Introduce xfs_notify_failure.c to handle failure related works, such as
implement ->notify_failure(), register/unregister dax holder in xfs, and
so on.
If the rmap feature of XFS enabled, we can query it to find files and
metadata which are associated with the corrupt data. For now all we do
is kill processes with that file mapped into their address spaces, but
future patches could actually do something about corrupt metadata.
After that, the memory failure needs to notify the processes who are
using those files.
Signed-off-by: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx>
---
fs/xfs/Makefile | 5 +
fs/xfs/xfs_buf.c | 7 +-
fs/xfs/xfs_fsops.c | 3 +
fs/xfs/xfs_mount.h | 1 +
fs/xfs/xfs_notify_failure.c | 219 ++++++++++++++++++++++++++++++++++++
fs/xfs/xfs_super.h | 1 +
6 files changed, 233 insertions(+), 3 deletions(-)
create mode 100644 fs/xfs/xfs_notify_failure.c
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 04611a1068b4..09f5560e29f2 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -128,6 +128,11 @@ xfs-$(CONFIG_SYSCTL) += xfs_sysctl.o
xfs-$(CONFIG_COMPAT) += xfs_ioctl32.o
xfs-$(CONFIG_EXPORTFS_BLOCK_OPS) += xfs_pnfs.o
+# notify failure
+ifeq ($(CONFIG_MEMORY_FAILURE),y)
+xfs-$(CONFIG_FS_DAX) += xfs_notify_failure.o
+endif
+
# online scrub/repair
ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index f9ca08398d32..9064b8dfbc66 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -5,6 +5,7 @@
*/
#include "xfs.h"
#include <linux/backing-dev.h>
+#include <linux/dax.h>
#include "xfs_shared.h"
#include "xfs_format.h"
@@ -1911,7 +1912,7 @@ xfs_free_buftarg(
list_lru_destroy(&btp->bt_lru);
blkdev_issue_flush(btp->bt_bdev);
- fs_put_dax(btp->bt_daxdev, NULL);
+ fs_put_dax(btp->bt_daxdev, btp->bt_mount);
kmem_free(btp);
}
@@ -1964,8 +1965,8 @@ xfs_alloc_buftarg(
btp->bt_mount = mp;
btp->bt_dev = bdev->bd_dev;
btp->bt_bdev = bdev;
- btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, NULL,
- NULL);
+ btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off, mp,
+ &xfs_dax_holder_operations);
/*
* Buffer IO error rate limiting. Limit it to no more than 10 messages
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 68f74549fa22..56530900bb86 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -536,6 +536,9 @@ xfs_do_force_shutdown(
} else if (flags & SHUTDOWN_CORRUPT_INCORE) {
tag = XFS_PTAG_SHUTDOWN_CORRUPT;
why = "Corruption of in-memory data";
+ } else if (flags & SHUTDOWN_CORRUPT_ONDISK) {
+ tag = XFS_PTAG_SHUTDOWN_CORRUPT;
+ why = "Corruption of on-disk metadata";
} else {
tag = XFS_PTAG_SHUTDOWN_IOERROR;
why = "Metadata I/O Error";
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index f6dc19de8322..9237cc159542 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -435,6 +435,7 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
#define SHUTDOWN_LOG_IO_ERROR 0x0002 /* write attempt to the log failed */
#define SHUTDOWN_FORCE_UMOUNT 0x0004 /* shutdown from a forced unmount */
#define SHUTDOWN_CORRUPT_INCORE 0x0008 /* corrupt in-memory data structures */
+#define SHUTDOWN_CORRUPT_ONDISK 0x0010 /* corrupt metadata on device */
#define XFS_SHUTDOWN_STRINGS \
{ SHUTDOWN_META_IO_ERROR, "metadata_io" }, \
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
new file mode 100644
index 000000000000..aac44f54feb4
--- /dev/null
+++ b/fs/xfs/xfs_notify_failure.c
@@ -0,0 +1,219 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Fujitsu. All Rights Reserved.
+ */
+
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_alloc.h"
+#include "xfs_bit.h"
+#include "xfs_btree.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_rtalloc.h"
+#include "xfs_trans.h"
+
+#include <linux/mm.h>
+#include <linux/dax.h>
+
+struct failure_info {
+ xfs_agblock_t startblock;
+ xfs_extlen_t blockcount;
+ int mf_flags;
+};
+
+static pgoff_t
+xfs_failure_pgoff(
+ struct xfs_mount *mp,
+ const struct xfs_rmap_irec *rec,
+ const struct failure_info *notify)
+{
+ uint64_t pos = rec->rm_offset;
+
+ if (notify->startblock > rec->rm_startblock)
+ pos += XFS_FSB_TO_B(mp,
+ notify->startblock - rec->rm_startblock);
+ return pos >> PAGE_SHIFT;
+}
+
+static unsigned long
+xfs_failure_pgcnt(
+ struct xfs_mount *mp,
+ const struct xfs_rmap_irec *rec,
+ const struct failure_info *notify)
+{
+ xfs_agblock_t end_rec;
+ xfs_agblock_t end_notify;
+ xfs_agblock_t start_cross;
+ xfs_agblock_t end_cross;
+
+ start_cross = max(rec->rm_startblock, notify->startblock);
+
+ end_rec = rec->rm_startblock + rec->rm_blockcount;
+ end_notify = notify->startblock + notify->blockcount;
+ end_cross = min(end_rec, end_notify);
+
+ return XFS_FSB_TO_B(mp, end_cross - start_cross) >> PAGE_SHIFT;
+}
+
+static int
+xfs_dax_failure_fn(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *rec,
+ void *data)
+{
+ struct xfs_mount *mp = cur->bc_mp;
+ struct xfs_inode *ip;
+ struct failure_info *notify = data;
+ int error = 0;
+
+ if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
+ (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
+ return -EFSCORRUPTED;
+ }
+
+ /* Get files that incore, filter out others that are not in use. */
+ error = xfs_iget(mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE,
+ 0, &ip);
+ /* Continue the rmap query if the inode isn't incore */
+ if (error == -ENODATA)
+ return 0;
+ if (error)
+ return error;
+
+ error = mf_dax_kill_procs(VFS_I(ip)->i_mapping,
+ xfs_failure_pgoff(mp, rec, notify),
+ xfs_failure_pgcnt(mp, rec, notify),
+ notify->mf_flags);
+ xfs_irele(ip);
+ return error;
+}
+
+static int
+xfs_dax_notify_ddev_failure(
+ struct xfs_mount *mp,
+ xfs_daddr_t daddr,
+ xfs_daddr_t bblen,
+ int mf_flags)
+{
+ struct xfs_trans *tp = NULL;
+ struct xfs_btree_cur *cur = NULL;
+ struct xfs_buf *agf_bp = NULL;
+ int error = 0;
+ xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr);
+ xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno);
+ xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen);
+ xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno);
+
+ error = xfs_trans_alloc_empty(mp, &tp);
+ if (error)
+ return error;
+
+ for (; agno <= end_agno; agno++) {
+ struct xfs_rmap_irec ri_low = { };
+ struct xfs_rmap_irec ri_high;
+ struct failure_info notify;
+ struct xfs_agf *agf;
+ xfs_agblock_t agend;
+
+ error = xfs_alloc_read_agf(mp, tp, agno, 0, &agf_bp);
+ if (error)
+ break;
+
+ cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, agf_bp->b_pag);
+
+ /*
+ * Set the rmap range from ri_low to ri_high, which represents
+ * a [start, end] where we looking for the files or metadata.
+ * The part of range out of a AG will be ignored. So, it's fine
+ * to set ri_low to "startblock" in all loops. When it reaches
+ * the last AG, set the ri_high to "endblock" to make sure we
+ * actually end at the end.
+ */
+ memset(&ri_high, 0xFF, sizeof(ri_high));
+ ri_low.rm_startblock = XFS_FSB_TO_AGBNO(mp, fsbno);
+ if (agno == end_agno)
+ ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno);
+
+ agf = agf_bp->b_addr;
+ agend = min(be32_to_cpu(agf->agf_length),
+ ri_high.rm_startblock);
+ notify.startblock = ri_low.rm_startblock;
+ notify.blockcount = agend - ri_low.rm_startblock;
+
+ error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
+ xfs_dax_failure_fn, ¬ify);
+ xfs_btree_del_cursor(cur, error);
+ xfs_trans_brelse(tp, agf_bp);
+ if (error)
+ break;
+
+ fsbno = XFS_AGB_TO_FSB(mp, agno + 1, 0);
+ }
+
+ xfs_trans_cancel(tp);
+ return error;
+}
+
+static int
+xfs_dax_notify_failure(
+ struct dax_device *dax_dev,
+ u64 offset,
+ u64 len,
+ int mf_flags)
+{
+ struct xfs_mount *mp = dax_holder(dax_dev);
+ u64 ddev_start;
+ u64 ddev_end;
+
+ if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) {
+ xfs_warn(mp,
+ "notify_failure() not supported on realtime device!");
+ return -EOPNOTSUPP;
+ }
+
+ if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
+ mp->m_logdev_targp != mp->m_ddev_targp) {
+ xfs_err(mp, "ondisk log corrupt, shutting down fs!");
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
+ return -EFSCORRUPTED;
+ }
+
+ if (!xfs_has_rmapbt(mp)) {
+ xfs_warn(mp, "notify_failure() needs rmapbt enabled!");
+ return -EOPNOTSUPP;
+ }
+
+ ddev_start = mp->m_ddev_targp->bt_dax_part_off;
+ ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
+
+ /* Ignore the range out of filesystem area */
+ if (offset + len < ddev_start)
+ return -ENXIO;
+ if (offset > ddev_end)
+ return -ENXIO;
+
+ /* Calculate the real range when it touches the boundary */
+ if (offset > ddev_start)
+ offset -= ddev_start;
+ else {
+ len -= ddev_start - offset;
+ offset = 0;
+ }
+ if (offset + len > ddev_end)
+ len -= ddev_end - offset;
+
+ return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
+ mf_flags);
+}
+
+const struct dax_holder_operations xfs_dax_holder_operations = {
+ .notify_failure = xfs_dax_notify_failure,
+};
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index 167d23f92ffe..27ab5087d0b3 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -93,6 +93,7 @@ extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
extern const struct export_operations xfs_export_operations;
extern const struct xattr_handler *xfs_xattr_handlers[];
extern const struct quotactl_ops xfs_quotactl_operations;
+extern const struct dax_holder_operations xfs_dax_holder_operations;
extern void xfs_reinit_percpu_counters(struct xfs_mount *mp);
--
2.35.1
