From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/fs/xfs/xfs_inode.c | 2063 ++++++++++++++++++++++++++++++++--------------------------
1 files changed, 1,138 insertions(+), 925 deletions(-)
diff --git a/kernel/fs/xfs/xfs_inode.c b/kernel/fs/xfs/xfs_inode.c
index cd81d6d..1900883 100644
--- a/kernel/fs/xfs/xfs_inode.c
+++ b/kernel/fs/xfs/xfs_inode.c
@@ -3,7 +3,6 @@
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
-#include <linux/log2.h>
#include <linux/iversion.h>
#include "xfs.h"
@@ -16,10 +15,7 @@
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
-#include "xfs_da_format.h"
-#include "xfs_da_btree.h"
#include "xfs_dir2.h"
-#include "xfs_attr_sf.h"
#include "xfs_attr.h"
#include "xfs_trans_space.h"
#include "xfs_trans.h"
@@ -32,7 +28,6 @@
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
-#include "xfs_cksum.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"
@@ -40,7 +35,6 @@
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"
-#include "xfs_dir2_priv.h"
kmem_zone_t *xfs_inode_zone;
@@ -50,7 +44,6 @@
*/
#define XFS_ITRUNC_MAX_EXTENTS 2
-STATIC int xfs_iflush_int(struct xfs_inode *, struct xfs_buf *);
STATIC int xfs_iunlink(struct xfs_trans *, struct xfs_inode *);
STATIC int xfs_iunlink_remove(struct xfs_trans *, struct xfs_inode *);
@@ -61,6 +54,12 @@
xfs_get_extsz_hint(
struct xfs_inode *ip)
{
+ /*
+ * No point in aligning allocations if we need to COW to actually
+ * write to them.
+ */
+ if (xfs_is_always_cow_inode(ip))
+ return 0;
if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
return ip->i_d.di_extsize;
if (XFS_IS_REALTIME_INODE(ip))
@@ -112,7 +111,7 @@
{
uint lock_mode = XFS_ILOCK_SHARED;
- if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+ if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE &&
(ip->i_df.if_flags & XFS_IFEXTENTS) == 0)
lock_mode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_mode);
@@ -125,7 +124,8 @@
{
uint lock_mode = XFS_ILOCK_SHARED;
- if (ip->i_d.di_aformat == XFS_DINODE_FMT_BTREE &&
+ if (ip->i_afp &&
+ ip->i_afp->if_format == XFS_DINODE_FMT_BTREE &&
(ip->i_afp->if_flags & XFS_IFEXTENTS) == 0)
lock_mode = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_mode);
@@ -144,17 +144,17 @@
*
* i_rwsem -> i_mmap_lock -> page_lock -> i_ilock
*
- * mmap_sem locking order:
+ * mmap_lock locking order:
*
- * i_rwsem -> page lock -> mmap_sem
- * mmap_sem -> i_mmap_lock -> page_lock
+ * i_rwsem -> page lock -> mmap_lock
+ * mmap_lock -> i_mmap_lock -> page_lock
*
- * The difference in mmap_sem locking order mean that we cannot hold the
+ * The difference in mmap_lock locking order mean that we cannot hold the
* i_mmap_lock over syscall based read(2)/write(2) based IO. These IO paths can
- * fault in pages during copy in/out (for buffered IO) or require the mmap_sem
+ * fault in pages during copy in/out (for buffered IO) or require the mmap_lock
* in get_user_pages() to map the user pages into the kernel address space for
* direct IO. Similarly the i_rwsem cannot be taken inside a page fault because
- * page faults already hold the mmap_sem.
+ * page faults already hold the mmap_lock.
*
* Hence to serialise fully against both syscall and mmap based IO, we need to
* take both the i_rwsem and the i_mmap_lock. These locks should *only* be both
@@ -441,17 +441,17 @@
*/
static void
xfs_lock_inodes(
- xfs_inode_t **ips,
- int inodes,
- uint lock_mode)
+ struct xfs_inode **ips,
+ int inodes,
+ uint lock_mode)
{
- int attempts = 0, i, j, try_lock;
- xfs_log_item_t *lp;
+ int attempts = 0, i, j, try_lock;
+ struct xfs_log_item *lp;
/*
* Currently supports between 2 and 5 inodes with exclusive locking. We
* support an arbitrary depth of locking here, but absolute limits on
- * inodes depend on the the type of locking and the limits placed by
+ * inodes depend on the type of locking and the limits placed by
* lockdep annotations in xfs_lock_inumorder. These are all checked by
* the asserts.
*/
@@ -485,7 +485,7 @@
*/
if (!try_lock) {
for (j = (i - 1); j >= 0 && !try_lock; j--) {
- lp = (xfs_log_item_t *)ips[j]->i_itemp;
+ lp = &ips[j]->i_itemp->ili_item;
if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags))
try_lock++;
}
@@ -551,7 +551,7 @@
struct xfs_inode *temp;
uint mode_temp;
int attempts = 0;
- xfs_log_item_t *lp;
+ struct xfs_log_item *lp;
ASSERT(hweight32(ip0_mode) == 1);
ASSERT(hweight32(ip1_mode) == 1);
@@ -585,7 +585,7 @@
* the second lock. If we can't get it, we must release the first one
* and try again.
*/
- lp = (xfs_log_item_t *)ip0->i_itemp;
+ lp = &ip0->i_itemp->ili_item;
if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) {
if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) {
xfs_iunlock(ip0, ip0_mode);
@@ -596,22 +596,6 @@
} else {
xfs_ilock(ip1, xfs_lock_inumorder(ip1_mode, 1));
}
-}
-
-void
-__xfs_iflock(
- struct xfs_inode *ip)
-{
- wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
- DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
-
- do {
- prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- if (xfs_isiflocked(ip))
- io_schedule();
- } while (!xfs_iflock_nowait(ip));
-
- finish_wait(wq, &wait.wq_entry);
}
STATIC uint
@@ -714,6 +698,68 @@
return error;
}
+/* Propagate di_flags from a parent inode to a child inode. */
+static void
+xfs_inode_inherit_flags(
+ struct xfs_inode *ip,
+ const struct xfs_inode *pip)
+{
+ unsigned int di_flags = 0;
+ umode_t mode = VFS_I(ip)->i_mode;
+
+ if (S_ISDIR(mode)) {
+ if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
+ di_flags |= XFS_DIFLAG_RTINHERIT;
+ if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+ di_flags |= XFS_DIFLAG_EXTSZINHERIT;
+ ip->i_d.di_extsize = pip->i_d.di_extsize;
+ }
+ if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+ di_flags |= XFS_DIFLAG_PROJINHERIT;
+ } else if (S_ISREG(mode)) {
+ if ((pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) &&
+ xfs_sb_version_hasrealtime(&ip->i_mount->m_sb))
+ di_flags |= XFS_DIFLAG_REALTIME;
+ if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+ di_flags |= XFS_DIFLAG_EXTSIZE;
+ ip->i_d.di_extsize = pip->i_d.di_extsize;
+ }
+ }
+ if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
+ xfs_inherit_noatime)
+ di_flags |= XFS_DIFLAG_NOATIME;
+ if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
+ xfs_inherit_nodump)
+ di_flags |= XFS_DIFLAG_NODUMP;
+ if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
+ xfs_inherit_sync)
+ di_flags |= XFS_DIFLAG_SYNC;
+ if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
+ xfs_inherit_nosymlinks)
+ di_flags |= XFS_DIFLAG_NOSYMLINKS;
+ if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
+ xfs_inherit_nodefrag)
+ di_flags |= XFS_DIFLAG_NODEFRAG;
+ if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
+ di_flags |= XFS_DIFLAG_FILESTREAM;
+
+ ip->i_d.di_flags |= di_flags;
+}
+
+/* Propagate di_flags2 from a parent inode to a child inode. */
+static void
+xfs_inode_inherit_flags2(
+ struct xfs_inode *ip,
+ const struct xfs_inode *pip)
+{
+ if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
+ ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+ ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
+ }
+ if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+ ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
+}
+
/*
* Allocate an inode on disk and return a copy of its in-core version.
* The in-core inode is locked exclusively. Set mode, nlink, and rdev
@@ -756,6 +802,7 @@
xfs_buf_t **ialloc_context,
xfs_inode_t **ipp)
{
+ struct inode *dir = pip ? VFS_I(pip) : NULL;
struct xfs_mount *mp = tp->t_mountp;
xfs_ino_t ino;
xfs_inode_t *ip;
@@ -801,26 +848,17 @@
return error;
ASSERT(ip != NULL);
inode = VFS_I(ip);
-
- /*
- * We always convert v1 inodes to v2 now - we only support filesystems
- * with >= v2 inode capability, so there is no reason for ever leaving
- * an inode in v1 format.
- */
- if (ip->i_d.di_version == 1)
- ip->i_d.di_version = 2;
-
- inode->i_mode = mode;
set_nlink(inode, nlink);
- ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
- ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
inode->i_rdev = rdev;
- xfs_set_projid(ip, prid);
+ ip->i_d.di_projid = prid;
- if (pip && XFS_INHERIT_GID(pip)) {
- ip->i_d.di_gid = pip->i_d.di_gid;
- if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
- inode->i_mode |= S_ISGID;
+ if (dir && !(dir->i_mode & S_ISGID) &&
+ (mp->m_flags & XFS_MOUNT_GRPID)) {
+ inode->i_uid = current_fsuid();
+ inode->i_gid = dir->i_gid;
+ inode->i_mode = mode;
+ } else {
+ inode_init_owner(inode, dir, mode);
}
/*
@@ -828,13 +866,12 @@
* ID or one of the supplementary group IDs, the S_ISGID bit is cleared
* (and only if the irix_sgid_inherit compatibility variable is set).
*/
- if ((irix_sgid_inherit) &&
- (inode->i_mode & S_ISGID) &&
- (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid))))
+ if (irix_sgid_inherit &&
+ (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid))
inode->i_mode &= ~S_ISGID;
ip->i_d.di_size = 0;
- ip->i_d.di_nextents = 0;
+ ip->i_df.if_nextents = 0;
ASSERT(ip->i_d.di_nblocks == 0);
tv = current_time(inode);
@@ -847,14 +884,12 @@
ip->i_d.di_dmstate = 0;
ip->i_d.di_flags = 0;
- if (ip->i_d.di_version == 3) {
+ if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
inode_set_iversion(inode, 1);
- ip->i_d.di_flags2 = 0;
+ ip->i_d.di_flags2 = mp->m_ino_geo.new_diflags2;
ip->i_d.di_cowextsize = 0;
- ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec;
- ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec;
+ ip->i_d.di_crtime = tv;
}
-
flags = XFS_ILOG_CORE;
switch (mode & S_IFMT) {
@@ -862,70 +897,19 @@
case S_IFCHR:
case S_IFBLK:
case S_IFSOCK:
- ip->i_d.di_format = XFS_DINODE_FMT_DEV;
+ ip->i_df.if_format = XFS_DINODE_FMT_DEV;
ip->i_df.if_flags = 0;
flags |= XFS_ILOG_DEV;
break;
case S_IFREG:
case S_IFDIR:
- if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
- uint di_flags = 0;
-
- if (S_ISDIR(mode)) {
- if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
- di_flags |= XFS_DIFLAG_RTINHERIT;
- if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
- di_flags |= XFS_DIFLAG_EXTSZINHERIT;
- ip->i_d.di_extsize = pip->i_d.di_extsize;
- }
- if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
- di_flags |= XFS_DIFLAG_PROJINHERIT;
- } else if (S_ISREG(mode)) {
- if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
- di_flags |= XFS_DIFLAG_REALTIME;
- if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
- di_flags |= XFS_DIFLAG_EXTSIZE;
- ip->i_d.di_extsize = pip->i_d.di_extsize;
- }
- }
- if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
- xfs_inherit_noatime)
- di_flags |= XFS_DIFLAG_NOATIME;
- if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
- xfs_inherit_nodump)
- di_flags |= XFS_DIFLAG_NODUMP;
- if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
- xfs_inherit_sync)
- di_flags |= XFS_DIFLAG_SYNC;
- if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
- xfs_inherit_nosymlinks)
- di_flags |= XFS_DIFLAG_NOSYMLINKS;
- if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
- xfs_inherit_nodefrag)
- di_flags |= XFS_DIFLAG_NODEFRAG;
- if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
- di_flags |= XFS_DIFLAG_FILESTREAM;
-
- ip->i_d.di_flags |= di_flags;
- }
- if (pip &&
- (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
- pip->i_d.di_version == 3 &&
- ip->i_d.di_version == 3) {
- uint64_t di_flags2 = 0;
-
- if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
- di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
- ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
- }
- if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
- di_flags2 |= XFS_DIFLAG2_DAX;
-
- ip->i_d.di_flags2 |= di_flags2;
- }
+ if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY))
+ xfs_inode_inherit_flags(ip, pip);
+ if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY))
+ xfs_inode_inherit_flags2(ip, pip);
/* FALLTHROUGH */
case S_IFLNK:
- ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
+ ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
ip->i_df.if_flags = XFS_IFEXTENTS;
ip->i_df.if_bytes = 0;
ip->i_df.if_u1.if_root = NULL;
@@ -933,11 +917,6 @@
default:
ASSERT(0);
}
- /*
- * Attribute fork settings for new inode.
- */
- ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
- ip->i_d.di_anextents = 0;
/*
* Log the new values stuffed into the inode.
@@ -1116,17 +1095,15 @@
/*
* Increment the link count on an inode & log the change.
*/
-static int
+static void
xfs_bumplink(
xfs_trans_t *tp,
xfs_inode_t *ip)
{
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
- ASSERT(ip->i_d.di_version > 1);
inc_nlink(VFS_I(ip));
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- return 0;
}
int
@@ -1160,8 +1137,7 @@
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()),
- xfs_kgid_to_gid(current_fsgid()), prid,
+ error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
if (error)
@@ -1221,8 +1197,7 @@
unlock_dp_on_error = false;
error = xfs_dir_createname(tp, dp, name, ip->i_ino,
- resblks ?
- resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
+ resblks - XFS_IALLOC_SPACE_RES(mp));
if (error) {
ASSERT(error != -ENOSPC);
goto out_trans_cancel;
@@ -1235,9 +1210,7 @@
if (error)
goto out_trans_cancel;
- error = xfs_bumplink(tp, dp);
- if (error)
- goto out_trans_cancel;
+ xfs_bumplink(tp, dp);
}
/*
@@ -1313,8 +1286,7 @@
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()),
- xfs_kgid_to_gid(current_fsgid()), prid,
+ error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
if (error)
@@ -1427,7 +1399,7 @@
* the tree quota mechanism could be circumvented.
*/
if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
- (xfs_get_projid(tdp) != xfs_get_projid(sip)))) {
+ tdp->i_d.di_projid != sip->i_d.di_projid)) {
error = -EXDEV;
goto error_return;
}
@@ -1454,9 +1426,7 @@
xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
- error = xfs_bumplink(tp, sip);
- if (error)
- goto error_return;
+ xfs_bumplink(tp, sip);
/*
* If this is a synchronous mount, make sure that the
@@ -1524,10 +1494,8 @@
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp = *tpp;
xfs_fileoff_t first_unmap_block;
- xfs_fileoff_t last_block;
xfs_filblks_t unmap_len;
int error = 0;
- int done = 0;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
@@ -1547,33 +1515,27 @@
* the end of the file (in a crash where the space is allocated
* but the inode size is not yet updated), simply remove any
* blocks which show up between the new EOF and the maximum
- * possible file size. If the first block to be removed is
- * beyond the maximum file size (ie it is the same as last_block),
- * then there is nothing to do.
+ * possible file size.
+ *
+ * We have to free all the blocks to the bmbt maximum offset, even if
+ * the page cache can't scale that far.
*/
first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
- last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
- if (first_unmap_block == last_block)
+ if (first_unmap_block >= XFS_MAX_FILEOFF) {
+ WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
return 0;
+ }
- ASSERT(first_unmap_block < last_block);
- unmap_len = last_block - first_unmap_block + 1;
- while (!done) {
+ unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
+ while (unmap_len > 0) {
ASSERT(tp->t_firstblock == NULLFSBLOCK);
- error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
- XFS_ITRUNC_MAX_EXTENTS, &done);
+ error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
+ flags, XFS_ITRUNC_MAX_EXTENTS);
if (error)
goto out;
- /*
- * Duplicate the transaction that has the permanent
- * reservation and commit the old transaction.
- */
+ /* free the just unmapped extents */
error = xfs_defer_finish(&tp);
- if (error)
- goto out;
-
- error = xfs_trans_roll_inode(&tp, ip);
if (error)
goto out;
}
@@ -1581,7 +1543,7 @@
if (whichfork == XFS_DATA_FORK) {
/* Remove all pending CoW reservations. */
error = xfs_reflink_cancel_cow_blocks(ip, &tp,
- first_unmap_block, last_block, true);
+ first_unmap_block, XFS_MAX_FILEOFF, true);
if (error)
goto out;
@@ -1662,7 +1624,7 @@
return 0;
/*
* If we can't get the iolock just skip truncating the blocks
- * past EOF because we could deadlock with the mmap_sem
+ * past EOF because we could deadlock with the mmap_lock
* otherwise. We'll get another chance to drop them once the
* last reference to the inode is dropped, so we'll never leak
* blocks permanently.
@@ -1714,7 +1676,7 @@
if (error)
goto error_trans_cancel;
- ASSERT(ip->i_d.di_nextents == 0);
+ ASSERT(ip->i_df.if_nextents == 0);
error = xfs_trans_commit(tp);
if (error)
@@ -1883,7 +1845,7 @@
if (S_ISREG(VFS_I(ip)->i_mode) &&
(ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
- ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
+ ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0))
truncate = 1;
error = xfs_qm_dqattach(ip);
@@ -1909,7 +1871,6 @@
}
ASSERT(!ip->i_afp);
- ASSERT(ip->i_d.di_anextents == 0);
ASSERT(ip->i_d.di_forkoff == 0);
/*
@@ -1926,6 +1887,336 @@
}
/*
+ * In-Core Unlinked List Lookups
+ * =============================
+ *
+ * Every inode is supposed to be reachable from some other piece of metadata
+ * with the exception of the root directory. Inodes with a connection to a
+ * file descriptor but not linked from anywhere in the on-disk directory tree
+ * are collectively known as unlinked inodes, though the filesystem itself
+ * maintains links to these inodes so that on-disk metadata are consistent.
+ *
+ * XFS implements a per-AG on-disk hash table of unlinked inodes. The AGI
+ * header contains a number of buckets that point to an inode, and each inode
+ * record has a pointer to the next inode in the hash chain. This
+ * singly-linked list causes scaling problems in the iunlink remove function
+ * because we must walk that list to find the inode that points to the inode
+ * being removed from the unlinked hash bucket list.
+ *
+ * What if we modelled the unlinked list as a collection of records capturing
+ * "X.next_unlinked = Y" relations? If we indexed those records on Y, we'd
+ * have a fast way to look up unlinked list predecessors, which avoids the
+ * slow list walk. That's exactly what we do here (in-core) with a per-AG
+ * rhashtable.
+ *
+ * Because this is a backref cache, we ignore operational failures since the
+ * iunlink code can fall back to the slow bucket walk. The only errors that
+ * should bubble out are for obviously incorrect situations.
+ *
+ * All users of the backref cache MUST hold the AGI buffer lock to serialize
+ * access or have otherwise provided for concurrency control.
+ */
+
+/* Capture a "X.next_unlinked = Y" relationship. */
+struct xfs_iunlink {
+ struct rhash_head iu_rhash_head;
+ xfs_agino_t iu_agino; /* X */
+ xfs_agino_t iu_next_unlinked; /* Y */
+};
+
+/* Unlinked list predecessor lookup hashtable construction */
+static int
+xfs_iunlink_obj_cmpfn(
+ struct rhashtable_compare_arg *arg,
+ const void *obj)
+{
+ const xfs_agino_t *key = arg->key;
+ const struct xfs_iunlink *iu = obj;
+
+ if (iu->iu_next_unlinked != *key)
+ return 1;
+ return 0;
+}
+
+static const struct rhashtable_params xfs_iunlink_hash_params = {
+ .min_size = XFS_AGI_UNLINKED_BUCKETS,
+ .key_len = sizeof(xfs_agino_t),
+ .key_offset = offsetof(struct xfs_iunlink,
+ iu_next_unlinked),
+ .head_offset = offsetof(struct xfs_iunlink, iu_rhash_head),
+ .automatic_shrinking = true,
+ .obj_cmpfn = xfs_iunlink_obj_cmpfn,
+};
+
+/*
+ * Return X, where X.next_unlinked == @agino. Returns NULLAGINO if no such
+ * relation is found.
+ */
+static xfs_agino_t
+xfs_iunlink_lookup_backref(
+ struct xfs_perag *pag,
+ xfs_agino_t agino)
+{
+ struct xfs_iunlink *iu;
+
+ iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino,
+ xfs_iunlink_hash_params);
+ return iu ? iu->iu_agino : NULLAGINO;
+}
+
+/*
+ * Take ownership of an iunlink cache entry and insert it into the hash table.
+ * If successful, the entry will be owned by the cache; if not, it is freed.
+ * Either way, the caller does not own @iu after this call.
+ */
+static int
+xfs_iunlink_insert_backref(
+ struct xfs_perag *pag,
+ struct xfs_iunlink *iu)
+{
+ int error;
+
+ error = rhashtable_insert_fast(&pag->pagi_unlinked_hash,
+ &iu->iu_rhash_head, xfs_iunlink_hash_params);
+ /*
+ * Fail loudly if there already was an entry because that's a sign of
+ * corruption of in-memory data. Also fail loudly if we see an error
+ * code we didn't anticipate from the rhashtable code. Currently we
+ * only anticipate ENOMEM.
+ */
+ if (error) {
+ WARN(error != -ENOMEM, "iunlink cache insert error %d", error);
+ kmem_free(iu);
+ }
+ /*
+ * Absorb any runtime errors that aren't a result of corruption because
+ * this is a cache and we can always fall back to bucket list scanning.
+ */
+ if (error != 0 && error != -EEXIST)
+ error = 0;
+ return error;
+}
+
+/* Remember that @prev_agino.next_unlinked = @this_agino. */
+static int
+xfs_iunlink_add_backref(
+ struct xfs_perag *pag,
+ xfs_agino_t prev_agino,
+ xfs_agino_t this_agino)
+{
+ struct xfs_iunlink *iu;
+
+ if (XFS_TEST_ERROR(false, pag->pag_mount, XFS_ERRTAG_IUNLINK_FALLBACK))
+ return 0;
+
+ iu = kmem_zalloc(sizeof(*iu), KM_NOFS);
+ iu->iu_agino = prev_agino;
+ iu->iu_next_unlinked = this_agino;
+
+ return xfs_iunlink_insert_backref(pag, iu);
+}
+
+/*
+ * Replace X.next_unlinked = @agino with X.next_unlinked = @next_unlinked.
+ * If @next_unlinked is NULLAGINO, we drop the backref and exit. If there
+ * wasn't any such entry then we don't bother.
+ */
+static int
+xfs_iunlink_change_backref(
+ struct xfs_perag *pag,
+ xfs_agino_t agino,
+ xfs_agino_t next_unlinked)
+{
+ struct xfs_iunlink *iu;
+ int error;
+
+ /* Look up the old entry; if there wasn't one then exit. */
+ iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino,
+ xfs_iunlink_hash_params);
+ if (!iu)
+ return 0;
+
+ /*
+ * Remove the entry. This shouldn't ever return an error, but if we
+ * couldn't remove the old entry we don't want to add it again to the
+ * hash table, and if the entry disappeared on us then someone's
+ * violated the locking rules and we need to fail loudly. Either way
+ * we cannot remove the inode because internal state is or would have
+ * been corrupt.
+ */
+ error = rhashtable_remove_fast(&pag->pagi_unlinked_hash,
+ &iu->iu_rhash_head, xfs_iunlink_hash_params);
+ if (error)
+ return error;
+
+ /* If there is no new next entry just free our item and return. */
+ if (next_unlinked == NULLAGINO) {
+ kmem_free(iu);
+ return 0;
+ }
+
+ /* Update the entry and re-add it to the hash table. */
+ iu->iu_next_unlinked = next_unlinked;
+ return xfs_iunlink_insert_backref(pag, iu);
+}
+
+/* Set up the in-core predecessor structures. */
+int
+xfs_iunlink_init(
+ struct xfs_perag *pag)
+{
+ return rhashtable_init(&pag->pagi_unlinked_hash,
+ &xfs_iunlink_hash_params);
+}
+
+/* Free the in-core predecessor structures. */
+static void
+xfs_iunlink_free_item(
+ void *ptr,
+ void *arg)
+{
+ struct xfs_iunlink *iu = ptr;
+ bool *freed_anything = arg;
+
+ *freed_anything = true;
+ kmem_free(iu);
+}
+
+void
+xfs_iunlink_destroy(
+ struct xfs_perag *pag)
+{
+ bool freed_anything = false;
+
+ rhashtable_free_and_destroy(&pag->pagi_unlinked_hash,
+ xfs_iunlink_free_item, &freed_anything);
+
+ ASSERT(freed_anything == false || XFS_FORCED_SHUTDOWN(pag->pag_mount));
+}
+
+/*
+ * Point the AGI unlinked bucket at an inode and log the results. The caller
+ * is responsible for validating the old value.
+ */
+STATIC int
+xfs_iunlink_update_bucket(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ struct xfs_buf *agibp,
+ unsigned int bucket_index,
+ xfs_agino_t new_agino)
+{
+ struct xfs_agi *agi = agibp->b_addr;
+ xfs_agino_t old_value;
+ int offset;
+
+ ASSERT(xfs_verify_agino_or_null(tp->t_mountp, agno, new_agino));
+
+ old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ trace_xfs_iunlink_update_bucket(tp->t_mountp, agno, bucket_index,
+ old_value, new_agino);
+
+ /*
+ * We should never find the head of the list already set to the value
+ * passed in because either we're adding or removing ourselves from the
+ * head of the list.
+ */
+ if (old_value == new_agino) {
+ xfs_buf_mark_corrupt(agibp);
+ return -EFSCORRUPTED;
+ }
+
+ agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
+ offset = offsetof(struct xfs_agi, agi_unlinked) +
+ (sizeof(xfs_agino_t) * bucket_index);
+ xfs_trans_log_buf(tp, agibp, offset, offset + sizeof(xfs_agino_t) - 1);
+ return 0;
+}
+
+/* Set an on-disk inode's next_unlinked pointer. */
+STATIC void
+xfs_iunlink_update_dinode(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ xfs_agino_t agino,
+ struct xfs_buf *ibp,
+ struct xfs_dinode *dip,
+ struct xfs_imap *imap,
+ xfs_agino_t next_agino)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ int offset;
+
+ ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));
+
+ trace_xfs_iunlink_update_dinode(mp, agno, agino,
+ be32_to_cpu(dip->di_next_unlinked), next_agino);
+
+ dip->di_next_unlinked = cpu_to_be32(next_agino);
+ offset = imap->im_boffset +
+ offsetof(struct xfs_dinode, di_next_unlinked);
+
+ /* need to recalc the inode CRC if appropriate */
+ xfs_dinode_calc_crc(mp, dip);
+ xfs_trans_inode_buf(tp, ibp);
+ xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1);
+}
+
+/* Set an in-core inode's unlinked pointer and return the old value. */
+STATIC int
+xfs_iunlink_update_inode(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ xfs_agnumber_t agno,
+ xfs_agino_t next_agino,
+ xfs_agino_t *old_next_agino)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_dinode *dip;
+ struct xfs_buf *ibp;
+ xfs_agino_t old_value;
+ int error;
+
+ ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));
+
+ error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, 0);
+ if (error)
+ return error;
+
+ /* Make sure the old pointer isn't garbage. */
+ old_value = be32_to_cpu(dip->di_next_unlinked);
+ if (!xfs_verify_agino_or_null(mp, agno, old_value)) {
+ xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
+ sizeof(*dip), __this_address);
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ /*
+ * Since we're updating a linked list, we should never find that the
+ * current pointer is the same as the new value, unless we're
+ * terminating the list.
+ */
+ *old_next_agino = old_value;
+ if (old_value == next_agino) {
+ if (next_agino != NULLAGINO) {
+ xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
+ dip, sizeof(*dip), __this_address);
+ error = -EFSCORRUPTED;
+ }
+ goto out;
+ }
+
+ /* Ok, update the new pointer. */
+ xfs_iunlink_update_dinode(tp, agno, XFS_INO_TO_AGINO(mp, ip->i_ino),
+ ibp, dip, &ip->i_imap, next_agino);
+ return 0;
+out:
+ xfs_trans_brelse(tp, ibp);
+ return error;
+}
+
+/*
* This is called when the inode's link count has gone to 0 or we are creating
* a tmpfile via O_TMPFILE. The inode @ip must have nlink == 0.
*
@@ -1934,76 +2225,177 @@
*/
STATIC int
xfs_iunlink(
- struct xfs_trans *tp,
- struct xfs_inode *ip)
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
{
- xfs_mount_t *mp = tp->t_mountp;
- xfs_agi_t *agi;
- xfs_dinode_t *dip;
- xfs_buf_t *agibp;
- xfs_buf_t *ibp;
- xfs_agino_t agino;
- short bucket_index;
- int offset;
- int error;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi;
+ struct xfs_buf *agibp;
+ xfs_agino_t next_agino;
+ xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
+ int error;
ASSERT(VFS_I(ip)->i_nlink == 0);
ASSERT(VFS_I(ip)->i_mode != 0);
+ trace_xfs_iunlink(ip);
- /*
- * Get the agi buffer first. It ensures lock ordering
- * on the list.
- */
- error = xfs_read_agi(mp, tp, XFS_INO_TO_AGNO(mp, ip->i_ino), &agibp);
+ /* Get the agi buffer first. It ensures lock ordering on the list. */
+ error = xfs_read_agi(mp, tp, agno, &agibp);
if (error)
return error;
- agi = XFS_BUF_TO_AGI(agibp);
+ agi = agibp->b_addr;
/*
- * Get the index into the agi hash table for the
- * list this inode will go on.
+ * Get the index into the agi hash table for the list this inode will
+ * go on. Make sure the pointer isn't garbage and that this inode
+ * isn't already on the list.
*/
- agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
- ASSERT(agino != 0);
- bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
- ASSERT(agi->agi_unlinked[bucket_index]);
- ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != agino);
+ next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ if (next_agino == agino ||
+ !xfs_verify_agino_or_null(mp, agno, next_agino)) {
+ xfs_buf_mark_corrupt(agibp);
+ return -EFSCORRUPTED;
+ }
- if (agi->agi_unlinked[bucket_index] != cpu_to_be32(NULLAGINO)) {
+ if (next_agino != NULLAGINO) {
+ xfs_agino_t old_agino;
+
/*
- * There is already another inode in the bucket we need
- * to add ourselves to. Add us at the front of the list.
- * Here we put the head pointer into our next pointer,
- * and then we fall through to point the head at us.
+ * There is already another inode in the bucket, so point this
+ * inode to the current head of the list.
*/
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
- 0, 0);
+ error = xfs_iunlink_update_inode(tp, ip, agno, next_agino,
+ &old_agino);
+ if (error)
+ return error;
+ ASSERT(old_agino == NULLAGINO);
+
+ /*
+ * agino has been unlinked, add a backref from the next inode
+ * back to agino.
+ */
+ error = xfs_iunlink_add_backref(agibp->b_pag, agino, next_agino);
+ if (error)
+ return error;
+ }
+
+ /* Point the head of the list to point to this inode. */
+ return xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index, agino);
+}
+
+/* Return the imap, dinode pointer, and buffer for an inode. */
+STATIC int
+xfs_iunlink_map_ino(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ xfs_agino_t agino,
+ struct xfs_imap *imap,
+ struct xfs_dinode **dipp,
+ struct xfs_buf **bpp)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ int error;
+
+ imap->im_blkno = 0;
+ error = xfs_imap(mp, tp, XFS_AGINO_TO_INO(mp, agno, agino), imap, 0);
+ if (error) {
+ xfs_warn(mp, "%s: xfs_imap returned error %d.",
+ __func__, error);
+ return error;
+ }
+
+ error = xfs_imap_to_bp(mp, tp, imap, dipp, bpp, 0);
+ if (error) {
+ xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
+ __func__, error);
+ return error;
+ }
+
+ return 0;
+}
+
+/*
+ * Walk the unlinked chain from @head_agino until we find the inode that
+ * points to @target_agino. Return the inode number, map, dinode pointer,
+ * and inode cluster buffer of that inode as @agino, @imap, @dipp, and @bpp.
+ *
+ * @tp, @pag, @head_agino, and @target_agino are input parameters.
+ * @agino, @imap, @dipp, and @bpp are all output parameters.
+ *
+ * Do not call this function if @target_agino is the head of the list.
+ */
+STATIC int
+xfs_iunlink_map_prev(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ xfs_agino_t head_agino,
+ xfs_agino_t target_agino,
+ xfs_agino_t *agino,
+ struct xfs_imap *imap,
+ struct xfs_dinode **dipp,
+ struct xfs_buf **bpp,
+ struct xfs_perag *pag)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ xfs_agino_t next_agino;
+ int error;
+
+ ASSERT(head_agino != target_agino);
+ *bpp = NULL;
+
+ /* See if our backref cache can find it faster. */
+ *agino = xfs_iunlink_lookup_backref(pag, target_agino);
+ if (*agino != NULLAGINO) {
+ error = xfs_iunlink_map_ino(tp, agno, *agino, imap, dipp, bpp);
if (error)
return error;
- ASSERT(dip->di_next_unlinked == cpu_to_be32(NULLAGINO));
- dip->di_next_unlinked = agi->agi_unlinked[bucket_index];
- offset = ip->i_imap.im_boffset +
- offsetof(xfs_dinode_t, di_next_unlinked);
+ if (be32_to_cpu((*dipp)->di_next_unlinked) == target_agino)
+ return 0;
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, dip);
-
- xfs_trans_inode_buf(tp, ibp);
- xfs_trans_log_buf(tp, ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, ibp);
+ /*
+ * If we get here the cache contents were corrupt, so drop the
+ * buffer and fall back to walking the bucket list.
+ */
+ xfs_trans_brelse(tp, *bpp);
+ *bpp = NULL;
+ WARN_ON_ONCE(1);
}
- /*
- * Point the bucket head pointer at the inode being inserted.
- */
- ASSERT(agino != 0);
- agi->agi_unlinked[bucket_index] = cpu_to_be32(agino);
- offset = offsetof(xfs_agi_t, agi_unlinked) +
- (sizeof(xfs_agino_t) * bucket_index);
- xfs_trans_log_buf(tp, agibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
+ trace_xfs_iunlink_map_prev_fallback(mp, agno);
+
+ /* Otherwise, walk the entire bucket until we find it. */
+ next_agino = head_agino;
+ while (next_agino != target_agino) {
+ xfs_agino_t unlinked_agino;
+
+ if (*bpp)
+ xfs_trans_brelse(tp, *bpp);
+
+ *agino = next_agino;
+ error = xfs_iunlink_map_ino(tp, agno, next_agino, imap, dipp,
+ bpp);
+ if (error)
+ return error;
+
+ unlinked_agino = be32_to_cpu((*dipp)->di_next_unlinked);
+ /*
+ * Make sure this pointer is valid and isn't an obvious
+ * infinite loop.
+ */
+ if (!xfs_verify_agino(mp, agno, unlinked_agino) ||
+ next_agino == unlinked_agino) {
+ XFS_CORRUPTION_ERROR(__func__,
+ XFS_ERRLEVEL_LOW, mp,
+ *dipp, sizeof(**dipp));
+ error = -EFSCORRUPTED;
+ return error;
+ }
+ next_agino = unlinked_agino;
+ }
+
return 0;
}
@@ -2012,181 +2404,190 @@
*/
STATIC int
xfs_iunlink_remove(
- xfs_trans_t *tp,
- xfs_inode_t *ip)
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
{
- xfs_ino_t next_ino;
- xfs_mount_t *mp;
- xfs_agi_t *agi;
- xfs_dinode_t *dip;
- xfs_buf_t *agibp;
- xfs_buf_t *ibp;
- xfs_agnumber_t agno;
- xfs_agino_t agino;
- xfs_agino_t next_agino;
- xfs_buf_t *last_ibp;
- xfs_dinode_t *last_dip = NULL;
- short bucket_index;
- int offset, last_offset = 0;
- int error;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi;
+ struct xfs_buf *agibp;
+ struct xfs_buf *last_ibp;
+ struct xfs_dinode *last_dip = NULL;
+ xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ xfs_agino_t next_agino;
+ xfs_agino_t head_agino;
+ short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
+ int error;
- mp = tp->t_mountp;
- agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+ trace_xfs_iunlink_remove(ip);
- /*
- * Get the agi buffer first. It ensures lock ordering
- * on the list.
- */
+ /* Get the agi buffer first. It ensures lock ordering on the list. */
error = xfs_read_agi(mp, tp, agno, &agibp);
if (error)
return error;
-
- agi = XFS_BUF_TO_AGI(agibp);
+ agi = agibp->b_addr;
/*
- * Get the index into the agi hash table for the
- * list this inode will go on.
+ * Get the index into the agi hash table for the list this inode will
+ * go on. Make sure the head pointer isn't garbage.
*/
- agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
- if (!xfs_verify_agino(mp, agno, agino))
- return -EFSCORRUPTED;
- bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
- if (!xfs_verify_agino(mp, agno,
- be32_to_cpu(agi->agi_unlinked[bucket_index]))) {
+ head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ if (!xfs_verify_agino(mp, agno, head_agino)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
agi, sizeof(*agi));
return -EFSCORRUPTED;
}
- if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) {
- /*
- * We're at the head of the list. Get the inode's on-disk
- * buffer to see if there is anyone after us on the list.
- * Only modify our next pointer if it is not already NULLAGINO.
- * This saves us the overhead of dealing with the buffer when
- * there is no need to change it.
- */
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
- 0, 0);
- if (error) {
- xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
- __func__, error);
+ /*
+ * Set our inode's next_unlinked pointer to NULL and then return
+ * the old pointer value so that we can update whatever was previous
+ * to us in the list to point to whatever was next in the list.
+ */
+ error = xfs_iunlink_update_inode(tp, ip, agno, NULLAGINO, &next_agino);
+ if (error)
+ return error;
+
+ /*
+ * If there was a backref pointing from the next inode back to this
+ * one, remove it because we've removed this inode from the list.
+ *
+ * Later, if this inode was in the middle of the list we'll update
+ * this inode's backref to point from the next inode.
+ */
+ if (next_agino != NULLAGINO) {
+ error = xfs_iunlink_change_backref(agibp->b_pag, next_agino,
+ NULLAGINO);
+ if (error)
return error;
- }
- next_agino = be32_to_cpu(dip->di_next_unlinked);
- ASSERT(next_agino != 0);
- if (next_agino != NULLAGINO) {
- dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
- offset = ip->i_imap.im_boffset +
- offsetof(xfs_dinode_t, di_next_unlinked);
-
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, dip);
-
- xfs_trans_inode_buf(tp, ibp);
- xfs_trans_log_buf(tp, ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, ibp);
- } else {
- xfs_trans_brelse(tp, ibp);
- }
- /*
- * Point the bucket head pointer at the next inode.
- */
- ASSERT(next_agino != 0);
- ASSERT(next_agino != agino);
- agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino);
- offset = offsetof(xfs_agi_t, agi_unlinked) +
- (sizeof(xfs_agino_t) * bucket_index);
- xfs_trans_log_buf(tp, agibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- } else {
- /*
- * We need to search the list for the inode being freed.
- */
- next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
- last_ibp = NULL;
- while (next_agino != agino) {
- struct xfs_imap imap;
-
- if (last_ibp)
- xfs_trans_brelse(tp, last_ibp);
-
- imap.im_blkno = 0;
- next_ino = XFS_AGINO_TO_INO(mp, agno, next_agino);
-
- error = xfs_imap(mp, tp, next_ino, &imap, 0);
- if (error) {
- xfs_warn(mp,
- "%s: xfs_imap returned error %d.",
- __func__, error);
- return error;
- }
-
- error = xfs_imap_to_bp(mp, tp, &imap, &last_dip,
- &last_ibp, 0, 0);
- if (error) {
- xfs_warn(mp,
- "%s: xfs_imap_to_bp returned error %d.",
- __func__, error);
- return error;
- }
-
- last_offset = imap.im_boffset;
- next_agino = be32_to_cpu(last_dip->di_next_unlinked);
- if (!xfs_verify_agino(mp, agno, next_agino)) {
- XFS_CORRUPTION_ERROR(__func__,
- XFS_ERRLEVEL_LOW, mp,
- last_dip, sizeof(*last_dip));
- return -EFSCORRUPTED;
- }
- }
-
- /*
- * Now last_ibp points to the buffer previous to us on the
- * unlinked list. Pull us from the list.
- */
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
- 0, 0);
- if (error) {
- xfs_warn(mp, "%s: xfs_imap_to_bp(2) returned error %d.",
- __func__, error);
- return error;
- }
- next_agino = be32_to_cpu(dip->di_next_unlinked);
- ASSERT(next_agino != 0);
- ASSERT(next_agino != agino);
- if (next_agino != NULLAGINO) {
- dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
- offset = ip->i_imap.im_boffset +
- offsetof(xfs_dinode_t, di_next_unlinked);
-
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, dip);
-
- xfs_trans_inode_buf(tp, ibp);
- xfs_trans_log_buf(tp, ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, ibp);
- } else {
- xfs_trans_brelse(tp, ibp);
- }
- /*
- * Point the previous inode on the list to the next inode.
- */
- last_dip->di_next_unlinked = cpu_to_be32(next_agino);
- ASSERT(next_agino != 0);
- offset = last_offset + offsetof(xfs_dinode_t, di_next_unlinked);
-
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, last_dip);
-
- xfs_trans_inode_buf(tp, last_ibp);
- xfs_trans_log_buf(tp, last_ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, last_ibp);
}
- return 0;
+
+ if (head_agino != agino) {
+ struct xfs_imap imap;
+ xfs_agino_t prev_agino;
+
+ /* We need to search the list for the inode being freed. */
+ error = xfs_iunlink_map_prev(tp, agno, head_agino, agino,
+ &prev_agino, &imap, &last_dip, &last_ibp,
+ agibp->b_pag);
+ if (error)
+ return error;
+
+ /* Point the previous inode on the list to the next inode. */
+ xfs_iunlink_update_dinode(tp, agno, prev_agino, last_ibp,
+ last_dip, &imap, next_agino);
+
+ /*
+ * Now we deal with the backref for this inode. If this inode
+ * pointed at a real inode, change the backref that pointed to
+ * us to point to our old next. If this inode was the end of
+ * the list, delete the backref that pointed to us. Note that
+ * change_backref takes care of deleting the backref if
+ * next_agino is NULLAGINO.
+ */
+ return xfs_iunlink_change_backref(agibp->b_pag, agino,
+ next_agino);
+ }
+
+ /* Point the head of the list to the next unlinked inode. */
+ return xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index,
+ next_agino);
+}
+
+/*
+ * Look up the inode number specified and if it is not already marked XFS_ISTALE
+ * mark it stale. We should only find clean inodes in this lookup that aren't
+ * already stale.
+ */
+static void
+xfs_ifree_mark_inode_stale(
+ struct xfs_buf *bp,
+ struct xfs_inode *free_ip,
+ xfs_ino_t inum)
+{
+ struct xfs_mount *mp = bp->b_mount;
+ struct xfs_perag *pag = bp->b_pag;
+ struct xfs_inode_log_item *iip;
+ struct xfs_inode *ip;
+
+retry:
+ rcu_read_lock();
+ ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum));
+
+ /* Inode not in memory, nothing to do */
+ if (!ip) {
+ rcu_read_unlock();
+ return;
+ }
+
+ /*
+ * because this is an RCU protected lookup, we could find a recently
+ * freed or even reallocated inode during the lookup. We need to check
+ * under the i_flags_lock for a valid inode here. Skip it if it is not
+ * valid, the wrong inode or stale.
+ */
+ spin_lock(&ip->i_flags_lock);
+ if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE))
+ goto out_iflags_unlock;
+
+ /*
+ * Don't try to lock/unlock the current inode, but we _cannot_ skip the
+ * other inodes that we did not find in the list attached to the buffer
+ * and are not already marked stale. If we can't lock it, back off and
+ * retry.
+ */
+ if (ip != free_ip) {
+ if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+ spin_unlock(&ip->i_flags_lock);
+ rcu_read_unlock();
+ delay(1);
+ goto retry;
+ }
+ }
+ ip->i_flags |= XFS_ISTALE;
+
+ /*
+ * If the inode is flushing, it is already attached to the buffer. All
+ * we needed to do here is mark the inode stale so buffer IO completion
+ * will remove it from the AIL.
+ */
+ iip = ip->i_itemp;
+ if (__xfs_iflags_test(ip, XFS_IFLUSHING)) {
+ ASSERT(!list_empty(&iip->ili_item.li_bio_list));
+ ASSERT(iip->ili_last_fields);
+ goto out_iunlock;
+ }
+
+ /*
+ * Inodes not attached to the buffer can be released immediately.
+ * Everything else has to go through xfs_iflush_abort() on journal
+ * commit as the flock synchronises removal of the inode from the
+ * cluster buffer against inode reclaim.
+ */
+ if (!iip || list_empty(&iip->ili_item.li_bio_list))
+ goto out_iunlock;
+
+ __xfs_iflags_set(ip, XFS_IFLUSHING);
+ spin_unlock(&ip->i_flags_lock);
+ rcu_read_unlock();
+
+ /* we have a dirty inode in memory that has not yet been flushed. */
+ spin_lock(&iip->ili_lock);
+ iip->ili_last_fields = iip->ili_fields;
+ iip->ili_fields = 0;
+ iip->ili_fsync_fields = 0;
+ spin_unlock(&iip->ili_lock);
+ ASSERT(iip->ili_last_fields);
+
+ if (ip != free_ip)
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return;
+
+out_iunlock:
+ if (ip != free_ip)
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_iflags_unlock:
+ spin_unlock(&ip->i_flags_lock);
+ rcu_read_unlock();
}
/*
@@ -2196,31 +2597,23 @@
*/
STATIC int
xfs_ifree_cluster(
- xfs_inode_t *free_ip,
- xfs_trans_t *tp,
+ struct xfs_inode *free_ip,
+ struct xfs_trans *tp,
struct xfs_icluster *xic)
{
- xfs_mount_t *mp = free_ip->i_mount;
- int blks_per_cluster;
- int inodes_per_cluster;
+ struct xfs_mount *mp = free_ip->i_mount;
+ struct xfs_ino_geometry *igeo = M_IGEO(mp);
+ struct xfs_buf *bp;
+ xfs_daddr_t blkno;
+ xfs_ino_t inum = xic->first_ino;
int nbufs;
int i, j;
int ioffset;
- xfs_daddr_t blkno;
- xfs_buf_t *bp;
- xfs_inode_t *ip;
- xfs_inode_log_item_t *iip;
- struct xfs_log_item *lip;
- struct xfs_perag *pag;
- xfs_ino_t inum;
+ int error;
- inum = xic->first_ino;
- pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
- blks_per_cluster = xfs_icluster_size_fsb(mp);
- inodes_per_cluster = blks_per_cluster << mp->m_sb.sb_inopblog;
- nbufs = mp->m_ialloc_blks / blks_per_cluster;
+ nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster;
- for (j = 0; j < nbufs; j++, inum += inodes_per_cluster) {
+ for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) {
/*
* The allocation bitmap tells us which inodes of the chunk were
* physically allocated. Skip the cluster if an inode falls into
@@ -2228,7 +2621,7 @@
*/
ioffset = inum - xic->first_ino;
if ((xic->alloc & XFS_INOBT_MASK(ioffset)) == 0) {
- ASSERT(ioffset % inodes_per_cluster == 0);
+ ASSERT(ioffset % igeo->inodes_per_cluster == 0);
continue;
}
@@ -2237,18 +2630,18 @@
/*
* We obtain and lock the backing buffer first in the process
- * here, as we have to ensure that any dirty inode that we
- * can't get the flush lock on is attached to the buffer.
+ * here to ensure dirty inodes attached to the buffer remain in
+ * the flushing state while we mark them stale.
+ *
* If we scan the in-memory inodes first, then buffer IO can
* complete before we get a lock on it, and hence we may fail
* to mark all the active inodes on the buffer stale.
*/
- bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
- mp->m_bsize * blks_per_cluster,
- XBF_UNMAPPED);
-
- if (!bp)
- return -ENOMEM;
+ error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
+ mp->m_bsize * igeo->blocks_per_cluster,
+ XBF_UNMAPPED, &bp);
+ if (error)
+ return error;
/*
* This buffer may not have been correctly initialised as we
@@ -2259,159 +2652,30 @@
* want it to fail. We can acheive this by adding a write
* verifier to the buffer.
*/
- bp->b_ops = &xfs_inode_buf_ops;
+ bp->b_ops = &xfs_inode_buf_ops;
/*
- * Walk the inodes already attached to the buffer and mark them
- * stale. These will all have the flush locks held, so an
- * in-memory inode walk can't lock them. By marking them all
- * stale first, we will not attempt to lock them in the loop
- * below as the XFS_ISTALE flag will be set.
+ * Now we need to set all the cached clean inodes as XFS_ISTALE,
+ * too. This requires lookups, and will skip inodes that we've
+ * already marked XFS_ISTALE.
*/
- list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
- if (lip->li_type == XFS_LI_INODE) {
- iip = (xfs_inode_log_item_t *)lip;
- ASSERT(iip->ili_logged == 1);
- lip->li_cb = xfs_istale_done;
- xfs_trans_ail_copy_lsn(mp->m_ail,
- &iip->ili_flush_lsn,
- &iip->ili_item.li_lsn);
- xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
- }
- }
-
-
- /*
- * For each inode in memory attempt to add it to the inode
- * buffer and set it up for being staled on buffer IO
- * completion. This is safe as we've locked out tail pushing
- * and flushing by locking the buffer.
- *
- * We have already marked every inode that was part of a
- * transaction stale above, which means there is no point in
- * even trying to lock them.
- */
- for (i = 0; i < inodes_per_cluster; i++) {
-retry:
- rcu_read_lock();
- ip = radix_tree_lookup(&pag->pag_ici_root,
- XFS_INO_TO_AGINO(mp, (inum + i)));
-
- /* Inode not in memory, nothing to do */
- if (!ip) {
- rcu_read_unlock();
- continue;
- }
-
- /*
- * because this is an RCU protected lookup, we could
- * find a recently freed or even reallocated inode
- * during the lookup. We need to check under the
- * i_flags_lock for a valid inode here. Skip it if it
- * is not valid, the wrong inode or stale.
- */
- spin_lock(&ip->i_flags_lock);
- if (ip->i_ino != inum + i ||
- __xfs_iflags_test(ip, XFS_ISTALE)) {
- spin_unlock(&ip->i_flags_lock);
- rcu_read_unlock();
- continue;
- }
- spin_unlock(&ip->i_flags_lock);
-
- /*
- * Don't try to lock/unlock the current inode, but we
- * _cannot_ skip the other inodes that we did not find
- * in the list attached to the buffer and are not
- * already marked stale. If we can't lock it, back off
- * and retry.
- */
- if (ip != free_ip) {
- if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
- rcu_read_unlock();
- delay(1);
- goto retry;
- }
-
- /*
- * Check the inode number again in case we're
- * racing with freeing in xfs_reclaim_inode().
- * See the comments in that function for more
- * information as to why the initial check is
- * not sufficient.
- */
- if (ip->i_ino != inum + i) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- rcu_read_unlock();
- continue;
- }
- }
- rcu_read_unlock();
-
- xfs_iflock(ip);
- xfs_iflags_set(ip, XFS_ISTALE);
-
- /*
- * we don't need to attach clean inodes or those only
- * with unlogged changes (which we throw away, anyway).
- */
- iip = ip->i_itemp;
- if (!iip || xfs_inode_clean(ip)) {
- ASSERT(ip != free_ip);
- xfs_ifunlock(ip);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- continue;
- }
-
- iip->ili_last_fields = iip->ili_fields;
- iip->ili_fields = 0;
- iip->ili_fsync_fields = 0;
- iip->ili_logged = 1;
- xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
- &iip->ili_item.li_lsn);
-
- xfs_buf_attach_iodone(bp, xfs_istale_done,
- &iip->ili_item);
-
- if (ip != free_ip)
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- }
+ for (i = 0; i < igeo->inodes_per_cluster; i++)
+ xfs_ifree_mark_inode_stale(bp, free_ip, inum + i);
xfs_trans_stale_inode_buf(tp, bp);
xfs_trans_binval(tp, bp);
}
-
- xfs_perag_put(pag);
return 0;
}
/*
- * Free any local-format buffers sitting around before we reset to
- * extents format.
- */
-static inline void
-xfs_ifree_local_data(
- struct xfs_inode *ip,
- int whichfork)
-{
- struct xfs_ifork *ifp;
-
- if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL)
- return;
-
- ifp = XFS_IFORK_PTR(ip, whichfork);
- xfs_idata_realloc(ip, -ifp->if_bytes, whichfork);
-}
-
-/*
- * This is called to return an inode to the inode free list.
- * The inode should already be truncated to 0 length and have
- * no pages associated with it. This routine also assumes that
- * the inode is already a part of the transaction.
+ * This is called to return an inode to the inode free list. The inode should
+ * already be truncated to 0 length and have no pages associated with it. This
+ * routine also assumes that the inode is already a part of the transaction.
*
- * The on-disk copy of the inode will have been added to the list
- * of unlinked inodes in the AGI. We need to remove the inode from
- * that list atomically with respect to freeing it here.
+ * The on-disk copy of the inode will have been added to the list of unlinked
+ * inodes in the AGI. We need to remove the inode from that list atomically with
+ * respect to freeing it here.
*/
int
xfs_ifree(
@@ -2420,38 +2684,50 @@
{
int error;
struct xfs_icluster xic = { 0 };
+ struct xfs_inode_log_item *iip = ip->i_itemp;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(VFS_I(ip)->i_nlink == 0);
- ASSERT(ip->i_d.di_nextents == 0);
- ASSERT(ip->i_d.di_anextents == 0);
+ ASSERT(ip->i_df.if_nextents == 0);
ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
ASSERT(ip->i_d.di_nblocks == 0);
/*
- * Pull the on-disk inode from the AGI unlinked list.
+ * Free the inode first so that we guarantee that the AGI lock is going
+ * to be taken before we remove the inode from the unlinked list. This
+ * makes the AGI lock -> unlinked list modification order the same as
+ * used in O_TMPFILE creation.
*/
- error = xfs_iunlink_remove(tp, ip);
- if (error)
- return error;
-
error = xfs_difree(tp, ip->i_ino, &xic);
if (error)
return error;
- xfs_ifree_local_data(ip, XFS_DATA_FORK);
- xfs_ifree_local_data(ip, XFS_ATTR_FORK);
+ error = xfs_iunlink_remove(tp, ip);
+ if (error)
+ return error;
+
+ /*
+ * Free any local-format data sitting around before we reset the
+ * data fork to extents format. Note that the attr fork data has
+ * already been freed by xfs_attr_inactive.
+ */
+ if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
+ kmem_free(ip->i_df.if_u1.if_data);
+ ip->i_df.if_u1.if_data = NULL;
+ ip->i_df.if_bytes = 0;
+ }
VFS_I(ip)->i_mode = 0; /* mark incore inode as free */
ip->i_d.di_flags = 0;
- ip->i_d.di_flags2 = 0;
+ ip->i_d.di_flags2 = ip->i_mount->m_ino_geo.new_diflags2;
ip->i_d.di_dmevmask = 0;
ip->i_d.di_forkoff = 0; /* mark the attr fork not in use */
- ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
- ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
+ ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
/* Don't attempt to replay owner changes for a deleted inode */
- ip->i_itemp->ili_fields &= ~(XFS_ILOG_AOWNER|XFS_ILOG_DOWNER);
+ spin_lock(&iip->ili_lock);
+ iip->ili_fields &= ~(XFS_ILOG_AOWNER | XFS_ILOG_DOWNER);
+ spin_unlock(&iip->ili_lock);
/*
* Bump the generation count so no one will be confused
@@ -2480,7 +2756,7 @@
trace_xfs_inode_unpin_nowait(ip, _RET_IP_);
/* Give the log a push to start the unpinning I/O */
- xfs_log_force_lsn(ip->i_mount, ip->i_itemp->ili_last_lsn, 0, NULL);
+ xfs_log_force_seq(ip->i_mount, ip->i_itemp->ili_commit_seq, 0, NULL);
}
@@ -2769,9 +3045,7 @@
error = xfs_droplink(tp, dp2);
if (error)
goto out_trans_abort;
- error = xfs_bumplink(tp, dp1);
- if (error)
- goto out_trans_abort;
+ xfs_bumplink(tp, dp1);
}
/*
@@ -2795,9 +3069,7 @@
error = xfs_droplink(tp, dp1);
if (error)
goto out_trans_abort;
- error = xfs_bumplink(tp, dp2);
- if (error)
- goto out_trans_abort;
+ xfs_bumplink(tp, dp2);
}
/*
@@ -2835,7 +3107,7 @@
/*
* xfs_rename_alloc_whiteout()
*
- * Return a referenced, unlinked, unlocked inode that that can be used as a
+ * Return a referenced, unlinked, unlocked inode that can be used as a
* whiteout in a rename transaction. We use a tmpfile inode here so that if we
* crash between allocating the inode and linking it into the rename transaction
* recovery will free the inode and we won't leak it.
@@ -2882,6 +3154,7 @@
struct xfs_trans *tp;
struct xfs_inode *wip = NULL; /* whiteout inode */
struct xfs_inode *inodes[__XFS_SORT_INODES];
+ int i;
int num_inodes = __XFS_SORT_INODES;
bool new_parent = (src_dp != target_dp);
bool src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
@@ -2899,7 +3172,6 @@
* appropriately.
*/
if (flags & RENAME_WHITEOUT) {
- ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE)));
error = xfs_rename_alloc_whiteout(target_dp, &wip);
if (error)
return error;
@@ -2956,7 +3228,7 @@
* tree quota mechanism would be circumvented.
*/
if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
- (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) {
+ target_dp->i_d.di_projid != src_ip->i_d.di_projid)) {
error = -EXDEV;
goto out_trans_cancel;
}
@@ -2995,6 +3267,30 @@
}
/*
+ * Lock the AGI buffers we need to handle bumping the nlink of the
+ * whiteout inode off the unlinked list and to handle dropping the
+ * nlink of the target inode. Per locking order rules, do this in
+ * increasing AG order and before directory block allocation tries to
+ * grab AGFs because we grab AGIs before AGFs.
+ *
+ * The (vfs) caller must ensure that if src is a directory then
+ * target_ip is either null or an empty directory.
+ */
+ for (i = 0; i < num_inodes && inodes[i] != NULL; i++) {
+ if (inodes[i] == wip ||
+ (inodes[i] == target_ip &&
+ (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) {
+ struct xfs_buf *bp;
+ xfs_agnumber_t agno;
+
+ agno = XFS_INO_TO_AGNO(mp, inodes[i]->i_ino);
+ error = xfs_read_agi(mp, tp, agno, &bp);
+ if (error)
+ goto out_trans_cancel;
+ }
+ }
+
+ /*
* Directory entry creation below may acquire the AGF. Remove
* the whiteout from the unlinked list first to preserve correct
* AGI/AGF locking order. This dirties the transaction so failures
@@ -3013,7 +3309,6 @@
goto out_trans_cancel;
xfs_bumplink(tp, wip);
- xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
VFS_I(wip)->i_state &= ~I_LINKABLE;
}
@@ -3035,9 +3330,7 @@
XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
if (new_parent && src_is_directory) {
- error = xfs_bumplink(tp, target_dp);
- if (error)
- goto out_trans_cancel;
+ xfs_bumplink(tp, target_dp);
}
} else { /* target_ip != NULL */
/*
@@ -3148,373 +3441,76 @@
return error;
}
-STATIC int
-xfs_iflush_cluster(
- struct xfs_inode *ip,
- struct xfs_buf *bp)
-{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_perag *pag;
- unsigned long first_index, mask;
- unsigned long inodes_per_cluster;
- int cilist_size;
- struct xfs_inode **cilist;
- struct xfs_inode *cip;
- int nr_found;
- int clcount = 0;
- int i;
-
- pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-
- inodes_per_cluster = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;
- cilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
- cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS);
- if (!cilist)
- goto out_put;
-
- mask = ~(((mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog)) - 1);
- first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
- rcu_read_lock();
- /* really need a gang lookup range call here */
- nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist,
- first_index, inodes_per_cluster);
- if (nr_found == 0)
- goto out_free;
-
- for (i = 0; i < nr_found; i++) {
- cip = cilist[i];
- if (cip == ip)
- continue;
-
- /*
- * because this is an RCU protected lookup, we could find a
- * recently freed or even reallocated inode during the lookup.
- * We need to check under the i_flags_lock for a valid inode
- * here. Skip it if it is not valid or the wrong inode.
- */
- spin_lock(&cip->i_flags_lock);
- if (!cip->i_ino ||
- __xfs_iflags_test(cip, XFS_ISTALE)) {
- spin_unlock(&cip->i_flags_lock);
- continue;
- }
-
- /*
- * Once we fall off the end of the cluster, no point checking
- * any more inodes in the list because they will also all be
- * outside the cluster.
- */
- if ((XFS_INO_TO_AGINO(mp, cip->i_ino) & mask) != first_index) {
- spin_unlock(&cip->i_flags_lock);
- break;
- }
- spin_unlock(&cip->i_flags_lock);
-
- /*
- * Do an un-protected check to see if the inode is dirty and
- * is a candidate for flushing. These checks will be repeated
- * later after the appropriate locks are acquired.
- */
- if (xfs_inode_clean(cip) && xfs_ipincount(cip) == 0)
- continue;
-
- /*
- * Try to get locks. If any are unavailable or it is pinned,
- * then this inode cannot be flushed and is skipped.
- */
-
- if (!xfs_ilock_nowait(cip, XFS_ILOCK_SHARED))
- continue;
- if (!xfs_iflock_nowait(cip)) {
- xfs_iunlock(cip, XFS_ILOCK_SHARED);
- continue;
- }
- if (xfs_ipincount(cip)) {
- xfs_ifunlock(cip);
- xfs_iunlock(cip, XFS_ILOCK_SHARED);
- continue;
- }
-
-
- /*
- * Check the inode number again, just to be certain we are not
- * racing with freeing in xfs_reclaim_inode(). See the comments
- * in that function for more information as to why the initial
- * check is not sufficient.
- */
- if (!cip->i_ino) {
- xfs_ifunlock(cip);
- xfs_iunlock(cip, XFS_ILOCK_SHARED);
- continue;
- }
-
- /*
- * arriving here means that this inode can be flushed. First
- * re-check that it's dirty before flushing.
- */
- if (!xfs_inode_clean(cip)) {
- int error;
- error = xfs_iflush_int(cip, bp);
- if (error) {
- xfs_iunlock(cip, XFS_ILOCK_SHARED);
- goto cluster_corrupt_out;
- }
- clcount++;
- } else {
- xfs_ifunlock(cip);
- }
- xfs_iunlock(cip, XFS_ILOCK_SHARED);
- }
-
- if (clcount) {
- XFS_STATS_INC(mp, xs_icluster_flushcnt);
- XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
- }
-
-out_free:
- rcu_read_unlock();
- kmem_free(cilist);
-out_put:
- xfs_perag_put(pag);
- return 0;
-
-
-cluster_corrupt_out:
- /*
- * Corruption detected in the clustering loop. Invalidate the
- * inode buffer and shut down the filesystem.
- */
- rcu_read_unlock();
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-
- /*
- * We'll always have an inode attached to the buffer for completion
- * process by the time we are called from xfs_iflush(). Hence we have
- * always need to do IO completion processing to abort the inodes
- * attached to the buffer. handle them just like the shutdown case in
- * xfs_buf_submit().
- */
- ASSERT(bp->b_iodone);
- bp->b_flags &= ~XBF_DONE;
- xfs_buf_stale(bp);
- xfs_buf_ioerror(bp, -EIO);
- xfs_buf_ioend(bp);
-
- /* abort the corrupt inode, as it was not attached to the buffer */
- xfs_iflush_abort(cip, false);
- kmem_free(cilist);
- xfs_perag_put(pag);
- return -EFSCORRUPTED;
-}
-
-/*
- * Flush dirty inode metadata into the backing buffer.
- *
- * The caller must have the inode lock and the inode flush lock held. The
- * inode lock will still be held upon return to the caller, and the inode
- * flush lock will be released after the inode has reached the disk.
- *
- * The caller must write out the buffer returned in *bpp and release it.
- */
-int
+static int
xfs_iflush(
- struct xfs_inode *ip,
- struct xfs_buf **bpp)
-{
- struct xfs_mount *mp = ip->i_mount;
- struct xfs_buf *bp = NULL;
- struct xfs_dinode *dip;
- int error;
-
- XFS_STATS_INC(mp, xs_iflush_count);
-
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
- ASSERT(xfs_isiflocked(ip));
- ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
- ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
-
- *bpp = NULL;
-
- xfs_iunpin_wait(ip);
-
- /*
- * For stale inodes we cannot rely on the backing buffer remaining
- * stale in cache for the remaining life of the stale inode and so
- * xfs_imap_to_bp() below may give us a buffer that no longer contains
- * inodes below. We have to check this after ensuring the inode is
- * unpinned so that it is safe to reclaim the stale inode after the
- * flush call.
- */
- if (xfs_iflags_test(ip, XFS_ISTALE)) {
- xfs_ifunlock(ip);
- return 0;
- }
-
- /*
- * This may have been unpinned because the filesystem is shutting
- * down forcibly. If that's the case we must not write this inode
- * to disk, because the log record didn't make it to disk.
- *
- * We also have to remove the log item from the AIL in this case,
- * as we wait for an empty AIL as part of the unmount process.
- */
- if (XFS_FORCED_SHUTDOWN(mp)) {
- error = -EIO;
- goto abort_out;
- }
-
- /*
- * Get the buffer containing the on-disk inode. We are doing a try-lock
- * operation here, so we may get an EAGAIN error. In that case, we
- * simply want to return with the inode still dirty.
- *
- * If we get any other error, we effectively have a corruption situation
- * and we cannot flush the inode, so we treat it the same as failing
- * xfs_iflush_int().
- */
- error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK,
- 0);
- if (error == -EAGAIN) {
- xfs_ifunlock(ip);
- return error;
- }
- if (error)
- goto corrupt_out;
-
- /*
- * First flush out the inode that xfs_iflush was called with.
- */
- error = xfs_iflush_int(ip, bp);
- if (error)
- goto corrupt_out;
-
- /*
- * If the buffer is pinned then push on the log now so we won't
- * get stuck waiting in the write for too long.
- */
- if (xfs_buf_ispinned(bp))
- xfs_log_force(mp, 0);
-
- /*
- * inode clustering: try to gather other inodes into this write
- *
- * Note: Any error during clustering will result in the filesystem
- * being shut down and completion callbacks run on the cluster buffer.
- * As we have already flushed and attached this inode to the buffer,
- * it has already been aborted and released by xfs_iflush_cluster() and
- * so we have no further error handling to do here.
- */
- error = xfs_iflush_cluster(ip, bp);
- if (error)
- return error;
-
- *bpp = bp;
- return 0;
-
-corrupt_out:
- if (bp)
- xfs_buf_relse(bp);
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-abort_out:
- /* abort the corrupt inode, as it was not attached to the buffer */
- xfs_iflush_abort(ip, false);
- return error;
-}
-
-/*
- * If there are inline format data / attr forks attached to this inode,
- * make sure they're not corrupt.
- */
-bool
-xfs_inode_verify_forks(
- struct xfs_inode *ip)
-{
- struct xfs_ifork *ifp;
- xfs_failaddr_t fa;
-
- fa = xfs_ifork_verify_data(ip, &xfs_default_ifork_ops);
- if (fa) {
- ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
- xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork",
- ifp->if_u1.if_data, ifp->if_bytes, fa);
- return false;
- }
-
- fa = xfs_ifork_verify_attr(ip, &xfs_default_ifork_ops);
- if (fa) {
- ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK);
- xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
- ifp ? ifp->if_u1.if_data : NULL,
- ifp ? ifp->if_bytes : 0, fa);
- return false;
- }
- return true;
-}
-
-STATIC int
-xfs_iflush_int(
struct xfs_inode *ip,
struct xfs_buf *bp)
{
struct xfs_inode_log_item *iip = ip->i_itemp;
struct xfs_dinode *dip;
struct xfs_mount *mp = ip->i_mount;
+ int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
- ASSERT(xfs_isiflocked(ip));
- ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
- ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
- ASSERT(iip != NULL && iip->ili_fields != 0);
- ASSERT(ip->i_d.di_version > 1);
+ ASSERT(xfs_iflags_test(ip, XFS_IFLUSHING));
+ ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
+ ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
+ ASSERT(iip->ili_item.li_buf == bp);
- /* set *dip = inode's place in the buffer */
dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
+ /*
+ * We don't flush the inode if any of the following checks fail, but we
+ * do still update the log item and attach to the backing buffer as if
+ * the flush happened. This is a formality to facilitate predictable
+ * error handling as the caller will shutdown and fail the buffer.
+ */
+ error = -EFSCORRUPTED;
if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC),
mp, XFS_ERRTAG_IFLUSH_1)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: Bad inode %Lu magic number 0x%x, ptr "PTR_FMT,
__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
- goto corrupt_out;
+ goto flush_out;
}
if (S_ISREG(VFS_I(ip)->i_mode)) {
if (XFS_TEST_ERROR(
- (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
- (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
+ ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
+ ip->i_df.if_format != XFS_DINODE_FMT_BTREE,
mp, XFS_ERRTAG_IFLUSH_3)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: Bad regular inode %Lu, ptr "PTR_FMT,
__func__, ip->i_ino, ip);
- goto corrupt_out;
+ goto flush_out;
}
} else if (S_ISDIR(VFS_I(ip)->i_mode)) {
if (XFS_TEST_ERROR(
- (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
- (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
- (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL),
+ ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
+ ip->i_df.if_format != XFS_DINODE_FMT_BTREE &&
+ ip->i_df.if_format != XFS_DINODE_FMT_LOCAL,
mp, XFS_ERRTAG_IFLUSH_4)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: Bad directory inode %Lu, ptr "PTR_FMT,
__func__, ip->i_ino, ip);
- goto corrupt_out;
+ goto flush_out;
}
}
- if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents >
+ if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp) >
ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: detected corrupt incore inode %Lu, "
"total extents = %d, nblocks = %Ld, ptr "PTR_FMT,
__func__, ip->i_ino,
- ip->i_d.di_nextents + ip->i_d.di_anextents,
+ ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp),
ip->i_d.di_nblocks, ip);
- goto corrupt_out;
+ goto flush_out;
}
if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
mp, XFS_ERRTAG_IFLUSH_6)) {
xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
"%s: bad inode %Lu, forkoff 0x%x, ptr "PTR_FMT,
__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
- goto corrupt_out;
+ goto flush_out;
}
/*
@@ -3526,12 +3522,19 @@
* backwards compatibility with old kernels that predate logging all
* inode changes.
*/
- if (ip->i_d.di_version < 3)
+ if (!xfs_sb_version_has_v3inode(&mp->m_sb))
ip->i_d.di_flushiter++;
- /* Check the inline fork data before we write out. */
- if (!xfs_inode_verify_forks(ip))
- goto corrupt_out;
+ /*
+ * If there are inline format data / attr forks attached to this inode,
+ * make sure they are not corrupt.
+ */
+ if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL &&
+ xfs_ifork_verify_local_data(ip))
+ goto flush_out;
+ if (ip->i_afp && ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL &&
+ xfs_ifork_verify_local_attr(ip))
+ goto flush_out;
/*
* Copy the dirty parts of the inode into the on-disk inode. We always
@@ -3547,7 +3550,6 @@
xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
if (XFS_IFORK_Q(ip))
xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK);
- xfs_inobp_check(mp, bp);
/*
* We've recorded everything logged in the inode, so we'd like to clear
@@ -3560,45 +3562,144 @@
*
* What we do is move the bits to the ili_last_fields field. When
* logging the inode, these bits are moved back to the ili_fields field.
- * In the xfs_iflush_done() routine we clear ili_last_fields, since we
- * know that the information those bits represent is permanently on
+ * In the xfs_buf_inode_iodone() routine we clear ili_last_fields, since
+ * we know that the information those bits represent is permanently on
* disk. As long as the flush completes before the inode is logged
* again, then both ili_fields and ili_last_fields will be cleared.
- *
- * We can play with the ili_fields bits here, because the inode lock
- * must be held exclusively in order to set bits there and the flush
- * lock protects the ili_last_fields bits. Set ili_logged so the flush
- * done routine can tell whether or not to look in the AIL. Also, store
- * the current LSN of the inode so that we can tell whether the item has
- * moved in the AIL from xfs_iflush_done(). In order to read the lsn we
- * need the AIL lock, because it is a 64 bit value that cannot be read
- * atomically.
*/
+ error = 0;
+flush_out:
+ spin_lock(&iip->ili_lock);
iip->ili_last_fields = iip->ili_fields;
iip->ili_fields = 0;
iip->ili_fsync_fields = 0;
- iip->ili_logged = 1;
+ spin_unlock(&iip->ili_lock);
+ /*
+ * Store the current LSN of the inode so that we can tell whether the
+ * item has moved in the AIL from xfs_buf_inode_iodone().
+ */
xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
&iip->ili_item.li_lsn);
- /*
- * Attach the function xfs_iflush_done to the inode's
- * buffer. This will remove the inode from the AIL
- * and unlock the inode's flush lock when the inode is
- * completely written to disk.
- */
- xfs_buf_attach_iodone(bp, xfs_iflush_done, &iip->ili_item);
-
/* generate the checksum. */
xfs_dinode_calc_crc(mp, dip);
+ return error;
+}
- ASSERT(!list_empty(&bp->b_li_list));
- ASSERT(bp->b_iodone != NULL);
+/*
+ * Non-blocking flush of dirty inode metadata into the backing buffer.
+ *
+ * The caller must have a reference to the inode and hold the cluster buffer
+ * locked. The function will walk across all the inodes on the cluster buffer it
+ * can find and lock without blocking, and flush them to the cluster buffer.
+ *
+ * On successful flushing of at least one inode, the caller must write out the
+ * buffer and release it. If no inodes are flushed, -EAGAIN will be returned and
+ * the caller needs to release the buffer. On failure, the filesystem will be
+ * shut down, the buffer will have been unlocked and released, and EFSCORRUPTED
+ * will be returned.
+ */
+int
+xfs_iflush_cluster(
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = bp->b_mount;
+ struct xfs_log_item *lip, *n;
+ struct xfs_inode *ip;
+ struct xfs_inode_log_item *iip;
+ int clcount = 0;
+ int error = 0;
+
+ /*
+ * We must use the safe variant here as on shutdown xfs_iflush_abort()
+ * can remove itself from the list.
+ */
+ list_for_each_entry_safe(lip, n, &bp->b_li_list, li_bio_list) {
+ iip = (struct xfs_inode_log_item *)lip;
+ ip = iip->ili_inode;
+
+ /*
+ * Quick and dirty check to avoid locks if possible.
+ */
+ if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING))
+ continue;
+ if (xfs_ipincount(ip))
+ continue;
+
+ /*
+ * The inode is still attached to the buffer, which means it is
+ * dirty but reclaim might try to grab it. Check carefully for
+ * that, and grab the ilock while still holding the i_flags_lock
+ * to guarantee reclaim will not be able to reclaim this inode
+ * once we drop the i_flags_lock.
+ */
+ spin_lock(&ip->i_flags_lock);
+ ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE));
+ if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) {
+ spin_unlock(&ip->i_flags_lock);
+ continue;
+ }
+
+ /*
+ * ILOCK will pin the inode against reclaim and prevent
+ * concurrent transactions modifying the inode while we are
+ * flushing the inode. If we get the lock, set the flushing
+ * state before we drop the i_flags_lock.
+ */
+ if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
+ spin_unlock(&ip->i_flags_lock);
+ continue;
+ }
+ __xfs_iflags_set(ip, XFS_IFLUSHING);
+ spin_unlock(&ip->i_flags_lock);
+
+ /*
+ * Abort flushing this inode if we are shut down because the
+ * inode may not currently be in the AIL. This can occur when
+ * log I/O failure unpins the inode without inserting into the
+ * AIL, leaving a dirty/unpinned inode attached to the buffer
+ * that otherwise looks like it should be flushed.
+ */
+ if (XFS_FORCED_SHUTDOWN(mp)) {
+ xfs_iunpin_wait(ip);
+ xfs_iflush_abort(ip);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ error = -EIO;
+ continue;
+ }
+
+ /* don't block waiting on a log force to unpin dirty inodes */
+ if (xfs_ipincount(ip)) {
+ xfs_iflags_clear(ip, XFS_IFLUSHING);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ continue;
+ }
+
+ if (!xfs_inode_clean(ip))
+ error = xfs_iflush(ip, bp);
+ else
+ xfs_iflags_clear(ip, XFS_IFLUSHING);
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ if (error)
+ break;
+ clcount++;
+ }
+
+ if (error) {
+ bp->b_flags |= XBF_ASYNC;
+ xfs_buf_ioend_fail(bp);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ return error;
+ }
+
+ if (!clcount)
+ return -EAGAIN;
+
+ XFS_STATS_INC(mp, xs_icluster_flushcnt);
+ XFS_STATS_ADD(mp, xs_icluster_flushinode, clcount);
return 0;
-corrupt_out:
- return -EFSCORRUPTED;
}
/* Release an inode. */
@@ -3609,3 +3710,115 @@
trace_xfs_irele(ip, _RET_IP_);
iput(VFS_I(ip));
}
+
+/*
+ * Ensure all commited transactions touching the inode are written to the log.
+ */
+int
+xfs_log_force_inode(
+ struct xfs_inode *ip)
+{
+ xfs_csn_t seq = 0;
+
+ xfs_ilock(ip, XFS_ILOCK_SHARED);
+ if (xfs_ipincount(ip))
+ seq = ip->i_itemp->ili_commit_seq;
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+ if (!seq)
+ return 0;
+ return xfs_log_force_seq(ip->i_mount, seq, XFS_LOG_SYNC, NULL);
+}
+
+/*
+ * Grab the exclusive iolock for a data copy from src to dest, making sure to
+ * abide vfs locking order (lowest pointer value goes first) and breaking the
+ * layout leases before proceeding. The loop is needed because we cannot call
+ * the blocking break_layout() with the iolocks held, and therefore have to
+ * back out both locks.
+ */
+static int
+xfs_iolock_two_inodes_and_break_layout(
+ struct inode *src,
+ struct inode *dest)
+{
+ int error;
+
+ if (src > dest)
+ swap(src, dest);
+
+retry:
+ /* Wait to break both inodes' layouts before we start locking. */
+ error = break_layout(src, true);
+ if (error)
+ return error;
+ if (src != dest) {
+ error = break_layout(dest, true);
+ if (error)
+ return error;
+ }
+
+ /* Lock one inode and make sure nobody got in and leased it. */
+ inode_lock(src);
+ error = break_layout(src, false);
+ if (error) {
+ inode_unlock(src);
+ if (error == -EWOULDBLOCK)
+ goto retry;
+ return error;
+ }
+
+ if (src == dest)
+ return 0;
+
+ /* Lock the other inode and make sure nobody got in and leased it. */
+ inode_lock_nested(dest, I_MUTEX_NONDIR2);
+ error = break_layout(dest, false);
+ if (error) {
+ inode_unlock(src);
+ inode_unlock(dest);
+ if (error == -EWOULDBLOCK)
+ goto retry;
+ return error;
+ }
+
+ return 0;
+}
+
+/*
+ * Lock two inodes so that userspace cannot initiate I/O via file syscalls or
+ * mmap activity.
+ */
+int
+xfs_ilock2_io_mmap(
+ struct xfs_inode *ip1,
+ struct xfs_inode *ip2)
+{
+ int ret;
+
+ ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
+ if (ret)
+ return ret;
+ if (ip1 == ip2)
+ xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
+ else
+ xfs_lock_two_inodes(ip1, XFS_MMAPLOCK_EXCL,
+ ip2, XFS_MMAPLOCK_EXCL);
+ return 0;
+}
+
+/* Unlock both inodes to allow IO and mmap activity. */
+void
+xfs_iunlock2_io_mmap(
+ struct xfs_inode *ip1,
+ struct xfs_inode *ip2)
+{
+ bool same_inode = (ip1 == ip2);
+
+ xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
+ if (!same_inode)
+ xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+ inode_unlock(VFS_I(ip2));
+ if (!same_inode)
+ inode_unlock(VFS_I(ip1));
+}
--
Gitblit v1.6.2