From: Goldwyn Rodrigues <rgoldwyn@suse.de>
To: linux-btrfs@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org, Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [PATCH 07/15] btrfs: add dax write support
Date: Tue, 26 Mar 2019 14:02:53 -0500 [thread overview]
Message-ID: <20190326190301.32365-8-rgoldwyn@suse.de> (raw)
In-Reply-To: <20190326190301.32365-1-rgoldwyn@suse.de>
From: Goldwyn Rodrigues <rgoldwyn@suse.com>
IOMAP_F_COW allows to inform the dax code, to first perform
a copy which are not page-aligned before performing the write.
A new struct btrfs_iomap is passed from iomap_begin() to
iomap_end(), which contains all the accounting and locking information
for CoW based writes.
For writing to a hole, iomap->cow_addr is set to zero. Would this
be better handled by a flag or can a valid filesystem block be at
offset zero of the device?
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
fs/btrfs/ctree.h | 6 +++
fs/btrfs/dax.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++++++--
fs/btrfs/file.c | 4 +-
3 files changed, 124 insertions(+), 5 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index a3543a4a063d..3bcd2a4959c1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3801,6 +3801,12 @@ int btree_readahead_hook(struct extent_buffer *eb, int err);
#ifdef CONFIG_FS_DAX
/* dax.c */
ssize_t btrfs_file_dax_read(struct kiocb *iocb, struct iov_iter *to);
+ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *from);
+#else
+static inline ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *from)
+{
+ return 0;
+}
#endif /* CONFIG_FS_DAX */
static inline int is_fstree(u64 rootid)
diff --git a/fs/btrfs/dax.c b/fs/btrfs/dax.c
index bf3d46b0acb6..49619fe3f94f 100644
--- a/fs/btrfs/dax.c
+++ b/fs/btrfs/dax.c
@@ -9,30 +9,124 @@
#ifdef CONFIG_FS_DAX
#include <linux/dax.h>
#include <linux/iomap.h>
+#include <linux/uio.h>
#include "ctree.h"
#include "btrfs_inode.h"
+struct btrfs_iomap {
+ u64 start;
+ u64 end;
+ int nocow;
+ struct extent_changeset *data_reserved;
+ struct extent_state *cached_state;
+};
+
static int btrfs_iomap_begin(struct inode *inode, loff_t pos,
loff_t length, unsigned flags, struct iomap *iomap)
{
struct extent_map *em;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, pos, length, 0);
+
+ if (flags & IOMAP_WRITE) {
+ int ret = 0, nocow;
+ struct extent_map *map = em;
+ struct btrfs_iomap *bi;
+
+ bi = kzalloc(sizeof(struct btrfs_iomap), GFP_NOFS);
+ if (!bi)
+ return -ENOMEM;
+
+ bi->start = round_down(pos, PAGE_SIZE);
+ bi->end = round_up(pos + length, PAGE_SIZE);
+
+ iomap->private = bi;
+
+ /* Wait for existing ordered extents in range to finish */
+ btrfs_wait_ordered_range(inode, bi->start, bi->end - bi->start);
+
+ lock_extent_bits(&BTRFS_I(inode)->io_tree, bi->start, bi->end, &bi->cached_state);
+
+ ret = btrfs_delalloc_reserve_space(inode, &bi->data_reserved,
+ bi->start, bi->end - bi->start);
+ if (ret) {
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, bi->start, bi->end,
+ &bi->cached_state);
+ kfree(bi);
+ return ret;
+ }
+
+ refcount_inc(&map->refs);
+ ret = btrfs_get_extent_map_write(&em, NULL,
+ inode, bi->start, bi->end - bi->start, &nocow);
+ if (ret) {
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, bi->start, bi->end,
+ &bi->cached_state);
+ btrfs_delalloc_release_space(inode,
+ bi->data_reserved, bi->start,
+ bi->end - bi->start, true);
+ extent_changeset_free(bi->data_reserved);
+ kfree(bi);
+ return ret;
+ }
+ if (!nocow) {
+ iomap->flags |= IOMAP_F_COW;
+ if (map->block_start != EXTENT_MAP_HOLE) {
+ iomap->cow_addr = map->block_start;
+ iomap->cow_pos = map->start;
+ }
+ } else {
+ bi->nocow = 1;
+ }
+ free_extent_map(map);
+ }
+
+ iomap->offset = em->start;
+ iomap->length = em->len;
+ iomap->bdev = em->bdev;
+ iomap->dax_dev = fs_info->dax_dev;
+
if (em->block_start == EXTENT_MAP_HOLE) {
iomap->type = IOMAP_HOLE;
return 0;
}
+
iomap->type = IOMAP_MAPPED;
- iomap->bdev = em->bdev;
- iomap->dax_dev = fs_info->dax_dev;
- iomap->offset = em->start;
- iomap->length = em->len;
iomap->addr = em->block_start;
return 0;
}
+static int btrfs_iomap_end(struct inode *inode, loff_t pos,
+ loff_t length, ssize_t written, unsigned flags,
+ struct iomap *iomap)
+{
+ struct btrfs_iomap *bi = iomap->private;
+ u64 wend;
+
+ if (!bi)
+ return 0;
+
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, bi->start, bi->end,
+ &bi->cached_state);
+
+ wend = round_up(pos + written, PAGE_SIZE);
+ if (wend < bi->end) {
+ btrfs_delalloc_release_space(inode,
+ bi->data_reserved, wend,
+ bi->end - wend, true);
+ }
+
+ btrfs_update_ordered_extent(inode, bi->start, wend - bi->start, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), wend - bi->start, false);
+ extent_changeset_free(bi->data_reserved);
+ kfree(bi);
+ return 0;
+}
+
static const struct iomap_ops btrfs_iomap_ops = {
.iomap_begin = btrfs_iomap_begin,
+ .iomap_end = btrfs_iomap_end,
};
ssize_t btrfs_file_dax_read(struct kiocb *iocb, struct iov_iter *to)
@@ -46,4 +140,21 @@ ssize_t btrfs_file_dax_read(struct kiocb *iocb, struct iov_iter *to)
return ret;
}
+
+ssize_t btrfs_file_dax_write(struct kiocb *iocb, struct iov_iter *iter)
+{
+ ssize_t ret = 0;
+ u64 pos = iocb->ki_pos;
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ ret = dax_iomap_rw(iocb, iter, &btrfs_iomap_ops);
+
+ if (ret > 0) {
+ pos += ret;
+ if (pos > i_size_read(inode))
+ i_size_write(inode, pos);
+ iocb->ki_pos = pos;
+ }
+ return ret;
+}
#endif /* CONFIG_FS_DAX */
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b620f4e718b2..3b320d0ab495 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1964,7 +1964,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
if (sync)
atomic_inc(&BTRFS_I(inode)->sync_writers);
- if (iocb->ki_flags & IOCB_DIRECT) {
+ if (IS_DAX(inode)) {
+ num_written = btrfs_file_dax_write(iocb, from);
+ } else if (iocb->ki_flags & IOCB_DIRECT) {
num_written = __btrfs_direct_write(iocb, from);
} else {
num_written = btrfs_buffered_write(iocb, from);
--
2.16.4
next prev parent reply other threads:[~2019-03-26 19:03 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20190326190301.32365-1-rgoldwyn@suse.de>
2019-03-26 19:02 ` [PATCH 01/15] btrfs: create a mount option for dax Goldwyn Rodrigues
2019-03-26 19:10 ` Matthew Wilcox
2019-03-27 11:00 ` Goldwyn Rodrigues
2019-03-27 12:00 ` Matthew Wilcox
2019-03-27 12:26 ` Goldwyn Rodrigues
2019-03-27 23:31 ` Goldwyn Rodrigues
2019-03-27 17:38 ` Adam Borowski
2019-03-28 14:49 ` David Sterba
2019-03-28 17:28 ` David Sterba
2019-03-28 17:57 ` Darrick J. Wong
2019-04-01 20:43 ` Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 02/15] btrfs: Carve out btrfs_get_extent_map_write() out of btrfs_get_blocks_write() Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 03/15] btrfs: basic dax read Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 04/15] dax: Introduce IOMAP_F_COW for copy-on-write Goldwyn Rodrigues
2019-03-27 17:54 ` Darrick J. Wong
2019-03-27 18:58 ` Goldwyn Rodrigues
2019-03-28 14:45 ` Darrick J. Wong
2019-04-01 4:38 ` Dave Chinner
2019-04-01 21:41 ` Goldwyn Rodrigues
2019-04-01 23:06 ` Dave Chinner
2019-04-03 1:56 ` Goldwyn Rodrigues
2019-04-03 3:20 ` Dave Chinner
2019-04-07 7:26 ` Christoph Hellwig
2019-03-26 19:02 ` [PATCH 05/15] btrfs: return whether extent is nocow or not Goldwyn Rodrigues
2019-03-31 18:42 ` Nikolay Borisov
2019-03-26 19:02 ` [PATCH 06/15] btrfs: Rename __endio_write_update_ordered() to btrfs_update_ordered_extent() Goldwyn Rodrigues
2019-03-26 19:02 ` Goldwyn Rodrigues [this message]
2019-03-28 14:53 ` [PATCH 07/15] btrfs: add dax write support Darrick J. Wong
2019-04-01 20:39 ` Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 08/15] dax: add dax_iomap_cow to copy a mmap page before writing Goldwyn Rodrigues
2019-03-28 15:41 ` Darrick J. Wong
2019-03-26 19:02 ` [PATCH 09/15] btrfs: add dax mmap support Goldwyn Rodrigues
2019-03-28 15:45 ` Darrick J. Wong
2019-03-26 19:02 ` [PATCH 10/15] btrfs: Add dax specific address_space_operations Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 11/15] fs: dedup file range to use a compare function Goldwyn Rodrigues
2019-03-28 17:04 ` Darrick J. Wong
2019-04-01 20:36 ` Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 12/15] btrfs: trace functions for btrfs_iomap_begin/end Goldwyn Rodrigues
2019-03-26 19:02 ` [PATCH 13/15] btrfs: handle dax page zeroing Goldwyn Rodrigues
2019-03-26 19:03 ` [PATCH 14/15] btrfs: Disable dax-based defrag and send Goldwyn Rodrigues
2019-03-26 19:03 ` [PATCH 15/15] btrfs: Writeprotect mmap pages on snapshot Goldwyn Rodrigues
2019-03-28 15:48 ` Darrick J. Wong
2019-03-26 19:09 ` [PATCH v2 00/15] btrfs dax support Goldwyn Rodrigues
2019-03-27 20:14 ` Adam Borowski
2019-03-27 23:26 ` Goldwyn Rodrigues
2019-03-28 10:24 ` [PATCH] btrfs: allow MAP_SYNC mmap Adam Borowski
2019-03-28 10:42 ` Adam Borowski
2019-04-01 20:08 ` Goldwyn Rodrigues
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=20190326190301.32365-8-rgoldwyn@suse.de \
--to=rgoldwyn@suse.de \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=rgoldwyn@suse.com \
/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).