summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/Kconfig2
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c27
-rw-r--r--fs/xfs/libxfs/xfs_defer.c28
-rw-r--r--fs/xfs/libxfs/xfs_defer.h2
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c3
-rw-r--r--fs/xfs/xfs_dquot.c5
-rw-r--r--fs/xfs/xfs_dquot_item_recover.c21
-rw-r--r--fs/xfs/xfs_inode.h8
-rw-r--r--fs/xfs/xfs_inode_item_recover.c46
-rw-r--r--fs/xfs/xfs_ioctl.c30
-rw-r--r--fs/xfs/xfs_iops.c7
-rw-r--r--fs/xfs/xfs_log.c23
-rw-r--r--fs/xfs/xfs_log_recover.c2
-rw-r--r--fs/xfs/xfs_reflink.c1
14 files changed, 147 insertions, 58 deletions
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index ed0bc8cbc703..567fb37274d3 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -147,7 +147,7 @@ config XFS_ONLINE_SCRUB_STATS
bool "XFS online metadata check usage data collection"
default y
depends on XFS_ONLINE_SCRUB
- select XFS_DEBUG
+ select DEBUG_FS
help
If you say Y here, the kernel will gather usage data about
the online metadata check subsystem. This includes the number
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3069194527dd..100ab5931b31 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2275,16 +2275,37 @@ xfs_alloc_min_freelist(
ASSERT(mp->m_alloc_maxlevels > 0);
+ /*
+ * For a btree shorter than the maximum height, the worst case is that
+ * every level gets split and a new level is added, then while inserting
+ * another entry to refill the AGFL, every level under the old root gets
+ * split again. This is:
+ *
+ * (full height split reservation) + (AGFL refill split height)
+ * = (current height + 1) + (current height - 1)
+ * = (new height) + (new height - 2)
+ * = 2 * new height - 2
+ *
+ * For a btree of maximum height, the worst case is that every level
+ * under the root gets split, then while inserting another entry to
+ * refill the AGFL, every level under the root gets split again. This is
+ * also:
+ *
+ * 2 * (current height - 1)
+ * = 2 * (new height - 1)
+ * = 2 * new height - 2
+ */
+
/* space needed by-bno freespace btree */
min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1,
- mp->m_alloc_maxlevels);
+ mp->m_alloc_maxlevels) * 2 - 2;
/* space needed by-size freespace btree */
min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1,
- mp->m_alloc_maxlevels);
+ mp->m_alloc_maxlevels) * 2 - 2;
/* space needed reverse mapping used space btree */
if (xfs_has_rmapbt(mp))
min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1,
- mp->m_rmap_maxlevels);
+ mp->m_rmap_maxlevels) * 2 - 2;
return min_free;
}
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index bcfb6a4203cd..f71679ce23b9 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -245,21 +245,18 @@ xfs_defer_create_intents(
return ret;
}
-/* Abort all the intents that were committed. */
STATIC void
-xfs_defer_trans_abort(
- struct xfs_trans *tp,
- struct list_head *dop_pending)
+xfs_defer_pending_abort(
+ struct xfs_mount *mp,
+ struct list_head *dop_list)
{
struct xfs_defer_pending *dfp;
const struct xfs_defer_op_type *ops;
- trace_xfs_defer_trans_abort(tp, _RET_IP_);
-
/* Abort intent items that don't have a done item. */
- list_for_each_entry(dfp, dop_pending, dfp_list) {
+ list_for_each_entry(dfp, dop_list, dfp_list) {
ops = defer_op_types[dfp->dfp_type];
- trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
+ trace_xfs_defer_pending_abort(mp, dfp);
if (dfp->dfp_intent && !dfp->dfp_done) {
ops->abort_intent(dfp->dfp_intent);
dfp->dfp_intent = NULL;
@@ -267,6 +264,16 @@ xfs_defer_trans_abort(
}
}
+/* Abort all the intents that were committed. */
+STATIC void
+xfs_defer_trans_abort(
+ struct xfs_trans *tp,
+ struct list_head *dop_pending)
+{
+ trace_xfs_defer_trans_abort(tp, _RET_IP_);
+ xfs_defer_pending_abort(tp->t_mountp, dop_pending);
+}
+
/*
* Capture resources that the caller said not to release ("held") when the
* transaction commits. Caller is responsible for zero-initializing @dres.
@@ -756,12 +763,13 @@ xfs_defer_ops_capture(
/* Release all resources that we used to capture deferred ops. */
void
-xfs_defer_ops_capture_free(
+xfs_defer_ops_capture_abort(
struct xfs_mount *mp,
struct xfs_defer_capture *dfc)
{
unsigned short i;
+ xfs_defer_pending_abort(mp, &dfc->dfc_dfops);
xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
@@ -802,7 +810,7 @@ xfs_defer_ops_capture_and_commit(
/* Commit the transaction and add the capture structure to the list. */
error = xfs_trans_commit(tp);
if (error) {
- xfs_defer_ops_capture_free(mp, dfc);
+ xfs_defer_ops_capture_abort(mp, dfc);
return error;
}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 114a3a4930a3..8788ad5f6a73 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -121,7 +121,7 @@ int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp,
struct list_head *capture_list);
void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp,
struct xfs_defer_resources *dres);
-void xfs_defer_ops_capture_free(struct xfs_mount *mp,
+void xfs_defer_ops_capture_abort(struct xfs_mount *mp,
struct xfs_defer_capture *d);
void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 543f3748c2a3..137a65bda95d 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -510,6 +510,9 @@ xfs_dinode_verify(
if (mode && nextents + naextents > nblocks)
return __this_address;
+ if (nextents + naextents == 0 && nblocks != 0)
+ return __this_address;
+
if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
return __this_address;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index ac6ba646624d..a013b87ab8d5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -562,7 +562,8 @@ xfs_dquot_from_disk(
struct xfs_dquot *dqp,
struct xfs_buf *bp)
{
- struct xfs_disk_dquot *ddqp = bp->b_addr + dqp->q_bufoffset;
+ struct xfs_dqblk *dqb = xfs_buf_offset(bp, dqp->q_bufoffset);
+ struct xfs_disk_dquot *ddqp = &dqb->dd_diskdq;
/*
* Ensure that we got the type and ID we were looking for.
@@ -1250,7 +1251,7 @@ xfs_qm_dqflush(
}
/* Flush the incore dquot to the ondisk buffer. */
- dqblk = bp->b_addr + dqp->q_bufoffset;
+ dqblk = xfs_buf_offset(bp, dqp->q_bufoffset);
xfs_dquot_to_disk(&dqblk->dd_diskdq, dqp);
/*
diff --git a/fs/xfs/xfs_dquot_item_recover.c b/fs/xfs/xfs_dquot_item_recover.c
index 8966ba842395..2c2720ce6923 100644
--- a/fs/xfs/xfs_dquot_item_recover.c
+++ b/fs/xfs/xfs_dquot_item_recover.c
@@ -19,6 +19,7 @@
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_log_recover.h"
+#include "xfs_error.h"
STATIC void
xlog_recover_dquot_ra_pass2(
@@ -65,6 +66,7 @@ xlog_recover_dquot_commit_pass2(
{
struct xfs_mount *mp = log->l_mp;
struct xfs_buf *bp;
+ struct xfs_dqblk *dqb;
struct xfs_disk_dquot *ddq, *recddq;
struct xfs_dq_logformat *dq_f;
xfs_failaddr_t fa;
@@ -130,14 +132,14 @@ xlog_recover_dquot_commit_pass2(
return error;
ASSERT(bp);
- ddq = xfs_buf_offset(bp, dq_f->qlf_boffset);
+ dqb = xfs_buf_offset(bp, dq_f->qlf_boffset);
+ ddq = &dqb->dd_diskdq;
/*
* If the dquot has an LSN in it, recover the dquot only if it's less
* than the lsn of the transaction we are replaying.
*/
if (xfs_has_crc(mp)) {
- struct xfs_dqblk *dqb = (struct xfs_dqblk *)ddq;
xfs_lsn_t lsn = be64_to_cpu(dqb->dd_lsn);
if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
@@ -147,10 +149,23 @@ xlog_recover_dquot_commit_pass2(
memcpy(ddq, recddq, item->ri_buf[1].i_len);
if (xfs_has_crc(mp)) {
- xfs_update_cksum((char *)ddq, sizeof(struct xfs_dqblk),
+ xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
XFS_DQUOT_CRC_OFF);
}
+ /* Validate the recovered dquot. */
+ fa = xfs_dqblk_verify(log->l_mp, dqb, dq_f->qlf_id);
+ if (fa) {
+ XFS_CORRUPTION_ERROR("Bad dquot after recovery",
+ XFS_ERRLEVEL_LOW, mp, dqb,
+ sizeof(struct xfs_dqblk));
+ xfs_alert(mp,
+ "Metadata corruption detected at %pS, dquot 0x%x",
+ fa, dq_f->qlf_id);
+ error = -EFSCORRUPTED;
+ goto out_release;
+ }
+
ASSERT(dq_f->qlf_size == 2);
ASSERT(bp->b_mount == mp);
bp->b_flags |= _XBF_LOGRECOVERY;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 3dc47937da5d..3beb470f1892 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -569,6 +569,14 @@ extern void xfs_setup_inode(struct xfs_inode *ip);
extern void xfs_setup_iops(struct xfs_inode *ip);
extern void xfs_diflags_to_iflags(struct xfs_inode *ip, bool init);
+static inline void xfs_update_stable_writes(struct xfs_inode *ip)
+{
+ if (bdev_stable_writes(xfs_inode_buftarg(ip)->bt_bdev))
+ mapping_set_stable_writes(VFS_I(ip)->i_mapping);
+ else
+ mapping_clear_stable_writes(VFS_I(ip)->i_mapping);
+}
+
/*
* When setting up a newly allocated inode, we need to call
* xfs_finish_inode_setup() once the inode is fully instantiated at
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index 0e5dba2343ea..144198a6b270 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -286,6 +286,7 @@ xlog_recover_inode_commit_pass2(
struct xfs_log_dinode *ldip;
uint isize;
int need_free = 0;
+ xfs_failaddr_t fa;
if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) {
in_f = item->ri_buf[0].i_addr;
@@ -369,24 +370,26 @@ xlog_recover_inode_commit_pass2(
* superblock flag to determine whether we need to look at di_flushiter
* to skip replay when the on disk inode is newer than the log one
*/
- if (!xfs_has_v3inodes(mp) &&
- ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
- /*
- * Deal with the wrap case, DI_MAX_FLUSH is less
- * than smaller numbers
- */
- if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
- ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
- /* do nothing */
- } else {
- trace_xfs_log_recover_inode_skip(log, in_f);
- error = 0;
- goto out_release;
+ if (!xfs_has_v3inodes(mp)) {
+ if (ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+ /*
+ * Deal with the wrap case, DI_MAX_FLUSH is less
+ * than smaller numbers
+ */
+ if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
+ ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) {
+ /* do nothing */
+ } else {
+ trace_xfs_log_recover_inode_skip(log, in_f);
+ error = 0;
+ goto out_release;
+ }
}
+
+ /* Take the opportunity to reset the flush iteration count */
+ ldip->di_flushiter = 0;
}
- /* Take the opportunity to reset the flush iteration count */
- ldip->di_flushiter = 0;
if (unlikely(S_ISREG(ldip->di_mode))) {
if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
@@ -528,8 +531,19 @@ out_owner_change:
(dip->di_mode != 0))
error = xfs_recover_inode_owner_change(mp, dip, in_f,
buffer_list);
- /* re-generate the checksum. */
+ /* re-generate the checksum and validate the recovered inode. */
xfs_dinode_calc_crc(log->l_mp, dip);
+ fa = xfs_dinode_verify(log->l_mp, in_f->ilf_ino, dip);
+ if (fa) {
+ XFS_CORRUPTION_ERROR(
+ "Bad dinode after recovery",
+ XFS_ERRLEVEL_LOW, mp, dip, sizeof(*dip));
+ xfs_alert(mp,
+ "Metadata corruption detected at %pS, inode 0x%llx",
+ fa, in_f->ilf_ino);
+ error = -EFSCORRUPTED;
+ goto out_release;
+ }
ASSERT(bp->b_mount == mp);
bp->b_flags |= _XBF_LOGRECOVERY;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index a82470e027f7..6c3919687ea6 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1121,23 +1121,25 @@ xfs_ioctl_setattr_xflags(
struct fileattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
+ bool rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
uint64_t i_flags2;
- /* Can't change realtime flag if any extents are allocated. */
- if ((ip->i_df.if_nextents || ip->i_delayed_blks) &&
- XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME))
- return -EINVAL;
+ if (rtflag != XFS_IS_REALTIME_INODE(ip)) {
+ /* Can't change realtime flag if any extents are allocated. */
+ if (ip->i_df.if_nextents || ip->i_delayed_blks)
+ return -EINVAL;
+ }
- /* If realtime flag is set then must have realtime device */
- if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
+ if (rtflag) {
+ /* If realtime flag is set then must have realtime device */
if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
xfs_extlen_to_rtxmod(mp, ip->i_extsize))
return -EINVAL;
- }
- /* Clear reflink if we are actually able to set the rt flag. */
- if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
- ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+ /* Clear reflink if we are actually able to set the rt flag. */
+ if (xfs_is_reflink_inode(ip))
+ ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+ }
/* diflags2 only valid for v3 inodes. */
i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
@@ -1148,6 +1150,14 @@ xfs_ioctl_setattr_xflags(
ip->i_diflags2 = i_flags2;
xfs_diflags_to_iflags(ip, false);
+
+ /*
+ * Make the stable writes flag match that of the device the inode
+ * resides on when flipping the RT flag.
+ */
+ if (rtflag != XFS_IS_REALTIME_INODE(ip) && S_ISREG(VFS_I(ip)->i_mode))
+ xfs_update_stable_writes(ip);
+
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index fdfda4fba12b..a0d77f5f512e 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1299,6 +1299,13 @@ xfs_setup_inode(
mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
/*
+ * For real-time inodes update the stable write flags to that of the RT
+ * device instead of the data device.
+ */
+ if (S_ISREG(inode->i_mode) && XFS_IS_REALTIME_INODE(ip))
+ xfs_update_stable_writes(ip);
+
+ /*
* If there is no attribute fork no ACL can exist on this inode,
* and it can't have any file capabilities attached to it either.
*/
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 51c100c86177..ee206facf0dc 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1893,9 +1893,7 @@ xlog_write_iclog(
* the buffer manually, the code needs to be kept in sync
* with the I/O completion path.
*/
- xlog_state_done_syncing(iclog);
- up(&iclog->ic_sema);
- return;
+ goto sync;
}
/*
@@ -1925,20 +1923,17 @@ xlog_write_iclog(
* avoid shutdown re-entering this path and erroring out again.
*/
if (log->l_targ != log->l_mp->m_ddev_targp &&
- blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) {
- xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
- return;
- }
+ blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev))
+ goto shutdown;
}
if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
iclog->ic_bio.bi_opf |= REQ_FUA;
iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
- if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) {
- xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
- return;
- }
+ if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count))
+ goto shutdown;
+
if (is_vmalloc_addr(iclog->ic_data))
flush_kernel_vmap_range(iclog->ic_data, count);
@@ -1959,6 +1954,12 @@ xlog_write_iclog(
}
submit_bio(&iclog->ic_bio);
+ return;
+shutdown:
+ xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
+sync:
+ xlog_state_done_syncing(iclog);
+ up(&iclog->ic_sema);
}
/*
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 13b94d2e605b..a1e18b24971a 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2511,7 +2511,7 @@ xlog_abort_defer_ops(
list_for_each_entry_safe(dfc, next, capture_list, dfc_list) {
list_del_init(&dfc->dfc_list);
- xfs_defer_ops_capture_free(mp, dfc);
+ xfs_defer_ops_capture_abort(mp, dfc);
}
}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 658edee8381d..e5b62dc28466 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -784,6 +784,7 @@ xfs_reflink_end_cow_extent(
}
}
del = got;
+ xfs_trim_extent(&del, *offset_fsb, end_fsb - *offset_fsb);
/* Grab the corresponding mapping in the data fork. */
nmaps = 1;
generated by cgit v1.2.3 (git 2.39.0) at 2024-08-20 22:47:10 +0300