linux-kernel - [PATCH v4] poly1305: generic C can be faster on chips with slow unaligned access

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon,  7 Nov 2016 20:47:09 +0100
From:   "Jason A. Donenfeld" <Jason@...c4.com>
To:     Herbert Xu <herbert@...dor.apana.org.au>,
        "David S. Miller" <davem@...emloft.net>,
        linux-crypto@...r.kernel.org, linux-kernel@...r.kernel.org,
        Martin Willi <martin@...ongswan.org>,
        Eric Biggers <ebiggers@...gle.com>,
        René van Dorst <opensource@...rst.com>
Cc:     "Jason A. Donenfeld" <Jason@...c4.com>
Subject: [PATCH v4] poly1305: generic C can be faster on chips with slow unaligned access

By using the unaligned access helpers, we drastically improve
performance on small MIPS routers that have to go through the exception
fix-up handler for these unaligned accesses.

Signed-off-by: Jason A. Donenfeld <Jason@...c4.com>
---
 crypto/poly1305_generic.c | 34 +++++++++++++++-------------------
 1 file changed, 15 insertions(+), 19 deletions(-)

diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index 2df9835d..b1c2d57 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -17,6 +17,7 @@
 #include <linux/crypto.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <asm/unaligned.h>
 
 static inline u64 mlt(u64 a, u64 b)
 {
@@ -33,11 +34,6 @@ static inline u32 and(u32 v, u32 mask)
 	return v & mask;
 }
 
-static inline u32 le32_to_cpuvp(const void *p)
-{
-	return le32_to_cpup(p);
-}
-
 int crypto_poly1305_init(struct shash_desc *desc)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
@@ -65,19 +61,19 @@ EXPORT_SYMBOL_GPL(crypto_poly1305_setkey);
 static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
 	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
-	dctx->r[0] = (le32_to_cpuvp(key +  0) >> 0) & 0x3ffffff;
-	dctx->r[1] = (le32_to_cpuvp(key +  3) >> 2) & 0x3ffff03;
-	dctx->r[2] = (le32_to_cpuvp(key +  6) >> 4) & 0x3ffc0ff;
-	dctx->r[3] = (le32_to_cpuvp(key +  9) >> 6) & 0x3f03fff;
-	dctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
+	dctx->r[0] = (get_unaligned_le32(key +  0) >> 0) & 0x3ffffff;
+	dctx->r[1] = (get_unaligned_le32(key +  3) >> 2) & 0x3ffff03;
+	dctx->r[2] = (get_unaligned_le32(key +  6) >> 4) & 0x3ffc0ff;
+	dctx->r[3] = (get_unaligned_le32(key +  9) >> 6) & 0x3f03fff;
+	dctx->r[4] = (get_unaligned_le32(key + 12) >> 8) & 0x00fffff;
 }
 
 static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
-	dctx->s[0] = le32_to_cpuvp(key +  0);
-	dctx->s[1] = le32_to_cpuvp(key +  4);
-	dctx->s[2] = le32_to_cpuvp(key +  8);
-	dctx->s[3] = le32_to_cpuvp(key + 12);
+	dctx->s[0] = get_unaligned_le32(key +  0);
+	dctx->s[1] = get_unaligned_le32(key +  4);
+	dctx->s[2] = get_unaligned_le32(key +  8);
+	dctx->s[3] = get_unaligned_le32(key + 12);
 }
 
 unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
@@ -137,11 +133,11 @@ static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
 	while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
 
 		/* h += m[i] */
-		h0 += (le32_to_cpuvp(src +  0) >> 0) & 0x3ffffff;
-		h1 += (le32_to_cpuvp(src +  3) >> 2) & 0x3ffffff;
-		h2 += (le32_to_cpuvp(src +  6) >> 4) & 0x3ffffff;
-		h3 += (le32_to_cpuvp(src +  9) >> 6) & 0x3ffffff;
-		h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
+		h0 += (get_unaligned_le32(src +  0) >> 0) & 0x3ffffff;
+		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
+		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
+		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
+		h4 += (get_unaligned_le32(src + 12) >> 8) | hibit;
 
 		/* h *= r */
 		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +
-- 
2.10.2