[PATCH 0/7] Tegra Security Engine driver improvements

[PATCH 0/7] Tegra Security Engine driver improvements

[Akhil R]

With the CRYPTO_TEST now being run asynchronously unveiled some
concurrency issues in the the Security Engine driver. These were not
caught during functional or fuzz testing as all the tests were run
synchronously.
This patchset contains the fixes for the concurrency issues and few
other improvements identified during the stress-ng and cryptsetup tests.

Akhil R (7):
  crypto: tegra: Use separate buffer for setkey
  crypto: tegra: Do not use fixed size buffers
  crypto: tegra: check retrun value for hash do_one_req
  crypto: tegra: Transfer HASH init function to crypto engine
  crypto: tegra: Fix HASH intermediate result handling
  crypto: tegra: Fix CMAC intermediate result handling
  crypto: tegra: Set IV to NULL explicitly for AES ECB

 drivers/crypto/tegra/tegra-se-aes.c  | 247 +++++++++++++-----------
 drivers/crypto/tegra/tegra-se-hash.c | 279 +++++++++++++++++----------
 drivers/crypto/tegra/tegra-se-key.c  |  10 +-
 drivers/crypto/tegra/tegra-se-main.c |  16 +-
 drivers/crypto/tegra/tegra-se.h      |  11 +-
 5 files changed, 346 insertions(+), 217 deletions(-)

-- 
2.43.2

[PATCH 1/7] crypto: tegra: Use separate buffer for setkey

[Akhil R]

The buffer which sends the commands to host1x was shared for all tasks
in the engine. This causes a problem with the setkey() function as it
gets called asynchronous to the crypto engine queue. Modifying the same
cmdbuf in setkey() will corrupt the ongoing host1x task and in turn
break the encryption/decryption operation. Hence use a separate cmdbuf
for setkey().

Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
---
 drivers/crypto/tegra/tegra-se-aes.c  | 16 ++++++++--------
 drivers/crypto/tegra/tegra-se-hash.c | 13 +++++++------
 drivers/crypto/tegra/tegra-se-key.c  | 10 ++++++++--
 drivers/crypto/tegra/tegra-se-main.c | 16 ++++++++++++----
 drivers/crypto/tegra/tegra-se.h      |  3 ++-
 5 files changed, 37 insertions(+), 21 deletions(-)

diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index 9d130592cc0a..5fc7e19b8ab8 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -282,7 +282,7 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
 
 	/* Prepare the command and submit for execution */
 	cmdlen = tegra_aes_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 
 	/* Copy the result */
 	tegra_aes_update_iv(req, ctx);
@@ -719,7 +719,7 @@ static int tegra_gcm_do_gmac(struct tegra_aead_ctx *ctx, struct tegra_aead_reqct
 
 	cmdlen = tegra_gmac_prep_cmd(ctx, rctx);
 
-	return tegra_se_host1x_submit(se, cmdlen);
+	return tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 }
 
 static int tegra_gcm_do_crypt(struct tegra_aead_ctx *ctx, struct tegra_aead_reqctx *rctx)
@@ -736,7 +736,7 @@ static int tegra_gcm_do_crypt(struct tegra_aead_ctx *ctx, struct tegra_aead_reqc
 
 	/* Prepare command and submit */
 	cmdlen = tegra_gcm_crypt_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		return ret;
 
@@ -759,7 +759,7 @@ static int tegra_gcm_do_final(struct tegra_aead_ctx *ctx, struct tegra_aead_reqc
 
 	/* Prepare command and submit */
 	cmdlen = tegra_gcm_prep_final_cmd(se, cpuvaddr, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		return ret;
 
@@ -891,7 +891,7 @@ static int tegra_ccm_do_cbcmac(struct tegra_aead_ctx *ctx, struct tegra_aead_req
 	/* Prepare command and submit */
 	cmdlen = tegra_cbcmac_prep_cmd(ctx, rctx);
 
-	return tegra_se_host1x_submit(se, cmdlen);
+	return tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 }
 
 static int tegra_ccm_set_msg_len(u8 *block, unsigned int msglen, int csize)
@@ -1098,7 +1098,7 @@ static int tegra_ccm_do_ctr(struct tegra_aead_ctx *ctx, struct tegra_aead_reqctx
 
 	/* Prepare command and submit */
 	cmdlen = tegra_ctr_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		return ret;
 
@@ -1519,8 +1519,8 @@ static int tegra_cmac_do_update(struct ahash_request *req)
 		tegra_cmac_paste_result(ctx->se, rctx);
 
 	cmdlen = tegra_cmac_prep_cmd(ctx, rctx);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 
-	ret = tegra_se_host1x_submit(se, cmdlen);
 	/*
 	 * If this is not the final update, copy the intermediate results
 	 * from the registers so that it can be used in the next 'update'
@@ -1553,7 +1553,7 @@ static int tegra_cmac_do_final(struct ahash_request *req)
 
 	/* Prepare command and submit */
 	cmdlen = tegra_cmac_prep_cmd(ctx, rctx);
-	ret = tegra_se_host1x_submit(se, cmdlen);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 	if (ret)
 		goto out;
 
diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c
index 4d4bd727f498..a0460e624523 100644
--- a/drivers/crypto/tegra/tegra-se-hash.c
+++ b/drivers/crypto/tegra/tegra-se-hash.c
@@ -300,8 +300,9 @@ static int tegra_sha_do_update(struct ahash_request *req)
 {
 	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
 	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct tegra_se *se = ctx->se;
 	unsigned int nblks, nresidue, size, ret;
-	u32 *cpuvaddr = ctx->se->cmdbuf->addr;
+	u32 *cpuvaddr = se->cmdbuf->addr;
 
 	nresidue = (req->nbytes + rctx->residue.size) % rctx->blk_size;
 	nblks = (req->nbytes + rctx->residue.size) / rctx->blk_size;
@@ -353,11 +354,11 @@ static int tegra_sha_do_update(struct ahash_request *req)
 	 * This is to support the import/export functionality.
 	 */
 	if (!(rctx->task & SHA_FIRST))
-		tegra_sha_paste_hash_result(ctx->se, rctx);
+		tegra_sha_paste_hash_result(se, rctx);
 
-	size = tegra_sha_prep_cmd(ctx->se, cpuvaddr, rctx);
+	size = tegra_sha_prep_cmd(se, cpuvaddr, rctx);
 
-	ret = tegra_se_host1x_submit(ctx->se, size);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, size);
 
 	/*
 	 * If this is not the final update, copy the intermediate results
@@ -365,7 +366,7 @@ static int tegra_sha_do_update(struct ahash_request *req)
 	 * call. This is to support the import/export functionality.
 	 */
 	if (!(rctx->task & SHA_FINAL))
-		tegra_sha_copy_hash_result(ctx->se, rctx);
+		tegra_sha_copy_hash_result(se, rctx);
 
 	return ret;
 }
@@ -388,7 +389,7 @@ static int tegra_sha_do_final(struct ahash_request *req)
 
 	size = tegra_sha_prep_cmd(se, cpuvaddr, rctx);
 
-	ret = tegra_se_host1x_submit(se, size);
+	ret = tegra_se_host1x_submit(se, se->cmdbuf, size);
 	if (ret)
 		goto out;
 
diff --git a/drivers/crypto/tegra/tegra-se-key.c b/drivers/crypto/tegra/tegra-se-key.c
index ac14678dbd30..276b261fb6df 100644
--- a/drivers/crypto/tegra/tegra-se-key.c
+++ b/drivers/crypto/tegra/tegra-se-key.c
@@ -115,11 +115,17 @@ static int tegra_key_insert(struct tegra_se *se, const u8 *key,
 			    u32 keylen, u16 slot, u32 alg)
 {
 	const u32 *keyval = (u32 *)key;
-	u32 *addr = se->cmdbuf->addr, size;
+	u32 *addr = se->keybuf->addr, size;
+	int ret;
+
+	mutex_lock(&kslt_lock);
 
 	size = tegra_key_prep_ins_cmd(se, addr, keyval, keylen, slot, alg);
+	ret = tegra_se_host1x_submit(se, se->keybuf, size);
 
-	return tegra_se_host1x_submit(se, size);
+	mutex_unlock(&kslt_lock);
+
+	return ret;
 }
 
 void tegra_key_invalidate(struct tegra_se *se, u32 keyid, u32 alg)
diff --git a/drivers/crypto/tegra/tegra-se-main.c b/drivers/crypto/tegra/tegra-se-main.c
index 918c0b10614d..1c94f1de0546 100644
--- a/drivers/crypto/tegra/tegra-se-main.c
+++ b/drivers/crypto/tegra/tegra-se-main.c
@@ -141,7 +141,7 @@ static struct tegra_se_cmdbuf *tegra_se_host1x_bo_alloc(struct tegra_se *se, ssi
 	return cmdbuf;
 }
 
-int tegra_se_host1x_submit(struct tegra_se *se, u32 size)
+int tegra_se_host1x_submit(struct tegra_se *se, struct tegra_se_cmdbuf *cmdbuf, u32 size)
 {
 	struct host1x_job *job;
 	int ret;
@@ -160,9 +160,9 @@ int tegra_se_host1x_submit(struct tegra_se *se, u32 size)
 	job->engine_fallback_streamid = se->stream_id;
 	job->engine_streamid_offset = SE_STREAM_ID;
 
-	se->cmdbuf->words = size;
+	cmdbuf->words = size;
 
-	host1x_job_add_gather(job, &se->cmdbuf->bo, size, 0);
+	host1x_job_add_gather(job, &cmdbuf->bo, size, 0);
 
 	ret = host1x_job_pin(job, se->dev);
 	if (ret) {
@@ -220,14 +220,22 @@ static int tegra_se_client_init(struct host1x_client *client)
 		goto syncpt_put;
 	}
 
+	se->keybuf = tegra_se_host1x_bo_alloc(se, SZ_4K);
+	if (!se->keybuf) {
+		ret = -ENOMEM;
+		goto cmdbuf_put;
+	}
+
 	ret = se->hw->init_alg(se);
 	if (ret) {
 		dev_err(se->dev, "failed to register algorithms\n");
-		goto cmdbuf_put;
+		goto keybuf_put;
 	}
 
 	return 0;
 
+keybuf_put:
+	tegra_se_cmdbuf_put(&se->keybuf->bo);
 cmdbuf_put:
 	tegra_se_cmdbuf_put(&se->cmdbuf->bo);
 syncpt_put:
diff --git a/drivers/crypto/tegra/tegra-se.h b/drivers/crypto/tegra/tegra-se.h
index b9dd7ceb8783..b54aefe717a1 100644
--- a/drivers/crypto/tegra/tegra-se.h
+++ b/drivers/crypto/tegra/tegra-se.h
@@ -420,6 +420,7 @@ struct tegra_se {
 	struct host1x_client client;
 	struct host1x_channel *channel;
 	struct tegra_se_cmdbuf *cmdbuf;
+	struct tegra_se_cmdbuf *keybuf;
 	struct crypto_engine *engine;
 	struct host1x_syncpt *syncpt;
 	struct device *dev;
@@ -502,7 +503,7 @@ void tegra_deinit_hash(struct tegra_se *se);
 int tegra_key_submit(struct tegra_se *se, const u8 *key,
 		     u32 keylen, u32 alg, u32 *keyid);
 void tegra_key_invalidate(struct tegra_se *se, u32 keyid, u32 alg);
-int tegra_se_host1x_submit(struct tegra_se *se, u32 size);
+int tegra_se_host1x_submit(struct tegra_se *se, struct tegra_se_cmdbuf *cmdbuf, u32 size);
 
 /* HOST1x OPCODES */
 static inline u32 host1x_opcode_setpayload(unsigned int payload)
-- 
2.43.2

Re: [PATCH 1/7] crypto: tegra: Use separate buffer for setkey

[Herbert Xu]

On Tue, Dec 17, 2024 at 09:42:01PM +0530, Akhil R wrote:
> The buffer which sends the commands to host1x was shared for all tasks
> in the engine. This causes a problem with the setkey() function as it
> gets called asynchronous to the crypto engine queue. Modifying the same
> cmdbuf in setkey() will corrupt the ongoing host1x task and in turn
> break the encryption/decryption operation. Hence use a separate cmdbuf
> for setkey().
> 
> Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
> Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
> ---
>  drivers/crypto/tegra/tegra-se-aes.c  | 16 ++++++++--------
>  drivers/crypto/tegra/tegra-se-hash.c | 13 +++++++------
>  drivers/crypto/tegra/tegra-se-key.c  | 10 ++++++++--
>  drivers/crypto/tegra/tegra-se-main.c | 16 ++++++++++++----
>  drivers/crypto/tegra/tegra-se.h      |  3 ++-
>  5 files changed, 37 insertions(+), 21 deletions(-)

So there is a maximum of 15 key slots? In that case you should not
be allocating them in setkey because there can be a lot more than
15 tfm's in the system.

Since the limit is so low they should only be allocated during an
encryption/decryption operation.

Cheers,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

RE: [PATCH 1/7] crypto: tegra: Use separate buffer for setkey

[Akhil R]

> On Tue, Dec 17, 2024 at 09:42:01PM +0530, Akhil R wrote:
> > The buffer which sends the commands to host1x was shared for all tasks
> > in the engine. This causes a problem with the setkey() function as it
> > gets called asynchronous to the crypto engine queue. Modifying the
> > same cmdbuf in setkey() will corrupt the ongoing host1x task and in
> > turn break the encryption/decryption operation. Hence use a separate
> > cmdbuf for setkey().
> >
> > Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine
> > driver")
> > Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
> > ---
> >  drivers/crypto/tegra/tegra-se-aes.c  | 16 ++++++++--------
> > drivers/crypto/tegra/tegra-se-hash.c | 13 +++++++------
> > drivers/crypto/tegra/tegra-se-key.c  | 10 ++++++++--
> > drivers/crypto/tegra/tegra-se-main.c | 16 ++++++++++++----
> >  drivers/crypto/tegra/tegra-se.h      |  3 ++-
> >  5 files changed, 37 insertions(+), 21 deletions(-)
> 
> So there is a maximum of 15 key slots? In that case you should not be allocating
> them in setkey because there can be a lot more than
> 15 tfm's in the system.
> 
> Since the limit is so low they should only be allocated during an
> encryption/decryption operation.

Yes. That's right. The hardware has only 15 keyslots.

I am working on a patch which will reserve few keyslots and use them during
encryption/decription operation in case the remaining keyslots get full. Means,
the setkey will try to get a keyslot, if it fails it will store the key in a variable. Then
during the encryption/decryption, it will use one of the reserved keyslot for the
operation.

This will allow users to have the capability of hardware protected keys and faster
operations if there are limited number of tfms. It also does not halt the operation
when there are more tfms.

Does it sound good, or do you think it will make the code overly complicated?

Regards,
Akhil

Re: [PATCH 1/7] crypto: tegra: Use separate buffer for setkey

[Herbert Xu]

On Tue, Dec 31, 2024 at 04:25:06AM +0000, Akhil R wrote:
>
> Does it sound good, or do you think it will make the code overly complicated?

My main concern was arbitrary failure when you exceeded the 16-slot
limit.  As long as that problem goes away I'm happy with any solution.

Thanks,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

RE: [PATCH 1/7] crypto: tegra: Use separate buffer for setkey

[Akhil R]

, Dec 31, 2024 at 04:25:06AM +0000, Akhil R wrote:
> >
> > Does it sound good, or do you think it will make the code overly complicated?
> 
> My main concern was arbitrary failure when you exceeded the 16-slot
> limit.  As long as that problem goes away I'm happy with any solution.

Thanks. I will send out a patch for this along with the other changes as the next version. 

Any concerns on the other patches in the series? I can push the updates together in
the next version, if anything.

Thanks,
Akhil

[PATCH 2/7] crypto: tegra: Do not use fixed size buffers

[Akhil R]

Allocate the buffer based on the request instead of a fixed buffer
length. In operations which may require larger buffer size, a fixed
buffer may fail.

Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
---
 drivers/crypto/tegra/tegra-se-aes.c  | 124 ++++++++++++++-------------
 drivers/crypto/tegra/tegra-se-hash.c |  38 +++++---
 drivers/crypto/tegra/tegra-se.h      |   2 -
 3 files changed, 89 insertions(+), 75 deletions(-)

diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index 5fc7e19b8ab8..b80786c5e4fd 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -263,12 +263,6 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
 	unsigned int cmdlen;
 	int ret;
 
-	rctx->datbuf.buf = dma_alloc_coherent(se->dev, SE_AES_BUFLEN,
-					      &rctx->datbuf.addr, GFP_KERNEL);
-	if (!rctx->datbuf.buf)
-		return -ENOMEM;
-
-	rctx->datbuf.size = SE_AES_BUFLEN;
 	rctx->iv = (u32 *)req->iv;
 	rctx->len = req->cryptlen;
 
@@ -278,6 +272,12 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
 			rctx->len += AES_BLOCK_SIZE - (rctx->len % AES_BLOCK_SIZE);
 	}
 
+	rctx->datbuf.size = rctx->len;
+	rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->datbuf.size,
+					      &rctx->datbuf.addr, GFP_KERNEL);
+	if (!rctx->datbuf.buf)
+		return -ENOMEM;
+
 	scatterwalk_map_and_copy(rctx->datbuf.buf, req->src, 0, req->cryptlen, 0);
 
 	/* Prepare the command and submit for execution */
@@ -289,7 +289,7 @@ static int tegra_aes_do_one_req(struct crypto_engine *engine, void *areq)
 	scatterwalk_map_and_copy(rctx->datbuf.buf, req->dst, 0, req->cryptlen, 1);
 
 	/* Free the buffer */
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
 			  rctx->datbuf.buf, rctx->datbuf.addr);
 
 	crypto_finalize_skcipher_request(se->engine, req, ret);
@@ -1117,6 +1117,11 @@ static int tegra_ccm_crypt_init(struct aead_request *req, struct tegra_se *se,
 	rctx->assoclen = req->assoclen;
 	rctx->authsize = crypto_aead_authsize(tfm);
 
+	if (rctx->encrypt)
+		rctx->cryptlen = req->cryptlen;
+	else
+		rctx->cryptlen = req->cryptlen - rctx->authsize;
+
 	memcpy(iv, req->iv, 16);
 
 	ret = tegra_ccm_check_iv(iv);
@@ -1145,30 +1150,26 @@ static int tegra_ccm_do_one_req(struct crypto_engine *engine, void *areq)
 	struct tegra_se *se = ctx->se;
 	int ret;
 
+	ret = tegra_ccm_crypt_init(req, se, rctx);
+	if (ret)
+		return ret;
+
 	/* Allocate buffers required */
-	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	rctx->inbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen + 100;
+	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->inbuf.size,
 					     &rctx->inbuf.addr, GFP_KERNEL);
 	if (!rctx->inbuf.buf)
 		return -ENOMEM;
 
-	rctx->inbuf.size = SE_AES_BUFLEN;
-
-	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	rctx->outbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen + 100;
+	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->outbuf.size,
 					      &rctx->outbuf.addr, GFP_KERNEL);
 	if (!rctx->outbuf.buf) {
 		ret = -ENOMEM;
 		goto outbuf_err;
 	}
 
-	rctx->outbuf.size = SE_AES_BUFLEN;
-
-	ret = tegra_ccm_crypt_init(req, se, rctx);
-	if (ret)
-		goto out;
-
 	if (rctx->encrypt) {
-		rctx->cryptlen = req->cryptlen;
-
 		/* CBC MAC Operation */
 		ret = tegra_ccm_compute_auth(ctx, rctx);
 		if (ret)
@@ -1179,8 +1180,6 @@ static int tegra_ccm_do_one_req(struct crypto_engine *engine, void *areq)
 		if (ret)
 			goto out;
 	} else {
-		rctx->cryptlen = req->cryptlen - ctx->authsize;
-
 		/* CTR operation */
 		ret = tegra_ccm_do_ctr(ctx, rctx);
 		if (ret)
@@ -1193,11 +1192,11 @@ static int tegra_ccm_do_one_req(struct crypto_engine *engine, void *areq)
 	}
 
 out:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->inbuf.size,
 			  rctx->outbuf.buf, rctx->outbuf.addr);
 
 outbuf_err:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->outbuf.size,
 			  rctx->inbuf.buf, rctx->inbuf.addr);
 
 	crypto_finalize_aead_request(ctx->se->engine, req, ret);
@@ -1213,23 +1212,6 @@ static int tegra_gcm_do_one_req(struct crypto_engine *engine, void *areq)
 	struct tegra_aead_reqctx *rctx = aead_request_ctx(req);
 	int ret;
 
-	/* Allocate buffers required */
-	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
-					     &rctx->inbuf.addr, GFP_KERNEL);
-	if (!rctx->inbuf.buf)
-		return -ENOMEM;
-
-	rctx->inbuf.size = SE_AES_BUFLEN;
-
-	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, SE_AES_BUFLEN,
-					      &rctx->outbuf.addr, GFP_KERNEL);
-	if (!rctx->outbuf.buf) {
-		ret = -ENOMEM;
-		goto outbuf_err;
-	}
-
-	rctx->outbuf.size = SE_AES_BUFLEN;
-
 	rctx->src_sg = req->src;
 	rctx->dst_sg = req->dst;
 	rctx->assoclen = req->assoclen;
@@ -1243,6 +1225,21 @@ static int tegra_gcm_do_one_req(struct crypto_engine *engine, void *areq)
 	memcpy(rctx->iv, req->iv, GCM_AES_IV_SIZE);
 	rctx->iv[3] = (1 << 24);
 
+	/* Allocate buffers required */
+	rctx->inbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen;
+	rctx->inbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->inbuf.size,
+					     &rctx->inbuf.addr, GFP_KERNEL);
+	if (!rctx->inbuf.buf)
+		return -ENOMEM;
+
+	rctx->outbuf.size = rctx->assoclen + rctx->authsize + rctx->cryptlen;
+	rctx->outbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->outbuf.size,
+					      &rctx->outbuf.addr, GFP_KERNEL);
+	if (!rctx->outbuf.buf) {
+		ret = -ENOMEM;
+		goto outbuf_err;
+	}
+
 	/* If there is associated data perform GMAC operation */
 	if (rctx->assoclen) {
 		ret = tegra_gcm_do_gmac(ctx, rctx);
@@ -1266,11 +1263,11 @@ static int tegra_gcm_do_one_req(struct crypto_engine *engine, void *areq)
 		ret = tegra_gcm_do_verify(ctx->se, rctx);
 
 out:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->outbuf.size,
 			  rctx->outbuf.buf, rctx->outbuf.addr);
 
 outbuf_err:
-	dma_free_coherent(ctx->se->dev, SE_AES_BUFLEN,
+	dma_free_coherent(ctx->se->dev, rctx->inbuf.size,
 			  rctx->inbuf.buf, rctx->inbuf.addr);
 
 	/* Finalize the request if there are no errors */
@@ -1497,6 +1494,11 @@ static int tegra_cmac_do_update(struct ahash_request *req)
 		return 0;
 	}
 
+	rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->datbuf.size,
+					      &rctx->datbuf.addr, GFP_KERNEL);
+	if (!rctx->datbuf.buf)
+		return -ENOMEM;
+
 	/* Copy the previous residue first */
 	if (rctx->residue.size)
 		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
@@ -1529,6 +1531,9 @@ static int tegra_cmac_do_update(struct ahash_request *req)
 	if (!(rctx->task & SHA_FINAL))
 		tegra_cmac_copy_result(ctx->se, rctx);
 
+	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
+			  rctx->datbuf.buf, rctx->datbuf.addr);
+
 	return ret;
 }
 
@@ -1543,10 +1548,20 @@ static int tegra_cmac_do_final(struct ahash_request *req)
 
 	if (!req->nbytes && !rctx->total_len && ctx->fallback_tfm) {
 		return crypto_shash_tfm_digest(ctx->fallback_tfm,
-					rctx->datbuf.buf, 0, req->result);
+					NULL, 0, req->result);
+	}
+
+	if (rctx->residue.size) {
+		rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->residue.size,
+						      &rctx->datbuf.addr, GFP_KERNEL);
+		if (!rctx->datbuf.buf) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+
+		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
 	}
 
-	memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
 	rctx->datbuf.size = rctx->residue.size;
 	rctx->total_len += rctx->residue.size;
 	rctx->config = tegra234_aes_cfg(SE_ALG_CMAC, 0);
@@ -1565,8 +1580,10 @@ static int tegra_cmac_do_final(struct ahash_request *req)
 		writel(0, se->base + se->hw->regs->result + (i * 4));
 
 out:
-	dma_free_coherent(se->dev, SE_SHA_BUFLEN,
-			  rctx->datbuf.buf, rctx->datbuf.addr);
+	if (rctx->residue.size)
+		dma_free_coherent(se->dev, rctx->datbuf.size,
+				  rctx->datbuf.buf, rctx->datbuf.addr);
+out_free:
 	dma_free_coherent(se->dev, crypto_ahash_blocksize(tfm) * 2,
 			  rctx->residue.buf, rctx->residue.addr);
 	return ret;
@@ -1672,28 +1689,15 @@ static int tegra_cmac_init(struct ahash_request *req)
 	rctx->residue.buf = dma_alloc_coherent(se->dev, rctx->blk_size * 2,
 					       &rctx->residue.addr, GFP_KERNEL);
 	if (!rctx->residue.buf)
-		goto resbuf_fail;
+		return -ENOMEM;
 
 	rctx->residue.size = 0;
 
-	rctx->datbuf.buf = dma_alloc_coherent(se->dev, SE_SHA_BUFLEN,
-					      &rctx->datbuf.addr, GFP_KERNEL);
-	if (!rctx->datbuf.buf)
-		goto datbuf_fail;
-
-	rctx->datbuf.size = 0;
-
 	/* Clear any previous result */
 	for (i = 0; i < CMAC_RESULT_REG_COUNT; i++)
 		writel(0, se->base + se->hw->regs->result + (i * 4));
 
 	return 0;
-
-datbuf_fail:
-	dma_free_coherent(se->dev, rctx->blk_size, rctx->residue.buf,
-			  rctx->residue.addr);
-resbuf_fail:
-	return -ENOMEM;
 }
 
 static int tegra_cmac_setkey(struct crypto_ahash *tfm, const u8 *key,
diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c
index a0460e624523..aed82d82b5fb 100644
--- a/drivers/crypto/tegra/tegra-se-hash.c
+++ b/drivers/crypto/tegra/tegra-se-hash.c
@@ -332,6 +332,11 @@ static int tegra_sha_do_update(struct ahash_request *req)
 		return 0;
 	}
 
+	rctx->datbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->datbuf.size,
+					      &rctx->datbuf.addr, GFP_KERNEL);
+	if (!rctx->datbuf.buf)
+		return -ENOMEM;
+
 	/* Copy the previous residue first */
 	if (rctx->residue.size)
 		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
@@ -368,6 +373,9 @@ static int tegra_sha_do_update(struct ahash_request *req)
 	if (!(rctx->task & SHA_FINAL))
 		tegra_sha_copy_hash_result(se, rctx);
 
+	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
+			  rctx->datbuf.buf, rctx->datbuf.addr);
+
 	return ret;
 }
 
@@ -380,7 +388,17 @@ static int tegra_sha_do_final(struct ahash_request *req)
 	u32 *cpuvaddr = se->cmdbuf->addr;
 	int size, ret = 0;
 
-	memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
+	if (rctx->residue.size) {
+		rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->residue.size,
+						      &rctx->datbuf.addr, GFP_KERNEL);
+		if (!rctx->datbuf.buf) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+
+		memcpy(rctx->datbuf.buf, rctx->residue.buf, rctx->residue.size);
+	}
+
 	rctx->datbuf.size = rctx->residue.size;
 	rctx->total_len += rctx->residue.size;
 
@@ -397,8 +415,10 @@ static int tegra_sha_do_final(struct ahash_request *req)
 	memcpy(req->result, rctx->digest.buf, rctx->digest.size);
 
 out:
-	dma_free_coherent(se->dev, SE_SHA_BUFLEN,
-			  rctx->datbuf.buf, rctx->datbuf.addr);
+	if (rctx->residue.size)
+		dma_free_coherent(se->dev, rctx->datbuf.size,
+				  rctx->datbuf.buf, rctx->datbuf.addr);
+out_free:
 	dma_free_coherent(se->dev, crypto_ahash_blocksize(tfm),
 			  rctx->residue.buf, rctx->residue.addr);
 	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
@@ -527,19 +547,11 @@ static int tegra_sha_init(struct ahash_request *req)
 	if (!rctx->residue.buf)
 		goto resbuf_fail;
 
-	rctx->datbuf.buf = dma_alloc_coherent(se->dev, SE_SHA_BUFLEN,
-					      &rctx->datbuf.addr, GFP_KERNEL);
-	if (!rctx->datbuf.buf)
-		goto datbuf_fail;
-
 	return 0;
 
-datbuf_fail:
-	dma_free_coherent(se->dev, rctx->blk_size, rctx->residue.buf,
-			  rctx->residue.addr);
 resbuf_fail:
-	dma_free_coherent(se->dev, SE_SHA_BUFLEN, rctx->datbuf.buf,
-			  rctx->datbuf.addr);
+	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
+			  rctx->digest.addr);
 digbuf_fail:
 	return -ENOMEM;
 }
diff --git a/drivers/crypto/tegra/tegra-se.h b/drivers/crypto/tegra/tegra-se.h
index b54aefe717a1..e196a90eedb9 100644
--- a/drivers/crypto/tegra/tegra-se.h
+++ b/drivers/crypto/tegra/tegra-se.h
@@ -340,8 +340,6 @@
 #define SE_CRYPTO_CTR_REG_COUNT			4
 #define SE_MAX_KEYSLOT				15
 #define SE_MAX_MEM_ALLOC			SZ_4M
-#define SE_AES_BUFLEN				0x8000
-#define SE_SHA_BUFLEN				0x2000
 
 #define SHA_FIRST	BIT(0)
 #define SHA_UPDATE	BIT(1)
-- 
2.43.2

[PATCH 3/7] crypto: tegra: check retrun value for hash do_one_req

[Akhil R]

Initialize and check the return value in hash *do_one_req() functions
and exit the function if there is an error. This fixes the
'uninitialized variable' warnings reported by testbots.

Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/r/202412071747.flPux4oB-lkp@intel.com/
Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
---
 drivers/crypto/tegra/tegra-se-aes.c  | 10 ++++++++--
 drivers/crypto/tegra/tegra-se-hash.c |  7 +++++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index b80786c5e4fd..6ed6da0ecc32 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -1596,18 +1596,24 @@ static int tegra_cmac_do_one_req(struct crypto_engine *engine, void *areq)
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
 	struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct tegra_se *se = ctx->se;
-	int ret;
+	int ret = 0;
 
 	if (rctx->task & SHA_UPDATE) {
 		ret = tegra_cmac_do_update(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_UPDATE;
 	}
 
 	if (rctx->task & SHA_FINAL) {
 		ret = tegra_cmac_do_final(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_FINAL;
 	}
-
+out:
 	crypto_finalize_hash_request(se->engine, req, ret);
 
 	return 0;
diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c
index aed82d82b5fb..d35bce81e017 100644
--- a/drivers/crypto/tegra/tegra-se-hash.c
+++ b/drivers/crypto/tegra/tegra-se-hash.c
@@ -437,14 +437,21 @@ static int tegra_sha_do_one_req(struct crypto_engine *engine, void *areq)
 
 	if (rctx->task & SHA_UPDATE) {
 		ret = tegra_sha_do_update(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_UPDATE;
 	}
 
 	if (rctx->task & SHA_FINAL) {
 		ret = tegra_sha_do_final(req);
+		if (ret)
+			goto out;
+
 		rctx->task &= ~SHA_FINAL;
 	}
 
+out:
 	crypto_finalize_hash_request(se->engine, req, ret);
 
 	return 0;
-- 
2.43.2

[PATCH 4/7] crypto: tegra: Transfer HASH init function to crypto engine

[Akhil R]

Ahash init() function was called asynchronous to the crypto engine queue.
This could corrupt the request context if there is any ongoing operation
for the same request. Queue the init function as well to the crypto
engine queue so that this scenario can be avoided.

Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
---
 drivers/crypto/tegra/tegra-se-aes.c  | 78 +++++++++++++---------
 drivers/crypto/tegra/tegra-se-hash.c | 98 ++++++++++++++++------------
 drivers/crypto/tegra/tegra-se.h      |  5 +-
 3 files changed, 109 insertions(+), 72 deletions(-)

diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index 6ed6da0ecc32..5d8237cda58f 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -1453,6 +1453,34 @@ static void tegra_cmac_paste_result(struct tegra_se *se, struct tegra_cmac_reqct
 		       se->base + se->hw->regs->result + (i * 4));
 }
 
+static int tegra_cmac_do_init(struct ahash_request *req)
+{
+	struct tegra_cmac_reqctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct tegra_se *se = ctx->se;
+	int i;
+
+	rctx->total_len = 0;
+	rctx->datbuf.size = 0;
+	rctx->residue.size = 0;
+	rctx->task |= SHA_FIRST;
+	rctx->blk_size = crypto_ahash_blocksize(tfm);
+
+	rctx->residue.buf = dma_alloc_coherent(se->dev, rctx->blk_size * 2,
+					       &rctx->residue.addr, GFP_KERNEL);
+	if (!rctx->residue.buf)
+		return -ENOMEM;
+
+	rctx->residue.size = 0;
+
+	/* Clear any previous result */
+	for (i = 0; i < CMAC_RESULT_REG_COUNT; i++)
+		writel(0, se->base + se->hw->regs->result + (i * 4));
+
+	return 0;
+}
+
 static int tegra_cmac_do_update(struct ahash_request *req)
 {
 	struct tegra_cmac_reqctx *rctx = ahash_request_ctx(req);
@@ -1598,6 +1626,14 @@ static int tegra_cmac_do_one_req(struct crypto_engine *engine, void *areq)
 	struct tegra_se *se = ctx->se;
 	int ret = 0;
 
+	if (rctx->task & SHA_INIT) {
+		ret = tegra_cmac_do_init(req);
+		if (ret)
+			goto out;
+
+		rctx->task &= ~SHA_INIT;
+	}
+
 	if (rctx->task & SHA_UPDATE) {
 		ret = tegra_cmac_do_update(req);
 		if (ret)
@@ -1678,34 +1714,6 @@ static void tegra_cmac_cra_exit(struct crypto_tfm *tfm)
 	tegra_key_invalidate(ctx->se, ctx->key_id, ctx->alg);
 }
 
-static int tegra_cmac_init(struct ahash_request *req)
-{
-	struct tegra_cmac_reqctx *rctx = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct tegra_se *se = ctx->se;
-	int i;
-
-	rctx->total_len = 0;
-	rctx->datbuf.size = 0;
-	rctx->residue.size = 0;
-	rctx->task = SHA_FIRST;
-	rctx->blk_size = crypto_ahash_blocksize(tfm);
-
-	rctx->residue.buf = dma_alloc_coherent(se->dev, rctx->blk_size * 2,
-					       &rctx->residue.addr, GFP_KERNEL);
-	if (!rctx->residue.buf)
-		return -ENOMEM;
-
-	rctx->residue.size = 0;
-
-	/* Clear any previous result */
-	for (i = 0; i < CMAC_RESULT_REG_COUNT; i++)
-		writel(0, se->base + se->hw->regs->result + (i * 4));
-
-	return 0;
-}
-
 static int tegra_cmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 			     unsigned int keylen)
 {
@@ -1722,6 +1730,17 @@ static int tegra_cmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 	return tegra_key_submit(ctx->se, key, keylen, ctx->alg, &ctx->key_id);
 }
 
+static int tegra_cmac_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct tegra_cmac_reqctx *rctx = ahash_request_ctx(req);
+
+	rctx->task = SHA_INIT;
+
+	return crypto_transfer_hash_request_to_engine(ctx->se->engine, req);
+}
+
 static int tegra_cmac_update(struct ahash_request *req)
 {
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -1761,8 +1780,7 @@ static int tegra_cmac_digest(struct ahash_request *req)
 	struct tegra_cmac_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct tegra_cmac_reqctx *rctx = ahash_request_ctx(req);
 
-	tegra_cmac_init(req);
-	rctx->task |= SHA_UPDATE | SHA_FINAL;
+	rctx->task |= SHA_INIT | SHA_UPDATE | SHA_FINAL;
 
 	return crypto_transfer_hash_request_to_engine(ctx->se->engine, req);
 }
diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c
index d35bce81e017..07e4c7320ec8 100644
--- a/drivers/crypto/tegra/tegra-se-hash.c
+++ b/drivers/crypto/tegra/tegra-se-hash.c
@@ -296,6 +296,44 @@ static void tegra_sha_paste_hash_result(struct tegra_se *se, struct tegra_sha_re
 		       se->base + se->hw->regs->result + (i * 4));
 }
 
+static int tegra_sha_do_init(struct ahash_request *req)
+{
+	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct tegra_se *se = ctx->se;
+
+	if (ctx->fallback)
+		return tegra_sha_fallback_init(req);
+
+	rctx->total_len = 0;
+	rctx->datbuf.size = 0;
+	rctx->residue.size = 0;
+	rctx->key_id = ctx->key_id;
+	rctx->task |= SHA_FIRST;
+	rctx->alg = ctx->alg;
+	rctx->blk_size = crypto_ahash_blocksize(tfm);
+	rctx->digest.size = crypto_ahash_digestsize(tfm);
+
+	rctx->digest.buf = dma_alloc_coherent(se->dev, rctx->digest.size,
+					      &rctx->digest.addr, GFP_KERNEL);
+	if (!rctx->digest.buf)
+		goto digbuf_fail;
+
+	rctx->residue.buf = dma_alloc_coherent(se->dev, rctx->blk_size,
+					       &rctx->residue.addr, GFP_KERNEL);
+	if (!rctx->residue.buf)
+		goto resbuf_fail;
+
+	return 0;
+
+resbuf_fail:
+	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
+			  rctx->digest.addr);
+digbuf_fail:
+	return -ENOMEM;
+}
+
 static int tegra_sha_do_update(struct ahash_request *req)
 {
 	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(req));
@@ -435,6 +473,14 @@ static int tegra_sha_do_one_req(struct crypto_engine *engine, void *areq)
 	struct tegra_se *se = ctx->se;
 	int ret = 0;
 
+	if (rctx->task & SHA_INIT) {
+		ret = tegra_sha_do_init(req);
+		if (ret)
+			goto out;
+
+		rctx->task &= ~SHA_INIT;
+	}
+
 	if (rctx->task & SHA_UPDATE) {
 		ret = tegra_sha_do_update(req);
 		if (ret)
@@ -525,44 +571,6 @@ static void tegra_sha_cra_exit(struct crypto_tfm *tfm)
 	tegra_key_invalidate(ctx->se, ctx->key_id, ctx->alg);
 }
 
-static int tegra_sha_init(struct ahash_request *req)
-{
-	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(tfm);
-	struct tegra_se *se = ctx->se;
-
-	if (ctx->fallback)
-		return tegra_sha_fallback_init(req);
-
-	rctx->total_len = 0;
-	rctx->datbuf.size = 0;
-	rctx->residue.size = 0;
-	rctx->key_id = ctx->key_id;
-	rctx->task = SHA_FIRST;
-	rctx->alg = ctx->alg;
-	rctx->blk_size = crypto_ahash_blocksize(tfm);
-	rctx->digest.size = crypto_ahash_digestsize(tfm);
-
-	rctx->digest.buf = dma_alloc_coherent(se->dev, rctx->digest.size,
-					      &rctx->digest.addr, GFP_KERNEL);
-	if (!rctx->digest.buf)
-		goto digbuf_fail;
-
-	rctx->residue.buf = dma_alloc_coherent(se->dev, rctx->blk_size,
-					       &rctx->residue.addr, GFP_KERNEL);
-	if (!rctx->residue.buf)
-		goto resbuf_fail;
-
-	return 0;
-
-resbuf_fail:
-	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
-			  rctx->digest.addr);
-digbuf_fail:
-	return -ENOMEM;
-}
-
 static int tegra_hmac_fallback_setkey(struct tegra_sha_ctx *ctx, const u8 *key,
 				      unsigned int keylen)
 {
@@ -588,6 +596,17 @@ static int tegra_hmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 	return tegra_key_submit(ctx->se, key, keylen, ctx->alg, &ctx->key_id);
 }
 
+static int tegra_sha_init(struct ahash_request *req)
+{
+	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct tegra_sha_ctx *ctx = crypto_ahash_ctx(tfm);
+
+	rctx->task = SHA_INIT;
+
+	return crypto_transfer_hash_request_to_engine(ctx->se->engine, req);
+}
+
 static int tegra_sha_update(struct ahash_request *req)
 {
 	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
@@ -639,8 +658,7 @@ static int tegra_sha_digest(struct ahash_request *req)
 	if (ctx->fallback)
 		return tegra_sha_fallback_digest(req);
 
-	tegra_sha_init(req);
-	rctx->task |= SHA_UPDATE | SHA_FINAL;
+	rctx->task |= SHA_INIT | SHA_UPDATE | SHA_FINAL;
 
 	return crypto_transfer_hash_request_to_engine(ctx->se->engine, req);
 }
diff --git a/drivers/crypto/tegra/tegra-se.h b/drivers/crypto/tegra/tegra-se.h
index e196a90eedb9..e1ec37bfb80a 100644
--- a/drivers/crypto/tegra/tegra-se.h
+++ b/drivers/crypto/tegra/tegra-se.h
@@ -342,8 +342,9 @@
 #define SE_MAX_MEM_ALLOC			SZ_4M
 
 #define SHA_FIRST	BIT(0)
-#define SHA_UPDATE	BIT(1)
-#define SHA_FINAL	BIT(2)
+#define SHA_INIT	BIT(1)
+#define SHA_UPDATE	BIT(2)
+#define SHA_FINAL	BIT(3)
 
 /* Security Engine operation modes */
 enum se_aes_alg {
-- 
2.43.2

[PATCH 5/7] crypto: tegra: Fix HASH intermediate result handling

[Akhil R]

The intermediate hash values generated during an update task were
handled incorrectly in the driver. The values have a defined format for
each algorithm. Copying and pasting from the HASH_RESULT register
balantly would not work for all the supported algorithms. This incorrect
handling causes failures when there is a context switch between multiple
operations.

To handle the expected format correctly, add a separate buffer for
storing the intermediate results for each request. Remove the previous
copy/paste functions which read/wrote to the registers directly. Instead
configure the hardware to get the intermediate result copied to the
buffer and use host1x path to restore the intermediate hash results.

Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
---
 drivers/crypto/tegra/tegra-se-hash.c | 151 +++++++++++++++++----------
 drivers/crypto/tegra/tegra-se.h      |   1 +
 2 files changed, 99 insertions(+), 53 deletions(-)

diff --git a/drivers/crypto/tegra/tegra-se-hash.c b/drivers/crypto/tegra/tegra-se-hash.c
index 07e4c7320ec8..407ed696a770 100644
--- a/drivers/crypto/tegra/tegra-se-hash.c
+++ b/drivers/crypto/tegra/tegra-se-hash.c
@@ -34,6 +34,7 @@ struct tegra_sha_reqctx {
 	struct tegra_se_datbuf datbuf;
 	struct tegra_se_datbuf residue;
 	struct tegra_se_datbuf digest;
+	struct tegra_se_datbuf intr_res;
 	unsigned int alg;
 	unsigned int config;
 	unsigned int total_len;
@@ -211,11 +212,64 @@ static int tegra_sha_fallback_export(struct ahash_request *req, void *out)
 	return crypto_ahash_export(&rctx->fallback_req, out);
 }
 
-static int tegra_sha_prep_cmd(struct tegra_se *se, u32 *cpuvaddr,
+static int tegra_se_insert_hash_result(struct tegra_sha_ctx *ctx, u32 *cpuvaddr,
 			      struct tegra_sha_reqctx *rctx)
 {
+	u32 *res = (u32 *)rctx->intr_res.buf;
+	int i = 0, j, idx;
+
+	cpuvaddr[i++] = 0;
+	cpuvaddr[i++] = host1x_opcode_setpayload(HASH_RESULT_REG_COUNT);
+	cpuvaddr[i++] = se_host1x_opcode_incr_w(SE_SHA_HASH_RESULT);
+
+	for (j = 0; j < HASH_RESULT_REG_COUNT; j++) {
+		int idx = j;
+
+		/*
+		 * The initial, intermediate and final hash value of SHA-384, SHA-512
+		 * in SHA_HASH_RESULT registers follow the below layout of bytes.
+		 *
+		 * +---------------+------------+
+		 * | HASH_RESULT_0 | B4...B7    |
+		 * +---------------+------------+
+		 * | HASH_RESULT_1 | B0...B3    |
+		 * +---------------+------------+
+		 * | HASH_RESULT_2 | B12...B15  |
+		 * +---------------+------------+
+		 * | HASH_RESULT_3 | B8...B11   |
+		 * +---------------+------------+
+		 * |            ......          |
+		 * +---------------+------------+
+		 * | HASH_RESULT_14| B60...B63  |
+		 * +---------------+------------+
+		 * | HASH_RESULT_15| B56...B59  |
+		 * +---------------+------------+
+		 *
+		 */
+		if (ctx->alg == SE_ALG_SHA384 || ctx->alg == SE_ALG_SHA512)
+			idx = (j % 2)? j - 1: j + 1;
+
+		/* For SHA-1, SHA-224, SHA-256, SHA-384, SHA-512 the initial
+		 * intermediate and final hash value when stored in
+		 * SHA_HASH_RESULT registers, the byte order is NOT in
+		 * little-endian.
+		 */
+		if (ctx->alg <= SE_ALG_SHA512)
+			cpuvaddr[i++] = be32_to_cpu(res[idx]);
+		else
+			cpuvaddr[i++] = res[idx];
+	}
+
+	return i;
+}
+
+
+static int tegra_sha_prep_cmd(struct tegra_sha_ctx *ctx, u32 *cpuvaddr,
+			      struct tegra_sha_reqctx *rctx)
+{
+	struct tegra_se *se = ctx->se;
 	u64 msg_len, msg_left;
-	int i = 0;
+	int i = 0, j;
 
 	msg_len = rctx->total_len * 8;
 	msg_left = rctx->datbuf.size * 8;
@@ -241,7 +295,7 @@ static int tegra_sha_prep_cmd(struct tegra_se *se, u32 *cpuvaddr,
 	cpuvaddr[i++] = upper_32_bits(msg_left);
 	cpuvaddr[i++] = 0;
 	cpuvaddr[i++] = 0;
-	cpuvaddr[i++] = host1x_opcode_setpayload(6);
+	cpuvaddr[i++] = host1x_opcode_setpayload(2);
 	cpuvaddr[i++] = se_host1x_opcode_incr_w(SE_SHA_CFG);
 	cpuvaddr[i++] = rctx->config;
 
@@ -249,15 +303,29 @@ static int tegra_sha_prep_cmd(struct tegra_se *se, u32 *cpuvaddr,
 		cpuvaddr[i++] = SE_SHA_TASK_HASH_INIT;
 		rctx->task &= ~SHA_FIRST;
 	} else {
-		cpuvaddr[i++] = 0;
+		/*
+		 * If it isn't the first task, program the HASH_RESULT register
+		 * with the intermediate result from the previous task
+		 */
+		i += tegra_se_insert_hash_result(ctx, cpuvaddr + i, rctx);
 	}
 
+	cpuvaddr[i++] = host1x_opcode_setpayload(4);
+	cpuvaddr[i++] = se_host1x_opcode_incr_w(SE_SHA_IN_ADDR);
 	cpuvaddr[i++] = rctx->datbuf.addr;
 	cpuvaddr[i++] = (u32)(SE_ADDR_HI_MSB(upper_32_bits(rctx->datbuf.addr)) |
 				SE_ADDR_HI_SZ(rctx->datbuf.size));
-	cpuvaddr[i++] = rctx->digest.addr;
-	cpuvaddr[i++] = (u32)(SE_ADDR_HI_MSB(upper_32_bits(rctx->digest.addr)) |
-				SE_ADDR_HI_SZ(rctx->digest.size));
+
+	if (rctx->task & SHA_UPDATE) {
+		cpuvaddr[i++] = rctx->intr_res.addr;
+		cpuvaddr[i++] = (u32)(SE_ADDR_HI_MSB(upper_32_bits(rctx->intr_res.addr)) |
+					SE_ADDR_HI_SZ(rctx->intr_res.size));
+	} else {
+		cpuvaddr[i++] = rctx->digest.addr;
+		cpuvaddr[i++] = (u32)(SE_ADDR_HI_MSB(upper_32_bits(rctx->digest.addr)) |
+					SE_ADDR_HI_SZ(rctx->digest.size));
+	}
+
 	if (rctx->key_id) {
 		cpuvaddr[i++] = host1x_opcode_setpayload(1);
 		cpuvaddr[i++] = se_host1x_opcode_nonincr_w(SE_SHA_CRYPTO_CFG);
@@ -266,36 +334,18 @@ static int tegra_sha_prep_cmd(struct tegra_se *se, u32 *cpuvaddr,
 
 	cpuvaddr[i++] = host1x_opcode_setpayload(1);
 	cpuvaddr[i++] = se_host1x_opcode_nonincr_w(SE_SHA_OPERATION);
-	cpuvaddr[i++] = SE_SHA_OP_WRSTALL |
-			SE_SHA_OP_START |
+	cpuvaddr[i++] = SE_SHA_OP_WRSTALL | SE_SHA_OP_START |
 			SE_SHA_OP_LASTBUF;
 	cpuvaddr[i++] = se_host1x_opcode_nonincr(host1x_uclass_incr_syncpt_r(), 1);
 	cpuvaddr[i++] = host1x_uclass_incr_syncpt_cond_f(1) |
 			host1x_uclass_incr_syncpt_indx_f(se->syncpt_id);
 
-	dev_dbg(se->dev, "msg len %llu msg left %llu cfg %#x",
-		msg_len, msg_left, rctx->config);
+	dev_dbg(se->dev, "msg len %llu msg left %llu sz %lu cfg %#x",
+		msg_len, msg_left, rctx->datbuf.size, rctx->config);
 
 	return i;
 }
 
-static void tegra_sha_copy_hash_result(struct tegra_se *se, struct tegra_sha_reqctx *rctx)
-{
-	int i;
-
-	for (i = 0; i < HASH_RESULT_REG_COUNT; i++)
-		rctx->result[i] = readl(se->base + se->hw->regs->result + (i * 4));
-}
-
-static void tegra_sha_paste_hash_result(struct tegra_se *se, struct tegra_sha_reqctx *rctx)
-{
-	int i;
-
-	for (i = 0; i < HASH_RESULT_REG_COUNT; i++)
-		writel(rctx->result[i],
-		       se->base + se->hw->regs->result + (i * 4));
-}
-
 static int tegra_sha_do_init(struct ahash_request *req)
 {
 	struct tegra_sha_reqctx *rctx = ahash_request_ctx(req);
@@ -325,8 +375,17 @@ static int tegra_sha_do_init(struct ahash_request *req)
 	if (!rctx->residue.buf)
 		goto resbuf_fail;
 
+	rctx->intr_res.size = HASH_RESULT_REG_COUNT * 4;
+	rctx->intr_res.buf = dma_alloc_coherent(se->dev, rctx->intr_res.size,
+					       &rctx->intr_res.addr, GFP_KERNEL);
+	if (!rctx->intr_res.buf)
+		goto intr_res_fail;
+
 	return 0;
 
+intr_res_fail:
+	dma_free_coherent(se->dev, rctx->residue.size, rctx->residue.buf,
+			  rctx->residue.addr);
 resbuf_fail:
 	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
 			  rctx->digest.addr);
@@ -356,7 +415,6 @@ static int tegra_sha_do_update(struct ahash_request *req)
 
 	rctx->src_sg = req->src;
 	rctx->datbuf.size = (req->nbytes + rctx->residue.size) - nresidue;
-	rctx->total_len += rctx->datbuf.size;
 
 	/*
 	 * If nbytes are less than a block size, copy it residue and
@@ -365,12 +423,12 @@ static int tegra_sha_do_update(struct ahash_request *req)
 	if (nblks < 1) {
 		scatterwalk_map_and_copy(rctx->residue.buf + rctx->residue.size,
 					 rctx->src_sg, 0, req->nbytes, 0);
-
 		rctx->residue.size += req->nbytes;
+
 		return 0;
 	}
 
-	rctx->datbuf.buf = dma_alloc_coherent(ctx->se->dev, rctx->datbuf.size,
+	rctx->datbuf.buf = dma_alloc_coherent(se->dev, rctx->datbuf.size,
 					      &rctx->datbuf.addr, GFP_KERNEL);
 	if (!rctx->datbuf.buf)
 		return -ENOMEM;
@@ -387,31 +445,15 @@ static int tegra_sha_do_update(struct ahash_request *req)
 
 	/* Update residue value with the residue after current block */
 	rctx->residue.size = nresidue;
+	rctx->total_len += rctx->datbuf.size;
 
 	rctx->config = tegra_sha_get_config(rctx->alg) |
-			SE_SHA_DST_HASH_REG;
-
-	/*
-	 * If this is not the first 'update' call, paste the previous copied
-	 * intermediate results to the registers so that it gets picked up.
-	 * This is to support the import/export functionality.
-	 */
-	if (!(rctx->task & SHA_FIRST))
-		tegra_sha_paste_hash_result(se, rctx);
-
-	size = tegra_sha_prep_cmd(se, cpuvaddr, rctx);
+			SE_SHA_DST_MEMORY;
 
+	size = tegra_sha_prep_cmd(ctx, cpuvaddr, rctx);
 	ret = tegra_se_host1x_submit(se, se->cmdbuf, size);
 
-	/*
-	 * If this is not the final update, copy the intermediate results
-	 * from the registers so that it can be used in the next 'update'
-	 * call. This is to support the import/export functionality.
-	 */
-	if (!(rctx->task & SHA_FINAL))
-		tegra_sha_copy_hash_result(se, rctx);
-
-	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
+	dma_free_coherent(se->dev, rctx->datbuf.size,
 			  rctx->datbuf.buf, rctx->datbuf.addr);
 
 	return ret;
@@ -443,8 +485,7 @@ static int tegra_sha_do_final(struct ahash_request *req)
 	rctx->config = tegra_sha_get_config(rctx->alg) |
 		       SE_SHA_DST_MEMORY;
 
-	size = tegra_sha_prep_cmd(se, cpuvaddr, rctx);
-
+	size = tegra_sha_prep_cmd(ctx, cpuvaddr, rctx);
 	ret = tegra_se_host1x_submit(se, se->cmdbuf, size);
 	if (ret)
 		goto out;
@@ -461,6 +502,10 @@ static int tegra_sha_do_final(struct ahash_request *req)
 			  rctx->residue.buf, rctx->residue.addr);
 	dma_free_coherent(se->dev, rctx->digest.size, rctx->digest.buf,
 			  rctx->digest.addr);
+
+	dma_free_coherent(se->dev, rctx->intr_res.size, rctx->intr_res.buf,
+			  rctx->intr_res.addr);
+
 	return ret;
 }
 
diff --git a/drivers/crypto/tegra/tegra-se.h b/drivers/crypto/tegra/tegra-se.h
index e1ec37bfb80a..0f5bcf27358b 100644
--- a/drivers/crypto/tegra/tegra-se.h
+++ b/drivers/crypto/tegra/tegra-se.h
@@ -24,6 +24,7 @@
 #define SE_STREAM_ID					0x90
 
 #define SE_SHA_CFG					0x4004
+#define SE_SHA_IN_ADDR					0x400c
 #define SE_SHA_KEY_ADDR					0x4094
 #define SE_SHA_KEY_DATA					0x4098
 #define SE_SHA_KEYMANIFEST				0x409c
-- 
2.43.2

[PATCH 6/7] crypto: tegra: Fix CMAC intermediate result handling

[Akhil R]

Saving and restoring of the intermediate results are needed if there is
context switch caused by another ongoing request on the same engine.
This is therefore not only to support import/export functionality.
Hence, save and restore the intermediate result for every non-first task.

Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
---
 drivers/crypto/tegra/tegra-se-aes.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index 5d8237cda58f..cdcf05e235ca 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -1541,9 +1541,8 @@ static int tegra_cmac_do_update(struct ahash_request *req)
 	rctx->residue.size = nresidue;
 
 	/*
-	 * If this is not the first 'update' call, paste the previous copied
+	 * If this is not the first task, paste the previous copied
 	 * intermediate results to the registers so that it gets picked up.
-	 * This is to support the import/export functionality.
 	 */
 	if (!(rctx->task & SHA_FIRST))
 		tegra_cmac_paste_result(ctx->se, rctx);
@@ -1551,13 +1550,7 @@ static int tegra_cmac_do_update(struct ahash_request *req)
 	cmdlen = tegra_cmac_prep_cmd(ctx, rctx);
 	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
 
-	/*
-	 * If this is not the final update, copy the intermediate results
-	 * from the registers so that it can be used in the next 'update'
-	 * call. This is to support the import/export functionality.
-	 */
-	if (!(rctx->task & SHA_FINAL))
-		tegra_cmac_copy_result(ctx->se, rctx);
+	tegra_cmac_copy_result(ctx->se, rctx);
 
 	dma_free_coherent(ctx->se->dev, rctx->datbuf.size,
 			  rctx->datbuf.buf, rctx->datbuf.addr);
@@ -1594,6 +1587,13 @@ static int tegra_cmac_do_final(struct ahash_request *req)
 	rctx->total_len += rctx->residue.size;
 	rctx->config = tegra234_aes_cfg(SE_ALG_CMAC, 0);
 
+	/*
+	 * If this is not the first task, paste the previous copied
+	 * intermediate results to the registers so that it gets picked up.
+	 */
+	if (!(rctx->task & SHA_FIRST))
+		tegra_cmac_paste_result(ctx->se, rctx);
+
 	/* Prepare command and submit */
 	cmdlen = tegra_cmac_prep_cmd(ctx, rctx);
 	ret = tegra_se_host1x_submit(se, se->cmdbuf, cmdlen);
-- 
2.43.2

[PATCH 7/7] crypto: tegra: Set IV to NULL explicitly for AES ECB

[Akhil R]

It may happen that the variable req->iv may have stale values or
zero sized buffer by default and may end up getting used during
encryption/decryption. This inturn may corrupt the results or break the
operation. Set the req->iv variable to NULL explicitly for algorithms
like AES-ECB where IV is not used.

Fixes:  0880bb3b00c8 ("crypto: tegra - Add Tegra Security Engine driver")
Signed-off-by: Akhil R <akhilrajeev@nvidia.com>
---
 drivers/crypto/tegra/tegra-se-aes.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/crypto/tegra/tegra-se-aes.c b/drivers/crypto/tegra/tegra-se-aes.c
index cdcf05e235ca..be0a0b51f5a5 100644
--- a/drivers/crypto/tegra/tegra-se-aes.c
+++ b/drivers/crypto/tegra/tegra-se-aes.c
@@ -443,6 +443,9 @@ static int tegra_aes_crypt(struct skcipher_request *req, bool encrypt)
 	if (!req->cryptlen)
 		return 0;
 
+	if (ctx->alg == SE_ALG_ECB)
+		req->iv = NULL;
+
 	rctx->encrypt = encrypt;
 	rctx->config = tegra234_aes_cfg(ctx->alg, encrypt);
 	rctx->crypto_config = tegra234_aes_crypto_cfg(ctx->alg, encrypt);
-- 
2.43.2