Clean up RAIDZ/DRAID ereport code

The RAIDZ and DRAID code is responsible for reporting checksum errors on
their child vdevs.  Checksum errors represent events where a disk
returned data or parity that should have been correct, but was not.  In
other words, these are instances of silent data corruption.  The
checksum errors show up in the vdev stats (and thus `zpool status`'s
CKSUM column), and in the event log (`zpool events`).

Note, this is in contrast with the more common "noisy" errors where a
disk goes offline, in which case ZFS knows that the disk is bad and
doesn't try to read it, or the device returns an error on the requested
read or write operation.

RAIDZ/DRAID generate checksum errors via three code paths:

1. When RAIDZ/DRAID reconstructs a damaged block, checksum errors are
reported on any children whose data was not used during the
reconstruction.  This is handled in `raidz_reconstruct()`.  This is the
most common type of RAIDZ/DRAID checksum error.

2. When RAIDZ/DRAID is not able to reconstruct a damaged block, that
means that the data has been lost.  The zio fails and an error is
returned to the consumer (e.g. the read(2) system call).  This would
happen if, for example, three different disks in a RAIDZ2 group are
silently damaged.  Since the damage is silent, it isn't possible to know
which three disks are damaged, so a checksum error is reported against
every child that returned data or parity for this read.  (For DRAID,
typically only one "group" of children is involved in each io.)  This
case is handled in `vdev_raidz_cksum_finish()`. This is the next most
common type of RAIDZ/DRAID checksum error.

3. If RAIDZ/DRAID is not able to reconstruct a damaged block (like in
case 2), but there happens to be additional copies of this block due to
"ditto blocks" (i.e. multiple DVA's in this blkptr_t), and one of those
copies is good, then RAIDZ/DRAID compares each sector of the data or
parity that it retrieved with the good data from the other DVA, and if
they differ then it reports a checksum error on this child.  This
differs from case 2 in that the checksum error is reported on only the
subset of children that actually have bad data or parity.  This case
happens very rarely, since normally only metadata has ditto blocks.  If
the silent damage is extensive, there will be many instances of case 2,
and the pool will likely be unrecoverable.

The code for handling case 3 is considerably more complicated than the
other cases, for two reasons:

1. It needs to run after the main raidz read logic has completed.  The
data RAIDZ read needs to be preserved until after the alternate DVA has
been read, which necessitates refcounts and callbacks managed by the
non-raidz-specific zio layer.

2. It's nontrivial to map the sections of data read by RAIDZ to the
correct data.  For example, the correct data does not include the parity
information, so the parity must be recalculated based on the correct
data, and then compared to the parity that was read from the RAIDZ
children.

Due to the complexity of case 3, the rareness of hitting it, and the
minimal benefit it provides above case 2, this commit removes the code
for case 3.  These types of errors will now be handled the same as case
2, i.e. the checksum error will be reported against all children that
returned data or parity.

Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Matthew Ahrens <[email protected]>
Closes #11735 

3 files changed, 6 insertions, 12 deletions

diff --git a/include/sys/vdev_raidz.h b/include/sys/vdev_raidz.h
index 029fdef5f..ee597eb0d 100644
--- a/include/sys/vdev_raidz.h
+++ b/include/sys/vdev_raidz.h
@@ -50,6 +50,8 @@ void vdev_raidz_reconstruct(struct raidz_map *, const int *, int);
 void vdev_raidz_child_done(zio_t *);
 void vdev_raidz_io_done(zio_t *);
 
+extern const zio_vsd_ops_t vdev_raidz_vsd_ops;
+
 /*
  * vdev_raidz_math interface
  */
diff --git a/include/sys/vdev_raidz_impl.h b/include/sys/vdev_raidz_impl.h
index ada12c0a7..b94d59eb7 100644
--- a/include/sys/vdev_raidz_impl.h
+++ b/include/sys/vdev_raidz_impl.h
@@ -108,8 +108,7 @@ typedef struct raidz_col {
 	uint64_t rc_size;		/* I/O size */
 	abd_t rc_abdstruct;		/* rc_abd probably points here */
 	abd_t *rc_abd;			/* I/O data */
-	void *rc_orig_data;		/* pre-reconstruction */
-	abd_t *rc_gdata;		/* used to store the "good" version */
+	abd_t *rc_orig_data;		/* pre-reconstruction */
 	int rc_error;			/* I/O error for this device */
 	uint8_t rc_tried;		/* Did we attempt this I/O column? */
 	uint8_t rc_skipped;		/* Did we skip this I/O column? */
@@ -124,7 +123,6 @@ typedef struct raidz_row {
 	uint64_t rr_missingdata;	/* Count of missing data devices */
 	uint64_t rr_missingparity;	/* Count of missing parity devices */
 	uint64_t rr_firstdatacol;	/* First data column/parity count */
-	abd_t *rr_abd_copy;		/* rm_asize-buffer of copied data */
 	abd_t *rr_abd_empty;		/* dRAID empty sector buffer */
 	int rr_nempty;			/* empty sectors included in parity */
 #ifdef ZFS_DEBUG
@@ -135,8 +133,6 @@ typedef struct raidz_row {
 } raidz_row_t;
 
 typedef struct raidz_map {
-	uintptr_t rm_reports;		/* # of referencing checksum reports */
-	boolean_t rm_freed;		/* map no longer has referencing ZIO */
 	boolean_t rm_ecksuminjected;	/* checksum error was injected */
 	int rm_nrows;			/* Regular row count */
 	int rm_nskip;			/* RAIDZ sectors skipped for padding */
diff --git a/include/sys/zio.h b/include/sys/zio.h
index 334ca064b..372855013 100644
--- a/include/sys/zio.h
+++ b/include/sys/zio.h
@@ -382,14 +382,8 @@ struct zio_cksum_report {
 	struct zio_bad_cksum	*zcr_ckinfo;	/* information from failure */
 };
 
-typedef void zio_vsd_cksum_report_f(zio_t *zio, zio_cksum_report_t *zcr,
-    void *arg);
-
-zio_vsd_cksum_report_f	zio_vsd_default_cksum_report;
-
 typedef struct zio_vsd_ops {
 	zio_done_func_t		*vsd_free;
-	zio_vsd_cksum_report_f	*vsd_cksum_report;
 } zio_vsd_ops_t;
 
 typedef struct zio_gang_node {
@@ -683,7 +677,7 @@ extern hrtime_t zio_handle_io_delay(zio_t *zio);
  */
 extern int zfs_ereport_start_checksum(spa_t *spa, vdev_t *vd,
     const zbookmark_phys_t *zb, struct zio *zio, uint64_t offset,
-    uint64_t length, void *arg, struct zio_bad_cksum *info);
+    uint64_t length, struct zio_bad_cksum *info);
 extern void zfs_ereport_finish_checksum(zio_cksum_report_t *report,
     const abd_t *good_data, const abd_t *bad_data, boolean_t drop_if_identical);
 
@@ -695,6 +689,8 @@ extern int zfs_ereport_post_checksum(spa_t *spa, vdev_t *vd,
     uint64_t length, const abd_t *good_data, const abd_t *bad_data,
     struct zio_bad_cksum *info);
 
+void zio_vsd_default_cksum_report(zio_t *zio, zio_cksum_report_t *zcr);
+
 /* Called from spa_sync(), but primarily an injection handler */
 extern void spa_handle_ignored_writes(spa_t *spa);