aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs/extent_io.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/extent_io.c')
-rw-r--r--fs/btrfs/extent_io.c606
1 files changed, 326 insertions, 280 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 76a0c8597d98..44fe66b53c8b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -163,13 +163,13 @@ int __init extent_io_init(void)
{
extent_state_cache = kmem_cache_create("btrfs_extent_state",
sizeof(struct extent_state), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!extent_state_cache)
return -ENOMEM;
extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
sizeof(struct extent_buffer), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!extent_buffer_cache)
goto free_state_cache;
@@ -726,14 +726,6 @@ next:
start = last_end + 1;
if (start <= end && state && !need_resched())
goto hit_next;
- goto search_again;
-
-out:
- spin_unlock(&tree->lock);
- if (prealloc)
- free_extent_state(prealloc);
-
- return 0;
search_again:
if (start > end)
@@ -742,6 +734,14 @@ search_again:
if (gfpflags_allow_blocking(mask))
cond_resched();
goto again;
+
+out:
+ spin_unlock(&tree->lock);
+ if (prealloc)
+ free_extent_state(prealloc);
+
+ return 0;
+
}
static void wait_on_state(struct extent_io_tree *tree,
@@ -873,8 +873,14 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
bits |= EXTENT_FIRST_DELALLOC;
again:
if (!prealloc && gfpflags_allow_blocking(mask)) {
+ /*
+ * Don't care for allocation failure here because we might end
+ * up not needing the pre-allocated extent state at all, which
+ * is the case if we only have in the tree extent states that
+ * cover our input range and don't cover too any other range.
+ * If we end up needing a new extent state we allocate it later.
+ */
prealloc = alloc_extent_state(mask);
- BUG_ON(!prealloc);
}
spin_lock(&tree->lock);
@@ -1037,7 +1043,13 @@ hit_next:
goto out;
}
- goto search_again;
+search_again:
+ if (start > end)
+ goto out;
+ spin_unlock(&tree->lock);
+ if (gfpflags_allow_blocking(mask))
+ cond_resched();
+ goto again;
out:
spin_unlock(&tree->lock);
@@ -1046,13 +1058,6 @@ out:
return err;
-search_again:
- if (start > end)
- goto out;
- spin_unlock(&tree->lock);
- if (gfpflags_allow_blocking(mask))
- cond_resched();
- goto again;
}
int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
@@ -1073,17 +1078,18 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
* @bits: the bits to set in this range
* @clear_bits: the bits to clear in this range
* @cached_state: state that we're going to cache
- * @mask: the allocation mask
*
* This will go through and set bits for the given range. If any states exist
* already in this range they are set with the given bit and cleared of the
* clear_bits. This is only meant to be used by things that are mergeable, ie
* converting from say DELALLOC to DIRTY. This is not meant to be used with
* boundary bits like LOCK.
+ *
+ * All allocations are done with GFP_NOFS.
*/
int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
unsigned bits, unsigned clear_bits,
- struct extent_state **cached_state, gfp_t mask)
+ struct extent_state **cached_state)
{
struct extent_state *state;
struct extent_state *prealloc = NULL;
@@ -1098,7 +1104,7 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
btrfs_debug_check_extent_io_range(tree, start, end);
again:
- if (!prealloc && gfpflags_allow_blocking(mask)) {
+ if (!prealloc) {
/*
* Best effort, don't worry if extent state allocation fails
* here for the first iteration. We might have a cached state
@@ -1106,7 +1112,7 @@ again:
* extent state allocations are needed. We'll only know this
* after locking the tree.
*/
- prealloc = alloc_extent_state(mask);
+ prealloc = alloc_extent_state(GFP_NOFS);
if (!prealloc && !first_iteration)
return -ENOMEM;
}
@@ -1263,7 +1269,13 @@ hit_next:
goto out;
}
- goto search_again;
+search_again:
+ if (start > end)
+ goto out;
+ spin_unlock(&tree->lock);
+ cond_resched();
+ first_iteration = false;
+ goto again;
out:
spin_unlock(&tree->lock);
@@ -1271,21 +1283,11 @@ out:
free_extent_state(prealloc);
return err;
-
-search_again:
- if (start > end)
- goto out;
- spin_unlock(&tree->lock);
- if (gfpflags_allow_blocking(mask))
- cond_resched();
- first_iteration = false;
- goto again;
}
/* wrappers around set/clear extent bit */
int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, gfp_t mask,
- struct extent_changeset *changeset)
+ unsigned bits, struct extent_changeset *changeset)
{
/*
* We don't support EXTENT_LOCKED yet, as current changeset will
@@ -1295,7 +1297,7 @@ int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
*/
BUG_ON(bits & EXTENT_LOCKED);
- return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, mask,
+ return __set_extent_bit(tree, start, end, bits, 0, NULL, NULL, GFP_NOFS,
changeset);
}
@@ -1308,8 +1310,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
}
int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
- unsigned bits, gfp_t mask,
- struct extent_changeset *changeset)
+ unsigned bits, struct extent_changeset *changeset)
{
/*
* Don't support EXTENT_LOCKED case, same reason as
@@ -1317,7 +1318,7 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
*/
BUG_ON(bits & EXTENT_LOCKED);
- return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, mask,
+ return __clear_extent_bit(tree, start, end, bits, 0, 0, NULL, GFP_NOFS,
changeset);
}
@@ -1363,23 +1364,23 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
{
- unsigned long index = start >> PAGE_CACHE_SHIFT;
- unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+ unsigned long index = start >> PAGE_SHIFT;
+ unsigned long end_index = end >> PAGE_SHIFT;
struct page *page;
while (index <= end_index) {
page = find_get_page(inode->i_mapping, index);
BUG_ON(!page); /* Pages should be in the extent_io_tree */
clear_page_dirty_for_io(page);
- page_cache_release(page);
+ put_page(page);
index++;
}
}
void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
{
- unsigned long index = start >> PAGE_CACHE_SHIFT;
- unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+ unsigned long index = start >> PAGE_SHIFT;
+ unsigned long end_index = end >> PAGE_SHIFT;
struct page *page;
while (index <= end_index) {
@@ -1387,7 +1388,7 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
BUG_ON(!page); /* Pages should be in the extent_io_tree */
__set_page_dirty_nobuffers(page);
account_page_redirty(page);
- page_cache_release(page);
+ put_page(page);
index++;
}
}
@@ -1397,15 +1398,15 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
*/
static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
{
- unsigned long index = start >> PAGE_CACHE_SHIFT;
- unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+ unsigned long index = start >> PAGE_SHIFT;
+ unsigned long end_index = end >> PAGE_SHIFT;
struct page *page;
while (index <= end_index) {
page = find_get_page(tree->mapping, index);
BUG_ON(!page); /* Pages should be in the extent_io_tree */
set_page_writeback(page);
- page_cache_release(page);
+ put_page(page);
index++;
}
}
@@ -1556,8 +1557,8 @@ static noinline void __unlock_for_delalloc(struct inode *inode,
{
int ret;
struct page *pages[16];
- unsigned long index = start >> PAGE_CACHE_SHIFT;
- unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+ unsigned long index = start >> PAGE_SHIFT;
+ unsigned long end_index = end >> PAGE_SHIFT;
unsigned long nr_pages = end_index - index + 1;
int i;
@@ -1571,7 +1572,7 @@ static noinline void __unlock_for_delalloc(struct inode *inode,
for (i = 0; i < ret; i++) {
if (pages[i] != locked_page)
unlock_page(pages[i]);
- page_cache_release(pages[i]);
+ put_page(pages[i]);
}
nr_pages -= ret;
index += ret;
@@ -1584,9 +1585,9 @@ static noinline int lock_delalloc_pages(struct inode *inode,
u64 delalloc_start,
u64 delalloc_end)
{
- unsigned long index = delalloc_start >> PAGE_CACHE_SHIFT;
+ unsigned long index = delalloc_start >> PAGE_SHIFT;
unsigned long start_index = index;
- unsigned long end_index = delalloc_end >> PAGE_CACHE_SHIFT;
+ unsigned long end_index = delalloc_end >> PAGE_SHIFT;
unsigned long pages_locked = 0;
struct page *pages[16];
unsigned long nrpages;
@@ -1619,11 +1620,11 @@ static noinline int lock_delalloc_pages(struct inode *inode,
pages[i]->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(pages[i]);
- page_cache_release(pages[i]);
+ put_page(pages[i]);
goto done;
}
}
- page_cache_release(pages[i]);
+ put_page(pages[i]);
pages_locked++;
}
nrpages -= ret;
@@ -1636,7 +1637,7 @@ done:
__unlock_for_delalloc(inode, locked_page,
delalloc_start,
((u64)(start_index + pages_locked - 1)) <<
- PAGE_CACHE_SHIFT);
+ PAGE_SHIFT);
}
return ret;
}
@@ -1696,7 +1697,7 @@ again:
free_extent_state(cached_state);
cached_state = NULL;
if (!loops) {
- max_bytes = PAGE_CACHE_SIZE;
+ max_bytes = PAGE_SIZE;
loops = 1;
goto again;
} else {
@@ -1735,8 +1736,8 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
int ret;
struct page *pages[16];
- unsigned long index = start >> PAGE_CACHE_SHIFT;
- unsigned long end_index = end >> PAGE_CACHE_SHIFT;
+ unsigned long index = start >> PAGE_SHIFT;
+ unsigned long end_index = end >> PAGE_SHIFT;
unsigned long nr_pages = end_index - index + 1;
int i;
@@ -1757,7 +1758,7 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
SetPagePrivate2(pages[i]);
if (pages[i] == locked_page) {
- page_cache_release(pages[i]);
+ put_page(pages[i]);
continue;
}
if (page_ops & PAGE_CLEAR_DIRTY)
@@ -1770,7 +1771,7 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
end_page_writeback(pages[i]);
if (page_ops & PAGE_UNLOCK)
unlock_page(pages[i]);
- page_cache_release(pages[i]);
+ put_page(pages[i]);
}
nr_pages -= ret;
index += ret;
@@ -1961,7 +1962,7 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
{
u64 start = page_offset(page);
- u64 end = start + PAGE_CACHE_SIZE - 1;
+ u64 end = start + PAGE_SIZE - 1;
if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, NULL))
SetPageUptodate(page);
}
@@ -1975,13 +1976,13 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
set_state_failrec(failure_tree, rec->start, NULL);
ret = clear_extent_bits(failure_tree, rec->start,
rec->start + rec->len - 1,
- EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
+ EXTENT_LOCKED | EXTENT_DIRTY);
if (ret)
err = ret;
ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start,
rec->start + rec->len - 1,
- EXTENT_DAMAGED, GFP_NOFS);
+ EXTENT_DAMAGED);
if (ret && !err)
err = ret;
@@ -2024,9 +2025,16 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
bio->bi_iter.bi_size = 0;
map_length = length;
+ /*
+ * Avoid races with device replace and make sure our bbio has devices
+ * associated to its stripes that don't go away while we are doing the
+ * read repair operation.
+ */
+ btrfs_bio_counter_inc_blocked(fs_info);
ret = btrfs_map_block(fs_info, WRITE, logical,
&map_length, &bbio, mirror_num);
if (ret) {
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
return -EIO;
}
@@ -2036,14 +2044,17 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
dev = bbio->stripes[mirror_num-1].dev;
btrfs_put_bbio(bbio);
if (!dev || !dev->bdev || !dev->writeable) {
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
return -EIO;
}
bio->bi_bdev = dev->bdev;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_SYNC);
bio_add_page(bio, page, length, pg_offset);
- if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
+ if (btrfsic_submit_bio_wait(bio)) {
/* try to remap that extent elsewhere? */
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
return -EIO;
@@ -2053,6 +2064,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
"read error corrected: ino %llu off %llu (dev %s sector %llu)",
btrfs_ino(inode), start,
rcu_str_deref(dev->name), sector);
+ btrfs_bio_counter_dec(fs_info);
bio_put(bio);
return 0;
}
@@ -2071,11 +2083,11 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
struct page *p = eb->pages[i];
ret = repair_io_failure(root->fs_info->btree_inode, start,
- PAGE_CACHE_SIZE, start, p,
+ PAGE_SIZE, start, p,
start - page_offset(p), mirror_num);
if (ret)
break;
- start += PAGE_CACHE_SIZE;
+ start += PAGE_SIZE;
}
return ret;
@@ -2232,13 +2244,12 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
/* set the bits in the private failure tree */
ret = set_extent_bits(failure_tree, start, end,
- EXTENT_LOCKED | EXTENT_DIRTY, GFP_NOFS);
+ EXTENT_LOCKED | EXTENT_DIRTY);
if (ret >= 0)
ret = set_state_failrec(failure_tree, start, failrec);
/* set the bits in the inode's tree */
if (ret >= 0)
- ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED,
- GFP_NOFS);
+ ret = set_extent_bits(tree, start, end, EXTENT_DAMAGED);
if (ret < 0) {
kfree(failrec);
return ret;
@@ -2376,7 +2387,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
int read_mode;
int ret;
- BUG_ON(failed_bio->bi_rw & REQ_WRITE);
+ BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
ret = btrfs_get_io_failure_record(inode, start, end, &failrec);
if (ret)
@@ -2402,12 +2413,12 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
free_io_failure(inode, failrec);
return -EIO;
}
+ bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
pr_debug("Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d\n",
read_mode, failrec->this_mirror, failrec->in_validation);
- ret = tree->ops->submit_bio_hook(inode, read_mode, bio,
- failrec->this_mirror,
+ ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror,
failrec->bio_flags, 0);
if (ret) {
free_io_failure(inode, failrec);
@@ -2466,8 +2477,8 @@ static void end_bio_extent_writepage(struct bio *bio)
* 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) {
- if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_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);
@@ -2541,8 +2552,8 @@ static void end_bio_extent_readpage(struct bio *bio)
* 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) {
- if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_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);
@@ -2598,13 +2609,13 @@ static void end_bio_extent_readpage(struct bio *bio)
readpage_ok:
if (likely(uptodate)) {
loff_t i_size = i_size_read(inode);
- pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+ pgoff_t end_index = i_size >> PAGE_SHIFT;
unsigned off;
/* Zero out the end if this page straddles i_size */
- off = i_size & (PAGE_CACHE_SIZE-1);
+ off = i_size & (PAGE_SIZE-1);
if (page->index == end_index && off)
- zero_user_segment(page, off, PAGE_CACHE_SIZE);
+ zero_user_segment(page, off, PAGE_SIZE);
SetPageUptodate(page);
} else {
ClearPageUptodate(page);
@@ -2686,12 +2697,6 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
btrfs_bio->csum = NULL;
btrfs_bio->csum_allocated = NULL;
btrfs_bio->end_io = NULL;
-
-#ifdef CONFIG_BLK_CGROUP
- /* FIXME, put this into bio_clone_bioset */
- if (bio->bi_css)
- bio_associate_blkcg(new, bio->bi_css);
-#endif
}
return new;
}
@@ -2713,8 +2718,8 @@ struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
}
-static int __must_check submit_one_bio(int rw, struct bio *bio,
- int mirror_num, unsigned long bio_flags)
+static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
+ unsigned long bio_flags)
{
int ret = 0;
struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
@@ -2725,33 +2730,31 @@ static int __must_check submit_one_bio(int rw, struct bio *bio,
start = page_offset(page) + bvec->bv_offset;
bio->bi_private = NULL;
-
bio_get(bio);
if (tree->ops && tree->ops->submit_bio_hook)
- ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
+ ret = tree->ops->submit_bio_hook(page->mapping->host, bio,
mirror_num, bio_flags, start);
else
- btrfsic_submit_bio(rw, bio);
+ btrfsic_submit_bio(bio);
bio_put(bio);
return ret;
}
-static int merge_bio(int rw, struct extent_io_tree *tree, struct page *page,
+static int merge_bio(struct extent_io_tree *tree, struct page *page,
unsigned long offset, size_t size, struct bio *bio,
unsigned long bio_flags)
{
int ret = 0;
if (tree->ops && tree->ops->merge_bio_hook)
- ret = tree->ops->merge_bio_hook(rw, page, offset, size, bio,
+ ret = tree->ops->merge_bio_hook(page, offset, size, bio,
bio_flags);
- BUG_ON(ret < 0);
return ret;
}
-static int submit_extent_page(int rw, struct extent_io_tree *tree,
+static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree,
struct writeback_control *wbc,
struct page *page, sector_t sector,
size_t size, unsigned long offset,
@@ -2768,7 +2771,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
struct bio *bio;
int contig = 0;
int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED;
- size_t page_size = min_t(size_t, size, PAGE_CACHE_SIZE);
+ size_t page_size = min_t(size_t, size, PAGE_SIZE);
if (bio_ret && *bio_ret) {
bio = *bio_ret;
@@ -2779,10 +2782,9 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
if (prev_bio_flags != bio_flags || !contig ||
force_bio_submit ||
- merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
+ merge_bio(tree, page, offset, page_size, bio, bio_flags) ||
bio_add_page(bio, page, page_size, offset) < page_size) {
- ret = submit_one_bio(rw, bio, mirror_num,
- prev_bio_flags);
+ ret = submit_one_bio(bio, mirror_num, prev_bio_flags);
if (ret < 0) {
*bio_ret = NULL;
return ret;
@@ -2803,6 +2805,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
bio_add_page(bio, page, page_size, offset);
bio->bi_end_io = end_io_func;
bio->bi_private = tree;
+ bio_set_op_attrs(bio, op, op_flags);
if (wbc) {
wbc_init_bio(wbc, bio);
wbc_account_io(wbc, page, page_size);
@@ -2811,7 +2814,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
if (bio_ret)
*bio_ret = bio;
else
- ret = submit_one_bio(rw, bio, mirror_num, bio_flags);
+ ret = submit_one_bio(bio, mirror_num, bio_flags);
return ret;
}
@@ -2821,7 +2824,7 @@ static void attach_extent_buffer_page(struct extent_buffer *eb,
{
if (!PagePrivate(page)) {
SetPagePrivate(page);
- page_cache_get(page);
+ get_page(page);
set_page_private(page, (unsigned long)eb);
} else {
WARN_ON(page->private != (unsigned long)eb);
@@ -2832,7 +2835,7 @@ void set_page_extent_mapped(struct page *page)
{
if (!PagePrivate(page)) {
SetPagePrivate(page);
- page_cache_get(page);
+ get_page(page);
set_page_private(page, EXTENT_PAGE_PRIVATE);
}
}
@@ -2869,18 +2872,19 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
* into the tree that are removed when the IO is done (by the end_io
* handlers)
* XXX JDM: This needs looking at to ensure proper page locking
+ * return 0 on success, otherwise return error
*/
static int __do_readpage(struct extent_io_tree *tree,
struct page *page,
get_extent_t *get_extent,
struct extent_map **em_cached,
struct bio **bio, int mirror_num,
- unsigned long *bio_flags, int rw,
+ unsigned long *bio_flags, int read_flags,
u64 *prev_em_start)
{
struct inode *inode = page->mapping->host;
u64 start = page_offset(page);
- u64 page_end = start + PAGE_CACHE_SIZE - 1;
+ u64 page_end = start + PAGE_SIZE - 1;
u64 end;
u64 cur = start;
u64 extent_offset;
@@ -2890,7 +2894,7 @@ static int __do_readpage(struct extent_io_tree *tree,
sector_t sector;
struct extent_map *em;
struct block_device *bdev;
- int ret;
+ int ret = 0;
int nr = 0;
size_t pg_offset = 0;
size_t iosize;
@@ -2909,12 +2913,12 @@ static int __do_readpage(struct extent_io_tree *tree,
}
}
- if (page->index == last_byte >> PAGE_CACHE_SHIFT) {
+ if (page->index == last_byte >> PAGE_SHIFT) {
char *userpage;
- size_t zero_offset = last_byte & (PAGE_CACHE_SIZE - 1);
+ size_t zero_offset = last_byte & (PAGE_SIZE - 1);
if (zero_offset) {
- iosize = PAGE_CACHE_SIZE - zero_offset;
+ iosize = PAGE_SIZE - zero_offset;
userpage = kmap_atomic(page);
memset(userpage + zero_offset, 0, iosize);
flush_dcache_page(page);
@@ -2922,14 +2926,14 @@ static int __do_readpage(struct extent_io_tree *tree,
}
}
while (cur <= end) {
- unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
+ unsigned long pnr = (last_byte >> PAGE_SHIFT) + 1;
bool force_bio_submit = false;
if (cur >= last_byte) {
char *userpage;
struct extent_state *cached = NULL;
- iosize = PAGE_CACHE_SIZE - pg_offset;
+ iosize = PAGE_SIZE - pg_offset;
userpage = kmap_atomic(page);
memset(userpage + pg_offset, 0, iosize);
flush_dcache_page(page);
@@ -3058,8 +3062,8 @@ static int __do_readpage(struct extent_io_tree *tree,
}
pnr -= page->index;
- ret = submit_extent_page(rw, tree, NULL, page,
- sector, disk_io_size, pg_offset,
+ ret = submit_extent_page(REQ_OP_READ, read_flags, tree, NULL,
+ page, sector, disk_io_size, pg_offset,
bdev, bio, pnr,
end_bio_extent_readpage, mirror_num,
*bio_flags,
@@ -3071,6 +3075,7 @@ static int __do_readpage(struct extent_io_tree *tree,
} else {
SetPageError(page);
unlock_extent(tree, cur, cur + iosize - 1);
+ goto out;
}
cur = cur + iosize;
pg_offset += iosize;
@@ -3081,7 +3086,7 @@ out:
SetPageUptodate(page);
unlock_page(page);
}
- return 0;
+ return ret;
}
static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
@@ -3090,7 +3095,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
get_extent_t *get_extent,
struct extent_map **em_cached,
struct bio **bio, int mirror_num,
- unsigned long *bio_flags, int rw,
+ unsigned long *bio_flags,
u64 *prev_em_start)
{
struct inode *inode;
@@ -3111,8 +3116,8 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
for (index = 0; index < nr_pages; index++) {
__do_readpage(tree, pages[index], get_extent, em_cached, bio,
- mirror_num, bio_flags, rw, prev_em_start);
- page_cache_release(pages[index]);
+ mirror_num, bio_flags, 0, prev_em_start);
+ put_page(pages[index]);
}
}
@@ -3121,7 +3126,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
int nr_pages, get_extent_t *get_extent,
struct extent_map **em_cached,
struct bio **bio, int mirror_num,
- unsigned long *bio_flags, int rw,
+ unsigned long *bio_flags,
u64 *prev_em_start)
{
u64 start = 0;
@@ -3134,18 +3139,18 @@ static void __extent_readpages(struct extent_io_tree *tree,
page_start = page_offset(pages[index]);
if (!end) {
start = page_start;
- end = start + PAGE_CACHE_SIZE - 1;
+ end = start + PAGE_SIZE - 1;
first_index = index;
} else if (end + 1 == page_start) {
- end += PAGE_CACHE_SIZE;
+ end += PAGE_SIZE;
} else {
__do_contiguous_readpages(tree, &pages[first_index],
index - first_index, start,
end, get_extent, em_cached,
bio, mirror_num, bio_flags,
- rw, prev_em_start);
+ prev_em_start);
start = page_start;
- end = start + PAGE_CACHE_SIZE - 1;
+ end = start + PAGE_SIZE - 1;
first_index = index;
}
}
@@ -3154,7 +3159,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
__do_contiguous_readpages(tree, &pages[first_index],
index - first_index, start,
end, get_extent, em_cached, bio,
- mirror_num, bio_flags, rw,
+ mirror_num, bio_flags,
prev_em_start);
}
@@ -3162,18 +3167,18 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
struct page *page,
get_extent_t *get_extent,
struct bio **bio, int mirror_num,
- unsigned long *bio_flags, int rw)
+ unsigned long *bio_flags, int read_flags)
{
struct inode *inode = page->mapping->host;
struct btrfs_ordered_extent *ordered;
u64 start = page_offset(page);
- u64 end = start + PAGE_CACHE_SIZE - 1;
+ u64 end = start + PAGE_SIZE - 1;
int ret;
while (1) {
lock_extent(tree, start, end);
ordered = btrfs_lookup_ordered_range(inode, start,
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
if (!ordered)
break;
unlock_extent(tree, start, end);
@@ -3182,7 +3187,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
}
ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
- bio_flags, rw, NULL);
+ bio_flags, read_flags, NULL);
return ret;
}
@@ -3194,20 +3199,16 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
int ret;
ret = __extent_read_full_page(tree, page, get_extent, &bio, mirror_num,
- &bio_flags, READ);
+ &bio_flags, 0);
if (bio)
- ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
+ ret = submit_one_bio(bio, mirror_num, bio_flags);
return ret;
}
-static noinline void update_nr_written(struct page *page,
- struct writeback_control *wbc,
- unsigned long nr_written)
+static void update_nr_written(struct page *page, struct writeback_control *wbc,
+ unsigned long nr_written)
{
wbc->nr_to_write -= nr_written;
- if (wbc->range_cyclic || (wbc->nr_to_write > 0 &&
- wbc->range_start == 0 && wbc->range_end == LLONG_MAX))
- page->mapping->writeback_index = page->index + nr_written;
}
/*
@@ -3227,7 +3228,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
unsigned long *nr_written)
{
struct extent_io_tree *tree = epd->tree;
- u64 page_end = delalloc_start + PAGE_CACHE_SIZE - 1;
+ u64 page_end = delalloc_start + PAGE_SIZE - 1;
u64 nr_delalloc;
u64 delalloc_to_write = 0;
u64 delalloc_end = 0;
@@ -3264,13 +3265,11 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
goto done;
}
/*
- * delalloc_end is already one less than the total
- * length, so we don't subtract one from
- * PAGE_CACHE_SIZE
+ * delalloc_end is already one less than the total length, so
+ * we don't subtract one from PAGE_SIZE
*/
delalloc_to_write += (delalloc_end - delalloc_start +
- PAGE_CACHE_SIZE) >>
- PAGE_CACHE_SHIFT;
+ PAGE_SIZE) >> PAGE_SHIFT;
delalloc_start = delalloc_end + 1;
}
if (wbc->nr_to_write < delalloc_to_write) {
@@ -3319,7 +3318,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
{
struct extent_io_tree *tree = epd->tree;
u64 start = page_offset(page);
- u64 page_end = start + PAGE_CACHE_SIZE - 1;
+ u64 page_end = start + PAGE_SIZE - 1;
u64 end;
u64 cur = start;
u64 extent_offset;
@@ -3370,6 +3369,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
while (cur <= end) {
u64 em_end;
+ unsigned long max_nr;
+
if (cur >= i_size) {
if (tree->ops && tree->ops->writepage_end_io_hook)
tree->ops->writepage_end_io_hook(page, cur,
@@ -3425,32 +3426,23 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
continue;
}
- if (tree->ops && tree->ops->writepage_io_hook) {
- ret = tree->ops->writepage_io_hook(page, cur,
- cur + iosize - 1);
- } else {
- ret = 0;
+ max_nr = (i_size >> PAGE_SHIFT) + 1;
+
+ set_range_writeback(tree, cur, cur + iosize - 1);
+ if (!PageWriteback(page)) {
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "page %lu not writeback, cur %llu end %llu",
+ page->index, cur, end);
}
- if (ret) {
- SetPageError(page);
- } else {
- unsigned long max_nr = (i_size >> PAGE_CACHE_SHIFT) + 1;
- set_range_writeback(tree, cur, cur + iosize - 1);
- if (!PageWriteback(page)) {
- btrfs_err(BTRFS_I(inode)->root->fs_info,
- "page %lu not writeback, cur %llu end %llu",
- page->index, cur, end);
- }
+ ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
+ page, sector, iosize, pg_offset,
+ bdev, &epd->bio, max_nr,
+ end_bio_extent_writepage,
+ 0, 0, 0, false);
+ if (ret)
+ SetPageError(page);
- ret = submit_extent_page(write_flags, tree, wbc, page,
- sector, iosize, pg_offset,
- bdev, &epd->bio, max_nr,
- end_bio_extent_writepage,
- 0, 0, 0, false);
- if (ret)
- SetPageError(page);
- }
cur = cur + iosize;
pg_offset += iosize;
nr++;
@@ -3477,19 +3469,17 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
struct inode *inode = page->mapping->host;
struct extent_page_data *epd = data;
u64 start = page_offset(page);
- u64 page_end = start + PAGE_CACHE_SIZE - 1;
+ u64 page_end = start + PAGE_SIZE - 1;
int ret;
int nr = 0;
size_t pg_offset = 0;
loff_t i_size = i_size_read(inode);
- unsigned long end_index = i_size >> PAGE_CACHE_SHIFT;
- int write_flags;
+ unsigned long end_index = i_size >> PAGE_SHIFT;
+ int write_flags = 0;
unsigned long nr_written = 0;
if (wbc->sync_mode == WB_SYNC_ALL)
write_flags = WRITE_SYNC;
- else
- write_flags = WRITE;
trace___extent_writepage(page, inode, wbc);
@@ -3497,10 +3487,10 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
ClearPageError(page);
- pg_offset = i_size & (PAGE_CACHE_SIZE - 1);
+ pg_offset = i_size & (PAGE_SIZE - 1);
if (page->index > end_index ||
(page->index == end_index && !pg_offset)) {
- page->mapping->a_ops->invalidatepage(page, 0, PAGE_CACHE_SIZE);
+ page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE);
unlock_page(page);
return 0;
}
@@ -3510,7 +3500,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
userpage = kmap_atomic(page);
memset(userpage + pg_offset, 0,
- PAGE_CACHE_SIZE - pg_offset);
+ PAGE_SIZE - pg_offset);
kunmap_atomic(userpage);
flush_dcache_page(page);
}
@@ -3733,7 +3723,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
u64 offset = eb->start;
unsigned long i, num_pages;
unsigned long bio_flags = 0;
- int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
+ int write_flags = (epd->sync_io ? WRITE_SYNC : 0) | REQ_META;
int ret = 0;
clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
@@ -3747,9 +3737,10 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
clear_page_dirty_for_io(p);
set_page_writeback(p);
- ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
- PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
- -1, end_bio_extent_buffer_writepage,
+ ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
+ p, offset >> 9, PAGE_SIZE, 0, bdev,
+ &epd->bio, -1,
+ end_bio_extent_buffer_writepage,
0, epd->bio_flags, bio_flags, false);
epd->bio_flags = bio_flags;
if (ret) {
@@ -3760,7 +3751,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
ret = -EIO;
break;
}
- offset += PAGE_CACHE_SIZE;
+ offset += PAGE_SIZE;
update_nr_written(p, wbc, 1);
unlock_page(p);
}
@@ -3804,8 +3795,8 @@ int btree_write_cache_pages(struct address_space *mapping,
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
} else {
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ index = wbc->range_start >> PAGE_SHIFT;
+ end = wbc->range_end >> PAGE_SHIFT;
scanned = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL)
@@ -3922,12 +3913,13 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
struct inode *inode = mapping->host;
int ret = 0;
int done = 0;
- int err = 0;
int nr_to_write_done = 0;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
pgoff_t end; /* Inclusive */
+ pgoff_t done_index;
+ int range_whole = 0;
int scanned = 0;
int tag;
@@ -3948,8 +3940,10 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
index = mapping->writeback_index; /* Start from prev offset */
end = -1;
} else {
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
+ index = wbc->range_start >> PAGE_SHIFT;
+ end = wbc->range_end >> PAGE_SHIFT;
+ if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+ range_whole = 1;
scanned = 1;
}
if (wbc->sync_mode == WB_SYNC_ALL)
@@ -3959,6 +3953,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
retry:
if (wbc->sync_mode == WB_SYNC_ALL)
tag_pages_for_writeback(mapping, index, end);
+ done_index = index;
while (!done && !nr_to_write_done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
@@ -3968,6 +3963,7 @@ retry:
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
+ done_index = page->index;
/*
* At this point we hold neither mapping->tree_lock nor
* lock on the page itself: the page may be truncated or
@@ -4009,8 +4005,20 @@ retry:
unlock_page(page);
ret = 0;
}
- if (!err && ret < 0)
- err = ret;
+ if (ret < 0) {
+ /*
+ * done_index is set past this page,
+ * so media errors will not choke
+ * background writeout for the entire
+ * file. This has consequences for
+ * range_cyclic semantics (ie. it may
+ * not be suitable for data integrity
+ * writeout).
+ */
+ done_index = page->index + 1;
+ done = 1;
+ break;
+ }
/*
* the filesystem may choose to bump up nr_to_write.
@@ -4022,7 +4030,7 @@ retry:
pagevec_release(&pvec);
cond_resched();
}
- if (!scanned && !done && !err) {
+ if (!scanned && !done) {
/*
* We hit the last page and there is more work to be done: wrap
* back to the start of the file
@@ -4031,20 +4039,23 @@ retry:
index = 0;
goto retry;
}
+
+ if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
+ mapping->writeback_index = done_index;
+
btrfs_add_delayed_iput(inode);
- return err;
+ return ret;
}
static void flush_epd_write_bio(struct extent_page_data *epd)
{
if (epd->bio) {
- int rw = WRITE;
int ret;
- if (epd->sync_io)
- rw = WRITE_SYNC;
+ bio_set_op_attrs(epd->bio, REQ_OP_WRITE,
+ epd->sync_io ? WRITE_SYNC : 0);
- ret = submit_one_bio(rw, epd->bio, 0, epd->bio_flags);
+ ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
BUG_ON(ret < 0); /* -ENOMEM */
epd->bio = NULL;
}
@@ -4083,8 +4094,8 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
int ret = 0;
struct address_space *mapping = inode->i_mapping;
struct page *page;
- unsigned long nr_pages = (end - start + PAGE_CACHE_SIZE) >>
- PAGE_CACHE_SHIFT;
+ unsigned long nr_pages = (end - start + PAGE_SIZE) >>
+ PAGE_SHIFT;
struct extent_page_data epd = {
.bio = NULL,
@@ -4102,18 +4113,18 @@ int extent_write_locked_range(struct extent_io_tree *tree, struct inode *inode,
};
while (start <= end) {
- page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+ page = find_get_page(mapping, start >> PAGE_SHIFT);
if (clear_page_dirty_for_io(page))
ret = __extent_writepage(page, &wbc_writepages, &epd);
else {
if (tree->ops && tree->ops->writepage_end_io_hook)
tree->ops->writepage_end_io_hook(page, start,
- start + PAGE_CACHE_SIZE - 1,
+ start + PAGE_SIZE - 1,
NULL, 1);
unlock_page(page);
}
- page_cache_release(page);
- start += PAGE_CACHE_SIZE;
+ put_page(page);
+ start += PAGE_SIZE;
}
flush_epd_write_bio(&epd);
@@ -4162,8 +4173,9 @@ int extent_readpages(struct extent_io_tree *tree,
prefetchw(&page->flags);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping,
- page->index, GFP_NOFS)) {
- page_cache_release(page);
+ page->index,
+ readahead_gfp_mask(mapping))) {
+ put_page(page);
continue;
}
@@ -4171,19 +4183,19 @@ int extent_readpages(struct extent_io_tree *tree,
if (nr < ARRAY_SIZE(pagepool))
continue;
__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
- &bio, 0, &bio_flags, READ, &prev_em_start);
+ &bio, 0, &bio_flags, &prev_em_start);
nr = 0;
}
if (nr)
__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
- &bio, 0, &bio_flags, READ, &prev_em_start);
+ &bio, 0, &bio_flags, &prev_em_start);
if (em_cached)
free_extent_map(em_cached);
BUG_ON(!list_empty(pages));
if (bio)
- return submit_one_bio(READ, bio, 0, bio_flags);
+ return submit_one_bio(bio, 0, bio_flags);
return 0;
}
@@ -4197,7 +4209,7 @@ int extent_invalidatepage(struct extent_io_tree *tree,
{
struct extent_state *cached_state = NULL;
u64 start = page_offset(page);
- u64 end = start + PAGE_CACHE_SIZE - 1;
+ u64 end = start + PAGE_SIZE - 1;
size_t blocksize = page->mapping->host->i_sb->s_blocksize;
start += ALIGN(offset, blocksize);
@@ -4223,7 +4235,7 @@ static int try_release_extent_state(struct extent_map_tree *map,
struct page *page, gfp_t mask)
{
u64 start = page_offset(page);
- u64 end = start + PAGE_CACHE_SIZE - 1;
+ u64 end = start + PAGE_SIZE - 1;
int ret = 1;
if (test_range_bit(tree, start, end,
@@ -4262,7 +4274,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
{
struct extent_map *em;
u64 start = page_offset(page);
- u64 end = start + PAGE_CACHE_SIZE - 1;
+ u64 end = start + PAGE_SIZE - 1;
if (gfpflags_allow_blocking(mask) &&
page->mapping->host->i_size > SZ_16M) {
@@ -4381,8 +4393,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (ret < 0) {
btrfs_free_path(path);
return ret;
+ } else {
+ WARN_ON(!ret);
+ if (ret == 1)
+ ret = 0;
}
- WARN_ON(!ret);
+
path->slots[0]--;
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
found_type = found_key.type;
@@ -4587,14 +4603,14 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
ClearPagePrivate(page);
set_page_private(page, 0);
/* One for the page private */
- page_cache_release(page);
+ put_page(page);
}
if (mapped)
spin_unlock(&page->mapping->private_lock);
- /* One for when we alloced the page */
- page_cache_release(page);
+ /* One for when we allocated the page */
+ put_page(page);
} while (index != 0);
}
@@ -4706,16 +4722,16 @@ err:
}
struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
- u64 start)
+ u64 start, u32 nodesize)
{
unsigned long len;
if (!fs_info) {
/*
* Called only from tests that don't always have a fs_info
- * available, but we know that nodesize is 4096
+ * available
*/
- len = 4096;
+ len = nodesize;
} else {
len = fs_info->tree_root->nodesize;
}
@@ -4779,7 +4795,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
rcu_read_lock();
eb = radix_tree_lookup(&fs_info->buffer_radix,
- start >> PAGE_CACHE_SHIFT);
+ start >> PAGE_SHIFT);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
/*
@@ -4811,7 +4827,7 @@ struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
- u64 start)
+ u64 start, u32 nodesize)
{
struct extent_buffer *eb, *exists = NULL;
int ret;
@@ -4819,17 +4835,17 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
- eb = alloc_dummy_extent_buffer(fs_info, start);
+ eb = alloc_dummy_extent_buffer(fs_info, start, nodesize);
if (!eb)
return NULL;
eb->fs_info = fs_info;
again:
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ ret = radix_tree_preload(GFP_NOFS);
if (ret)
goto free_eb;
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> PAGE_CACHE_SHIFT, eb);
+ start >> PAGE_SHIFT, eb);
spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
@@ -4862,7 +4878,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
unsigned long len = fs_info->tree_root->nodesize;
unsigned long num_pages = num_extent_pages(start, len);
unsigned long i;
- unsigned long index = start >> PAGE_CACHE_SHIFT;
+ unsigned long index = start >> PAGE_SHIFT;
struct extent_buffer *eb;
struct extent_buffer *exists = NULL;
struct page *p;
@@ -4870,18 +4886,25 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
int uptodate = 1;
int ret;
+ if (!IS_ALIGNED(start, fs_info->tree_root->sectorsize)) {
+ btrfs_err(fs_info, "bad tree block start %llu", start);
+ return ERR_PTR(-EINVAL);
+ }
+
eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
eb = __alloc_extent_buffer(fs_info, start, len);
if (!eb)
- return NULL;
+ return ERR_PTR(-ENOMEM);
for (i = 0; i < num_pages; i++, index++) {
p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
- if (!p)
+ if (!p) {
+ exists = ERR_PTR(-ENOMEM);
goto free_eb;
+ }
spin_lock(&mapping->private_lock);
if (PagePrivate(p)) {
@@ -4896,7 +4919,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
if (atomic_inc_not_zero(&exists->refs)) {
spin_unlock(&mapping->private_lock);
unlock_page(p);
- page_cache_release(p);
+ put_page(p);
mark_extent_buffer_accessed(exists, p);
goto free_eb;
}
@@ -4908,7 +4931,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
*/
ClearPagePrivate(p);
WARN_ON(PageDirty(p));
- page_cache_release(p);
+ put_page(p);
}
attach_extent_buffer_page(eb, p);
spin_unlock(&mapping->private_lock);
@@ -4925,13 +4948,15 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
again:
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
- if (ret)
+ ret = radix_tree_preload(GFP_NOFS);
+ if (ret) {
+ exists = ERR_PTR(ret);
goto free_eb;
+ }
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> PAGE_CACHE_SHIFT, eb);
+ start >> PAGE_SHIFT, eb);
spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
@@ -4994,7 +5019,7 @@ static int release_extent_buffer(struct extent_buffer *eb)
spin_lock(&fs_info->buffer_lock);
radix_tree_delete(&fs_info->buffer_radix,
- eb->start >> PAGE_CACHE_SHIFT);
+ eb->start >> PAGE_SHIFT);
spin_unlock(&fs_info->buffer_lock);
} else {
spin_unlock(&eb->refs_lock);
@@ -5168,8 +5193,8 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
if (start) {
WARN_ON(start < eb->start);
- start_i = (start >> PAGE_CACHE_SHIFT) -
- (eb->start >> PAGE_CACHE_SHIFT);
+ start_i = (start >> PAGE_SHIFT) -
+ (eb->start >> PAGE_SHIFT);
} else {
start_i = 0;
}
@@ -5200,22 +5225,38 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
atomic_set(&eb->io_pages, num_reads);
for (i = start_i; i < num_pages; i++) {
page = eb->pages[i];
+
if (!PageUptodate(page)) {
+ if (ret) {
+ atomic_dec(&eb->io_pages);
+ unlock_page(page);
+ continue;
+ }
+
ClearPageError(page);
err = __extent_read_full_page(tree, page,
get_extent, &bio,
mirror_num, &bio_flags,
- READ | REQ_META);
- if (err)
+ REQ_META);
+ if (err) {
ret = err;
+ /*
+ * We use &bio in above __extent_read_full_page,
+ * so we ensure that if it returns error, the
+ * current page fails to add itself to bio and
+ * it's been unlocked.
+ *
+ * We must dec io_pages by ourselves.
+ */
+ atomic_dec(&eb->io_pages);
+ }
} else {
unlock_page(page);
}
}
if (bio) {
- err = submit_one_bio(READ | REQ_META, bio, mirror_num,
- bio_flags);
+ err = submit_one_bio(bio, mirror_num, bio_flags);
if (err)
return err;
}
@@ -5252,18 +5293,18 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
struct page *page;
char *kaddr;
char *dst = (char *)dstv;
- size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
- unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+ size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+ unsigned long i = (start_offset + start) >> PAGE_SHIFT;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
page = eb->pages[i];
- cur = min(len, (PAGE_CACHE_SIZE - offset));
+ cur = min(len, (PAGE_SIZE - offset));
kaddr = page_address(page);
memcpy(dst, kaddr + offset, cur);
@@ -5283,19 +5324,19 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
struct page *page;
char *kaddr;
char __user *dst = (char __user *)dstv;
- size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
- unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+ size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+ unsigned long i = (start_offset + start) >> PAGE_SHIFT;
int ret = 0;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
page = eb->pages[i];
- cur = min(len, (PAGE_CACHE_SIZE - offset));
+ cur = min(len, (PAGE_SIZE - offset));
kaddr = page_address(page);
if (copy_to_user(dst, kaddr + offset, cur)) {
ret = -EFAULT;
@@ -5311,28 +5352,33 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
return ret;
}
+/*
+ * return 0 if the item is found within a page.
+ * return 1 if the item spans two pages.
+ * return -EINVAL otherwise.
+ */
int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
unsigned long min_len, char **map,
unsigned long *map_start,
unsigned long *map_len)
{
- size_t offset = start & (PAGE_CACHE_SIZE - 1);
+ size_t offset = start & (PAGE_SIZE - 1);
char *kaddr;
struct page *p;
- size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
- unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+ size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+ unsigned long i = (start_offset + start) >> PAGE_SHIFT;
unsigned long end_i = (start_offset + start + min_len - 1) >>
- PAGE_CACHE_SHIFT;
+ PAGE_SHIFT;
if (i != end_i)
- return -EINVAL;
+ return 1;
if (i == 0) {
offset = start_offset;
*map_start = 0;
} else {
offset = 0;
- *map_start = ((u64)i << PAGE_CACHE_SHIFT) - start_offset;
+ *map_start = ((u64)i << PAGE_SHIFT) - start_offset;
}
if (start + min_len > eb->len) {
@@ -5345,7 +5391,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
p = eb->pages[i];
kaddr = page_address(p);
*map = kaddr + offset;
- *map_len = PAGE_CACHE_SIZE - offset;
+ *map_len = PAGE_SIZE - offset;
return 0;
}
@@ -5358,19 +5404,19 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
struct page *page;
char *kaddr;
char *ptr = (char *)ptrv;
- size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
- unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+ size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+ unsigned long i = (start_offset + start) >> PAGE_SHIFT;
int ret = 0;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
page = eb->pages[i];
- cur = min(len, (PAGE_CACHE_SIZE - offset));
+ cur = min(len, (PAGE_SIZE - offset));
kaddr = page_address(page);
ret = memcmp(ptr, kaddr + offset, cur);
@@ -5393,19 +5439,19 @@ void write_extent_buffer(struct extent_buffer *eb, const void *srcv,
struct page *page;
char *kaddr;
char *src = (char *)srcv;
- size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
- unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+ size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+ unsigned long i = (start_offset + start) >> PAGE_SHIFT;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
page = eb->pages[i];
WARN_ON(!PageUptodate(page));
- cur = min(len, PAGE_CACHE_SIZE - offset);
+ cur = min(len, PAGE_SIZE - offset);
kaddr = page_address(page);
memcpy(kaddr + offset, src, cur);
@@ -5423,19 +5469,19 @@ void memset_extent_buffer(struct extent_buffer *eb, char c,
size_t offset;
struct page *page;
char *kaddr;
- size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
- unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT;
+ size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
+ unsigned long i = (start_offset + start) >> PAGE_SHIFT;
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
- offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1);
+ offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
page = eb->pages[i];
WARN_ON(!PageUptodate(page));
- cur = min(len, PAGE_CACHE_SIZE - offset);
+ cur = min(len, PAGE_SIZE - offset);
kaddr = page_address(page);
memset(kaddr + offset, c, cur);
@@ -5454,19 +5500,19 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
size_t offset;
struct page *page;
char *kaddr;
- size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1);
- unsigned long i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT;
+ size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1);
+ unsigned long i = (start_offset + dst_offset) >> PAGE_SHIFT;
WARN_ON(src->len != dst_len);
offset = (start_offset + dst_offset) &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
while (len > 0) {
page = dst->pages[i];
WARN_ON(!PageUptodate(page));
- cur = min(len, (unsigned long)(PAGE_CACHE_SIZE - offset));
+ cur = min(len, (unsigned long)(PAGE_SIZE - offset));
kaddr = page_address(page);
read_extent_buffer(src, kaddr + offset, src_offset, cur);
@@ -5508,7 +5554,7 @@ static inline void eb_bitmap_offset(struct extent_buffer *eb,
unsigned long *page_index,
size_t *page_offset)
{
- size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
+ size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
size_t byte_offset = BIT_BYTE(nr);
size_t offset;
@@ -5519,8 +5565,8 @@ static inline void eb_bitmap_offset(struct extent_buffer *eb,
*/
offset = start_offset + start + byte_offset;
- *page_index = offset >> PAGE_CACHE_SHIFT;
- *page_offset = offset & (PAGE_CACHE_SIZE - 1);
+ *page_index = offset >> PAGE_SHIFT;
+ *page_offset = offset & (PAGE_SIZE - 1);
}
/**
@@ -5572,7 +5618,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
len -= bits_to_set;
bits_to_set = BITS_PER_BYTE;
mask_to_set = ~0U;
- if (++offset >= PAGE_CACHE_SIZE && len > 0) {
+ if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
page = eb->pages[++i];
WARN_ON(!PageUptodate(page));
@@ -5614,7 +5660,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
len -= bits_to_clear;
bits_to_clear = BITS_PER_BYTE;
mask_to_clear = ~0U;
- if (++offset >= PAGE_CACHE_SIZE && len > 0) {
+ if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
page = eb->pages[++i];
WARN_ON(!PageUptodate(page));
@@ -5661,7 +5707,7 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
size_t cur;
size_t dst_off_in_page;
size_t src_off_in_page;
- size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1);
+ size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1);
unsigned long dst_i;
unsigned long src_i;
@@ -5680,17 +5726,17 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
while (len > 0) {
dst_off_in_page = (start_offset + dst_offset) &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
src_off_in_page = (start_offset + src_offset) &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
- dst_i = (start_offset + dst_offset) >> PAGE_CACHE_SHIFT;
- src_i = (start_offset + src_offset) >> PAGE_CACHE_SHIFT;
+ dst_i = (start_offset + dst_offset) >> PAGE_SHIFT;
+ src_i = (start_offset + src_offset) >> PAGE_SHIFT;
- cur = min(len, (unsigned long)(PAGE_CACHE_SIZE -
+ cur = min(len, (unsigned long)(PAGE_SIZE -
src_off_in_page));
cur = min_t(unsigned long, cur,
- (unsigned long)(PAGE_CACHE_SIZE - dst_off_in_page));
+ (unsigned long)(PAGE_SIZE - dst_off_in_page));
copy_pages(dst->pages[dst_i], dst->pages[src_i],
dst_off_in_page, src_off_in_page, cur);
@@ -5709,7 +5755,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
size_t src_off_in_page;
unsigned long dst_end = dst_offset + len - 1;
unsigned long src_end = src_offset + len - 1;
- size_t start_offset = dst->start & ((u64)PAGE_CACHE_SIZE - 1);
+ size_t start_offset = dst->start & ((u64)PAGE_SIZE - 1);
unsigned long dst_i;
unsigned long src_i;
@@ -5728,13 +5774,13 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
return;
}
while (len > 0) {
- dst_i = (start_offset + dst_end) >> PAGE_CACHE_SHIFT;
- src_i = (start_offset + src_end) >> PAGE_CACHE_SHIFT;
+ dst_i = (start_offset + dst_end) >> PAGE_SHIFT;
+ src_i = (start_offset + src_end) >> PAGE_SHIFT;
dst_off_in_page = (start_offset + dst_end) &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
src_off_in_page = (start_offset + src_end) &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
cur = min_t(unsigned long, len, src_off_in_page + 1);
cur = min(cur, dst_off_in_page + 1);
@@ -5753,7 +5799,7 @@ int try_release_extent_buffer(struct page *page)
struct extent_buffer *eb;
/*
- * We need to make sure noboody is attaching this page to an eb right
+ * We need to make sure nobody is attaching this page to an eb right
* now.
*/
spin_lock(&page->mapping->private_lock);
Powered by cgit, Gruvboxed by Blaster4385.