crypto: arch/lib - limit simd usage to 4k chunks

The initial Zinc patchset, after some mailing list discussion, contained
code to ensure that kernel_fpu_enable would not be kept on for more than
a 4k chunk, since it disables preemption. The choice of 4k isn't totally
scientific, but it's not a bad guess either, and it's what's used in
both the x86 poly1305, blake2s, and nhpoly1305 code already (in the form
of PAGE_SIZE, which this commit corrects to be explicitly 4k for the
former two).

Ard did some back of the envelope calculations and found that
at 5 cycles/byte (overestimate) on a 1ghz processor (pretty slow), 4k
means we have a maximum preemption disabling of 20us, which Sebastian
confirmed was probably a good limit.

Unfortunately the chunking appears to have been left out of the final
patchset that added the glue code. So, this commit adds it back in.

Fixes: 84e03fa39fbe ("crypto: x86/chacha - expose SIMD ChaCha routine as library function")
Fixes: b3aad5bad26a ("crypto: arm64/chacha - expose arm64 ChaCha routine as library function")
Fixes: a44a3430d71b ("crypto: arm/chacha - expose ARM ChaCha routine as library function")
Fixes: d7d7b8535662 ("crypto: x86/poly1305 - wire up faster implementations for kernel")
Fixes: f569ca164751 ("crypto: arm64/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation")
Fixes: a6b803b3ddc7 ("crypto: arm/poly1305 - incorporate OpenSSL/CRYPTOGAMS NEON implementation")
Fixes: ed0356eda153 ("crypto: blake2s - x86_64 SIMD implementation")
Cc: Eric Biggers <ebiggers@google.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: stable@vger.kernel.org
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

2 files changed, 22 insertions, 7 deletions

diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c
index 6fdb0ac62b3d..59da6c0b63b6 100644
--- a/arch/arm/crypto/chacha-glue.c
+++ b/arch/arm/crypto/chacha-glue.c
@@ -91,9 +91,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
 		return;
 	}
 
-	kernel_neon_begin();
-	chacha_doneon(state, dst, src, bytes, nrounds);
-	kernel_neon_end();
+	do {
+		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+		kernel_neon_begin();
+		chacha_doneon(state, dst, src, todo, nrounds);
+		kernel_neon_end();
+
+		bytes -= todo;
+		src += todo;
+		dst += todo;
+	} while (bytes);
 }
 EXPORT_SYMBOL(chacha_crypt_arch);
 
diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c
index ceec04ec2f40..13cfef4ae22e 100644
--- a/arch/arm/crypto/poly1305-glue.c
+++ b/arch/arm/crypto/poly1305-glue.c
@@ -160,13 +160,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
 		unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
 
 		if (static_branch_likely(&have_neon) && do_neon) {
-			kernel_neon_begin();
-			poly1305_blocks_neon(&dctx->h, src, len, 1);
-			kernel_neon_end();
+			do {
+				unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+				kernel_neon_begin();
+				poly1305_blocks_neon(&dctx->h, src, todo, 1);
+				kernel_neon_end();
+
+				len -= todo;
+				src += todo;
+			} while (len);
 		} else {
 			poly1305_blocks_arm(&dctx->h, src, len, 1);
+			src += len;
 		}
-		src += len;
 		nbytes %= POLY1305_BLOCK_SIZE;
 	}