Merge tag 'refcount-cow-domain-6.1_2022-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.1-fixesAxfs-6.1-fixes-4

xfs: improve runtime refcountbt corruption detection

Fuzz testing of the refcount btree demonstrated a weakness in validation
of refcount btree records during normal runtime.  The idea of using the
upper bit of the rc_startblock field to separate the refcount records
into one group for shared space and another for CoW staging extents was
added at the last minute.  The incore struct left this bit encoded in
the upper bit of the startblock field, which makes it all too easy for
arithmetic operations to overflow if we don't detect the cowflag
properly.

When I ran a norepair fuzz tester, I was able to crash the kernel on one
of these accidental overflows by fuzzing a key record in a node block,
which broke lookups.  To fix the problem, make the domain (shared/cow) a
separate field in the incore record.

Unfortunately, a customer also hit this once in production.  Due to bugs
in the kernel running on the VM host, writes to the disk image would
occasionally be lost.  Given sufficient memory pressure on the VM guest,
a refcountbt xfs_buf could be reclaimed and later reloaded from the
stale copy on the virtual disk.  The stale disk contents were a refcount
btree leaf block full of records for the wrong domain, and this caused
an infinite loop in the guest VM.

v2: actually include the refcount adjust loop invariant checking patch;
    move the deferred refcount continuation checks earlier in the series;
    break up the megapatch into smaller pieces; fix an uninitialized list
    error.
v3: in the continuation check patch, verify the per-ag extent before
    converting it to a fsblock

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

* tag 'refcount-cow-domain-6.1_2022-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: rename XFS_REFC_COW_START to _COWFLAG
  xfs: fix uninitialized list head in struct xfs_refcount_recovery
  xfs: fix agblocks check in the cow leftover recovery function
  xfs: check record domain when accessing refcount records
  xfs: remove XFS_FIND_RCEXT_SHARED and _COW
  xfs: refactor domain and refcount checking
  xfs: report refcount domain in tracepoints
  xfs: track cow/shared record domains explicitly in xfs_refcount_irec
  xfs: refactor refcount record usage in xchk_refcountbt_rec
  xfs: move _irec structs to xfs_types.h
  xfs: check deferred refcount op continuation parameters
  xfs: create a predicate to verify per-AG extents
  xfs: make sure aglen never goes negative in xfs_refcount_adjust_extents

1 files changed, 39 insertions, 9 deletions

diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index cb7c81ba7fa3..372d871bccc5 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -799,6 +799,9 @@ TRACE_DEFINE_ENUM(PE_SIZE_PTE);
 TRACE_DEFINE_ENUM(PE_SIZE_PMD);
 TRACE_DEFINE_ENUM(PE_SIZE_PUD);
 
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED);
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW);
+
 TRACE_EVENT(xfs_filemap_fault,
 	TP_PROTO(struct xfs_inode *ip, enum page_entry_size pe_size,
 		 bool write_fault),
@@ -2925,6 +2928,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, domain)
 		__field(xfs_agblock_t, startblock)
 		__field(xfs_extlen_t, blockcount)
 		__field(xfs_nlink_t, refcount)
@@ -2932,13 +2936,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
 		__entry->refcount = irec->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->startblock,
 		  __entry->blockcount,
 		  __entry->refcount)
@@ -2958,6 +2964,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, domain)
 		__field(xfs_agblock_t, startblock)
 		__field(xfs_extlen_t, blockcount)
 		__field(xfs_nlink_t, refcount)
@@ -2966,14 +2973,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->domain = irec->rc_domain;
 		__entry->startblock = irec->rc_startblock;
 		__entry->blockcount = irec->rc_blockcount;
 		__entry->refcount = irec->rc_refcount;
 		__entry->agbno = agbno;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->startblock,
 		  __entry->blockcount,
 		  __entry->refcount,
@@ -2994,9 +3003,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, i1_domain)
 		__field(xfs_agblock_t, i1_startblock)
 		__field(xfs_extlen_t, i1_blockcount)
 		__field(xfs_nlink_t, i1_refcount)
+		__field(enum xfs_refc_domain, i2_domain)
 		__field(xfs_agblock_t, i2_startblock)
 		__field(xfs_extlen_t, i2_blockcount)
 		__field(xfs_nlink_t, i2_refcount)
@@ -3004,20 +3015,24 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
 		__entry->i1_refcount = i1->rc_refcount;
+		__entry->i2_domain = i2->rc_domain;
 		__entry->i2_startblock = i2->rc_startblock;
 		__entry->i2_blockcount = i2->rc_blockcount;
 		__entry->i2_refcount = i2->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i1_startblock,
 		  __entry->i1_blockcount,
 		  __entry->i1_refcount,
+		  __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i2_startblock,
 		  __entry->i2_blockcount,
 		  __entry->i2_refcount)
@@ -3038,9 +3053,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, i1_domain)
 		__field(xfs_agblock_t, i1_startblock)
 		__field(xfs_extlen_t, i1_blockcount)
 		__field(xfs_nlink_t, i1_refcount)
+		__field(enum xfs_refc_domain, i2_domain)
 		__field(xfs_agblock_t, i2_startblock)
 		__field(xfs_extlen_t, i2_blockcount)
 		__field(xfs_nlink_t, i2_refcount)
@@ -3049,21 +3066,25 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
 		__entry->i1_refcount = i1->rc_refcount;
+		__entry->i2_domain = i2->rc_domain;
 		__entry->i2_startblock = i2->rc_startblock;
 		__entry->i2_blockcount = i2->rc_blockcount;
 		__entry->i2_refcount = i2->rc_refcount;
 		__entry->agbno = agbno;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i1_startblock,
 		  __entry->i1_blockcount,
 		  __entry->i1_refcount,
+		  __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i2_startblock,
 		  __entry->i2_blockcount,
 		  __entry->i2_refcount,
@@ -3086,12 +3107,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, i1_domain)
 		__field(xfs_agblock_t, i1_startblock)
 		__field(xfs_extlen_t, i1_blockcount)
 		__field(xfs_nlink_t, i1_refcount)
+		__field(enum xfs_refc_domain, i2_domain)
 		__field(xfs_agblock_t, i2_startblock)
 		__field(xfs_extlen_t, i2_blockcount)
 		__field(xfs_nlink_t, i2_refcount)
+		__field(enum xfs_refc_domain, i3_domain)
 		__field(xfs_agblock_t, i3_startblock)
 		__field(xfs_extlen_t, i3_blockcount)
 		__field(xfs_nlink_t, i3_refcount)
@@ -3099,27 +3123,33 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
 		__entry->agno = agno;
+		__entry->i1_domain = i1->rc_domain;
 		__entry->i1_startblock = i1->rc_startblock;
 		__entry->i1_blockcount = i1->rc_blockcount;
 		__entry->i1_refcount = i1->rc_refcount;
+		__entry->i2_domain = i2->rc_domain;
 		__entry->i2_startblock = i2->rc_startblock;
 		__entry->i2_blockcount = i2->rc_blockcount;
 		__entry->i2_refcount = i2->rc_refcount;
+		__entry->i3_domain = i3->rc_domain;
 		__entry->i3_startblock = i3->rc_startblock;
 		__entry->i3_blockcount = i3->rc_blockcount;
 		__entry->i3_refcount = i3->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u -- "
-		  "agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+		  "dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i1_startblock,
 		  __entry->i1_blockcount,
 		  __entry->i1_refcount,
+		  __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i2_startblock,
 		  __entry->i2_blockcount,
 		  __entry->i2_refcount,
+		  __print_symbolic(__entry->i3_domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->i3_startblock,
 		  __entry->i3_blockcount,
 		  __entry->i3_refcount)