From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: darrick.wong@oracle.com
Cc: linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-api@vger.kernel.org
Subject: [PATCH 17/18] xfs: remove old swap extents implementation
Date: Tue, 28 Apr 2020 19:46:05 -0700 [thread overview]
Message-ID: <158812836551.168506.6339048941371563780.stgit@magnolia> (raw)
In-Reply-To: <158812825316.168506.932540609191384366.stgit@magnolia>
From: Darrick J. Wong <darrick.wong@oracle.com>
Migrate the old XFS_IOC_SWAPEXT implementation to use our shiny new one.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
fs/xfs/xfs_bmap_util.c | 193 ------------------------------------------------
fs/xfs/xfs_bmap_util.h | 2
fs/xfs/xfs_ioctl.c | 108 ++++++++-------------------
3 files changed, 32 insertions(+), 271 deletions(-)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 639b42b1d568..df373107e782 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1334,23 +1334,6 @@ xfs_swap_extents_check_format(
return 0;
}
-static int
-xfs_swap_extent_flush(
- struct xfs_inode *ip)
-{
- int error;
-
- error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
- if (error)
- return error;
- truncate_pagecache_range(VFS_I(ip), 0, -1);
-
- /* Verify O_DIRECT for ftmp */
- if (VFS_I(ip)->i_mapping->nrpages)
- return -EINVAL;
- return 0;
-}
-
/*
* Fix up the owners of the bmbt blocks to refer to the current inode. The
* change owner scan attempts to order all modified buffers in the current
@@ -1519,181 +1502,6 @@ xfs_swap_extent_forks(
return 0;
}
-int
-xfs_swap_extents(
- struct xfs_inode *ip, /* target inode */
- struct xfs_inode *tip, /* tmp inode */
- struct xfs_swapext *sxp)
-{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_trans *tp;
- struct xfs_bstat *sbp = &sxp->sx_stat;
- int error = 0;
- int lock_flags;
- int resblks = 0;
-
- /*
- * Lock the inodes against other IO, page faults and truncate to
- * begin with. Then we can ensure the inodes are flushed and have no
- * page cache safely. Once we have done this we can take the ilocks and
- * do the rest of the checks.
- */
- lock_two_nondirectories(VFS_I(ip), VFS_I(tip));
- lock_flags = XFS_MMAPLOCK_EXCL;
- xfs_lock_two_inodes(ip, XFS_MMAPLOCK_EXCL, tip, XFS_MMAPLOCK_EXCL);
-
- /* Verify that both files have the same format */
- if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
- error = -EINVAL;
- goto out_unlock;
- }
-
- /* Verify both files are either real-time or non-realtime */
- if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
- error = -EINVAL;
- goto out_unlock;
- }
-
- error = xfs_qm_dqattach(ip);
- if (error)
- goto out_unlock;
-
- error = xfs_qm_dqattach(tip);
- if (error)
- goto out_unlock;
-
- error = xfs_swap_extent_flush(ip);
- if (error)
- goto out_unlock;
- error = xfs_swap_extent_flush(tip);
- if (error)
- goto out_unlock;
-
- if (xfs_inode_has_cow_data(tip)) {
- error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true);
- if (error)
- goto out_unlock;
- }
-
- /*
- * Extent "swapping" with rmap requires a permanent reservation and
- * a block reservation because it's really just a remap operation
- * performed with log redo items!
- */
- if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
- int w = XFS_DATA_FORK;
- uint32_t ipnext = XFS_IFORK_NEXTENTS(ip, w);
- uint32_t tipnext = XFS_IFORK_NEXTENTS(tip, w);
-
- /*
- * Conceptually this shouldn't affect the shape of either bmbt,
- * but since we atomically move extents one by one, we reserve
- * enough space to rebuild both trees.
- */
- resblks = XFS_SWAP_RMAP_SPACE_RES(mp, ipnext, w);
- resblks += XFS_SWAP_RMAP_SPACE_RES(mp, tipnext, w);
-
- /*
- * Handle the corner case where either inode might straddle the
- * btree format boundary. If so, the inode could bounce between
- * btree <-> extent format on unmap -> remap cycles, freeing and
- * allocating a bmapbt block each time.
- */
- if (ipnext == (XFS_IFORK_MAXEXT(ip, w) + 1))
- resblks += XFS_IFORK_MAXEXT(ip, w);
- if (tipnext == (XFS_IFORK_MAXEXT(tip, w) + 1))
- resblks += XFS_IFORK_MAXEXT(tip, w);
- }
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
- if (error)
- goto out_unlock;
-
- /*
- * Lock and join the inodes to the tansaction so that transaction commit
- * or cancel will unlock the inodes from this point onwards.
- */
- xfs_lock_two_inodes(ip, XFS_ILOCK_EXCL, tip, XFS_ILOCK_EXCL);
- lock_flags |= XFS_ILOCK_EXCL;
- xfs_trans_ijoin(tp, ip, 0);
- xfs_trans_ijoin(tp, tip, 0);
-
-
- /* Verify all data are being swapped */
- if (sxp->sx_offset != 0 ||
- sxp->sx_length != ip->i_d.di_size ||
- sxp->sx_length != tip->i_d.di_size) {
- error = -EFAULT;
- goto out_trans_cancel;
- }
-
- trace_xfs_swap_extent_before(ip, 0);
- trace_xfs_swap_extent_before(tip, 1);
-
- /* check inode formats now that data is flushed */
- error = xfs_swap_extents_check_format(ip, tip);
- if (error) {
- xfs_notice(mp,
- "%s: inode 0x%llx format is incompatible for exchanging.",
- __func__, ip->i_ino);
- goto out_trans_cancel;
- }
-
- /*
- * Compare the current change & modify times with that
- * passed in. If they differ, we abort this swap.
- * This is the mechanism used to ensure the calling
- * process that the file was not changed out from
- * under it.
- */
- if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
- (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
- (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
- (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
- error = -EBUSY;
- goto out_trans_cancel;
- }
-
- /*
- * Note the trickiness in setting the log flags - we set the owner log
- * flag on the opposite inode (i.e. the inode we are setting the new
- * owner to be) because once we swap the forks and log that, log
- * recovery is going to see the fork as owned by the swapped inode,
- * not the pre-swapped inodes.
- */
- if (xfs_sb_version_hasrmapbt(&mp->m_sb))
- error = xfs_swapext_deferred_bmap(&tp, ip, tip, XFS_DATA_FORK,
- 0, 0, XFS_B_TO_FSB(ip->i_mount,
- i_size_read(VFS_I(ip))), 0);
- else
- error = xfs_swap_extent_forks(&tp, ip, tip);
- if (error) {
- trace_xfs_swap_extent_error(ip, error, _THIS_IP_);
- goto out_trans_cancel;
- }
-
- /*
- * If this is a synchronous mount, make sure that the
- * transaction goes to disk before returning to the user.
- */
- if (mp->m_flags & XFS_MOUNT_WSYNC)
- xfs_trans_set_sync(tp);
-
- error = xfs_trans_commit(tp);
-
- trace_xfs_swap_extent_after(ip, 0);
- trace_xfs_swap_extent_after(tip, 1);
-
-out_unlock:
- xfs_iunlock(ip, lock_flags);
- xfs_iunlock(tip, lock_flags);
- unlock_two_nondirectories(VFS_I(ip), VFS_I(tip));
- return error;
-
-out_trans_cancel:
- xfs_trans_cancel(tp);
- goto out_unlock;
-}
-
/* Prepare two files to have their data swapped. */
int
xfs_swap_range_prep(
@@ -2061,4 +1869,3 @@ xfs_swap_range(
xfs_trans_cancel(tp);
goto out_unlock;
}
-
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index d3444a63bbd7..e0712c274dd2 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -66,8 +66,6 @@ int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset,
bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
int xfs_free_eofblocks(struct xfs_inode *ip);
-int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
- struct xfs_swapext *sx);
int xfs_swap_range_prep(struct file *file1, struct file *file2,
struct file_swap_range *fsr);
int xfs_swap_range(struct xfs_inode *ip1, struct xfs_inode *ip2,
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 274423ba3bb5..f93de4f7a944 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1864,81 +1864,47 @@ xfs_ioc_scrub_metadata(
int
xfs_ioc_swapext(
- xfs_swapext_t *sxp)
+ struct xfs_swapext __user *arg)
{
- xfs_inode_t *ip, *tip;
- struct fd f, tmp;
- int error = 0;
+ struct xfs_swapext sx;
+ struct file_swap_range fsr = { 0 };
+ struct fd fd2, fd1;
+ int error = 0;
- /* Pull information for the target fd */
- f = fdget((int)sxp->sx_fdtarget);
- if (!f.file) {
- error = -EINVAL;
- goto out;
- }
+ if (copy_from_user(&sx, arg, sizeof(struct xfs_swapext)))
+ return -EFAULT;
- if (!(f.file->f_mode & FMODE_WRITE) ||
- !(f.file->f_mode & FMODE_READ) ||
- (f.file->f_flags & O_APPEND)) {
- error = -EBADF;
- goto out_put_file;
- }
+ fd2 = fdget((int)sx.sx_fdtarget);
+ if (!fd2.file)
+ return -EINVAL;
- tmp = fdget((int)sxp->sx_fdtmp);
- if (!tmp.file) {
+ fd1 = fdget((int)sx.sx_fdtmp);
+ if (!fd1.file) {
error = -EINVAL;
- goto out_put_file;
+ goto dest_fdput;
}
- if (!(tmp.file->f_mode & FMODE_WRITE) ||
- !(tmp.file->f_mode & FMODE_READ) ||
- (tmp.file->f_flags & O_APPEND)) {
- error = -EBADF;
- goto out_put_tmp_file;
- }
+ fsr.file1_fd = sx.sx_fdtmp;
+ fsr.length = sx.sx_length;
+ fsr.flags = FILE_SWAP_RANGE_NONATOMIC | FILE_SWAP_RANGE_FILE2_FRESH |
+ FILE_SWAP_RANGE_FULL_FILES;
+ fsr.file2_ino = sx.sx_stat.bs_ino;
+ fsr.file2_mtime = sx.sx_stat.bs_mtime.tv_sec;
+ fsr.file2_ctime = sx.sx_stat.bs_ctime.tv_sec;
+ fsr.file2_mtime_nsec = sx.sx_stat.bs_mtime.tv_nsec;
+ fsr.file2_ctime_nsec = sx.sx_stat.bs_ctime.tv_nsec;
- if (IS_SWAPFILE(file_inode(f.file)) ||
- IS_SWAPFILE(file_inode(tmp.file))) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
+ error = vfs_swap_file_range(fd1.file, fd2.file, &fsr);
/*
- * We need to ensure that the fds passed in point to XFS inodes
- * before we cast and access them as XFS structures as we have no
- * control over what the user passes us here.
+ * The old implementation returned EFAULT if the swap range was not
+ * the entirety of both files.
*/
- if (f.file->f_op != &xfs_file_operations ||
- tmp.file->f_op != &xfs_file_operations) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
-
- ip = XFS_I(file_inode(f.file));
- tip = XFS_I(file_inode(tmp.file));
-
- if (ip->i_mount != tip->i_mount) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
-
- if (ip->i_ino == tip->i_ino) {
- error = -EINVAL;
- goto out_put_tmp_file;
- }
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- error = -EIO;
- goto out_put_tmp_file;
- }
-
- error = xfs_swap_extents(ip, tip, sxp);
-
- out_put_tmp_file:
- fdput(tmp);
- out_put_file:
- fdput(f);
- out:
+ if (error == -EDOM)
+ error = -EFAULT;
+ fdput(fd1);
+dest_fdput:
+ fdput(fd2);
return error;
}
@@ -2183,18 +2149,8 @@ xfs_file_ioctl(
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(filp, arg);
- case XFS_IOC_SWAPEXT: {
- struct xfs_swapext sxp;
-
- if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
- return -EFAULT;
- error = mnt_want_write_file(filp);
- if (error)
- return error;
- error = xfs_ioc_swapext(&sxp);
- mnt_drop_write_file(filp);
- return error;
- }
+ case XFS_IOC_SWAPEXT:
+ return xfs_ioc_swapext(arg);
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
next prev parent reply other threads:[~2020-04-29 2:46 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-29 2:44 [PATCH RFC 00/18] xfs: atomic file updates Darrick J. Wong
2020-04-29 2:44 ` [PATCH 01/18] xfs: clean up the error handling in xfs_swap_extent_rmap Darrick J. Wong
2020-04-29 2:44 ` [PATCH 02/18] xfs: fix xfs_reflink_remap_prep calling conventions Darrick J. Wong
2020-05-01 22:54 ` Allison Collins
2020-04-29 2:44 ` [PATCH 03/18] vfs: introduce new file extent swap ioctl Darrick J. Wong
2020-04-29 2:44 ` [PATCH 04/18] xfs: support deferred bmap updates on the attr fork Darrick J. Wong
2020-04-29 2:44 ` [PATCH 05/18] xfs: xfs_bmap_finish_one should map unwritten extents properly Darrick J. Wong
2020-04-29 2:44 ` [PATCH 06/18] xfs: create a log incompat flag for atomic extent swapping Darrick J. Wong
2020-04-29 2:45 ` [PATCH 07/18] xfs: allow deferred ops items to put themselves at the end of the pending queue Darrick J. Wong
2020-04-29 2:45 ` [PATCH 08/18] xfs: introduce a swap-extent log intent item Darrick J. Wong
2020-04-29 2:45 ` [PATCH 09/18] xfs: create deferred log items for extent swapping Darrick J. Wong
2020-04-29 2:45 ` [PATCH 10/18] xfs: refactor locking and unlocking two inodes against userspace IO Darrick J. Wong
2020-04-29 2:45 ` [PATCH 11/18] xfs: add a ->swap_file_range handler Darrick J. Wong
2020-04-29 2:45 ` [PATCH 12/18] xfs: add error injection to test swapext recovery Darrick J. Wong
2020-04-29 2:45 ` [PATCH 13/18] xfs: allow xfs_swap_range to use older extent swap algorithms Darrick J. Wong
2020-04-29 2:45 ` [PATCH 14/18] xfs: port xfs_swap_extents_rmap to our new code Darrick J. Wong
2020-04-29 2:45 ` [PATCH 15/18] xfs: consolidate all of the xfs_swap_extent_forks code Darrick J. Wong
2020-04-29 2:45 ` [PATCH 16/18] xfs: refactor reflink flag handling in xfs_swap_extent_forks Darrick J. Wong
2020-04-29 2:46 ` Darrick J. Wong [this message]
2020-04-29 2:46 ` [PATCH 18/18] xfs: fix quota accounting in the old fork swap code Darrick J. Wong
2020-05-01 19:46 ` [PATCH RFC 00/18] xfs: atomic file updates Jann Horn
2020-05-01 20:11 ` Darrick J. Wong
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=158812836551.168506.6339048941371563780.stgit@magnolia \
--to=darrick.wong@oracle.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.