MFC r305328: MFV r303081: 7163 ztest failures due to excess error injection

illumos/illumos-gate@f34284d835bc555f987c1310df46c034c3101155
https://github.com/illumos/illumos-gate/commit/f34284d835bc555f987c1310df46c034c
3101155

https://www.illumos.org/issues/7163
  Running zloop from zfs-precommit hit this assertion:
       *panicstr/s
  0xfffffd7fd7419370: assertion failed for thread 0xfffffd7fe29ed240,
  thread-id 577: parent != NULL, file ../../../uts/common/fs/zfs/dbuf.c, line
  1827
       $c
  libc.so.1`_lwp_kill+0xa()
  libc.so.1`_assfail+0x182(fffffd7ffb1c29fa, fffffd7ffb1cc028, 723)
  libc.so.1`assfail+0x19(fffffd7ffb1c29fa, fffffd7ffb1cc028, 723)
  libzpool.so.1`dbuf_dirty+0xc69(10e3bc10, 3601700)
  libzpool.so.1`dbuf_dirty+0x61e(10c73640, 3601700)
  libzpool.so.1`dbuf_dirty+0x61e(10e28280, 3601700)
  libzpool.so.1`dmu_buf_will_fill+0x64(10e28280, 3601700)
  libzpool.so.1`dmu_write+0x1b6(2c7e640, d, 400000002e000000, 200, 3717b40,
  3601700)
  ztest_replay_write+0x568(4950d0, 3717a80, 0)
  ztest_write+0x125(4950d0, d, 400000002e000000, 200, 413f000)
  ztest_io+0x1bb(4950d0, d, 400000002e000000)
  ztest_dmu_write_parallel+0xaa(4950d0, 6)
  ztest_execute+0x83(1, 420c98, 6)
  ztest_thread+0xf4(6)
  libc.so.1`_thrp_setup+0x8a(fffffd7fe29ed240)
  libc.so.1`_lwp_start()
  This is another manifestation of ECKSUM in ztest:
  The lowest level ancestor that’s in memory is the L8 (topmost). The L7
  ancestor is blkid 0x10:
       ::dbufs -O 0x2c7e640 -o d -l 7 |::dbuf
  addr object lvl blkid holds os
  600be50 d 7 4 1 ztest/ds_6
  719d880 d 7 0 4 ztest/ds_6

Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>

1 files changed, 24 insertions, 2 deletions

diff --git a/cddl/contrib/opensolaris/cmd/ztest/ztest.c b/cddl/contrib/opensolaris/cmd/ztest/ztest.c
index 29d7fb8..5fc5717 100644
--- a/cddl/contrib/opensolaris/cmd/ztest/ztest.c
+++ b/cddl/contrib/opensolaris/cmd/ztest/ztest.c
@@ -4793,7 +4793,7 @@ ztest_fault_inject(ztest_ds_t *zd, uint64_t id)
 	char path0[MAXPATHLEN];
 	char pathrand[MAXPATHLEN];
 	size_t fsize;
-	int bshift = SPA_MAXBLOCKSHIFT + 2;	/* don't scrog all labels */
+	int bshift = SPA_MAXBLOCKSHIFT + 2;
 	int iters = 1000;
 	int maxfaults;
 	int mirror_save;
@@ -4983,7 +4983,29 @@ ztest_fault_inject(ztest_ds_t *zd, uint64_t id)
 		    (leaves << bshift) + (leaf << bshift) +
 		    (ztest_random(1ULL << (bshift - 1)) & -8ULL);
 
-		if (offset >= fsize)
+		/*
+		 * Only allow damage to the labels at one end of the vdev.
+		 *
+		 * If all labels are damaged, the device will be totally
+		 * inaccessible, which will result in loss of data,
+		 * because we also damage (parts of) the other side of
+		 * the mirror/raidz.
+		 *
+		 * Additionally, we will always have both an even and an
+		 * odd label, so that we can handle crashes in the
+		 * middle of vdev_config_sync().
+		 */
+		if ((leaf & 1) == 0 && offset < VDEV_LABEL_START_SIZE)
+			continue;
+
+		/*
+		 * The two end labels are stored at the "end" of the disk, but
+		 * the end of the disk (vdev_psize) is aligned to
+		 * sizeof (vdev_label_t).
+		 */
+		uint64_t psize = P2ALIGN(fsize, sizeof (vdev_label_t));
+		if ((leaf & 1) == 1 &&
+		    offset + sizeof (bad) > psize - VDEV_LABEL_END_SIZE)
 			continue;
 
 		VERIFY(mutex_lock(&ztest_vdev_lock) == 0);