aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/inode.c')
-rw-r--r--fs/btrfs/inode.c939
1 files changed, 653 insertions, 286 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 41a5688ffdfe..b0f421f332ae 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -60,6 +60,7 @@
#include "hash.h"
#include "props.h"
#include "qgroup.h"
+#include "dedupe.h"
struct btrfs_iget_args {
struct btrfs_key *location;
@@ -105,8 +106,9 @@ static int btrfs_truncate(struct inode *inode);
static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
static noinline int cow_file_range(struct inode *inode,
struct page *locked_page,
- u64 start, u64 end, int *page_started,
- unsigned long *nr_written, int unlock);
+ u64 start, u64 end, u64 delalloc_end,
+ int *page_started, unsigned long *nr_written,
+ int unlock, struct btrfs_dedupe_hash *hash);
static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
u64 len, u64 orig_start,
u64 block_start, u64 block_len,
@@ -194,7 +196,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
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);
@@ -208,13 +210,13 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
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);
@@ -294,7 +296,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
start, aligned_end, NULL,
1, 1, extent_item_size, &extent_inserted);
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out;
}
@@ -305,7 +307,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
inline_len, compressed_size,
compress_type, compressed_pages);
if (ret && ret != -ENOSPC) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out;
} else if (ret == -ENOSPC) {
ret = 1;
@@ -322,7 +324,7 @@ out:
* 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;
@@ -374,12 +376,12 @@ static inline int inode_need_compress(struct inode *inode)
struct btrfs_root *root = BTRFS_I(inode)->root;
/* force compress */
- if (btrfs_test_opt(root, FORCE_COMPRESS))
+ if (btrfs_test_opt(root->fs_info, FORCE_COMPRESS))
return 1;
/* bad compression ratios */
if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS)
return 0;
- if (btrfs_test_opt(root, COMPRESS) ||
+ if (btrfs_test_opt(root->fs_info, COMPRESS) ||
BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS ||
BTRFS_I(inode)->force_compress)
return 1;
@@ -435,8 +437,8 @@ static noinline void compress_file_range(struct inode *inode,
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
@@ -455,7 +457,7 @@ again:
/*
* skip compression for a small file range(<=blocksize) that
- * isn't an inline extent, since it dosen't save disk space at all.
+ * isn't an inline extent, since it doesn't save disk space at all.
*/
if (total_compressed <= blocksize &&
(start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
@@ -514,7 +516,7 @@ again:
if (!ret) {
unsigned long offset = total_compressed &
- (PAGE_CACHE_SIZE - 1);
+ (PAGE_SIZE - 1);
struct page *page = pages[nr_pages_ret - 1];
char *kaddr;
@@ -524,7 +526,7 @@ again:
if (offset) {
kaddr = kmap_atomic(page);
memset(kaddr + offset, 0,
- PAGE_CACHE_SIZE - offset);
+ PAGE_SIZE - offset);
kunmap_atomic(kaddr);
}
will_compress = 1;
@@ -580,21 +582,39 @@ cont:
* 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 {
num_bytes = total_in;
+ *num_added += 1;
+
+ /*
+ * The async work queues will take care of doing actual
+ * allocation on disk for these compressed pages, and
+ * will submit them to the elevator.
+ */
+ add_async_extent(async_cow, start, num_bytes,
+ total_compressed, pages, nr_pages_ret,
+ compress_type);
+
+ if (start + num_bytes < end) {
+ start += num_bytes;
+ pages = NULL;
+ cond_resched();
+ goto again;
+ }
+ return;
}
}
- if (!will_compress && pages) {
+ if (pages) {
/*
* the compression code ran but failed to make things smaller,
* free any pages it allocated and our page pointer array
*/
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;
@@ -602,55 +622,35 @@ cont:
nr_pages_ret = 0;
/* flag the file so we don't compress in the future */
- if (!btrfs_test_opt(root, FORCE_COMPRESS) &&
+ if (!btrfs_test_opt(root->fs_info, FORCE_COMPRESS) &&
!(BTRFS_I(inode)->force_compress)) {
BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
}
}
- if (will_compress) {
- *num_added += 1;
-
- /* the async work queues will take care of doing actual
- * allocation on disk for these compressed pages,
- * and will submit them to the elevator.
- */
- add_async_extent(async_cow, start, num_bytes,
- total_compressed, pages, nr_pages_ret,
- compress_type);
-
- if (start + num_bytes < end) {
- start += num_bytes;
- pages = NULL;
- cond_resched();
- goto again;
- }
- } else {
cleanup_and_bail_uncompressed:
- /*
- * No compression, but we still need to write the pages in
- * the file we've been given so far. redirty the locked
- * page if it corresponds to our extent and set things up
- * for the async work queue to run cow_file_range to do
- * the normal delalloc dance
- */
- if (page_offset(locked_page) >= start &&
- page_offset(locked_page) <= end) {
- __set_page_dirty_nobuffers(locked_page);
- /* unlocked later on in the async handlers */
- }
- if (redirty)
- extent_range_redirty_for_io(inode, start, end);
- add_async_extent(async_cow, start, end - start + 1,
- 0, NULL, 0, BTRFS_COMPRESS_NONE);
- *num_added += 1;
- }
+ /*
+ * No compression, but we still need to write the pages in the file
+ * we've been given so far. redirty the locked page if it corresponds
+ * to our extent and set things up for the async work queue to run
+ * cow_file_range to do the normal delalloc dance.
+ */
+ if (page_offset(locked_page) >= start &&
+ page_offset(locked_page) <= end)
+ __set_page_dirty_nobuffers(locked_page);
+ /* unlocked later on in the async handlers */
+
+ if (redirty)
+ extent_range_redirty_for_io(inode, start, end);
+ add_async_extent(async_cow, start, end - start + 1, 0, NULL, 0,
+ BTRFS_COMPRESS_NONE);
+ *num_added += 1;
return;
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);
}
@@ -664,7 +664,7 @@ static void free_async_extent_pages(struct async_extent *async_extent)
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;
@@ -712,7 +712,10 @@ retry:
async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
- &page_started, &nr_written, 0);
+ async_extent->start +
+ async_extent->ram_size - 1,
+ &page_started, &nr_written, 0,
+ NULL);
/* JDM XXX */
@@ -824,6 +827,7 @@ retry:
async_extent->ram_size - 1, 0);
goto out_free_reserve;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
/*
* clear dirty, set writeback and unlock the pages.
@@ -861,6 +865,7 @@ retry:
}
return;
out_free_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_free:
extent_clear_unlock_delalloc(inode, async_extent->start,
@@ -923,9 +928,9 @@ static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
*/
static noinline int cow_file_range(struct inode *inode,
struct page *locked_page,
- u64 start, u64 end, int *page_started,
- unsigned long *nr_written,
- int unlock)
+ u64 start, u64 end, u64 delalloc_end,
+ int *page_started, unsigned long *nr_written,
+ int unlock, struct btrfs_dedupe_hash *hash)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 alloc_hint = 0;
@@ -966,7 +971,7 @@ static noinline int cow_file_range(struct inode *inode,
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) {
@@ -1038,6 +1043,8 @@ static noinline int cow_file_range(struct inode *inode,
goto out_drop_extent_cache;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+
if (disk_num_bytes < cur_alloc_size)
break;
@@ -1066,6 +1073,7 @@ out:
out_drop_extent_cache:
btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
out_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_unlock:
extent_clear_unlock_delalloc(inode, start, end, locked_page,
@@ -1106,8 +1114,8 @@ static noinline void async_cow_submit(struct btrfs_work *work)
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
@@ -1151,7 +1159,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
async_cow->start = start;
if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS &&
- !btrfs_test_opt(root, FORCE_COMPRESS))
+ !btrfs_test_opt(root->fs_info, FORCE_COMPRESS))
cur_end = end;
else
cur_end = min(end, start + SZ_512K - 1);
@@ -1164,8 +1172,8 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
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,
@@ -1377,6 +1385,9 @@ next_slot:
*/
if (csum_exist_in_range(root, disk_bytenr, num_bytes))
goto out_check;
+ if (!btrfs_inc_nocow_writers(root->fs_info,
+ disk_bytenr))
+ goto out_check;
nocow = 1;
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
extent_end = found_key.offset +
@@ -1391,6 +1402,9 @@ out_check:
path->slots[0]++;
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info,
+ disk_bytenr);
goto next_slot;
}
if (!nocow) {
@@ -1407,10 +1421,14 @@ out_check:
if (cow_start != (u64)-1) {
ret = cow_file_range(inode, locked_page,
cow_start, found_key.offset - 1,
- page_started, nr_written, 1);
+ end, page_started, nr_written, 1,
+ NULL);
if (ret) {
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info,
+ disk_bytenr);
goto error;
}
cow_start = (u64)-1;
@@ -1453,6 +1471,8 @@ out_check:
ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr,
num_bytes, num_bytes, type);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info, disk_bytenr);
BUG_ON(ret); /* -ENOMEM */
if (root->root_key.objectid ==
@@ -1485,8 +1505,8 @@ out_check:
}
if (cow_start != (u64)-1) {
- ret = cow_file_range(inode, locked_page, cow_start, end,
- page_started, nr_written, 1);
+ ret = cow_file_range(inode, locked_page, cow_start, end, end,
+ page_started, nr_written, 1, NULL);
if (ret)
goto error;
}
@@ -1545,8 +1565,8 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 0, nr_written);
} else if (!inode_need_compress(inode)) {
- ret = cow_file_range(inode, locked_page, start, end,
- page_started, nr_written, 1);
+ ret = cow_file_range(inode, locked_page, start, end, end,
+ page_started, nr_written, 1, NULL);
} else {
set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
&BTRFS_I(inode)->runtime_flags);
@@ -1724,7 +1744,7 @@ static void btrfs_set_bit_hook(struct inode *inode,
}
/* For sanity tests */
- if (btrfs_test_is_dummy_root(root))
+ if (btrfs_is_testing(root->fs_info))
return;
__percpu_counter_add(&root->fs_info->delalloc_bytes, len,
@@ -1783,7 +1803,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
btrfs_delalloc_release_metadata(inode, len);
/* For sanity tests. */
- if (btrfs_test_is_dummy_root(root))
+ if (btrfs_is_testing(root->fs_info))
return;
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
@@ -1806,8 +1826,12 @@ static void btrfs_clear_bit_hook(struct inode *inode,
/*
* extent_io.c merge_bio_hook, this must check the chunk tree to make sure
* we don't create bios that span stripes or chunks
+ *
+ * return 1 if page cannot be merged to bio
+ * return 0 if page can be merged to bio
+ * return error otherwise
*/
-int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
+int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
size_t size, struct bio *bio,
unsigned long bio_flags)
{
@@ -1822,10 +1846,10 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
length = bio->bi_iter.bi_size;
map_length = length;
- ret = btrfs_map_block(root->fs_info, rw, logical,
+ ret = btrfs_map_block(root->fs_info, bio_op(bio), logical,
&map_length, NULL, 0);
- /* Will always return 0 with map_multi == NULL */
- BUG_ON(ret < 0);
+ if (ret < 0)
+ return ret;
if (map_length < length + size)
return 1;
return 0;
@@ -1839,9 +1863,8 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
* At IO completion time the cums attached on the ordered extent record
* are inserted into the btree
*/
-static int __btrfs_submit_bio_start(struct inode *inode, int rw,
- struct bio *bio, int mirror_num,
- unsigned long bio_flags,
+static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
+ int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -1860,14 +1883,14 @@ static int __btrfs_submit_bio_start(struct inode *inode, int rw,
* At IO completion time the cums attached on the ordered extent record
* are inserted into the btree
*/
-static int __btrfs_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
+static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
- ret = btrfs_map_bio(root, rw, bio, mirror_num, 1);
+ ret = btrfs_map_bio(root, bio, mirror_num, 1);
if (ret) {
bio->bi_error = ret;
bio_endio(bio);
@@ -1879,7 +1902,7 @@ static int __btrfs_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
* extent_io.c submission hook. This does the right thing for csum calculation
* on write, or reading the csums from the tree before a read
*/
-static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
+static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
@@ -1894,7 +1917,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
if (btrfs_is_free_space_inode(inode))
metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
- if (!(rw & REQ_WRITE)) {
+ if (bio_op(bio) != REQ_OP_WRITE) {
ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata);
if (ret)
goto out;
@@ -1916,7 +1939,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
goto mapit;
/* we're doing a write, do the async checksumming */
ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
- inode, rw, bio, mirror_num,
+ inode, bio, mirror_num,
bio_flags, bio_offset,
__btrfs_submit_bio_start,
__btrfs_submit_bio_done);
@@ -1928,7 +1951,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
}
mapit:
- ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
+ ret = btrfs_map_bio(root, bio, mirror_num, 0);
out:
if (ret < 0) {
@@ -1960,9 +1983,9 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
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);
+ cached_state);
}
/* see btrfs_writepage_start_hook for details on why this is required */
@@ -1993,7 +2016,7 @@ again:
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);
@@ -2003,7 +2026,7 @@ again:
goto out;
ordered = btrfs_lookup_ordered_range(inode, page_start,
- PAGE_CACHE_SIZE);
+ PAGE_SIZE);
if (ordered) {
unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
page_end, &cached_state, GFP_NOFS);
@@ -2014,7 +2037,7 @@ again:
}
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);
@@ -2030,7 +2053,7 @@ out:
&cached_state, GFP_NOFS);
out_page:
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
kfree(fixup);
}
@@ -2063,7 +2086,7 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
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;
@@ -2579,7 +2602,7 @@ again:
ret = btrfs_insert_empty_item(trans, root, path, &key,
sizeof(*extent));
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out_free_path;
}
@@ -2606,7 +2629,7 @@ again:
backref->root_id, backref->inum,
new->file_pos); /* start - extent_offset */
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out_free_path;
}
@@ -2875,7 +2898,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
ret = btrfs_update_inode_fallback(trans, root, inode);
if (ret) /* -ENOMEM or corruption */
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out;
}
@@ -2935,7 +2958,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
ordered_extent->file_offset, ordered_extent->len,
trans->transid);
if (ret < 0) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out_unlock;
}
@@ -2945,7 +2968,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
btrfs_ordered_update_i_size(inode, 0, ordered_extent);
ret = btrfs_update_inode_fallback(trans, root, inode);
if (ret) { /* -ENOMEM or corruption */
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out_unlock;
}
ret = 0;
@@ -3103,8 +3126,7 @@ static int btrfs_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID &&
test_range_bit(io_tree, start, end, EXTENT_NODATASUM, 1, NULL)) {
- clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM,
- GFP_NOFS);
+ clear_extent_bits(io_tree, start, end, EXTENT_NODATASUM);
return 0;
}
@@ -3190,7 +3212,7 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root,
root->root_key.objectid);
if (ret)
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
else
clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
&root->state);
@@ -3256,7 +3278,16 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
/* grab metadata reservation from transaction handle */
if (reserve) {
ret = btrfs_orphan_reserve_metadata(trans, inode);
- BUG_ON(ret); /* -ENOSPC in reservation; Logic error? JDM */
+ ASSERT(!ret);
+ if (ret) {
+ atomic_dec(&root->orphan_inodes);
+ clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
+ &BTRFS_I(inode)->runtime_flags);
+ if (insert)
+ clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+ &BTRFS_I(inode)->runtime_flags);
+ return ret;
+ }
}
/* insert an orphan item to track this unlinked/truncated file */
@@ -3272,7 +3303,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
if (ret != -EEXIST) {
clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
&BTRFS_I(inode)->runtime_flags);
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
return ret;
}
}
@@ -3284,7 +3315,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
ret = btrfs_insert_orphan_item(trans, root->fs_info->tree_root,
root->root_key.objectid);
if (ret && ret != -EEXIST) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
return ret;
}
}
@@ -3706,7 +3737,7 @@ cache_index:
* and doesn't have an inode ref with the name "bar" anymore.
*
* Setting last_unlink_trans to last_trans is a pessimistic approach,
- * but it guarantees correctness at the expense of ocassional full
+ * but it guarantees correctness at the expense of occasional full
* transaction commits on fsync if our inode is a directory, or if our
* inode is not a directory, logging its parent unnecessarily.
*/
@@ -3983,20 +4014,20 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
btrfs_info(root->fs_info,
"failed to delete reference to %.*s, inode %llu parent %llu",
name_len, name, ino, dir_ino);
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto err;
}
skip_backref:
ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto err;
}
ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len,
inode, dir_ino);
if (ret != 0 && ret != -ENOENT) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto err;
}
@@ -4005,7 +4036,7 @@ skip_backref:
if (ret == -ENOENT)
ret = 0;
else if (ret)
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
err:
btrfs_free_path(path);
if (ret)
@@ -4119,7 +4150,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
WARN_ON(key.type != BTRFS_ROOT_ITEM_KEY || key.objectid != objectid);
ret = btrfs_delete_one_dir_name(trans, root, path, di);
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out;
}
btrfs_release_path(path);
@@ -4129,7 +4160,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
dir_ino, &index, name, name_len);
if (ret < 0) {
if (ret != -ENOENT) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out;
}
di = btrfs_search_dir_index_item(root, path, dir_ino,
@@ -4139,7 +4170,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
ret = -ENOENT;
else
ret = PTR_ERR(di);
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out;
}
@@ -4152,7 +4183,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out;
}
@@ -4161,7 +4192,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
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);
+ btrfs_abort_transaction(trans, ret);
out:
btrfs_free_path(path);
return ret;
@@ -4247,7 +4278,7 @@ static int truncate_inline_extent(struct inode *inode,
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,
@@ -4482,7 +4513,6 @@ search_again:
pending_del_nr);
if (err) {
btrfs_abort_transaction(trans,
- root,
err);
goto error;
}
@@ -4494,8 +4524,7 @@ search_again:
item_end,
new_size);
if (err) {
- btrfs_abort_transaction(trans,
- root, err);
+ btrfs_abort_transaction(trans, err);
goto error;
}
} else if (test_bit(BTRFS_ROOT_REF_COWS,
@@ -4534,6 +4563,7 @@ delete:
BUG_ON(ret);
if (btrfs_should_throttle_delayed_refs(trans, root))
btrfs_async_run_delayed_refs(root,
+ trans->transid,
trans->delayed_ref_updates * 2, 0);
if (be_nice) {
if (truncate_space_check(trans, root,
@@ -4558,8 +4588,7 @@ delete:
pending_del_slot,
pending_del_nr);
if (ret) {
- btrfs_abort_transaction(trans,
- root, ret);
+ btrfs_abort_transaction(trans, ret);
goto error;
}
pending_del_nr = 0;
@@ -4592,7 +4621,7 @@ out:
ret = btrfs_del_items(trans, root, path, pending_del_slot,
pending_del_nr);
if (ret)
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
}
error:
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
@@ -4633,7 +4662,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
struct extent_state *cached_state = NULL;
char *kaddr;
u32 blocksize = root->sectorsize;
- pgoff_t index = from >> PAGE_CACHE_SHIFT;
+ pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (blocksize - 1);
struct page *page;
gfp_t mask = btrfs_alloc_write_mask(mapping);
@@ -4668,7 +4697,7 @@ again:
lock_page(page);
if (page->mapping != mapping) {
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
goto again;
}
if (!PageUptodate(page)) {
@@ -4686,7 +4715,7 @@ again:
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;
@@ -4728,7 +4757,7 @@ out_unlock:
btrfs_delalloc_release_space(inode, block_start,
blocksize);
unlock_page(page);
- page_cache_release(page);
+ put_page(page);
out:
return ret;
}
@@ -4761,7 +4790,7 @@ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode,
ret = btrfs_drop_extents(trans, root, inode, offset, offset + len, 1);
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
btrfs_end_transaction(trans, root);
return ret;
}
@@ -4769,7 +4798,7 @@ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode,
ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset,
0, 0, len, 0, len, 0, 0, 0);
if (ret)
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
else
btrfs_update_inode(trans, root, inode);
btrfs_end_transaction(trans, root);
@@ -4962,7 +4991,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
* be instantly completed which will give us extents that need
* to be truncated. If we fail to get an orphan inode down we
* could have left over extents that were never meant to live,
- * so we need to garuntee from this point on that everything
+ * so we need to guarantee from this point on that everything
* will be consistent.
*/
ret = btrfs_orphan_add(trans, inode);
@@ -4996,7 +5025,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
i_size_write(inode, BTRFS_I(inode)->disk_i_size);
err = btrfs_orphan_del(trans, inode);
if (err)
- btrfs_abort_transaction(trans, root, err);
+ btrfs_abort_transaction(trans, err);
btrfs_end_transaction(trans, root);
}
}
@@ -5134,11 +5163,18 @@ void btrfs_evict_inode(struct inode *inode)
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *rsv, *global_rsv;
int steal_from_global = 0;
- u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
+ u64 min_size;
int ret;
trace_btrfs_inode_evict(inode);
+ if (!root) {
+ kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
+ return;
+ }
+
+ min_size = btrfs_calc_trunc_metadata_size(root, 1);
+
evict_inode_truncate_pages(inode);
if (inode->i_nlink &&
@@ -5232,14 +5268,14 @@ void btrfs_evict_inode(struct inode *inode)
}
/*
- * We can't just steal from the global reserve, we need tomake
+ * We can't just steal from the global reserve, we need to make
* sure there is room to do it, if not we need to commit and try
* again.
*/
if (steal_from_global) {
if (!btrfs_check_space_for_delayed_refs(trans, root))
ret = btrfs_block_rsv_migrate(global_rsv, rsv,
- min_size);
+ min_size, 0);
else
ret = -ENOSPC;
}
@@ -5733,6 +5769,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
int name_len;
int is_curr = 0; /* ctx->pos points to the current index? */
bool emitted;
+ bool put = false;
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
@@ -5750,7 +5787,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
if (key_type == BTRFS_DIR_INDEX_KEY) {
INIT_LIST_HEAD(&ins_list);
INIT_LIST_HEAD(&del_list);
- btrfs_get_delayed_items(inode, &ins_list, &del_list);
+ put = btrfs_readdir_get_delayed_items(inode, &ins_list,
+ &del_list);
}
key.type = key_type;
@@ -5897,8 +5935,8 @@ next:
nopos:
ret = 0;
err:
- if (key_type == BTRFS_DIR_INDEX_KEY)
- btrfs_put_delayed_items(&ins_list, &del_list);
+ if (put)
+ btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
btrfs_free_path(path);
return ret;
}
@@ -6213,9 +6251,9 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
btrfs_inherit_iflags(inode, dir);
if (S_ISREG(mode)) {
- if (btrfs_test_opt(root, NODATASUM))
+ if (btrfs_test_opt(root->fs_info, NODATASUM))
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
- if (btrfs_test_opt(root, NODATACOW))
+ if (btrfs_test_opt(root->fs_info, NODATACOW))
BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW |
BTRFS_INODE_NODATASUM;
}
@@ -6293,7 +6331,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
if (ret == -EEXIST || ret == -EOVERFLOW)
goto fail_dir_item;
else if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
return ret;
}
@@ -6304,7 +6342,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
current_fs_time(parent_inode->i_sb);
ret = btrfs_update_inode(trans, root, parent_inode);
if (ret)
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
return ret;
fail_dir_item:
@@ -6717,7 +6755,7 @@ static noinline int uncompress_inline(struct btrfs_path *path,
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);
@@ -6879,8 +6917,8 @@ next:
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;
@@ -6899,9 +6937,9 @@ next:
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);
@@ -6964,7 +7002,18 @@ insert:
* existing will always be non-NULL, since there must be
* extent causing the -EEXIST.
*/
- if (start >= extent_map_end(existing) ||
+ if (existing->start == em->start &&
+ extent_map_end(existing) == extent_map_end(em) &&
+ em->block_start == existing->block_start) {
+ /*
+ * these two extents are the same, it happens
+ * with inlines especially
+ */
+ free_extent_map(em);
+ em = existing;
+ err = 0;
+
+ } else if (start >= extent_map_end(existing) ||
start <= existing->start) {
/*
* The existing extent map is the one nearest to
@@ -7129,6 +7178,43 @@ out:
return em;
}
+static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
+ const u64 start,
+ const u64 len,
+ const u64 orig_start,
+ const u64 block_start,
+ const u64 block_len,
+ const u64 orig_block_len,
+ const u64 ram_bytes,
+ const int type)
+{
+ struct extent_map *em = NULL;
+ int ret;
+
+ down_read(&BTRFS_I(inode)->dio_sem);
+ if (type != BTRFS_ORDERED_NOCOW) {
+ em = create_pinned_em(inode, start, len, orig_start,
+ block_start, block_len, orig_block_len,
+ ram_bytes, type);
+ if (IS_ERR(em))
+ goto out;
+ }
+ ret = btrfs_add_ordered_extent_dio(inode, start, block_start,
+ len, block_len, type);
+ if (ret) {
+ if (em) {
+ free_extent_map(em);
+ btrfs_drop_extent_cache(inode, start,
+ start + len - 1, 0);
+ }
+ em = ERR_PTR(ret);
+ }
+ out:
+ up_read(&BTRFS_I(inode)->dio_sem);
+
+ return em;
+}
+
static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
u64 start, u64 len)
{
@@ -7144,41 +7230,13 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
if (ret)
return ERR_PTR(ret);
- /*
- * Create the ordered extent before the extent map. This is to avoid
- * races with the fast fsync path that would lead to it logging file
- * extent items that point to disk extents that were not yet written to.
- * The fast fsync path collects ordered extents into a local list and
- * then collects all the new extent maps, so we must create the ordered
- * extent first and make sure the fast fsync path collects any new
- * ordered extents after collecting new extent maps as well.
- * The fsync path simply can not rely on inode_dio_wait() because it
- * causes deadlock with AIO.
- */
- ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
- ins.offset, ins.offset, 0);
- if (ret) {
+ em = btrfs_create_dio_extent(inode, start, ins.offset, start,
+ ins.objectid, ins.offset, ins.offset,
+ ins.offset, 0);
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+ if (IS_ERR(em))
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- return ERR_PTR(ret);
- }
- em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
- ins.offset, ins.offset, ins.offset, 0);
- if (IS_ERR(em)) {
- struct btrfs_ordered_extent *oe;
-
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- oe = btrfs_lookup_ordered_extent(inode, start);
- ASSERT(oe);
- if (WARN_ON(!oe))
- return em;
- set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
- set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
- btrfs_remove_ordered_extent(inode, oe);
- /* Once for our lookup and once for the ordered extents tree. */
- btrfs_put_ordered_extent(oe);
- btrfs_put_ordered_extent(oe);
- }
return em;
}
@@ -7336,12 +7394,12 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
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();
@@ -7382,7 +7440,7 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
* include/linux/pagemap.h for details.
*/
if (unlikely(page != *pagep)) {
- page_cache_release(page);
+ put_page(page);
page = NULL;
}
}
@@ -7390,7 +7448,7 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
if (page) {
if (page->index <= end_idx)
found = true;
- page_cache_release(page);
+ put_page(page);
}
rcu_read_unlock();
@@ -7408,7 +7466,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
cached_state);
/*
* We're concerned with the entire range that we're going to be
- * doing DIO to, so we need to make sure theres no ordered
+ * doing DIO to, so we need to make sure there's no ordered
* extents in this range.
*/
ordered = btrfs_lookup_ordered_range(inode, lockstart,
@@ -7570,7 +7628,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
if (current->journal_info) {
/*
* Need to pull our outstanding extents and set journal_info to NULL so
- * that anything that needs to check if there's a transction doesn't get
+ * that anything that needs to check if there's a transaction doesn't get
* confused.
*/
dio_data = current->journal_info;
@@ -7603,7 +7661,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
* decompress it, so there will be buffering required no matter what we
* do, so go ahead and fallback to buffered.
*
- * We return -ENOTBLK because thats what makes DIO go ahead and go back
+ * We return -ENOTBLK because that's what makes DIO go ahead and go back
* to buffered IO. Don't blame me, this is the price we pay for using
* the generic code.
*/
@@ -7650,24 +7708,21 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
block_start = em->block_start + (start - em->start);
if (can_nocow_extent(inode, start, &len, &orig_start,
- &orig_block_len, &ram_bytes) == 1) {
+ &orig_block_len, &ram_bytes) == 1 &&
+ btrfs_inc_nocow_writers(root->fs_info, block_start)) {
+ struct extent_map *em2;
+
+ em2 = btrfs_create_dio_extent(inode, start, len,
+ orig_start, block_start,
+ len, orig_block_len,
+ ram_bytes, type);
+ btrfs_dec_nocow_writers(root->fs_info, block_start);
if (type == BTRFS_ORDERED_PREALLOC) {
free_extent_map(em);
- em = create_pinned_em(inode, start, len,
- orig_start,
- block_start, len,
- orig_block_len,
- ram_bytes, type);
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
- goto unlock_err;
- }
+ em = em2;
}
-
- ret = btrfs_add_ordered_extent_dio(inode, start,
- block_start, len, len, type);
- if (ret) {
- free_extent_map(em);
+ if (em2 && IS_ERR(em2)) {
+ ret = PTR_ERR(em2);
goto unlock_err;
}
goto unlock;
@@ -7746,12 +7801,12 @@ err:
}
static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
- int rw, int mirror_num)
+ int mirror_num)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
- BUG_ON(rw & REQ_WRITE);
+ BUG_ON(bio_op(bio) == REQ_OP_WRITE);
bio_get(bio);
@@ -7760,7 +7815,7 @@ static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio,
if (ret)
goto err;
- ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
+ ret = btrfs_map_bio(root, bio, mirror_num, 0);
err:
bio_put(bio);
return ret;
@@ -7811,7 +7866,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
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)
@@ -7839,13 +7894,13 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
free_io_failure(inode, failrec);
return -EIO;
}
+ bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
btrfs_debug(BTRFS_I(inode)->root->fs_info,
"Repair DIO Read Error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d\n",
read_mode, failrec->this_mirror, failrec->in_validation);
- ret = submit_dio_repair_bio(inode, bio, read_mode,
- failrec->this_mirror);
+ ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
if (ret) {
free_io_failure(inode, failrec);
bio_put(bio);
@@ -8135,7 +8190,7 @@ static void btrfs_endio_direct_write(struct bio *bio)
bio_put(bio);
}
-static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw,
+static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
struct bio *bio, int mirror_num,
unsigned long bio_flags, u64 offset)
{
@@ -8153,8 +8208,8 @@ static void btrfs_end_dio_bio(struct bio *bio)
if (err)
btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
- "direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
- btrfs_ino(dip->inode), bio->bi_rw,
+ "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d",
+ btrfs_ino(dip->inode), bio_op(bio), bio->bi_rw,
(unsigned long long)bio->bi_iter.bi_sector,
bio->bi_iter.bi_size, err);
@@ -8228,11 +8283,11 @@ static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,
}
static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
- int rw, u64 file_offset, int skip_sum,
+ u64 file_offset, int skip_sum,
int async_submit)
{
struct btrfs_dio_private *dip = bio->bi_private;
- int write = rw & REQ_WRITE;
+ bool write = bio_op(bio) == REQ_OP_WRITE;
struct btrfs_root *root = BTRFS_I(inode)->root;
int ret;
@@ -8253,8 +8308,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
if (write && async_submit) {
ret = btrfs_wq_submit_bio(root->fs_info,
- inode, rw, bio, 0, 0,
- file_offset,
+ inode, bio, 0, 0, file_offset,
__btrfs_submit_bio_start_direct_io,
__btrfs_submit_bio_done);
goto err;
@@ -8273,13 +8327,13 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
goto err;
}
map:
- ret = btrfs_map_bio(root, rw, bio, 0, async_submit);
+ ret = btrfs_map_bio(root, bio, 0, async_submit);
err:
bio_put(bio);
return ret;
}
-static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
+static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
int skip_sum)
{
struct inode *inode = dip->inode;
@@ -8298,8 +8352,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
int i;
map_length = orig_bio->bi_iter.bi_size;
- ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
- &map_length, NULL, 0);
+ ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
+ start_sector << 9, &map_length, NULL, 0);
if (ret)
return -EIO;
@@ -8319,6 +8373,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
if (!bio)
return -ENOMEM;
+ bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw);
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
@@ -8338,7 +8393,7 @@ next_block:
* before we're done setting it up
*/
atomic_inc(&dip->pending_bios);
- ret = __btrfs_submit_dio_bio(bio, inode, rw,
+ ret = __btrfs_submit_dio_bio(bio, inode,
file_offset, skip_sum,
async_submit);
if (ret) {
@@ -8356,12 +8411,13 @@ next_block:
start_sector, GFP_NOFS);
if (!bio)
goto out_err;
+ bio_set_op_attrs(bio, bio_op(orig_bio), orig_bio->bi_rw);
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
map_length = orig_bio->bi_iter.bi_size;
- ret = btrfs_map_block(root->fs_info, rw,
+ ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
start_sector << 9,
&map_length, NULL, 0);
if (ret) {
@@ -8381,7 +8437,7 @@ next_block:
}
submit:
- ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum,
+ ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
async_submit);
if (!ret)
return 0;
@@ -8401,14 +8457,14 @@ out_err:
return 0;
}
-static void btrfs_submit_direct(int rw, struct bio *dio_bio,
- struct inode *inode, loff_t file_offset)
+static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+ loff_t file_offset)
{
struct btrfs_dio_private *dip = NULL;
struct bio *io_bio = NULL;
struct btrfs_io_bio *btrfs_bio;
int skip_sum;
- int write = rw & REQ_WRITE;
+ bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
int ret = 0;
skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
@@ -8459,7 +8515,7 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
dio_data->unsubmitted_oe_range_end;
}
- ret = btrfs_submit_direct_hook(rw, dip, skip_sum);
+ ret = btrfs_submit_direct_hook(dip, skip_sum);
if (!ret)
return;
@@ -8541,13 +8597,13 @@ out:
return retval;
}
-static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
- loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_dio_data dio_data = { 0 };
+ loff_t offset = iocb->ki_pos;
size_t count = 0;
int flags = 0;
bool wakeup = true;
@@ -8607,7 +8663,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
ret = __blockdev_direct_IO(iocb, inode,
BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iter, offset, btrfs_get_blocks_direct, NULL,
+ iter, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (iov_iter_rw(iter) == WRITE) {
current->journal_info = NULL;
@@ -8719,7 +8775,7 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
if (ret == 1) {
ClearPagePrivate(page);
set_page_private(page, 0);
- page_cache_release(page);
+ put_page(page);
}
return ret;
}
@@ -8739,7 +8795,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
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;
@@ -8822,7 +8878,7 @@ 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 |
@@ -8837,7 +8893,7 @@ again:
if (PagePrivate(page)) {
ClearPagePrivate(page);
set_page_private(page, 0);
- page_cache_release(page);
+ put_page(page);
}
}
@@ -8874,11 +8930,11 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
u64 page_end;
u64 end;
- reserved_space = PAGE_CACHE_SIZE;
+ 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;
/*
@@ -8934,15 +8990,15 @@ again:
goto again;
}
- if (page->index == ((size - 1) >> PAGE_CACHE_SHIFT)) {
+ if (page->index == ((size - 1) >> PAGE_SHIFT)) {
reserved_space = round_up(size - page_start, root->sectorsize);
- if (reserved_space < PAGE_CACHE_SIZE) {
+ 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_CACHE_SIZE - reserved_space);
+ PAGE_SIZE - reserved_space);
}
}
@@ -8969,14 +9025,14 @@ again:
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);
}
@@ -9019,7 +9075,7 @@ static int btrfs_truncate(struct inode *inode)
return ret;
/*
- * Yes ladies and gentelment, this is indeed ugly. The fact is we have
+ * Yes ladies and gentlemen, this is indeed ugly. The fact is we have
* 3 things going on here
*
* 1) We need to reserve space for our orphan item and the space to
@@ -9033,15 +9089,15 @@ static int btrfs_truncate(struct inode *inode)
* space reserved in case it uses space during the truncate (thank you
* very much snapshotting).
*
- * And we need these to all be seperate. The fact is we can use alot of
+ * And we need these to all be separate. The fact is we can use a lot of
* space doing the truncate, and we have no earthly idea how much space
- * we will use, so we need the truncate reservation to be seperate so it
+ * we will use, so we need the truncate reservation to be separate so it
* doesn't end up using space reserved for updating the inode or
* removing the orphan item. We also need to be able to stop the
* transaction and start a new one, which means we need to be able to
* update the inode several times, and we have no idea of knowing how
* many times that will be, so we can't just reserve 1 item for the
- * entirety of the opration, so that has to be done seperately as well.
+ * entirety of the operation, so that has to be done separately as well.
* Then there is the orphan item, which does indeed need to be held on
* to for the whole operation, and we need nobody to touch this reserved
* space except the orphan code.
@@ -9072,7 +9128,7 @@ static int btrfs_truncate(struct inode *inode)
/* Migrate the slack space for the truncate to our reserve */
ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv, rsv,
- min_size);
+ min_size, 0);
BUG_ON(ret);
/*
@@ -9112,7 +9168,7 @@ static int btrfs_truncate(struct inode *inode)
}
ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv,
- rsv, min_size);
+ rsv, min_size, 0);
BUG_ON(ret); /* shouldn't happen */
trans->block_rsv = rsv;
}
@@ -9133,7 +9189,6 @@ static int btrfs_truncate(struct inode *inode)
ret = btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root);
}
-
out:
btrfs_free_block_rsv(root, rsv);
@@ -9230,6 +9285,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
INIT_LIST_HEAD(&ei->delalloc_inodes);
INIT_LIST_HEAD(&ei->delayed_iput);
RB_CLEAR_NODE(&ei->rb_node);
+ init_rwsem(&ei->dio_sem);
return inode;
}
@@ -9341,25 +9397,25 @@ int btrfs_init_cachep(void)
btrfs_trans_handle_cachep = kmem_cache_create("btrfs_trans_handle",
sizeof(struct btrfs_trans_handle), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL);
if (!btrfs_trans_handle_cachep)
goto fail;
btrfs_transaction_cachep = kmem_cache_create("btrfs_transaction",
sizeof(struct btrfs_transaction), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL);
if (!btrfs_transaction_cachep)
goto fail;
btrfs_path_cachep = kmem_cache_create("btrfs_path",
sizeof(struct btrfs_path), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!btrfs_path_cachep)
goto fail;
btrfs_free_space_cachep = kmem_cache_create("btrfs_free_space",
sizeof(struct btrfs_free_space), 0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!btrfs_free_space_cachep)
goto fail;
@@ -9387,10 +9443,281 @@ static int btrfs_getattr(struct vfsmount *mnt,
return 0;
}
+static int btrfs_rename_exchange(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry)
+{
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(old_dir)->root;
+ struct btrfs_root *dest = BTRFS_I(new_dir)->root;
+ struct inode *new_inode = new_dentry->d_inode;
+ struct inode *old_inode = old_dentry->d_inode;
+ struct timespec ctime = CURRENT_TIME;
+ struct dentry *parent;
+ u64 old_ino = btrfs_ino(old_inode);
+ u64 new_ino = btrfs_ino(new_inode);
+ u64 old_idx = 0;
+ u64 new_idx = 0;
+ u64 root_objectid;
+ int ret;
+ bool root_log_pinned = false;
+ bool dest_log_pinned = false;
+
+ /* we only allow rename subvolume link between subvolumes */
+ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
+ return -EXDEV;
+
+ /* close the race window with snapshot create/destroy ioctl */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&root->fs_info->subvol_sem);
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&dest->fs_info->subvol_sem);
+
+ /*
+ * We want to reserve the absolute worst case amount of items. So if
+ * both inodes are subvols and we need to unlink them then that would
+ * require 4 item modifications, but if they are both normal inodes it
+ * would require 5 item modifications, so we'll assume their normal
+ * inodes. So 5 * 2 is 10, plus 2 for the new links, so 12 total items
+ * should cover the worst case number of items we'll modify.
+ */
+ trans = btrfs_start_transaction(root, 12);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
+
+ /*
+ * We need to find a free sequence number both in the source and
+ * in the destination directory for the exchange.
+ */
+ ret = btrfs_set_inode_index(new_dir, &old_idx);
+ if (ret)
+ goto out_fail;
+ ret = btrfs_set_inode_index(old_dir, &new_idx);
+ if (ret)
+ goto out_fail;
+
+ BTRFS_I(old_inode)->dir_index = 0ULL;
+ BTRFS_I(new_inode)->dir_index = 0ULL;
+
+ /* Reference for the source. */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(root->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(root);
+ root_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, dest,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len,
+ old_ino,
+ btrfs_ino(new_dir), old_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* And now for the dest. */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(dest->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(dest);
+ dest_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, root,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len,
+ new_ino,
+ btrfs_ino(old_dir), new_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* Update inode version and ctime/mtime. */
+ inode_inc_iversion(old_dir);
+ inode_inc_iversion(new_dir);
+ inode_inc_iversion(old_inode);
+ inode_inc_iversion(new_inode);
+ old_dir->i_ctime = old_dir->i_mtime = ctime;
+ new_dir->i_ctime = new_dir->i_mtime = ctime;
+ old_inode->i_ctime = ctime;
+ new_inode->i_ctime = ctime;
+
+ if (old_dentry->d_parent != new_dentry->d_parent) {
+ btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
+ btrfs_record_unlink_dir(trans, new_dir, new_inode, 1);
+ }
+
+ /* src is a subvolume */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, root, old_dir,
+ root_objectid,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ } else { /* src is an inode */
+ ret = __btrfs_unlink_inode(trans, root, old_dir,
+ old_dentry->d_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, root, old_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_fail;
+ }
+
+ /* dest is a subvolume */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, dest, new_dir,
+ root_objectid,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ } else { /* dest is an inode */
+ ret = __btrfs_unlink_inode(trans, dest, new_dir,
+ new_dentry->d_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, dest, new_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, new_dir, old_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len, 0, old_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, old_dir, new_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len, 0, new_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_fail;
+ }
+
+ if (old_inode->i_nlink == 1)
+ BTRFS_I(old_inode)->dir_index = old_idx;
+ if (new_inode->i_nlink == 1)
+ BTRFS_I(new_inode)->dir_index = new_idx;
+
+ if (root_log_pinned) {
+ parent = new_dentry->d_parent;
+ btrfs_log_new_name(trans, old_inode, old_dir, parent);
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ parent = old_dentry->d_parent;
+ btrfs_log_new_name(trans, new_inode, new_dir, parent);
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+out_fail:
+ /*
+ * If we have pinned a log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && (root_log_pinned || dest_log_pinned)) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ if (root_log_pinned) {
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+ }
+ ret = btrfs_end_transaction(trans, root);
+out_notrans:
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&dest->fs_info->subvol_sem);
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&root->fs_info->subvol_sem);
+
+ return ret;
+}
+
+static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct inode *dir,
+ struct dentry *dentry)
+{
+ int ret;
+ struct inode *inode;
+ u64 objectid;
+ u64 index;
+
+ ret = btrfs_find_free_ino(root, &objectid);
+ if (ret)
+ return ret;
+
+ inode = btrfs_new_inode(trans, root, dir,
+ dentry->d_name.name,
+ dentry->d_name.len,
+ btrfs_ino(dir),
+ objectid,
+ S_IFCHR | WHITEOUT_MODE,
+ &index);
+
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ return ret;
+ }
+
+ inode->i_op = &btrfs_special_inode_operations;
+ init_special_inode(inode, inode->i_mode,
+ WHITEOUT_DEV);
+
+ ret = btrfs_init_inode_security(trans, inode, dir,
+ &dentry->d_name);
+ if (ret)
+ goto out;
+
+ ret = btrfs_add_nondir(trans, dir, dentry,
+ inode, 0, index);
+ if (ret)
+ goto out;
+
+ ret = btrfs_update_inode(trans, root, inode);
+out:
+ unlock_new_inode(inode);
+ if (ret)
+ inode_dec_link_count(inode);
+ iput(inode);
+
+ return ret;
+}
+
static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct btrfs_trans_handle *trans;
+ unsigned int trans_num_items;
struct btrfs_root *root = BTRFS_I(old_dir)->root;
struct btrfs_root *dest = BTRFS_I(new_dir)->root;
struct inode *new_inode = d_inode(new_dentry);
@@ -9399,6 +9726,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
u64 root_objectid;
int ret;
u64 old_ino = btrfs_ino(old_inode);
+ bool log_pinned = false;
if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
return -EPERM;
@@ -9449,15 +9777,21 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
* We want to reserve the absolute worst case amount of items. So if
* both inodes are subvols and we need to unlink them then that would
* require 4 item modifications, but if they are both normal inodes it
- * would require 5 item modifications, so we'll assume their normal
+ * would require 5 item modifications, so we'll assume they are normal
* inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items
* should cover the worst case number of items we'll modify.
+ * If our rename has the whiteout flag, we need more 5 units for the
+ * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item
+ * when selinux is enabled).
*/
- trans = btrfs_start_transaction(root, 11);
+ trans_num_items = 11;
+ if (flags & RENAME_WHITEOUT)
+ trans_num_items += 5;
+ trans = btrfs_start_transaction(root, trans_num_items);
if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- goto out_notrans;
- }
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
if (dest != root)
btrfs_record_root_in_trans(trans, dest);
@@ -9471,6 +9805,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
/* force full log commit if subvolume involved. */
btrfs_set_log_full_commit(root->fs_info, trans);
} else {
+ btrfs_pin_log_trans(root);
+ log_pinned = true;
ret = btrfs_insert_inode_ref(trans, dest,
new_dentry->d_name.name,
new_dentry->d_name.len,
@@ -9478,14 +9814,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
btrfs_ino(new_dir), index);
if (ret)
goto out_fail;
- /*
- * this is an ugly little race, but the rename is required
- * to make sure that if we crash, the inode is either at the
- * old name or the new one. pinning the log transaction lets
- * us make sure we don't allow a log commit to come in after
- * we unlink the name but before we add the new name back in.
- */
- btrfs_pin_log_trans(root);
}
inode_inc_iversion(old_dir);
@@ -9512,7 +9840,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
ret = btrfs_update_inode(trans, root, old_inode);
}
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out_fail;
}
@@ -9536,7 +9864,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (!ret && new_inode->i_nlink == 0)
ret = btrfs_orphan_add(trans, d_inode(new_dentry));
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out_fail;
}
}
@@ -9545,19 +9873,53 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
new_dentry->d_name.name,
new_dentry->d_name.len, 0, index);
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
goto out_fail;
}
if (old_inode->i_nlink == 1)
BTRFS_I(old_inode)->dir_index = index;
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+ if (log_pinned) {
struct dentry *parent = new_dentry->d_parent;
+
btrfs_log_new_name(trans, old_inode, old_dir, parent);
btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
+
+ if (flags & RENAME_WHITEOUT) {
+ ret = btrfs_whiteout_for_rename(trans, root, old_dir,
+ old_dentry);
+
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_fail;
+ }
}
out_fail:
+ /*
+ * If we have pinned the log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && log_pinned) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
btrfs_end_transaction(trans, root);
out_notrans:
if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
@@ -9570,10 +9932,14 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
- if (flags & ~RENAME_NOREPLACE)
+ if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
- return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry);
+ if (flags & RENAME_EXCHANGE)
+ return btrfs_rename_exchange(old_dir, old_dentry, new_dir,
+ new_dentry);
+
+ return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
static void btrfs_run_delalloc_work(struct btrfs_work *work)
@@ -9942,6 +10308,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
btrfs_end_transaction(trans, root);
break;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
last_alloc = ins.offset;
ret = insert_reserved_file_extent(trans, inode,
@@ -9952,7 +10319,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
if (ret) {
btrfs_free_reserved_extent(root, ins.objectid,
ins.offset, 0);
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
if (own_trans)
btrfs_end_transaction(trans, root);
break;
@@ -10012,7 +10379,7 @@ next:
ret = btrfs_update_inode(trans, root, inode);
if (ret) {
- btrfs_abort_transaction(trans, root, ret);
+ btrfs_abort_transaction(trans, ret);
if (own_trans)
btrfs_end_transaction(trans, root);
break;
@@ -10160,10 +10527,10 @@ static const struct inode_operations btrfs_dir_inode_operations = {
.symlink = btrfs_symlink,
.setattr = btrfs_setattr,
.mknod = btrfs_mknod,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = btrfs_permission,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
@@ -10181,10 +10548,10 @@ static const struct inode_operations btrfs_dir_ro_inode_operations = {
static const struct file_operations btrfs_dir_file_operations = {
.llseek = generic_file_llseek,
.read = generic_read_dir,
- .iterate = btrfs_real_readdir,
+ .iterate_shared = btrfs_real_readdir,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
- .compat_ioctl = btrfs_ioctl,
+ .compat_ioctl = btrfs_compat_ioctl,
#endif
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
@@ -10237,10 +10604,10 @@ static const struct address_space_operations btrfs_symlink_aops = {
static const struct inode_operations btrfs_file_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.permission = btrfs_permission,
.fiemap = btrfs_fiemap,
.get_acl = btrfs_get_acl,
@@ -10251,10 +10618,10 @@ static const struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = btrfs_get_acl,
.set_acl = btrfs_set_acl,
.update_time = btrfs_update_time,
@@ -10265,10 +10632,10 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
- .setxattr = btrfs_setxattr,
+ .setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = btrfs_listxattr,
- .removexattr = btrfs_removexattr,
+ .removexattr = generic_removexattr,
.update_time = btrfs_update_time,
};
Powered by cgit, Gruvboxed by Blaster4385.