| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20240429174746.2132161-16-john.g.garry@oracle.com>
Date: Mon, 29 Apr 2024 17:47:40 +0000
From: John Garry <john.g.garry@...cle.com>
To: david@...morbit.com, djwong@...nel.org, hch@....de,
viro@...iv.linux.org.uk, brauner@...nel.org, jack@...e.cz,
chandan.babu@...cle.com, willy@...radead.org
Cc: axboe@...nel.dk, martin.petersen@...cle.com, linux-kernel@...r.kernel.org,
linux-fsdevel@...r.kernel.org, tytso@....edu, jbongio@...gle.com,
ojaswin@...ux.ibm.com, ritesh.list@...il.com, mcgrof@...nel.org,
p.raghav@...sung.com, linux-xfs@...r.kernel.org,
catherine.hoang@...cle.com, John Garry <john.g.garry@...cle.com>
Subject: [PATCH v3 15/21] fs: xfs: iomap: Sub-extent zeroing
Set iomap->extent_size when sub-extent zeroing is required.
We treat a sub-extent write same as an unaligned write, so we can leverage
the existing sub-FSblock unaligned write support, i.e. try a shared lock
with IOMAP_DIO_OVERWRITE_ONLY flag, if this fails then try the exclusive
lock.
In xfs_iomap_write_unwritten(), FSB calcs are now based on the extsize.
Signed-off-by: John Garry <john.g.garry@...cle.com>
---
fs/xfs/xfs_file.c | 35 ++++++++++++++++++++++-------------
fs/xfs/xfs_iomap.c | 13 +++++++++++--
2 files changed, 33 insertions(+), 15 deletions(-)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e81e01e6b22b..ee4f94cf6f4e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -620,18 +620,19 @@ xfs_file_dio_write_aligned(
* Handle block unaligned direct I/O writes
*
* In most cases direct I/O writes will be done holding IOLOCK_SHARED, allowing
- * them to be done in parallel with reads and other direct I/O writes. However,
- * if the I/O is not aligned to filesystem blocks, the direct I/O layer may need
- * to do sub-block zeroing and that requires serialisation against other direct
- * I/O to the same block. In this case we need to serialise the submission of
- * the unaligned I/O so that we don't get racing block zeroing in the dio layer.
- * In the case where sub-block zeroing is not required, we can do concurrent
- * sub-block dios to the same block successfully.
+ * them to be done in parallel with reads and other direct I/O writes.
+ * However if the I/O is not aligned to filesystem blocks/extent, the direct
+ * I/O layer may need to do sub-block/extent zeroing and that requires
+ * serialisation against other direct I/O to the same block/extent. In this
+ * case we need to serialise the submission of the unaligned I/O so that we
+ * don't get racing block/extent zeroing in the dio layer.
+ * In the case where sub-block/extent zeroing is not required, we can do
+ * concurrent sub-block/extent dios to the same block/extent successfully.
*
* Optimistically submit the I/O using the shared lock first, but use the
* IOMAP_DIO_OVERWRITE_ONLY flag to tell the lower layers to return -EAGAIN
- * if block allocation or partial block zeroing would be required. In that case
- * we try again with the exclusive lock.
+ * if block/extent allocation or partial block/extent zeroing would be
+ * required. In that case we try again with the exclusive lock.
*/
static noinline ssize_t
xfs_file_dio_write_unaligned(
@@ -646,9 +647,9 @@ xfs_file_dio_write_unaligned(
ssize_t ret;
/*
- * Extending writes need exclusivity because of the sub-block zeroing
- * that the DIO code always does for partial tail blocks beyond EOF, so
- * don't even bother trying the fast path in this case.
+ * Extending writes need exclusivity because of the sub-block/extent
+ * zeroing that the DIO code always does for partial tail blocks
+ * beyond EOF, so don't even bother trying the fast path in this case.
*/
if (iocb->ki_pos > isize || iocb->ki_pos + count >= isize) {
if (iocb->ki_flags & IOCB_NOWAIT)
@@ -714,11 +715,19 @@ xfs_file_dio_write(
struct xfs_inode *ip = XFS_I(file_inode(iocb->ki_filp));
struct xfs_buftarg *target = xfs_inode_buftarg(ip);
size_t count = iov_iter_count(from);
+ struct xfs_mount *mp = ip->i_mount;
+ unsigned int blockmask;
/* direct I/O must be aligned to device logical sector size */
if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
- if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask)
+
+ if (xfs_inode_has_forcealign(ip) && ip->i_extsize > 1)
+ blockmask = XFS_FSB_TO_B(mp, ip->i_extsize) - 1;
+ else
+ blockmask = mp->m_blockmask;
+
+ if ((iocb->ki_pos | count) & blockmask)
return xfs_file_dio_write_unaligned(ip, iocb, from);
return xfs_file_dio_write_aligned(ip, iocb, from);
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 4087af7f3c9f..1a3692bbc84d 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -138,6 +138,8 @@ xfs_bmbt_to_iomap(
iomap->validity_cookie = sequence_cookie;
iomap->folio_ops = &xfs_iomap_folio_ops;
+ if (xfs_inode_has_forcealign(ip) && ip->i_extsize > 1)
+ iomap->extent_size = XFS_FSB_TO_B(mp, ip->i_extsize);
return 0;
}
@@ -570,8 +572,15 @@ xfs_iomap_write_unwritten(
trace_xfs_unwritten_convert(ip, offset, count);
- offset_fsb = XFS_B_TO_FSBT(mp, offset);
- count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
+ if (xfs_inode_has_forcealign(ip) && ip->i_extsize > 1) {
+ xfs_extlen_t extsize_bytes = mp->m_sb.sb_blocksize * ip->i_extsize;
+
+ offset_fsb = XFS_B_TO_FSBT(mp, round_down(offset, extsize_bytes));
+ count_fsb = XFS_B_TO_FSB(mp, round_up(offset + count, extsize_bytes));
+ } else {
+ offset_fsb = XFS_B_TO_FSBT(mp, offset);
+ count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
+ }
count_fsb = (xfs_filblks_t)(count_fsb - offset_fsb);
/*
--
2.31.1
Powered by blists - more mailing lists