diff mbox series

[v6,5/6] crypto: arm64/aes-ccm - reduce NEON begin/end calls for common case

Message ID 20210526100729.12939-6-ardb@kernel.org
State Superseded
Headers show
Series [v6,1/6] crypto: arm64/gcm-aes-ce - remove non-SIMD fallback path | expand

Commit Message

Ard Biesheuvel May 26, 2021, 10:07 a.m. UTC 
AES-CCM (as used in WPA2 CCMP, for instance) typically involves
authenticate-only data, and operates on a single network packet, and so
the common case is for the authenticate, en/decrypt and finalize SIMD
helpers to all be called exactly once in sequence. Since
kernel_neon_end() now involves manipulation of the preemption state as
well as the softirq mask state, let's reduce the number of times we are
forced to call it to only once if we are handling this common case.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/arm64/crypto/aes-ce-ccm-core.S |  1 +
 arch/arm64/crypto/aes-ce-ccm-glue.c | 74 +++++++++++---------
 2 files changed, 43 insertions(+), 32 deletions(-)

Comments

Ard Biesheuvel May 26, 2021, 6:08 p.m. UTC | #1 
On Wed, 26 May 2021 at 19:14, Eric Biggers <ebiggers@kernel.org> wrote:
>
> On Wed, May 26, 2021 at 12:07:28PM +0200, Ard Biesheuvel wrote:
> > AES-CCM (as used in WPA2 CCMP, for instance) typically involves
> > authenticate-only data, and operates on a single network packet, and so
> > the common case is for the authenticate, en/decrypt and finalize SIMD
> > helpers to all be called exactly once in sequence. Since
> > kernel_neon_end() now involves manipulation of the preemption state as
> > well as the softirq mask state, let's reduce the number of times we are
> > forced to call it to only once if we are handling this common case.
> >
> > Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
> > ---
> >  arch/arm64/crypto/aes-ce-ccm-core.S |  1 +
> >  arch/arm64/crypto/aes-ce-ccm-glue.c | 74 +++++++++++---------
> >  2 files changed, 43 insertions(+), 32 deletions(-)
> >
> > diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
> > index 99a028e298ed..8adff299fcd3 100644
> > --- a/arch/arm64/crypto/aes-ce-ccm-core.S
> > +++ b/arch/arm64/crypto/aes-ce-ccm-core.S
> > @@ -124,6 +124,7 @@ SYM_FUNC_START(ce_aes_ccm_final)
> >  SYM_FUNC_END(ce_aes_ccm_final)
> >
> >       .macro  aes_ccm_do_crypt,enc
> > +     cbz     x2, 5f
> >       ldr     x8, [x6, #8]                    /* load lower ctr */
> >       ld1     {v0.16b}, [x5]                  /* load mac */
> >  CPU_LE(      rev     x8, x8                  )       /* keep swabbed ctr in reg */
> > diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
> > index 54bd2494a000..98159f2c49ae 100644
> > --- a/arch/arm64/crypto/aes-ce-ccm-glue.c
> > +++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
> > @@ -97,10 +97,8 @@ static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
> >  static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
> >                          u32 abytes, u32 *macp)
> >  {
> > -     kernel_neon_begin();
> >       ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
> >                            num_rounds(key));
> > -     kernel_neon_end();
> >  }
> [...]
> > +     if (req->assoclen)
> > +             ccm_calculate_auth_mac(req, mac);
> > +
>
> This still makes all the associated data be processed under a single
> kernel_neon_begin() / kernel_neon_end() pair, even if there is a large amount of
> it.  Shouldn't it be limited to a reasonable amount at a time, like 4K?
> This sort of thing has been considered a bug before, e.g. see
> commit 706024a52c6 ("crypto: arch/lib - limit simd usage to 4k chunks").
>
> You could do the entire CCM operation under a single pair as long as there isn't
> more than 4K of associated data.
>

Good point. I'll add a separate patch for that.
diff mbox series

Patch

diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 99a028e298ed..8adff299fcd3 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -124,6 +124,7 @@  SYM_FUNC_START(ce_aes_ccm_final)
 SYM_FUNC_END(ce_aes_ccm_final)
 
 	.macro	aes_ccm_do_crypt,enc
+	cbz	x2, 5f
 	ldr	x8, [x6, #8]			/* load lower ctr */
 	ld1	{v0.16b}, [x5]			/* load mac */
 CPU_LE(	rev	x8, x8			)	/* keep swabbed ctr in reg */
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 54bd2494a000..98159f2c49ae 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -97,10 +97,8 @@  static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
 static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
 			   u32 abytes, u32 *macp)
 {
-	kernel_neon_begin();
 	ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
 			     num_rounds(key));
-	kernel_neon_end();
 }
 
 static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
@@ -157,35 +155,41 @@  static int ccm_encrypt(struct aead_request *req)
 	if (err)
 		return err;
 
-	if (req->assoclen)
-		ccm_calculate_auth_mac(req, mac);
-
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
+	if (unlikely(err))
+		return err;
 
-	while (walk.nbytes) {
+	kernel_neon_begin();
+
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	do {
 		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
 		if (walk.nbytes == walk.total)
 			tail = 0;
 
-		kernel_neon_begin();
 		ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
 				   walk.nbytes - tail, ctx->key_enc,
 				   num_rounds(ctx), mac, walk.iv);
-		kernel_neon_end();
 
-		err = skcipher_walk_done(&walk, tail);
-	}
-	if (!err) {
-		kernel_neon_begin();
-		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+		if (walk.nbytes == walk.total)
+			ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+
 		kernel_neon_end();
-	}
-	if (err)
-		return err;
+
+		if (walk.nbytes) {
+			err = skcipher_walk_done(&walk, tail);
+			if (unlikely(err))
+				return err;
+			if (unlikely(walk.nbytes))
+				kernel_neon_begin();
+		}
+	} while (walk.nbytes);
 
 	/* copy authtag to end of dst */
 	scatterwalk_map_and_copy(mac, req->dst, req->assoclen + req->cryptlen,
@@ -209,35 +213,41 @@  static int ccm_decrypt(struct aead_request *req)
 	if (err)
 		return err;
 
-	if (req->assoclen)
-		ccm_calculate_auth_mac(req, mac);
-
 	/* preserve the original iv for the final round */
 	memcpy(buf, req->iv, AES_BLOCK_SIZE);
 
 	err = skcipher_walk_aead_decrypt(&walk, req, false);
+	if (unlikely(err))
+		return err;
+
+	kernel_neon_begin();
 
-	while (walk.nbytes) {
+	if (req->assoclen)
+		ccm_calculate_auth_mac(req, mac);
+
+	do {
 		u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
 		if (walk.nbytes == walk.total)
 			tail = 0;
 
-		kernel_neon_begin();
 		ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
-					   walk.nbytes - tail, ctx->key_enc,
-					   num_rounds(ctx), mac, walk.iv);
-		kernel_neon_end();
+				   walk.nbytes - tail, ctx->key_enc,
+				   num_rounds(ctx), mac, walk.iv);
+
+		if (walk.nbytes == walk.total)
+			ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
 
-		err = skcipher_walk_done(&walk, tail);
-	}
-	if (!err) {
-		kernel_neon_begin();
-		ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
 		kernel_neon_end();
-	}
-	if (err)
-		return err;
+
+		if (walk.nbytes) {
+			err = skcipher_walk_done(&walk, tail);
+			if (unlikely(err))
+				return err;
+			if (unlikely(walk.nbytes))
+				kernel_neon_begin();
+		}
+	} while (walk.nbytes);
 
 	/* compare calculated auth tag with the stored one */
 	scatterwalk_map_and_copy(buf, req->src,