xfs: implement online scrubbing of rtsummary infoscrub-rtsummary_2021-09-17

Finish the realtime summary scrubber by adding the functions we need to
compute a fresh copy of the rtsummary info and comparing it to the copy
on disk.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>

7 files changed, 258 insertions, 27 deletions

diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 645e22b5d0b8..bc0e78c91f38 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -85,10 +85,16 @@ int xchk_setup_xattr(struct xfs_scrub *sc);
 int xchk_setup_symlink(struct xfs_scrub *sc);
 int xchk_setup_parent(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
-int xchk_setup_rt(struct xfs_scrub *sc);
+int xchk_setup_rtbitmap(struct xfs_scrub *sc);
+int xchk_setup_rtsummary(struct xfs_scrub *sc);
 #else
 static inline int
-xchk_setup_rt(struct xfs_scrub *sc)
+xchk_setup_rtbitmap(struct xfs_scrub *sc)
+{
+	return -ENOENT;
+}
+static inline int
+xchk_setup_rtsummary(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 3a84545561e8..c04f4d552d56 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -19,12 +19,12 @@
 
 /* Set us up with the realtime metadata locked. */
 int
-xchk_setup_rt(
+xchk_setup_rtbitmap(
 	struct xfs_scrub	*sc)
 {
 	int			error;
 
-	error = xchk_setup_fs(sc);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/scrub/rtsummary.c b/fs/xfs/scrub/rtsummary.c
index 1a3d5a8b010c..c4cfd4e2ebb3 100644
--- a/fs/xfs/scrub/rtsummary.c
+++ b/fs/xfs/scrub/rtsummary.c
@@ -14,41 +14,220 @@
 #include "xfs_trans.h"
 #include "xfs_rtalloc.h"
 #include "xfs_inode.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/xfile.h"
 
-/* Scrub the realtime summary. */
+/*
+ * Realtime Summary
+ * ================
+ *
+ * We check the realtime summary by scanning the realtime bitmap file to create
+ * a new summary file incore, and then we compare the computed version against
+ * the ondisk version.  We use the 'xfile' functionality to store this
+ * (potentially large) amount of data in pageable memory.
+ */
+
+/* Set us up to check the rtsummary file. */
 int
-xchk_rtsummary(
+xchk_setup_rtsummary(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_inode	*rsumip = sc->mp->m_rsumip;
-	struct xfs_inode	*old_ip = sc->ip;
-	uint			old_ilock_flags = sc->ilock_flags;
-	int			error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
+
+	/*
+	 * Create an xfile to construct a new rtsummary file.  The xfile allows
+	 * us to avoid pinning kernel memory for this purpose.
+	 */
+	sc->xfile = xfile_create("rtsummary", mp->m_rsumsize);
+	if (IS_ERR(sc->xfile))
+		return PTR_ERR(sc->xfile);
+
+	error = xchk_trans_alloc(sc, 0);
+	if (error)
+		return error;
+
+	/* Allocate a memory buffer for the summary comparison. */
+	sc->buf = kvmalloc(sc->mp->m_sb.sb_blocksize,
+			GFP_KERNEL | __GFP_NOWARN | __GFP_RETRY_MAYFAIL);
+	if (!sc->buf)
+		return -ENOMEM;
+
+	error = xchk_install_inode(sc, sc->mp->m_rsumip);
+	if (error)
+		return error;
 
 	/*
-	 * We ILOCK'd the rt bitmap ip in the setup routine, now lock the
-	 * rt summary ip in compliance with the rt inode locking rules.
-	 *
-	 * Since we switch sc->ip to rsumip we have to save the old ilock
-	 * flags so that we don't mix up the inode state that @sc tracks.
+	 * Locking order requires us to take the rtbitmap first.  We must be
+	 * careful to unlock it ourselves when we are done with the rtbitmap
+	 * file since the scrub infrastructure won't do that for us...
 	 */
-	sc->ip = rsumip;
+	xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
+
+	/* ...and then we can lock the rtsummary inode. */
 	sc->ilock_flags = XFS_ILOCK_EXCL | XFS_ILOCK_RTSUM;
 	xfs_ilock(sc->ip, sc->ilock_flags);
+	return 0;
+}
+
+/* Update the summary file to reflect the free extent that we've accumulated. */
+STATIC int
+xchk_rtsum_record_free(
+	struct xfs_trans		*tp,
+	const struct xfs_rtalloc_rec	*rec,
+	void				*priv)
+{
+	struct xfs_scrub		*sc = priv;
+	struct xfs_mount		*mp = sc->mp;
+	xfs_rtblock_t			rbmoff;
+	unsigned int			offs;
+	unsigned int			lenlog;
+	xfs_suminfo_t			v = 0;
+	int				error = 0;
+
+	if (xchk_should_terminate(sc, &error))
+		return error;
+
+	/* Compute the relevant location in the rtsum file. */
+	rbmoff = XFS_BITTOBLOCK(mp, rec->ar_startext);
+	lenlog = XFS_RTBLOCKLOG(rec->ar_extcount);
+	offs = XFS_SUMOFFS(mp, lenlog, rbmoff);
+
+	if (!xfs_verify_rtext(mp, rec->ar_startext, rec->ar_extcount)) {
+		xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
+		return -EFSCORRUPTED;
+	}
+
+	/* Read current rtsummary contents. */
+	error = xfile_pread(sc->xfile, &v, sizeof(xfs_suminfo_t),
+			sizeof(xfs_suminfo_t) * offs);
+	if (error)
+		return error;
+
+	/* Bump the summary count... */
+	v++;
+	trace_xchk_rtsum_record_free(mp, rec->ar_startext, rec->ar_extcount,
+			lenlog, offs, v);
+
+	/* ...and write it back. */
+	error = xfile_pwrite(sc->xfile, &v, sizeof(xfs_suminfo_t),
+			sizeof(xfs_suminfo_t) * offs);
+	if (error)
+		return error;
+
+	return 0;
+}
+
+/* Compute the realtime summary from the realtime bitmap. */
+STATIC int
+xchk_rtsum_compute(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	unsigned long long	rtbmp_bytes;
+
+	/* If the bitmap size doesn't match the computed size, bail. */
+	rtbmp_bytes = howmany_64(mp->m_sb.sb_rextents, NBBY);
+	if (roundup_64(rtbmp_bytes, mp->m_sb.sb_blocksize) !=
+			mp->m_rbmip->i_disk_size)
+		return -EFSCORRUPTED;
+
+	return xfs_rtalloc_query_all(sc->tp, xchk_rtsum_record_free, sc);
+}
+
+/* Compare the rtsummary file against the one we computed. */
+STATIC int
+xchk_rtsum_compare(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	struct xfs_bmbt_irec	map;
+	xfs_rtblock_t		off;
+	loff_t			pos;
+	int			nmap;
+	int			error = 0;
+
+	for (off = 0, pos = 0;
+	     pos < mp->m_rsumsize;
+	     pos += mp->m_sb.sb_blocksize, off++) {
+		size_t		count;
+
+		if (xchk_should_terminate(sc, &error) ||
+		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
+			break;
+
+		/* Make sure we have a written extent. */
+		nmap = 1;
+		error = xfs_bmapi_read(mp->m_rsumip, off, 1, &map, &nmap,
+				XFS_DATA_FORK);
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
+			break;
+
+		if (nmap != 1 || !xfs_bmap_is_written_extent(&map)) {
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+			break;
+		}
+
+		/* Read a block's worth of ondisk rtsummary file. */
+		error = xfs_rtbuf_get(mp, sc->tp, off, 1, &bp);
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, off, &error))
+			break;
+
+		/* Read a block's worth of computed rtsummary file. */
+		count = min_t(loff_t, mp->m_rsumsize - pos,
+				mp->m_sb.sb_blocksize);
+		error = xfile_pread(sc->xfile, sc->buf, count, pos);
+		if (error) {
+			xfs_trans_brelse(sc->tp, bp);
+			break;
+		}
+
+		if (memcmp(bp->b_addr, sc->buf, count) != 0)
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, off);
+
+		xfs_trans_brelse(sc->tp, bp);
+	}
+
+	return error;
+}
+
+/* Scrub the realtime summary. */
+int
+xchk_rtsummary(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	int			error = 0;
 
 	/* Invoke the fork scrubber. */
 	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
-		goto out;
-
-	/* XXX: implement this some day */
-	xchk_set_incomplete(sc);
-out:
-	/* Switch back to the rtbitmap inode and lock flags. */
-	xfs_iunlock(sc->ip, sc->ilock_flags);
-	sc->ilock_flags = old_ilock_flags;
-	sc->ip = old_ip;
+		goto out_rbm;
+
+	/* Construct the new summary file from the rtbitmap. */
+	error = xchk_rtsum_compute(sc);
+	if (error == -EFSCORRUPTED) {
+		/*
+		 * EFSCORRUPTED means the rtbitmap is corrupt, which is an xref
+		 * error since we're checking the summary file.
+		 */
+		xchk_ino_xref_set_corrupt(sc, mp->m_rbmip->i_ino);
+		error = 0;
+		goto out_rbm;
+	}
+	if (error)
+		goto out_rbm;
+
+	/* Does the computed summary file match the actual rtsummary file? */
+	error = xchk_rtsum_compare(sc);
+
+out_rbm:
+	/* Unlock the rtbitmap since we're done with it. */
+	xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 	return error;
 }
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 6381cbb5fad2..7d1837bc997d 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -24,6 +24,7 @@
 #include "scrub/trace.h"
 #include "scrub/repair.h"
 #include "scrub/health.h"
+#include "scrub/xfile.h"
 
 /*
  * Online Scrub and Repair
@@ -175,6 +176,10 @@ xchk_teardown(
 		mutex_unlock(&sc->mp->m_quotainfo->qi_quotaofflock);
 		sc->flags &= ~XCHK_HAS_QUOTAOFFLOCK;
 	}
+	if (sc->xfile) {
+		xfile_destroy(sc->xfile);
+		sc->xfile = NULL;
+	}
 	if (sc->buf) {
 		kmem_free(sc->buf);
 		sc->buf = NULL;
@@ -304,14 +309,14 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
-		.setup	= xchk_setup_rt,
+		.setup	= xchk_setup_rtbitmap,
 		.scrub	= xchk_rtbitmap,
 		.has	= xfs_has_realtime,
 		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
-		.setup	= xchk_setup_rt,
+		.setup	= xchk_setup_rtsummary,
 		.scrub	= xchk_rtsummary,
 		.has	= xfs_has_realtime,
 		.repair	= xrep_notsupported,
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 820de2121e5d..e04984ff97aa 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -69,7 +69,13 @@ struct xfs_scrub {
 	 */
 	struct xfs_inode		*ip;
 
+	/* Kernel memory buffer used by scrubbers; freed at teardown. */
 	void				*buf;
+
+	/* xfile used by the scrubbers; freed at teardown. */
+	struct xfile			*xfile;
+
+	/* Lock flags for @ip. */
 	uint				ilock_flags;
 
 	/* See the XCHK/XREP state flags below. */
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index e92f6c0502a9..f3c7f04ad9bc 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -762,6 +762,38 @@ TRACE_EVENT(xfbma_sort_stats,
 		  __entry->error)
 );
 
+TRACE_EVENT(xchk_rtsum_record_free,
+	TP_PROTO(struct xfs_mount *mp, xfs_rtblock_t start,
+		 uint64_t len, unsigned int log, loff_t pos, xfs_suminfo_t v),
+	TP_ARGS(mp, start, len, log, pos, v),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, rtdev)
+		__field(xfs_rtblock_t, start)
+		__field(unsigned long long, len)
+		__field(unsigned int, log)
+		__field(loff_t, pos)
+		__field(xfs_suminfo_t, v)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rtdev = mp->m_rtdev_targp->bt_dev;
+		__entry->start = start;
+		__entry->len = len;
+		__entry->log = log;
+		__entry->pos = pos;
+		__entry->v = v;
+	),
+	TP_printk("dev %d:%d rtdev %d:%d rtx 0x%llx rtxcount 0x%llx log %u rsumpos 0x%llx sumcount %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->rtdev), MINOR(__entry->rtdev),
+		  __entry->start,
+		  __entry->len,
+		  __entry->log,
+		  __entry->pos,
+		  __entry->v)
+)
+
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 31c96f477738..d7dd43b0678f 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -22,6 +22,9 @@
  * daddr: physical block number in 512b blocks
  * bbcount: number of blocks in a physical extent, in 512b blocks
  *
+ * rtx: physical rt extent number for extent mappings
+ * rtxcount: number of rt extents in an extent mapping
+ *
  * owner: reverse-mapping owner, usually inodes
  *
  * fileoff: file offset, in fs blocks