From 58f74b2203d786da37128cbf786873996145bfdc Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 22 Dec 2020 13:59:24 +0800
Subject: btrfs: refactor btrfs_dec_test_* functions for ordered extents
The refactoring involves the following modifications:
- Return bool instead of int
- Parameter update for @cached of btrfs_dec_test_first_ordered_pending()
For btrfs_dec_test_first_ordered_pending(), @cached is only used to
return the finished ordered extent.
Rename it to @finished_ret.
- Comment updates
* Change one stale comment
Which still refers to btrfs_dec_test_ordered_pending(), but the
context is calling btrfs_dec_test_first_ordered_pending().
* Follow the common comment style for both functions
Add more detailed descriptions for parameters and the return value
* Move the reason why test_and_set_bit() is used into the call sites
- Change how the return value is calculated
The most anti-human part of the return value is:
if (...)
ret = 1;
...
return ret == 0;
This means, when we set ret to 1, the function returns 0.
Change the local variable name to @finished, and directly return the
value of it.
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/ordered-data.h | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
(limited to 'fs/btrfs/ordered-data.h')
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 0bfa82b58e23..46194c2c05d4 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -152,11 +152,11 @@ btrfs_ordered_inode_tree_init(struct btrfs_ordered_inode_tree *t)
void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry);
void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
struct btrfs_ordered_extent *entry);
-int btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
- struct btrfs_ordered_extent **cached,
- u64 file_offset, u64 io_size, int uptodate);
-int btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
- struct btrfs_ordered_extent **cached,
+bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
+ struct btrfs_ordered_extent **cached,
+ u64 file_offset, u64 io_size, int uptodate);
+bool btrfs_dec_test_first_ordered_pending(struct btrfs_inode *inode,
+ struct btrfs_ordered_extent **finished_ret,
u64 *file_offset, u64 io_size,
int uptodate);
int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
--
cgit v1.2.3
From 3c198fe064491dcceaed9e15c6c997e92e71293e Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Thu, 21 Jan 2021 14:13:54 +0800
Subject: btrfs: rework the order of btrfs_ordered_extent::flags
[BUG]
There is a long existing bug in the last parameter of
btrfs_add_ordered_extent(), in commit 771ed689d2cd ("Btrfs: Optimize
compressed writeback and reads") back to 2008.
In that ancient commit btrfs_add_ordered_extent() expects the @type
parameter to be one of the following:
- BTRFS_ORDERED_REGULAR
- BTRFS_ORDERED_NOCOW
- BTRFS_ORDERED_PREALLOC
- BTRFS_ORDERED_COMPRESSED
But we pass 0 in cow_file_range(), which means BTRFS_ORDERED_IO_DONE.
Ironically extra check in __btrfs_add_ordered_extent() won't set the bit
if we see (type == IO_DONE || type == IO_COMPLETE), and avoid any
obvious bug.
But this still leads to regular COW ordered extent having no bit to
indicate its type in various trace events, rendering REGULAR bit
useless.
[FIX]
Change the following aspects to avoid such problem:
- Reorder btrfs_ordered_extent::flags
Now the type bits go first (REGULAR/NOCOW/PREALLCO/COMPRESSED), then
DIRECT bit, finally extra status bits like IO_DONE/COMPLETE/IOERR.
- Add extra ASSERT() for btrfs_add_ordered_extent_*()
- Remove @type parameter for btrfs_add_ordered_extent_compress()
As the only valid @type here is BTRFS_ORDERED_COMPRESSED.
- Remove the unnecessary special check for IO_DONE/COMPLETE in
__btrfs_add_ordered_extent()
This is just to make the code work, with extra ASSERT(), there are
limited values can be passed in.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/ordered-data.h | 37 ++++++++++++++++++++++++-------------
1 file changed, 24 insertions(+), 13 deletions(-)
(limited to 'fs/btrfs/ordered-data.h')
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 46194c2c05d4..cca3307807e8 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -27,7 +27,7 @@ struct btrfs_ordered_sum {
};
/*
- * bits for the flags field:
+ * Bits for btrfs_ordered_extent::flags.
*
* BTRFS_ORDERED_IO_DONE is set when all of the blocks are written.
* It is used to make sure metadata is inserted into the tree only once
@@ -38,24 +38,36 @@ struct btrfs_ordered_sum {
* IO is done and any metadata is inserted into the tree.
*/
enum {
+ /*
+ * Different types for direct io, one and only one of the 4 type can
+ * be set when creating ordered extent.
+ *
+ * REGULAR: For regular non-compressed COW write
+ * NOCOW: For NOCOW write into existing non-hole extent
+ * PREALLOC: For NOCOW write into preallocated extent
+ * COMPRESSED: For compressed COW write
+ */
+ BTRFS_ORDERED_REGULAR,
+ BTRFS_ORDERED_NOCOW,
+ BTRFS_ORDERED_PREALLOC,
+ BTRFS_ORDERED_COMPRESSED,
+
+ /*
+ * Extra bit for direct io, can only be set for
+ * REGULAR/NOCOW/PREALLOC. No direct io for compressed extent.
+ */
+ BTRFS_ORDERED_DIRECT,
+
+ /* Extra status bits for ordered extents */
+
/* set when all the pages are written */
BTRFS_ORDERED_IO_DONE,
/* set when removed from the tree */
BTRFS_ORDERED_COMPLETE,
- /* set when we want to write in place */
- BTRFS_ORDERED_NOCOW,
- /* writing a zlib compressed extent */
- BTRFS_ORDERED_COMPRESSED,
- /* set when writing to preallocated extent */
- BTRFS_ORDERED_PREALLOC,
- /* set when we're doing DIO with this extent */
- BTRFS_ORDERED_DIRECT,
/* We had an io error when writing this out */
BTRFS_ORDERED_IOERR,
/* Set when we have to truncate an extent */
BTRFS_ORDERED_TRUNCATED,
- /* Regular IO for COW */
- BTRFS_ORDERED_REGULAR,
/* Used during fsync to track already logged extents */
BTRFS_ORDERED_LOGGED,
/* We have already logged all the csums of the ordered extent */
@@ -167,8 +179,7 @@ int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset,
u64 disk_num_bytes, int type);
int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset,
u64 disk_bytenr, u64 num_bytes,
- u64 disk_num_bytes, int type,
- int compress_type);
+ u64 disk_num_bytes, int compress_type);
void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
struct btrfs_ordered_sum *sum);
struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,
--
cgit v1.2.3
From d22002fd37bd970480c59754dfa448866a1f38bd Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Thu, 4 Feb 2021 19:22:00 +0900
Subject: btrfs: zoned: split ordered extent when bio is sent
For a zone append write, the device decides the location the data is being
written to. Therefore we cannot ensure that two bios are written
consecutively on the device. In order to ensure that an ordered extent
maps to a contiguous region on disk, we need to maintain a "one bio ==
one ordered extent" rule.
Implement splitting of an ordered extent and extent map on bio submission
to adhere to the rule.
extract_ordered_extent() hooks into btrfs_submit_data_bio() and splits the
corresponding ordered extent so that the ordered extent's region fits into
one bio and the corresponding device limits.
Several sanity checks need to be done in extract_ordered_extent() e.g.
- We cannot split once end_bio'd ordered extent because we cannot divide
ordered->bytes_left for the split ones
- We do not expect a compressed ordered extent
- We should not have checksum list because we omit the list splitting.
Since the function is called before btrfs_wq_submit_bio() or
btrfs_csum_one_bio(), this should be always ensured.
We also need to split an extent map by creating a new one. If not,
unpin_extent_cache() complains about the difference between the start of
the extent map and the file's logical offset.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/ordered-data.h | 2 ++
1 file changed, 2 insertions(+)
(limited to 'fs/btrfs/ordered-data.h')
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index cca3307807e8..c400be75a3f1 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -201,6 +201,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
u64 end,
struct extent_state **cached_state);
+int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre,
+ u64 post);
int __init ordered_data_init(void);
void __cold ordered_data_exit(void);
--
cgit v1.2.3
From d8e3fb106f393858b90b3befc4f6092a76c86d1c Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Thu, 4 Feb 2021 19:22:05 +0900
Subject: btrfs: zoned: use ZONE_APPEND write for zoned mode
Enable zone append writing for zoned mode. When using zone append, a
bio is issued to the start of a target zone and the device decides to
place it inside the zone. Upon completion the device reports the actual
written position back to the host.
Three parts are necessary to enable zone append mode. First, modify the
bio to use REQ_OP_ZONE_APPEND in btrfs_submit_bio_hook() and adjust the
bi_sector to point the beginning of the zone.
Second, record the returned physical address (and disk/partno) to the
ordered extent in end_bio_extent_writepage() after the bio has been
completed. We cannot resolve the physical address to the logical address
because we can neither take locks nor allocate a buffer in this end_bio
context. So, we need to record the physical address to resolve it later
in btrfs_finish_ordered_io().
And finally, rewrite the logical addresses of the extent mapping and
checksum data according to the physical address using btrfs_rmap_block.
If the returned address matches the originally allocated address, we can
skip this rewriting process.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
fs/btrfs/ordered-data.h | 8 ++++++++
1 file changed, 8 insertions(+)
(limited to 'fs/btrfs/ordered-data.h')
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index c400be75a3f1..99e0853e4d3b 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -139,6 +139,14 @@ struct btrfs_ordered_extent {
struct completion completion;
struct btrfs_work flush_work;
struct list_head work_list;
+
+ /*
+ * Used to reverse-map physical address returned from ZONE_APPEND write
+ * command in a workqueue context
+ */
+ u64 physical;
+ struct gendisk *disk;
+ u8 partno;
};
/*
--
cgit v1.2.3