[PATCH 6/9] lib/crypto: arm64/sha256: Remove obsolete chunking logic

Eric Biggers posted 9 patches 8 hours ago
[PATCH 6/9] lib/crypto: arm64/sha256: Remove obsolete chunking logic
Posted by Eric Biggers 8 hours ago
Since commit aefbab8e77eb ("arm64: fpsimd: Preserve/restore kernel mode
NEON at context switch"), kernel-mode NEON sections have been
preemptible on arm64.  And since commit 7dadeaa6e851 ("sched: Further
restrict the preemption modes"), voluntary preemption is no longer
supported on arm64 either.  Therefore, there's no longer any need to
limit the length of kernel-mode NEON sections on arm64.

Simplify the SHA-256 code accordingly.

Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 lib/crypto/arm64/sha256-ce.S | 14 +++++---------
 lib/crypto/arm64/sha256.h    | 29 ++++++++---------------------
 2 files changed, 13 insertions(+), 30 deletions(-)

diff --git a/lib/crypto/arm64/sha256-ce.S b/lib/crypto/arm64/sha256-ce.S
index e4bfe42a61a9..b54ad977afa3 100644
--- a/lib/crypto/arm64/sha256-ce.S
+++ b/lib/crypto/arm64/sha256-ce.S
@@ -77,15 +77,15 @@
 	ld1		{ v8.4s-v11.4s}, [\tmp], #64
 	ld1		{v12.4s-v15.4s}, [\tmp]
 	.endm
 
 	/*
-	 * size_t __sha256_ce_transform(struct sha256_block_state *state,
-	 *				const u8 *data, size_t nblocks);
+	 * void sha256_ce_transform(struct sha256_block_state *state,
+	 *			    const u8 *data, size_t nblocks);
 	 */
 	.text
-SYM_FUNC_START(__sha256_ce_transform)
+SYM_FUNC_START(sha256_ce_transform)
 
 	load_round_constants	x8
 
 	/* load state */
 	ld1		{dgav.4s, dgbv.4s}, [x0]
@@ -125,21 +125,17 @@ CPU_LE(	rev32		v19.16b, v19.16b	)
 
 	/* update state */
 	add		dgav.4s, dgav.4s, dg0v.4s
 	add		dgbv.4s, dgbv.4s, dg1v.4s
 
-	/* return early if voluntary preemption is needed */
-	cond_yield	1f, x5, x6
-
 	/* handled all input blocks? */
 	cbnz		x2, 0b
 
 	/* store new state */
-1:	st1		{dgav.4s, dgbv.4s}, [x0]
-	mov		x0, x2
+	st1		{dgav.4s, dgbv.4s}, [x0]
 	ret
-SYM_FUNC_END(__sha256_ce_transform)
+SYM_FUNC_END(sha256_ce_transform)
 
 	.unreq dga
 	.unreq dgav
 	.unreq dgb
 	.unreq dgbv
diff --git a/lib/crypto/arm64/sha256.h b/lib/crypto/arm64/sha256.h
index 1fad3d7baa9a..b4353d3c4dd0 100644
--- a/lib/crypto/arm64/sha256.h
+++ b/lib/crypto/arm64/sha256.h
@@ -12,30 +12,21 @@ static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_ce);
 
 asmlinkage void sha256_block_data_order(struct sha256_block_state *state,
 					const u8 *data, size_t nblocks);
 asmlinkage void sha256_block_neon(struct sha256_block_state *state,
 				  const u8 *data, size_t nblocks);
-asmlinkage size_t __sha256_ce_transform(struct sha256_block_state *state,
-					const u8 *data, size_t nblocks);
+asmlinkage void sha256_ce_transform(struct sha256_block_state *state,
+				    const u8 *data, size_t nblocks);
 
 static void sha256_blocks(struct sha256_block_state *state,
 			  const u8 *data, size_t nblocks)
 {
 	if (static_branch_likely(&have_neon) && likely(may_use_simd())) {
-		if (static_branch_likely(&have_ce)) {
-			do {
-				size_t rem;
-
-				scoped_ksimd()
-					rem = __sha256_ce_transform(state, data,
-								    nblocks);
-
-				data += (nblocks - rem) * SHA256_BLOCK_SIZE;
-				nblocks = rem;
-			} while (nblocks);
-		} else {
-			scoped_ksimd()
+		scoped_ksimd() {
+			if (static_branch_likely(&have_ce))
+				sha256_ce_transform(state, data, nblocks);
+			else
 				sha256_block_neon(state, data, nblocks);
 		}
 	} else {
 		sha256_block_data_order(state, data, nblocks);
 	}
@@ -53,17 +44,13 @@ asmlinkage void sha256_ce_finup2x(const struct __sha256_ctx *ctx,
 static bool sha256_finup_2x_arch(const struct __sha256_ctx *ctx,
 				 const u8 *data1, const u8 *data2, size_t len,
 				 u8 out1[SHA256_DIGEST_SIZE],
 				 u8 out2[SHA256_DIGEST_SIZE])
 {
-	/*
-	 * The assembly requires len >= SHA256_BLOCK_SIZE && len <= INT_MAX.
-	 * Further limit len to 65536 to avoid spending too long with preemption
-	 * disabled.  (Of course, in practice len is nearly always 4096 anyway.)
-	 */
+	/* The assembly requires len >= SHA256_BLOCK_SIZE && len <= INT_MAX. */
 	if (static_branch_likely(&have_ce) && len >= SHA256_BLOCK_SIZE &&
-	    len <= 65536 && likely(may_use_simd())) {
+	    len <= INT_MAX && likely(may_use_simd())) {
 		scoped_ksimd()
 			sha256_ce_finup2x(ctx, data1, data2, len, out1, out2);
 		kmsan_unpoison_memory(out1, SHA256_DIGEST_SIZE);
 		kmsan_unpoison_memory(out2, SHA256_DIGEST_SIZE);
 		return true;
-- 
2.53.0