From: Goldwyn Rodrigues <rgoldwyn@suse.de>
To: linux-btrfs@vger.kernel.org
Cc: kilobyte@angband.pl, linux-fsdevel@vger.kernel.org, jack@suse.cz,
david@fromorbit.com, willy@infradead.org, hch@lst.de,
darrick.wong@oracle.com, dsterba@suse.cz, nborisov@suse.com,
linux-nvdimm@lists.01.org, Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [PATCH 07/18] btrfs: add dax write support
Date: Mon, 29 Apr 2019 12:26:38 -0500 [thread overview]
Message-ID: <20190429172649.8288-8-rgoldwyn@suse.de> (raw)
In-Reply-To: <20190429172649.8288-1-rgoldwyn@suse.de>
From: Goldwyn Rodrigues <rgoldwyn@suse.com>
IOMAP_DAX_COW allows to inform the dax code, to first perform
a copy which are not page-aligned before performing the write.
The responsibility of checking if data edges are page aligned
is performed in ->iomap_begin() and the source address is
stored in ->inline_data
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->inline_data is set to zero.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
---
fs/btrfs/ctree.h | 6 ++
fs/btrfs/dax.c | 182 +++++++++++++++++++++++++++++++++++++++++++++++++++++--
fs/btrfs/file.c | 4 +-
3 files changed, 185 insertions(+), 7 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 1e3e758b83c2..eec01eb92f33 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..f5cc9bcdbf14 100644
--- a/fs/btrfs/dax.c
+++ b/fs/btrfs/dax.c
@@ -9,30 +9,184 @@
#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;
+ bool nocow;
+ struct extent_changeset *data_reserved;
+ struct extent_state *cached_state;
+};
+
+static struct btrfs_iomap *btrfs_iomap_init(struct inode *inode,
+ struct extent_map **em,
+ loff_t pos, loff_t length)
+{
+ int ret = 0;
+ struct extent_map *map = *em;
+ struct btrfs_iomap *bi;
+
+ bi = kzalloc(sizeof(struct btrfs_iomap), GFP_NOFS);
+ if (!bi)
+ return ERR_PTR(-ENOMEM);
+
+ bi->start = round_down(pos, PAGE_SIZE);
+ bi->end = PAGE_ALIGN(pos + length);
+
+ /* 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 ERR_PTR(ret);
+ }
+
+ refcount_inc(&map->refs);
+ ret = btrfs_get_extent_map_write(em, NULL,
+ inode, bi->start, bi->end - bi->start, &bi->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 ERR_PTR(ret);
+ }
+ free_extent_map(map);
+ return bi;
+}
+
+static void *dax_address(struct block_device *bdev, struct dax_device *dax_dev,
+ sector_t sector, loff_t pos, loff_t length)
+{
+ size_t size = ALIGN(pos + length, PAGE_SIZE);
+ int id, ret = 0;
+ void *kaddr = NULL;
+ pgoff_t pgoff;
+ long map_len;
+
+ id = dax_read_lock();
+
+ ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+ if (ret)
+ goto out;
+
+ map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
+ &kaddr, NULL);
+ if (map_len < 0)
+ ret = map_len;
+
+out:
+ dax_read_unlock(id);
+ if (ret)
+ return ERR_PTR(ret);
+ return kaddr;
+}
+
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);
+ struct btrfs_iomap *bi = NULL;
+ unsigned offset = pos & (PAGE_SIZE - 1);
+ u64 srcblk = 0;
+ loff_t diff;
+
em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, pos, length, 0);
+
+ iomap->type = IOMAP_MAPPED;
+
+ if (flags & IOMAP_WRITE) {
+ if (em->block_start != EXTENT_MAP_HOLE)
+ srcblk = em->block_start + pos - em->start - offset;
+
+ bi = btrfs_iomap_init(inode, &em, pos, length);
+ if (IS_ERR(bi))
+ return PTR_ERR(bi);
+
+ }
+
+ /*
+ * Advance the difference between pos and start, to align well with
+ * inline_data in case of writes
+ */
+ diff = round_down(pos - em->start, PAGE_SIZE);
+ iomap->offset = em->start + diff;
+ iomap->length = em->len - diff;
+ iomap->bdev = em->bdev;
+ iomap->dax_dev = fs_info->dax_dev;
+
+ /*
+ * This will be true for reads only since we have already
+ * allocated em
+ */
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;
+
+ iomap->addr = em->block_start + diff;
+ /* Check if we really need to copy data from old extent */
+ if (bi && !bi->nocow && (offset || pos + length < bi->end)) {
+ iomap->type = IOMAP_DAX_COW;
+ if (srcblk) {
+ sector_t sector = (srcblk + (pos & PAGE_MASK) -
+ iomap->offset) >> 9;
+ iomap->inline_data = dax_address(em->bdev,
+ fs_info->dax_dev, sector, pos, length);
+ if (IS_ERR(iomap->inline_data)) {
+ kfree(bi);
+ return PTR_ERR(iomap->inline_data);
+ }
+ }
+ }
+
+ iomap->private = bi;
+ 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 = PAGE_ALIGN(pos + written);
+ 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 +200,20 @@ 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 9194591f9eea..a795023e26ca 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:[~2019-04-29 17:27 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-29 17:26 [PATCH v4 00/18] btrfs dax support Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 01/18] btrfs: create a mount option for dax Goldwyn Rodrigues
2019-05-21 18:02 ` Darrick J. Wong
2019-04-29 17:26 ` [PATCH 02/18] btrfs: Carve out btrfs_get_extent_map_write() out of btrfs_get_blocks_write() Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 03/18] btrfs: basic dax read Goldwyn Rodrigues
2019-05-21 15:14 ` Darrick J. Wong
2019-05-22 21:50 ` Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 04/18] dax: Introduce IOMAP_DAX_COW to CoW edges during writes Goldwyn Rodrigues
2019-05-21 16:51 ` Darrick J. Wong
2019-05-22 20:14 ` Goldwyn Rodrigues
2019-05-23 2:10 ` Dave Chinner
2019-05-23 9:05 ` Shiyang Ruan
2019-05-23 11:51 ` Goldwyn Rodrigues
2019-05-27 8:25 ` Shiyang Ruan
2019-05-28 9:17 ` Jan Kara
2019-05-29 2:01 ` Shiyang Ruan
2019-05-29 2:47 ` Dave Chinner
2019-05-29 4:02 ` Shiyang Ruan
2019-05-29 4:07 ` Darrick J. Wong
2019-05-29 4:46 ` Dave Chinner
2019-05-29 13:46 ` Jan Kara
2019-05-29 22:14 ` Dave Chinner
2019-05-30 11:16 ` Jan Kara
2019-05-30 22:59 ` Dave Chinner
2019-04-29 17:26 ` [PATCH 05/18] btrfs: return whether extent is nocow or not Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 06/18] btrfs: Rename __endio_write_update_ordered() to btrfs_update_ordered_extent() Goldwyn Rodrigues
2019-04-29 17:26 ` Goldwyn Rodrigues [this message]
2019-05-21 17:08 ` [PATCH 07/18] btrfs: add dax write support Darrick J. Wong
2019-04-29 17:26 ` [PATCH 08/18] dax: memcpy page in case of IOMAP_DAX_COW for mmap faults Goldwyn Rodrigues
2019-05-21 17:46 ` Darrick J. Wong
2019-05-22 19:11 ` Goldwyn Rodrigues
2019-05-23 4:02 ` Darrick J. Wong
2019-05-23 12:10 ` Jan Kara
2019-04-29 17:26 ` [PATCH 09/18] btrfs: Add dax specific address_space_operations Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 10/18] dax: replace mmap entry in case of CoW Goldwyn Rodrigues
2019-05-21 17:35 ` Darrick J. Wong
2019-05-23 13:38 ` Jan Kara
2019-04-29 17:26 ` [PATCH 11/18] btrfs: add dax mmap support Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 12/18] btrfs: allow MAP_SYNC mmap Goldwyn Rodrigues
2019-05-10 15:32 ` [PATCH for-goldwyn] btrfs: disallow MAP_SYNC outside of DAX mounts Adam Borowski
2019-05-10 15:41 ` Dan Williams
2019-05-10 15:59 ` Pankaj Gupta
2019-05-23 13:44 ` [PATCH 12/18] btrfs: allow MAP_SYNC mmap Jan Kara
2019-05-23 16:19 ` Adam Borowski
2019-04-29 17:26 ` [PATCH 13/18] fs: dedup file range to use a compare function Goldwyn Rodrigues
2019-05-21 18:17 ` Darrick J. Wong
2019-04-29 17:26 ` [PATCH 14/18] dax: memcpy before zeroing range Goldwyn Rodrigues
2019-05-21 17:27 ` Darrick J. Wong
2019-04-29 17:26 ` [PATCH 15/18] btrfs: handle dax page zeroing Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 16/18] btrfs: Writeprotect mmap pages on snapshot Goldwyn Rodrigues
2019-05-23 14:04 ` Jan Kara
2019-05-23 15:27 ` Goldwyn Rodrigues
2019-05-23 19:07 ` Jan Kara
2019-05-23 21:22 ` Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 17/18] btrfs: Disable dax-based defrag and send Goldwyn Rodrigues
2019-04-29 17:26 ` [PATCH 18/18] btrfs: trace functions for btrfs_iomap_begin/end Goldwyn Rodrigues
-- strict thread matches above, loose matches on Subject: below --
2019-04-16 16:41 [PATCH v3 00/18] btrfs dax support Goldwyn Rodrigues
2019-04-16 16:41 ` [PATCH 07/18] btrfs: add dax write support 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=20190429172649.8288-8-rgoldwyn@suse.de \
--to=rgoldwyn@suse.de \
--cc=darrick.wong@oracle.com \
--cc=david@fromorbit.com \
--cc=dsterba@suse.cz \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=kilobyte@angband.pl \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nvdimm@lists.01.org \
--cc=nborisov@suse.com \
--cc=rgoldwyn@suse.com \
--cc=willy@infradead.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).