* [PATCH V16 01/18] Btrfs: subpage-blocksize: Fix whole page read.
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 02/18] Btrfs: subpage-blocksize: Fix whole page write Chandan Rajendra
` (17 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
For the subpage-blocksize scenario, a page can contain multiple
blocks. In such cases, this patch handles reading data from files.
To track the status of individual blocks of a page, this patch makes use
of a bitmap pointed to by the newly introduced per-page 'struct
btrfs_page_private'.
The per-page btrfs_page_private->io_lock plays the same role as
BH_Uptodate_Lock (see end_buffer_async_read()) i.e. without the io_lock
we may end up in the following situation,
NOTE: Assume 64k page size and 4k block size. Also assume that the first
12 blocks of the page are contiguous while the next 4 blocks are
contiguous. When reading the page we end up submitting two "logical
address space" bios. So end_bio_extent_readpage function is invoked
twice, once for each bio.
|-------------------------+-------------------------+-------------|
| Task A | Task B | Task C |
|-------------------------+-------------------------+-------------|
| end_bio_extent_readpage | | |
| process block 0 | | |
| - clear BLK_STATE_IO | | |
| - page_read_complete | | |
| process block 1 | | |
| | | |
| | | |
| | end_bio_extent_readpage | |
| | process block 0 | |
| | - clear BLK_STATE_IO | |
| | - page_read_complete | |
| | process block 1 | |
| | | |
| process block 11 | process block 3 | |
| - clear BLK_STATE_IO | - clear BLK_STATE_IO | |
| - page_read_complete | - page_read_complete | |
| - returns true | - returns true | |
| - unlock_page() | | |
| | | lock_page() |
| | - unlock_page() | |
|-------------------------+-------------------------+-------------|
We end up incorrectly unlocking the page twice and "Task C" ends up
working on an unlocked page. So private->io_lock makes sure that only
one of the tasks gets "true" as the return value when page_io_complete()
is invoked. As an optimization the patch gets the io_lock only when the
last block of the bio_vec is being processed.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/extent_io.c | 321 +++++++++++++++++++++++++++++++++------------------
fs/btrfs/extent_io.h | 71 +++++++++++-
fs/btrfs/inode.c | 13 +--
3 files changed, 280 insertions(+), 125 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d247fc0..1a9ce2c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1321,6 +1321,95 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
changeset);
}
+static int modify_page_blks_state(struct page *page,
+ unsigned long blk_states,
+ u64 start, u64 end, int set)
+{
+ struct inode *inode = page->mapping->host;
+ unsigned long *bitmap;
+ unsigned long first_state;
+ unsigned long state;
+ u64 nr_blks;
+ u64 blk;
+
+ BUG_ON(!PagePrivate(page));
+
+ bitmap = ((struct btrfs_page_private *)page->private)->bstate;
+
+ blk = BTRFS_BYTES_TO_BLKS(BTRFS_I(inode)->root->fs_info,
+ start & (PAGE_SIZE - 1));
+ nr_blks = BTRFS_BYTES_TO_BLKS(BTRFS_I(inode)->root->fs_info,
+ (end - start + 1));
+
+ first_state = find_next_bit(&blk_states, BLK_NR_STATE, 0);
+
+ while (nr_blks--) {
+ state = first_state;
+
+ while (state < BLK_NR_STATE) {
+ if (set)
+ set_bit((blk * BLK_NR_STATE) + state, bitmap);
+ else
+ clear_bit((blk * BLK_NR_STATE) + state, bitmap);
+
+ state = find_next_bit(&blk_states, BLK_NR_STATE,
+ state + 1);
+ }
+
+ ++blk;
+ }
+
+ return 0;
+}
+
+int set_page_blks_state(struct page *page, unsigned long blk_states,
+ u64 start, u64 end)
+{
+ return modify_page_blks_state(page, blk_states, start, end, 1);
+}
+
+int clear_page_blks_state(struct page *page, unsigned long blk_states,
+ u64 start, u64 end)
+{
+ return modify_page_blks_state(page, blk_states, start, end, 0);
+}
+
+int test_page_blks_state(struct page *page, enum blk_state blk_state,
+ u64 start, u64 end, int check_all)
+{
+ struct inode *inode = page->mapping->host;
+ unsigned long *bitmap;
+ unsigned long blk;
+ u64 nr_blks;
+ int found = 0;
+
+ BUG_ON(!PagePrivate(page));
+
+ bitmap = ((struct btrfs_page_private *)page->private)->bstate;
+
+ blk = BTRFS_BYTES_TO_BLKS(BTRFS_I(inode)->root->fs_info,
+ start & (PAGE_SIZE - 1));
+ nr_blks = BTRFS_BYTES_TO_BLKS(BTRFS_I(inode)->root->fs_info,
+ (end - start + 1));
+
+ while (nr_blks--) {
+ if (test_bit((blk * BLK_NR_STATE) + blk_state, bitmap)) {
+ if (!check_all)
+ return 1;
+ found = 1;
+ } else if (check_all) {
+ return 0;
+ }
+
+ ++blk;
+ }
+
+ if (!check_all && !found)
+ return 0;
+
+ return 1;
+}
+
/*
* either insert or lock state struct between start and end use mask to tell
* us if waiting is desired.
@@ -1958,14 +2047,22 @@ int test_range_bit(struct extent_io_tree *tree, u64 start, u64 end,
* helper function to set a given page up to date if all the
* extents in the tree for that page are up to date
*/
-static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
+static void check_page_uptodate(struct page *page)
{
u64 start = page_offset(page);
u64 end = start + PAGE_SIZE - 1;
- if (test_range_bit(tree, start, end, EXTENT_UPTODATE, 1, NULL))
+ if (test_page_blks_state(page, BLK_STATE_UPTODATE, start, end, 1))
SetPageUptodate(page);
}
+static int page_io_complete(struct page *page)
+{
+ u64 start = page_offset(page);
+ u64 end = start + PAGE_SIZE - 1;
+
+ return !test_page_blks_state(page, BLK_STATE_IO, start, end, 0);
+}
+
int free_io_failure(struct inode *inode, struct io_failure_record *rec)
{
int ret;
@@ -2282,7 +2379,9 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
* a) deliver good data to the caller
* b) correct the bad sectors on disk
*/
- if (failed_bio->bi_vcnt > 1) {
+ if ((failed_bio->bi_vcnt > 1)
+ || (failed_bio->bi_io_vec->bv_len
+ > BTRFS_I(inode)->root->sectorsize)) {
/*
* to fulfill b), we need to know the exact failing sectors, as
* we don't want to rewrite any more than the failed ones. thus,
@@ -2488,18 +2587,6 @@ static void end_bio_extent_writepage(struct bio *bio)
bio_put(bio);
}
-static void
-endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len,
- int uptodate)
-{
- struct extent_state *cached = NULL;
- u64 end = start + len - 1;
-
- if (uptodate && tree->track_uptodate)
- set_extent_uptodate(tree, start, end, &cached, GFP_ATOMIC);
- unlock_extent_cached(tree, start, end, &cached, GFP_ATOMIC);
-}
-
/*
* after a readpage IO is done, we need to:
* clear the uptodate bits on error
@@ -2516,67 +2603,50 @@ static void end_bio_extent_readpage(struct bio *bio)
struct bio_vec *bvec;
int uptodate = !bio->bi_error;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+ struct extent_state *cached = NULL;
+ struct btrfs_page_private *pg_private;
struct extent_io_tree *tree;
+ unsigned long flags;
u64 offset = 0;
u64 start;
u64 end;
- u64 len;
- u64 extent_start = 0;
- u64 extent_len = 0;
+ int nr_sectors;
int mirror;
+ int unlock;
int ret;
int i;
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
struct inode *inode = page->mapping->host;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
"mirror=%u\n", (u64)bio->bi_iter.bi_sector,
bio->bi_error, io_bio->mirror_num);
tree = &BTRFS_I(inode)->io_tree;
- /* We always issue full-page reads, but if some block
- * in a page fails to read, blk_update_request() will
- * advance bv_offset and adjust bv_len to compensate.
- * Print a warning for nonzero offsets, and an error
- * if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) {
- if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE)
- btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
- "partial page read in btrfs with offset %u and length %u",
- bvec->bv_offset, bvec->bv_len);
- else
- btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
- "incomplete page read in btrfs with offset %u and "
- "length %u",
- bvec->bv_offset, bvec->bv_len);
- }
-
- start = page_offset(page);
- end = start + bvec->bv_offset + bvec->bv_len - 1;
- len = bvec->bv_len;
-
+ start = page_offset(page) + bvec->bv_offset;
+ end = start + bvec->bv_len - 1;
+ nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ bvec->bv_len);
mirror = io_bio->mirror_num;
+
+next_block:
if (likely(uptodate && tree->ops &&
- tree->ops->readpage_end_io_hook)) {
+ tree->ops->readpage_end_io_hook)) {
ret = tree->ops->readpage_end_io_hook(io_bio, offset,
- page, start, end,
- mirror);
+ page, start,
+ start + root->sectorsize - 1,
+ mirror);
if (ret)
uptodate = 0;
else
- clean_io_failure(inode, start, page, 0);
+ clean_io_failure(inode, start, page,
+ start - page_offset(page));
}
- if (likely(uptodate))
- goto readpage_ok;
-
- if (tree->ops && tree->ops->readpage_io_failed_hook) {
- ret = tree->ops->readpage_io_failed_hook(page, mirror);
- if (!ret && !bio->bi_error)
- uptodate = 1;
- } else {
+ if (!uptodate) {
/*
* The generic bio_readpage_error handles errors the
* following way: If possible, new read requests are
@@ -2587,58 +2657,61 @@ static void end_bio_extent_readpage(struct bio *bio)
* can't handle the error it will return -EIO and we
* remain responsible for that page.
*/
- ret = bio_readpage_error(bio, offset, page, start, end,
- mirror);
+ ret = bio_readpage_error(bio, offset, page,
+ start, start + root->sectorsize - 1,
+ mirror);
if (ret == 0) {
uptodate = !bio->bi_error;
- offset += len;
- continue;
+ offset += root->sectorsize;
+ if (--nr_sectors) {
+ start += root->sectorsize;
+ goto next_block;
+ } else {
+ continue;
+ }
}
}
-readpage_ok:
- if (likely(uptodate)) {
- loff_t i_size = i_size_read(inode);
- pgoff_t end_index = i_size >> PAGE_SHIFT;
- unsigned off;
-
- /* Zero out the end if this page straddles i_size */
- off = i_size & (PAGE_SIZE-1);
- if (page->index == end_index && off)
- zero_user_segment(page, off, PAGE_SIZE);
- SetPageUptodate(page);
+
+ if (uptodate) {
+ set_page_blks_state(page, 1 << BLK_STATE_UPTODATE, start,
+ start + root->sectorsize - 1);
+ check_page_uptodate(page);
} else {
ClearPageUptodate(page);
SetPageError(page);
}
- unlock_page(page);
- offset += len;
-
- if (unlikely(!uptodate)) {
- if (extent_len) {
- endio_readpage_release_extent(tree,
- extent_start,
- extent_len, 1);
- extent_start = 0;
- extent_len = 0;
- }
- endio_readpage_release_extent(tree, start,
- end - start + 1, 0);
- } else if (!extent_len) {
- extent_start = start;
- extent_len = end + 1 - start;
- } else if (extent_start + extent_len == start) {
- extent_len += end + 1 - start;
- } else {
- endio_readpage_release_extent(tree, extent_start,
- extent_len, uptodate);
- extent_start = start;
- extent_len = end + 1 - start;
+
+ offset += root->sectorsize;
+
+ if (--nr_sectors) {
+ clear_page_blks_state(page, 1 << BLK_STATE_IO,
+ start, start + root->sectorsize - 1);
+ clear_extent_bit(tree, start, start + root->sectorsize - 1,
+ EXTENT_LOCKED, 1, 0, &cached, GFP_ATOMIC);
+ start += root->sectorsize;
+ goto next_block;
}
+
+ WARN_ON(!PagePrivate(page));
+
+ pg_private = (struct btrfs_page_private *)page->private;
+
+ spin_lock_irqsave(&pg_private->io_lock, flags);
+
+ clear_page_blks_state(page, 1 << BLK_STATE_IO,
+ start, start + root->sectorsize - 1);
+
+ unlock = page_io_complete(page);
+
+ spin_unlock_irqrestore(&pg_private->io_lock, flags);
+
+ clear_extent_bit(tree, start, start + root->sectorsize - 1,
+ EXTENT_LOCKED, 1, 0, &cached, GFP_ATOMIC);
+
+ if (unlock)
+ unlock_page(page);
}
- if (extent_len)
- endio_readpage_release_extent(tree, extent_start, extent_len,
- uptodate);
if (io_bio->end_io)
io_bio->end_io(io_bio, bio->bi_error);
bio_put(bio);
@@ -2828,13 +2901,36 @@ static void attach_extent_buffer_page(struct extent_buffer *eb,
}
}
-void set_page_extent_mapped(struct page *page)
+int set_page_extent_mapped(struct page *page)
{
+ struct btrfs_page_private *pg_private;
+
if (!PagePrivate(page)) {
+ pg_private = kzalloc(sizeof(*pg_private), GFP_NOFS);
+ if (!pg_private)
+ return -ENOMEM;
+
+ spin_lock_init(&pg_private->io_lock);
+
SetPagePrivate(page);
+
get_page(page);
- set_page_private(page, EXTENT_PAGE_PRIVATE);
+ set_page_private(page, (unsigned long)pg_private);
}
+
+ return 0;
+}
+
+int clear_page_extent_mapped(struct page *page)
+{
+ if (PagePrivate(page)) {
+ kfree((struct btrfs_page_private *)(page->private));
+ ClearPagePrivate(page);
+ set_page_private(page, 0);
+ put_page(page);
+ }
+
+ return 0;
}
static struct extent_map *
@@ -2901,13 +2997,6 @@ static int __do_readpage(struct extent_io_tree *tree,
set_page_extent_mapped(page);
end = page_end;
- if (!PageUptodate(page)) {
- if (cleancache_get_page(page) == 0) {
- BUG_ON(blocksize != PAGE_SIZE);
- unlock_extent(tree, start, end);
- goto out;
- }
- }
if (page->index == last_byte >> PAGE_SHIFT) {
char *userpage;
@@ -2927,18 +3016,17 @@ static int __do_readpage(struct extent_io_tree *tree,
if (cur >= last_byte) {
char *userpage;
- struct extent_state *cached = NULL;
iosize = PAGE_SIZE - pg_offset;
userpage = kmap_atomic(page);
memset(userpage + pg_offset, 0, iosize);
flush_dcache_page(page);
kunmap_atomic(userpage);
- set_extent_uptodate(tree, cur, cur + iosize - 1,
- &cached, GFP_NOFS);
+ set_page_blks_state(page, 1 << BLK_STATE_UPTODATE, cur,
+ cur + iosize - 1);
unlock_extent_cached(tree, cur,
cur + iosize - 1,
- &cached, GFP_NOFS);
+ NULL, GFP_NOFS);
break;
}
em = __get_extent_map(inode, page, pg_offset, cur,
@@ -2973,6 +3061,13 @@ static int __do_readpage(struct extent_io_tree *tree,
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
block_start = EXTENT_MAP_HOLE;
+ if ((block_start != EXTENT_MAP_HOLE) &&
+ (blocksize == PAGE_SIZE) && !PageUptodate(page) &&
+ (cleancache_get_page(page) == 0)) {
+ unlock_extent(tree, cur, end);
+ break;
+ }
+
/*
* If we have a file range that points to a compressed extent
* and it's followed by a consecutive file range that points to
@@ -3028,8 +3123,8 @@ static int __do_readpage(struct extent_io_tree *tree,
flush_dcache_page(page);
kunmap_atomic(userpage);
- set_extent_uptodate(tree, cur, cur + iosize - 1,
- &cached, GFP_NOFS);
+ set_page_blks_state(page, 1 << BLK_STATE_UPTODATE, cur,
+ cur + iosize - 1);
unlock_extent_cached(tree, cur,
cur + iosize - 1,
&cached, GFP_NOFS);
@@ -3038,9 +3133,9 @@ static int __do_readpage(struct extent_io_tree *tree,
continue;
}
/* the get_extent function already copied into the page */
- if (test_range_bit(tree, cur, cur_end,
- EXTENT_UPTODATE, 1, NULL)) {
- check_page_uptodate(tree, page);
+ if (test_page_blks_state(page, BLK_STATE_UPTODATE, cur,
+ cur_end, 1)) {
+ check_page_uptodate(page);
unlock_extent(tree, cur, cur + iosize - 1);
cur = cur + iosize;
pg_offset += iosize;
@@ -3058,6 +3153,8 @@ static int __do_readpage(struct extent_io_tree *tree,
}
pnr -= page->index;
+ set_page_blks_state(page, 1 << BLK_STATE_IO, cur,
+ cur + iosize - 1);
ret = submit_extent_page(rw, tree, NULL, page,
sector, disk_io_size, pg_offset,
bdev, bio, pnr,
@@ -3070,12 +3167,14 @@ static int __do_readpage(struct extent_io_tree *tree,
*bio_flags = this_bio_flag;
} else {
SetPageError(page);
+ clear_page_blks_state(page, 1 << BLK_STATE_IO, cur,
+ cur + iosize - 1);
unlock_extent(tree, cur, cur + iosize - 1);
}
cur = cur + iosize;
pg_offset += iosize;
}
-out:
+
if (!nr) {
if (!PageError(page))
SetPageUptodate(page);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index b5e0ade..026befc 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -52,11 +52,64 @@
#define PAGE_SET_PRIVATE2 (1 << 4)
#define PAGE_SET_ERROR (1 << 5)
+enum blk_state {
+ BLK_STATE_UPTODATE,
+ BLK_STATE_DIRTY,
+ BLK_STATE_IO,
+ BLK_NR_STATE,
+};
+
/*
- * page->private values. Every page that is controlled by the extent
- * map has page->private set to one.
- */
-#define EXTENT_PAGE_PRIVATE 1
+ The maximum number of blocks per page (i.e. 32) occurs when using 2k
+ as the block size and having 64k as the page size.
+*/
+#define BLK_STATE_NR_LONGS DIV_ROUND_UP(BLK_NR_STATE * 32, BITS_PER_LONG)
+
+/*
+ btrfs_page_private->io_lock plays the same role as BH_Uptodate_Lock
+ (see end_buffer_async_read()) i.e. without the io_lock we may end up
+ in the following situation,
+
+ NOTE: Assume 64k page size and 4k block size. Also assume that the first 12
+ blocks of the page are contiguous while the next 4 blocks are contiguous. When
+ reading the page we end up submitting two "logical address space" bios. So
+ end_bio_extent_readpage function is invoked twice, once for each bio.
+
+ |-------------------------+-------------------------+-------------|
+ | Task A | Task B | Task C |
+ |-------------------------+-------------------------+-------------|
+ | end_bio_extent_readpage | | |
+ | process block 0 | | |
+ | - clear BLK_STATE_IO | | |
+ | - page_read_complete | | |
+ | process block 1 | | |
+ | | | |
+ | | | |
+ | | end_bio_extent_readpage | |
+ | | process block 0 | |
+ | | - clear BLK_STATE_IO | |
+ | | - page_read_complete | |
+ | | process block 1 | |
+ | | | |
+ | process block 11 | process block 3 | |
+ | - clear BLK_STATE_IO | - clear BLK_STATE_IO | |
+ | - page_read_complete | - page_read_complete | |
+ | - returns true | - returns true | |
+ | - unlock_page() | | |
+ | | | lock_page() |
+ | | - unlock_page() | |
+ |-------------------------+-------------------------+-------------|
+
+ We end up incorrectly unlocking the page twice and "Task C" ends up
+ working on an unlocked page. So private->io_lock makes sure that
+ only one of the tasks gets "true" as the return value when
+ page_io_complete() is invoked. As an optimization the patch gets the
+ io_lock only when the last block of the bio_vec is being processed.
+*/
+struct btrfs_page_private {
+ spinlock_t io_lock;
+ unsigned long bstate[BLK_STATE_NR_LONGS];
+};
struct extent_state;
struct btrfs_root;
@@ -342,8 +395,14 @@ int extent_readpages(struct extent_io_tree *tree,
get_extent_t get_extent);
int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len, get_extent_t *get_extent);
-void set_page_extent_mapped(struct page *page);
-
+int set_page_extent_mapped(struct page *page);
+int clear_page_extent_mapped(struct page *page);
+int set_page_blks_state(struct page *page, unsigned long blk_states,
+ u64 start, u64 end);
+int clear_page_blks_state(struct page *page, unsigned long blk_states,
+ u64 start, u64 end);
+int test_page_blks_state(struct page *page, enum blk_state blk_state,
+ u64 start, u64 end, int check_all);
struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2aaba58..768ca2c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6750,7 +6750,6 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
struct btrfs_key found_key;
struct extent_map *em = NULL;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
- struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_trans_handle *trans = NULL;
const bool new_inline = !page || create;
@@ -6927,8 +6926,8 @@ next:
kunmap(page);
btrfs_mark_buffer_dirty(leaf);
}
- set_extent_uptodate(io_tree, em->start,
- extent_map_end(em) - 1, NULL, GFP_NOFS);
+ set_page_blks_state(page, 1 << BLK_STATE_UPTODATE, em->start,
+ extent_map_end(em) - 1);
goto insert;
}
not_found:
@@ -8716,11 +8715,9 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
tree = &BTRFS_I(page->mapping->host)->io_tree;
map = &BTRFS_I(page->mapping->host)->extent_tree;
ret = try_release_extent_mapping(map, tree, page, gfp_flags);
- if (ret == 1) {
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
- }
+ if (ret == 1)
+ clear_page_extent_mapped(page);
+
return ret;
}
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 02/18] Btrfs: subpage-blocksize: Fix whole page write
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 01/18] Btrfs: subpage-blocksize: Fix whole page read Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 03/18] Btrfs: subpage-blocksize: Make sure delalloc range intersects with the locked page's range Chandan Rajendra
` (16 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
For the subpage-blocksize scenario, a page can contain multiple
blocks. In such cases, this patch handles writing data to files.
Also, When setting EXTENT_DELALLOC, we no longer set EXTENT_UPTODATE bit on
the extent_io_tree since uptodate status is being tracked by the bitmap
pointed to by page->private.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/extent_io.c | 129 +++++++++++++++++++++-----------------------------
fs/btrfs/file.c | 16 +++++++
fs/btrfs/inode.c | 64 ++++++++++++++++++++-----
fs/btrfs/relocation.c | 3 ++
4 files changed, 125 insertions(+), 87 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1a9ce2c..9b6c8e0 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1481,24 +1481,6 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
}
}
-/*
- * helper function to set both pages and extents in the tree writeback
- */
-static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
-{
- unsigned long index = start >> PAGE_SHIFT;
- unsigned long end_index = end >> PAGE_SHIFT;
- struct page *page;
-
- while (index <= end_index) {
- page = find_get_page(tree->mapping, index);
- BUG_ON(!page); /* Pages should be in the extent_io_tree */
- set_page_writeback(page);
- put_page(page);
- index++;
- }
-}
-
/* find the first state struct with 'bits' set after 'start', and
* return it. tree->lock must be held. NULL will returned if
* nothing was found after 'start'
@@ -2552,36 +2534,34 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
*/
static void end_bio_extent_writepage(struct bio *bio)
{
+ struct btrfs_page_private *pg_private;
struct bio_vec *bvec;
+ unsigned long flags;
u64 start;
u64 end;
+ int clear_writeback;
int i;
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- /* We always issue full-page reads, but if some block
- * in a page fails to read, blk_update_request() will
- * advance bv_offset and adjust bv_len to compensate.
- * Print a warning for nonzero offsets, and an error
- * if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_SIZE) {
- if (bvec->bv_offset + bvec->bv_len != PAGE_SIZE)
- btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
- "partial page write in btrfs with offset %u and length %u",
- bvec->bv_offset, bvec->bv_len);
- else
- btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
- "incomplete page write in btrfs with offset %u and "
- "length %u",
- bvec->bv_offset, bvec->bv_len);
- }
+ start = page_offset(page) + bvec->bv_offset;
+ end = start + bvec->bv_len - 1;
+
+ pg_private = (struct btrfs_page_private *)page->private;
- start = page_offset(page);
- end = start + bvec->bv_offset + bvec->bv_len - 1;
+ spin_lock_irqsave(&pg_private->io_lock, flags);
end_extent_writepage(page, bio->bi_error, start, end);
- end_page_writeback(page);
+
+ clear_page_blks_state(page, 1 << BLK_STATE_IO, start, end);
+
+ clear_writeback = page_io_complete(page);
+
+ spin_unlock_irqrestore(&pg_private->io_lock, flags);
+
+ if (clear_writeback)
+ end_page_writeback(page);
}
bio_put(bio);
@@ -3423,10 +3403,9 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
u64 block_start;
u64 iosize;
sector_t sector;
- struct extent_state *cached_state = NULL;
struct extent_map *em;
struct block_device *bdev;
- size_t pg_offset = 0;
+ size_t pg_offset;
size_t blocksize;
int ret = 0;
int nr = 0;
@@ -3473,20 +3452,29 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
page_end, NULL, 1);
break;
}
- em = epd->get_extent(inode, page, pg_offset, cur,
- end - cur + 1, 1);
+
+ if (!test_page_blks_state(page, BLK_STATE_DIRTY, cur,
+ cur + blocksize - 1, 1)) {
+ cur += blocksize;
+ continue;
+ }
+
+ pg_offset = cur & (PAGE_SIZE - 1);
+
+ em = epd->get_extent(inode, page, pg_offset, cur, blocksize, 1);
if (IS_ERR_OR_NULL(em)) {
SetPageError(page);
ret = PTR_ERR_OR_ZERO(em);
break;
}
- extent_offset = cur - em->start;
em_end = extent_map_end(em);
BUG_ON(em_end <= cur);
BUG_ON(end < cur);
- iosize = min(em_end - cur, end - cur + 1);
- iosize = ALIGN(iosize, blocksize);
+
+ iosize = blocksize;
+
+ extent_offset = cur - em->start;
sector = (em->block_start + extent_offset) >> 9;
bdev = em->bdev;
block_start = em->block_start;
@@ -3494,32 +3482,20 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
free_extent_map(em);
em = NULL;
- /*
- * compressed and inline extents are written through other
- * paths in the FS
- */
- if (compressed || block_start == EXTENT_MAP_HOLE ||
- block_start == EXTENT_MAP_INLINE) {
- /*
- * end_io notification does not happen here for
- * compressed extents
- */
- if (!compressed && tree->ops &&
- tree->ops->writepage_end_io_hook)
- tree->ops->writepage_end_io_hook(page, cur,
- cur + iosize - 1,
- NULL, 1);
- else if (compressed) {
- /* we don't want to end_page_writeback on
- * a compressed extent. this happens
- * elsewhere
- */
- nr++;
- }
+ BUG_ON(compressed);
+ BUG_ON(block_start == EXTENT_MAP_INLINE);
- cur += iosize;
- pg_offset += iosize;
- continue;
+ if (block_start == EXTENT_MAP_HOLE) {
+ if (test_page_blks_state(page, BLK_STATE_UPTODATE, cur,
+ cur + iosize - 1, 1)) {
+ clear_page_blks_state(page,
+ 1 << BLK_STATE_DIRTY, cur,
+ cur + iosize - 1);
+ cur += iosize;
+ continue;
+ } else {
+ BUG();
+ }
}
if (tree->ops && tree->ops->writepage_io_hook) {
@@ -3533,7 +3509,13 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
} else {
unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1;
- set_range_writeback(tree, cur, cur + iosize - 1);
+ clear_page_blks_state(page, 1 << BLK_STATE_DIRTY, cur,
+ cur + iosize - 1);
+ set_page_writeback(page);
+
+ set_page_blks_state(page, 1 << BLK_STATE_IO, cur,
+ cur + iosize - 1);
+
if (!PageWriteback(page)) {
btrfs_err(BTRFS_I(inode)->root->fs_info,
"page %lu not writeback, cur %llu end %llu",
@@ -3548,17 +3530,14 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
if (ret)
SetPageError(page);
}
- cur = cur + iosize;
- pg_offset += iosize;
+
+ cur += iosize;
nr++;
}
done:
*nr_ret = nr;
done_unlocked:
-
- /* drop our reference on any cached states */
- free_extent_state(cached_state);
return ret;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 8d7b5a4..e2f0968 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -495,6 +495,9 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
u64 num_bytes;
u64 start_pos;
u64 end_of_last_block;
+ u64 start;
+ u64 end;
+ u64 page_end;
u64 end_pos = pos + write_bytes;
loff_t isize = i_size_read(inode);
@@ -507,11 +510,24 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
if (err)
return err;
+ start = start_pos;
+
for (i = 0; i < num_pages; i++) {
struct page *p = pages[i];
SetPageUptodate(p);
ClearPageChecked(p);
+
+ end = page_end = page_offset(p) + PAGE_SIZE - 1;
+
+ if (i == num_pages - 1)
+ end = min_t(u64, page_end, end_of_last_block);
+
+ set_page_blks_state(p,
+ 1 << BLK_STATE_DIRTY | 1 << BLK_STATE_UPTODATE,
+ start, end);
set_page_dirty(p);
+
+ start = page_end + 1;
}
/*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 768ca2c..c333099 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -210,6 +210,9 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
page = find_get_page(inode->i_mapping,
start >> PAGE_SHIFT);
btrfs_set_file_extent_compression(leaf, ei, 0);
+ clear_page_blks_state(page, 1 << BLK_STATE_DIRTY, start,
+ round_up(start + size - 1, root->sectorsize)
+ - 1);
kaddr = kmap_atomic(page);
offset = start & (PAGE_SIZE - 1);
write_extent_buffer(leaf, kaddr + offset, ptr, size);
@@ -2023,6 +2026,11 @@ again:
}
btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state);
+
+ set_page_blks_state(page,
+ 1 << BLK_STATE_DIRTY | 1 << BLK_STATE_UPTODATE,
+ page_start, page_end);
+
ClearPageChecked(page);
set_page_dirty(page);
out:
@@ -3025,26 +3033,48 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
struct btrfs_ordered_extent *ordered_extent = NULL;
struct btrfs_workqueue *wq;
btrfs_work_func_t func;
+ u64 ordered_start, ordered_end;
+ int done;
trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
ClearPagePrivate2(page);
- if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
- end - start + 1, uptodate))
- return 0;
+loop:
+ ordered_extent = btrfs_lookup_ordered_range(inode, start,
+ end - start + 1);
+ if (!ordered_extent)
+ goto out;
- if (btrfs_is_free_space_inode(inode)) {
- wq = root->fs_info->endio_freespace_worker;
- func = btrfs_freespace_write_helper;
- } else {
- wq = root->fs_info->endio_write_workers;
- func = btrfs_endio_write_helper;
+ ordered_start = max_t(u64, start, ordered_extent->file_offset);
+ ordered_end = min_t(u64, end,
+ ordered_extent->file_offset + ordered_extent->len - 1);
+
+ done = btrfs_dec_test_ordered_pending(inode, &ordered_extent,
+ ordered_start,
+ ordered_end - ordered_start + 1,
+ uptodate);
+ if (done) {
+ if (btrfs_is_free_space_inode(inode)) {
+ wq = root->fs_info->endio_freespace_worker;
+ func = btrfs_freespace_write_helper;
+ } else {
+ wq = root->fs_info->endio_write_workers;
+ func = btrfs_endio_write_helper;
+ }
+
+ btrfs_init_work(&ordered_extent->work, func,
+ finish_ordered_fn, NULL, NULL);
+ btrfs_queue_work(wq, &ordered_extent->work);
}
- btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
- NULL);
- btrfs_queue_work(wq, &ordered_extent->work);
+ btrfs_put_ordered_extent(ordered_extent);
+
+ start = ordered_end + 1;
+
+ if (start < end)
+ goto loop;
+out:
return 0;
}
@@ -4705,6 +4735,9 @@ again:
goto out_unlock;
}
+ set_page_blks_state(page, 1 << BLK_STATE_DIRTY | 1 << BLK_STATE_UPTODATE,
+ block_start, block_end);
+
if (offset != blocksize) {
if (!len)
len = blocksize - offset;
@@ -8820,6 +8853,9 @@ again:
* This means the reserved space should be freed here.
*/
btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+
+ clear_page_blks_state(page, 1 << BLK_STATE_DIRTY, page_start, page_end);
+
if (!inode_evicting) {
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY |
@@ -8963,6 +8999,10 @@ again:
ret = VM_FAULT_SIGBUS;
goto out_unlock;
}
+
+ set_page_blks_state(page, 1 << BLK_STATE_DIRTY | 1 << BLK_STATE_UPTODATE,
+ page_start, end);
+
ret = 0;
/* page is wholly or partially inside EOF */
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 08ef890..35fd62e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3187,6 +3187,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
}
btrfs_set_extent_delalloc(inode, page_start, page_end, NULL);
+ set_page_blks_state(page,
+ 1 << BLK_STATE_DIRTY | 1 << BLK_STATE_UPTODATE,
+ page_start, page_end);
set_page_dirty(page);
unlock_extent(&BTRFS_I(inode)->io_tree,
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 03/18] Btrfs: subpage-blocksize: Make sure delalloc range intersects with the locked page's range
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 01/18] Btrfs: subpage-blocksize: Fix whole page read Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 02/18] Btrfs: subpage-blocksize: Fix whole page write Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 04/18] Btrfs: subpage-blocksize: Define extent_buffer_head Chandan Rajendra
` (15 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
find_delalloc_range indirectly depends on EXTENT_UPTODDATE to make sure that
the delalloc range returned intersects with the file range mapped by the
page. Since we now track "uptodate" state in a per-page
bitmap (i.e. in btrfs_page_private->bstate), this commit makes an explicit
check to make sure that the delalloc range starts from within the file range
mapped by the page.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/extent_io.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9b6c8e0..70d32ef 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1568,6 +1568,7 @@ out:
* 1 is returned if we find something, 0 if nothing was in the tree
*/
static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
+ struct page *locked_page,
u64 *start, u64 *end, u64 max_bytes,
struct extent_state **cached_state)
{
@@ -1576,6 +1577,9 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
u64 cur_start = *start;
u64 found = 0;
u64 total_bytes = 0;
+ u64 page_end;
+
+ page_end = page_offset(locked_page) + PAGE_CACHE_SIZE - 1;
spin_lock(&tree->lock);
@@ -1596,7 +1600,8 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
(state->state & EXTENT_BOUNDARY))) {
goto out;
}
- if (!(state->state & EXTENT_DELALLOC)) {
+ if (!(state->state & EXTENT_DELALLOC)
+ || (page_end < state->start)) {
if (!found)
*end = state->end;
goto out;
@@ -1734,8 +1739,9 @@ again:
/* step one, find a bunch of delalloc bytes starting at start */
delalloc_start = *start;
delalloc_end = 0;
- found = find_delalloc_range(tree, &delalloc_start, &delalloc_end,
- max_bytes, &cached_state);
+ found = find_delalloc_range(tree, locked_page,
+ &delalloc_start, &delalloc_end,
+ max_bytes, &cached_state);
if (!found || delalloc_end <= *start) {
*start = delalloc_start;
*end = delalloc_end;
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 04/18] Btrfs: subpage-blocksize: Define extent_buffer_head.
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (2 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 03/18] Btrfs: subpage-blocksize: Make sure delalloc range intersects with the locked page's range Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 9:57 ` kbuild test robot
2016-04-14 8:32 ` [PATCH V16 05/18] Btrfs: subpage-blocksize: Read tree blocks whose size is < PAGE_CACHE_SIZE Chandan Rajendra
` (14 subsequent siblings)
18 siblings, 1 reply; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
In order to handle multiple extent buffers per page, first we need to create a
way to handle all the extent buffers that are attached to a page.
This patch creates a new data structure 'struct extent_buffer_head', and moves
fields that are common to all extent buffers from 'struct extent_buffer' to
'struct extent_buffer_head'
Also, this patch moves EXTENT_BUFFER_TREE_REF, EXTENT_BUFFER_DUMMY and
EXTENT_BUFFER_IN_TREE flags from extent_buffer->ebflags to
extent_buffer_head->bflags.
Reviewed-by: Liu Bo <bo.li.liu@oracle.com>
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/ctree.c | 2 +-
fs/btrfs/ctree.h | 6 +-
fs/btrfs/disk-io.c | 72 +++---
fs/btrfs/extent-tree.c | 6 +-
fs/btrfs/extent_io.c | 590 ++++++++++++++++++++++++++++---------------
fs/btrfs/extent_io.h | 63 +++--
fs/btrfs/root-tree.c | 2 +-
fs/btrfs/volumes.c | 2 +-
include/trace/events/btrfs.h | 2 +-
9 files changed, 490 insertions(+), 255 deletions(-)
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index ec7928a..23118f4 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -160,7 +160,7 @@ struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
* the inc_not_zero dance and if it doesn't work then
* synchronize_rcu and try again.
*/
- if (atomic_inc_not_zero(&eb->refs)) {
+ if (atomic_inc_not_zero(&eb_head(eb)->refs)) {
rcu_read_unlock();
break;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 84a6a5b..8e6eafa 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2464,14 +2464,16 @@ static inline void btrfs_set_token_##name(struct extent_buffer *eb, \
#define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(struct extent_buffer *eb) \
{ \
- type *p = page_address(eb->pages[0]); \
+ type *p = page_address(eb_head(eb)->pages[0]) + \
+ (eb->start & (PAGE_SIZE -1)); \
u##bits res = le##bits##_to_cpu(p->member); \
return res; \
} \
static inline void btrfs_set_##name(struct extent_buffer *eb, \
u##bits val) \
{ \
- type *p = page_address(eb->pages[0]); \
+ type *p = page_address(eb_head(eb)->pages[0]) + \
+ (eb->start & (PAGE_SIZE -1)); \
p->member = cpu_to_le##bits(val); \
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4e47849..f0cf922 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -375,10 +375,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
ret = 0;
goto out;
}
- btrfs_err_rl(eb->fs_info,
+ btrfs_err_rl(eb_head(eb)->fs_info,
"parent transid verify failed on %llu wanted %llu found %llu",
- eb->start,
- parent_transid, btrfs_header_generation(eb));
+ eb->start, parent_transid, btrfs_header_generation(eb));
ret = 1;
/*
@@ -452,7 +451,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
int mirror_num = 0;
int failed_mirror = 0;
- clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags);
io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
while (1) {
ret = read_extent_buffer_pages(io_tree, eb, start,
@@ -471,7 +470,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
* there is no reason to read the other copies, they won't be
* any less wrong.
*/
- if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
+ if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags))
break;
num_copies = btrfs_num_copies(root->fs_info,
@@ -510,7 +509,7 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
struct extent_buffer *eb;
eb = (struct extent_buffer *)page->private;
- if (page != eb->pages[0])
+ if (page != eb_head(eb)->pages[0])
return 0;
found_start = btrfs_header_bytenr(eb);
@@ -635,12 +634,12 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
*/
extent_buffer_get(eb);
- reads_done = atomic_dec_and_test(&eb->io_pages);
+ reads_done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
if (!reads_done)
goto err;
eb->read_mirror = mirror;
- if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
+ if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags)) {
ret = -EIO;
goto err;
}
@@ -679,7 +678,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
* return -EIO.
*/
if (found_level == 0 && check_leaf(root, eb)) {
- set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
+ set_bit(EXTENT_BUFFER_CORRUPT, &eb->ebflags);
ret = -EIO;
}
@@ -687,7 +686,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
set_extent_buffer_uptodate(eb);
err:
if (reads_done &&
- test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
+ test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->ebflags))
btree_readahead_hook(fs_info, eb, eb->start, ret);
if (ret) {
@@ -696,7 +695,7 @@ err:
* again, we have to make sure it has something
* to decrement
*/
- atomic_inc(&eb->io_pages);
+ atomic_inc(&eb_head(eb)->io_bvecs);
clear_extent_buffer_uptodate(eb);
}
free_extent_buffer(eb);
@@ -709,11 +708,11 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
struct extent_buffer *eb;
eb = (struct extent_buffer *)page->private;
- set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
+ set_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags);
eb->read_mirror = failed_mirror;
- atomic_dec(&eb->io_pages);
- if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
- btree_readahead_hook(eb->fs_info, eb, eb->start, -EIO);
+ atomic_dec(&eb_head(eb)->io_bvecs);
+ if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->ebflags))
+ btree_readahead_hook(eb_head(eb)->fs_info, eb, eb->start, -EIO);
return -EIO; /* we fixed nothing */
}
@@ -1070,13 +1069,24 @@ static int btree_set_page_dirty(struct page *page)
{
#ifdef DEBUG
struct extent_buffer *eb;
+ int i, dirty = 0;
BUG_ON(!PagePrivate(page));
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
- BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
- BUG_ON(!atomic_read(&eb->refs));
- btrfs_assert_tree_locked(eb);
+
+ do {
+ dirty = test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags);
+ if (dirty)
+ break;
+ } while ((eb = eb->eb_next) != NULL);
+
+ BUG_ON(!dirty);
+
+ eb = (struct extent_buffer *)page->private;
+ BUG_ON(!atomic_read(&(eb_head(eb)->refs)));
+
+ btrfs_assert_tree_locked(&ebh->eb);
#endif
return __set_page_dirty_nobuffers(page);
}
@@ -1117,7 +1127,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
if (!buf)
return 0;
- set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
+ set_bit(EXTENT_BUFFER_READAHEAD, &buf->ebflags);
ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK,
btree_get_extent, mirror_num);
@@ -1126,7 +1136,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
return ret;
}
- if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
+ if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->ebflags)) {
free_extent_buffer(buf);
return -EIO;
} else if (extent_buffer_uptodate(buf)) {
@@ -1154,14 +1164,16 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
int btrfs_write_tree_block(struct extent_buffer *buf)
{
- return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
+ return filemap_fdatawrite_range(eb_head(buf)->pages[0]->mapping,
+ buf->start,
buf->start + buf->len - 1);
}
int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
{
- return filemap_fdatawait_range(buf->pages[0]->mapping,
- buf->start, buf->start + buf->len - 1);
+ return filemap_fdatawait_range(eb_head(buf)->pages[0]->mapping,
+ buf->start,
+ buf->start + buf->len - 1);
}
struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
@@ -1191,7 +1203,8 @@ void clean_tree_block(struct btrfs_trans_handle *trans,
fs_info->running_transaction->transid) {
btrfs_assert_tree_locked(buf);
- if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
+ if (test_and_clear_bit(EXTENT_BUFFER_DIRTY,
+ &buf->ebflags)) {
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-buf->len,
fs_info->dirty_metadata_batch);
@@ -3949,7 +3962,7 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
int atomic)
{
int ret;
- struct inode *btree_inode = buf->pages[0]->mapping->host;
+ struct inode *btree_inode = eb_head(buf)->pages[0]->mapping->host;
ret = extent_buffer_uptodate(buf);
if (!ret)
@@ -3974,10 +3987,10 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
* enabled. Normal people shouldn't be marking dummy buffers as dirty
* outside of the sanity tests.
*/
- if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags)))
+ if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY, &eb_head(buf)->bflags)))
return;
#endif
- root = BTRFS_I(buf->pages[0]->mapping->host)->root;
+ root = BTRFS_I(eb_head(buf)->pages[0]->mapping->host)->root;
btrfs_assert_tree_locked(buf);
if (transid != root->fs_info->generation)
WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, "
@@ -4031,7 +4044,8 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root)
int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
{
- struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
+ struct btrfs_root *root =
+ BTRFS_I(eb_head(buf)->pages[0]->mapping->host)->root;
return btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
}
@@ -4366,7 +4380,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
wait_on_extent_buffer_writeback(eb);
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY,
- &eb->bflags))
+ &eb->ebflags))
clear_extent_buffer_dirty(eb);
free_extent_buffer_stale(eb);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 84e060e..b8df911 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6849,7 +6849,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
goto out;
}
- WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
+ WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->ebflags));
btrfs_add_free_space(cache, buf->start, buf->len);
btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
@@ -6867,7 +6867,7 @@ out:
* Deleting the buffer, clear the corrupt flag since it doesn't matter
* anymore.
*/
- clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
+ clear_bit(EXTENT_BUFFER_CORRUPT, &buf->ebflags);
}
/* Can return -ENOMEM */
@@ -7907,7 +7907,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
btrfs_tree_lock(buf);
clean_tree_block(trans, root->fs_info, buf);
- clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
+ clear_bit(EXTENT_BUFFER_STALE, &buf->ebflags);
btrfs_set_lock_blocking(buf);
set_extent_buffer_uptodate(buf);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 70d32ef..4a62196 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -22,6 +22,7 @@
#include "backref.h"
static struct kmem_cache *extent_state_cache;
+static struct kmem_cache *extent_buffer_head_cache;
static struct kmem_cache *extent_buffer_cache;
static struct bio_set *btrfs_bioset;
@@ -61,6 +62,7 @@ void btrfs_leak_debug_check(void)
{
struct extent_state *state;
struct extent_buffer *eb;
+ struct extent_buffer_head *ebh;
while (!list_empty(&states)) {
state = list_entry(states.next, struct extent_state, leak_list);
@@ -73,12 +75,17 @@ void btrfs_leak_debug_check(void)
}
while (!list_empty(&buffers)) {
- eb = list_entry(buffers.next, struct extent_buffer, leak_list);
- printk(KERN_ERR "BTRFS: buffer leak start %llu len %lu "
- "refs %d\n",
- eb->start, eb->len, atomic_read(&eb->refs));
- list_del(&eb->leak_list);
- kmem_cache_free(extent_buffer_cache, eb);
+ ebh = list_entry(buffers.next, struct extent_buffer_head, leak_list);
+ printk(KERN_ERR "btrfs buffer leak ");
+
+ eb = &ebh->eb;
+ do {
+ printk(KERN_ERR "eb %p %llu:%lu ", eb, eb->start, eb->len);
+ } while ((eb = eb->eb_next) != NULL);
+
+ printk(KERN_ERR "refs %d\n", atomic_read(&ebh->refs));
+ list_del(&ebh->leak_list);
+ kmem_cache_free(extent_buffer_cache, ebh);
}
}
@@ -167,11 +174,17 @@ int __init extent_io_init(void)
if (!extent_state_cache)
return -ENOMEM;
+ extent_buffer_head_cache = kmem_cache_create("btrfs_extent_buffer_head",
+ sizeof(struct extent_buffer_head), 0,
+ SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
+ if (!extent_buffer_head_cache)
+ goto free_state_cache;
+
extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer",
sizeof(struct extent_buffer), 0,
SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD, NULL);
if (!extent_buffer_cache)
- goto free_state_cache;
+ goto free_buffer_head_cache;
btrfs_bioset = bioset_create(BIO_POOL_SIZE,
offsetof(struct btrfs_io_bio, bio));
@@ -191,6 +204,10 @@ free_buffer_cache:
kmem_cache_destroy(extent_buffer_cache);
extent_buffer_cache = NULL;
+free_buffer_head_cache:
+ kmem_cache_destroy(extent_buffer_head_cache);
+ extent_buffer_head_cache = NULL;
+
free_state_cache:
kmem_cache_destroy(extent_state_cache);
extent_state_cache = NULL;
@@ -1579,7 +1596,7 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
u64 total_bytes = 0;
u64 page_end;
- page_end = page_offset(locked_page) + PAGE_CACHE_SIZE - 1;
+ page_end = page_offset(locked_page) + PAGE_SIZE - 1;
spin_lock(&tree->lock);
@@ -2153,7 +2170,7 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
return -EROFS;
for (i = 0; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
ret = repair_io_failure(root->fs_info->btree_inode, start,
PAGE_SIZE, start, p,
@@ -3631,8 +3648,8 @@ done_unlocked:
void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
{
- wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_WRITEBACK,
- TASK_UNINTERRUPTIBLE);
+ wait_on_bit_io(&eb->ebflags, EXTENT_BUFFER_WRITEBACK,
+ TASK_UNINTERRUPTIBLE);
}
static noinline_for_stack int
@@ -3650,7 +3667,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
btrfs_tree_lock(eb);
}
- if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) {
+ if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags)) {
btrfs_tree_unlock(eb);
if (!epd->sync_io)
return 0;
@@ -3661,7 +3678,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
while (1) {
wait_on_extent_buffer_writeback(eb);
btrfs_tree_lock(eb);
- if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags))
+ if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags))
break;
btrfs_tree_unlock(eb);
}
@@ -3672,17 +3689,17 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
* under IO since we can end up having no IO bits set for a short period
* of time.
*/
- spin_lock(&eb->refs_lock);
- if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
- set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
- spin_unlock(&eb->refs_lock);
+ spin_lock(&eb_head(eb)->refs_lock);
+ if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags)) {
+ set_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags);
+ spin_unlock(&eb_head(eb)->refs_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-eb->len,
fs_info->dirty_metadata_batch);
ret = 1;
} else {
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&eb_head(eb)->refs_lock);
}
btrfs_tree_unlock(eb);
@@ -3692,7 +3709,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
if (!trylock_page(p)) {
if (!flush) {
@@ -3708,18 +3725,19 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
static void end_extent_buffer_writeback(struct extent_buffer *eb)
{
- clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags);
smp_mb__after_atomic();
- wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
+ wake_up_bit(&eb->ebflags, EXTENT_BUFFER_WRITEBACK);
}
static void set_btree_ioerr(struct page *page)
{
struct extent_buffer *eb = (struct extent_buffer *)page->private;
- struct btrfs_inode *btree_ino = BTRFS_I(eb->fs_info->btree_inode);
+ struct extent_buffer_head *ebh = eb_head(eb);
+ struct btrfs_inode *btree_ino = BTRFS_I(ebh->fs_info->btree_inode);
SetPageError(page);
- if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))
+ if (test_and_set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags))
return;
/*
@@ -3786,10 +3804,10 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
- done = atomic_dec_and_test(&eb->io_pages);
+ done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
if (bio->bi_error ||
- test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
+ test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags)) {
ClearPageUptodate(page);
set_btree_ioerr(page);
}
@@ -3818,14 +3836,14 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
int ret = 0;
- clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags);
num_pages = num_extent_pages(eb->start, eb->len);
- atomic_set(&eb->io_pages, num_pages);
+ atomic_set(&eb_head(eb)->io_bvecs, num_pages);
if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
bio_flags = EXTENT_BIO_TREE_LOG;
for (i = 0; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
clear_page_dirty_for_io(p);
set_page_writeback(p);
@@ -3837,7 +3855,8 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
if (ret) {
set_btree_ioerr(p);
end_page_writeback(p);
- if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
+ if (atomic_sub_and_test(num_pages - i,
+ &eb_head(eb)->io_bvecs))
end_extent_buffer_writeback(eb);
ret = -EIO;
break;
@@ -3849,7 +3868,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
if (unlikely(ret)) {
for (; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
clear_page_dirty_for_io(p);
unlock_page(p);
}
@@ -3937,7 +3956,7 @@ retry:
continue;
}
- ret = atomic_inc_not_zero(&eb->refs);
+ ret = atomic_inc_not_zero(&eb_head(eb)->refs);
spin_unlock(&mapping->private_lock);
if (!ret)
continue;
@@ -4615,17 +4634,36 @@ out:
return ret;
}
-static void __free_extent_buffer(struct extent_buffer *eb)
+static void __free_extent_buffer(struct extent_buffer_head *ebh)
{
- btrfs_leak_debug_del(&eb->leak_list);
- kmem_cache_free(extent_buffer_cache, eb);
+ struct extent_buffer *eb, *next_eb;
+
+ btrfs_leak_debug_del(&ebh->leak_list);
+
+ eb = ebh->eb.eb_next;
+ while (eb) {
+ next_eb = eb->eb_next;
+ kmem_cache_free(extent_buffer_cache, eb);
+ eb = next_eb;
+ }
+
+ kmem_cache_free(extent_buffer_head_cache, ebh);
}
int extent_buffer_under_io(struct extent_buffer *eb)
{
- return (atomic_read(&eb->io_pages) ||
- test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) ||
- test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+ struct extent_buffer_head *ebh = eb->ebh;
+ int dirty_or_writeback = 0;
+
+ for (eb = &ebh->eb; eb; eb = eb->eb_next) {
+ if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags)
+ || test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags)) {
+ dirty_or_writeback = 1;
+ break;
+ }
+ }
+
+ return (atomic_read(&ebh->io_bvecs) || dirty_or_writeback);
}
/*
@@ -4635,7 +4673,8 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
{
unsigned long index;
struct page *page;
- int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+ struct extent_buffer_head *ebh = eb_head(eb);
+ int mapped = !test_bit(EXTENT_BUFFER_HEAD_DUMMY, &ebh->bflags);
BUG_ON(extent_buffer_under_io(eb));
@@ -4644,8 +4683,11 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
return;
do {
+ struct extent_buffer *e;
+
index--;
- page = eb->pages[index];
+
+ page = ebh->pages[index];
if (!page)
continue;
if (mapped)
@@ -4658,8 +4700,10 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
* this eb.
*/
if (PagePrivate(page) &&
- page->private == (unsigned long)eb) {
- BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+ page->private == (unsigned long)(&ebh->eb)) {
+ for (e = &ebh->eb; !e; e = e->eb_next)
+ BUG_ON(test_bit(EXTENT_BUFFER_DIRTY,
+ &e->ebflags));
BUG_ON(PageDirty(page));
BUG_ON(PageWriteback(page));
/*
@@ -4686,20 +4730,18 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
{
btrfs_release_extent_buffer_page(eb);
- __free_extent_buffer(eb);
+ __free_extent_buffer(eb_head(eb));
}
-static struct extent_buffer *
-__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
- unsigned long len)
+static void __init_extent_buffer(struct extent_buffer *eb,
+ struct extent_buffer_head *ebh,
+ u64 start,
+ unsigned long len)
{
- struct extent_buffer *eb = NULL;
-
- eb = kmem_cache_zalloc(extent_buffer_cache, GFP_NOFS|__GFP_NOFAIL);
eb->start = start;
eb->len = len;
- eb->fs_info = fs_info;
- eb->bflags = 0;
+ eb->ebh = ebh;
+ eb->eb_next = NULL;
rwlock_init(&eb->lock);
atomic_set(&eb->write_locks, 0);
atomic_set(&eb->read_locks, 0);
@@ -4710,12 +4752,27 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
eb->lock_nested = 0;
init_waitqueue_head(&eb->write_lock_wq);
init_waitqueue_head(&eb->read_lock_wq);
+}
- btrfs_leak_debug_add(&eb->leak_list, &buffers);
+static struct extent_buffer *
+__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
+ unsigned long len)
+{
+ struct extent_buffer_head *ebh = NULL;
+ struct extent_buffer *cur_eb, *prev_eb;
+ struct extent_buffer *eb = NULL;
+ int i;
+
+ ebh = kmem_cache_zalloc(extent_buffer_head_cache, GFP_NOFS|__GFP_NOFAIL);
+ if (ebh == NULL)
+ return NULL;
+ ebh->fs_info = fs_info;
+ ebh->bflags = 0;
+ btrfs_leak_debug_add(&ebh->leak_list, &buffers);
- spin_lock_init(&eb->refs_lock);
- atomic_set(&eb->refs, 1);
- atomic_set(&eb->io_pages, 0);
+ spin_lock_init(&ebh->refs_lock);
+ atomic_set(&ebh->refs, 1);
+ atomic_set(&ebh->io_bvecs, 0);
/*
* Sanity checks, currently the maximum is 64k covered by 16x 4k pages
@@ -4724,7 +4781,44 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
> MAX_INLINE_EXTENT_BUFFER_SIZE);
BUG_ON(len > MAX_INLINE_EXTENT_BUFFER_SIZE);
+ if (len < PAGE_SIZE) {
+ int ebs_per_page = PAGE_SIZE / len;
+ u64 st = start & ~(PAGE_SIZE - 1);
+
+ prev_eb = NULL;
+ cur_eb = &ebh->eb;
+ for (i = 0; i < ebs_per_page; i++, st += len) {
+ if (prev_eb) {
+ cur_eb = kmem_cache_zalloc(extent_buffer_cache,
+ GFP_NOFS|__GFP_NOFAIL);
+ if (cur_eb == NULL)
+ goto out;
+ prev_eb->eb_next = cur_eb;
+ }
+ __init_extent_buffer(cur_eb, ebh, st, len);
+ prev_eb = cur_eb;
+ if (st == start)
+ eb = cur_eb;
+ }
+ BUG_ON(!eb);
+ } else {
+ eb = &ebh->eb;
+ __init_extent_buffer(eb, ebh, start, len);
+ }
+
return eb;
+
+out:
+ cur_eb = ebh->eb.eb_next;
+ while (cur_eb) {
+ prev_eb = cur_eb;
+ cur_eb = cur_eb->eb_next;
+ kmem_cache_free(extent_buffer_cache, prev_eb);
+ }
+
+ kmem_cache_free(extent_buffer_head_cache, ebh);
+
+ return NULL;
}
struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
@@ -4734,7 +4828,8 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
struct extent_buffer *new;
unsigned long num_pages = num_extent_pages(src->start, src->len);
- new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
+ new = __alloc_extent_buffer(eb_head(src)->fs_info, src->start,
+ src->len);
if (new == NULL)
return NULL;
@@ -4744,15 +4839,25 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
btrfs_release_extent_buffer(new);
return NULL;
}
- attach_extent_buffer_page(new, p);
+ attach_extent_buffer_page(&(eb_head(new)->eb), p);
WARN_ON(PageDirty(p));
SetPageUptodate(p);
- new->pages[i] = p;
+ eb_head(new)->pages[i] = p;
}
+ /*
+ * copy_extent_buffer() now checks for the presence of
+ * EXTENT_BUFFER_UPTODATE flag (instead of the page's
+ * PG_Uptodate flag) in dst extent buffer. Hence we set
+ * EXTENT_BUFFER_UPTODATE bit before copy_extent_buffer()
+ * is invoked. It is safe since this is the only function
+ * that has a reference to the just allocated dummy extent
+ * buffer.
+ */
+ set_bit(EXTENT_BUFFER_UPTODATE, &new->ebflags);
+ set_bit(EXTENT_BUFFER_HEAD_DUMMY, &eb_head(new)->bflags);
+
copy_extent_buffer(new, src, 0, 0, src->len);
- set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
- set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
return new;
}
@@ -4771,19 +4876,19 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
return NULL;
for (i = 0; i < num_pages; i++) {
- eb->pages[i] = alloc_page(GFP_NOFS);
- if (!eb->pages[i])
+ eb_head(eb)->pages[i] = alloc_page(GFP_NOFS);
+ if (!eb_head(eb)->pages[i])
goto err;
}
set_extent_buffer_uptodate(eb);
btrfs_set_header_nritems(eb, 0);
- set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+ set_bit(EXTENT_BUFFER_HEAD_DUMMY, &eb_head(eb)->bflags);
return eb;
err:
for (; i > 0; i--)
- __free_page(eb->pages[i - 1]);
- __free_extent_buffer(eb);
+ __free_page(eb_head(eb)->pages[i - 1]);
+ __free_extent_buffer(eb_head(eb));
return NULL;
}
@@ -4828,14 +4933,16 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
* So bump the ref count first, then set the bit. If someone
* beat us to it, drop the ref we added.
*/
- refs = atomic_read(&eb->refs);
- if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
+ refs = atomic_read(&eb_head(eb)->refs);
+ if (refs >= 2 && test_bit(EXTENT_BUFFER_HEAD_TREE_REF,
+ &eb_head(eb)->bflags))
return;
- spin_lock(&eb->refs_lock);
- if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
- atomic_inc(&eb->refs);
- spin_unlock(&eb->refs_lock);
+ spin_lock(&eb_head(eb)->refs_lock);
+ if (!test_and_set_bit(EXTENT_BUFFER_HEAD_TREE_REF,
+ &eb_head(eb)->bflags))
+ atomic_inc(&eb_head(eb)->refs);
+ spin_unlock(&eb_head(eb)->refs_lock);
}
static void mark_extent_buffer_accessed(struct extent_buffer *eb,
@@ -4847,44 +4954,67 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb,
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- struct page *p = eb->pages[i];
+ struct page *p = eb_head(eb)->pages[i];
if (p != accessed)
mark_page_accessed(p);
}
}
+static int extent_buffer_head_stale(struct extent_buffer_head *ebh)
+{
+ struct extent_buffer *eb = &ebh->eb;
+
+ do {
+ if (test_bit(EXTENT_BUFFER_STALE, &eb->ebflags))
+ return 1;
+ } while ((eb = eb->eb_next) != NULL);
+
+ return 0;
+}
+
struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start)
{
+ struct extent_buffer_head *ebh;
struct extent_buffer *eb;
rcu_read_lock();
- eb = radix_tree_lookup(&fs_info->buffer_radix,
- start >> PAGE_SHIFT);
- if (eb && atomic_inc_not_zero(&eb->refs)) {
+ ebh = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> PAGE_SHIFT);
+ if (ebh && atomic_inc_not_zero(&ebh->refs)) {
rcu_read_unlock();
/*
- * Lock our eb's refs_lock to avoid races with
- * free_extent_buffer. When we get our eb it might be flagged
- * with EXTENT_BUFFER_STALE and another task running
- * free_extent_buffer might have seen that flag set,
- * eb->refs == 2, that the buffer isn't under IO (dirty and
- * writeback flags not set) and it's still in the tree (flag
- * EXTENT_BUFFER_TREE_REF set), therefore being in the process
- * of decrementing the extent buffer's reference count twice.
- * So here we could race and increment the eb's reference count,
- * clear its stale flag, mark it as dirty and drop our reference
- * before the other task finishes executing free_extent_buffer,
- * which would later result in an attempt to free an extent
- * buffer that is dirty.
+ * Lock our ebh's refs_lock to avoid races with
+ * free_extent_buffer. When we get our eb it might be
+ * flagged with EXTENT_BUFFER_STALE and another task
+ * running free_extent_buffer might have seen that
+ * flag set, ebh->refs == 2, that the buffer isn't
+ * under IO (dirty and writeback flags not set) and
+ * it's still in the tree (flag
+ * EXTENT_BUFFER_HEAD_TREE_REF set), therefore being
+ * in the process of decrementing the extent buffer's
+ * reference count twice. So here we could race and
+ * increment the ebh's reference count, clear its
+ * stale flag, mark it as dirty and drop our reference
+ * before the other task finishes executing
+ * free_extent_buffer, which would later result in an
+ * attempt to free an extent buffer head (along with
+ * its extent buffers) that has a dirty extent buffer.
*/
- if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) {
- spin_lock(&eb->refs_lock);
- spin_unlock(&eb->refs_lock);
- }
- mark_extent_buffer_accessed(eb, NULL);
- return eb;
+ eb = &ebh->eb;
+ do {
+ if (eb->start == start) {
+ if (extent_buffer_head_stale(ebh)) {
+ spin_lock(&ebh->refs_lock);
+ spin_unlock(&ebh->refs_lock);
+ }
+ mark_extent_buffer_accessed(eb, NULL);
+ return eb;
+ }
+ } while ((eb = eb->eb_next) != NULL);
+
+ BUG();
}
rcu_read_unlock();
@@ -4922,7 +5052,7 @@ again:
goto again;
}
check_buffer_tree_ref(eb);
- set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
+ set_bit(EXTENT_BUFFER_HEAD_IN_TREE, &eb->bflags);
/*
* We will free dummy extent buffer's if they come into
@@ -4945,7 +5075,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
unsigned long num_pages = num_extent_pages(start, len);
unsigned long i;
unsigned long index = start >> PAGE_SHIFT;
- struct extent_buffer *eb;
+ struct extent_buffer *eb, *cur_eb;
struct extent_buffer *exists = NULL;
struct page *p;
struct address_space *mapping = fs_info->btree_inode->i_mapping;
@@ -4975,12 +5105,18 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
* overwrite page->private.
*/
exists = (struct extent_buffer *)p->private;
- if (atomic_inc_not_zero(&exists->refs)) {
+ if (atomic_inc_not_zero(&eb_head(exists)->refs)) {
spin_unlock(&mapping->private_lock);
unlock_page(p);
put_page(p);
- mark_extent_buffer_accessed(exists, p);
- goto free_eb;
+ do {
+ if (exists->start == start) {
+ mark_extent_buffer_accessed(exists, p);
+ goto free_eb;
+ }
+ } while ((exists = exists->eb_next) != NULL);
+
+ BUG();
}
exists = NULL;
@@ -4992,10 +5128,11 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
WARN_ON(PageDirty(p));
put_page(p);
}
- attach_extent_buffer_page(eb, p);
+ attach_extent_buffer_page(&(eb_head(eb)->eb), p);
spin_unlock(&mapping->private_lock);
WARN_ON(PageDirty(p));
- eb->pages[i] = p;
+ mark_page_accessed(p);
+ eb_head(eb)->pages[i] = p;
if (!PageUptodate(p))
uptodate = 0;
@@ -5004,16 +5141,22 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
* and why we unlock later
*/
}
- if (uptodate)
- set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ if (uptodate) {
+ cur_eb = &(eb_head(eb)->eb);
+ do {
+ set_bit(EXTENT_BUFFER_UPTODATE, &cur_eb->ebflags);
+ } while ((cur_eb = cur_eb->eb_next) != NULL);
+ }
again:
ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
- if (ret)
+ if (ret) {
+ exists = NULL;
goto free_eb;
+ }
spin_lock(&fs_info->buffer_lock);
ret = radix_tree_insert(&fs_info->buffer_radix,
- start >> PAGE_SHIFT, eb);
+ start >> PAGE_SHIFT, eb_head(eb));
spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
@@ -5025,7 +5168,7 @@ again:
}
/* add one reference for the tree */
check_buffer_tree_ref(eb);
- set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
+ set_bit(EXTENT_BUFFER_HEAD_IN_TREE, &eb_head(eb)->bflags);
/*
* there is a race where release page may have
@@ -5036,20 +5179,20 @@ again:
* after the extent buffer is in the radix tree so
* it doesn't get lost
*/
- SetPageChecked(eb->pages[0]);
+ SetPageChecked(eb_head(eb)->pages[0]);
for (i = 1; i < num_pages; i++) {
- p = eb->pages[i];
+ p = eb_head(eb)->pages[i];
ClearPageChecked(p);
unlock_page(p);
}
- unlock_page(eb->pages[0]);
+ unlock_page(eb_head(eb)->pages[0]);
return eb;
free_eb:
- WARN_ON(!atomic_dec_and_test(&eb->refs));
+ WARN_ON(!atomic_dec_and_test(&eb_head(eb)->refs));
for (i = 0; i < num_pages; i++) {
- if (eb->pages[i])
- unlock_page(eb->pages[i]);
+ if (eb_head(eb)->pages[i])
+ unlock_page(eb_head(eb)->pages[i]);
}
btrfs_release_extent_buffer(eb);
@@ -5058,92 +5201,111 @@ free_eb:
static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
{
- struct extent_buffer *eb =
- container_of(head, struct extent_buffer, rcu_head);
+ struct extent_buffer_head *ebh =
+ container_of(head, struct extent_buffer_head, rcu_head);
- __free_extent_buffer(eb);
+ __free_extent_buffer(ebh);
}
/* Expects to have eb->eb_lock already held */
-static int release_extent_buffer(struct extent_buffer *eb)
+static int release_extent_buffer(struct extent_buffer_head *ebh)
{
- WARN_ON(atomic_read(&eb->refs) == 0);
- if (atomic_dec_and_test(&eb->refs)) {
- if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
- struct btrfs_fs_info *fs_info = eb->fs_info;
+ WARN_ON(atomic_read(&ebh->refs) == 0);
+ if (atomic_dec_and_test(&ebh->refs)) {
+ if (test_and_clear_bit(EXTENT_BUFFER_HEAD_IN_TREE,
+ &ebh->bflags)) {
+ struct btrfs_fs_info *fs_info = ebh->fs_info;
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&ebh->refs_lock);
spin_lock(&fs_info->buffer_lock);
radix_tree_delete(&fs_info->buffer_radix,
- eb->start >> PAGE_SHIFT);
+ ebh->eb.start >> PAGE_SHIFT);
spin_unlock(&fs_info->buffer_lock);
} else {
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&ebh->refs_lock);
}
/* Should be safe to release our pages at this point */
- btrfs_release_extent_buffer_page(eb);
+ btrfs_release_extent_buffer_page(&ebh->eb);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
- __free_extent_buffer(eb);
+ if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
+ &eb_head(buf)->bflags))) {
+ __free_extent_buffer(eb_head(eb));
return 1;
}
#endif
- call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
+ call_rcu(&ebh->rcu_head, btrfs_release_extent_buffer_rcu);
return 1;
}
- spin_unlock(&eb->refs_lock);
+ spin_unlock(&ebh->refs_lock);
return 0;
}
void free_extent_buffer(struct extent_buffer *eb)
{
+ struct extent_buffer_head *ebh;
int refs;
int old;
if (!eb)
return;
+ ebh = eb_head(eb);
while (1) {
- refs = atomic_read(&eb->refs);
+ refs = atomic_read(&ebh->refs);
if (refs <= 3)
break;
- old = atomic_cmpxchg(&eb->refs, refs, refs - 1);
+ old = atomic_cmpxchg(&ebh->refs, refs, refs - 1);
if (old == refs)
return;
}
- spin_lock(&eb->refs_lock);
- if (atomic_read(&eb->refs) == 2 &&
- test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))
- atomic_dec(&eb->refs);
+ spin_lock(&ebh->refs_lock);
+ if (atomic_read(&ebh->refs) == 2 &&
+ test_bit(EXTENT_BUFFER_HEAD_DUMMY, &ebh->bflags))
+ atomic_dec(&ebh->refs);
- if (atomic_read(&eb->refs) == 2 &&
- test_bit(EXTENT_BUFFER_STALE, &eb->bflags) &&
+ if (atomic_read(&ebh->refs) == 2 &&
+ test_bit(EXTENT_BUFFER_STALE, &eb->ebflags) &&
!extent_buffer_under_io(eb) &&
- test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
- atomic_dec(&eb->refs);
+ test_and_clear_bit(EXTENT_BUFFER_HEAD_TREE_REF, &ebh->bflags))
+ atomic_dec(&ebh->refs);
/*
* I know this is terrible, but it's temporary until we stop tracking
* the uptodate bits and such for the extent buffers.
*/
- release_extent_buffer(eb);
+ release_extent_buffer(ebh);
}
void free_extent_buffer_stale(struct extent_buffer *eb)
{
+ struct extent_buffer_head *ebh;
if (!eb)
return;
- spin_lock(&eb->refs_lock);
- set_bit(EXTENT_BUFFER_STALE, &eb->bflags);
+ ebh = eb_head(eb);
+ spin_lock(&ebh->refs_lock);
+
+ set_bit(EXTENT_BUFFER_STALE, &eb->ebflags);
+ if (atomic_read(&ebh->refs) == 2 && !extent_buffer_under_io(eb) &&
+ test_and_clear_bit(EXTENT_BUFFER_HEAD_TREE_REF, &ebh->bflags))
+ atomic_dec(&ebh->refs);
- if (atomic_read(&eb->refs) == 2 && !extent_buffer_under_io(eb) &&
- test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
- atomic_dec(&eb->refs);
- release_extent_buffer(eb);
+ release_extent_buffer(ebh);
+}
+
+static int page_ebs_clean(struct extent_buffer_head *ebh)
+{
+ struct extent_buffer *eb = &ebh->eb;
+
+ do {
+ if (test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags))
+ return 0;
+ } while ((eb = eb->eb_next) != NULL);
+
+ return 1;
}
void clear_extent_buffer_dirty(struct extent_buffer *eb)
@@ -5154,8 +5316,11 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
num_pages = num_extent_pages(eb->start, eb->len);
+ if (eb->len < PAGE_SIZE && !page_ebs_clean(eb_head(eb)))
+ return;
+
for (i = 0; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (!PageDirty(page))
continue;
@@ -5173,7 +5338,7 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
ClearPageError(page);
unlock_page(page);
}
- WARN_ON(atomic_read(&eb->refs) == 0);
+ WARN_ON(atomic_read(&eb_head(eb)->refs) == 0);
}
int set_extent_buffer_dirty(struct extent_buffer *eb)
@@ -5184,14 +5349,14 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
check_buffer_tree_ref(eb);
- was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
+ was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags);
num_pages = num_extent_pages(eb->start, eb->len);
- WARN_ON(atomic_read(&eb->refs) == 0);
- WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
+ WARN_ON(atomic_read(&eb_head(eb)->refs) == 0);
+ WARN_ON(!test_bit(EXTENT_BUFFER_HEAD_TREE_REF, &eb_head(eb)->bflags));
for (i = 0; i < num_pages; i++)
- set_page_dirty(eb->pages[i]);
+ set_page_dirty(eb_head(eb)->pages[i]);
return was_dirty;
}
@@ -5201,10 +5366,10 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb)
struct page *page;
unsigned long num_pages;
- clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
num_pages = num_extent_pages(eb->start, eb->len);
for (i = 0; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (page)
ClearPageUptodate(page);
}
@@ -5212,21 +5377,41 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb)
void set_extent_buffer_uptodate(struct extent_buffer *eb)
{
+ struct extent_buffer_head *ebh;
unsigned long i;
struct page *page;
unsigned long num_pages;
+ int uptodate;
- set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
- num_pages = num_extent_pages(eb->start, eb->len);
- for (i = 0; i < num_pages; i++) {
- page = eb->pages[i];
- SetPageUptodate(page);
+ ebh = eb->ebh;
+
+ set_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
+ if (eb->len < PAGE_SIZE) {
+ eb = &(eb_head(eb)->eb);
+ uptodate = 1;
+ do {
+ if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags)) {
+ uptodate = 0;
+ break;
+ }
+ } while ((eb = eb->eb_next) != NULL);
+
+ if (uptodate) {
+ page = ebh->pages[0];
+ SetPageUptodate(page);
+ }
+ } else {
+ num_pages = num_extent_pages(eb->start, eb->len);
+ for (i = 0; i < num_pages; i++) {
+ page = ebh->pages[i];
+ SetPageUptodate(page);
+ }
}
}
int extent_buffer_uptodate(struct extent_buffer *eb)
{
- return test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ return test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
}
int read_extent_buffer_pages(struct extent_io_tree *tree,
@@ -5245,7 +5430,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
struct bio *bio = NULL;
unsigned long bio_flags = 0;
- if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
+ if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags))
return 0;
if (start) {
@@ -5258,7 +5443,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
num_pages = num_extent_pages(eb->start, eb->len);
for (i = start_i; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (wait == WAIT_NONE) {
if (!trylock_page(page))
goto unlock_exit;
@@ -5273,15 +5458,15 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
}
if (all_uptodate) {
if (start_i == 0)
- set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+ set_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags);
goto unlock_exit;
}
- clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
+ clear_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags);
eb->read_mirror = 0;
- atomic_set(&eb->io_pages, num_reads);
+ atomic_set(&eb_head(eb)->io_bvecs, num_reads);
for (i = start_i; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
if (!PageUptodate(page)) {
ClearPageError(page);
err = __extent_read_full_page(tree, page,
@@ -5306,7 +5491,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
return ret;
for (i = start_i; i < num_pages; i++) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
wait_on_page_locked(page);
if (!PageUptodate(page))
ret = -EIO;
@@ -5317,7 +5502,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
unlock_exit:
i = start_i;
while (locked_pages > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
i++;
unlock_page(page);
locked_pages--;
@@ -5343,7 +5528,7 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
cur = min(len, (PAGE_SIZE - offset));
kaddr = page_address(page);
@@ -5375,7 +5560,7 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv,
offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
cur = min(len, (PAGE_SIZE - offset));
kaddr = page_address(page);
@@ -5424,7 +5609,7 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
return -EINVAL;
}
- p = eb->pages[i];
+ p = eb_head(eb)->pages[i];
kaddr = page_address(p);
*map = kaddr + offset;
*map_len = PAGE_SIZE - offset;
@@ -5450,7 +5635,7 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
cur = min(len, (PAGE_SIZE - offset));
@@ -5480,12 +5665,12 @@ void write_extent_buffer(struct extent_buffer *eb, const void *srcv,
WARN_ON(start > eb->len);
WARN_ON(start + len > eb->start + eb->len);
+ WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags));
offset = (start_offset + start) & (PAGE_SIZE - 1);
while (len > 0) {
- page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ page = eb_head(eb)->pages[i];
cur = min(len, PAGE_SIZE - offset);
kaddr = page_address(page);
@@ -5513,9 +5698,10 @@ void memset_extent_buffer(struct extent_buffer *eb, char c,
offset = (start_offset + start) & (PAGE_SIZE - 1);
+ WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags));
+
while (len > 0) {
- page = eb->pages[i];
- WARN_ON(!PageUptodate(page));
+ page = eb_head(eb)->pages[i];
cur = min(len, PAGE_SIZE - offset);
kaddr = page_address(page);
@@ -5544,9 +5730,10 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
offset = (start_offset + dst_offset) &
(PAGE_SIZE - 1);
+ WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &dst->ebflags));
+
while (len > 0) {
- page = dst->pages[i];
- WARN_ON(!PageUptodate(page));
+ page = eb_head(dst)->pages[i];
cur = min(len, (unsigned long)(PAGE_SIZE - offset));
@@ -5620,7 +5807,7 @@ int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
size_t offset;
eb_bitmap_offset(eb, start, nr, &i, &offset);
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
@@ -5645,7 +5832,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
unsigned int mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
eb_bitmap_offset(eb, start, pos, &i, &offset);
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
@@ -5656,7 +5843,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
mask_to_set = ~0U;
if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
- page = eb->pages[++i];
+ page = eb_head(eb)->pages[++i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
}
@@ -5687,7 +5874,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
unsigned int mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
eb_bitmap_offset(eb, start, pos, &i, &offset);
- page = eb->pages[i];
+ page = eb_head(eb)->pages[i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
@@ -5698,7 +5885,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
mask_to_clear = ~0U;
if (++offset >= PAGE_SIZE && len > 0) {
offset = 0;
- page = eb->pages[++i];
+ page = eb_head(eb)->pages[++i];
WARN_ON(!PageUptodate(page));
kaddr = page_address(page);
}
@@ -5748,13 +5935,13 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
unsigned long src_i;
if (src_offset + len > dst->len) {
- btrfs_err(dst->fs_info,
+ btrfs_err(eb_head(dst)->fs_info,
"memmove bogus src_offset %lu move "
"len %lu dst len %lu", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- btrfs_err(dst->fs_info,
+ btrfs_err(eb_head(dst)->fs_info,
"memmove bogus dst_offset %lu move "
"len %lu dst len %lu", dst_offset, len, dst->len);
BUG_ON(1);
@@ -5774,8 +5961,9 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
cur = min_t(unsigned long, cur,
(unsigned long)(PAGE_SIZE - dst_off_in_page));
- copy_pages(dst->pages[dst_i], dst->pages[src_i],
- dst_off_in_page, src_off_in_page, cur);
+ copy_pages(eb_head(dst)->pages[dst_i],
+ eb_head(dst)->pages[src_i],
+ dst_off_in_page, src_off_in_page, cur);
src_offset += cur;
dst_offset += cur;
@@ -5796,13 +5984,15 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
unsigned long src_i;
if (src_offset + len > dst->len) {
- btrfs_err(dst->fs_info, "memmove bogus src_offset %lu move "
- "len %lu len %lu", src_offset, len, dst->len);
+ btrfs_err(eb_head(dst)->fs_info,
+ "memmove bogus src_offset %lu move len %lu len %lu",
+ src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- btrfs_err(dst->fs_info, "memmove bogus dst_offset %lu move "
- "len %lu len %lu", dst_offset, len, dst->len);
+ btrfs_err(eb_head(dst)->fs_info,
+ "memmove bogus dst_offset %lu move len %lu len %lu",
+ dst_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset < src_offset) {
@@ -5820,9 +6010,10 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
cur = min_t(unsigned long, len, src_off_in_page + 1);
cur = min(cur, dst_off_in_page + 1);
- copy_pages(dst->pages[dst_i], dst->pages[src_i],
- dst_off_in_page - cur + 1,
- src_off_in_page - cur + 1, cur);
+ copy_pages(eb_head(dst)->pages[dst_i],
+ eb_head(dst)->pages[src_i],
+ dst_off_in_page - cur + 1,
+ src_off_in_page - cur + 1, cur);
dst_end -= cur;
src_end -= cur;
@@ -5832,6 +6023,7 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
int try_release_extent_buffer(struct page *page)
{
+ struct extent_buffer_head *ebh;
struct extent_buffer *eb;
/*
@@ -5847,14 +6039,15 @@ int try_release_extent_buffer(struct page *page)
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
+ ebh = eb->ebh;
/*
* This is a little awful but should be ok, we need to make sure that
* the eb doesn't disappear out from under us while we're looking at
* this page.
*/
- spin_lock(&eb->refs_lock);
- if (atomic_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) {
- spin_unlock(&eb->refs_lock);
+ spin_lock(&ebh->refs_lock);
+ if (atomic_read(&ebh->refs) != 1 || extent_buffer_under_io(eb)) {
+ spin_unlock(&ebh->refs_lock);
spin_unlock(&page->mapping->private_lock);
return 0;
}
@@ -5864,10 +6057,11 @@ int try_release_extent_buffer(struct page *page)
* If tree ref isn't set then we know the ref on this eb is a real ref,
* so just return, this page will likely be freed soon anyway.
*/
- if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
- spin_unlock(&eb->refs_lock);
+ if (!test_and_clear_bit(EXTENT_BUFFER_HEAD_TREE_REF, &ebh->bflags)) {
+ spin_unlock(&ebh->refs_lock);
return 0;
}
- return release_extent_buffer(eb);
+ return release_extent_buffer(ebh);
}
+
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 026befc..1996e08 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -31,18 +31,20 @@
#define EXTENT_BIO_TREE_LOG 2
#define EXTENT_BIO_FLAG_SHIFT 16
-/* these are bit numbers for test/set bit */
+/* these are bit numbers for test/set bit on extent buffer head */
+#define EXTENT_BUFFER_HEAD_TREE_REF 0
+#define EXTENT_BUFFER_HEAD_DUMMY 1
+#define EXTENT_BUFFER_HEAD_IN_TREE 2
+
+/* these are bit numbers for test/set bit on extent buffer */
#define EXTENT_BUFFER_UPTODATE 0
-#define EXTENT_BUFFER_DIRTY 2
-#define EXTENT_BUFFER_CORRUPT 3
-#define EXTENT_BUFFER_READAHEAD 4 /* this got triggered by readahead */
-#define EXTENT_BUFFER_TREE_REF 5
-#define EXTENT_BUFFER_STALE 6
-#define EXTENT_BUFFER_WRITEBACK 7
-#define EXTENT_BUFFER_READ_ERR 8 /* read IO error */
-#define EXTENT_BUFFER_DUMMY 9
-#define EXTENT_BUFFER_IN_TREE 10
-#define EXTENT_BUFFER_WRITE_ERR 11 /* write IO error */
+#define EXTENT_BUFFER_DIRTY 1
+#define EXTENT_BUFFER_CORRUPT 2
+#define EXTENT_BUFFER_READAHEAD 3 /* this got triggered by readahead */
+#define EXTENT_BUFFER_STALE 4
+#define EXTENT_BUFFER_WRITEBACK 5
+#define EXTENT_BUFFER_READ_ERR 6 /* read IO error */
+#define EXTENT_BUFFER_WRITE_ERR 7 /* write IO error */
/* these are flags for extent_clear_unlock_delalloc */
#define PAGE_UNLOCK (1 << 0)
@@ -174,17 +176,17 @@ struct extent_state {
#define INLINE_EXTENT_BUFFER_PAGES 16
#define MAX_INLINE_EXTENT_BUFFER_SIZE (INLINE_EXTENT_BUFFER_PAGES * PAGE_SIZE)
+
+/* Forward declaration */
+struct extent_buffer_head;
+
struct extent_buffer {
u64 start;
unsigned long len;
- unsigned long bflags;
- struct btrfs_fs_info *fs_info;
- spinlock_t refs_lock;
- atomic_t refs;
- atomic_t io_pages;
+ unsigned long ebflags;
+ struct extent_buffer_head *ebh;
+ struct extent_buffer *eb_next;
int read_mirror;
- struct rcu_head rcu_head;
- pid_t lock_owner;
/* count of read lock holders on the extent buffer */
atomic_t write_locks;
@@ -197,6 +199,8 @@ struct extent_buffer {
/* >= 0 if eb belongs to a log tree, -1 otherwise */
short log_index;
+ pid_t lock_owner;
+
/* protects write locks */
rwlock_t lock;
@@ -209,7 +213,20 @@ struct extent_buffer {
* to unlock
*/
wait_queue_head_t read_lock_wq;
+ wait_queue_head_t lock_wq;
+};
+
+struct extent_buffer_head {
+ unsigned long bflags;
+ struct btrfs_fs_info *fs_info;
+ spinlock_t refs_lock;
+ atomic_t refs;
+ atomic_t io_bvecs;
+ struct rcu_head rcu_head;
+
struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
+
+ struct extent_buffer eb;
#ifdef CONFIG_BTRFS_DEBUG
struct list_head leak_list;
#endif
@@ -237,6 +254,14 @@ static inline int extent_compress_type(unsigned long bio_flags)
return bio_flags >> EXTENT_BIO_FLAG_SHIFT;
}
+/*
+ * return the extent_buffer_head that contains the extent buffer provided.
+ */
+static inline struct extent_buffer_head *eb_head(struct extent_buffer *eb)
+{
+ return eb->ebh;
+
+}
struct extent_map_tree;
typedef struct extent_map *(get_extent_t)(struct inode *inode,
@@ -430,7 +455,7 @@ static inline unsigned long num_extent_pages(u64 start, u64 len)
static inline void extent_buffer_get(struct extent_buffer *eb)
{
- atomic_inc(&eb->refs);
+ atomic_inc(&eb_head(eb)->refs);
}
int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 9fcd6df..2b6024f 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -45,7 +45,7 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
if (!need_reset && btrfs_root_generation(item)
!= btrfs_root_generation_v2(item)) {
if (btrfs_root_generation_v2(item) != 0) {
- btrfs_warn(eb->fs_info,
+ btrfs_warn(eb_head(eb)->fs_info,
"mismatching "
"generation and generation_v2 "
"found in root item. This root "
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bd0f45f..f6aa4f5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6528,7 +6528,7 @@ int btrfs_read_sys_array(struct btrfs_root *root)
* to silence the warning eg. on PowerPC 64.
*/
if (PAGE_SIZE > BTRFS_SUPER_INFO_SIZE)
- SetPageUptodate(sb->pages[0]);
+ SetPageUptodate(eb_head(sb)->pages[0]);
write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE);
array_size = btrfs_super_sys_array_size(super_copy);
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index e90e82a..4fc0b40 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -700,7 +700,7 @@ TRACE_EVENT(btrfs_cow_block,
TP_fast_assign(
__entry->root_objectid = root->root_key.objectid;
__entry->buf_start = buf->start;
- __entry->refs = atomic_read(&buf->refs);
+ __entry->refs = atomic_read(&eb_head(buf)->refs);
__entry->cow_start = cow->start;
__entry->buf_level = btrfs_header_level(buf);
__entry->cow_level = btrfs_header_level(cow);
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH V16 04/18] Btrfs: subpage-blocksize: Define extent_buffer_head.
2016-04-14 8:32 ` [PATCH V16 04/18] Btrfs: subpage-blocksize: Define extent_buffer_head Chandan Rajendra
@ 2016-04-14 9:57 ` kbuild test robot
0 siblings, 0 replies; 22+ messages in thread
From: kbuild test robot @ 2016-04-14 9:57 UTC (permalink / raw)
To: Chandan Rajendra
Cc: kbuild-all, linux-btrfs, Chandan Rajendra, dsterba, clm, jbacik,
chandan, aneesh.kumar
[-- Attachment #1: Type: text/plain, Size: 3565 bytes --]
Hi Chandan,
[auto build test WARNING on tip/perf/core]
[also build test WARNING on v4.6-rc3 next-20160414]
[cannot apply to btrfs/next]
[if your patch is applied to the wrong git tree, please drop us a note to help improving the system]
url: https://github.com/0day-ci/linux/commits/Chandan-Rajendra/Allow-I-O-on-blocks-whose-size-is-less-than-page-size/20160414-163922
config: x86_64-randconfig-s1-04141600 (attached as .config)
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
All warnings (new ones prefixed by >>):
fs/btrfs/extent_io.c: In function 'alloc_test_extent_buffer':
fs/btrfs/extent_io.c:5037:4: error: 'struct extent_buffer' has no member named 'fs_info'
eb->fs_info = fs_info;
^
fs/btrfs/extent_io.c:5055:41: error: 'struct extent_buffer' has no member named 'bflags'
set_bit(EXTENT_BUFFER_HEAD_IN_TREE, &eb->bflags);
^
fs/btrfs/extent_io.c:5063:16: error: 'struct extent_buffer' has no member named 'refs'
atomic_inc(&eb->refs);
^
In file included from arch/x86/include/asm/bitops.h:15:0,
from include/linux/bitops.h:36,
from fs/btrfs/extent_io.c:1:
fs/btrfs/extent_io.c: In function 'release_extent_buffer':
fs/btrfs/extent_io.c:5233:16: error: 'buf' undeclared (first use in this function)
&eb_head(buf)->bflags))) {
^
include/linux/compiler.h:151:30: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^
>> fs/btrfs/extent_io.c:5232:3: note: in expansion of macro 'if'
if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
^
>> fs/btrfs/extent_io.c:5232:7: note: in expansion of macro 'unlikely'
if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
^
fs/btrfs/extent_io.c:5232:16: note: in expansion of macro 'test_bit'
if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
^
fs/btrfs/extent_io.c:5233:16: note: each undeclared identifier is reported only once for each function it appears in
&eb_head(buf)->bflags))) {
^
include/linux/compiler.h:151:30: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^
>> fs/btrfs/extent_io.c:5232:3: note: in expansion of macro 'if'
if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
^
>> fs/btrfs/extent_io.c:5232:7: note: in expansion of macro 'unlikely'
if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
^
fs/btrfs/extent_io.c:5232:16: note: in expansion of macro 'test_bit'
if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
^
fs/btrfs/extent_io.c:5234:33: error: 'eb' undeclared (first use in this function)
__free_extent_buffer(eb_head(eb));
^
vim +/if +5232 fs/btrfs/extent_io.c
5226 spin_unlock(&ebh->refs_lock);
5227 }
5228
5229 /* Should be safe to release our pages at this point */
5230 btrfs_release_extent_buffer_page(&ebh->eb);
5231 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
> 5232 if (unlikely(test_bit(EXTENT_BUFFER_HEAD_DUMMY,
> 5233 &eb_head(buf)->bflags))) {
5234 __free_extent_buffer(eb_head(eb));
5235 return 1;
5236 }
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/octet-stream, Size: 28671 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH V16 05/18] Btrfs: subpage-blocksize: Read tree blocks whose size is < PAGE_CACHE_SIZE
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (3 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 04/18] Btrfs: subpage-blocksize: Define extent_buffer_head Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 06/18] Btrfs: subpage-blocksize: Write only dirty extent buffers belonging to a page Chandan Rajendra
` (13 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
In the case of subpage-blocksize, this patch makes it possible to read
only a single metadata block from the disk instead of all the metadata
blocks that map into a page.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/disk-io.c | 52 +++++++++------------
fs/btrfs/disk-io.h | 3 ++
fs/btrfs/extent_io.c | 124 +++++++++++++++++++++++++++++++++++++++++++++++----
3 files changed, 139 insertions(+), 40 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f0cf922..55be491 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -612,29 +612,36 @@ static noinline int check_leaf(struct btrfs_root *root,
return 0;
}
-static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
- u64 phy_offset, struct page *page,
- u64 start, u64 end, int mirror)
+int verify_extent_buffer_read(struct btrfs_io_bio *io_bio,
+ struct page *page,
+ u64 start, u64 end, int mirror)
{
- u64 found_start;
- int found_level;
+ struct address_space *mapping = (io_bio->bio).bi_io_vec->bv_page->mapping;
+ struct extent_buffer_head *ebh;
struct extent_buffer *eb;
- struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
+ struct btrfs_root *root = BTRFS_I(mapping->host)->root;
struct btrfs_fs_info *fs_info = root->fs_info;
- int ret = 0;
+ u64 found_start;
+ int found_level;
int reads_done;
-
- if (!page->private)
- goto out;
+ int ret = 0;
eb = (struct extent_buffer *)page->private;
+ do {
+ if ((eb->start <= start) && (eb->start + eb->len - 1 > start))
+ break;
+ } while ((eb = eb->eb_next) != NULL);
+
+ ASSERT(eb);
+
+ ebh = eb_head(eb);
/* the pending IO might have been the only thing that kept this buffer
* in memory. Make sure we have a ref for all this other checks
*/
extent_buffer_get(eb);
- reads_done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
+ reads_done = atomic_dec_and_test(&ebh->io_bvecs);
if (!reads_done)
goto err;
@@ -690,30 +697,13 @@ err:
btree_readahead_hook(fs_info, eb, eb->start, ret);
if (ret) {
- /*
- * our io error hook is going to dec the io pages
- * again, we have to make sure it has something
- * to decrement
- */
atomic_inc(&eb_head(eb)->io_bvecs);
clear_extent_buffer_uptodate(eb);
}
- free_extent_buffer(eb);
-out:
- return ret;
-}
-static int btree_io_failed_hook(struct page *page, int failed_mirror)
-{
- struct extent_buffer *eb;
+ free_extent_buffer(eb);
- eb = (struct extent_buffer *)page->private;
- set_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags);
- eb->read_mirror = failed_mirror;
- atomic_dec(&eb_head(eb)->io_bvecs);
- if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->ebflags))
- btree_readahead_hook(eb_head(eb)->fs_info, eb, eb->start, -EIO);
- return -EIO; /* we fixed nothing */
+ return ret;
}
static void end_workqueue_bio(struct bio *bio)
@@ -4505,8 +4495,6 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
}
static const struct extent_io_ops btree_extent_io_ops = {
- .readpage_end_io_hook = btree_readpage_end_io_hook,
- .readpage_io_failed_hook = btree_io_failed_hook,
.submit_bio_hook = btree_submit_bio_hook,
/* note we're sharing with inode.c for the merge bio hook */
.merge_bio_hook = btrfs_merge_bio_hook,
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8e79d00..c6ae230 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -113,6 +113,9 @@ static inline void btrfs_put_fs_root(struct btrfs_root *root)
kfree(root);
}
+int verify_extent_buffer_read(struct btrfs_io_bio *io_bio,
+ struct page *page,
+ u64 start, u64 end, int mirror);
void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
int atomic);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4a62196..5ee2827 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -14,6 +14,7 @@
#include "extent_io.h"
#include "extent_map.h"
#include "ctree.h"
+#include "disk-io.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "check-integrity.h"
@@ -2173,7 +2174,7 @@ int repair_eb_io_failure(struct btrfs_root *root, struct extent_buffer *eb,
struct page *p = eb_head(eb)->pages[i];
ret = repair_io_failure(root->fs_info->btree_inode, start,
- PAGE_SIZE, start, p,
+ eb->len, start, p,
start - page_offset(p), mirror_num);
if (ret)
break;
@@ -3723,6 +3724,80 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
return ret;
}
+static void end_bio_extent_buffer_readpage(struct bio *bio)
+{
+ struct address_space *mapping = bio->bi_io_vec->bv_page->mapping;
+ struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
+ struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+ struct extent_buffer *eb;
+ struct btrfs_root *root;
+ struct bio_vec *bvec;
+ struct page *page;
+ int uptodate = !bio->bi_error;
+ u64 start;
+ u64 end;
+ int mirror;
+ int ret;
+ int i;
+
+ bio_for_each_segment_all(bvec, bio, i) {
+ page = bvec->bv_page;
+ root = BTRFS_I(page->mapping->host)->root;
+
+ start = page_offset(page) + bvec->bv_offset;
+ end = start + bvec->bv_len - 1;
+
+ if (!page->private) {
+ unlock_page(page);
+ clear_extent_bit(tree, start, end,
+ EXTENT_LOCKED, 1, 0, NULL,
+ GFP_ATOMIC);
+ continue;
+ }
+
+ eb = (struct extent_buffer *)page->private;
+
+ do {
+ /*
+ read_extent_buffer_pages() does not start
+ I/O on PG_uptodate pages. Hence the bio may
+ map only part of the extent buffer.
+ */
+ if ((eb->start <= start) && (eb->start + eb->len - 1 > start))
+ break;
+ } while ((eb = eb->eb_next) != NULL);
+
+ BUG_ON(!eb);
+
+ mirror = io_bio->mirror_num;
+
+ if (uptodate) {
+ ret = verify_extent_buffer_read(io_bio, page, start,
+ end, mirror);
+ if (ret)
+ uptodate = 0;
+ }
+
+ if (!uptodate) {
+ set_bit(EXTENT_BUFFER_READ_ERR, &eb->ebflags);
+ eb->read_mirror = mirror;
+ atomic_dec(&eb_head(eb)->io_bvecs);
+ if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD,
+ &eb->ebflags))
+ btree_readahead_hook(root->fs_info, eb, eb->start,
+ -EIO);
+ ClearPageUptodate(page);
+ SetPageError(page);
+ }
+
+ unlock_page(page);
+ clear_extent_bit(tree, start, end,
+ EXTENT_LOCKED, 1, 0, NULL, GFP_ATOMIC);
+ }
+
+ bio_put(bio);
+}
+
static void end_extent_buffer_writeback(struct extent_buffer *eb)
{
clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags);
@@ -5418,6 +5493,9 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
struct extent_buffer *eb, u64 start, int wait,
get_extent_t *get_extent, int mirror_num)
{
+ struct inode *inode = tree->mapping->host;
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ struct extent_state *cached_state = NULL;
unsigned long i;
unsigned long start_i;
struct page *page;
@@ -5445,10 +5523,17 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
for (i = start_i; i < num_pages; i++) {
page = eb_head(eb)->pages[i];
if (wait == WAIT_NONE) {
- if (!trylock_page(page))
+ if (!trylock_page(page)) {
goto unlock_exit;
+ } else {
+ if (PageWriteback(page)) {
+ unlock_page(page);
+ goto unlock_exit;
+ }
+ }
} else {
lock_page(page);
+ wait_on_page_writeback(page);
}
locked_pages++;
if (!PageUptodate(page)) {
@@ -5469,10 +5554,32 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
page = eb_head(eb)->pages[i];
if (!PageUptodate(page)) {
ClearPageError(page);
- err = __extent_read_full_page(tree, page,
- get_extent, &bio,
- mirror_num, &bio_flags,
- READ | REQ_META);
+ if (eb->len < PAGE_SIZE) {
+ lock_extent_bits(tree, eb->start, eb->start + eb->len - 1,
+ &cached_state);
+ err = submit_extent_page(READ | REQ_META, tree,
+ NULL, page,
+ eb->start >> 9, eb->len,
+ eb->start - page_offset(page),
+ fs_info->fs_devices->latest_bdev,
+ &bio, -1,
+ end_bio_extent_buffer_readpage,
+ mirror_num, bio_flags,
+ bio_flags, false);
+ } else {
+ lock_extent_bits(tree, page_offset(page),
+ page_offset(page) + PAGE_SIZE - 1,
+ &cached_state);
+ err = submit_extent_page(READ | REQ_META, tree,
+ NULL, page,
+ page_offset(page) >> 9,
+ PAGE_SIZE, 0,
+ fs_info->fs_devices->latest_bdev,
+ &bio, -1,
+ end_bio_extent_buffer_readpage,
+ mirror_num, bio_flags,
+ bio_flags, false);
+ }
if (err)
ret = err;
} else {
@@ -5493,10 +5600,11 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
for (i = start_i; i < num_pages; i++) {
page = eb_head(eb)->pages[i];
wait_on_page_locked(page);
- if (!PageUptodate(page))
- ret = -EIO;
}
+ if (!extent_buffer_uptodate(eb))
+ ret = -EIO;
+
return ret;
unlock_exit:
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 06/18] Btrfs: subpage-blocksize: Write only dirty extent buffers belonging to a page
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (4 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 05/18] Btrfs: subpage-blocksize: Read tree blocks whose size is < PAGE_CACHE_SIZE Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 07/18] Btrfs: subpage-blocksize: Allow mounting filesystems where sectorsize < PAGE_SIZE Chandan Rajendra
` (12 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
For the subpage-blocksize scenario, this patch adds the ability to write
a single extent buffer to the disk.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/disk-io.c | 32 +++---
fs/btrfs/extent_io.c | 277 +++++++++++++++++++++++++++++++++++++++++----------
2 files changed, 242 insertions(+), 67 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 55be491..708b8cb 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -504,28 +504,30 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
{
- u64 start = page_offset(page);
- u64 found_start;
struct extent_buffer *eb;
+ u64 found_start;
+ int ret;
eb = (struct extent_buffer *)page->private;
if (page != eb_head(eb)->pages[0])
return 0;
- found_start = btrfs_header_bytenr(eb);
- /*
- * Please do not consolidate these warnings into a single if.
- * It is useful to know what went wrong.
- */
- if (WARN_ON(found_start != start))
- return -EUCLEAN;
- if (WARN_ON(!PageUptodate(page)))
- return -EUCLEAN;
-
- ASSERT(memcmp_extent_buffer(eb, fs_info->fsid,
- btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
+ do {
+ if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags))
+ continue;
+ if (WARN_ON(!test_bit(EXTENT_BUFFER_UPTODATE, &eb->ebflags)))
+ continue;
+ found_start = btrfs_header_bytenr(eb);
+ if (WARN_ON(found_start != eb->start))
+ return 0;
+ ASSERT(memcmp_extent_buffer(eb, fs_info->fsid,
+ btrfs_header_fsid(), BTRFS_FSID_SIZE) == 0);
+ ret = csum_tree_block(fs_info, eb, 0);
+ if (ret)
+ return ret;
+ } while ((eb = eb->eb_next) != NULL);
- return csum_tree_block(fs_info, eb, 0);
+ return 0;
}
static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 5ee2827..bbf5841 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3653,29 +3653,49 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
TASK_UNINTERRUPTIBLE);
}
-static noinline_for_stack int
-lock_extent_buffer_for_io(struct extent_buffer *eb,
- struct btrfs_fs_info *fs_info,
- struct extent_page_data *epd)
+static void lock_extent_buffer_pages(struct extent_buffer_head *ebh,
+ struct extent_page_data *epd)
{
+ struct extent_buffer *eb = &ebh->eb;
unsigned long i, num_pages;
- int flush = 0;
+
+ num_pages = num_extent_pages(eb->start, eb->len);
+ for (i = 0; i < num_pages; i++) {
+ struct page *p = ebh->pages[i];
+ if (!trylock_page(p)) {
+ flush_write_bio(epd);
+ lock_page(p);
+ }
+ }
+
+ return;
+}
+
+static int noinline_for_stack
+lock_extent_buffer_for_io(struct extent_buffer *eb,
+ struct btrfs_fs_info *fs_info,
+ struct extent_page_data *epd)
+{
+ int dirty;
int ret = 0;
if (!btrfs_try_tree_write_lock(eb)) {
- flush = 1;
flush_write_bio(epd);
btrfs_tree_lock(eb);
}
if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags)) {
+ dirty = test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags);
btrfs_tree_unlock(eb);
- if (!epd->sync_io)
- return 0;
- if (!flush) {
- flush_write_bio(epd);
- flush = 1;
+ if (!epd->sync_io) {
+ if (!dirty)
+ return 1;
+ else
+ return 2;
}
+
+ flush_write_bio(epd);
+
while (1) {
wait_on_extent_buffer_writeback(eb);
btrfs_tree_lock(eb);
@@ -3698,29 +3718,14 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-eb->len,
fs_info->dirty_metadata_batch);
- ret = 1;
+ ret = 0;
} else {
spin_unlock(&eb_head(eb)->refs_lock);
+ ret = 1;
}
btrfs_tree_unlock(eb);
- if (!ret)
- return ret;
-
- num_pages = num_extent_pages(eb->start, eb->len);
- for (i = 0; i < num_pages; i++) {
- struct page *p = eb_head(eb)->pages[i];
-
- if (!trylock_page(p)) {
- if (!flush) {
- flush_write_bio(epd);
- flush = 1;
- }
- lock_page(p);
- }
- }
-
return ret;
}
@@ -3805,9 +3810,8 @@ static void end_extent_buffer_writeback(struct extent_buffer *eb)
wake_up_bit(&eb->ebflags, EXTENT_BUFFER_WRITEBACK);
}
-static void set_btree_ioerr(struct page *page)
+static void set_btree_ioerr(struct extent_buffer *eb, struct page *page)
{
- struct extent_buffer *eb = (struct extent_buffer *)page->private;
struct extent_buffer_head *ebh = eb_head(eb);
struct btrfs_inode *btree_ino = BTRFS_I(ebh->fs_info->btree_inode);
@@ -3868,7 +3872,8 @@ static void set_btree_ioerr(struct page *page)
}
}
-static void end_bio_extent_buffer_writepage(struct bio *bio)
+
+static void end_bio_subpagesize_blocksize_ebh_writepage(struct bio *bio)
{
struct bio_vec *bvec;
struct extent_buffer *eb;
@@ -3876,15 +3881,58 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
+ u64 start, end;
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
+ start = page_offset(page) + bvec->bv_offset;
+ end = start + bvec->bv_len - 1;
+
+ do {
+ if (!(eb->start >= start
+ && (eb->start + eb->len) <= (end + 1))) {
+ continue;
+ }
+
+ done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
+
+ if (bio->bi_error
+ || test_bit(EXTENT_BUFFER_WRITE_ERR,
+ &eb->ebflags)) {
+ ClearPageUptodate(page);
+ set_btree_ioerr(eb, page);
+ }
+
+ if (done)
+ end_page_writeback(page);
+
+ end_extent_buffer_writeback(eb);
+
+ } while ((eb = eb->eb_next) != NULL);
+
+ }
+
+ bio_put(bio);
+}
+
+static void end_bio_regular_ebh_writepage(struct bio *bio)
+{
+ struct extent_buffer *eb;
+ struct bio_vec *bvec;
+ int i, done;
+
+ bio_for_each_segment_all(bvec, bio, i) {
+ struct page *page = bvec->bv_page;
+
+ eb = (struct extent_buffer *)page->private;
+ BUG_ON(!eb);
+
done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
if (bio->bi_error ||
test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags)) {
ClearPageUptodate(page);
- set_btree_ioerr(page);
+ set_btree_ioerr(eb, page);
}
end_page_writeback(page);
@@ -3898,14 +3946,17 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
bio_put(bio);
}
-static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
- struct btrfs_fs_info *fs_info,
- struct writeback_control *wbc,
- struct extent_page_data *epd)
+
+static noinline_for_stack int
+write_regular_ebh(struct extent_buffer_head *ebh,
+ struct btrfs_fs_info *fs_info,
+ struct writeback_control *wbc,
+ struct extent_page_data *epd)
{
struct block_device *bdev = fs_info->fs_devices->latest_bdev;
struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
- u64 offset = eb->start;
+ struct extent_buffer *eb = &ebh->eb;
+ u64 offset = eb->start & ~(PAGE_SIZE - 1);
unsigned long i, num_pages;
unsigned long bio_flags = 0;
int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
@@ -3924,11 +3975,11 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
set_page_writeback(p);
ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
PAGE_SIZE, 0, bdev, &epd->bio,
- -1, end_bio_extent_buffer_writepage,
- 0, epd->bio_flags, bio_flags, false);
+ -1, end_bio_regular_ebh_writepage,
+ 0, epd->bio_flags, bio_flags, false);
epd->bio_flags = bio_flags;
if (ret) {
- set_btree_ioerr(p);
+ set_btree_ioerr(eb, p);
end_page_writeback(p);
if (atomic_sub_and_test(num_pages - i,
&eb_head(eb)->io_bvecs))
@@ -3952,12 +4003,84 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
return ret;
}
+static int write_subpagesize_blocksize_ebh(struct extent_buffer_head *ebh,
+ struct btrfs_fs_info *fs_info,
+ struct writeback_control *wbc,
+ struct extent_page_data *epd,
+ unsigned long ebs_to_write)
+{
+ struct block_device *bdev = fs_info->fs_devices->latest_bdev;
+ struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
+ struct extent_buffer *eb;
+ struct page *p;
+ u64 offset;
+ unsigned long i;
+ unsigned long bio_flags = 0;
+ int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
+ int ret = 0, err = 0;
+
+ eb = &ebh->eb;
+ p = ebh->pages[0];
+ clear_page_dirty_for_io(p);
+ set_page_writeback(p);
+ i = 0;
+ do {
+ if (!test_bit(i++, &ebs_to_write))
+ continue;
+
+ clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags);
+ atomic_inc(&eb_head(eb)->io_bvecs);
+
+ if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
+ bio_flags = EXTENT_BIO_TREE_LOG;
+
+ offset = eb->start - page_offset(p);
+
+ ret = submit_extent_page(rw, tree, wbc, p, eb->start >> 9,
+ eb->len, offset,
+ bdev, &epd->bio, -1,
+ end_bio_subpagesize_blocksize_ebh_writepage,
+ 0, epd->bio_flags, bio_flags, false);
+ epd->bio_flags = bio_flags;
+ if (ret) {
+ set_btree_ioerr(eb, p);
+ atomic_dec(&eb_head(eb)->io_bvecs);
+ end_extent_buffer_writeback(eb);
+ err = -EIO;
+ }
+ } while ((eb = eb->eb_next) != NULL);
+
+ if (!err) {
+ update_nr_written(p, wbc, 1);
+ }
+
+ unlock_page(p);
+
+ return ret;
+}
+
+static void redirty_extent_buffer_pages_for_writepage(struct extent_buffer *eb,
+ struct writeback_control *wbc)
+{
+ unsigned long i, num_pages;
+ struct page *p;
+
+ num_pages = num_extent_pages(eb->start, eb->len);
+ for (i = 0; i < num_pages; i++) {
+ p = eb_head(eb)->pages[i];
+ redirty_page_for_writepage(wbc, p);
+ }
+
+ return;
+}
+
int btree_write_cache_pages(struct address_space *mapping,
- struct writeback_control *wbc)
+ struct writeback_control *wbc)
{
struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree;
struct btrfs_fs_info *fs_info = BTRFS_I(mapping->host)->root->fs_info;
- struct extent_buffer *eb, *prev_eb = NULL;
+ struct extent_buffer *eb;
+ struct extent_buffer_head *ebh, *prev_ebh = NULL;
struct extent_page_data epd = {
.bio = NULL,
.tree = tree,
@@ -3968,6 +4091,7 @@ int btree_write_cache_pages(struct address_space *mapping,
int ret = 0;
int done = 0;
int nr_to_write_done = 0;
+ unsigned long ebs_to_write, dirty_ebs;
struct pagevec pvec;
int nr_pages;
pgoff_t index;
@@ -3994,7 +4118,7 @@ retry:
while (!done && !nr_to_write_done && (index <= end) &&
(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
- unsigned i;
+ unsigned i, j;
scanned = 1;
for (i = 0; i < nr_pages; i++) {
@@ -4026,30 +4150,79 @@ retry:
continue;
}
- if (eb == prev_eb) {
+ ebh = eb_head(eb);
+ if (ebh == prev_ebh) {
spin_unlock(&mapping->private_lock);
continue;
}
- ret = atomic_inc_not_zero(&eb_head(eb)->refs);
+ ret = atomic_inc_not_zero(&ebh->refs);
spin_unlock(&mapping->private_lock);
if (!ret)
continue;
- prev_eb = eb;
- ret = lock_extent_buffer_for_io(eb, fs_info, &epd);
- if (!ret) {
- free_extent_buffer(eb);
+ prev_ebh = ebh;
+
+ j = 0;
+ ebs_to_write = dirty_ebs = 0;
+ eb = &ebh->eb;
+ do {
+ BUG_ON(j >= BITS_PER_LONG);
+
+ ret = lock_extent_buffer_for_io(eb, fs_info, &epd);
+ switch (ret) {
+ case 0:
+ /*
+ EXTENT_BUFFER_DIRTY was set and we were able to
+ clear it.
+ */
+ set_bit(j, &ebs_to_write);
+ break;
+ case 2:
+ /*
+ EXTENT_BUFFER_DIRTY was set, but we were unable
+ to clear EXTENT_BUFFER_WRITEBACK that was set
+ before we got the extent buffer locked.
+ */
+ set_bit(j, &dirty_ebs);
+ default:
+ /*
+ EXTENT_BUFFER_DIRTY wasn't set.
+ */
+ break;
+ }
+ ++j;
+ } while ((eb = eb->eb_next) != NULL);
+
+ ret = 0;
+
+ if (!ebs_to_write) {
+ free_extent_buffer(&ebh->eb);
continue;
}
- ret = write_one_eb(eb, fs_info, wbc, &epd);
+ /*
+ Now that we know that atleast one of the extent buffer
+ belonging to the extent buffer head must be written to
+ the disk, lock the extent_buffer_head's pages.
+ */
+ lock_extent_buffer_pages(ebh, &epd);
+
+ if (ebh->eb.len < PAGE_SIZE) {
+ ret = write_subpagesize_blocksize_ebh(ebh, fs_info, wbc, &epd, ebs_to_write);
+ if (dirty_ebs) {
+ redirty_extent_buffer_pages_for_writepage(&ebh->eb, wbc);
+ }
+ } else {
+ ret = write_regular_ebh(ebh, fs_info, wbc, &epd);
+ }
+
if (ret) {
done = 1;
- free_extent_buffer(eb);
+ free_extent_buffer(&ebh->eb);
break;
}
- free_extent_buffer(eb);
+ free_extent_buffer(&ebh->eb);
/*
* the filesystem may choose to bump up nr_to_write.
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 07/18] Btrfs: subpage-blocksize: Allow mounting filesystems where sectorsize < PAGE_SIZE
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (5 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 06/18] Btrfs: subpage-blocksize: Write only dirty extent buffers belonging to a page Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 08/18] Btrfs: subpage-blocksize: Deal with partial ordered extent allocations Chandan Rajendra
` (11 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
This patch allows mounting filesystems with sectorsize smaller than the
PAGE_SIZE.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/disk-io.c | 10 +++-------
1 file changed, 3 insertions(+), 7 deletions(-)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 708b8cb..1db0063 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4076,17 +4076,12 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
* Check sectorsize and nodesize first, other check will need it.
* Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
*/
- if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+ if (!is_power_of_2(sectorsize) || sectorsize < 2048 ||
sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize);
ret = -EINVAL;
}
- /* Only PAGE SIZE is supported yet */
- if (sectorsize != PAGE_SIZE) {
- printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n",
- sectorsize, PAGE_SIZE);
- ret = -EINVAL;
- }
+
if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize);
@@ -4110,6 +4105,7 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
btrfs_super_chunk_root(sb));
ret = -EINVAL;
}
+
if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
btrfs_super_log_root(sb));
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 08/18] Btrfs: subpage-blocksize: Deal with partial ordered extent allocations.
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (6 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 07/18] Btrfs: subpage-blocksize: Allow mounting filesystems where sectorsize < PAGE_SIZE Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 09/18] Btrfs: subpage-blocksize: Explicitly track I/O status of blocks of an ordered extent Chandan Rajendra
` (10 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
In subpage-blocksize scenario, extent allocations for only some of the
dirty blocks of a page can succeed, while allocation for rest of the
blocks can fail. This patch allows I/O against such pages to be
submitted.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/extent_io.c | 27 ++++++++++++++-------------
fs/btrfs/inode.c | 39 ++++++++++++++++++++++++++-------------
2 files changed, 40 insertions(+), 26 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index bbf5841..e14bcef 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1851,17 +1851,23 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
if (page_ops & PAGE_SET_PRIVATE2)
SetPagePrivate2(pages[i]);
+ if (page_ops & PAGE_SET_ERROR)
+ SetPageError(pages[i]);
+
if (pages[i] == locked_page) {
put_page(pages[i]);
continue;
}
- if (page_ops & PAGE_CLEAR_DIRTY)
+
+ if ((page_ops & PAGE_CLEAR_DIRTY)
+ && !PagePrivate2(pages[i]))
clear_page_dirty_for_io(pages[i]);
- if (page_ops & PAGE_SET_WRITEBACK)
+ if ((page_ops & PAGE_SET_WRITEBACK)
+ && !PagePrivate2(pages[i]))
set_page_writeback(pages[i]);
- if (page_ops & PAGE_SET_ERROR)
- SetPageError(pages[i]);
- if (page_ops & PAGE_END_WRITEBACK)
+
+ if ((page_ops & PAGE_END_WRITEBACK)
+ && !PagePrivate2(pages[i]))
end_page_writeback(pages[i]);
if (page_ops & PAGE_UNLOCK)
unlock_page(pages[i]);
@@ -2539,7 +2545,7 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
uptodate = 0;
}
- if (!uptodate) {
+ if (!uptodate || PageError(page)) {
ClearPageUptodate(page);
SetPageError(page);
ret = ret < 0 ? ret : -EIO;
@@ -3357,7 +3363,6 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
nr_written);
/* File system has been set read-only */
if (ret) {
- SetPageError(page);
/* fill_delalloc should be return < 0 for error
* but just in case, we use > 0 here meaning the
* IO is started, so we don't want to return > 0
@@ -3577,7 +3582,6 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
struct inode *inode = page->mapping->host;
struct extent_page_data *epd = data;
u64 start = page_offset(page);
- u64 page_end = start + PAGE_SIZE - 1;
int ret;
int nr = 0;
size_t pg_offset = 0;
@@ -3622,7 +3626,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
ret = writepage_delalloc(inode, page, wbc, epd, start, &nr_written);
if (ret == 1)
goto done_unlocked;
- if (ret)
+ if (ret && !PagePrivate2(page))
goto done;
ret = __extent_writepage_io(inode, page, wbc, epd,
@@ -3636,10 +3640,7 @@ done:
set_page_writeback(page);
end_page_writeback(page);
}
- if (PageError(page)) {
- ret = ret < 0 ? ret : -EIO;
- end_extent_writepage(page, ret, start, page_end);
- }
+
unlock_page(page);
return ret;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c333099..519ac44 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -940,6 +940,8 @@ static noinline int cow_file_range(struct inode *inode,
struct btrfs_key ins;
struct extent_map *em;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+ struct btrfs_ordered_extent *ordered;
+ unsigned long page_ops, extent_ops;
int ret = 0;
if (btrfs_is_free_space_inode(inode)) {
@@ -984,8 +986,6 @@ static noinline int cow_file_range(struct inode *inode,
btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
while (disk_num_bytes > 0) {
- unsigned long op;
-
cur_alloc_size = disk_num_bytes;
ret = btrfs_reserve_extent(root, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
@@ -1038,7 +1038,7 @@ static noinline int cow_file_range(struct inode *inode,
ret = btrfs_reloc_clone_csums(inode, start,
cur_alloc_size);
if (ret)
- goto out_drop_extent_cache;
+ goto out_remove_ordered_extent;
}
if (disk_num_bytes < cur_alloc_size)
@@ -1051,13 +1051,12 @@ static noinline int cow_file_range(struct inode *inode,
* Do set the Private2 bit so we know this page was properly
* setup for writepage
*/
- op = unlock ? PAGE_UNLOCK : 0;
- op |= PAGE_SET_PRIVATE2;
-
+ page_ops = unlock ? PAGE_UNLOCK : 0;
+ page_ops |= PAGE_SET_PRIVATE2;
+ extent_ops = EXTENT_LOCKED | EXTENT_DELALLOC;
extent_clear_unlock_delalloc(inode, start,
- start + ram_size - 1, locked_page,
- EXTENT_LOCKED | EXTENT_DELALLOC,
- op);
+ start + ram_size - 1, locked_page,
+ extent_ops, page_ops);
disk_num_bytes -= cur_alloc_size;
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
@@ -1066,16 +1065,30 @@ static noinline int cow_file_range(struct inode *inode,
out:
return ret;
+out_remove_ordered_extent:
+ ordered = btrfs_lookup_ordered_extent(inode, start);
+ BUG_ON(!ordered);
+ btrfs_remove_ordered_extent(inode, ordered);
+ /* once for us */
+ btrfs_put_ordered_extent(ordered);
+ /* once for the tree */
+ btrfs_put_ordered_extent(ordered);
+
out_drop_extent_cache:
btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
+
out_reserve:
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
+
out_unlock:
+ page_ops = unlock ? PAGE_UNLOCK : 0;
+ page_ops |= PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK
+ | PAGE_SET_ERROR;
+ extent_ops = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING
+ | EXTENT_DEFRAG;
+
extent_clear_unlock_delalloc(inode, start, end, locked_page,
- EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
- EXTENT_DELALLOC | EXTENT_DEFRAG,
- PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
- PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
+ extent_ops, page_ops);
goto out;
}
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 09/18] Btrfs: subpage-blocksize: Explicitly track I/O status of blocks of an ordered extent.
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (7 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 08/18] Btrfs: subpage-blocksize: Deal with partial ordered extent allocations Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 10/18] Btrfs: subpage-blocksize: btrfs_punch_hole: Fix uptodate blocks check Chandan Rajendra
` (9 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
In subpage-blocksize scenario a page can have more than one block. So in
addition to PagePrivate2 flag, we would have to track the I/O status of
each block of a page to reliably mark the ordered extent as complete.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/extent_io.c | 19 +--
fs/btrfs/extent_io.h | 5 +-
fs/btrfs/inode.c | 365 ++++++++++++++++++++++++++++++++++--------------
fs/btrfs/ordered-data.c | 19 +++
fs/btrfs/ordered-data.h | 4 +
5 files changed, 297 insertions(+), 115 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e14bcef..98fff69 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4569,11 +4569,10 @@ int extent_invalidatepage(struct extent_io_tree *tree,
* to drop the page.
*/
static int try_release_extent_state(struct extent_map_tree *map,
- struct extent_io_tree *tree,
- struct page *page, gfp_t mask)
+ struct extent_io_tree *tree,
+ struct page *page, u64 start, u64 end,
+ gfp_t mask)
{
- u64 start = page_offset(page);
- u64 end = start + PAGE_SIZE - 1;
int ret = 1;
if (test_range_bit(tree, start, end,
@@ -4607,12 +4606,12 @@ static int try_release_extent_state(struct extent_map_tree *map,
* map records are removed
*/
int try_release_extent_mapping(struct extent_map_tree *map,
- struct extent_io_tree *tree, struct page *page,
- gfp_t mask)
+ struct extent_io_tree *tree, struct page *page,
+ u64 start, u64 end, gfp_t mask)
{
struct extent_map *em;
- u64 start = page_offset(page);
- u64 end = start + PAGE_SIZE - 1;
+ u64 orig_start = start;
+ u64 orig_end = end;
if (gfpflags_allow_blocking(mask) &&
page->mapping->host->i_size > SZ_16M) {
@@ -4646,7 +4645,9 @@ int try_release_extent_mapping(struct extent_map_tree *map,
free_extent_map(em);
}
}
- return try_release_extent_state(map, tree, page, mask);
+ return try_release_extent_state(map, tree, page,
+ orig_start, orig_end,
+ mask);
}
/*
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 1996e08..db5ebaf 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -273,8 +273,9 @@ typedef struct extent_map *(get_extent_t)(struct inode *inode,
void extent_io_tree_init(struct extent_io_tree *tree,
struct address_space *mapping);
int try_release_extent_mapping(struct extent_map_tree *map,
- struct extent_io_tree *tree, struct page *page,
- gfp_t mask);
+ struct extent_io_tree *tree, struct page *page,
+ u64 start, u64 end,
+ gfp_t mask);
int try_release_extent_buffer(struct page *page);
int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 519ac44..2a6d829 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3038,56 +3038,119 @@ static void finish_ordered_fn(struct btrfs_work *work)
btrfs_finish_ordered_io(ordered_extent);
}
-static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state, int uptodate)
+static void mark_blks_io_complete(struct btrfs_ordered_extent *ordered,
+ u64 blk, u64 nr_blks, int uptodate)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = ordered->inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_ordered_extent *ordered_extent = NULL;
struct btrfs_workqueue *wq;
btrfs_work_func_t func;
- u64 ordered_start, ordered_end;
int done;
- trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
+ while (nr_blks--) {
+ if (test_and_set_bit(blk, ordered->blocks_done)) {
+ blk++;
+ continue;
+ }
- ClearPagePrivate2(page);
-loop:
- ordered_extent = btrfs_lookup_ordered_range(inode, start,
- end - start + 1);
- if (!ordered_extent)
- goto out;
+ done = btrfs_dec_test_ordered_pending(inode, &ordered,
+ ordered->file_offset
+ + (blk << inode->i_blkbits),
+ root->sectorsize,
+ uptodate);
+ if (done) {
+ if (btrfs_is_free_space_inode(inode)) {
+ wq = root->fs_info->endio_freespace_worker;
+ func = btrfs_freespace_write_helper;
+ } else {
+ wq = root->fs_info->endio_write_workers;
+ func = btrfs_endio_write_helper;
+ }
- ordered_start = max_t(u64, start, ordered_extent->file_offset);
- ordered_end = min_t(u64, end,
- ordered_extent->file_offset + ordered_extent->len - 1);
-
- done = btrfs_dec_test_ordered_pending(inode, &ordered_extent,
- ordered_start,
- ordered_end - ordered_start + 1,
- uptodate);
- if (done) {
- if (btrfs_is_free_space_inode(inode)) {
- wq = root->fs_info->endio_freespace_worker;
- func = btrfs_freespace_write_helper;
- } else {
- wq = root->fs_info->endio_write_workers;
- func = btrfs_endio_write_helper;
+ btrfs_init_work(&ordered->work, func,
+ finish_ordered_fn, NULL, NULL);
+ btrfs_queue_work(wq, &ordered->work);
}
- btrfs_init_work(&ordered_extent->work, func,
- finish_ordered_fn, NULL, NULL);
- btrfs_queue_work(wq, &ordered_extent->work);
+ blk++;
}
+}
- btrfs_put_ordered_extent(ordered_extent);
+int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
+ struct extent_state *state, int uptodate)
+{
+ struct inode *inode = page->mapping->host;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_ordered_extent *ordered_extent = NULL;
+ u64 blk, nr_blks;
+ int clear;
- start = ordered_end + 1;
+ trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
- if (start < end)
- goto loop;
+ while (start < end) {
+ ordered_extent = btrfs_lookup_ordered_extent(inode, start);
+ if (!ordered_extent) {
+ start += root->sectorsize;
+ continue;
+ }
+
+ blk = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ start - ordered_extent->file_offset);
+
+ nr_blks = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ min(end, ordered_extent->file_offset
+ + ordered_extent->len - 1)
+ + 1 - start);
+
+ BUG_ON(!nr_blks);
+
+ mark_blks_io_complete(ordered_extent, blk, nr_blks, uptodate);
+
+ start = ordered_extent->file_offset + ordered_extent->len;
+
+ btrfs_put_ordered_extent(ordered_extent);
+ }
+
+ start = page_offset(page);
+ end = start + PAGE_SIZE - 1;
+ clear = 1;
+
+ while (start < end) {
+ ordered_extent = btrfs_lookup_ordered_extent(inode, start);
+ if (!ordered_extent) {
+ start += root->sectorsize;
+ continue;
+ }
+
+ blk = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ start - ordered_extent->file_offset);
+ nr_blks = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ min(end, ordered_extent->file_offset
+ + ordered_extent->len - 1)
+ + 1 - start);
+
+ BUG_ON(!nr_blks);
+
+ while (nr_blks--) {
+ if (!test_bit(blk++, ordered_extent->blocks_done)) {
+ clear = 0;
+ break;
+ }
+ }
+
+ if (!clear) {
+ btrfs_put_ordered_extent(ordered_extent);
+ break;
+ }
+
+ start += ordered_extent->len;
+
+ btrfs_put_ordered_extent(ordered_extent);
+ }
+
+ if (clear)
+ ClearPagePrivate2(page);
-out:
return 0;
}
@@ -8752,7 +8815,9 @@ btrfs_readpages(struct file *file, struct address_space *mapping,
return extent_readpages(tree, mapping, pages, nr_pages,
btrfs_get_extent);
}
-static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
+
+static int __btrfs_releasepage(struct page *page, u64 start, u64 end,
+ gfp_t gfp_flags)
{
struct extent_io_tree *tree;
struct extent_map_tree *map;
@@ -8760,33 +8825,151 @@ static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags)
tree = &BTRFS_I(page->mapping->host)->io_tree;
map = &BTRFS_I(page->mapping->host)->extent_tree;
- ret = try_release_extent_mapping(map, tree, page, gfp_flags);
- if (ret == 1)
+
+ ret = try_release_extent_mapping(map, tree, page, start, end,
+ gfp_flags);
+ if ((ret == 1) && ((end - start + 1) == PAGE_SIZE)) {
clear_page_extent_mapped(page);
+ } else {
+ ret = 0;
+ }
return ret;
}
static int btrfs_releasepage(struct page *page, gfp_t gfp_flags)
{
+ u64 start = page_offset(page);
+ u64 end = start + PAGE_SIZE - 1;
+
if (PageWriteback(page) || PageDirty(page))
return 0;
- return __btrfs_releasepage(page, gfp_flags & GFP_NOFS);
+
+ return __btrfs_releasepage(page, start, end, gfp_flags & GFP_NOFS);
+}
+
+static void invalidate_ordered_extent_blocks(struct inode *inode,
+ struct btrfs_ordered_extent *ordered,
+ u64 locked_start, u64 locked_end,
+ u64 cur,
+ int inode_evicting)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_ordered_inode_tree *ordered_tree;
+ struct extent_io_tree *tree;
+ u64 blk, blk_done, nr_blks;
+ u64 end;
+ u64 new_len;
+
+ tree = &BTRFS_I(inode)->io_tree;
+
+ end = min(locked_end, ordered->file_offset + ordered->len - 1);
+
+ if (!inode_evicting) {
+ clear_extent_bit(tree, cur, end,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 0, NULL,
+ GFP_NOFS);
+ unlock_extent(tree, locked_start, locked_end);
+ }
+
+
+ ordered_tree = &BTRFS_I(inode)->ordered_tree;
+ spin_lock_irq(&ordered_tree->lock);
+ set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
+ new_len = cur - ordered->file_offset;
+ if (new_len < ordered->truncated_len)
+ ordered->truncated_len = new_len;
+
+ blk = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ cur - ordered->file_offset);
+ nr_blks = BTRFS_BYTES_TO_BLKS(root->fs_info, end + 1 - cur);
+
+ while (nr_blks--) {
+ blk_done = !test_and_set_bit(blk, ordered->blocks_done);
+ if (blk_done) {
+ spin_unlock_irq(&ordered_tree->lock);
+ if (btrfs_dec_test_ordered_pending(inode, &ordered,
+ ordered->file_offset + (blk << inode->i_blkbits),
+ root->sectorsize,
+ 1))
+ btrfs_finish_ordered_io(ordered);
+
+ spin_lock_irq(&ordered_tree->lock);
+ }
+ blk++;
+ }
+
+ spin_unlock_irq(&ordered_tree->lock);
+
+ if (!inode_evicting)
+ lock_extent_bits(tree, locked_start, locked_end, NULL);
+}
+
+static int page_blocks_written(struct page *page)
+{
+ struct btrfs_ordered_extent *ordered;
+ struct btrfs_root *root;
+ struct inode *inode;
+ unsigned long outstanding_blk;
+ u64 page_start, page_end;
+ u64 blk, last_blk, nr_blks;
+ u64 cur;
+ u64 len;
+
+ inode = page->mapping->host;
+ root = BTRFS_I(inode)->root;
+
+ page_start = page_offset(page);
+ page_end = page_start + PAGE_SIZE - 1;
+
+ cur = page_start;
+ while (cur < page_end) {
+ ordered = btrfs_lookup_ordered_extent(inode, cur);
+ if (!ordered) {
+ cur += root->sectorsize;
+ continue;
+ }
+
+ blk = BTRFS_BYTES_TO_BLKS(root->fs_info,
+ cur - ordered->file_offset);
+ len = min(page_end, ordered->file_offset + ordered->len - 1)
+ - cur + 1;
+ nr_blks = BTRFS_BYTES_TO_BLKS(root->fs_info, len);
+
+ last_blk = blk + nr_blks - 1;
+
+ outstanding_blk = find_next_zero_bit(ordered->blocks_done,
+ BTRFS_BYTES_TO_BLKS(root->fs_info,
+ ordered->len),
+ blk);
+ if (outstanding_blk <= last_blk) {
+ btrfs_put_ordered_extent(ordered);
+ return 0;
+ }
+
+ btrfs_put_ordered_extent(ordered);
+ cur += len;
+ }
+
+ return 1;
}
static void btrfs_invalidatepage(struct page *page, unsigned int offset,
- unsigned int length)
+ unsigned int length)
{
struct inode *inode = page->mapping->host;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *tree;
struct btrfs_ordered_extent *ordered;
- struct extent_state *cached_state = NULL;
- u64 page_start = page_offset(page);
- u64 page_end = page_start + PAGE_SIZE - 1;
- u64 start;
- u64 end;
+ u64 start, end, cur;
+ u64 page_start, page_end;
int inode_evicting = inode->i_state & I_FREEING;
+ page_start = page_offset(page);
+ page_end = page_start + PAGE_SIZE - 1;
+
/*
* we have the page locked, so new writeback can't start,
* and the dirty bit won't be cleared while we are here.
@@ -8797,61 +8980,35 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
wait_on_page_writeback(page);
tree = &BTRFS_I(inode)->io_tree;
- if (offset) {
+
+ start = round_up(offset, root->sectorsize);
+ end = round_down(offset + length, root->sectorsize) - 1;
+ if (end - start + 1 < root->sectorsize) {
btrfs_releasepage(page, GFP_NOFS);
return;
}
+ start = round_up(page_start + offset, root->sectorsize);
+ end = round_down(page_start + offset + length,
+ root->sectorsize) - 1;
+
if (!inode_evicting)
- lock_extent_bits(tree, page_start, page_end, &cached_state);
-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, start, end,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 0, &cached_state,
- GFP_NOFS);
- /*
- * whoever cleared the private bit is responsible
- * for the finish_ordered_io
- */
- if (TestClearPagePrivate2(page)) {
- struct btrfs_ordered_inode_tree *tree;
- u64 new_len;
+ lock_extent_bits(tree, start, end, NULL);
- tree = &BTRFS_I(inode)->ordered_tree;
+ cur = start;
+ while (cur < end) {
+ ordered = btrfs_lookup_ordered_extent(inode, cur);
+ if (!ordered) {
+ cur += root->sectorsize;
+ continue;
+ }
- spin_lock_irq(&tree->lock);
- set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
- new_len = start - ordered->file_offset;
- if (new_len < ordered->truncated_len)
- ordered->truncated_len = new_len;
- spin_unlock_irq(&tree->lock);
+ invalidate_ordered_extent_blocks(inode, ordered,
+ start, end, cur,
+ inode_evicting);
- if (btrfs_dec_test_ordered_pending(inode, &ordered,
- start,
- end - start + 1, 1))
- btrfs_finish_ordered_io(ordered);
- }
+ cur = min(end + 1, ordered->file_offset + ordered->len);
btrfs_put_ordered_extent(ordered);
- if (!inode_evicting) {
- cached_state = NULL;
- lock_extent_bits(tree, start, end,
- &cached_state);
- }
-
- start = end + 1;
- if (start < page_end)
- goto again;
}
/*
@@ -8867,26 +9024,26 @@ again:
*/
btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
- clear_page_blks_state(page, 1 << BLK_STATE_DIRTY, page_start, page_end);
+ clear_page_blks_state(page, 1 << BLK_STATE_DIRTY, start, end);
- if (!inode_evicting) {
- clear_extent_bit(tree, page_start, page_end,
- EXTENT_LOCKED | EXTENT_DIRTY |
- EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 1,
- &cached_state, GFP_NOFS);
+ if (page_blocks_written(page))
+ ClearPagePrivate2(page);
- __btrfs_releasepage(page, GFP_NOFS);
+ if (!inode_evicting) {
+ clear_extent_bit(tree, start, end,
+ EXTENT_LOCKED | EXTENT_DIRTY |
+ EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 1, NULL, GFP_NOFS);
+ __btrfs_releasepage(page, start, end, GFP_NOFS);
}
- ClearPageChecked(page);
- if (PagePrivate(page)) {
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
+ if (!offset && length == PAGE_SIZE) {
+ ClearPageChecked(page);
+ clear_page_extent_mapped(page);
}
}
+
/*
* btrfs_page_mkwrite() is not allowed to change the file size as it gets
* called from a page fault handler when a page is first dirtied. Hence we must
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 0de7da5..218fdc7 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -190,12 +190,27 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
struct btrfs_ordered_inode_tree *tree;
struct rb_node *node;
struct btrfs_ordered_extent *entry;
+ u64 nr_longs;
+ u64 nr_blks;
tree = &BTRFS_I(inode)->ordered_tree;
entry = kmem_cache_zalloc(btrfs_ordered_extent_cache, GFP_NOFS);
if (!entry)
return -ENOMEM;
+ nr_blks = BTRFS_BYTES_TO_BLKS(root->fs_info, len);
+ nr_longs = BITS_TO_LONGS(nr_blks);
+ if (nr_longs == 1) {
+ entry->blocks_done = &entry->blocks_bitmap;
+ } else {
+ entry->blocks_done = kzalloc(nr_longs * sizeof(unsigned long),
+ GFP_NOFS);
+ if (!entry->blocks_done) {
+ kmem_cache_free(btrfs_ordered_extent_cache, entry);
+ return -ENOMEM;
+ }
+ }
+
entry->file_offset = file_offset;
entry->start = start;
entry->len = len;
@@ -577,6 +592,10 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
list_del(&sum->list);
kfree(sum);
}
+
+ if (entry->blocks_done != &entry->blocks_bitmap)
+ kfree(entry->blocks_done);
+
kmem_cache_free(btrfs_ordered_extent_cache, entry);
}
}
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 23c9605..41264bc 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -139,6 +139,10 @@ struct btrfs_ordered_extent {
struct completion completion;
struct btrfs_work flush_work;
struct list_head work_list;
+
+ /* bitmap to track the blocks that have been written to disk */
+ unsigned long *blocks_done;
+ unsigned long blocks_bitmap;
};
/*
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 10/18] Btrfs: subpage-blocksize: btrfs_punch_hole: Fix uptodate blocks check
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (8 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 09/18] Btrfs: subpage-blocksize: Explicitly track I/O status of blocks of an ordered extent Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 11/18] Btrfs: subpage-blocksize: Prevent writes to an extent buffer when PG_writeback flag is set Chandan Rajendra
` (8 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
In case of subpage-blocksize, the file blocks to be punched may map only
part of a page. For file blocks inside such pages, we need to check for
the presence of BLK_STATE_UPTODATE flag.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/file.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 65 insertions(+), 1 deletion(-)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e2f0968..a17bcab 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2321,6 +2321,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
struct btrfs_path *path;
struct btrfs_block_rsv *rsv;
struct btrfs_trans_handle *trans;
+ struct address_space *mapping = inode->i_mapping;
+ pgoff_t start_index, end_index;
u64 lockstart;
u64 lockend;
u64 tail_start;
@@ -2333,6 +2335,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
int err = 0;
unsigned int rsv_count;
bool same_block;
+ bool same_page;
bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
u64 ino_size;
bool truncated_block = false;
@@ -2429,11 +2432,43 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
goto out_only_mutex;
}
+ start_index = lockstart >> PAGE_CACHE_SHIFT;
+ end_index = lockend >> PAGE_CACHE_SHIFT;
+
+ same_page = lockstart >> PAGE_CACHE_SHIFT
+ == lockend >> PAGE_CACHE_SHIFT;
+
while (1) {
struct btrfs_ordered_extent *ordered;
+ struct page *start_page = NULL;
+ struct page *end_page = NULL;
+ u64 nr_pages;
truncate_pagecache_range(inode, lockstart, lockend);
+ if (lockstart & (PAGE_CACHE_SIZE - 1)) {
+ start_page = find_or_create_page(mapping, start_index,
+ GFP_NOFS);
+ if (!start_page) {
+ mutex_unlock(&inode->i_mutex);
+ return -ENOMEM;
+ }
+ }
+
+ if (!same_page && ((lockend + 1) & (PAGE_CACHE_SIZE - 1))) {
+ end_page = find_or_create_page(mapping, end_index,
+ GFP_NOFS);
+ if (!end_page) {
+ if (start_page) {
+ unlock_page(start_page);
+ page_cache_release(start_page);
+ }
+ mutex_unlock(&inode->i_mutex);
+ return -ENOMEM;
+ }
+ }
+
+
lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state);
ordered = btrfs_lookup_first_ordered_extent(inode, lockend);
@@ -2443,18 +2478,47 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
* and nobody raced in and read a page in this range, if we did
* we need to try again.
*/
+ nr_pages = round_up(lockend, PAGE_CACHE_SIZE)
+ - round_down(lockstart, PAGE_CACHE_SIZE);
+ nr_pages >>= PAGE_CACHE_SHIFT;
+
if ((!ordered ||
(ordered->file_offset + ordered->len <= lockstart ||
ordered->file_offset > lockend)) &&
- !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
+ (!(start_page && PagePrivate(start_page) &&
+ test_page_blks_state(start_page, 1 << BLK_STATE_UPTODATE,
+ lockstart,
+ min(lockstart + PAGE_CACHE_SIZE - 1, lockend), 0)) &&
+ !(end_page && PagePrivate(end_page) &&
+ test_page_blks_state(end_page, 1 << BLK_STATE_UPTODATE,
+ page_offset(end_page), lockend, 0)) &&
+ !(nr_pages > 2 && btrfs_page_exists_in_range(inode,
+ round_up(lockstart, PAGE_CACHE_SIZE),
+ round_down(lockend, PAGE_CACHE_SIZE) - 1)))) {
if (ordered)
btrfs_put_ordered_extent(ordered);
+ if (end_page) {
+ unlock_page(end_page);
+ page_cache_release(end_page);
+ }
+ if (start_page) {
+ unlock_page(start_page);
+ page_cache_release(start_page);
+ }
break;
}
if (ordered)
btrfs_put_ordered_extent(ordered);
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
lockend, &cached_state, GFP_NOFS);
+ if (end_page) {
+ unlock_page(end_page);
+ page_cache_release(end_page);
+ }
+ if (start_page) {
+ unlock_page(start_page);
+ page_cache_release(start_page);
+ }
ret = btrfs_wait_ordered_range(inode, lockstart,
lockend - lockstart + 1);
if (ret) {
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 11/18] Btrfs: subpage-blocksize: Prevent writes to an extent buffer when PG_writeback flag is set
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (9 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 10/18] Btrfs: subpage-blocksize: btrfs_punch_hole: Fix uptodate blocks check Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 12/18] Revert "btrfs: fix lockups from btrfs_clear_path_blocking" Chandan Rajendra
` (7 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
In non-subpage-blocksize scenario, BTRFS_HEADER_FLAG_WRITTEN flag
prevents Btrfs code from writing into an extent buffer whose pages are
under writeback. This facility isn't sufficient for achieving the same
in subpage-blocksize scenario, since we have more than one extent buffer
mapped to a page.
Hence this patch adds a new flag (i.e. EXTENT_BUFFER_HEAD_WRITEBACK) and
corresponding code to track the writeback status of the page and to
prevent writes to any of the extent buffers mapped to the page while
writeback is going on.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/ctree.c | 21 ++++++-
fs/btrfs/extent-tree.c | 11 ++++
fs/btrfs/extent_io.c | 150 ++++++++++++++++++++++++++++++++++++++++---------
fs/btrfs/extent_io.h | 1 +
fs/btrfs/file.c | 34 +++++------
5 files changed, 172 insertions(+), 45 deletions(-)
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 23118f4..7d76add 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1539,6 +1539,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
struct extent_buffer *parent, int parent_slot,
struct extent_buffer **cow_ret)
{
+ struct extent_buffer_head *ebh = eb_head(buf);
u64 search_start;
int ret;
@@ -1552,6 +1553,14 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
trans->transid, root->fs_info->generation);
if (!should_cow_block(trans, root, buf)) {
+ if (test_bit(EXTENT_BUFFER_HEAD_WRITEBACK, &ebh->bflags)) {
+ if (parent)
+ btrfs_set_lock_blocking(parent);
+ btrfs_set_lock_blocking(buf);
+ wait_on_bit_io(&ebh->bflags,
+ EXTENT_BUFFER_HEAD_WRITEBACK,
+ TASK_UNINTERRUPTIBLE);
+ }
*cow_ret = buf;
return 0;
}
@@ -2671,6 +2680,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_key *key, struct btrfs_path *p, int
ins_len, int cow)
{
+ struct extent_buffer_head *ebh;
struct extent_buffer *b;
int slot;
int ret;
@@ -2773,8 +2783,17 @@ again:
* then we don't want to set the path blocking,
* so we test it here
*/
- if (!should_cow_block(trans, root, b))
+ if (!should_cow_block(trans, root, b)) {
+ ebh = eb_head(b);
+ if (test_bit(EXTENT_BUFFER_HEAD_WRITEBACK,
+ &ebh->bflags)) {
+ btrfs_set_path_blocking(p);
+ wait_on_bit_io(&ebh->bflags,
+ EXTENT_BUFFER_HEAD_WRITEBACK,
+ TASK_UNINTERRUPTIBLE);
+ }
goto cow_done;
+ }
/*
* must have write locks on this node and the
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b8df911..4625413 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -7898,14 +7898,25 @@ static struct extent_buffer *
btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
u64 bytenr, int level)
{
+ struct extent_buffer_head *ebh;
struct extent_buffer *buf;
buf = btrfs_find_create_tree_block(root, bytenr);
if (!buf)
return ERR_PTR(-ENOMEM);
+
+ ebh = eb_head(buf);
btrfs_set_header_generation(buf, trans->transid);
btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
btrfs_tree_lock(buf);
+
+ if (test_bit(EXTENT_BUFFER_HEAD_WRITEBACK,
+ &ebh->bflags)) {
+ btrfs_set_lock_blocking(buf);
+ wait_on_bit_io(&ebh->bflags, EXTENT_BUFFER_HEAD_WRITEBACK,
+ TASK_UNINTERRUPTIBLE);
+ }
+
clean_tree_block(trans, root->fs_info, buf);
clear_bit(EXTENT_BUFFER_STALE, &buf->ebflags);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 98fff69..75221a9 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3654,6 +3654,52 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
TASK_UNINTERRUPTIBLE);
}
+static void lock_extent_buffers(struct extent_buffer_head *ebh,
+ struct extent_page_data *epd)
+{
+ struct extent_buffer *locked_eb = NULL;
+ struct extent_buffer *eb;
+again:
+ eb = &ebh->eb;
+ do {
+ if (eb == locked_eb)
+ continue;
+
+ if (!btrfs_try_tree_write_lock(eb))
+ goto backoff;
+
+ } while ((eb = eb->eb_next) != NULL);
+
+ return;
+
+backoff:
+ if (locked_eb && (locked_eb->start > eb->start))
+ btrfs_tree_unlock(locked_eb);
+
+ locked_eb = eb;
+
+ eb = &ebh->eb;
+ while (eb != locked_eb) {
+ btrfs_tree_unlock(eb);
+ eb = eb->eb_next;
+ }
+
+ flush_write_bio(epd);
+
+ btrfs_tree_lock(locked_eb);
+
+ goto again;
+}
+
+static void unlock_extent_buffers(struct extent_buffer_head *ebh)
+{
+ struct extent_buffer *eb = &ebh->eb;
+
+ do {
+ btrfs_tree_unlock(eb);
+ } while ((eb = eb->eb_next) != NULL);
+}
+
static void lock_extent_buffer_pages(struct extent_buffer_head *ebh,
struct extent_page_data *epd)
{
@@ -3673,21 +3719,17 @@ static void lock_extent_buffer_pages(struct extent_buffer_head *ebh,
}
static int noinline_for_stack
-lock_extent_buffer_for_io(struct extent_buffer *eb,
+mark_extent_buffer_writeback(struct extent_buffer *eb,
struct btrfs_fs_info *fs_info,
struct extent_page_data *epd)
{
+ struct extent_buffer_head *ebh = eb_head(eb);
+ struct extent_buffer *cur;
int dirty;
int ret = 0;
- if (!btrfs_try_tree_write_lock(eb)) {
- flush_write_bio(epd);
- btrfs_tree_lock(eb);
- }
-
if (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags)) {
dirty = test_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags);
- btrfs_tree_unlock(eb);
if (!epd->sync_io) {
if (!dirty)
return 1;
@@ -3695,15 +3737,23 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
return 2;
}
+ cur = &ebh->eb;
+ do {
+ btrfs_set_lock_blocking(cur);
+ } while ((cur = cur->eb_next) != NULL);
+
flush_write_bio(epd);
while (1) {
wait_on_extent_buffer_writeback(eb);
- btrfs_tree_lock(eb);
if (!test_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags))
break;
- btrfs_tree_unlock(eb);
}
+
+ cur = &ebh->eb;
+ do {
+ btrfs_clear_lock_blocking(cur);
+ } while ((cur = cur->eb_next) != NULL);
}
/*
@@ -3711,22 +3761,20 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
* under IO since we can end up having no IO bits set for a short period
* of time.
*/
- spin_lock(&eb_head(eb)->refs_lock);
+ spin_lock(&ebh->refs_lock);
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->ebflags)) {
set_bit(EXTENT_BUFFER_WRITEBACK, &eb->ebflags);
- spin_unlock(&eb_head(eb)->refs_lock);
+ spin_unlock(&ebh->refs_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-eb->len,
fs_info->dirty_metadata_batch);
ret = 0;
} else {
- spin_unlock(&eb_head(eb)->refs_lock);
+ spin_unlock(&ebh->refs_lock);
ret = 1;
}
- btrfs_tree_unlock(eb);
-
return ret;
}
@@ -3876,8 +3924,8 @@ static void set_btree_ioerr(struct extent_buffer *eb, struct page *page)
static void end_bio_subpagesize_blocksize_ebh_writepage(struct bio *bio)
{
- struct bio_vec *bvec;
struct extent_buffer *eb;
+ struct bio_vec *bvec;
int i, done;
bio_for_each_segment_all(bvec, bio, i) {
@@ -3909,6 +3957,15 @@ static void end_bio_subpagesize_blocksize_ebh_writepage(struct bio *bio)
end_extent_buffer_writeback(eb);
+ if (done) {
+ struct extent_buffer_head *ebh = eb_head(eb);
+
+ clear_bit(EXTENT_BUFFER_HEAD_WRITEBACK,
+ &ebh->bflags);
+ smp_mb__after_atomic();
+ wake_up_bit(&ebh->bflags,
+ EXTENT_BUFFER_HEAD_WRITEBACK);
+ }
} while ((eb = eb->eb_next) != NULL);
}
@@ -3918,6 +3975,7 @@ static void end_bio_subpagesize_blocksize_ebh_writepage(struct bio *bio)
static void end_bio_regular_ebh_writepage(struct bio *bio)
{
+ struct extent_buffer_head *ebh;
struct extent_buffer *eb;
struct bio_vec *bvec;
int i, done;
@@ -3928,7 +3986,9 @@ static void end_bio_regular_ebh_writepage(struct bio *bio)
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
- done = atomic_dec_and_test(&eb_head(eb)->io_bvecs);
+ ebh = eb_head(eb);
+
+ done = atomic_dec_and_test(&ebh->io_bvecs);
if (bio->bi_error ||
test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags)) {
@@ -3942,6 +4002,10 @@ static void end_bio_regular_ebh_writepage(struct bio *bio)
continue;
end_extent_buffer_writeback(eb);
+
+ clear_bit(EXTENT_BUFFER_HEAD_WRITEBACK, &ebh->bflags);
+ smp_mb__after_atomic();
+ wake_up_bit(&ebh->bflags, EXTENT_BUFFER_HEAD_WRITEBACK);
}
bio_put(bio);
@@ -3983,8 +4047,14 @@ write_regular_ebh(struct extent_buffer_head *ebh,
set_btree_ioerr(eb, p);
end_page_writeback(p);
if (atomic_sub_and_test(num_pages - i,
- &eb_head(eb)->io_bvecs))
+ &ebh->io_bvecs)) {
end_extent_buffer_writeback(eb);
+ clear_bit(EXTENT_BUFFER_HEAD_WRITEBACK,
+ &ebh->bflags);
+ smp_mb__after_atomic();
+ wake_up_bit(&ebh->bflags,
+ EXTENT_BUFFER_HEAD_WRITEBACK);
+ }
ret = -EIO;
break;
}
@@ -4018,6 +4088,7 @@ static int write_subpagesize_blocksize_ebh(struct extent_buffer_head *ebh,
unsigned long i;
unsigned long bio_flags = 0;
int rw = (epd->sync_io ? WRITE_SYNC : WRITE) | REQ_META;
+ int nr_eb_submitted = 0;
int ret = 0, err = 0;
eb = &ebh->eb;
@@ -4030,7 +4101,7 @@ static int write_subpagesize_blocksize_ebh(struct extent_buffer_head *ebh,
continue;
clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->ebflags);
- atomic_inc(&eb_head(eb)->io_bvecs);
+ atomic_inc(&ebh->io_bvecs);
if (btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID)
bio_flags = EXTENT_BIO_TREE_LOG;
@@ -4048,6 +4119,8 @@ static int write_subpagesize_blocksize_ebh(struct extent_buffer_head *ebh,
atomic_dec(&eb_head(eb)->io_bvecs);
end_extent_buffer_writeback(eb);
err = -EIO;
+ } else {
+ ++nr_eb_submitted;
}
} while ((eb = eb->eb_next) != NULL);
@@ -4055,6 +4128,12 @@ static int write_subpagesize_blocksize_ebh(struct extent_buffer_head *ebh,
update_nr_written(p, wbc, 1);
}
+ if (!nr_eb_submitted) {
+ clear_bit(EXTENT_BUFFER_HEAD_WRITEBACK, &ebh->bflags);
+ smp_mb__after_atomic();
+ wake_up_bit(&ebh->bflags, EXTENT_BUFFER_HEAD_WRITEBACK);
+ }
+
unlock_page(p);
return ret;
@@ -4166,24 +4245,31 @@ retry:
j = 0;
ebs_to_write = dirty_ebs = 0;
+
+ lock_extent_buffers(ebh, &epd);
+
+ set_bit(EXTENT_BUFFER_HEAD_WRITEBACK, &ebh->bflags);
+
eb = &ebh->eb;
do {
BUG_ON(j >= BITS_PER_LONG);
- ret = lock_extent_buffer_for_io(eb, fs_info, &epd);
+ ret = mark_extent_buffer_writeback(eb, fs_info,
+ &epd);
switch (ret) {
case 0:
/*
- EXTENT_BUFFER_DIRTY was set and we were able to
- clear it.
+ EXTENT_BUFFER_DIRTY was set and we were
+ able to clear it.
*/
set_bit(j, &ebs_to_write);
break;
case 2:
/*
- EXTENT_BUFFER_DIRTY was set, but we were unable
- to clear EXTENT_BUFFER_WRITEBACK that was set
- before we got the extent buffer locked.
+ EXTENT_BUFFER_DIRTY was set, but we were
+ unable to clear EXTENT_BUFFER_WRITEBACK
+ that was set before we got the extent
+ buffer locked.
*/
set_bit(j, &dirty_ebs);
default:
@@ -4197,22 +4283,32 @@ retry:
ret = 0;
+ unlock_extent_buffers(ebh);
+
if (!ebs_to_write) {
+ clear_bit(EXTENT_BUFFER_HEAD_WRITEBACK,
+ &ebh->bflags);
+ smp_mb__after_atomic();
+ wake_up_bit(&ebh->bflags,
+ EXTENT_BUFFER_HEAD_WRITEBACK);
free_extent_buffer(&ebh->eb);
continue;
}
/*
- Now that we know that atleast one of the extent buffer
+ Now that we know that atleast one of the extent buffers
belonging to the extent buffer head must be written to
the disk, lock the extent_buffer_head's pages.
*/
lock_extent_buffer_pages(ebh, &epd);
if (ebh->eb.len < PAGE_SIZE) {
- ret = write_subpagesize_blocksize_ebh(ebh, fs_info, wbc, &epd, ebs_to_write);
+ ret = write_subpagesize_blocksize_ebh(ebh, fs_info,
+ wbc, &epd,
+ ebs_to_write);
if (dirty_ebs) {
- redirty_extent_buffer_pages_for_writepage(&ebh->eb, wbc);
+ redirty_extent_buffer_pages_for_writepage(&ebh->eb,
+ wbc);
}
} else {
ret = write_regular_ebh(ebh, fs_info, wbc, &epd);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index db5ebaf..63ad8c0 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -35,6 +35,7 @@
#define EXTENT_BUFFER_HEAD_TREE_REF 0
#define EXTENT_BUFFER_HEAD_DUMMY 1
#define EXTENT_BUFFER_HEAD_IN_TREE 2
+#define EXTENT_BUFFER_HEAD_WRITEBACK 3
/* these are bit numbers for test/set bit on extent buffer */
#define EXTENT_BUFFER_UPTODATE 0
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a17bcab..8d35c47 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2432,11 +2432,11 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
goto out_only_mutex;
}
- start_index = lockstart >> PAGE_CACHE_SHIFT;
- end_index = lockend >> PAGE_CACHE_SHIFT;
+ start_index = lockstart >> PAGE_SHIFT;
+ end_index = lockend >> PAGE_SHIFT;
- same_page = lockstart >> PAGE_CACHE_SHIFT
- == lockend >> PAGE_CACHE_SHIFT;
+ same_page = lockstart >> PAGE_SHIFT
+ == lockend >> PAGE_SHIFT;
while (1) {
struct btrfs_ordered_extent *ordered;
@@ -2446,7 +2446,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
truncate_pagecache_range(inode, lockstart, lockend);
- if (lockstart & (PAGE_CACHE_SIZE - 1)) {
+ if (lockstart & (PAGE_SIZE - 1)) {
start_page = find_or_create_page(mapping, start_index,
GFP_NOFS);
if (!start_page) {
@@ -2455,13 +2455,13 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
}
}
- if (!same_page && ((lockend + 1) & (PAGE_CACHE_SIZE - 1))) {
+ if (!same_page && ((lockend + 1) & (PAGE_SIZE - 1))) {
end_page = find_or_create_page(mapping, end_index,
GFP_NOFS);
if (!end_page) {
if (start_page) {
unlock_page(start_page);
- page_cache_release(start_page);
+ put_page(start_page);
}
mutex_unlock(&inode->i_mutex);
return -ENOMEM;
@@ -2478,9 +2478,9 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
* and nobody raced in and read a page in this range, if we did
* we need to try again.
*/
- nr_pages = round_up(lockend, PAGE_CACHE_SIZE)
- - round_down(lockstart, PAGE_CACHE_SIZE);
- nr_pages >>= PAGE_CACHE_SHIFT;
+ nr_pages = round_up(lockend, PAGE_SIZE)
+ - round_down(lockstart, PAGE_SIZE);
+ nr_pages >>= PAGE_SHIFT;
if ((!ordered ||
(ordered->file_offset + ordered->len <= lockstart ||
@@ -2488,22 +2488,22 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
(!(start_page && PagePrivate(start_page) &&
test_page_blks_state(start_page, 1 << BLK_STATE_UPTODATE,
lockstart,
- min(lockstart + PAGE_CACHE_SIZE - 1, lockend), 0)) &&
+ min(lockstart + PAGE_SIZE - 1, lockend), 0)) &&
!(end_page && PagePrivate(end_page) &&
test_page_blks_state(end_page, 1 << BLK_STATE_UPTODATE,
page_offset(end_page), lockend, 0)) &&
!(nr_pages > 2 && btrfs_page_exists_in_range(inode,
- round_up(lockstart, PAGE_CACHE_SIZE),
- round_down(lockend, PAGE_CACHE_SIZE) - 1)))) {
+ round_up(lockstart, PAGE_SIZE),
+ round_down(lockend, PAGE_SIZE) - 1)))) {
if (ordered)
btrfs_put_ordered_extent(ordered);
if (end_page) {
unlock_page(end_page);
- page_cache_release(end_page);
+ put_page(end_page);
}
if (start_page) {
unlock_page(start_page);
- page_cache_release(start_page);
+ put_page(start_page);
}
break;
}
@@ -2513,11 +2513,11 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
lockend, &cached_state, GFP_NOFS);
if (end_page) {
unlock_page(end_page);
- page_cache_release(end_page);
+ put_page(end_page);
}
if (start_page) {
unlock_page(start_page);
- page_cache_release(start_page);
+ put_page(start_page);
}
ret = btrfs_wait_ordered_range(inode, lockstart,
lockend - lockstart + 1);
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 12/18] Revert "btrfs: fix lockups from btrfs_clear_path_blocking"
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (10 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 11/18] Btrfs: subpage-blocksize: Prevent writes to an extent buffer when PG_writeback flag is set Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 13/18] Btrfs: subpage-blocksize: Fix file defragmentation code Chandan Rajendra
` (6 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
The patch "Btrfs: subpage-blocksize: Prevent writes to an extent buffer
when PG_writeback flag is set" requires btrfs_try_tree_write_lock() to
be a true try lock w.r.t to both spinning and blocking locks. During
2015's Vault Conference Btrfs meetup, Chris Mason had suggested that he
will write up a suitable locking function to be used when writing dirty
pages that map metadata blocks. Until we have a suitable locking
function available, this patch temporarily disables the commit
f82c458a2c3ffb94b431fc6ad791a79df1b3713e.
---
fs/btrfs/ctree.c | 14 ++++++++++++--
fs/btrfs/locking.c | 24 +++---------------------
fs/btrfs/locking.h | 2 --
3 files changed, 15 insertions(+), 25 deletions(-)
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 7d76add..4a753c9 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -81,6 +81,13 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
{
int i;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ /* lockdep really cares that we take all of these spinlocks
+ * in the right order. If any of the locks in the path are not
+ * currently blocking, it is going to complain. So, make really
+ * really sure by forcing the path to blocking before we clear
+ * the path blocking.
+ */
if (held) {
btrfs_set_lock_blocking_rw(held, held_rw);
if (held_rw == BTRFS_WRITE_LOCK)
@@ -89,6 +96,7 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
held_rw = BTRFS_READ_LOCK_BLOCKING;
}
btrfs_set_path_blocking(p);
+#endif
for (i = BTRFS_MAX_LEVEL - 1; i >= 0; i--) {
if (p->nodes[i] && p->locks[i]) {
@@ -100,8 +108,10 @@ noinline void btrfs_clear_path_blocking(struct btrfs_path *p,
}
}
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
if (held)
btrfs_clear_lock_blocking_rw(held, held_rw);
+#endif
}
/* this also releases the path */
@@ -2904,7 +2914,7 @@ cow_done:
}
p->locks[level] = BTRFS_WRITE_LOCK;
} else {
- err = btrfs_tree_read_lock_atomic(b);
+ err = btrfs_try_tree_read_lock(b);
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
@@ -3036,7 +3046,7 @@ again:
}
level = btrfs_header_level(b);
- err = btrfs_tree_read_lock_atomic(b);
+ err = btrfs_try_tree_read_lock(b);
if (!err) {
btrfs_set_path_blocking(p);
btrfs_tree_read_lock(b);
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index d13128c..8b50e60 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -132,26 +132,6 @@ again:
}
/*
- * take a spinning read lock.
- * returns 1 if we get the read lock and 0 if we don't
- * this won't wait for blocking writers
- */
-int btrfs_tree_read_lock_atomic(struct extent_buffer *eb)
-{
- if (atomic_read(&eb->blocking_writers))
- return 0;
-
- read_lock(&eb->lock);
- if (atomic_read(&eb->blocking_writers)) {
- read_unlock(&eb->lock);
- return 0;
- }
- atomic_inc(&eb->read_locks);
- atomic_inc(&eb->spinning_readers);
- return 1;
-}
-
-/*
* returns 1 if we get the read lock and 0 if we don't
* this won't wait for blocking writers
*/
@@ -182,7 +162,9 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb)
atomic_read(&eb->blocking_readers))
return 0;
- write_lock(&eb->lock);
+ if (!write_trylock(&eb->lock))
+ return 0;
+
if (atomic_read(&eb->blocking_writers) ||
atomic_read(&eb->blocking_readers)) {
write_unlock(&eb->lock);
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index c44a9d5..b81e0e9 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -35,8 +35,6 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw);
void btrfs_assert_tree_locked(struct extent_buffer *eb);
int btrfs_try_tree_read_lock(struct extent_buffer *eb);
int btrfs_try_tree_write_lock(struct extent_buffer *eb);
-int btrfs_tree_read_lock_atomic(struct extent_buffer *eb);
-
static inline void btrfs_tree_unlock_rw(struct extent_buffer *eb, int rw)
{
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 13/18] Btrfs: subpage-blocksize: Fix file defragmentation code
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (11 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 12/18] Revert "btrfs: fix lockups from btrfs_clear_path_blocking" Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 14/18] Btrfs: subpage-blocksize: extent_clear_unlock_delalloc: Prevent page from being unlocked more than once Chandan Rajendra
` (5 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
This commit gets file defragmentation code to work in subpage-blocksize
scenario. It does this by keeping track of page offsets that mark block
boundaries and passing them as arguments to the functions that implement
the defragmentation logic.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/ioctl.c | 193 +++++++++++++++++++++++++++++++++++++------------------
1 file changed, 132 insertions(+), 61 deletions(-)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5a23806..bf79dbc 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -893,12 +893,13 @@ out_unlock:
static int check_defrag_in_cache(struct inode *inode, u64 offset, u32 thresh)
{
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_map *em = NULL;
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
u64 end;
read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, offset, PAGE_SIZE);
+ em = lookup_extent_mapping(em_tree, offset, root->sectorsize);
read_unlock(&em_tree->lock);
if (em) {
@@ -988,7 +989,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_map *em;
- u64 len = PAGE_SIZE;
+ u64 len = BTRFS_I(inode)->root->sectorsize;
/*
* hopefully we have this extent in the tree already, try without
@@ -1107,15 +1108,18 @@ out:
* before calling this.
*/
static int cluster_pages_for_defrag(struct inode *inode,
- struct page **pages,
- unsigned long start_index,
- unsigned long num_pages)
+ struct page **pages,
+ unsigned long start_index,
+ size_t pg_offset,
+ unsigned long num_blks)
{
- unsigned long file_end;
u64 isize = i_size_read(inode);
+ u64 start_blk;
+ u64 end_blk;
u64 page_start;
u64 page_end;
u64 page_cnt;
+ u64 blk_cnt;
int ret;
int i;
int i_done;
@@ -1124,20 +1128,25 @@ static int cluster_pages_for_defrag(struct inode *inode,
struct extent_io_tree *tree;
gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
- file_end = (isize - 1) >> PAGE_SHIFT;
- if (!isize || start_index > file_end)
+ start_blk = (start_index << PAGE_SHIFT) + pg_offset;
+ start_blk >>= inode->i_blkbits;
+ end_blk = (isize - 1) >> inode->i_blkbits;
+ if (!isize || start_blk > end_blk)
return 0;
- page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
+ blk_cnt = min_t(u64, (u64)num_blks, (u64)end_blk - start_blk + 1);
ret = btrfs_delalloc_reserve_space(inode,
- start_index << PAGE_SHIFT,
- page_cnt << PAGE_SHIFT);
+ start_blk << inode->i_blkbits,
+ blk_cnt << inode->i_blkbits);
if (ret)
return ret;
i_done = 0;
tree = &BTRFS_I(inode)->io_tree;
+ page_cnt = DIV_ROUND_UP(pg_offset + (blk_cnt << inode->i_blkbits),
+ PAGE_SIZE);
+
/* step one, lock all the pages */
for (i = 0; i < page_cnt; i++) {
struct page *page;
@@ -1148,12 +1157,22 @@ again:
break;
page_start = page_offset(page);
- page_end = page_start + PAGE_SIZE - 1;
+
+ if (i == 0)
+ page_start += pg_offset;
+
+ if (i == page_cnt - 1) {
+ page_end = (start_index << PAGE_SHIFT) + pg_offset;
+ page_end += (blk_cnt << inode->i_blkbits) - 1;
+ } else {
+ page_end = page_offset(page) + PAGE_SIZE - 1;
+ }
+
while (1) {
lock_extent_bits(tree, page_start, page_end,
&cached_state);
- ordered = btrfs_lookup_ordered_extent(inode,
- page_start);
+ ordered = btrfs_lookup_ordered_range(inode, page_start,
+ page_end - page_start + 1);
unlock_extent_cached(tree, page_start, page_end,
&cached_state, GFP_NOFS);
if (!ordered)
@@ -1192,7 +1211,7 @@ again:
}
pages[i] = page;
- i_done++;
+ i_done += (page_end - page_start + 1) >> inode->i_blkbits;
}
if (!i_done || ret)
goto out;
@@ -1204,55 +1223,76 @@ again:
* so now we have a nice long stream of locked
* and up to date pages, lets wait on them
*/
- for (i = 0; i < i_done; i++)
+ page_cnt = DIV_ROUND_UP(pg_offset + (i_done << inode->i_blkbits),
+ PAGE_SIZE);
+ for (i = 0; i < page_cnt; i++)
wait_on_page_writeback(pages[i]);
- page_start = page_offset(pages[0]);
- page_end = page_offset(pages[i_done - 1]) + PAGE_SIZE;
+ page_start = page_offset(pages[0]) + pg_offset;
+ page_end = page_start + (i_done << inode->i_blkbits) - 1;
lock_extent_bits(&BTRFS_I(inode)->io_tree,
- page_start, page_end - 1, &cached_state);
+ page_start, page_end, &cached_state);
clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
- page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
+ page_end, EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
&cached_state, GFP_NOFS);
- if (i_done != page_cnt) {
+ if (i_done != blk_cnt) {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
btrfs_delalloc_release_space(inode,
- start_index << PAGE_SHIFT,
- (page_cnt - i_done) << PAGE_SHIFT);
+ start_blk << inode->i_blkbits,
+ (blk_cnt - i_done) << inode->i_blkbits);
}
- set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
+ set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end,
&cached_state, GFP_NOFS);
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
- page_start, page_end - 1, &cached_state,
+ page_start, page_end, &cached_state,
GFP_NOFS);
- for (i = 0; i < i_done; i++) {
+ for (i = 0; i < page_cnt; i++) {
clear_page_dirty_for_io(pages[i]);
ClearPageChecked(pages[i]);
set_page_extent_mapped(pages[i]);
+
+ page_start = page_offset(pages[i]);
+ if (i == 0)
+ page_start += pg_offset;
+
+ if (i == page_cnt - 1) {
+ page_end = page_offset(pages[0]) + pg_offset;
+ page_end += (i_done << inode->i_blkbits) - 1;
+ } else {
+ page_end = page_offset(pages[i]) + PAGE_SIZE - 1;
+ }
+
+ set_page_blks_state(pages[i],
+ 1 << BLK_STATE_UPTODATE | 1 << BLK_STATE_DIRTY,
+ page_start, page_end);
set_page_dirty(pages[i]);
unlock_page(pages[i]);
put_page(pages[i]);
}
return i_done;
out:
- for (i = 0; i < i_done; i++) {
- unlock_page(pages[i]);
- put_page(pages[i]);
+ if (i_done) {
+ page_cnt = DIV_ROUND_UP(pg_offset + (i_done << inode->i_blkbits),
+ PAGE_SIZE);
+ for (i = 0; i < page_cnt; i++) {
+ unlock_page(pages[i]);
+ put_page(pages[i]);
+ }
}
+
btrfs_delalloc_release_space(inode,
- start_index << PAGE_SHIFT,
- page_cnt << PAGE_SHIFT);
+ start_blk << inode->i_blkbits,
+ blk_cnt << inode->i_blkbits);
return ret;
-
}
int btrfs_defrag_file(struct inode *inode, struct file *file,
@@ -1261,19 +1301,24 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct file_ra_state *ra = NULL;
+ unsigned long first_off, last_off;
+ unsigned long first_block, last_block;
unsigned long last_index;
u64 isize = i_size_read(inode);
u64 last_len = 0;
u64 skip = 0;
u64 defrag_end = 0;
u64 newer_off = range->start;
+ u64 start;
+ u64 page_cnt;
unsigned long i;
unsigned long ra_index = 0;
+ size_t pg_offset;
int ret;
int defrag_count = 0;
int compress_type = BTRFS_COMPRESS_ZLIB;
u32 extent_thresh = range->extent_thresh;
- unsigned long max_cluster = SZ_256K >> PAGE_SHIFT;
+ unsigned long max_cluster = SZ_256K >> inode->i_blkbits;
unsigned long cluster = max_cluster;
u64 new_align = ~((u64)SZ_128K - 1);
struct page **pages = NULL;
@@ -1307,8 +1352,14 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
ra = &file->f_ra;
}
- pages = kmalloc_array(max_cluster, sizeof(struct page *),
- GFP_NOFS);
+ /*
+ * In subpage-blocksize scenario the first of "max_cluster" blocks
+ * may start on a non-zero page offset. In such scenarios we need one
+ * page more than what would be needed in the case where the first block
+ * maps to first block of a page.
+ */
+ page_cnt = (max_cluster >> (PAGE_SHIFT - inode->i_blkbits)) + 1;
+ pages = kmalloc_array(page_cnt, sizeof(struct page *), GFP_NOFS);
if (!pages) {
ret = -ENOMEM;
goto out_ra;
@@ -1316,12 +1367,15 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
/* find the last page to defrag */
if (range->start + range->len > range->start) {
- last_index = min_t(u64, isize - 1,
- range->start + range->len - 1) >> PAGE_SHIFT;
+ last_off = min_t(u64, isize - 1, range->start + range->len - 1);
} else {
- last_index = (isize - 1) >> PAGE_SHIFT;
+ last_off = isize - 1;
}
+ last_off = round_up(last_off, root->sectorsize) - 1;
+ last_block = last_off >> inode->i_blkbits;
+ last_index = last_off >> PAGE_SHIFT;
+
if (newer_than) {
ret = find_new_extents(root, inode, newer_than,
&newer_off, SZ_64K);
@@ -1331,14 +1385,20 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
* we always align our defrag to help keep
* the extents in the file evenly spaced
*/
- i = (newer_off & new_align) >> PAGE_SHIFT;
+ first_off = newer_off & new_align;
} else
goto out_ra;
} else {
- i = range->start >> PAGE_SHIFT;
+ first_off = range->start;
}
+
+ first_off = round_down(first_off, root->sectorsize);
+ first_block = first_off >> inode->i_blkbits;
+ i = first_off >> PAGE_SHIFT;
+ pg_offset = first_off & (PAGE_SIZE - 1);
+
if (!max_to_defrag)
- max_to_defrag = last_index - i + 1;
+ max_to_defrag = last_block - first_block + 1;
/*
* make writeback starts from i, so the defrag range can be
@@ -1362,39 +1422,50 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
break;
}
- if (!should_defrag_range(inode, (u64)i << PAGE_SHIFT,
- extent_thresh, &last_len, &skip,
- &defrag_end, range->flags &
- BTRFS_DEFRAG_RANGE_COMPRESS)) {
+ start = pg_offset + ((u64)i << PAGE_SHIFT);
+ if (!should_defrag_range(inode, start,
+ extent_thresh, &last_len, &skip,
+ &defrag_end, range->flags &
+ BTRFS_DEFRAG_RANGE_COMPRESS)) {
unsigned long next;
/*
* the should_defrag function tells us how much to skip
* bump our counter by the suggested amount
*/
- next = DIV_ROUND_UP(skip, PAGE_SIZE);
- i = max(i + 1, next);
+ next = max(skip, start + root->sectorsize);
+ next >>= inode->i_blkbits;
+
+ first_off = next << inode->i_blkbits;
+ i = first_off >> PAGE_SHIFT;
+ pg_offset = first_off & (PAGE_SIZE - 1);
continue;
}
if (!newer_than) {
- cluster = (PAGE_ALIGN(defrag_end) >>
- PAGE_SHIFT) - i;
+ cluster = (defrag_end >> inode->i_blkbits)
+ - (start >> inode->i_blkbits);
+
cluster = min(cluster, max_cluster);
} else {
cluster = max_cluster;
}
- if (i + cluster > ra_index) {
+ page_cnt = pg_offset + (cluster << inode->i_blkbits) - 1;
+ page_cnt = DIV_ROUND_UP(page_cnt, PAGE_SIZE);
+ if (i + page_cnt > ra_index) {
ra_index = max(i, ra_index);
btrfs_force_ra(inode->i_mapping, ra, file, ra_index,
- cluster);
- ra_index += cluster;
+ page_cnt);
+ ra_index += DIV_ROUND_UP(pg_offset +
+ (cluster << inode->i_blkbits),
+ PAGE_SIZE);
}
inode_lock(inode);
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
BTRFS_I(inode)->force_compress = compress_type;
- ret = cluster_pages_for_defrag(inode, pages, i, cluster);
+ ret = cluster_pages_for_defrag(inode, pages, i, pg_offset,
+ cluster);
if (ret < 0) {
inode_unlock(inode);
goto out_ra;
@@ -1408,29 +1479,29 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
if (newer_off == (u64)-1)
break;
- if (ret > 0)
- i += ret;
-
newer_off = max(newer_off + 1,
- (u64)i << PAGE_SHIFT);
+ start + (ret << inode->i_blkbits));
ret = find_new_extents(root, inode, newer_than,
&newer_off, SZ_64K);
if (!ret) {
range->start = newer_off;
- i = (newer_off & new_align) >> PAGE_SHIFT;
+ first_off = newer_off & new_align;
} else {
break;
}
} else {
if (ret > 0) {
- i += ret;
- last_len += ret << PAGE_SHIFT;
+ first_off = start + (ret << inode->i_blkbits);
+ last_len += ret << inode->i_blkbits;
} else {
- i++;
+ first_off = start + root->sectorsize;
last_len = 0;
}
}
+ first_off = round_down(first_off, root->sectorsize);
+ i = first_off >> PAGE_SHIFT;
+ pg_offset = first_off & (PAGE_SIZE - 1);
}
if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO)) {
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 14/18] Btrfs: subpage-blocksize: extent_clear_unlock_delalloc: Prevent page from being unlocked more than once
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (12 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 13/18] Btrfs: subpage-blocksize: Fix file defragmentation code Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 15/18] Btrfs: subpage-blocksize: Enable dedupe ioctl Chandan Rajendra
` (4 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
extent_clear_unlock_delalloc() can unlock a page more than once as shown
below (assume 4k as the block size and 64k as the page size).
cow_file_range
create 4k ordered extent corresponding to page offsets 0 - 4095
extent_clear_unlock_delalloc corresponding to page offsets 0 - 4095
unlock page
create 4k ordered extent corresponding to page offsets 4096 - 8191
extent_clear_unlock_delalloc corresponding to page offsets 4096 - 8191
unlock page
To prevent such a scenario this commit passes "delalloc end" to
extent_clear_unlock_delalloc() to help decide whether the page can be unlocked
or not.
NOTE: Since extent_clear_unlock_delalloc() is used by compression code
as well, the commit passes ordered extent "end" as the value for the
argument corresponding to "delalloc end" for invocations made from
compression code path. This will be fixed by a future commit that gets
compression to work in subpage-blocksize scenario.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/extent_io.c | 16 ++++++----
fs/btrfs/extent_io.h | 5 ++--
fs/btrfs/inode.c | 84 ++++++++++++++++++++++++++++++----------------------
3 files changed, 61 insertions(+), 44 deletions(-)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 75221a9..3fee8ee1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1823,9 +1823,8 @@ out_failed:
}
void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
- struct page *locked_page,
- unsigned clear_bits,
- unsigned long page_ops)
+ u64 delalloc_end, struct page *locked_page,
+ unsigned clear_bits, unsigned long page_ops)
{
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
int ret;
@@ -1833,6 +1832,7 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
unsigned long index = start >> PAGE_SHIFT;
unsigned long end_index = end >> PAGE_SHIFT;
unsigned long nr_pages = end_index - index + 1;
+ u64 page_end;
int i;
clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS);
@@ -1869,8 +1869,14 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
if ((page_ops & PAGE_END_WRITEBACK)
&& !PagePrivate2(pages[i]))
end_page_writeback(pages[i]);
- if (page_ops & PAGE_UNLOCK)
- unlock_page(pages[i]);
+
+ if (page_ops & PAGE_UNLOCK) {
+ page_end = page_offset(pages[i]) +
+ PAGE_SIZE - 1;
+ if ((page_end <= end)
+ || (end == delalloc_end))
+ unlock_page(pages[i]);
+ }
put_page(pages[i]);
}
nr_pages -= ret;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 63ad8c0..0419a89 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -499,9 +499,8 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset,
void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end);
void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end);
void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
- struct page *locked_page,
- unsigned bits_to_clear,
- unsigned long page_ops);
+ u64 delalloc_end, struct page *locked_page,
+ unsigned bits_to_clear, unsigned long page_ops);
struct bio *
btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
gfp_t gfp_flags);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2a6d829..dfd5392 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -104,9 +104,10 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr);
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);
+ struct page *locked_page,
+ u64 start, u64 end, u64 delalloc_end,
+ int *page_started, unsigned long *nr_written,
+ int unlock);
static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
u64 len, u64 orig_start,
u64 block_start, u64 block_len,
@@ -561,12 +562,13 @@ cont:
* we don't need to create any more async work items.
* Unlock and free up our temp pages.
*/
- extent_clear_unlock_delalloc(inode, start, end, NULL,
- clear_flags, PAGE_UNLOCK |
- PAGE_CLEAR_DIRTY |
- PAGE_SET_WRITEBACK |
- page_error_op |
- PAGE_END_WRITEBACK);
+ extent_clear_unlock_delalloc(inode, start, end, end,
+ NULL, clear_flags,
+ PAGE_UNLOCK
+ | PAGE_CLEAR_DIRTY
+ | PAGE_SET_WRITEBACK
+ | page_error_op
+ | PAGE_END_WRITEBACK);
goto free_pages_out;
}
}
@@ -715,6 +717,8 @@ retry:
async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
+ async_extent->start +
+ async_extent->ram_size - 1,
&page_started, &nr_written, 0);
/* JDM XXX */
@@ -834,6 +838,8 @@ retry:
extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
+ async_extent->start +
+ async_extent->ram_size - 1,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK);
@@ -853,9 +859,10 @@ retry:
tree->ops->writepage_end_io_hook(p, start, end,
NULL, 0);
p->mapping = NULL;
- extent_clear_unlock_delalloc(inode, start, end, NULL, 0,
- PAGE_END_WRITEBACK |
- PAGE_SET_ERROR);
+ extent_clear_unlock_delalloc(inode, start, end, end,
+ NULL, 0,
+ PAGE_END_WRITEBACK |
+ PAGE_SET_ERROR);
free_async_extent_pages(async_extent);
}
alloc_hint = ins.objectid + ins.offset;
@@ -869,6 +876,8 @@ out_free:
extent_clear_unlock_delalloc(inode, async_extent->start,
async_extent->start +
async_extent->ram_size - 1,
+ async_extent->start +
+ async_extent->ram_size - 1,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
@@ -925,10 +934,10 @@ static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
* IO when we return.
*/
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)
+ struct page *locked_page,
+ u64 start, u64 end, u64 delalloc_end,
+ int *page_started, unsigned long *nr_written,
+ int unlock)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 alloc_hint = 0;
@@ -964,7 +973,8 @@ static noinline int cow_file_range(struct inode *inode,
ret = cow_file_range_inline(root, inode, start, end, 0, 0,
NULL);
if (ret == 0) {
- extent_clear_unlock_delalloc(inode, start, end, NULL,
+ extent_clear_unlock_delalloc(inode, start, end,
+ delalloc_end, NULL,
EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DEFRAG, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
@@ -1054,9 +1064,9 @@ static noinline int cow_file_range(struct inode *inode,
page_ops = unlock ? PAGE_UNLOCK : 0;
page_ops |= PAGE_SET_PRIVATE2;
extent_ops = EXTENT_LOCKED | EXTENT_DELALLOC;
- extent_clear_unlock_delalloc(inode, start,
- start + ram_size - 1, locked_page,
- extent_ops, page_ops);
+ extent_clear_unlock_delalloc(inode, start, start + ram_size - 1,
+ delalloc_end, locked_page, extent_ops,
+ page_ops);
disk_num_bytes -= cur_alloc_size;
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
@@ -1087,8 +1097,8 @@ out_unlock:
extent_ops = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING
| EXTENT_DEFRAG;
- extent_clear_unlock_delalloc(inode, start, end, locked_page,
- extent_ops, page_ops);
+ extent_clear_unlock_delalloc(inode, start, end, delalloc_end,
+ locked_page, extent_ops, page_ops);
goto out;
}
@@ -1235,9 +1245,9 @@ static noinline int csum_exist_in_range(struct btrfs_root *root,
* blocks on disk
*/
static noinline int run_delalloc_nocow(struct inode *inode,
- struct page *locked_page,
- u64 start, u64 end, int *page_started, int force,
- unsigned long *nr_written)
+ struct page *locked_page,
+ u64 start, u64 end, int *page_started,
+ int force, unsigned long *nr_written)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
@@ -1263,7 +1273,8 @@ static noinline int run_delalloc_nocow(struct inode *inode,
path = btrfs_alloc_path();
if (!path) {
- extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ extent_clear_unlock_delalloc(inode, start, end, end,
+ locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, PAGE_UNLOCK |
@@ -1281,7 +1292,8 @@ static noinline int run_delalloc_nocow(struct inode *inode,
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
- extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ extent_clear_unlock_delalloc(inode, start, end, end,
+ locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, PAGE_UNLOCK |
@@ -1422,8 +1434,8 @@ out_check:
btrfs_release_path(path);
if (cow_start != (u64)-1) {
ret = cow_file_range(inode, locked_page,
- cow_start, found_key.offset - 1,
- page_started, nr_written, 1);
+ cow_start, found_key.offset - 1, end,
+ page_started, nr_written, 1);
if (ret) {
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
@@ -1483,10 +1495,10 @@ out_check:
}
extent_clear_unlock_delalloc(inode, cur_offset,
- cur_offset + num_bytes - 1,
- locked_page, EXTENT_LOCKED |
- EXTENT_DELALLOC, PAGE_UNLOCK |
- PAGE_SET_PRIVATE2);
+ cur_offset + num_bytes - 1, end,
+ locked_page, EXTENT_LOCKED |
+ EXTENT_DELALLOC, PAGE_UNLOCK |
+ PAGE_SET_PRIVATE2);
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
@@ -1501,7 +1513,7 @@ out_check:
}
if (cow_start != (u64)-1) {
- ret = cow_file_range(inode, locked_page, cow_start, end,
+ ret = cow_file_range(inode, locked_page, cow_start, end, end,
page_started, nr_written, 1);
if (ret)
goto error;
@@ -1513,7 +1525,7 @@ error:
ret = err;
if (ret && cur_offset < end)
- extent_clear_unlock_delalloc(inode, cur_offset, end,
+ extent_clear_unlock_delalloc(inode, cur_offset, end, end,
locked_page, EXTENT_LOCKED |
EXTENT_DELALLOC | EXTENT_DEFRAG |
EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
@@ -1561,7 +1573,7 @@ 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,
+ ret = cow_file_range(inode, locked_page, start, end, end,
page_started, nr_written, 1);
} else {
set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 15/18] Btrfs: subpage-blocksize: Enable dedupe ioctl
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (13 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 14/18] Btrfs: subpage-blocksize: extent_clear_unlock_delalloc: Prevent page from being unlocked more than once Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 16/18] Btrfs: btrfs_clone: Flush dirty blocks of a page that do not map the clone range Chandan Rajendra
` (3 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
The function implementing the dedupe ioctl
i.e. btrfs_ioctl_file_extent_same(), returns with an error in
subpage-blocksize scenario. This was done due to the fact that Btrfs did
not have code to deal with block size < page size. This commit removes
this restriction since we now support "block size < page size".
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/ioctl.c | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bf79dbc..4ff7cf8 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3256,21 +3256,11 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
{
struct inode *src = file_inode(src_file);
struct inode *dst = file_inode(dst_file);
- u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize;
ssize_t res;
if (olen > BTRFS_MAX_DEDUPE_LEN)
olen = BTRFS_MAX_DEDUPE_LEN;
- if (WARN_ON_ONCE(bs < PAGE_SIZE)) {
- /*
- * Btrfs does not support blocksize < page_size. As a
- * result, btrfs_cmp_data() won't correctly handle
- * this situation without an update.
- */
- return -EINVAL;
- }
-
res = btrfs_extent_same(src, loff, olen, dst, dst_loff);
if (res)
return res;
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 16/18] Btrfs: btrfs_clone: Flush dirty blocks of a page that do not map the clone range
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (14 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 15/18] Btrfs: subpage-blocksize: Enable dedupe ioctl Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 9:36 ` kbuild test robot
2016-04-14 8:32 ` [PATCH V16 17/18] Btrfs: subpage-blocksize: Make file extent relocate code subpage blocksize aware Chandan Rajendra
` (2 subsequent siblings)
18 siblings, 1 reply; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
After cloning the required extents, we truncate all the pages that map
the file range being cloned. In subpage-blocksize scenario, we could
have dirty blocks before and/or after the clone range in the
leading/trailing pages. Truncating these pages would lead to data
loss. Hence this commit forces such dirty blocks to be flushed to disk
before performing the clone operation.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/ioctl.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4ff7cf8..3038589 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3849,6 +3849,7 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
int ret;
u64 len = olen;
u64 bs = root->fs_info->sb->s_blocksize;
+ u64 dest_end;
int same_inode = src == inode;
/*
@@ -3909,6 +3910,21 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
goto out_unlock;
}
+ if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
+ !IS_ALIGNED(destoff, PAGE_CACHE_SIZE)) {
+ ret = filemap_write_and_wait_range(inode->i_mapping,
+ round_down(destoff, PAGE_CACHE_SIZE),
+ destoff - 1);
+ }
+
+ dest_end = destoff + len - 1;
+ if ((dest_end < inode->i_size) &&
+ !IS_ALIGNED(dest_end + 1, PAGE_CACHE_SIZE)) {
+ ret = filemap_write_and_wait_range(inode->i_mapping,
+ dest_end + 1,
+ round_up(dest_end, PAGE_CACHE_SIZE));
+ }
+
if (destoff > inode->i_size) {
ret = btrfs_cont_expand(inode, inode->i_size, destoff);
if (ret)
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH V16 16/18] Btrfs: btrfs_clone: Flush dirty blocks of a page that do not map the clone range
2016-04-14 8:32 ` [PATCH V16 16/18] Btrfs: btrfs_clone: Flush dirty blocks of a page that do not map the clone range Chandan Rajendra
@ 2016-04-14 9:36 ` kbuild test robot
0 siblings, 0 replies; 22+ messages in thread
From: kbuild test robot @ 2016-04-14 9:36 UTC (permalink / raw)
To: Chandan Rajendra
Cc: kbuild-all, linux-btrfs, Chandan Rajendra, dsterba, clm, jbacik,
chandan, aneesh.kumar
[-- Attachment #1: Type: text/plain, Size: 3275 bytes --]
Hi Chandan,
[auto build test ERROR on tip/perf/core]
[also build test ERROR on v4.6-rc3 next-20160414]
[cannot apply to btrfs/next]
[if your patch is applied to the wrong git tree, please drop us a note to help improving the system]
url: https://github.com/0day-ci/linux/commits/Chandan-Rajendra/Allow-I-O-on-blocks-whose-size-is-less-than-page-size/20160414-163922
config: x86_64-randconfig-x006-201615 (attached as .config)
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
Note: the linux-review/Chandan-Rajendra/Allow-I-O-on-blocks-whose-size-is-less-than-page-size/20160414-163922 HEAD 753cfebe561d4ba706b6095f0df83e345888dd92 builds fine.
It only hurts bisectibility.
All error/warnings (new ones prefixed by >>):
In file included from include/linux/linkage.h:4:0,
from include/linux/kernel.h:6,
from fs/btrfs/ioctl.c:19:
fs/btrfs/ioctl.c: In function 'btrfs_clone_files':
>> fs/btrfs/ioctl.c:3913:27: error: 'PAGE_CACHE_SIZE' undeclared (first use in this function)
if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
^
include/linux/compiler.h:151:30: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^
>> fs/btrfs/ioctl.c:3913:2: note: in expansion of macro 'if'
if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
^
>> include/linux/kernel.h:64:34: note: in expansion of macro '__round_mask'
#define round_down(x, y) ((x) & ~__round_mask(x, y))
^
>> fs/btrfs/ioctl.c:3913:7: note: in expansion of macro 'round_down'
if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
^
fs/btrfs/ioctl.c:3913:27: note: each undeclared identifier is reported only once for each function it appears in
if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
^
include/linux/compiler.h:151:30: note: in definition of macro '__trace_if'
if (__builtin_constant_p(!!(cond)) ? !!(cond) : \
^
>> fs/btrfs/ioctl.c:3913:2: note: in expansion of macro 'if'
if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
^
>> include/linux/kernel.h:64:34: note: in expansion of macro '__round_mask'
#define round_down(x, y) ((x) & ~__round_mask(x, y))
^
>> fs/btrfs/ioctl.c:3913:7: note: in expansion of macro 'round_down'
if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
^
vim +/PAGE_CACHE_SIZE +3913 fs/btrfs/ioctl.c
3907 /* verify if ranges are overlapped within the same file */
3908 if (same_inode) {
3909 if (destoff + len > off && destoff < off + len)
3910 goto out_unlock;
3911 }
3912
> 3913 if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
3914 !IS_ALIGNED(destoff, PAGE_CACHE_SIZE)) {
3915 ret = filemap_write_and_wait_range(inode->i_mapping,
3916 round_down(destoff, PAGE_CACHE_SIZE),
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/octet-stream, Size: 21786 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread
* [PATCH V16 17/18] Btrfs: subpage-blocksize: Make file extent relocate code subpage blocksize aware
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (15 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 16/18] Btrfs: btrfs_clone: Flush dirty blocks of a page that do not map the clone range Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 8:32 ` [PATCH V16 18/18] Btrfs: subpage-blocksize: __btrfs_lookup_bio_sums: Set offset when moving to a new bio_vec Chandan Rajendra
2016-04-14 11:30 ` [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
The file extent relocation code currently assumes blocksize to be same
as PAGE_CACHE_SIZE. This commit adds code to support subpage blocksize
scenario.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/ioctl.c | 10 +++----
fs/btrfs/relocation.c | 73 +++++++++++++++++++++++++++++++++------------------
2 files changed, 53 insertions(+), 30 deletions(-)
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 3038589..7d39cba 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3910,19 +3910,19 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
goto out_unlock;
}
- if ((round_down(destoff, PAGE_CACHE_SIZE) < inode->i_size) &&
- !IS_ALIGNED(destoff, PAGE_CACHE_SIZE)) {
+ if ((round_down(destoff, PAGE_SIZE) < inode->i_size) &&
+ !IS_ALIGNED(destoff, PAGE_SIZE)) {
ret = filemap_write_and_wait_range(inode->i_mapping,
- round_down(destoff, PAGE_CACHE_SIZE),
+ round_down(destoff, PAGE_SIZE),
destoff - 1);
}
dest_end = destoff + len - 1;
if ((dest_end < inode->i_size) &&
- !IS_ALIGNED(dest_end + 1, PAGE_CACHE_SIZE)) {
+ !IS_ALIGNED(dest_end + 1, PAGE_SIZE)) {
ret = filemap_write_and_wait_range(inode->i_mapping,
dest_end + 1,
- round_up(dest_end, PAGE_CACHE_SIZE));
+ round_up(dest_end, PAGE_SIZE));
}
if (destoff > inode->i_size) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 35fd62e..61a6414 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3103,14 +3103,19 @@ static int relocate_file_extent_cluster(struct inode *inode,
{
u64 page_start;
u64 page_end;
+ u64 block_start;
+ u64 block_end;
u64 offset = BTRFS_I(inode)->index_cnt;
+ u64 blocksize = BTRFS_I(inode)->root->sectorsize;
unsigned long index;
unsigned long last_index;
struct page *page;
struct file_ra_state *ra;
gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
+ int nr_blocks;
int nr = 0;
int ret = 0;
+ int i;
if (!cluster->nr)
return 0;
@@ -3130,13 +3135,13 @@ static int relocate_file_extent_cluster(struct inode *inode,
if (ret)
goto out;
+ page_start = cluster->start - offset;
+ page_end = min_t(u64, page_start + PAGE_SIZE - 1,
+ cluster->end - offset);
+
index = (cluster->start - offset) >> PAGE_SHIFT;
last_index = (cluster->end - offset) >> PAGE_SHIFT;
while (index <= last_index) {
- ret = btrfs_delalloc_reserve_metadata(inode, PAGE_SIZE);
- if (ret)
- goto out;
-
page = find_lock_page(inode->i_mapping, index);
if (!page) {
page_cache_sync_readahead(inode->i_mapping,
@@ -3145,8 +3150,6 @@ static int relocate_file_extent_cluster(struct inode *inode,
page = find_or_create_page(inode->i_mapping, index,
mask);
if (!page) {
- btrfs_delalloc_release_metadata(inode,
- PAGE_SIZE);
ret = -ENOMEM;
goto out;
}
@@ -3164,42 +3167,62 @@ static int relocate_file_extent_cluster(struct inode *inode,
if (!PageUptodate(page)) {
unlock_page(page);
put_page(page);
- btrfs_delalloc_release_metadata(inode,
- PAGE_SIZE);
ret = -EIO;
goto out;
}
}
- page_start = page_offset(page);
- page_end = page_start + PAGE_SIZE - 1;
+ nr_blocks = (page_end + 1 - page_start) >> inode->i_blkbits;
+ i = 0;
- lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
+ while (i < nr_blocks) {
+ ret = btrfs_delalloc_reserve_metadata(inode, blocksize);
+ if (ret) {
+ if (i)
+ set_page_dirty(page);
+ unlock_page(page);
+ put_page(page);
+ goto out;
+ }
+
+ block_start = page_start + (i << inode->i_blkbits);
+ block_end = block_start + blocksize - 1;
+
+ lock_extent(&BTRFS_I(inode)->io_tree, block_start,
+ block_end);
+
+ set_page_extent_mapped(page);
- set_page_extent_mapped(page);
+ if (nr < cluster->nr &&
+ block_start + offset == cluster->boundary[nr]) {
+ set_extent_bits(&BTRFS_I(inode)->io_tree,
+ block_start, block_end,
+ EXTENT_BOUNDARY, GFP_NOFS);
+ nr++;
+ }
+
+ btrfs_set_extent_delalloc(inode, block_start,
+ block_end, NULL);
+ set_page_blks_state(page,
+ 1 << BLK_STATE_DIRTY | 1 << BLK_STATE_UPTODATE,
+ block_start, block_end);
- if (nr < cluster->nr &&
- page_start + offset == cluster->boundary[nr]) {
- set_extent_bits(&BTRFS_I(inode)->io_tree,
- page_start, page_end,
- EXTENT_BOUNDARY, GFP_NOFS);
- nr++;
+ unlock_extent(&BTRFS_I(inode)->io_tree,
+ block_start, block_end);
+ i++;
}
- btrfs_set_extent_delalloc(inode, page_start, page_end, NULL);
- set_page_blks_state(page,
- 1 << BLK_STATE_DIRTY | 1 << BLK_STATE_UPTODATE,
- page_start, page_end);
set_page_dirty(page);
-
- unlock_extent(&BTRFS_I(inode)->io_tree,
- page_start, page_end);
unlock_page(page);
put_page(page);
index++;
balance_dirty_pages_ratelimited(inode->i_mapping);
btrfs_throttle(BTRFS_I(inode)->root);
+
+ page_start += PAGE_SIZE;
+ page_end = min_t(u64, page_start + PAGE_SIZE - 1,
+ cluster->end - offset);
}
WARN_ON(nr != cluster->nr);
out:
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* [PATCH V16 18/18] Btrfs: subpage-blocksize: __btrfs_lookup_bio_sums: Set offset when moving to a new bio_vec
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (16 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 17/18] Btrfs: subpage-blocksize: Make file extent relocate code subpage blocksize aware Chandan Rajendra
@ 2016-04-14 8:32 ` Chandan Rajendra
2016-04-14 11:30 ` [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 8:32 UTC (permalink / raw)
To: linux-btrfs; +Cc: Chandan Rajendra, dsterba, clm, jbacik, chandan, aneesh.kumar
In __btrfs_lookup_bio_sums() we set the file offset value at the
beginning of every iteration of the while loop. This is incorrect since
the blocks mapped by the current bvec->bv_page might not yet have been
completely processed.
This commit fixes the issue by setting the file offset value when we
move to the next bvec of the bio.
Signed-off-by: Chandan Rajendra <chandan@linux.vnet.ibm.com>
---
fs/btrfs/file-item.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 7a7d6e2..472b069 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -222,11 +222,11 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
if (dio)
offset = logical_offset;
+ else
+ offset = page_offset(bvec->bv_page) + bvec->bv_offset;
page_bytes_left = bvec->bv_len;
while (bio_index < bio->bi_vcnt) {
- if (!dio)
- offset = page_offset(bvec->bv_page) + bvec->bv_offset;
count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
(u32 *)csum, nblocks);
if (count)
@@ -301,6 +301,9 @@ found:
goto done;
}
bvec++;
+ if (!dio)
+ offset = page_offset(bvec->bv_page)
+ + bvec->bv_offset;
page_bytes_left = bvec->bv_len;
}
--
2.1.0
^ permalink raw reply related [flat|nested] 22+ messages in thread* Re: [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size
2016-04-14 8:32 [PATCH V16 00/18] Allow I/O on blocks whose size is less than page size Chandan Rajendra
` (17 preceding siblings ...)
2016-04-14 8:32 ` [PATCH V16 18/18] Btrfs: subpage-blocksize: __btrfs_lookup_bio_sums: Set offset when moving to a new bio_vec Chandan Rajendra
@ 2016-04-14 11:30 ` Chandan Rajendra
18 siblings, 0 replies; 22+ messages in thread
From: Chandan Rajendra @ 2016-04-14 11:30 UTC (permalink / raw)
To: linux-btrfs; +Cc: dsterba, clm, jbacik, chandan, aneesh.kumar
Hello all,
I accidentally sent out patches from the incorrect branch. Please ignore this
patchset.
--
chandan
^ permalink raw reply [flat|nested] 22+ messages in thread