[PATCH v2 10/20] lib/crypto: Switch ARM and arm64 to 'ksimd' scoped guard API

Ard Biesheuvel posted 20 patches 13 hours ago
[PATCH v2 10/20] lib/crypto: Switch ARM and arm64 to 'ksimd' scoped guard API
Posted by Ard Biesheuvel 13 hours ago
From: Ard Biesheuvel <ardb@kernel.org>

Before modifying the prototypes of kernel_neon_begin() and
kernel_neon_end() to accommodate kernel mode FP/SIMD state buffers
allocated on the stack, move arm64 to the new 'ksimd' scoped guard API,
which encapsulates the calls to those functions.

For symmetry, do the same for 32-bit ARM too.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 lib/crypto/arm/chacha-glue.c        |  6 ++----
 lib/crypto/arm/poly1305-glue.c      |  6 ++----
 lib/crypto/arm/sha1.h               | 13 ++++++-------
 lib/crypto/arm/sha256.h             | 14 +++++++-------
 lib/crypto/arm/sha512.h             |  6 +++---
 lib/crypto/arm64/chacha-neon-glue.c | 11 ++++-------
 lib/crypto/arm64/poly1305-glue.c    |  6 ++----
 lib/crypto/arm64/sha1.h             |  7 +++----
 lib/crypto/arm64/sha256.h           | 15 +++++++--------
 lib/crypto/arm64/sha512.h           |  8 ++++----
 10 files changed, 40 insertions(+), 52 deletions(-)

diff --git a/lib/crypto/arm/chacha-glue.c b/lib/crypto/arm/chacha-glue.c
index 88ec96415283..9c2e8d5edf20 100644
--- a/lib/crypto/arm/chacha-glue.c
+++ b/lib/crypto/arm/chacha-glue.c
@@ -14,7 +14,6 @@
 
 #include <asm/cputype.h>
 #include <asm/hwcap.h>
-#include <asm/neon.h>
 #include <asm/simd.h>
 
 asmlinkage void chacha_block_xor_neon(const struct chacha_state *state,
@@ -90,9 +89,8 @@ void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
 	do {
 		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
 
-		kernel_neon_begin();
-		chacha_doneon(state, dst, src, todo, nrounds);
-		kernel_neon_end();
+		scoped_ksimd()
+			chacha_doneon(state, dst, src, todo, nrounds);
 
 		bytes -= todo;
 		src += todo;
diff --git a/lib/crypto/arm/poly1305-glue.c b/lib/crypto/arm/poly1305-glue.c
index 2d86c78af883..3e4624477e9f 100644
--- a/lib/crypto/arm/poly1305-glue.c
+++ b/lib/crypto/arm/poly1305-glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <asm/hwcap.h>
-#include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/internal/poly1305.h>
 #include <linux/cpufeature.h>
@@ -39,9 +38,8 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 		do {
 			unsigned int todo = min_t(unsigned int, len, SZ_4K);
 
-			kernel_neon_begin();
-			poly1305_blocks_neon(state, src, todo, padbit);
-			kernel_neon_end();
+			scoped_ksimd()
+				poly1305_blocks_neon(state, src, todo, padbit);
 
 			len -= todo;
 			src += todo;
diff --git a/lib/crypto/arm/sha1.h b/lib/crypto/arm/sha1.h
index fa1e92419000..a4296ffefd05 100644
--- a/lib/crypto/arm/sha1.h
+++ b/lib/crypto/arm/sha1.h
@@ -4,7 +4,6 @@
  *
  * Copyright 2025 Google LLC
  */
-#include <asm/neon.h>
 #include <asm/simd.h>
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
@@ -22,12 +21,12 @@ static void sha1_blocks(struct sha1_block_state *state,
 {
 	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
 	    static_branch_likely(&have_neon) && likely(may_use_simd())) {
-		kernel_neon_begin();
-		if (static_branch_likely(&have_ce))
-			sha1_ce_transform(state, data, nblocks);
-		else
-			sha1_transform_neon(state, data, nblocks);
-		kernel_neon_end();
+		scoped_ksimd() {
+			if (static_branch_likely(&have_ce))
+				sha1_ce_transform(state, data, nblocks);
+			else
+				sha1_transform_neon(state, data, nblocks);
+		}
 	} else {
 		sha1_block_data_order(state, data, nblocks);
 	}
diff --git a/lib/crypto/arm/sha256.h b/lib/crypto/arm/sha256.h
index da75cbdc51d4..df861cc5b9ff 100644
--- a/lib/crypto/arm/sha256.h
+++ b/lib/crypto/arm/sha256.h
@@ -4,7 +4,7 @@
  *
  * Copyright 2025 Google LLC
  */
-#include <asm/neon.h>
+#include <asm/simd.h>
 #include <crypto/internal/simd.h>
 
 asmlinkage void sha256_block_data_order(struct sha256_block_state *state,
@@ -22,12 +22,12 @@ static void sha256_blocks(struct sha256_block_state *state,
 {
 	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
 	    static_branch_likely(&have_neon) && crypto_simd_usable()) {
-		kernel_neon_begin();
-		if (static_branch_likely(&have_ce))
-			sha256_ce_transform(state, data, nblocks);
-		else
-			sha256_block_data_order_neon(state, data, nblocks);
-		kernel_neon_end();
+		scoped_ksimd() {
+			if (static_branch_likely(&have_ce))
+				sha256_ce_transform(state, data, nblocks);
+			else
+				sha256_block_data_order_neon(state, data, nblocks);
+		}
 	} else {
 		sha256_block_data_order(state, data, nblocks);
 	}
diff --git a/lib/crypto/arm/sha512.h b/lib/crypto/arm/sha512.h
index f147b6490d6c..35b80e7e7db7 100644
--- a/lib/crypto/arm/sha512.h
+++ b/lib/crypto/arm/sha512.h
@@ -6,6 +6,7 @@
  */
 
 #include <asm/neon.h>
+#include <asm/simd.h>
 #include <crypto/internal/simd.h>
 
 static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
@@ -20,9 +21,8 @@ static void sha512_blocks(struct sha512_block_state *state,
 {
 	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
 	    static_branch_likely(&have_neon) && likely(crypto_simd_usable())) {
-		kernel_neon_begin();
-		sha512_block_data_order_neon(state, data, nblocks);
-		kernel_neon_end();
+		scoped_ksimd()
+			sha512_block_data_order_neon(state, data, nblocks);
 	} else {
 		sha512_block_data_order(state, data, nblocks);
 	}
diff --git a/lib/crypto/arm64/chacha-neon-glue.c b/lib/crypto/arm64/chacha-neon-glue.c
index d0188f974ca5..a3d109f0ce1e 100644
--- a/lib/crypto/arm64/chacha-neon-glue.c
+++ b/lib/crypto/arm64/chacha-neon-glue.c
@@ -25,7 +25,6 @@
 #include <linux/module.h>
 
 #include <asm/hwcap.h>
-#include <asm/neon.h>
 #include <asm/simd.h>
 
 asmlinkage void chacha_block_xor_neon(const struct chacha_state *state,
@@ -67,9 +66,8 @@ void hchacha_block_arch(const struct chacha_state *state,
 	if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
 		hchacha_block_generic(state, out, nrounds);
 	} else {
-		kernel_neon_begin();
-		hchacha_block_neon(state, out, nrounds);
-		kernel_neon_end();
+		scoped_ksimd()
+			hchacha_block_neon(state, out, nrounds);
 	}
 }
 EXPORT_SYMBOL(hchacha_block_arch);
@@ -84,9 +82,8 @@ void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
 	do {
 		unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
 
-		kernel_neon_begin();
-		chacha_doneon(state, dst, src, todo, nrounds);
-		kernel_neon_end();
+		scoped_ksimd()
+			chacha_doneon(state, dst, src, todo, nrounds);
 
 		bytes -= todo;
 		src += todo;
diff --git a/lib/crypto/arm64/poly1305-glue.c b/lib/crypto/arm64/poly1305-glue.c
index 31aea21ce42f..c83ce7d835d9 100644
--- a/lib/crypto/arm64/poly1305-glue.c
+++ b/lib/crypto/arm64/poly1305-glue.c
@@ -6,7 +6,6 @@
  */
 
 #include <asm/hwcap.h>
-#include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/internal/poly1305.h>
 #include <linux/cpufeature.h>
@@ -38,9 +37,8 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
 		do {
 			unsigned int todo = min_t(unsigned int, len, SZ_4K);
 
-			kernel_neon_begin();
-			poly1305_blocks_neon(state, src, todo, padbit);
-			kernel_neon_end();
+			scoped_ksimd()
+				poly1305_blocks_neon(state, src, todo, padbit);
 
 			len -= todo;
 			src += todo;
diff --git a/lib/crypto/arm64/sha1.h b/lib/crypto/arm64/sha1.h
index f822563538cc..3d0da0045fed 100644
--- a/lib/crypto/arm64/sha1.h
+++ b/lib/crypto/arm64/sha1.h
@@ -4,7 +4,6 @@
  *
  * Copyright 2025 Google LLC
  */
-#include <asm/neon.h>
 #include <asm/simd.h>
 #include <linux/cpufeature.h>
 
@@ -20,9 +19,9 @@ static void sha1_blocks(struct sha1_block_state *state,
 		do {
 			size_t rem;
 
-			kernel_neon_begin();
-			rem = __sha1_ce_transform(state, data, nblocks);
-			kernel_neon_end();
+			scoped_ksimd()
+				rem = __sha1_ce_transform(state, data, nblocks);
+
 			data += (nblocks - rem) * SHA1_BLOCK_SIZE;
 			nblocks = rem;
 		} while (nblocks);
diff --git a/lib/crypto/arm64/sha256.h b/lib/crypto/arm64/sha256.h
index a211966c124a..0a9f9d70bb43 100644
--- a/lib/crypto/arm64/sha256.h
+++ b/lib/crypto/arm64/sha256.h
@@ -4,7 +4,7 @@
  *
  * Copyright 2025 Google LLC
  */
-#include <asm/neon.h>
+#include <asm/simd.h>
 #include <crypto/internal/simd.h>
 #include <linux/cpufeature.h>
 
@@ -27,17 +27,16 @@ static void sha256_blocks(struct sha256_block_state *state,
 			do {
 				size_t rem;
 
-				kernel_neon_begin();
-				rem = __sha256_ce_transform(state,
-							    data, nblocks);
-				kernel_neon_end();
+				scoped_ksimd()
+					rem = __sha256_ce_transform(state, data,
+								    nblocks);
+
 				data += (nblocks - rem) * SHA256_BLOCK_SIZE;
 				nblocks = rem;
 			} while (nblocks);
 		} else {
-			kernel_neon_begin();
-			sha256_block_neon(state, data, nblocks);
-			kernel_neon_end();
+			scoped_ksimd()
+				sha256_block_neon(state, data, nblocks);
 		}
 	} else {
 		sha256_block_data_order(state, data, nblocks);
diff --git a/lib/crypto/arm64/sha512.h b/lib/crypto/arm64/sha512.h
index 6abb40b467f2..1b6c3974d553 100644
--- a/lib/crypto/arm64/sha512.h
+++ b/lib/crypto/arm64/sha512.h
@@ -5,7 +5,7 @@
  * Copyright 2025 Google LLC
  */
 
-#include <asm/neon.h>
+#include <asm/simd.h>
 #include <crypto/internal/simd.h>
 #include <linux/cpufeature.h>
 
@@ -25,9 +25,9 @@ static void sha512_blocks(struct sha512_block_state *state,
 		do {
 			size_t rem;
 
-			kernel_neon_begin();
-			rem = __sha512_ce_transform(state, data, nblocks);
-			kernel_neon_end();
+			scoped_ksimd()
+				rem = __sha512_ce_transform(state, data, nblocks);
+
 			data += (nblocks - rem) * SHA512_BLOCK_SIZE;
 			nblocks = rem;
 		} while (nblocks);
-- 
2.51.0.618.g983fd99d29-goog