dm verity: add error handling modes for corrupted blocks

Add device specific modes to dm-verity to specify how corrupted
blocks should be handled.  The following modes are defined:

  - DM_VERITY_MODE_EIO is the default behavior, where reading a
    corrupted block results in -EIO.

  - DM_VERITY_MODE_LOGGING only logs corrupted blocks, but does
    not block the read.

  - DM_VERITY_MODE_RESTART calls kernel_restart when a corrupted
    block is discovered.

In addition, each mode sends a uevent to notify userspace of
corruption and to allow further recovery actions.

The driver defaults to previous behavior (DM_VERITY_MODE_EIO)
and other modes can be enabled with an additional parameter to
the verity table.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>

Documentation/device-mapper/verity.txt

@@ -11,6 +11,7 @@ Construction Parameters
     <data_block_size> <hash_block_size>
     <num_data_blocks> <hash_start_block>
     <algorithm> <digest> <salt>
+    [<#opt_params> <opt_params>]
 
 <version>
     This is the type of the on-disk hash format.
@@ -62,6 +63,22 @@ Construction Parameters
 <salt>
     The hexadecimal encoding of the salt value.
 
+<#opt_params>
+    Number of optional parameters. If there are no optional parameters,
+    the optional paramaters section can be skipped or #opt_params can be zero.
+    Otherwise #opt_params is the number of following arguments.
+
+    Example of optional parameters section:
+        1 ignore_corruption
+
+ignore_corruption
+    Log corrupted blocks, but allow read operations to proceed normally.
+
+restart_on_corruption
+    Restart the system when a corrupted block is discovered. This option is
+    not compatible with ignore_corruption and requires user space support to
+    avoid restart loops.
+
 Theory of operation
 ===================
 

drivers/md/dm-verity.c

@@ -18,20 +18,39 @@
 
 #include <linux/module.h>
 #include <linux/device-mapper.h>
+#include <linux/reboot.h>
 #include <crypto/hash.h>
 
 #define DM_MSG_PREFIX			"verity"
 
+#define DM_VERITY_ENV_LENGTH		42
+#define DM_VERITY_ENV_VAR_NAME		"DM_VERITY_ERR_BLOCK_NR"
+
 #define DM_VERITY_IO_VEC_INLINE		16
 #define DM_VERITY_MEMPOOL_SIZE		4
 #define DM_VERITY_DEFAULT_PREFETCH_SIZE	262144
 
 #define DM_VERITY_MAX_LEVELS		63
+#define DM_VERITY_MAX_CORRUPTED_ERRS	100
+
+#define DM_VERITY_OPT_LOGGING		"ignore_corruption"
+#define DM_VERITY_OPT_RESTART		"restart_on_corruption"
 
 static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;
 
 module_param_named(prefetch_cluster, dm_verity_prefetch_cluster, uint, S_IRUGO | S_IWUSR);
 
+enum verity_mode {
+	DM_VERITY_MODE_EIO,
+	DM_VERITY_MODE_LOGGING,
+	DM_VERITY_MODE_RESTART
+};
+
+enum verity_block_type {
+	DM_VERITY_BLOCK_TYPE_DATA,
+	DM_VERITY_BLOCK_TYPE_METADATA
+};
+
 struct dm_verity {
 	struct dm_dev *data_dev;
 	struct dm_dev *hash_dev;
@@ -54,6 +73,8 @@ struct dm_verity {
 	unsigned digest_size;	/* digest size for the current hash algorithm */
 	unsigned shash_descsize;/* the size of temporary space for crypto */
 	int hash_failed;	/* set to 1 if hash of any block failed */
+	enum verity_mode mode;	/* mode for handling verification errors */
+	unsigned corrupted_errs;/* Number of errors for corrupted blocks */
 
 	mempool_t *vec_mempool;	/* mempool of bio vector */
 
@@ -174,6 +195,57 @@ static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level,
 		*offset = idx << (v->hash_dev_block_bits - v->hash_per_block_bits);
 }
 
+/*
+ * Handle verification errors.
+ */
+static int verity_handle_err(struct dm_verity *v, enum verity_block_type type,
+			     unsigned long long block)
+{
+	char verity_env[DM_VERITY_ENV_LENGTH];
+	char *envp[] = { verity_env, NULL };
+	const char *type_str = "";
+	struct mapped_device *md = dm_table_get_md(v->ti->table);
+
+	/* Corruption should be visible in device status in all modes */
+	v->hash_failed = 1;
+
+	if (v->corrupted_errs >= DM_VERITY_MAX_CORRUPTED_ERRS)
+		goto out;
+
+	v->corrupted_errs++;
+
+	switch (type) {
+	case DM_VERITY_BLOCK_TYPE_DATA:
+		type_str = "data";
+		break;
+	case DM_VERITY_BLOCK_TYPE_METADATA:
+		type_str = "metadata";
+		break;
+	default:
+		BUG();
+	}
+
+	DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str,
+		block);
+
+	if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS)
+		DMERR("%s: reached maximum errors", v->data_dev->name);
+
+	snprintf(verity_env, DM_VERITY_ENV_LENGTH, "%s=%d,%llu",
+		DM_VERITY_ENV_VAR_NAME, type, block);
+
+	kobject_uevent_env(&disk_to_dev(dm_disk(md))->kobj, KOBJ_CHANGE, envp);
+
+out:
+	if (v->mode == DM_VERITY_MODE_LOGGING)
+		return 0;
+
+	if (v->mode == DM_VERITY_MODE_RESTART)
+		kernel_restart("dm-verity device corrupted");
+
+	return 1;
+}
+
 /*
  * Verify hash of a metadata block pertaining to the specified data block
  * ("block" argument) at a specified level ("level" argument).
@@ -251,11 +323,11 @@ static int verity_verify_level(struct dm_verity_io *io, sector_t block,
 			goto release_ret_r;
 		}
 		if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
-			DMERR_LIMIT("metadata block %llu is corrupted",
+			if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_METADATA,
-				(unsigned long long)hash_block);
+					      hash_block)) {
-			v->hash_failed = 1;
+				r = -EIO;
-			r = -EIO;
+				goto release_ret_r;
-			goto release_ret_r;
+			}
 		} else
 			aux->hash_verified = 1;
 	}
@@ -367,10 +439,9 @@ test_block_hash:
 			return r;
 		}
 		if (unlikely(memcmp(result, io_want_digest(v, io), v->digest_size))) {
-			DMERR_LIMIT("data block %llu is corrupted",
+			if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
-				(unsigned long long)(io->block + b));
+					      io->block + b))
-			v->hash_failed = 1;
+				return -EIO;
-			return -EIO;
 		}
 	}
 
@@ -546,6 +617,19 @@ static void verity_status(struct dm_target *ti, status_type_t type,
 		else
 			for (x = 0; x < v->salt_size; x++)
 				DMEMIT("%02x", v->salt[x]);
+		if (v->mode != DM_VERITY_MODE_EIO) {
+			DMEMIT(" 1 ");
+			switch (v->mode) {
+			case DM_VERITY_MODE_LOGGING:
+				DMEMIT(DM_VERITY_OPT_LOGGING);
+				break;
+			case DM_VERITY_MODE_RESTART:
+				DMEMIT(DM_VERITY_OPT_RESTART);
+				break;
+			default:
+				BUG();
+			}
+		}
 		break;
 	}
 }
@@ -647,13 +731,19 @@ static void verity_dtr(struct dm_target *ti)
 static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 {
 	struct dm_verity *v;
-	unsigned num;
+	struct dm_arg_set as;
+	const char *opt_string;
+	unsigned int num, opt_params;
 	unsigned long long num_ll;
 	int r;
 	int i;
 	sector_t hash_position;
 	char dummy;
 
+	static struct dm_arg _args[] = {
+		{0, 1, "Invalid number of feature args"},
+	};
+
 	v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL);
 	if (!v) {
 		ti->error = "Cannot allocate verity structure";
@@ -668,8 +758,8 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
-	if (argc != 10) {
+	if (argc < 10) {
-		ti->error = "Invalid argument count: exactly 10 arguments required";
+		ti->error = "Not enough arguments";
 		r = -EINVAL;
 		goto bad;
 	}
@@ -790,6 +880,39 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		}
 	}
 
+	argv += 10;
+	argc -= 10;
+
+	/* Optional parameters */
+	if (argc) {
+		as.argc = argc;
+		as.argv = argv;
+
+		r = dm_read_arg_group(_args, &as, &opt_params, &ti->error);
+		if (r)
+			goto bad;
+
+		while (opt_params) {
+			opt_params--;
+			opt_string = dm_shift_arg(&as);
+			if (!opt_string) {
+				ti->error = "Not enough feature arguments";
+				r = -EINVAL;
+				goto bad;
+			}
+
+			if (!strcasecmp(opt_string, DM_VERITY_OPT_LOGGING))
+				v->mode = DM_VERITY_MODE_LOGGING;
+			else if (!strcasecmp(opt_string, DM_VERITY_OPT_RESTART))
+				v->mode = DM_VERITY_MODE_RESTART;
+			else {
+				ti->error = "Invalid feature arguments";
+				r = -EINVAL;
+				goto bad;
+			}
+		}
+	}
+
 	v->hash_per_block_bits =
 		__fls((1 << v->hash_dev_block_bits) / v->digest_size);
 

drivers/md/dm.c

@@ -3483,6 +3483,7 @@ struct gendisk *dm_disk(struct mapped_device *md)
 {
 	return md->disk;
 }
+EXPORT_SYMBOL_GPL(dm_disk);
 
 struct kobject *dm_kobject(struct mapped_device *md)
 {