dm flakey: introduce random_read_corrupt and random_write_corrupt options

The random_read_corrupt and random_write_corrupt options corrupt a
random byte in a bio with the provided probability. The corruption
only happens in the "down" interval.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@kernel.org>

2 files changed, 110 insertions, 20 deletions

diff --git a/Documentation/admin-guide/device-mapper/dm-flakey.rst b/Documentation/admin-guide/device-mapper/dm-flakey.rst
index f7104c01b0f7..f967c5fea219 100644
--- a/Documentation/admin-guide/device-mapper/dm-flakey.rst
+++ b/Documentation/admin-guide/device-mapper/dm-flakey.rst
@@ -67,6 +67,16 @@ Optional feature parameters:
 	Perform the replacement only if bio->bi_opf has all the
 	selected flags set.
 
+  random_read_corrupt <probability>
+	During <down interval>, replace random byte in a read bio
+	with a random value. probability is an integer between
+	0 and 1000000000 meaning 0% to 100% probability of corruption.
+
+  random_write_corrupt <probability>
+	During <down interval>, replace random byte in a write bio
+	with a random value. probability is an integer between
+	0 and 1000000000 meaning 0% to 100% probability of corruption.
+
 Examples:
 
 Replaces the 32nd byte of READ bios with the value 1::
diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 079d48b29628..120153e44ae0 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -16,6 +16,8 @@
 
 #define DM_MSG_PREFIX "flakey"
 
+#define PROBABILITY_BASE	1000000000
+
 #define all_corrupt_bio_flags_match(bio, fc)	\
 	(((bio)->bi_opf & (fc)->corrupt_bio_flags) == (fc)->corrupt_bio_flags)
 
@@ -34,6 +36,8 @@ struct flakey_c {
 	unsigned int corrupt_bio_rw;
 	unsigned int corrupt_bio_value;
 	blk_opf_t corrupt_bio_flags;
+	unsigned int random_read_corrupt;
+	unsigned int random_write_corrupt;
 };
 
 enum feature_flag_bits {
@@ -54,10 +58,11 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 	const char *arg_name;
 
 	static const struct dm_arg _args[] = {
-		{0, 7, "Invalid number of feature args"},
+		{0, 11, "Invalid number of feature args"},
 		{1, UINT_MAX, "Invalid corrupt bio byte"},
 		{0, 255, "Invalid corrupt value to write into bio byte (0-255)"},
 		{0, UINT_MAX, "Invalid corrupt bio flags mask"},
+		{0, PROBABILITY_BASE, "Invalid random corrupt argument"},
 	};
 
 	/* No feature arguments supplied. */
@@ -170,6 +175,32 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 			continue;
 		}
 
+		if (!strcasecmp(arg_name, "random_read_corrupt")) {
+			if (!argc) {
+				ti->error = "Feature random_read_corrupt requires a parameter";
+				return -EINVAL;
+			}
+			r = dm_read_arg(_args + 4, as, &fc->random_read_corrupt, &ti->error);
+			if (r)
+				return r;
+			argc--;
+
+			continue;
+		}
+
+		if (!strcasecmp(arg_name, "random_write_corrupt")) {
+			if (!argc) {
+				ti->error = "Feature random_write_corrupt requires a parameter";
+				return -EINVAL;
+			}
+			r = dm_read_arg(_args + 4, as, &fc->random_write_corrupt, &ti->error);
+			if (r)
+				return r;
+			argc--;
+
+			continue;
+		}
+
 		ti->error = "Unrecognised flakey feature requested";
 		return -EINVAL;
 	}
@@ -184,7 +215,8 @@ static int parse_features(struct dm_arg_set *as, struct flakey_c *fc,
 	}
 
 	if (!fc->corrupt_bio_byte && !test_bit(ERROR_READS, &fc->flags) &&
-	    !test_bit(DROP_WRITES, &fc->flags) && !test_bit(ERROR_WRITES, &fc->flags)) {
+	    !test_bit(DROP_WRITES, &fc->flags) && !test_bit(ERROR_WRITES, &fc->flags) &&
+	    !fc->random_read_corrupt && !fc->random_write_corrupt) {
 		set_bit(ERROR_WRITES, &fc->flags);
 		set_bit(ERROR_READS, &fc->flags);
 	}
@@ -306,36 +338,57 @@ static void flakey_map_bio(struct dm_target *ti, struct bio *bio)
 	bio->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector);
 }
 
-static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
+static void corrupt_bio_common(struct bio *bio, unsigned int corrupt_bio_byte,
+			       unsigned char corrupt_bio_value)
 {
-	unsigned int corrupt_bio_byte = fc->corrupt_bio_byte - 1;
-
 	struct bvec_iter iter;
 	struct bio_vec bvec;
 
-	if (!bio_has_data(bio))
-		return;
-
 	/*
 	 * Overwrite the Nth byte of the bio's data, on whichever page
 	 * it falls.
 	 */
 	bio_for_each_segment(bvec, bio, iter) {
 		if (bio_iter_len(bio, iter) > corrupt_bio_byte) {
-			char *segment = bvec_kmap_local(&bvec);
-			segment[corrupt_bio_byte] = fc->corrupt_bio_value;
+			unsigned char *segment = bvec_kmap_local(&bvec);
+			segment[corrupt_bio_byte] = corrupt_bio_value;
 			kunmap_local(segment);
 			DMDEBUG("Corrupting data bio=%p by writing %u to byte %u "
 				"(rw=%c bi_opf=%u bi_sector=%llu size=%u)\n",
-				bio, fc->corrupt_bio_value, fc->corrupt_bio_byte,
+				bio, corrupt_bio_value, corrupt_bio_byte,
 				(bio_data_dir(bio) == WRITE) ? 'w' : 'r', bio->bi_opf,
-				(unsigned long long)bio->bi_iter.bi_sector, bio->bi_iter.bi_size);
+				(unsigned long long)bio->bi_iter.bi_sector,
+				bio->bi_iter.bi_size);
 			break;
 		}
 		corrupt_bio_byte -= bio_iter_len(bio, iter);
 	}
 }
 
+static void corrupt_bio_data(struct bio *bio, struct flakey_c *fc)
+{
+	unsigned int corrupt_bio_byte = fc->corrupt_bio_byte - 1;
+
+	if (!bio_has_data(bio))
+		return;
+
+	corrupt_bio_common(bio, corrupt_bio_byte, fc->corrupt_bio_value);
+}
+
+static void corrupt_bio_random(struct bio *bio)
+{
+	unsigned int corrupt_byte;
+	unsigned char corrupt_value;
+
+	if (!bio_has_data(bio))
+		return;
+
+	corrupt_byte = get_random_u32() % bio->bi_iter.bi_size;
+	corrupt_value = get_random_u8();
+
+	corrupt_bio_common(bio, corrupt_byte, corrupt_value);
+}
+
 static void clone_free(struct bio *clone)
 {
 	struct folio_iter fi;
@@ -436,6 +489,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	/* Are we alive ? */
 	elapsed = (jiffies - fc->start_time) / HZ;
 	if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) {
+		bool corrupt_fixed, corrupt_random;
 		/*
 		 * Flag this bio as submitted while down.
 		 */
@@ -465,16 +519,28 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		/*
 		 * Corrupt matching writes.
 		 */
+		corrupt_fixed = false;
+		corrupt_random = false;
 		if (fc->corrupt_bio_byte && fc->corrupt_bio_rw == WRITE) {
-			if (all_corrupt_bio_flags_match(bio, fc)) {
-				struct bio *clone = clone_bio(ti, fc, bio);
-				if (clone) {
+			if (all_corrupt_bio_flags_match(bio, fc))
+				corrupt_fixed = true;
+		}
+		if (fc->random_write_corrupt) {
+			u64 rnd = get_random_u64();
+			u32 rem = do_div(rnd, PROBABILITY_BASE);
+			if (rem < fc->random_write_corrupt)
+				corrupt_random = true;
+		}
+		if (corrupt_fixed || corrupt_random) {
+			struct bio *clone = clone_bio(ti, fc, bio);
+			if (clone) {
+				if (corrupt_fixed)
 					corrupt_bio_data(clone, fc);
-					submit_bio(clone);
-					return DM_MAPIO_SUBMITTED;
-				}
+				if (corrupt_random)
+					corrupt_bio_random(clone);
+				submit_bio(clone);
+				return DM_MAPIO_SUBMITTED;
 			}
-			goto map_bio;
 		}
 	}
 
@@ -503,6 +569,12 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 				corrupt_bio_data(bio, fc);
 			}
 		}
+		if (fc->random_read_corrupt) {
+			u64 rnd = get_random_u64();
+			u32 rem = do_div(rnd, PROBABILITY_BASE);
+			if (rem < fc->random_read_corrupt)
+				corrupt_bio_random(bio);
+		}
 		if (test_bit(ERROR_READS, &fc->flags)) {
 			/*
 			 * Error read during the down_interval if drop_writes
@@ -535,7 +607,10 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
 		error_reads = test_bit(ERROR_READS, &fc->flags);
 		drop_writes = test_bit(DROP_WRITES, &fc->flags);
 		error_writes = test_bit(ERROR_WRITES, &fc->flags);
-		DMEMIT(" %u", error_reads + drop_writes + error_writes + (fc->corrupt_bio_byte > 0) * 5);
+		DMEMIT(" %u", error_reads + drop_writes + error_writes +
+			(fc->corrupt_bio_byte > 0) * 5 +
+			(fc->random_read_corrupt > 0) * 2 +
+			(fc->random_write_corrupt > 0) * 2);
 
 		if (error_reads)
 			DMEMIT(" error_reads");
@@ -550,6 +625,11 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
 			       (fc->corrupt_bio_rw == WRITE) ? 'w' : 'r',
 			       fc->corrupt_bio_value, fc->corrupt_bio_flags);
 
+		if (fc->random_read_corrupt > 0)
+			DMEMIT(" random_read_corrupt %u", fc->random_read_corrupt);
+		if (fc->random_write_corrupt > 0)
+			DMEMIT(" random_write_corrupt %u", fc->random_write_corrupt);
+
 		break;
 
 	case STATUSTYPE_IMA: