[PATCH] dm: switch dm-verity to async hash crypto API

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Use of the synchronous digest API limits dm-verity when using pure
CPU based algorithm providers and rules out the use of most off
CPU algorithm providers which are normally asynchronous by nature,
which can speed up performance even further.

This reduced performance is especially expressed during boot when
a typical dm-verity use case makes a lot of file access to the
protected volume.

Move dm-verity to the asynchronous hash API to gain more performance
with potentially less CPU load, showing a speedup of 13% while using
the same underlying shash provider (Arm asm SHA256) and 21% speedup
with an off-CPU cryptographic engine algorithm provider (Arm CryptoCell)
for large files/volumes while showing no meaningful effect for small
files.

The following measurements demonstrate the results:

...
-rwxr-xr-x    1 root     root       16.0M Jan  1  1980 fs1.img
-rwxr-xr-x    1 root     root       16.0M Jan  1  1980 fs2.img
-rwxr-xr-x    1 root     root      817.4M Jan  1  1980 fsb1.img
-rwxr-xr-x    1 root     root       39.1M Jan  1  1980 fsb2.img

fs1.img and fsb1.img are small and large file system images, respectfully.
fs2.img and fsb2.img are small and large hash volumes, respectfully.

Before change (Arm asm shash)
32768+0 records in
32768+0 records out
real    0m 0.83s
user    0m 0.02s
sys     0m 0.17s

1674040+0 records in
1674040+0 records out
real    0m 41.22s
user    0m 1.15s
sys     0m 8.74s

1674040+0 records in
1674040+0 records out
real    0m 41.26s
user    0m 1.02s
sys     0m 8.95s

After change (Arm asm ahash):
32768+0 records in
32768+0 records out
real    0m 0.81s
user    0m 0.02s
sys     0m 0.17s

1674040+0 records in
1674040+0 records out
real    0m 38.52s
user    0m 1.13s
sys     0m 8.80s

1674040+0 records in
1674040+0 records out
real    0m 36.38s
user    0m 1.08s
sys     0m 8.18s

After change (Arm CryptoCell ahash):
32768+0 records in
32768+0 records out
real    0m 0.81s
user    0m 0.01s
sys     0m 0.18s

1674040+0 records in
1674040+0 records out
real    0m 35.87s
user    0m 0.95s
sys     0m 8.19s

1674040+0 records in
1674040+0 records out
real    0m 33.96s
user    0m 1.10s
sys     0m 8.00s

All measurements done on a dual core Zynq ZC706 development board
with an Armv7 processors.

Signed-off-by: Gilad Ben-Yossef <gilad@xxxxxxxxxxxxx>
---
 drivers/md/dm-verity-fec.c    |   4 +-
 drivers/md/dm-verity-target.c | 230 +++++++++++++++++++++++++++++++-----------
 drivers/md/dm-verity.h        |  26 +++--
 3 files changed, 192 insertions(+), 68 deletions(-)

diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c
index 0f0eb8a..dab98fe 100644
--- a/drivers/md/dm-verity-fec.c
+++ b/drivers/md/dm-verity-fec.c
@@ -188,7 +188,7 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio,
 static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io,
 			  u8 *want_digest, u8 *data)
 {
-	if (unlikely(verity_hash(v, verity_io_hash_desc(v, io),
+	if (unlikely(verity_hash(v, verity_io_hash_req(v, io),
 				 data, 1 << v->data_dev_block_bits,
 				 verity_io_real_digest(v, io))))
 		return 0;
@@ -397,7 +397,7 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io,
 	}
 
 	/* Always re-validate the corrected block against the expected hash */
-	r = verity_hash(v, verity_io_hash_desc(v, io), fio->output,
+	r = verity_hash(v, verity_io_hash_req(v, io), fio->output,
 			1 << v->data_dev_block_bits,
 			verity_io_real_digest(v, io));
 	if (unlikely(r < 0))
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 7335d8a..910f083 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -93,81 +93,144 @@ static sector_t verity_position_at_level(struct dm_verity *v, sector_t block,
 }
 
 /*
- * Wrapper for crypto_shash_init, which handles verity salting.
+ * Callback function for asynchrnous crypto API completion notification
  */
-static int verity_hash_init(struct dm_verity *v, struct shash_desc *desc)
+static void verity_hash_done(struct crypto_async_request *base, int err)
+{
+	struct verity_result *res = (struct verity_result *)base->data;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	res->err = err;
+	complete(&res->completion);
+}
+
+/*
+ * Wait for async crypto API callback
+ */
+static inline int verity_wait_hash(struct verity_result *res)
 {
 	int r;
 
-	desc->tfm = v->tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+	r = wait_for_completion_interruptible(&res->completion);
 
-	r = crypto_shash_init(desc);
+	if (!r)
+		r = res->err;
 
-	if (unlikely(r < 0)) {
-		DMERR("crypto_shash_init failed: %d", r);
-		return r;
-	}
+	reinit_completion(&res->completion);
+	return r;
+}
 
-	if (likely(v->version >= 1)) {
-		r = crypto_shash_update(desc, v->salt, v->salt_size);
+static int verity_hash_update(struct dm_verity *v, struct ahash_request *req,
+				const u8 *data, size_t len,
+				struct verity_result *res)
+{
+	int r;
+	struct scatterlist sg;
 
-		if (unlikely(r < 0)) {
-			DMERR("crypto_shash_update failed: %d", r);
-			return r;
-		}
+	sg_init_table(&sg, 1);
+	sg_set_buf(&sg, data, len);
+	ahash_request_set_crypt(req, &sg, NULL, len);
+	r = crypto_ahash_update(req);
+
+	switch (r) {
+	case 0:
+		break;
+
+	case -EINPROGRESS:
+	case -EBUSY:
+		r = verity_wait_hash(res);
+		break;
+
+	default:
+		DMERR("crypto_ahash_update request submission failed: %d", r);
 	}
 
-	return 0;
+	if (unlikely(r < 0))
+		DMERR("crypto_ahash_update failed: %d", r);
+
+	return r;
 }
 
-static int verity_hash_update(struct dm_verity *v, struct shash_desc *desc,
-			      const u8 *data, size_t len)
+/*
+ * Wrapper for crypto_ahash_init, which handles verity salting.
+ */
+static int verity_hash_init(struct dm_verity *v, struct ahash_request *req,
+				struct verity_result *res)
 {
-	int r = crypto_shash_update(desc, data, len);
+	int r;
 
-	if (unlikely(r < 0))
-		DMERR("crypto_shash_update failed: %d", r);
+	ahash_request_set_tfm(req, v->tfm);
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
+				verity_hash_done, (void *)res);
+	init_completion(&res->completion);
+
+	r = crypto_ahash_init(req);
+
+	if (unlikely(r < 0)) {
+		DMERR("crypto_ahash_init failed: %d", r);
+		return r;
+	}
+
+	if (likely(v->version >= 1))
+		r = verity_hash_update(v, req, v->salt, v->salt_size, res);
 
 	return r;
 }
 
-static int verity_hash_final(struct dm_verity *v, struct shash_desc *desc,
-			     u8 *digest)
+static int verity_hash_final(struct dm_verity *v, struct ahash_request *req,
+			     u8 *digest, struct verity_result *res)
 {
 	int r;
 
 	if (unlikely(!v->version)) {
-		r = crypto_shash_update(desc, v->salt, v->salt_size);
+		r = verity_hash_update(v, req, v->salt, v->salt_size, res);
 
 		if (r < 0) {
-			DMERR("crypto_shash_update failed: %d", r);
-			return r;
+			DMERR("verity_hash_final failed updating salt: %d", r);
+			goto out;
 		}
 	}
 
-	r = crypto_shash_final(desc, digest);
+	ahash_request_set_crypt(req, NULL, digest, 0);
+	r = crypto_ahash_final(req);
 
-	if (unlikely(r < 0))
-		DMERR("crypto_shash_final failed: %d", r);
+	switch (r) {
+	case 0:
+		break;
+
+	case -EINPROGRESS:
+	case -EBUSY:
+		r = verity_wait_hash(res);
+		break;
+
+	default:
+		DMERR("crypto_ahash_final request submission failed: %d", r);
+	}
 
+out:
 	return r;
 }
 
-int verity_hash(struct dm_verity *v, struct shash_desc *desc,
+int verity_hash(struct dm_verity *v, struct ahash_request *req,
 		const u8 *data, size_t len, u8 *digest)
 {
 	int r;
+	struct verity_result res;
 
-	r = verity_hash_init(v, desc);
+	r = verity_hash_init(v, req, &res);
 	if (unlikely(r < 0))
-		return r;
+		goto out;
 
-	r = verity_hash_update(v, desc, data, len);
+	r = verity_hash_update(v, req, data, len, &res);
 	if (unlikely(r < 0))
-		return r;
+		goto out;
+
+	r = verity_hash_final(v, req, digest, &res);
 
-	return verity_hash_final(v, desc, digest);
+out:
+	return r;
 }
 
 static void verity_hash_at_level(struct dm_verity *v, sector_t block, int level,
@@ -275,7 +338,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io,
 			goto release_ret_r;
 		}
 
-		r = verity_hash(v, verity_io_hash_desc(v, io),
+		r = verity_hash(v, verity_io_hash_req(v, io),
 				data, 1 << v->hash_dev_block_bits,
 				verity_io_real_digest(v, io));
 		if (unlikely(r < 0))
@@ -344,6 +407,63 @@ int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
 }
 
 /*
+ * Calculates the digest for the given bio
+ */
+int verity_for_io_block(struct dm_verity *v, struct dm_verity_io *io,
+			struct bvec_iter *iter)
+{
+	unsigned int todo = 1 << v->data_dev_block_bits;
+	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
+	struct scatterlist sg;
+	struct verity_result res;
+	struct ahash_request *req = verity_io_hash_req(v, io);
+
+	do {
+		int r;
+		unsigned int len;
+		struct bio_vec bv = bio_iter_iovec(bio, *iter);
+
+		sg_init_table(&sg, 1);
+
+		len = bv.bv_len;
+
+		if (likely(len >= todo))
+			len = todo;
+		/*
+		 * Operating on a single page at a time looks suboptimal
+		 * until you consider the typical block size is 4,096B.
+		 * Going through this loops twice should be very rare.
+		 */
+		sg_set_page(&sg, bv.bv_page, bv.bv_len, bv.bv_offset);
+		ahash_request_set_crypt(req, &sg, NULL, len);
+		r = crypto_ahash_update(req);
+
+		switch (r) {
+		case 0:
+			break;
+
+		case -EINPROGRESS:
+		case -EBUSY:
+			r = verity_wait_hash(&res);
+			break;
+
+		default:
+			break;
+		}
+
+		if (unlikely(r < 0)) {
+			DMERR("verity_for_io_block failed: %d", r);
+			return r;
+		}
+
+		bio_advance_iter(bio, iter, len);
+		todo -= len;
+	} while (todo);
+
+	return 0;
+}
+
+/*
  * Calls function process for 1 << v->data_dev_block_bits bytes in the bio_vec
  * starting from iter.
  */
@@ -381,12 +501,6 @@ int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 	return 0;
 }
 
-static int verity_bv_hash_update(struct dm_verity *v, struct dm_verity_io *io,
-				 u8 *data, size_t len)
-{
-	return verity_hash_update(v, verity_io_hash_desc(v, io), data, len);
-}
-
 static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
 			  u8 *data, size_t len)
 {
@@ -403,10 +517,11 @@ static int verity_verify_io(struct dm_verity_io *io)
 	struct dm_verity *v = io->v;
 	struct bvec_iter start;
 	unsigned b;
+	struct verity_result res;
 
 	for (b = 0; b < io->n_blocks; b++) {
 		int r;
-		struct shash_desc *desc = verity_io_hash_desc(v, io);
+		struct ahash_request *req = verity_io_hash_req(v, io);
 
 		r = verity_hash_for_block(v, io, io->block + b,
 					  verity_io_want_digest(v, io),
@@ -427,16 +542,17 @@ static int verity_verify_io(struct dm_verity_io *io)
 			continue;
 		}
 
-		r = verity_hash_init(v, desc);
+		r = verity_hash_init(v, req, &res);
 		if (unlikely(r < 0))
 			return r;
 
 		start = io->iter;
-		r = verity_for_bv_block(v, io, &io->iter, verity_bv_hash_update);
+		r = verity_for_io_block(v, io, &io->iter);
 		if (unlikely(r < 0))
 			return r;
 
-		r = verity_hash_final(v, desc, verity_io_real_digest(v, io));
+		r = verity_hash_final(v, req, verity_io_real_digest(v, io),
+					&res);
 		if (unlikely(r < 0))
 			return r;
 
@@ -705,7 +821,7 @@ static void verity_dtr(struct dm_target *ti)
 	kfree(v->zero_digest);
 
 	if (v->tfm)
-		crypto_free_shash(v->tfm);
+		crypto_free_ahash(v->tfm);
 
 	kfree(v->alg_name);
 
@@ -723,7 +839,7 @@ static void verity_dtr(struct dm_target *ti)
 static int verity_alloc_zero_digest(struct dm_verity *v)
 {
 	int r = -ENOMEM;
-	struct shash_desc *desc;
+	struct ahash_request *req;
 	u8 *zero_data;
 
 	v->zero_digest = kmalloc(v->digest_size, GFP_KERNEL);
@@ -731,9 +847,9 @@ static int verity_alloc_zero_digest(struct dm_verity *v)
 	if (!v->zero_digest)
 		return r;
 
-	desc = kmalloc(v->shash_descsize, GFP_KERNEL);
+	req = kmalloc(v->ahash_reqsize, GFP_KERNEL);
 
-	if (!desc)
+	if (!req)
 		return r; /* verity_dtr will free zero_digest */
 
 	zero_data = kzalloc(1 << v->data_dev_block_bits, GFP_KERNEL);
@@ -741,11 +857,11 @@ static int verity_alloc_zero_digest(struct dm_verity *v)
 	if (!zero_data)
 		goto out;
 
-	r = verity_hash(v, desc, zero_data, 1 << v->data_dev_block_bits,
+	r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits,
 			v->zero_digest);
 
 out:
-	kfree(desc);
+	kfree(req);
 	kfree(zero_data);
 
 	return r;
@@ -923,21 +1039,21 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		goto bad;
 	}
 
-	v->tfm = crypto_alloc_shash(v->alg_name, 0, 0);
+	v->tfm = crypto_alloc_ahash(v->alg_name, 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(v->tfm)) {
 		ti->error = "Cannot initialize hash function";
 		r = PTR_ERR(v->tfm);
 		v->tfm = NULL;
 		goto bad;
 	}
-	v->digest_size = crypto_shash_digestsize(v->tfm);
+	v->digest_size = crypto_ahash_digestsize(v->tfm);
 	if ((1 << v->hash_dev_block_bits) < v->digest_size * 2) {
 		ti->error = "Digest size too big";
 		r = -EINVAL;
 		goto bad;
 	}
-	v->shash_descsize =
-		sizeof(struct shash_desc) + crypto_shash_descsize(v->tfm);
+	v->ahash_reqsize = sizeof(struct ahash_request) +
+		crypto_ahash_reqsize(v->tfm);
 
 	v->root_digest = kmalloc(v->digest_size, GFP_KERNEL);
 	if (!v->root_digest) {
@@ -1037,7 +1153,7 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 
 	ti->per_io_data_size = sizeof(struct dm_verity_io) +
-				v->shash_descsize + v->digest_size * 2;
+				v->ahash_reqsize + v->digest_size * 2;
 
 	r = verity_fec_ctr(v);
 	if (r)
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index fb419f4..aed710a 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -37,7 +37,7 @@ struct dm_verity {
 	struct dm_target *ti;
 	struct dm_bufio_client *bufio;
 	char *alg_name;
-	struct crypto_shash *tfm;
+	struct crypto_ahash *tfm;
 	u8 *root_digest;	/* digest of the root block */
 	u8 *salt;		/* salt: its size is salt_size */
 	u8 *zero_digest;	/* digest for a zero block */
@@ -52,7 +52,7 @@ struct dm_verity {
 	unsigned char levels;	/* the number of tree levels */
 	unsigned char version;
 	unsigned digest_size;	/* digest size for the current hash algorithm */
-	unsigned shash_descsize;/* the size of temporary space for crypto */
+	unsigned int ahash_reqsize;/* 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 */
@@ -81,31 +81,36 @@ struct dm_verity_io {
 	/*
 	 * Three variably-size fields follow this struct:
 	 *
-	 * u8 hash_desc[v->shash_descsize];
+	 * u8 hash_req[v->ahash_reqsize];
 	 * u8 real_digest[v->digest_size];
 	 * u8 want_digest[v->digest_size];
 	 *
-	 * To access them use: verity_io_hash_desc(), verity_io_real_digest()
+	 * To access them use: verity_io_hash_req(), verity_io_real_digest()
 	 * and verity_io_want_digest().
 	 */
 };
 
-static inline struct shash_desc *verity_io_hash_desc(struct dm_verity *v,
+struct verity_result {
+	struct completion completion;
+	int err;
+};
+
+static inline struct ahash_request *verity_io_hash_req(struct dm_verity *v,
 						     struct dm_verity_io *io)
 {
-	return (struct shash_desc *)(io + 1);
+	return (struct ahash_request *)(io + 1);
 }
 
 static inline u8 *verity_io_real_digest(struct dm_verity *v,
 					struct dm_verity_io *io)
 {
-	return (u8 *)(io + 1) + v->shash_descsize;
+	return (u8 *)(io + 1) + v->ahash_reqsize;
 }
 
 static inline u8 *verity_io_want_digest(struct dm_verity *v,
 					struct dm_verity_io *io)
 {
-	return (u8 *)(io + 1) + v->shash_descsize + v->digest_size;
+	return (u8 *)(io + 1) + v->ahash_reqsize + v->digest_size;
 }
 
 static inline u8 *verity_io_digest_end(struct dm_verity *v,
@@ -114,13 +119,16 @@ static inline u8 *verity_io_digest_end(struct dm_verity *v,
 	return verity_io_want_digest(v, io) + v->digest_size;
 }
 
+extern int verity_for_io_block(struct dm_verity *v, struct dm_verity_io *io,
+				struct bvec_iter *iter);
+
 extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io,
 			       struct bvec_iter *iter,
 			       int (*process)(struct dm_verity *v,
 					      struct dm_verity_io *io,
 					      u8 *data, size_t len));
 
-extern int verity_hash(struct dm_verity *v, struct shash_desc *desc,
+extern int verity_hash(struct dm_verity *v, struct ahash_request *req,
 		       const u8 *data, size_t len, u8 *digest);
 
 extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io,
-- 
2.1.4

--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/dm-devel



[Index of Archives]     [DM Crypt]     [Fedora Desktop]     [ATA RAID]     [Fedora Marketing]     [Fedora Packaging]     [Fedora SELinux]     [Yosemite Discussion]     [KDE Users]     [Fedora Docs]

  Powered by Linux