From: Jan Kara <jack@suse.com>
To: linux-ext4@vger.kernel.org
Cc: Ted Tso <tytso@mit.edu>, Dan Williams <dan.j.williams@intel.com>,
ross.zwisler@linux.intel.com, willy@linux.intel.com,
Jan Kara <jack@suse.com>
Subject: [PATCH 9/9] ext4: Use pre-zeroed blocks for DAX page faults
Date: Thu, 22 Oct 2015 10:16:01 +0200 [thread overview]
Message-ID: <1445501761-14528-10-git-send-email-jack@suse.com> (raw)
In-Reply-To: <1445501761-14528-1-git-send-email-jack@suse.com>
Make DAX fault path use pre-zeroed blocks to avoid races with extent
conversion and zeroing when two page faults to the same block happen.
Signed-off-by: Jan Kara <jack@suse.com>
---
fs/ext4/ext4.h | 4 +--
fs/ext4/file.c | 20 +++-----------
fs/ext4/inode.c | 81 +++++++++++++++++++++++++++++++++++++++++++++------------
3 files changed, 69 insertions(+), 36 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0a11a34d54c9..9b6e5813968b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2284,8 +2284,8 @@ struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
int ext4_get_block_write(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
-int ext4_get_block_dax(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create);
+int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 0d24ebcd7c9e..749b222e6498 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -193,18 +193,6 @@ out:
}
#ifdef CONFIG_FS_DAX
-static void ext4_end_io_unwritten(struct buffer_head *bh, int uptodate)
-{
- struct inode *inode = bh->b_assoc_map->host;
- /* XXX: breaks on 32-bit > 16TB. Is that even supported? */
- loff_t offset = (loff_t)(uintptr_t)bh->b_private << inode->i_blkbits;
- int err;
- if (!uptodate)
- return;
- WARN_ON(!buffer_unwritten(bh));
- err = ext4_convert_unwritten_extents(NULL, inode, offset, bh->b_size);
-}
-
static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int result;
@@ -225,8 +213,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
else
- result = __dax_fault(vma, vmf, ext4_get_block_dax,
- ext4_end_io_unwritten);
+ result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
if (write) {
if (!IS_ERR(handle))
@@ -262,7 +249,7 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
result = VM_FAULT_SIGBUS;
else
result = __dax_pmd_fault(vma, addr, pmd, flags,
- ext4_get_block_dax, ext4_end_io_unwritten);
+ ext4_dax_mmap_get_block, NULL);
if (write) {
if (!IS_ERR(handle))
@@ -283,8 +270,7 @@ static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
- err = __dax_mkwrite(vma, vmf, ext4_get_block_dax,
- ext4_end_io_unwritten);
+ err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 73c6214084d4..c2a476a35464 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -718,16 +718,6 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
- if (IS_DAX(inode) && buffer_unwritten(bh)) {
- /*
- * dgc: I suspect unwritten conversion on ext4+DAX is
- * fundamentally broken here when there are concurrent
- * read/write in progress on this inode.
- */
- WARN_ON_ONCE(io_end);
- bh->b_assoc_map = inode->i_mapping;
- bh->b_private = (void *)(unsigned long)iblock;
- }
if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
set_buffer_defer_completion(bh);
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
@@ -3050,17 +3040,74 @@ static int ext4_get_block_overwrite(struct inode *inode, sector_t iblock,
return ret;
}
-int ext4_get_block_dax(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+#ifdef CONFIG_FS_DAX
+int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
{
- int flags = EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_UNWRIT_EXT;
+ int ret, err;
+ int credits;
+ struct ext4_map_blocks map;
+ handle_t *handle = NULL;
+ int flags = 0;
- if (create)
- flags |= EXT4_GET_BLOCKS_CREATE;
- ext4_debug("ext4_get_block_dax: inode %lu, create flag %d\n",
+ ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n",
inode->i_ino, create);
- return _ext4_get_block(inode, iblock, bh_result, flags);
+ map.m_lblk = iblock;
+ map.m_len = bh_result->b_size >> inode->i_blkbits;
+ credits = ext4_chunk_trans_blocks(inode, map.m_len);
+ if (create) {
+ flags |= EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_CREATE_ZERO;
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ return ret;
+ }
+ }
+
+ ret = ext4_map_blocks(handle, inode, &map, flags);
+ if (create) {
+ err = ext4_journal_stop(handle);
+ if (ret >= 0 && err < 0)
+ ret = err;
+ }
+ if (ret <= 0)
+ goto out;
+ if (map.m_flags & EXT4_MAP_UNWRITTEN) {
+ int err2;
+
+ /*
+ * We are protected by i_mmap_sem so we know block cannot go
+ * away from under us even though we dropped i_data_sem.
+ * Convert extent to written and write zeros there.
+ *
+ * Note: We may get here even when create == 0.
+ */
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+
+ err = ext4_map_blocks(handle, inode, &map,
+ EXT4_GET_BLOCKS_CONVERT | EXT4_GET_BLOCKS_CREATE_ZERO);
+ if (err < 0)
+ ret = err;
+ err2 = ext4_journal_stop(handle);
+ if (err2 < 0 && ret > 0)
+ ret = err2;
+ }
+out:
+ WARN_ON_ONCE(ret == 0 && create);
+ if (ret > 0) {
+ map_bh(bh_result, inode->i_sb, map.m_pblk);
+ bh_result->b_state = (bh_result->b_state & ~EXT4_MAP_FLAGS) |
+ map.m_flags;
+ bh_result->b_size = map.m_len << inode->i_blkbits;
+ ret = 0;
+ }
+ return ret;
}
+#endif
static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
ssize_t size, void *private)
--
2.1.4
next prev parent reply other threads:[~2015-10-22 8:16 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-10-22 8:15 [PATCH 0/9 v2] ext4: Punch hole and DAX fixes Jan Kara
2015-10-22 8:15 ` [PATCH 1/9] ext4: Fix races between page faults and hole punching Jan Kara
2015-10-24 1:21 ` Theodore Ts'o
2015-10-25 4:58 ` Jan Kara
2015-10-22 8:15 ` [PATCH 2/9] ext4: Move unlocked dio protection from ext4_alloc_file_blocks() Jan Kara
2015-10-22 8:15 ` [PATCH 3/9] ext4: Fix races between buffered IO and collapse / insert range Jan Kara
2015-10-24 1:22 ` Theodore Ts'o
2015-10-24 4:59 ` Theodore Ts'o
2015-10-22 8:15 ` [PATCH 4/9] ext4: Fix races of writeback with punch hole and zero range Jan Kara
2015-10-22 8:15 ` [PATCH 5/9] ext4: Document lock ordering Jan Kara
2015-10-22 8:15 ` [PATCH 6/9] ext4: Get rid of EXT4_GET_BLOCKS_NO_LOCK flag Jan Kara
2015-10-22 8:15 ` [PATCH 7/9] ext4: Provide ext4_issue_zeroout() Jan Kara
2015-10-22 8:16 ` [PATCH 8/9] ext4: Implement allocation of pre-zeroed blocks Jan Kara
2015-10-22 8:16 ` Jan Kara [this message]
2015-10-25 9:23 ` [PATCH 9/9] ext4: Use pre-zeroed blocks for DAX page faults Theodore Ts'o
2015-10-22 18:09 ` [PATCH 0/9 v2] ext4: Punch hole and DAX fixes Ross Zwisler
2015-10-22 21:14 ` Jan Kara
2015-10-23 3:35 ` Eryu Guan
-- strict thread matches above, loose matches on Subject: below --
2015-11-04 16:18 [PATCH 0/9 v3] " Jan Kara
2015-11-04 16:18 ` [PATCH 9/9] ext4: Use pre-zeroed blocks for DAX page faults Jan Kara
2015-11-10 19:50 [PATCH 0/9 v4] ext4: Punch hole and DAX fixes Jan Kara
2015-11-10 19:50 ` [PATCH 9/9] ext4: Use pre-zeroed blocks for DAX page faults Jan Kara
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=1445501761-14528-10-git-send-email-jack@suse.com \
--to=jack@suse.com \
--cc=dan.j.williams@intel.com \
--cc=linux-ext4@vger.kernel.org \
--cc=ross.zwisler@linux.intel.com \
--cc=tytso@mit.edu \
--cc=willy@linux.intel.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).