From: Omar Sandoval <osandov@osandov.com>
To: linux-fsdevel@vger.kernel.org, linux-btrfs@vger.kernel.org
Cc: Dave Chinner <david@fromorbit.com>, Jann Horn <jannh@google.com>,
Amir Goldstein <amir73il@gmail.com>,
Aleksa Sarai <cyphar@cyphar.com>,
linux-api@vger.kernel.org, kernel-team@fb.com
Subject: [RFC PATCH v3 08/12] btrfs: add ram_bytes and offset to btrfs_ordered_extent
Date: Wed, 20 Nov 2019 10:24:28 -0800 [thread overview]
Message-ID: <acc02c48287b503195a513e4210d6ddd9e89418a.1574273658.git.osandov@fb.com> (raw)
In-Reply-To: <cover.1574273658.git.osandov@fb.com>
From: Omar Sandoval <osandov@fb.com>
Currently, we only create ordered extents when ram_bytes == num_bytes
and offset == 0. However, RWF_ENCODED writes may create extents which
only refer to a subset of the full unencoded extent, so we need to plumb
these fields through the ordered extent infrastructure and pass them
down to insert_reserved_file_extent().
Since we're changing the btrfs_add_ordered_extent* signature, let's get
rid of the trivial wrappers and add a kernel-doc.
Signed-off-by: Omar Sandoval <osandov@fb.com>
---
fs/btrfs/inode.c | 65 +++++++++++++++++++++++------------------
fs/btrfs/ordered-data.c | 65 +++++++++++++++--------------------------
fs/btrfs/ordered-data.h | 16 ++++------
3 files changed, 67 insertions(+), 79 deletions(-)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 62d6aaccc202..d53580ad2c46 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -846,13 +846,12 @@ static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
goto out_free_reserve;
free_extent_map(em);
- ret = btrfs_add_ordered_extent_compress(inode,
- async_extent->start,
- ins.objectid,
- async_extent->ram_size,
- ins.offset,
- BTRFS_ORDERED_COMPRESSED,
- async_extent->compress_type);
+ ret = btrfs_add_ordered_extent(inode, async_extent->start,
+ async_extent->ram_size,
+ async_extent->ram_size,
+ ins.objectid, ins.offset, 0,
+ 1 << BTRFS_ORDERED_COMPRESSED,
+ async_extent->compress_type);
if (ret) {
btrfs_drop_extent_cache(BTRFS_I(inode),
async_extent->start,
@@ -1046,8 +1045,9 @@ static noinline int cow_file_range(struct inode *inode,
}
free_extent_map(em);
- ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
- ram_size, cur_alloc_size, 0);
+ ret = btrfs_add_ordered_extent(inode, start, ram_size, ram_size,
+ ins.objectid, cur_alloc_size, 0,
+ 0, BTRFS_COMPRESS_NONE);
if (ret)
goto out_drop_extent_cache;
@@ -1584,10 +1584,11 @@ static noinline int run_delalloc_nocow(struct inode *inode,
goto error;
}
free_extent_map(em);
- ret = btrfs_add_ordered_extent(inode, cur_offset,
- disk_bytenr, num_bytes,
- num_bytes,
- BTRFS_ORDERED_PREALLOC);
+ ret = btrfs_add_ordered_extent(inode,
+ cur_offset, num_bytes, num_bytes,
+ disk_bytenr, num_bytes, 0,
+ 1 << BTRFS_ORDERED_PREALLOC,
+ BTRFS_COMPRESS_NONE);
if (ret) {
btrfs_drop_extent_cache(BTRFS_I(inode),
cur_offset,
@@ -1597,9 +1598,11 @@ static noinline int run_delalloc_nocow(struct inode *inode,
}
} else {
ret = btrfs_add_ordered_extent(inode, cur_offset,
+ num_bytes, num_bytes,
disk_bytenr, num_bytes,
- num_bytes,
- BTRFS_ORDERED_NOCOW);
+ 0,
+ 1 << BTRFS_ORDERED_NOCOW,
+ BTRFS_COMPRESS_NONE);
if (ret)
goto error;
}
@@ -2269,7 +2272,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
struct inode *inode, u64 file_pos,
u64 disk_bytenr, u64 disk_num_bytes,
- u64 num_bytes, u64 ram_bytes,
+ u64 offset, u64 num_bytes, u64 ram_bytes,
u8 compression, u8 encryption,
u16 other_encoding, int extent_type)
{
@@ -2319,7 +2322,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
btrfs_set_file_extent_type(leaf, fi, extent_type);
btrfs_set_file_extent_disk_bytenr(leaf, fi, disk_bytenr);
btrfs_set_file_extent_disk_num_bytes(leaf, fi, disk_num_bytes);
- btrfs_set_file_extent_offset(leaf, fi, 0);
+ btrfs_set_file_extent_offset(leaf, fi, offset);
btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
btrfs_set_file_extent_ram_bytes(leaf, fi, ram_bytes);
btrfs_set_file_extent_compression(leaf, fi, compression);
@@ -2345,7 +2348,8 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
qg_released = ret;
ret = btrfs_alloc_reserved_file_extent(trans, root,
btrfs_ino(BTRFS_I(inode)),
- file_pos, qg_released, &ins);
+ file_pos - offset, qg_released,
+ &ins);
out:
btrfs_free_path(path);
@@ -2382,7 +2386,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
u64 start, end;
int compress_type = 0;
int ret = 0;
- u64 logical_len = ordered_extent->num_bytes;
+ u64 num_bytes = ordered_extent->num_bytes;
+ u64 ram_bytes = ordered_extent->ram_bytes;
bool nolock;
bool truncated = false;
bool range_locked = false;
@@ -2409,9 +2414,9 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
truncated = true;
- logical_len = ordered_extent->truncated_len;
+ num_bytes = ram_bytes = ordered_extent->truncated_len;
/* Truncated the entire extent, don't bother adding */
- if (!logical_len)
+ if (!num_bytes)
goto out;
}
@@ -2466,13 +2471,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
ret = btrfs_mark_extent_written(trans, BTRFS_I(inode),
ordered_extent->file_offset,
ordered_extent->file_offset +
- logical_len);
+ num_bytes);
} else {
BUG_ON(root == fs_info->tree_root);
ret = insert_reserved_file_extent(trans, inode, start,
ordered_extent->disk_bytenr,
ordered_extent->disk_num_bytes,
- logical_len, logical_len,
+ ordered_extent->offset,
+ num_bytes, ram_bytes,
compress_type, 0, 0,
BTRFS_FILE_EXTENT_REG);
if (!ret) {
@@ -2520,7 +2526,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
u64 unwritten_start = start;
if (truncated)
- unwritten_start += logical_len;
+ unwritten_start += num_bytes;
clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
/* Drop the cache for the part of the extent we didn't write. */
@@ -2537,7 +2543,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
* errored out then we don't need to do this as the accounting
* has already been done.
*/
- if ((ret || !logical_len) &&
+ if ((ret || !num_bytes) &&
clear_reserved_extent &&
!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
!test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
@@ -6609,8 +6615,11 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
if (IS_ERR(em))
goto out;
}
- ret = btrfs_add_ordered_extent_dio(inode, start, block_start,
- len, block_len, type);
+ ret = btrfs_add_ordered_extent(inode, start, len, len, block_start,
+ block_len, 0,
+ (1 << type) |
+ (1 << BTRFS_ORDERED_DIRECT),
+ BTRFS_COMPRESS_NONE);
if (ret) {
if (em) {
free_extent_map(em);
@@ -9743,7 +9752,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
last_alloc = ins.offset;
ret = insert_reserved_file_extent(trans, inode,
cur_offset, ins.objectid,
- ins.offset, ins.offset,
+ ins.offset, 0, ins.offset,
ins.offset, 0, 0, 0,
BTRFS_FILE_EXTENT_PREALLOC);
if (ret) {
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 94e2485006ab..3c6edc307657 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -160,15 +160,27 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
return ret;
}
-/* allocate and add a new ordered_extent into the per-inode tree.
+/**
+ * btrfs_add_ordered_extent - Add an ordered extent to the per-inode tree.
+ * @inode: inode that this extent is for.
+ * @file_offset: Logical offset in file where the extent starts.
+ * @num_bytes: Logical length of extent in file.
+ * @ram_bytes: Full length of unencoded data.
+ * @disk_bytenr: Offset of extent on disk.
+ * @disk_num_bytes: Size of extent on disk.
+ * @offset: Offset into unencoded data where file data starts.
+ * @flags: Flags specifying type of extent (1 << BTRFS_ORDERED_*).
+ * @compress_type: Compression algorithm used for data.
*
- * The tree is given a single reference on the ordered extent that was
- * inserted.
+ * Most of these parameters correspond to &struct btrfs_file_extent_item. The
+ * tree is given a single reference on the ordered extent that was inserted.
+ *
+ * Return: 0 or -ENOMEM.
*/
-static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
- u64 disk_bytenr, u64 num_bytes,
- u64 disk_num_bytes, int type, int dio,
- int compress_type)
+int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
+ u64 num_bytes, u64 ram_bytes, u64 disk_bytenr,
+ u64 disk_num_bytes, u64 offset, int flags,
+ int compress_type)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -182,20 +194,19 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
return -ENOMEM;
entry->file_offset = file_offset;
- entry->disk_bytenr = disk_bytenr;
entry->num_bytes = num_bytes;
+ entry->ram_bytes = ram_bytes;
+ entry->disk_bytenr = disk_bytenr;
entry->disk_num_bytes = disk_num_bytes;
+ entry->offset = offset;
entry->bytes_left = num_bytes;
entry->inode = igrab(inode);
entry->compress_type = compress_type;
entry->truncated_len = (u64)-1;
- if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE)
- set_bit(type, &entry->flags);
-
- if (dio) {
+ entry->flags = flags;
+ if (flags & (1 << BTRFS_ORDERED_DIRECT)) {
percpu_counter_add_batch(&fs_info->dio_bytes, num_bytes,
fs_info->delalloc_batch);
- set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);
}
/* one ref for the tree */
@@ -241,34 +252,6 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
return 0;
}
-int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
- u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
- int type)
-{
- return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
- num_bytes, disk_num_bytes, type, 0,
- BTRFS_COMPRESS_NONE);
-}
-
-int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
- u64 disk_bytenr, u64 num_bytes,
- u64 disk_num_bytes, int type)
-{
- return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
- num_bytes, disk_num_bytes, type, 1,
- BTRFS_COMPRESS_NONE);
-}
-
-int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
- u64 disk_bytenr, u64 num_bytes,
- u64 disk_num_bytes, int type,
- int compress_type)
-{
- return __btrfs_add_ordered_extent(inode, file_offset, disk_bytenr,
- num_bytes, disk_num_bytes, type, 0,
- compress_type);
-}
-
/*
* Add a struct btrfs_ordered_sum into the list of checksums to be inserted
* when an ordered extent is finished. If the list covers more than one
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 4a3dd80e776c..a038bda16fdf 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -71,9 +71,11 @@ struct btrfs_ordered_extent {
* These fields directly correspond to the same fields in
* btrfs_file_extent_item.
*/
- u64 disk_bytenr;
u64 num_bytes;
+ u64 ram_bytes;
+ u64 disk_bytenr;
u64 disk_num_bytes;
+ u64 offset;
/* number of bytes that still need writing */
u64 bytes_left;
@@ -160,15 +162,9 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
u64 *file_offset, u64 io_size,
int uptodate);
int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
- u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
- int type);
-int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset,
- u64 disk_bytenr, u64 num_bytes,
- u64 disk_num_bytes, int type);
-int btrfs_add_ordered_extent_compress(struct inode *inode, u64 file_offset,
- u64 disk_bytenr, u64 num_bytes,
- u64 disk_num_bytes, int type,
- int compress_type);
+ u64 num_bytes, u64 ram_bytes, u64 disk_bytenr,
+ u64 disk_num_bytes, u64 offset, int flags,
+ 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 inode *inode,
--
2.24.0
next prev parent reply other threads:[~2019-11-20 18:25 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-20 18:24 [RFC PATCH v3 00/12] fs: interface for directly reading/writing compressed data Omar Sandoval
2019-11-20 18:24 ` [PATCH man-pages v2] Document encoded I/O Omar Sandoval
2019-12-05 18:58 ` [RFC PATCH v3 00/12] fs: interface for directly reading/writing compressed data Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 01/12] iov_iter: add copy_struct_from_iter() Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 02/12] fs: add O_ALLOW_ENCODED open flag Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 03/12] fs: add RWF_ENCODED for reading/writing compressed data Omar Sandoval
2019-11-26 13:53 ` Nikolay Borisov
2019-11-26 17:36 ` Omar Sandoval
2019-11-27 9:00 ` Nikolay Borisov
2019-11-27 9:10 ` Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 04/12] btrfs: get rid of trivial __btrfs_lookup_bio_sums() wrappers Omar Sandoval
2019-11-26 13:56 ` Nikolay Borisov
2019-11-26 17:42 ` Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 05/12] btrfs: don't advance offset for compressed bios in btrfs_csum_one_bio() Omar Sandoval
2019-11-26 14:18 ` Nikolay Borisov
2019-11-26 17:50 ` Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 06/12] btrfs: remove dead snapshot-aware defrag code Omar Sandoval
2019-11-26 15:13 ` Nikolay Borisov
2019-11-20 18:24 ` [RFC PATCH v3 07/12] btrfs: make btrfs_ordered_extent naming consistent with btrfs_file_extent_item Omar Sandoval
2019-11-20 18:24 ` Omar Sandoval [this message]
2019-11-27 10:13 ` [RFC PATCH v3 08/12] btrfs: add ram_bytes and offset to btrfs_ordered_extent Nikolay Borisov
2019-11-20 18:24 ` [RFC PATCH v3 09/12] btrfs: support different disk extent size for delalloc Omar Sandoval
2019-11-27 10:33 ` Nikolay Borisov
2019-11-20 18:24 ` [RFC PATCH v3 10/12] btrfs: optionally extend i_size in cow_file_range_inline() Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 11/12] btrfs: implement RWF_ENCODED reads Omar Sandoval
2019-11-20 18:24 ` [RFC PATCH v3 12/12] btrfs: implement RWF_ENCODED writes Omar Sandoval
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=acc02c48287b503195a513e4210d6ddd9e89418a.1574273658.git.osandov@fb.com \
--to=osandov@osandov.com \
--cc=amir73il@gmail.com \
--cc=cyphar@cyphar.com \
--cc=david@fromorbit.com \
--cc=jannh@google.com \
--cc=kernel-team@fb.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).