[PATCH AUTOSEL 4.19 070/191] crypto: chacha20 - Fix chacha20_block() keystream alignment (again)

[PATCH AUTOSEL 4.19 070/191] crypto: chacha20 - Fix chacha20_block() keystream alignment (again)

[Sasha Levin]

From: Eric Biggers <ebiggers@google.com>

[ Upstream commit a5e9f557098e54af44ade5d501379be18435bfbf ]

In commit 9f480faec58c ("crypto: chacha20 - Fix keystream alignment for
chacha20_block()"), I had missed that chacha20_block() can be called
directly on the buffer passed to get_random_bytes(), which can have any
alignment.  So, while my commit didn't break anything, it didn't fully
solve the alignment problems.

Revert my solution and just update chacha20_block() to use
put_unaligned_le32(), so the output buffer need not be aligned.
This is simpler, and on many CPUs it's the same speed.

But, I kept the 'tmp' buffers in extract_crng_user() and
_get_random_bytes() 4-byte aligned, since that alignment is actually
needed for _crng_backtrack_protect() too.

Reported-by: Stephan Müller <smueller@chronox.de>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 crypto/chacha20_generic.c |  7 ++++---
 drivers/char/random.c     | 24 ++++++++++++------------
 include/crypto/chacha20.h |  3 +--
 lib/chacha20.c            |  6 +++---
 4 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c
index e451c3cb6a56e..3ae96587caf9a 100644
--- a/crypto/chacha20_generic.c
+++ b/crypto/chacha20_generic.c
@@ -18,20 +18,21 @@
 static void chacha20_docrypt(u32 *state, u8 *dst, const u8 *src,
 			     unsigned int bytes)
 {
-	u32 stream[CHACHA20_BLOCK_WORDS];
+	/* aligned to potentially speed up crypto_xor() */
+	u8 stream[CHACHA20_BLOCK_SIZE] __aligned(sizeof(long));
 
 	if (dst != src)
 		memcpy(dst, src, bytes);
 
 	while (bytes >= CHACHA20_BLOCK_SIZE) {
 		chacha20_block(state, stream);
-		crypto_xor(dst, (const u8 *)stream, CHACHA20_BLOCK_SIZE);
+		crypto_xor(dst, stream, CHACHA20_BLOCK_SIZE);
 		bytes -= CHACHA20_BLOCK_SIZE;
 		dst += CHACHA20_BLOCK_SIZE;
 	}
 	if (bytes) {
 		chacha20_block(state, stream);
-		crypto_xor(dst, (const u8 *)stream, bytes);
+		crypto_xor(dst, stream, bytes);
 	}
 }
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 0a84b7f468ad0..86fe1df902393 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -433,9 +433,9 @@ static int crng_init_cnt = 0;
 static unsigned long crng_global_init_time = 0;
 #define CRNG_INIT_CNT_THRESH (2*CHACHA20_KEY_SIZE)
 static void _extract_crng(struct crng_state *crng,
-			  __u32 out[CHACHA20_BLOCK_WORDS]);
+			  __u8 out[CHACHA20_BLOCK_SIZE]);
 static void _crng_backtrack_protect(struct crng_state *crng,
-				    __u32 tmp[CHACHA20_BLOCK_WORDS], int used);
+				    __u8 tmp[CHACHA20_BLOCK_SIZE], int used);
 static void process_random_ready_list(void);
 static void _get_random_bytes(void *buf, int nbytes);
 
@@ -929,7 +929,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 	unsigned long	flags;
 	int		i, num;
 	union {
-		__u32	block[CHACHA20_BLOCK_WORDS];
+		__u8	block[CHACHA20_BLOCK_SIZE];
 		__u32	key[8];
 	} buf;
 
@@ -976,7 +976,7 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
 }
 
 static void _extract_crng(struct crng_state *crng,
-			  __u32 out[CHACHA20_BLOCK_WORDS])
+			  __u8 out[CHACHA20_BLOCK_SIZE])
 {
 	unsigned long v, flags;
 
@@ -993,7 +993,7 @@ static void _extract_crng(struct crng_state *crng,
 	spin_unlock_irqrestore(&crng->lock, flags);
 }
 
-static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
+static void extract_crng(__u8 out[CHACHA20_BLOCK_SIZE])
 {
 	struct crng_state *crng = NULL;
 
@@ -1011,7 +1011,7 @@ static void extract_crng(__u32 out[CHACHA20_BLOCK_WORDS])
  * enough) to mutate the CRNG key to provide backtracking protection.
  */
 static void _crng_backtrack_protect(struct crng_state *crng,
-				    __u32 tmp[CHACHA20_BLOCK_WORDS], int used)
+				    __u8 tmp[CHACHA20_BLOCK_SIZE], int used)
 {
 	unsigned long	flags;
 	__u32		*s, *d;
@@ -1023,14 +1023,14 @@ static void _crng_backtrack_protect(struct crng_state *crng,
 		used = 0;
 	}
 	spin_lock_irqsave(&crng->lock, flags);
-	s = &tmp[used / sizeof(__u32)];
+	s = (__u32 *) &tmp[used];
 	d = &crng->state[4];
 	for (i=0; i < 8; i++)
 		*d++ ^= *s++;
 	spin_unlock_irqrestore(&crng->lock, flags);
 }
 
-static void crng_backtrack_protect(__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
+static void crng_backtrack_protect(__u8 tmp[CHACHA20_BLOCK_SIZE], int used)
 {
 	struct crng_state *crng = NULL;
 
@@ -1046,7 +1046,7 @@ static void crng_backtrack_protect(__u32 tmp[CHACHA20_BLOCK_WORDS], int used)
 static ssize_t extract_crng_user(void __user *buf, size_t nbytes)
 {
 	ssize_t ret = 0, i = CHACHA20_BLOCK_SIZE;
-	__u32 tmp[CHACHA20_BLOCK_WORDS];
+	__u8 tmp[CHACHA20_BLOCK_SIZE] __aligned(4);
 	int large_request = (nbytes > 256);
 
 	while (nbytes) {
@@ -1625,7 +1625,7 @@ static void _warn_unseeded_randomness(const char *func_name, void *caller,
  */
 static void _get_random_bytes(void *buf, int nbytes)
 {
-	__u32 tmp[CHACHA20_BLOCK_WORDS];
+	__u8 tmp[CHACHA20_BLOCK_SIZE] __aligned(4);
 
 	trace_get_random_bytes(nbytes, _RET_IP_);
 
@@ -2251,7 +2251,7 @@ u64 get_random_u64(void)
 	batch = raw_cpu_ptr(&batched_entropy_u64);
 	spin_lock_irqsave(&batch->batch_lock, flags);
 	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
-		extract_crng((__u32 *)batch->entropy_u64);
+		extract_crng((u8 *)batch->entropy_u64);
 		batch->position = 0;
 	}
 	ret = batch->entropy_u64[batch->position++];
@@ -2278,7 +2278,7 @@ u32 get_random_u32(void)
 	batch = raw_cpu_ptr(&batched_entropy_u32);
 	spin_lock_irqsave(&batch->batch_lock, flags);
 	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
-		extract_crng(batch->entropy_u32);
+		extract_crng((u8 *)batch->entropy_u32);
 		batch->position = 0;
 	}
 	ret = batch->entropy_u32[batch->position++];
diff --git a/include/crypto/chacha20.h b/include/crypto/chacha20.h
index b83d66073db03..f76302d99e2be 100644
--- a/include/crypto/chacha20.h
+++ b/include/crypto/chacha20.h
@@ -13,13 +13,12 @@
 #define CHACHA20_IV_SIZE	16
 #define CHACHA20_KEY_SIZE	32
 #define CHACHA20_BLOCK_SIZE	64
-#define CHACHA20_BLOCK_WORDS	(CHACHA20_BLOCK_SIZE / sizeof(u32))
 
 struct chacha20_ctx {
 	u32 key[8];
 };
 
-void chacha20_block(u32 *state, u32 *stream);
+void chacha20_block(u32 *state, u8 *stream);
 void crypto_chacha20_init(u32 *state, struct chacha20_ctx *ctx, u8 *iv);
 int crypto_chacha20_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			   unsigned int keysize);
diff --git a/lib/chacha20.c b/lib/chacha20.c
index c1cc50fb68c9f..d907fec6a9ed1 100644
--- a/lib/chacha20.c
+++ b/lib/chacha20.c
@@ -16,9 +16,9 @@
 #include <asm/unaligned.h>
 #include <crypto/chacha20.h>
 
-void chacha20_block(u32 *state, u32 *stream)
+void chacha20_block(u32 *state, u8 *stream)
 {
-	u32 x[16], *out = stream;
+	u32 x[16];
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(x); i++)
@@ -67,7 +67,7 @@ void chacha20_block(u32 *state, u32 *stream)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(x); i++)
-		out[i] = cpu_to_le32(x[i] + state[i]);
+		put_unaligned_le32(x[i] + state[i], &stream[i * sizeof(u32)]);
 
 	state[12]++;
 }
-- 
2.20.1

[PATCH AUTOSEL 4.19 072/191] crypto: arm/crc32 - avoid warning when compiling with Clang

[Sasha Levin]

From: Stefan Agner <stefan@agner.ch>

[ Upstream commit cd560235d8f9ddd94aa51e1c4dabdf3212b9b241 ]

The table id (second) argument to MODULE_DEVICE_TABLE is often
referenced otherwise. This is not the case for CPU features. This
leads to a warning when building the kernel with Clang:
  arch/arm/crypto/crc32-ce-glue.c:239:33: warning: variable
    'crc32_cpu_feature' is not needed and will not be emitted
    [-Wunneeded-internal-declaration]
  static const struct cpu_feature crc32_cpu_feature[] = {
                                  ^

Avoid warnings by using __maybe_unused, similar to commit 1f318a8bafcf
("modules: mark __inittest/__exittest as __maybe_unused").

Fixes: 2a9faf8b7e43 ("crypto: arm/crc32 - enable module autoloading based on CPU feature bits")
Signed-off-by: Stefan Agner <stefan@agner.ch>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm/crypto/crc32-ce-glue.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c
index 96e62ec105d06..cd9e93b46c2dd 100644
--- a/arch/arm/crypto/crc32-ce-glue.c
+++ b/arch/arm/crypto/crc32-ce-glue.c
@@ -236,7 +236,7 @@ static void __exit crc32_pmull_mod_exit(void)
 				  ARRAY_SIZE(crc32_pmull_algs));
 }
 
-static const struct cpu_feature crc32_cpu_feature[] = {
+static const struct cpu_feature __maybe_unused crc32_cpu_feature[] = {
 	{ cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { }
 };
 MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature);
-- 
2.20.1

[PATCH AUTOSEL 4.19 157/191] crypto: s5p-sss: Fix race in error handling

[Sasha Levin]

From: Christoph Manszewski <c.manszewski@samsung.com>

[ Upstream commit 5842cd44786055231b233ed5ed98cdb63ffb7db3 ]

Remove a race condition introduced by error path in functions:
s5p_aes_interrupt and s5p_aes_crypt_start. Setting the busy field of
struct s5p_aes_dev to false made it possible for s5p_tasklet_cb to
change the req field, before s5p_aes_complete was called.

Change the first parameter of s5p_aes_complete to struct
ablkcipher_request. Before spin_unlock, make a copy of the currently
handled request, to ensure s5p_aes_complete function call with the
correct request.

Signed-off-by: Christoph Manszewski <c.manszewski@samsung.com>
Acked-by: Kamil Konieczny <k.konieczny@partner.samsung.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/crypto/s5p-sss.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index faa282074e5aa..9021ad9df0c45 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -475,9 +475,9 @@ static void s5p_sg_done(struct s5p_aes_dev *dev)
 }
 
 /* Calls the completion. Cannot be called with dev->lock hold. */
-static void s5p_aes_complete(struct s5p_aes_dev *dev, int err)
+static void s5p_aes_complete(struct ablkcipher_request *req, int err)
 {
-	dev->req->base.complete(&dev->req->base, err);
+	req->base.complete(&req->base, err);
 }
 
 static void s5p_unset_outdata(struct s5p_aes_dev *dev)
@@ -655,6 +655,7 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
 {
 	struct platform_device *pdev = dev_id;
 	struct s5p_aes_dev *dev = platform_get_drvdata(pdev);
+	struct ablkcipher_request *req;
 	int err_dma_tx = 0;
 	int err_dma_rx = 0;
 	int err_dma_hx = 0;
@@ -727,7 +728,7 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
 
 		spin_unlock_irqrestore(&dev->lock, flags);
 
-		s5p_aes_complete(dev, 0);
+		s5p_aes_complete(dev->req, 0);
 		/* Device is still busy */
 		tasklet_schedule(&dev->tasklet);
 	} else {
@@ -752,11 +753,12 @@ static irqreturn_t s5p_aes_interrupt(int irq, void *dev_id)
 error:
 	s5p_sg_done(dev);
 	dev->busy = false;
+	req = dev->req;
 	if (err_dma_hx == 1)
 		s5p_set_dma_hashdata(dev, dev->hash_sg_iter);
 
 	spin_unlock_irqrestore(&dev->lock, flags);
-	s5p_aes_complete(dev, err);
+	s5p_aes_complete(req, err);
 
 hash_irq_end:
 	/*
@@ -1983,7 +1985,7 @@ static void s5p_aes_crypt_start(struct s5p_aes_dev *dev, unsigned long mode)
 	s5p_sg_done(dev);
 	dev->busy = false;
 	spin_unlock_irqrestore(&dev->lock, flags);
-	s5p_aes_complete(dev, err);
+	s5p_aes_complete(req, err);
 }
 
 static void s5p_tasklet_cb(unsigned long data)
-- 
2.20.1

[PATCH AUTOSEL 4.19 158/191] crypto: s5p-sss: Fix Fix argument list alignment

[Sasha Levin]

From: Christoph Manszewski <c.manszewski@samsung.com>

[ Upstream commit 6c12b6ba45490eeb820fdceccf5a53f42a26799c ]

Fix misalignment of continued argument list.

Signed-off-by: Christoph Manszewski <c.manszewski@samsung.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Kamil Konieczny <k.konieczny@partner.samsung.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/crypto/s5p-sss.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 9021ad9df0c45..b7216935236f0 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -491,7 +491,7 @@ static void s5p_unset_indata(struct s5p_aes_dev *dev)
 }
 
 static int s5p_make_sg_cpy(struct s5p_aes_dev *dev, struct scatterlist *src,
-			    struct scatterlist **dst)
+			   struct scatterlist **dst)
 {
 	void *pages;
 	int len;
@@ -1889,7 +1889,7 @@ static int s5p_set_indata_start(struct s5p_aes_dev *dev,
 }
 
 static int s5p_set_outdata_start(struct s5p_aes_dev *dev,
-				struct ablkcipher_request *req)
+				 struct ablkcipher_request *req)
 {
 	struct scatterlist *sg;
 	int err;
-- 
2.20.1

[PATCH AUTOSEL 4.19 159/191] crypto: fix a memory leak in rsa-kcs1pad's encryption mode

[Sasha Levin]

From: Dan Aloni <dan@kernelim.com>

[ Upstream commit 3944f139d5592790b70bc64f197162e643a8512b ]

The encryption mode of pkcs1pad never uses out_sg and out_buf, so
there's no need to allocate the buffer, which presently is not even
being freed.

CC: Herbert Xu <herbert@gondor.apana.org.au>
CC: linux-crypto@vger.kernel.org
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Dan Aloni <dan@kernelim.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 crypto/rsa-pkcs1pad.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index 9893dbfc1af45..812476e468213 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -261,15 +261,6 @@ static int pkcs1pad_encrypt(struct akcipher_request *req)
 	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
 			ctx->key_size - 1 - req->src_len, req->src);
 
-	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
-	if (!req_ctx->out_buf) {
-		kfree(req_ctx->in_buf);
-		return -ENOMEM;
-	}
-
-	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
-			ctx->key_size, NULL);
-
 	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_encrypt_sign_complete_cb, req);
-- 
2.20.1