_bioset = bioset_create(BIO_POOL_SIZE,
offsetof(struct btrfs_io_bio, bio));
@@ -191,6 +204,10 @@ free_buffer_cache:
kmem_cache_destroy(extent_buffer_cache);
extent_buffer_cache = NULL;
+free_buffer_head_cache:
+ kmem_cache_destroy(extent_buffer_head_cache);
+ extent_buffer_head_cache = NULL;
+
free_state_cache:
kmem_cache_destroy(extent_state_cache);
extent_state_cache = NULL;
@@ -2153,7 +2170,7 @@ int repair_eb_io_failure(struct btrfs_root *root, struct
extent_buffer *eb,
return -EROFS;
for (i = 0; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
ret = repair_io_failure(root->fs_info->btree_inode, start,
PAGE_CACHE_SIZE, start, p,
@@ -3672,8 +3689,8 @@ done_unlocked:
void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
{
- wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK,
- TASK_UNINTERRUPTIBLE);
+ wait_on_bit_io(&eb->ebflags, EXTENT_BUFFER_WRITEBACK,
+ TASK_UNINTERRUPTIBLE);
}
static noinline_for_stack int
@@ -3691,7 +3708,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
btrfs_tree_lock(eb);
}
- if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) {
+ if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags)) {
btrfs_tree_unlock(eb);
if (!epd->sync_io)
return 0;
@@ -3702,7 +3719,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
while (1) {
wait_on_extent_buffer_writeback(eb);
btrfs_tree_lock(eb);
- if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags))
+ if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags))
break;
btrfs_tree_unlock(eb);
}
@@ -3713,17 +3730,17 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
* under IO since we can end up having no IO bits set for a short period
* of time.
*/
- spin_lock(&eb->refs_lock);
- if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
- set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
- spin_unlock(&eb->refs_lock);
+ spin_lock(&eb_head(eb)->refs_lock);
+ if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags)) {
+ set_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags);
+ spin_unlock(&eb_head(eb)->refs_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-eb->len,
fs_info->dirty_metadata_batch);
ret = 1;
} else {
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&eb_head(eb)->refs_lock);
}
btrfs_tree_unlock(eb);
@@ -3733,7 +3750,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
if (!trylock_page(p)) {
if (!flush) {
@@ -3749,18 +3766,19 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
static void end_extent_buffer_writeback(struct extent_buffer *eb)
{
- clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags);
smp_mb__after_atomic();
- wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
+ wake_up_bit(&eb->ebflags, 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);
+ struct extent_buffer_head *ebh = eb_head(eb);
+ struct btrfs_inode *btree_ino = BTRFS_I(ebh->fs_info->btree_inode);
SetPageError(page);
- if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
+ if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags))
return;
/*
@@ -3827,10 +3845,10 @@ static void end_bio_extent_buffer_writepage(struct bio
*bio)
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
- done = atomic_dec_and_test(&eb->io_pages);
+ done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
if (bio->bi_error ||
- test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
+ test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags)) {
ClearPageUptodate(page);
set_btree_ioerr(page);
}
@@ -3859,14 +3877,14 @@ static noinline_for_stack int write_one_eb(struct
extent_buffer *eb,
int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
int ret = 0;
- clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags);
num_pages = num_extent_pages(eb->start, eb->len);
- atomic_set(&eb->io_pages, num_pages);
+ atomic_set(&eb_head(eb)->io_bvecs, 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 = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
clear_page_dirty_for_io(p);
set_page_writeback(p);
@@ -3878,7 +3896,8 @@ static noinline_for_stack int write_one_eb(struct
extent_buffer *eb,
if (ret) {
set_btree_ioerr(p);
end_page_writeback(p);
- if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
+ if (atomic_sub_and_test(num_pages - i,
+ &eb_head(eb)->io_bvecs))
end_extent_buffer_writeback(eb);
ret = -EIO;
break;
@@ -3890,7 +3909,7 @@ static noinline_for_stack int write_one_eb(struct
extent_buffer *eb,
if (unlikely(ret)) {
for (; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
clear_page_dirty_for_io(p);
unlock_page(p);
}
@@ -3978,7 +3997,7 @@ retry:
continue;
}
- ret = atomic_inc_not_zero(&eb->refs);
+ ret = atomic_inc_not_zero(&eb_head(eb)->refs);
spin_unlock(&mapping->private_lock);
if (!ret)
continue;
@@ -4656,17 +4675,36 @@ out:
return ret;
}
-static void __free_extent_buffer(struct extent_buffer *eb)
+static void __free_extent_buffer(struct extent_buffer_head *ebh)
{
- btrfs_leak_debug_del(&eb->leak_list);
- kmem_cache_free(extent_buffer_cache, eb);
+ struct extent_buffer *eb, *next_eb;
+
+ btrfs_leak_debug_del(&ebh->leak_list);
+
+ eb = ebh->eb.eb_next;
+ while (eb) {
+ next_eb = eb->eb_next;
+ kmem_cache_free(extent_buffer_cache, eb);
+ eb = next_eb;
+ }
+
+ kmem_cache_free(extent_buffer_head_cache, ebh);
}
int extent_buffer_under_io(struct extent_buffer *eb)
{
- return (atomic_read(&eb->io_pages) ||
- test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
- test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+ struct extent_buffer_head *ebh = eb->ebh;
+ int dirty_or_writeback = 0;
+
+ for (eb = &ebh->eb; eb; eb = eb->eb_next) {
+ if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags)
+ || test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags)) {
+ dirty_or_writeback = 1;
+ break;
+ }
+ }
+
+ return (atomic_read(&ebh->io_bvecs) || dirty_or_writeback);
}
/*
@@ -4676,7 +4714,8 @@ static void btrfs_release_extent_buffer_page(struct
extent_buffer *eb)
{
unsigned long index;
struct page *page;
- int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+ struct extent_buffer_head *ebh = eb_head(eb);
+ int mapped = !test_bit(EXTENT_BUFFER_HEAD_DUMMY, &ebh->bflags);
BUG_ON(extent_buffer_under_io(eb));
@@ -4685,8 +4724,11 @@ static void btrfs_release_extent_buffer_page(struct
extent_buffer *eb)
return;
do {
+ struct extent_buffer *e;
+
index--;
- page = eb->pages[index];
+
+ page = ebh->pages[index];
if (!page)
continue;
if (mapped)
@@ -4699,8 +4741,10 @@ static void btrfs_release_extent_buffer_page(struct
extent_buffer *eb)
* this eb.
*/
if (PagePrivate(page) &&
- page->private == (unsigned long)eb) {
- BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+ page->private == (unsigned long)(&ebh->eb)) {
+ for (e = &ebh->eb; !e; e = e->eb_next)
+ BUG_ON(test_bit(EXTENT_BUFFER_DIRTY,
+ &e->ebflags));
BUG_ON(PageDirty(page));
BUG_ON(PageWriteback(page));
/*
@@ -4727,20 +4771,18 @@ static void btrfs_release_extent_buffer_page(struct
extent_buffer *eb)
static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
{
btrfs_release_extent_buffer_page(eb);
- __free_extent_buffer(eb);
+ __free_extent_buffer(eb_head(eb));
}
-static struct extent_buffer *
-__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
- unsigned long len)
+static void __init_extent_buffer(struct extent_buffer *eb,
+ struct extent_buffer_head *ebh,
+ u64 start,
+ unsigned long len)
{
- struct extent_buffer *eb = NULL;
-
- eb = kmem_cache_zalloc(extent_buffer_cache, GFP_NOFS|__GFP_NOFAIL);
eb->start = start;
eb->len = len;
- eb->fs_info = fs_info;
- eb->bflags = 0;
+ eb->ebh = ebh;
+ eb->eb_next = NULL;
rwlock_init(&eb->lock);
atomic_set(&eb->write_locks, 0);
atomic_set(&eb->read_locks, 0);
@@ -4751,12 +4793,27 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start,
eb->lock_nested = 0;
init_waitqueue_head(&eb->write_lock_wq);
init_waitqueue_head(&eb->read_lock_wq);
+}
- btrfs_leak_debug_add(&eb->leak_list, &buffers);
+static struct extent_buffer *
+__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
+ unsigned long len)
+{
+ struct extent_buffer_head *ebh = NULL;
+ struct extent_buffer *cur_eb, *prev_eb;
+ struct extent_buffer *eb = NULL;
+ int i;
+
+ ebh = kmem_cache_zalloc(extent_buffer_head_cache,
GFP_NOFS|__GFP_NOFAIL);
+ if (ebh == NULL)
+ return NULL;
+ ebh->fs_info = fs_info;
+ ebh->bflags = 0;
+ btrfs_leak_debug_add(&ebh->leak_list, &buffers);
- spin_lock_init(&eb->refs_lock);
- atomic_set(&eb->refs, 1);
- atomic_set(&eb->io_pages, 0);
+ spin_lock_init(&ebh->refs_lock);
+ atomic_set(&ebh->refs, 1);
+ atomic_set(&ebh->io_bvecs, 0);
/*
* Sanity checks, currently the maximum is 64k covered by 16x 4k pages
@@ -4765,7 +4822,44 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64
start,
> MAX_INLINE_EXTENT_BUFFER_SIZE);
BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE);
+ if (len < PAGE_CACHE_SIZE) {
+ int ebs_per_page = PAGE_CACHE_SIZE / len;
+ u64 st = start & ~(PAGE_CACHE_SIZE - 1);
+
+ prev_eb = NULL;
+ cur_eb = &ebh->eb;
+ for (i = 0; i < ebs_per_page; i++, st += len) {
+ if (prev_eb) {
+ cur_eb = kmem_cache_zalloc(extent_buffer_cache,
+ GFP_NOFS|__GFP_NOFAIL);
+ if (cur_eb == NULL)
+ goto out;
+ prev_eb->eb_next = cur_eb;
+ }
+ __init_extent_buffer(cur_eb, ebh, st, len);
+ prev_eb = cur_eb;
+ if (st == start)
+ eb = cur_eb;
+ }
+ BUG_ON(!eb);
+ } else {
+ eb = &ebh->eb;
+ __init_extent_buffer(eb, ebh, start, len);
+ }
+
return eb;
+
+out:
+ cur_eb = ebh->eb.eb_next;
+ while (cur_eb) {
+ prev_eb = cur_eb;
+ cur_eb = cur_eb->eb_next;
+ kmem_cache_free(extent_buffer_cache, prev_eb);
+ }
+
+ kmem_cache_free(extent_buffer_head_cache, ebh);
+
+ return NULL;
}
struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
@@ -4775,7 +4869,8 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct
extent_buffer *src)
struct extent_buffer *new;
unsigned long num_pages = num_extent_pages(src->start, src->len);
- new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
+ new = __alloc_extent_buffer(eb_head(src)->fs_info, src->start,
+ src->len);
if (new == NULL)
return NULL;
@@ -4785,15 +4880,25 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct
extent_buffer *src)
btrfs_release_extent_buffer(new);
return NULL;
}
- attach_extent_buffer_page(new, p);
+ attach_extent_buffer_page(&(eb_head(new)->eb), p);
WARN_ON(PageDirty(p));
SetPageUptodate(p);
- new->pages[i] = p;
+ eb_head(new)->pages[i] = p;
}
+ /*
+ * copy_extent_buffer() now checks for the presence of
+ * EXTENT_BUFFER_UPTODATE flag (instead of the page's
+ * PG_Uptodate flag) in dst extent buffer. Hence we set
+ * EXTENT_BUFFER_UPTODATE bit before copy_extent_buffer()
+ * is invoked. It is safe since this is the only function
+ * that has a reference to the just allocated dummy extent
+ * buffer.
+ */
+ set_bit(EXTENT_BUFFER_UPTODATE, &new->ebflags);
+ set_bit(EXTENT_BUFFER_HEAD_DUMMY, &eb_head(new)->bflags);
+
copy_extent_buffer(new, src, 0, 0, src->len);
- set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
- set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
return new;
}
@@ -4812,19 +4917,19 @@ struct extent_buffer
*__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
return NULL;
for (i = 0; i < num_pages; i++) {
- eb->pages[i] = alloc_page(GFP_NOFS);
- if (!eb->pages[i])
+ eb_head(eb)->pages[i] = alloc_page(GFP_NOFS);
+ if (!eb_head(eb)->pages[i])
goto err;
}
set_extent_buffer_uptodate(eb);
btrfs_set_header_nritems(eb, 0);
- set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+ set_bit(EXTENT_BUFFER_HEAD_DUMMY, &eb_head(eb)->bflags);
return eb;
err:
for (; i > 0; i--)
- __free_page(eb->pages[i - 1]);
- __free_extent_buffer(eb);
+ __free_page(eb_head(eb)->pages[i - 1]);
+ __free_extent_buffer(eb_head(eb));
return NULL;
}
@@ -4869,14 +4974,16 @@ static void check_buffer_tree_ref(struct extent_buffer
*eb)
* So bump the ref count first, then set the bit. If someone
* beat us to it, drop the ref we added.
*/
- refs = atomic_read(&eb->refs);
- if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
+ refs = atomic_read(&eb_head(eb)->refs);
+ if (refs >= 2 && test_bit(EXTENT_BUFFER_HEAD_TREE_REF,
+ &eb_head(eb)->bflags))
return;
- spin_lock(&eb->refs_lock);
- if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
- atomic_inc(&eb->refs);
- spin_unlock(&eb->refs_lock);
+ spin_lock(&eb_head(eb)->refs_lock);
+ if (!test_and_set_bit(EXTENT_BUFFER_HEAD_TREE_REF,
+ &eb_head(eb)->bflags))
+ atomic_inc(&eb_head(eb)->refs);
+ spin_unlock(&eb_head(eb)->refs_lock);
}
static void mark_extent_buffer_accessed(struct extent_buffer *eb,
@@ -4888,44 +4995,67 @@ static void mark_extent_buffer_accessed(struct
extent_buffer *eb,
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
if (p != accessed)
mark_page_accessed(p);
}
}
+static int extent_buffer_head_stale(struct extent_buffer_head *ebh)
+{
+ struct extent_buffer *eb = &ebh->eb;
+
+ do {
+ if (test_bit(EXTENT_BUFFER_STALE, &eb->ebflags))
+ return 1;
+ } while ((eb = eb->eb_next) != NULL);
+
+ return 0;
+}
+
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start)
{
+ struct extent_buffer_head *ebh;
struct extent_buffer *eb;
rcu_read_lock();
- eb = radix_tree_lookup(&fs_info->buffer_radix,
- start >> PAGE_CACHE_SHIFT);
- if (eb && atomic_inc_not_zero(&eb->refs)) {
+ ebh = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> PAGE_CACHE_SHIFT);
+ if (ebh && atomic_inc_not_zero(&ebh->refs)) {
rcu_read_unlock();
/*
- * Lock our eb's refs_lock to avoid races with
- * free_extent_buffer. When we get our eb it might be flagged
- * with EXTENT_BUFFER_STALE and another task running
- * free_extent_buffer might have seen that flag set,
- * eb->refs == 2, that the buffer isn't under IO (dirty and
- * writeback flags not set) and it's still in the tree (flag
- * EXTENT_BUFFER_TREE_REF set), therefore being in the process
- * of decrementing the extent buffer's reference count twice.
- * So here we could race and increment the eb's reference count,
- * clear its stale flag, mark it as dirty and drop our reference
- * before the other task finishes executing free_extent_buffer,
- * which would later result in an attempt to free an extent
- * buffer that is dirty.
+ * Lock our ebh's refs_lock to avoid races with
+ * free_extent_buffer. When we get our eb it might be
+ * flagged with EXTENT_BUFFER_STALE and another task
+ * running free_extent_buffer might have seen that
+ * flag set, ebh->refs == 2, that the buffer isn't
+ * under IO (dirty and writeback flags not set) and
+ * it's still in the tree (flag
+ * EXTENT_BUFFER_HEAD_TREE_REF set), therefore being
+ * in the process of decrementing the extent buffer's
+ * reference count twice. So here we could race and
+ * increment the ebh's reference count, clear its
+ * stale flag, mark it as dirty and drop our reference
+ * before the other task finishes executing
+ * free_extent_buffer, which would later result in an
+ * attempt to free an extent buffer head (along with
+ * its extent buffers) that has a dirty extent buffer.
*/
- if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
- spin_lock(&eb->refs_lock);
- spin_unlock(&eb->refs_lock);
- }
- mark_extent_buffer_accessed(eb, NULL);
- return eb;
+ eb = &ebh->eb;
+ do {
+ if (eb->start == start) {
+ if (extent_buffer_head_stale(ebh)) {
+ spin_lock(&ebh->refs_lock);
+ spin_unlock(&ebh->refs_lock);
+ }
+ mark_extent_buffer_accessed(eb, NULL);
+ return eb;
+ }
+ } while ((eb = eb->eb_next) != NULL);
+
+ BUG();
}
rcu_read_unlock();
@@ -4963,7 +5093,7 @@ again:
goto again;
}
check_buffer_tree_ref(eb);
- set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
+ set_bit(EXTENT_BUFFER_HEAD_IN_TREE, &eb->bflags);
/*
* We will free dummy extent buffer's if they come into
@@ -4986,7 +5116,7 @@ struct extent_buffer *alloc_extent_buffer(struct
btrfs_fs_info *fs_info,
unsigned long num_pages = num_extent_pages(start, len);
unsigned long i;
unsigned long index = start >> PAGE_CACHE_SHIFT;
- struct extent_buffer *eb;
+ struct extent_buffer *eb, *cur_eb;
struct extent_buffer *exists = NULL;
struct page *p;
struct address_space *mapping = fs_info->btree_inode->i_mapping;
@@ -5016,12 +5146,18 @@ struct extent_buffer *alloc_extent_buffer(struct
btrfs_fs_info *fs_info,
* overwrite page->private.
*/
exists = (struct extent_buffer *)p->private;
- if (atomic_inc_not_zero(&exists->refs)) {
+ if (atomic_inc_not_zero(&eb_head(exists)->refs)) {
spin_unlock(&mapping->private_lock);
unlock_page(p);
page_cache_release(p);
- mark_extent_buffer_accessed(exists, p);
- goto free_eb;
+ do {
+ if (exists->start == start) {
+
mark_extent_buffer_accessed(exists, p);
+ goto free_eb;
+ }
+ } while ((exists = exists->eb_next) != NULL);
+
+ BUG();
}
exists = NULL;
@@ -5033,10 +5169,11 @@ struct extent_buffer *alloc_extent_buffer(struct
btrfs_fs_info *fs_info,
WARN_ON(PageDirty(p));
page_cache_release(p);
}
- attach_extent_buffer_page(eb, p);
+ attach_extent_buffer_page(&(eb_head(eb)->eb), p);
spin_unlock(&mapping->private_lock);
WARN_ON(PageDirty(p));
- eb->pages[i] = p;
+ mark_page_accessed(p);
+ eb_head(eb)->pages[i] = p;
if (!PageUptodate(p))
uptodate = 0;
@@ -5045,16 +5182,22 @@ struct extent_buffer *alloc_extent_buffer(struct
btrfs_fs_info *fs_info,
* and why we unlock later
*/
}
- if (uptodate)
- set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ if (uptodate) {
+ cur_eb = &(eb_head(eb)->eb);
+ do {
+ set_bit(EXTENT_BUFFER_UPTODATE, &cur_eb->ebflags);
+ } while ((cur_eb = cur_eb->eb_next) != NULL);
+ }
again:
ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
- if (ret)
+ if (ret) {
+ exists = NULL;
goto free_eb;
+ }
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> PAGE_CACHE_SHIFT, eb);
+ start >> PAGE_CACHE_SHIFT, eb_head(eb));
spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
@@ -5066,7 +5209,7 @@ again:
}
/* add one reference for the tree */
check_buffer_tree_ref(eb);
- set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
+ set_bit(EXTENT_BUFFER_HEAD_IN_TREE, &eb_head(eb)->bflags);
/*
* there is a race where release page may have
@@ -5077,20 +5220,20 @@ again:
* after the extent buffer is in the radix tree so
* it doesn't get lost
*/
- SetPageChecked(eb->pages[0]);
+ SetPageChecked(eb_head(eb)->pages[0]);
for (i = 1; i < num_pages; i++) {
- p = eb->pages[i];
+ p = eb_head(eb)->pages[i];
ClearPageChecked(p);
unlock_page(p);
}
- unlock_page(eb->pages[0]);
+ unlock_page(eb_head(eb)->pages[0]);
return eb;
free_eb:
- WARN_ON(!atomic_dec_and_test(&eb->refs));
+ WARN_ON(!atomic_dec_and_test(&eb_head(eb)->refs));
for (i = 0; i < num_pages; i++) {
- if (eb->pages[i])
- unlock_page(eb->pages[i]);
+ if (eb_head(eb)->pages[i])
+ unlock_page(eb_head(eb)->pages[i]);
}
btrfs_release_extent_buffer(eb);
@@ -5099,92 +5242,111 @@ free_eb:
static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
{
- struct extent_buffer *eb =
- container_of(head, struct extent_buffer, rcu_head);
+ struct extent_buffer_head *ebh =
+ container_of(head, struct extent_buffer_head, rcu_head);
- __free_extent_buffer(eb);
+ __free_extent_buffer(ebh);
}
/* Expects to have eb->eb_lock already held */
-static int release_extent_buffer(struct extent_buffer *eb)
+static int release_extent_buffer(struct extent_buffer_head *ebh)
{
- WARN_ON(atomic_read(&eb->refs) == 0);
- if (atomic_dec_and_test(&eb->refs)) {
- if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
- struct btrfs_fs_info *fs_info = eb->fs_info;
+ WARN_ON(atomic_read(&ebh->refs) == 0);
+ if (atomic_dec_and_test(&ebh->refs)) {
+ if (test_and_clear_bit(EXTENT_BUFFER_HEAD_IN_TREE,
+ &ebh->bflags)) {
+ struct btrfs_fs_info *fs_info = ebh->fs_info;
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&ebh->refs_lock);
spin_lock(&fs_info->buffer_lock);
radix_tree_delete(&fs_info->buffer_radix,
- eb->start >> PAGE_CACHE_SHIFT);
+ ebh->eb.start >> PAGE_CACHE_SHIFT);
spin_unlock(&fs_info->buffer_lock);
} else {
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&ebh->refs_lock);
}
/* Should be safe to release our pages at this point */
- btrfs_release_extent_buffer_page(eb);
+ btrfs_release_extent_buffer_page(&ebh->eb);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
- __free_extent_buffer(eb);
+ if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
+ &eb_head(buf)->bflags))) {
+ __free_extent_buffer(eb_head(eb));
return 1;
}
#endif
- call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
+ call_rcu(&ebh->rcu_head, btrfs_release_extent_buffer_rcu);
return 1;
}
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&ebh->refs_lock);
return 0;
}
void free_extent_buffer(struct extent_buffer *eb)
{
+ struct extent_buffer_head *ebh;
int refs;
int old;
if (!eb)
return;
+ ebh = eb_head(eb);
while (1) {
- refs = atomic_read(&eb->refs);
+ refs = atomic_read(&ebh->refs);
if (refs <= 3)
break;
- old = atomic_cmpxchg(&eb->refs, refs, refs - 1);
+ old = atomic_cmpxchg(&ebh->refs, refs, refs - 1);
if (old == refs)
return;
}
- spin_lock(&eb->refs_lock);
- if (atomic_read(&eb->refs) == 2 &&
- test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))
- atomic_dec(&eb->refs);
+ spin_lock(&ebh->refs_lock);
+ if (atomic_read(&ebh->refs) == 2 &&
+ test_bit(EXTENT_BUFFER_HEAD_DUMMY, &ebh->bflags))
+ atomic_dec(&ebh->refs);
- if (atomic_read(&eb->refs) == 2 &&
- test_bit(EXTENT_BUFFER_STALE, &eb->bflags) &&
+ if (atomic_read(&ebh->refs) == 2 &&
+ test_bit(EXTENT_BUFFER_STALE, &eb->ebflags) &&
!extent_buffer_under_io(eb) &&
- test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
- atomic_dec(&eb->refs);
+ test_and_clear_bit(EXTENT_BUFFER_HEAD_TREE_REF, &ebh->bflags))
+ atomic_dec(&ebh->refs);
/*
* I know this is terrible, but it's temporary until we stop tracking
* the uptodate bits and such for the extent buffers.
*/
- release_extent_buffer(eb);
+ release_extent_buffer(ebh);
}
void free_extent_buffer_stale(struct extent_buffer *eb)
{
+ struct extent_buffer_head *ebh;
if (!eb)
return;
- spin_lock(&eb->refs_lock);
- set_bit(EXTENT_BUFFER_STALE, &eb->bflags);
+ ebh = eb_head(eb);
+ spin_lock(&ebh->refs_lock);
+
+ set_bit(EXTENT_BUFFER_STALE, &eb->ebflags);
+ if (atomic_read(&ebh->refs) == 2 && !extent_buffer_under_io(eb) &&
+ test_and_clear_bit(EXTENT_BUFFER_HEAD_TREE_REF, &ebh->bflags))
+ atomic_dec(&ebh->refs);
- if (atomic_read(&eb->refs) == 2 && !extent_buffer_under_io(eb) &&
- test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
- atomic_dec(&eb->refs);
- release_extent_buffer(eb);
+ release_extent_buffer(ebh);
+}
+
+static int page_ebs_clean(struct extent_buffer_head *ebh)
+{
+ struct extent_buffer *eb = &ebh->eb;
+
+ do {
+ if (test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags))
+ return 0;
+ } while ((eb = eb->eb_next) != NULL);
+
+ return 1;
}
void clear_extent_buffer_dirty(struct extent_buffer *eb)
@@ -5195,8 +5357,11 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
num_pages = num_extent_pages(eb->start, eb->len);
+ if (eb->len < PAGE_CACHE_SIZE && !page_ebs_clean(eb_head(eb)))
+ return;
+
for (i = 0; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (!PageDirty(page))
continue;
@@ -5214,7 +5379,7 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
ClearPageError(page);
unlock_page(page);
}
- WARN_ON(atomic_read(&eb->refs) == 0);
+ WARN_ON(atomic_read(&eb_head(eb)->refs) == 0);
}
int set_extent_buffer_dirty(struct extent_buffer *eb)
@@ -5225,14 +5390,14 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
check_buffer_tree_ref(eb);
- was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
+ was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags);
num_pages = num_extent_pages(eb->start, eb->len);
- WARN_ON(atomic_read(&eb->refs) == 0);
- WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
+ WARN_ON(atomic_read(&eb_head(eb)->refs) == 0);
+ WARN_ON(!test_bit(EXTENT_BUFFER_HEAD_TREE_REF, &eb_head(eb)->bflags));
for (i = 0; i < num_pages; i++)
- set_page_dirty(eb->pages[i]);
+ set_page_dirty(eb_head(eb)->pages[i]);
return was_dirty;
}
@@ -5242,10 +5407,10 @@ void clear_extent_buffer_uptodate(struct extent_buffer
*eb)
struct page *page;
unsigned long num_pages;
- clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (page)
ClearPageUptodate(page);
}
@@ -5253,21 +5418,41 @@ void clear_extent_buffer_uptodate(struct extent_buffer
*eb)
void set_extent_buffer_uptodate(struct extent_buffer *eb)
{
+ struct extent_buffer_head *ebh;
unsigned long i;
struct page *page;
unsigned long num_pages;
+ int uptodate;
- set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
- num_pages = num_extent_pages(eb->start, eb->len);
- for (i = 0; i < num_pages; i++) {
- page = eb->pages[i];
- SetPageUptodate(page);
+ ebh = eb->ebh;
+
+ set_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
+ if (eb->len < PAGE_CACHE_SIZE) {
+ eb = &(eb_head(eb)->eb);
+ uptodate = 1;
+ do {
+ if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags)) {
+ uptodate = 0;
+ break;
+ }
+ } while ((eb = eb->eb_next) != NULL);
+
+ if (uptodate) {
+ page = ebh->pages[0];
+ SetPageUptodate(page);
+ }
+ } else {
+ num_pages = num_extent_pages(eb->start, eb->len);
+ for (i = 0; i < num_pages; i++) {
+ page = ebh->pages[i];
+ SetPageUptodate(page);
+ }
}
}
int extent_buffer_uptodate(struct extent_buffer *eb)
{
- return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ return test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
}
int read_extent_buffer_pages(struct extent_io_tree *tree,
@@ -5286,7 +5471,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
struct bio *bio = NULL;
unsigned long bio_flags = 0;
- if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
+ if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags))
return 0;
if (start) {
@@ -5299,7 +5484,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
num_pages = num_extent_pages(eb->start, eb->len);
for (i = start_i; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (wait == WAIT_NONE) {
if (!trylock_page(page))
goto unlock_exit;
@@ -5314,15 +5499,15 @@ int read_extent_buffer_pages(struct extent_io_tree
*tree,
}
if (all_uptodate) {
if (start_i == 0)
- set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ set_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
goto unlock_exit;
}
- clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags);
eb->read_mirror = 0;
- atomic_set(&eb->io_pages, num_reads);
+ atomic_set(&eb_head(eb)->io_bvecs, num_reads);
for (i = start_i; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (!PageUptodate(page)) {
ClearPageError(page);
err = __extent_read_full_page(tree, page,
@@ -5347,7 +5532,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
return ret;
for (i = start_i; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
wait_on_page_locked(page);
if (!PageUptodate(page))
ret = -EIO;
@@ -5358,7 +5543,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
unlock_exit:
i = start_i;
while (locked_pages > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
i++;
unlock_page(page);
locked_pages--;
@@ -5384,7 +5569,7 @@ void read_extent_buffer(struct extent_buffer *eb, void
*dstv,
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
cur = min(len, (PAGE_CACHE_SIZE - offset));
kaddr = page_address(page);
@@ -5416,7 +5601,7 @@ int read_extent_buffer_to_user(struct extent_buffer *eb,
void __user *dstv,
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
cur = min(len, (PAGE_CACHE_SIZE - offset));
kaddr = page_address(page);
@@ -5465,7 +5650,7 @@ int map_private_extent_buffer(struct extent_buffer *eb,
unsigned long start,
return -EINVAL;
}
- p = eb->pages[i];
+ p = eb_head(eb)->pages[i];
kaddr = page_address(p);
*map = kaddr + offset;
*map_len = PAGE_CACHE_SIZE - offset;
@@ -5491,7 +5676,7 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const
void *ptrv,
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
cur = min(len, (PAGE_CACHE_SIZE - offset));
@@ -5521,12 +5706,12 @@ void write_extent_buffer(struct extent_buffer *eb,
const void *srcv,
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
+ WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags));
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ page = eb_head(eb)->pages[i];
cur = min(len, PAGE_CACHE_SIZE - offset);
kaddr = page_address(page);
@@ -5554,9 +5739,10 @@ void memset_extent_buffer(struct extent_buffer *eb, char
c,
offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+ WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags));
+
while (len > 0) {
- page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ page = eb_head(eb)->pages[i];
cur = min(len, PAGE_CACHE_SIZE - offset);
kaddr = page_address(page);
@@ -5585,9 +5771,10 @@ void copy_extent_buffer(struct extent_buffer *dst,
struct extent_buffer *src,
offset = (start_offset + dst_offset) &
(PAGE_CACHE_SIZE - 1);
+ WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &dst->ebflags));
+
while (len > 0) {
- page = dst->pages[i];
- WARN_ON(!PageUptodate(page));
+ page = eb_head(dst)->pages[i];
cur = min(len, (unsigned long)(PAGE_CACHE_SIZE - offset));
@@ -5661,7 +5848,7 @@ int extent_buffer_test_bit(struct extent_buffer *eb,
unsigned long start,
size_t offset;
eb_bitmap_offset(eb, start, nr, &i, &offset);
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
@@ -5686,7 +5873,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb,
unsigned long start,
unsigned int mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
eb_bitmap_offset(eb, start, pos, &i, &offset);
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
@@ -5697,7 +5884,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb,
unsigned long start,
mask_to_set = ~0U;
if (++offset >= PAGE_CACHE_SIZE && len > 0) {
offset = 0;
- page = eb->pages[++i];
+ page = eb_head(eb)->pages[++i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
}
@@ -5728,7 +5915,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb,
unsigned long start,
unsigned int mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
eb_bitmap_offset(eb, start, pos, &i, &offset);
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
@@ -5739,7 +5926,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb,
unsigned long start,
mask_to_clear = ~0U;
if (++offset >= PAGE_CACHE_SIZE && len > 0) {
offset = 0;
- page = eb->pages[++i];
+ page = eb_head(eb)->pages[++i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
}
@@ -5789,13 +5976,13 @@ void memcpy_extent_buffer(struct extent_buffer *dst,
unsigned long dst_offset,
unsigned long src_i;
if (src_offset + len > dst->len) {
- btrfs_err(dst->fs_info,
+ btrfs_err(eb_head(dst)->fs_info,
"memmove bogus src_offset %lu move "
"len %lu dst len %lu", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- btrfs_err(dst->fs_info,
+ btrfs_err(eb_head(dst)->fs_info,
"memmove bogus dst_offset %lu move "
"len %lu dst len %lu", dst_offset, len, dst->len);
BUG_ON(1);
@@ -5815,8 +6002,9 @@ void memcpy_extent_buffer(struct extent_buffer *dst,
unsigned long dst_offset,
cur = min_t(unsigned long, cur,
(unsigned long)(PAGE_CACHE_SIZE - dst_off_in_page));
- copy_pages(dst->pages[dst_i], dst->pages[src_i],
- dst_off_in_page, src_off_in_page, cur);
+ copy_pages(eb_head(dst)->pages[dst_i],
+ eb_head(dst)->pages[src_i],
+ dst_off_in_page, src_off_in_page, cur);
src_offset += cur;
dst_offset += cur;
@@ -5837,13 +6025,15 @@ void memmove_extent_buffer(struct extent_buffer *dst,
unsigned long dst_offset,
unsigned long src_i;
if (src_offset + len > dst->len) {
- btrfs_err(dst->fs_info, "memmove bogus src_offset %lu move "
- "len %lu len %lu", src_offset, len, dst->len);
+ btrfs_err(eb_head(dst)->fs_info,
+ "memmove bogus src_offset %lu move len %lu len %lu",
+ src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- btrfs_err(dst->fs_info, "memmove bogus dst_offset %lu move "
- "len %lu len %lu", dst_offset, len, dst->len);
+ btrfs_err(eb_head(dst)->fs_info,
+ "memmove bogus dst_offset %lu move len %lu len %lu",
+ dst_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset < src_offset) {
@@ -5861,9 +6051,10 @@ void memmove_extent_buffer(struct extent_buffer *dst,
unsigned long dst_offset,
cur = min_t(unsigned long, len, src_off_in_page + 1);
cur = min(cur, dst_off_in_page + 1);
- copy_pages(dst->pages[dst_i], dst->pages[src_i],
- dst_off_in_page - cur + 1,
- src_off_in_page - cur + 1, cur);
+ copy_pages(eb_head(dst)->pages[dst_i],
+ eb_head(dst)->pages[src_i],
+ dst_off_in_page - cur + 1,
+ src_off_in_page - cur + 1, cur);
dst_end -= cur;
src_end -= cur;
@@ -5873,6 +6064,7 @@ void memmove_extent_buffer(struct extent_buffer *dst,
unsigned long dst_offset,
int try_release_extent_buffer(struct page *page)
{
+ struct extent_buffer_head *ebh;
struct extent_buffer *eb;
/*
@@ -5888,14 +6080,15 @@ int try_release_extent_buffer(struct page *page)
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
+ ebh = eb->ebh;
/*
* This is a little awful but should be ok, we need to make sure that
* the eb doesn't disappear out from under us while we're looking at
* this page.
*/
- spin_lock(&eb->refs_lock);
- if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
- spin_unlock(&eb->refs_lock);
+ spin_lock(&ebh->refs_lock);
+ if (atomic_read(&ebh->refs) != 1 || extent_buffer_under_io(eb)) {
+ spin_unlock(&ebh->refs_lock);
spin_unlock(&page->mapping->private_lock);
return 0;
}
@@ -5905,10 +6098,11 @@ int try_release_extent_buffer(struct page *page)
* If tree ref isn't set then we know the ref on this eb is a real ref,
* so just return, this page will likely be freed soon anyway.
*/
- if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
- spin_unlock(&eb->refs_lock);
+ if (!test_and_clear_bit(EXTENT_BUFFER_HEAD_TREE_REF, &ebh->bflags)) {
+ spin_unlock(&ebh->refs_lock);
return 0;
}
- return release_extent_buffer(eb);
+ return release_extent_buffer(ebh);
}
+
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index e7d377f..a9c81cf 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -32,18 +32,20 @@
#define EXTENT_BIO_PARENT_LOCKED 4
#define EXTENT_BIO_FLAG_SHIFT 16
-/* these are bit numbers for test/set bit */
+/* these are bit numbers for test/set bit on extent buffer head */
+#define EXTENT_BUFFER_HEAD_TREE_REF 0
+#define EXTENT_BUFFER_HEAD_DUMMY 1
+#define EXTENT_BUFFER_HEAD_IN_TREE 2
+
+/* these are bit numbers for test/set bit on extent buffer */
#define EXTENT_BUFFER_UPTODATE 0
-#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_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 */
+#define EXTENT_BUFFER_DIRTY 1
+#define EXTENT_BUFFER_CORRUPT 2
+#define EXTENT_BUFFER_READAHEAD 3 /* this got triggered by readahead */
+#define EXTENT_BUFFER_STALE 4
+#define EXTENT_BUFFER_WRITEBACK 5
+#define EXTENT_BUFFER_READ_ERR 6 /* read IO error */
+#define EXTENT_BUFFER_WRITE_ERR 7 /* write IO error */
/* these are flags for extent_clear_unlock_delalloc */
#define PAGE_UNLOCK (1 << 0)
@@ -175,17 +177,17 @@ struct extent_state {
#define INLINE_EXTENT_BUFFER_PAGES 16
#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES *
PAGE_CACHE_SIZE)
+
+/* Forward declaration */
+struct extent_buffer_head;
+
struct extent_buffer {
u64 start;
unsigned long len;
- unsigned long bflags;
- struct btrfs_fs_info *fs_info;
- spinlock_t refs_lock;
- atomic_t refs;
- atomic_t io_pages;
+ unsigned long ebflags;
+ struct extent_buffer_head *ebh;
+ struct extent_buffer *eb_next;
int read_mirror;
- struct rcu_head rcu_head;
- pid_t lock_owner;
/* count of read lock holders on the extent buffer */
atomic_t write_locks;
@@ -198,6 +200,8 @@ struct extent_buffer {
/* >= 0 if eb belongs to a log tree, -1 otherwise */
short log_index;
+ pid_t lock_owner;
+
/* protects write locks */
rwlock_t lock;
@@ -210,7 +214,20 @@ struct extent_buffer {
* to unlock
*/
wait_queue_head_t read_lock_wq;
+ wait_queue_head_t lock_wq;
+};
+
+struct extent_buffer_head {
+ unsigned long bflags;
+ struct btrfs_fs_info *fs_info;
+ spinlock_t refs_lock;
+ atomic_t refs;
+ atomic_t io_bvecs;
+ struct rcu_head rcu_head;
+
struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
+
+ struct extent_buffer eb;
#ifdef CONFIG_BTRFS_DEBUG
struct list_head leak_list;
#endif
@@ -238,6 +255,14 @@ static inline int extent_compress_type(unsigned long
bio_flags)
return bio_flags >> EXTENT_BIO_FLAG_SHIFT;
}
+/*
+ * return the extent_buffer_head that contains the extent buffer provided.
+ */
+static inline struct extent_buffer_head *eb_head(struct extent_buffer *eb)
+{
+ return eb->ebh;
+
+}
struct extent_map_tree;
typedef struct extent_map *(get_extent_t)(struct inode *inode,
@@ -435,7 +460,7 @@ static inline unsigned long num_extent_pages(u64 start, u64
len)
static inline void extent_buffer_get(struct extent_buffer *eb)
{
- atomic_inc(&eb->refs);
+ atomic_inc(&eb_head(eb)->refs);
}
int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7cf8509..ddf4dc4 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -45,7 +45,7 @@ static void btrfs_read_root_item(struct extent_buffer *eb,
int slot,
if (!need_reset && btrfs_root_generation(item)
!= btrfs_root_generation_v2(item)) {
if (btrfs_root_generation_v2(item) != 0) {
- btrfs_warn(eb->fs_info,
+ btrfs_warn(eb_head(eb)->fs_info,
"mismatching "
"generation and generation_v2 "
"found in root item. This root "
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 366b335..fba90b9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6523,7 +6523,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
* to silence the warning eg. on PowerPC 64.
*/
if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE)
- SetPageUptodate(sb->pages[0]);
+ SetPageUptodate(eb_head(sb)->pages[0]);
write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
array_size = btrfs_super_sys_array_size(super_copy);
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index d866f21..3f9227e 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -700,7 +700,7 @@ TRACE_EVENT(btrfs_cow_block,
TP_fast_assign(
__entry->root_objectid = root->root_key.objectid;
__entry->buf_start = buf->start;
- __entry->refs = atomic_read(&buf->refs);
+ __entry->refs = atomic_read(&eb_head(buf)->refs);
__entry->cow_start = cow->start;
__entry->buf_level = btrfs_header_level(buf);
__entry->cow_level = btrfs_header_level(cow);
--
2.1.0
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
