diff mbox series

[3/5] crypto: arm64/aes-bs - move kernel mode neon en/disable into loop

Message ID 20171201211927.24653-4-ard.biesheuvel@linaro.org
State New
Headers show
Series crypto: arm64 - disable NEON across scatterwalk API calls | expand

Commit Message

Ard Biesheuvel Dec. 1, 2017, 9:19 p.m. UTC 
When kernel mode NEON was first introduced on arm64, the preserve and
restore of the userland NEON state was completely unoptimized, and
involved saving all registers on each call to kernel_neon_begin(),
and restoring them on each call to kernel_neon_end(). For this reason,
the NEON crypto code that was introduced at the time keeps the NEON
enabled throughout the execution of the crypto API methods, which may
include calls back into the crypto API that could result in memory
allocation or other actions that we should avoid when running with
preemption disabled.

Since then, we have optimized the kernel mode NEON handling, which now
restores lazily (upon return to userland), and so the preserve action
is only costly the first time it is called after entering the kernel.

So let's put the kernel_neon_begin() and kernel_neon_end() calls around
the actual invocations of the NEON crypto code, and run the remainder of
the code with kernel mode NEON disabled (and preemption enabled)

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>

---
 arch/arm64/crypto/aes-neonbs-glue.c | 26 +++++++++-----------
 1 file changed, 12 insertions(+), 14 deletions(-)

-- 
2.11.0

--
To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox series

Patch

diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index 9d823c77ec84..fa09dc340a1e 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -101,7 +101,6 @@  static int __ecb_crypt(struct skcipher_request *req,
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -109,12 +108,13 @@  static int __ecb_crypt(struct skcipher_request *req,
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->rk,
 		   ctx->rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -160,17 +160,17 @@  static int cbc_encrypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
 		/* fall back to the non-bitsliced NEON implementation */
+		kernel_neon_begin();
 		neon_aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				     ctx->enc, ctx->key.rounds, blocks,
 				     walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -183,7 +183,6 @@  static int cbc_decrypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	kernel_neon_begin();
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 
@@ -191,13 +190,14 @@  static int cbc_decrypt(struct skcipher_request *req)
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		aesbs_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				  ctx->key.rk, ctx->key.rounds, blocks,
 				  walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -231,7 +231,6 @@  static int ctr_encrypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	kernel_neon_begin();
 	while (walk.nbytes > 0) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
 		u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
@@ -242,8 +241,10 @@  static int ctr_encrypt(struct skcipher_request *req)
 			final = NULL;
 		}
 
+		kernel_neon_begin();
 		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				  ctx->rk, ctx->rounds, blocks, walk.iv, final);
+		kernel_neon_end();
 
 		if (final) {
 			u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
@@ -258,8 +259,6 @@  static int ctr_encrypt(struct skcipher_request *req)
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
-
 	return err;
 }
 
@@ -307,9 +306,8 @@  static int __xts_crypt(struct skcipher_request *req,
 	err = skcipher_walk_virt(&walk, req, true);
 
 	kernel_neon_begin();
-
-	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey,
-			     ctx->key.rounds, 1);
+	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1);
+	kernel_neon_end();
 
 	while (walk.nbytes >= AES_BLOCK_SIZE) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -318,13 +316,13 @@  static int __xts_crypt(struct skcipher_request *req,
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
 
+		kernel_neon_begin();
 		fn(walk.dst.virt.addr, walk.src.virt.addr, ctx->key.rk,
 		   ctx->key.rounds, blocks, walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk,
 					 walk.nbytes - blocks * AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
-
 	return err;
 }