crypto: arm64/aes-blk - move kernel mode neon en/disable into loop

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)

Note that this requires some reshuffling of the registers in the asm
code, because the XTS routines can no longer rely on the registers to
retain their contents between invocations.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

1 files changed, 46 insertions, 49 deletions

diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 2fa850e86aa8..253188fb8cb0 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -64,17 +64,17 @@ MODULE_LICENSE("GPL v2");
 
 /* defined in aes-modes.S */
 asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, int first);
+				int rounds, int blocks);
 asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, int first);
+				int rounds, int blocks);
 
 asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, u8 iv[], int first);
+				int rounds, int blocks, u8 iv[]);
 asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, u8 iv[], int first);
+				int rounds, int blocks, u8 iv[]);
 
 asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				int rounds, int blocks, u8 ctr[], int first);
+				int rounds, int blocks, u8 ctr[]);
 
 asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
 				int rounds, int blocks, u8 const rk2[], u8 iv[],
@@ -133,19 +133,19 @@ static int ecb_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_enc, rounds, blocks, first);
+				(u8 *)ctx->key_enc, rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -153,19 +153,19 @@ static int ecb_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_dec, rounds, blocks, first);
+				(u8 *)ctx->key_dec, rounds, blocks);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -173,20 +173,19 @@ static int cbc_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
-				first);
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -194,20 +193,19 @@ static int cbc_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
-	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_dec, rounds, blocks, walk.iv,
-				first);
+				(u8 *)ctx->key_dec, rounds, blocks, walk.iv);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 	return err;
 }
 
@@ -215,20 +213,18 @@ static int ctr_encrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
-	int err, first, rounds = 6 + ctx->key_length / 4;
+	int err, rounds = 6 + ctx->key_length / 4;
 	struct skcipher_walk walk;
 	int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	first = 1;
-	kernel_neon_begin();
 	while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+		kernel_neon_begin();
 		aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
-				(u8 *)ctx->key_enc, rounds, blocks, walk.iv,
-				first);
+				(u8 *)ctx->key_enc, rounds, blocks, walk.iv);
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
-		first = 0;
+		kernel_neon_end();
 	}
 	if (walk.nbytes) {
 		u8 __aligned(8) tail[AES_BLOCK_SIZE];
@@ -241,12 +237,13 @@ static int ctr_encrypt(struct skcipher_request *req)
 		 */
 		blocks = -1;
 
+		kernel_neon_begin();
 		aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, rounds,
-				blocks, walk.iv, first);
+				blocks, walk.iv);
+		kernel_neon_end();
 		crypto_xor_cpy(tdst, tsrc, tail, nbytes);
 		err = skcipher_walk_done(&walk, 0);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -270,16 +267,16 @@ static int xts_encrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		kernel_neon_begin();
 		aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_enc, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -292,16 +289,16 @@ static int xts_decrypt(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	unsigned int blocks;
 
-	err = skcipher_walk_virt(&walk, req, true);
+	err = skcipher_walk_virt(&walk, req, false);
 
-	kernel_neon_begin();
 	for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
+		kernel_neon_begin();
 		aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				(u8 *)ctx->key1.key_dec, rounds, blocks,
 				(u8 *)ctx->key2.key_enc, walk.iv, first);
+		kernel_neon_end();
 		err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
 	}
-	kernel_neon_end();
 
 	return err;
 }
@@ -425,7 +422,7 @@ static int cmac_setkey(struct crypto_shash *tfm, const u8 *in_key,
 
 	/* encrypt the zero vector */
 	kernel_neon_begin();
-	aes_ecb_encrypt(ctx->consts, (u8[AES_BLOCK_SIZE]){}, rk, rounds, 1, 1);
+	aes_ecb_encrypt(ctx->consts, (u8[AES_BLOCK_SIZE]){}, rk, rounds, 1);
 	kernel_neon_end();
 
 	cmac_gf128_mul_by_x(consts, consts);
@@ -454,8 +451,8 @@ static int xcbc_setkey(struct crypto_shash *tfm, const u8 *in_key,
 		return err;
 
 	kernel_neon_begin();
-	aes_ecb_encrypt(key, ks[0], rk, rounds, 1, 1);
-	aes_ecb_encrypt(ctx->consts, ks[1], rk, rounds, 2, 0);
+	aes_ecb_encrypt(key, ks[0], rk, rounds, 1);
+	aes_ecb_encrypt(ctx->consts, ks[1], rk, rounds, 2);
 	kernel_neon_end();
 
 	return cbcmac_setkey(tfm, key, sizeof(key));