while (compressed_size > 0) {
cpage = compressed_pages[i];
cur_size = min_t(unsigned long, compressed_size,
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
kaddr = kmap_atomic(cpage);
write_extent_buffer(leaf, kaddr, ptr, cur_size);
compress_type);
} else {
page = find_get_page(inode->i_mapping,
- start >> PAGE_CACHE_SHIFT);
+ start >> PAGE_SHIFT);
btrfs_set_file_extent_compression(leaf, ei, 0);
kaddr = kmap_atomic(page);
- offset = start & (PAGE_CACHE_SIZE - 1);
+ offset = start & (PAGE_SIZE - 1);
write_extent_buffer(leaf, kaddr + offset, ptr, size);
kunmap_atomic(kaddr);
- page_cache_release(page);
+ put_page(page);
}
btrfs_mark_buffer_dirty(leaf);
btrfs_release_path(path);
data_len = compressed_size;
if (start > 0 ||
- actual_end > PAGE_CACHE_SIZE ||
+ actual_end > root->sectorsize ||
data_len > BTRFS_MAX_INLINE_DATA_SIZE(root) ||
(!compressed_size &&
(actual_end & (root->sectorsize - 1)) == 0) ||
* And at reserve time, it's always aligned to page size, so
* just free one page here.
*/
- btrfs_qgroup_free_data(inode, 0, PAGE_CACHE_SIZE);
+ btrfs_qgroup_free_data(inode, 0, PAGE_SIZE);
btrfs_free_path(path);
btrfs_end_transaction(trans, root);
return ret;
actual_end = min_t(u64, isize, end + 1);
again:
will_compress = 0;
- nr_pages = (end >> PAGE_CACHE_SHIFT) - (start >> PAGE_CACHE_SHIFT) + 1;
- nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_CACHE_SIZE);
+ nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
+ nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_SIZE);
/*
* we don't want to send crud past the end of i_size through
if (!ret) {
unsigned long offset = total_compressed &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
struct page *page = pages[nr_pages_ret - 1];
char *kaddr;
if (offset) {
kaddr = kmap_atomic(page);
memset(kaddr + offset, 0,
- PAGE_CACHE_SIZE - offset);
+ PAGE_SIZE - offset);
kunmap_atomic(kaddr);
}
will_compress = 1;
* one last check to make sure the compression is really a
* win, compare the page count read with the blocks on disk
*/
- total_in = ALIGN(total_in, PAGE_CACHE_SIZE);
+ total_in = ALIGN(total_in, PAGE_SIZE);
if (total_compressed >= total_in) {
will_compress = 0;
} else {
*/
for (i = 0; i < nr_pages_ret; i++) {
WARN_ON(pages[i]->mapping);
- page_cache_release(pages[i]);
+ put_page(pages[i]);
}
kfree(pages);
pages = NULL;
free_pages_out:
for (i = 0; i < nr_pages_ret; i++) {
WARN_ON(pages[i]->mapping);
- page_cache_release(pages[i]);
+ put_page(pages[i]);
}
kfree(pages);
}
for (i = 0; i < async_extent->nr_pages; i++) {
WARN_ON(async_extent->pages[i]->mapping);
- page_cache_release(async_extent->pages[i]);
+ put_page(async_extent->pages[i]);
}
kfree(async_extent->pages);
async_extent->nr_pages = 0;
PAGE_END_WRITEBACK);
*nr_written = *nr_written +
- (end - start + PAGE_CACHE_SIZE) / PAGE_CACHE_SIZE;
+ (end - start + PAGE_SIZE) / PAGE_SIZE;
*page_started = 1;
goto out;
} else if (ret < 0) {
async_cow = container_of(work, struct async_cow, work);
root = async_cow->root;
- nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >>
- PAGE_CACHE_SHIFT;
+ nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >>
+ PAGE_SHIFT;
/*
* atomic_sub_return implies a barrier for waitqueue_active
async_cow_start, async_cow_submit,
async_cow_free);
- nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
- PAGE_CACHE_SHIFT;
+ nr_pages = (cur_end - start + PAGE_SIZE) >>
+ PAGE_SHIFT;
atomic_add(nr_pages, &root->fs_info->async_delalloc_pages);
btrfs_queue_work(root->fs_info->delalloc_workers,
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
struct extent_state **cached_state)
{
- WARN_ON((end & (PAGE_CACHE_SIZE - 1)) == 0);
+ WARN_ON((end & (PAGE_SIZE - 1)) == 0);
return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
cached_state, GFP_NOFS);
}
inode = page->mapping->host;
page_start = page_offset(page);
- page_end = page_offset(page) + PAGE_CACHE_SIZE - 1;
+ page_end = page_offset(page) + PAGE_SIZE - 1;
lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end,
&cached_state);
if (PagePrivate2(page))
goto out;
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+ ordered = btrfs_lookup_ordered_range(inode, page_start,
+ PAGE_SIZE);
if (ordered) {
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
page_end, &cached_state, GFP_NOFS);
}
ret = btrfs_delalloc_reserve_space(inode, page_start,
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
if (ret) {
mapping_set_error(page->mapping, ret);
end_extent_writepage(page, ret, page_start, page_end);
&cached_state, GFP_NOFS);
out_page:
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
kfree(fixup);
}
return -EAGAIN;
SetPageChecked(page);
- page_cache_get(page);
+ get_page(page);
btrfs_init_work(&fixup->work, btrfs_fixup_helper,
btrfs_writepage_fixup_worker, NULL, NULL);
fixup->page = page;
btrfs_i_size_write(dir, dir->i_size - name_len * 2);
inode_inc_iversion(inode);
inode_inc_iversion(dir);
- inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+ inode->i_ctime = dir->i_mtime =
+ dir->i_ctime = current_fs_time(inode->i_sb);
ret = btrfs_update_inode(trans, root, dir);
out:
return ret;
btrfs_i_size_write(dir, dir->i_size - name_len * 2);
inode_inc_iversion(dir);
- dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+ dir->i_mtime = dir->i_ctime = current_fs_time(dir->i_sb);
ret = btrfs_update_inode_fallback(trans, root, dir);
if (ret)
btrfs_abort_transaction(trans, root, ret);
{
int ret;
+ /*
+ * This is only used to apply pressure to the enospc system, we don't
+ * intend to use this reservation at all.
+ */
bytes_deleted = btrfs_csum_bytes_to_leaves(root, bytes_deleted);
+ bytes_deleted *= root->nodesize;
ret = btrfs_block_rsv_add(root, &root->fs_info->trans_block_rsv,
bytes_deleted, BTRFS_RESERVE_NO_FLUSH);
- if (!ret)
+ if (!ret) {
+ trace_btrfs_space_reservation(root->fs_info, "transaction",
+ trans->transid,
+ bytes_deleted, 1);
trans->bytes_reserved += bytes_deleted;
+ }
return ret;
}
if (btrfs_file_extent_compression(leaf, fi) != BTRFS_COMPRESS_NONE) {
loff_t offset = new_size;
- loff_t page_end = ALIGN(offset, PAGE_CACHE_SIZE);
+ loff_t page_end = ALIGN(offset, PAGE_SIZE);
/*
* Zero out the remaining of the last page of our inline extent,
* read the extent item from disk (data not in the page cache).
*/
btrfs_release_path(path);
- return btrfs_truncate_page(inode, offset, page_end - offset, 0);
+ return btrfs_truncate_block(inode, offset, page_end - offset,
+ 0);
}
btrfs_set_file_extent_ram_bytes(leaf, fi, size);
}
/*
- * btrfs_truncate_page - read, zero a chunk and write a page
+ * btrfs_truncate_block - read, zero a chunk and write a block
* @inode - inode that we're zeroing
* @from - the offset to start zeroing
* @len - the length to zero, 0 to zero the entire range respective to the
* offset
* @front - zero up to the offset instead of from the offset on
*
- * This will find the page for the "from" offset and cow the page and zero the
+ * This will find the block for the "from" offset and cow the block and zero the
* part we want to zero. This is used with truncate and hole punching.
*/
-int btrfs_truncate_page(struct inode *inode, loff_t from, loff_t len,
+int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
int front)
{
struct address_space *mapping = inode->i_mapping;
struct extent_state *cached_state = NULL;
char *kaddr;
u32 blocksize = root->sectorsize;
- pgoff_t index = from >> PAGE_CACHE_SHIFT;
- unsigned offset = from & (PAGE_CACHE_SIZE-1);
+ pgoff_t index = from >> PAGE_SHIFT;
+ unsigned offset = from & (blocksize - 1);
struct page *page;
gfp_t mask = btrfs_alloc_write_mask(mapping);
int ret = 0;
- u64 page_start;
- u64 page_end;
+ u64 block_start;
+ u64 block_end;
if ((offset & (blocksize - 1)) == 0 &&
(!len || ((len & (blocksize - 1)) == 0)))
goto out;
+
ret = btrfs_delalloc_reserve_space(inode,
- round_down(from, PAGE_CACHE_SIZE), PAGE_CACHE_SIZE);
+ round_down(from, blocksize), blocksize);
if (ret)
goto out;
page = find_or_create_page(mapping, index, mask);
if (!page) {
btrfs_delalloc_release_space(inode,
- round_down(from, PAGE_CACHE_SIZE),
- PAGE_CACHE_SIZE);
+ round_down(from, blocksize),
+ blocksize);
ret = -ENOMEM;
goto out;
}
- page_start = page_offset(page);
- page_end = page_start + PAGE_CACHE_SIZE - 1;
+ block_start = round_down(from, blocksize);
+ block_end = block_start + blocksize - 1;
if (!PageUptodate(page)) {
ret = btrfs_readpage(NULL, page);
lock_page(page);
if (page->mapping != mapping) {
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
goto again;
}
if (!PageUptodate(page)) {
}
wait_on_page_writeback(page);
- lock_extent_bits(io_tree, page_start, page_end, &cached_state);
+ lock_extent_bits(io_tree, block_start, block_end, &cached_state);
set_page_extent_mapped(page);
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+ ordered = btrfs_lookup_ordered_extent(inode, block_start);
if (ordered) {
- unlock_extent_cached(io_tree, page_start, page_end,
+ unlock_extent_cached(io_tree, block_start, block_end,
&cached_state, GFP_NOFS);
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
btrfs_start_ordered_extent(inode, ordered, 1);
btrfs_put_ordered_extent(ordered);
goto again;
}
- clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, block_start, block_end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+ ret = btrfs_set_extent_delalloc(inode, block_start, block_end,
&cached_state);
if (ret) {
- unlock_extent_cached(io_tree, page_start, page_end,
+ unlock_extent_cached(io_tree, block_start, block_end,
&cached_state, GFP_NOFS);
goto out_unlock;
}
- if (offset != PAGE_CACHE_SIZE) {
+ if (offset != blocksize) {
if (!len)
- len = PAGE_CACHE_SIZE - offset;
+ len = blocksize - offset;
kaddr = kmap(page);
if (front)
- memset(kaddr, 0, offset);
+ memset(kaddr + (block_start - page_offset(page)),
+ 0, offset);
else
- memset(kaddr + offset, 0, len);
+ memset(kaddr + (block_start - page_offset(page)) + offset,
+ 0, len);
flush_dcache_page(page);
kunmap(page);
}
ClearPageChecked(page);
set_page_dirty(page);
- unlock_extent_cached(io_tree, page_start, page_end, &cached_state,
+ unlock_extent_cached(io_tree, block_start, block_end, &cached_state,
GFP_NOFS);
out_unlock:
if (ret)
- btrfs_delalloc_release_space(inode, page_start,
- PAGE_CACHE_SIZE);
+ btrfs_delalloc_release_space(inode, block_start,
+ blocksize);
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
out:
return ret;
}
int err = 0;
/*
- * If our size started in the middle of a page we need to zero out the
- * rest of the page before we expand the i_size, otherwise we could
+ * If our size started in the middle of a block we need to zero out the
+ * rest of the block before we expand the i_size, otherwise we could
* expose stale data.
*/
- err = btrfs_truncate_page(inode, oldsize, 0, 0);
+ err = btrfs_truncate_block(inode, oldsize, 0, 0);
if (err)
return err;
}
if (newsize > oldsize) {
- truncate_pagecache(inode, newsize);
/*
* Don't do an expanding truncate while snapshoting is ongoing.
* This is to ensure the snapshot captures a fully consistent
i_size_write(inode, newsize);
btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
+ pagecache_isize_extended(inode, oldsize, newsize);
ret = btrfs_update_inode(trans, root, inode);
btrfs_end_write_no_snapshoting(root);
btrfs_end_transaction(trans, root);
inode->i_op = &btrfs_dir_ro_inode_operations;
inode->i_fop = &simple_dir_operations;
inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
- inode->i_mtime = CURRENT_TIME;
+ inode->i_mtime = current_fs_time(inode->i_sb);
inode->i_atime = inode->i_mtime;
inode->i_ctime = inode->i_mtime;
BTRFS_I(inode)->i_otime = inode->i_mtime;
if (name_len <= sizeof(tmp_name)) {
name_ptr = tmp_name;
} else {
- name_ptr = kmalloc(name_len, GFP_NOFS);
+ name_ptr = kmalloc(name_len, GFP_KERNEL);
if (!name_ptr) {
ret = -ENOMEM;
goto err;
inode_init_owner(inode, dir, mode);
inode_set_bytes(inode, 0);
- inode->i_mtime = CURRENT_TIME;
+ inode->i_mtime = current_fs_time(inode->i_sb);
inode->i_atime = inode->i_mtime;
inode->i_ctime = inode->i_mtime;
BTRFS_I(inode)->i_otime = inode->i_mtime;
btrfs_i_size_write(parent_inode, parent_inode->i_size +
name_len * 2);
inode_inc_iversion(parent_inode);
- parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME;
+ parent_inode->i_mtime = parent_inode->i_ctime =
+ current_fs_time(parent_inode->i_sb);
ret = btrfs_update_inode(trans, root, parent_inode);
if (ret)
btrfs_abort_transaction(trans, root, ret);
BTRFS_I(inode)->dir_index = 0ULL;
inc_nlink(inode);
inode_inc_iversion(inode);
- inode->i_ctime = CURRENT_TIME;
+ inode->i_ctime = current_fs_time(inode->i_sb);
ihold(inode);
set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
read_extent_buffer(leaf, tmp, ptr, inline_size);
- max_size = min_t(unsigned long, PAGE_CACHE_SIZE, max_size);
+ max_size = min_t(unsigned long, PAGE_SIZE, max_size);
ret = btrfs_decompress(compress_type, tmp, page,
extent_offset, inline_size, max_size);
kfree(tmp);
size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_offset = page_offset(page) + pg_offset - extent_start;
- copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset,
- size - extent_offset);
+ copy_size = min_t(u64, PAGE_SIZE - pg_offset,
+ size - extent_offset);
em->start = extent_start + extent_offset;
em->len = ALIGN(copy_size, root->sectorsize);
em->orig_block_len = em->len;
map = kmap(page);
read_extent_buffer(leaf, map + pg_offset, ptr,
copy_size);
- if (pg_offset + copy_size < PAGE_CACHE_SIZE) {
+ if (pg_offset + copy_size < PAGE_SIZE) {
memset(map + pg_offset + copy_size, 0,
- PAGE_CACHE_SIZE - pg_offset -
+ PAGE_SIZE - pg_offset -
copy_size);
}
kunmap(page);
int start_idx;
int end_idx;
- start_idx = start >> PAGE_CACHE_SHIFT;
+ start_idx = start >> PAGE_SHIFT;
/*
* end is the last byte in the last page. end == start is legal
*/
- end_idx = end >> PAGE_CACHE_SHIFT;
+ end_idx = end >> PAGE_SHIFT;
rcu_read_lock();
* include/linux/pagemap.h for details.
*/
if (unlikely(page != *pagep)) {
- page_cache_release(page);
+ put_page(page);
page = NULL;
}
}
if (page) {
if (page->index <= end_idx)
found = true;
- page_cache_release(page);
+ put_page(page);
}
rcu_read_unlock();
cached_state, GFP_NOFS);
if (ordered) {
- btrfs_start_ordered_extent(inode, ordered, 1);
+ /*
+ * If we are doing a DIO read and the ordered extent we
+ * found is for a buffered write, we can not wait for it
+ * to complete and retry, because if we do so we can
+ * deadlock with concurrent buffered writes on page
+ * locks. This happens only if our DIO read covers more
+ * than one extent map, if at this point has already
+ * created an ordered extent for a previous extent map
+ * and locked its range in the inode's io tree, and a
+ * concurrent write against that previous extent map's
+ * range and this range started (we unlock the ranges
+ * in the io tree only when the bios complete and
+ * buffered writes always lock pages before attempting
+ * to lock range in the io tree).
+ */
+ if (writing ||
+ test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
+ btrfs_start_ordered_extent(inode, ordered, 1);
+ else
+ ret = -ENOTBLK;
btrfs_put_ordered_extent(ordered);
} else {
/*
* that page.
*/
ret = -ENOTBLK;
- break;
}
+ if (ret)
+ break;
+
cond_resched();
}
}
static int dio_read_error(struct inode *inode, struct bio *failed_bio,
- struct page *page, u64 start, u64 end,
- int failed_mirror, bio_end_io_t *repair_endio,
- void *repair_arg)
+ struct page *page, unsigned int pgoff,
+ u64 start, u64 end, int failed_mirror,
+ bio_end_io_t *repair_endio, void *repair_arg)
{
struct io_failure_record *failrec;
struct bio *bio;
return -EIO;
}
- if (failed_bio->bi_vcnt > 1)
+ if ((failed_bio->bi_vcnt > 1)
+ || (failed_bio->bi_io_vec->bv_len
+ > BTRFS_I(inode)->root->sectorsize))
read_mode = READ_SYNC | REQ_FAILFAST_DEV;
else
read_mode = READ_SYNC;
isector = start - btrfs_io_bio(failed_bio)->logical;
isector >>= inode->i_sb->s_blocksize_bits;
bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
- 0, isector, repair_endio, repair_arg);
+ pgoff, isector, repair_endio, repair_arg);
if (!bio) {
free_io_failure(inode, failrec);
return -EIO;
static void btrfs_retry_endio_nocsum(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
+ struct inode *inode;
struct bio_vec *bvec;
int i;
if (bio->bi_error)
goto end;
+ ASSERT(bio->bi_vcnt == 1);
+ inode = bio->bi_io_vec->bv_page->mapping->host;
+ ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
done->uptodate = 1;
bio_for_each_segment_all(bvec, bio, i)
clean_io_failure(done->inode, done->start, bvec->bv_page, 0);
static int __btrfs_correct_data_nocsum(struct inode *inode,
struct btrfs_io_bio *io_bio)
{
+ struct btrfs_fs_info *fs_info;
struct bio_vec *bvec;
struct btrfs_retry_complete done;
u64 start;
+ unsigned int pgoff;
+ u32 sectorsize;
+ int nr_sectors;
int i;
int ret;
+ fs_info = BTRFS_I(inode)->root->fs_info;
+ sectorsize = BTRFS_I(inode)->root->sectorsize;
+
start = io_bio->logical;
done.inode = inode;
bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-try_again:
+ nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+ pgoff = bvec->bv_offset;
+
+next_block_or_try_again:
done.uptodate = 0;
done.start = start;
init_completion(&done.done);
- ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
- start + bvec->bv_len - 1,
- io_bio->mirror_num,
- btrfs_retry_endio_nocsum, &done);
+ ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+ pgoff, start, start + sectorsize - 1,
+ io_bio->mirror_num,
+ btrfs_retry_endio_nocsum, &done);
if (ret)
return ret;
if (!done.uptodate) {
/* We might have another mirror, so try again */
- goto try_again;
+ goto next_block_or_try_again;
}
- start += bvec->bv_len;
+ start += sectorsize;
+
+ if (nr_sectors--) {
+ pgoff += sectorsize;
+ goto next_block_or_try_again;
+ }
}
return 0;
{
struct btrfs_retry_complete *done = bio->bi_private;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+ struct inode *inode;
struct bio_vec *bvec;
+ u64 start;
int uptodate;
int ret;
int i;
goto end;
uptodate = 1;
+
+ start = done->start;
+
+ ASSERT(bio->bi_vcnt == 1);
+ inode = bio->bi_io_vec->bv_page->mapping->host;
+ ASSERT(bio->bi_io_vec->bv_len == BTRFS_I(inode)->root->sectorsize);
+
bio_for_each_segment_all(bvec, bio, i) {
ret = __readpage_endio_check(done->inode, io_bio, i,
- bvec->bv_page, 0,
- done->start, bvec->bv_len);
+ bvec->bv_page, bvec->bv_offset,
+ done->start, bvec->bv_len);
if (!ret)
clean_io_failure(done->inode, done->start,
- bvec->bv_page, 0);
+ bvec->bv_page, bvec->bv_offset);
else
uptodate = 0;
}
static int __btrfs_subio_endio_read(struct inode *inode,
struct btrfs_io_bio *io_bio, int err)
{
+ struct btrfs_fs_info *fs_info;
struct bio_vec *bvec;
struct btrfs_retry_complete done;
u64 start;
u64 offset = 0;
+ u32 sectorsize;
+ int nr_sectors;
+ unsigned int pgoff;
+ int csum_pos;
int i;
int ret;
+ fs_info = BTRFS_I(inode)->root->fs_info;
+ sectorsize = BTRFS_I(inode)->root->sectorsize;
+
err = 0;
start = io_bio->logical;
done.inode = inode;
bio_for_each_segment_all(bvec, &io_bio->bio, i) {
- ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
- 0, start, bvec->bv_len);
+ nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+
+ pgoff = bvec->bv_offset;
+next_block:
+ csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
+ ret = __readpage_endio_check(inode, io_bio, csum_pos,
+ bvec->bv_page, pgoff, start,
+ sectorsize);
if (likely(!ret))
goto next;
try_again:
done.start = start;
init_completion(&done.done);
- ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, start,
- start + bvec->bv_len - 1,
- io_bio->mirror_num,
- btrfs_retry_endio, &done);
+ ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+ pgoff, start, start + sectorsize - 1,
+ io_bio->mirror_num,
+ btrfs_retry_endio, &done);
if (ret) {
err = ret;
goto next;
goto try_again;
}
next:
- offset += bvec->bv_len;
- start += bvec->bv_len;
+ offset += sectorsize;
+ start += sectorsize;
+
+ ASSERT(nr_sectors);
+
+ if (--nr_sectors) {
+ pgoff += sectorsize;
+ goto next_block;
+ }
}
return err;
u64 file_offset = dip->logical_offset;
u64 submit_len = 0;
u64 map_length;
- int nr_pages = 0;
- int ret;
+ u32 blocksize = root->sectorsize;
int async_submit = 0;
+ int nr_sectors;
+ int ret;
+ int i;
map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
atomic_inc(&dip->pending_bios);
while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
- if (map_length < submit_len + bvec->bv_len ||
- bio_add_page(bio, bvec->bv_page, bvec->bv_len,
- bvec->bv_offset) < bvec->bv_len) {
+ nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info, bvec->bv_len);
+ i = 0;
+next_block:
+ if (unlikely(map_length < submit_len + blocksize ||
+ bio_add_page(bio, bvec->bv_page, blocksize,
+ bvec->bv_offset + (i * blocksize)) < blocksize)) {
/*
* inc the count before we submit the bio so
* we know the end IO handler won't happen before
file_offset += submit_len;
submit_len = 0;
- nr_pages = 0;
bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
start_sector, GFP_NOFS);
bio_put(bio);
goto out_err;
}
+
+ goto next_block;
} else {
- submit_len += bvec->bv_len;
- nr_pages++;
+ submit_len += blocksize;
+ if (--nr_sectors) {
+ i++;
+ goto next_block;
+ }
bvec++;
}
}
if (ret == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
- page_cache_release(page);
+ put_page(page);
}
return ret;
}
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
u64 page_start = page_offset(page);
- u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
+ u64 page_end = page_start + PAGE_SIZE - 1;
+ u64 start;
+ u64 end;
int inode_evicting = inode->i_state & I_FREEING;
/*
if (!inode_evicting)
lock_extent_bits(tree, page_start, page_end, &cached_state);
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+again:
+ start = page_start;
+ ordered = btrfs_lookup_ordered_range(inode, start,
+ page_end - start + 1);
if (ordered) {
+ end = min(page_end, ordered->file_offset + ordered->len - 1);
/*
* IO on this page will never be started, so we need
* to account for any ordered extents now
*/
if (!inode_evicting)
- clear_extent_bit(tree, page_start, page_end,
+ clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, 1, 0, &cached_state,
spin_lock_irq(&tree->lock);
set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
- new_len = page_start - ordered->file_offset;
+ new_len = start - ordered->file_offset;
if (new_len < ordered->truncated_len)
ordered->truncated_len = new_len;
spin_unlock_irq(&tree->lock);
if (btrfs_dec_test_ordered_pending(inode, &ordered,
- page_start,
- PAGE_CACHE_SIZE, 1))
+ start,
+ end - start + 1, 1))
btrfs_finish_ordered_io(ordered);
}
btrfs_put_ordered_extent(ordered);
if (!inode_evicting) {
cached_state = NULL;
- lock_extent_bits(tree, page_start, page_end,
+ lock_extent_bits(tree, start, end,
&cached_state);
}
+
+ start = end + 1;
+ if (start < page_end)
+ goto again;
}
/*
* 2) Not written to disk
* This means the reserved space should be freed here.
*/
- btrfs_qgroup_free_data(inode, page_start, PAGE_CACHE_SIZE);
+ btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
if (!inode_evicting) {
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY |
if (PagePrivate(page)) {
ClearPagePrivate(page);
set_page_private(page, 0);
- page_cache_release(page);
+ put_page(page);
}
}
loff_t size;
int ret;
int reserved = 0;
+ u64 reserved_space;
u64 page_start;
u64 page_end;
+ u64 end;
+
+ reserved_space = PAGE_SIZE;
sb_start_pagefault(inode->i_sb);
page_start = page_offset(page);
- page_end = page_start + PAGE_CACHE_SIZE - 1;
+ page_end = page_start + PAGE_SIZE - 1;
+ end = page_end;
+ /*
+ * Reserving delalloc space after obtaining the page lock can lead to
+ * deadlock. For example, if a dirty page is locked by this function
+ * and the call to btrfs_delalloc_reserve_space() ends up triggering
+ * dirty page write out, then the btrfs_writepage() function could
+ * end up waiting indefinitely to get a lock on the page currently
+ * being processed by btrfs_page_mkwrite() function.
+ */
ret = btrfs_delalloc_reserve_space(inode, page_start,
- PAGE_CACHE_SIZE);
+ reserved_space);
if (!ret) {
ret = file_update_time(vma->vm_file);
reserved = 1;
* we can't set the delalloc bits if there are pending ordered
* extents. Drop our locks and wait for them to finish
*/
- ordered = btrfs_lookup_ordered_extent(inode, page_start);
+ ordered = btrfs_lookup_ordered_range(inode, page_start, page_end);
if (ordered) {
unlock_extent_cached(io_tree, page_start, page_end,
&cached_state, GFP_NOFS);
goto again;
}
+ if (page->index == ((size - 1) >> PAGE_SHIFT)) {
+ reserved_space = round_up(size - page_start, root->sectorsize);
+ if (reserved_space < PAGE_SIZE) {
+ end = page_start + reserved_space - 1;
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->outstanding_extents++;
+ spin_unlock(&BTRFS_I(inode)->lock);
+ btrfs_delalloc_release_space(inode, page_start,
+ PAGE_SIZE - reserved_space);
+ }
+ }
+
/*
* XXX - page_mkwrite gets called every time the page is dirtied, even
* if it was already dirty, so for space accounting reasons we need to
* is probably a better way to do this, but for now keep consistent with
* prepare_pages in the normal write path.
*/
- clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end,
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, page_start, page_end,
+ ret = btrfs_set_extent_delalloc(inode, page_start, end,
&cached_state);
if (ret) {
unlock_extent_cached(io_tree, page_start, page_end,
ret = 0;
/* page is wholly or partially inside EOF */
- if (page_start + PAGE_CACHE_SIZE > size)
- zero_start = size & ~PAGE_CACHE_MASK;
+ if (page_start + PAGE_SIZE > size)
+ zero_start = size & ~PAGE_MASK;
else
- zero_start = PAGE_CACHE_SIZE;
+ zero_start = PAGE_SIZE;
- if (zero_start != PAGE_CACHE_SIZE) {
+ if (zero_start != PAGE_SIZE) {
kaddr = kmap(page);
- memset(kaddr + zero_start, 0, PAGE_CACHE_SIZE - zero_start);
+ memset(kaddr + zero_start, 0, PAGE_SIZE - zero_start);
flush_dcache_page(page);
kunmap(page);
}
}
unlock_page(page);
out:
- btrfs_delalloc_release_space(inode, page_start, PAGE_CACHE_SIZE);
+ btrfs_delalloc_release_space(inode, page_start, reserved_space);
out_noreserve:
sb_end_pagefault(inode->i_sb);
return ret;
* destroy cache.
*/
rcu_barrier();
- if (btrfs_inode_cachep)
- kmem_cache_destroy(btrfs_inode_cachep);
- if (btrfs_trans_handle_cachep)
- kmem_cache_destroy(btrfs_trans_handle_cachep);
- if (btrfs_transaction_cachep)
- kmem_cache_destroy(btrfs_transaction_cachep);
- if (btrfs_path_cachep)
- kmem_cache_destroy(btrfs_path_cachep);
- if (btrfs_free_space_cachep)
- kmem_cache_destroy(btrfs_free_space_cachep);
+ kmem_cache_destroy(btrfs_inode_cachep);
+ kmem_cache_destroy(btrfs_trans_handle_cachep);
+ kmem_cache_destroy(btrfs_transaction_cachep);
+ kmem_cache_destroy(btrfs_path_cachep);
+ kmem_cache_destroy(btrfs_free_space_cachep);
}
int btrfs_init_cachep(void)
generic_fillattr(inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
- stat->blksize = PAGE_CACHE_SIZE;
spin_lock(&BTRFS_I(inode)->lock);
delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
struct btrfs_root *dest = BTRFS_I(new_dir)->root;
struct inode *new_inode = d_inode(new_dentry);
struct inode *old_inode = d_inode(old_dentry);
- struct timespec ctime = CURRENT_TIME;
u64 index = 0;
u64 root_objectid;
int ret;
inode_inc_iversion(old_dir);
inode_inc_iversion(new_dir);
inode_inc_iversion(old_inode);
- old_dir->i_ctime = old_dir->i_mtime = ctime;
- new_dir->i_ctime = new_dir->i_mtime = ctime;
- old_inode->i_ctime = ctime;
+ old_dir->i_ctime = old_dir->i_mtime =
+ new_dir->i_ctime = new_dir->i_mtime =
+ old_inode->i_ctime = current_fs_time(old_dir->i_sb);
if (old_dentry->d_parent != new_dentry->d_parent)
btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
if (new_inode) {
inode_inc_iversion(new_inode);
- new_inode->i_ctime = CURRENT_TIME;
+ new_inode->i_ctime = current_fs_time(new_inode->i_sb);
if (unlikely(btrfs_ino(new_inode) ==
BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
root_objectid = BTRFS_I(new_inode)->location.objectid;
*alloc_hint = ins.objectid + ins.offset;
inode_inc_iversion(inode);
- inode->i_ctime = CURRENT_TIME;
+ inode->i_ctime = current_fs_time(inode->i_sb);
BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
(actual_len > inode->i_size) &&
projects / linux-2.6-block.git / blobdiff