From: Ard Biesheuvel <ardb+git@google.com>
To: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org, linux-crypto@vger.kernel.org,
herbert@gondor.apana.org.au, ebiggers@kernel.org,
Ard Biesheuvel <ardb@kernel.org>
Subject: [PATCH v3 09/21] lib/crypto: Switch ARM and arm64 to 'ksimd' scoped guard API
Date: Wed, 8 Oct 2025 17:45:43 +0200 [thread overview]
Message-ID: <20251008154533.3089255-32-ardb+git@google.com> (raw)
In-Reply-To: <20251008154533.3089255-23-ardb+git@google.com>
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.
Reviewed-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
lib/crypto/arm/chacha.h | 6 ++----
lib/crypto/arm/poly1305.h | 6 ++----
lib/crypto/arm/sha1.h | 13 ++++++-------
lib/crypto/arm/sha256.h | 12 ++++++------
lib/crypto/arm/sha512.h | 6 ++----
lib/crypto/arm64/chacha.h | 11 ++++-------
lib/crypto/arm64/poly1305.h | 6 ++----
lib/crypto/arm64/sha1.h | 7 +++----
lib/crypto/arm64/sha256.h | 19 ++++++++-----------
lib/crypto/arm64/sha512.h | 8 ++++----
10 files changed, 39 insertions(+), 55 deletions(-)
diff --git a/lib/crypto/arm/chacha.h b/lib/crypto/arm/chacha.h
index 0cae30f8ee5d..b27ba00b3b23 100644
--- a/lib/crypto/arm/chacha.h
+++ b/lib/crypto/arm/chacha.h
@@ -12,7 +12,6 @@
#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,
@@ -87,9 +86,8 @@ static void chacha_crypt_arch(struct chacha_state *state, u8 *dst,
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.h b/lib/crypto/arm/poly1305.h
index 0021cf368307..0fe903d8de55 100644
--- a/lib/crypto/arm/poly1305.h
+++ b/lib/crypto/arm/poly1305.h
@@ -6,7 +6,6 @@
*/
#include <asm/hwcap.h>
-#include <asm/neon.h>
#include <asm/simd.h>
#include <linux/cpufeature.h>
#include <linux/jump_label.h>
@@ -32,9 +31,8 @@ static void poly1305_blocks(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 29f8bcad0447..3e2d8c7cab9f 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 7556457b3094..ae7e52dd6e3b 100644
--- a/lib/crypto/arm/sha256.h
+++ b/lib/crypto/arm/sha256.h
@@ -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) && likely(may_use_simd())) {
- 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 d1b485dd275d..8d3af965d2b3 100644
--- a/lib/crypto/arm/sha512.h
+++ b/lib/crypto/arm/sha512.h
@@ -18,10 +18,8 @@ static void sha512_blocks(struct sha512_block_state *state,
const u8 *data, size_t nblocks)
{
if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
- static_branch_likely(&have_neon) && likely(may_use_simd())) {
- 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.h b/lib/crypto/arm64/chacha.h
index ba6c22d46086..ca8c6a8b0578 100644
--- a/lib/crypto/arm64/chacha.h
+++ b/lib/crypto/arm64/chacha.h
@@ -23,7 +23,6 @@
#include <linux/kernel.h>
#include <asm/hwcap.h>
-#include <asm/neon.h>
#include <asm/simd.h>
asmlinkage void chacha_block_xor_neon(const struct chacha_state *state,
@@ -65,9 +64,8 @@ static 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);
}
}
@@ -81,9 +79,8 @@ static void chacha_crypt_arch(struct chacha_state *state, u8 *dst,
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.h b/lib/crypto/arm64/poly1305.h
index aed5921ccd9a..b77669767cd6 100644
--- a/lib/crypto/arm64/poly1305.h
+++ b/lib/crypto/arm64/poly1305.h
@@ -6,7 +6,6 @@
*/
#include <asm/hwcap.h>
-#include <asm/neon.h>
#include <asm/simd.h>
#include <linux/cpufeature.h>
#include <linux/jump_label.h>
@@ -31,9 +30,8 @@ static void poly1305_blocks(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 aaef4ebfc5e3..bc7071f1be09 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 80d06df27d3a..568dff0f276a 100644
--- a/lib/crypto/arm64/sha256.h
+++ b/lib/crypto/arm64/sha256.h
@@ -4,7 +4,6 @@
*
* Copyright 2025 Google LLC
*/
-#include <asm/neon.h>
#include <asm/simd.h>
#include <linux/cpufeature.h>
@@ -27,17 +26,16 @@ 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);
@@ -66,9 +64,8 @@ static bool sha256_finup_2x_arch(const struct __sha256_ctx *ctx,
if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
static_branch_likely(&have_ce) && len >= SHA256_BLOCK_SIZE &&
len <= 65536 && likely(may_use_simd())) {
- kernel_neon_begin();
- sha256_ce_finup2x(ctx, data1, data2, len, out1, out2);
- kernel_neon_end();
+ 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;
diff --git a/lib/crypto/arm64/sha512.h b/lib/crypto/arm64/sha512.h
index ddb0d256f73a..7eb7ef04d268 100644
--- a/lib/crypto/arm64/sha512.h
+++ b/lib/crypto/arm64/sha512.h
@@ -4,7 +4,7 @@
*
* Copyright 2025 Google LLC
*/
-#include <asm/neon.h>
+
#include <asm/simd.h>
#include <linux/cpufeature.h>
@@ -24,9 +24,9 @@ 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);
--
2.51.0.710.ga91ca5db03-goog
next prev parent reply other threads:[~2025-10-08 15:47 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-08 15:45 [PATCH v3 00/21] arm64: Move kernel mode FPSIMD buffer to the stack Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 01/21] crypto/arm64: aes-ce-ccm - Avoid pointless yield of the NEON unit Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 02/21] crypto/arm64: sm4-ce-ccm " Ard Biesheuvel
2025-10-17 17:03 ` Eric Biggers
2025-10-08 15:45 ` [PATCH v3 03/21] crypto/arm64: sm4-ce-gcm " Ard Biesheuvel
2025-10-17 17:04 ` Eric Biggers
2025-10-08 15:45 ` [PATCH v3 04/21] arm64/simd: Add scoped guard API for kernel mode SIMD Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 05/21] ARM/simd: " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 06/21] crypto: aegis128-neon - Move to more abstract 'ksimd' guard API Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 07/21] raid6: " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 08/21] lib/crc: Switch ARM and arm64 to 'ksimd' scoped " Ard Biesheuvel
2025-10-08 15:45 ` Ard Biesheuvel [this message]
2025-10-08 15:45 ` [PATCH v3 10/21] crypto/arm64: aes-ccm - Switch " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 11/21] crypto/arm64: aes-blk " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 12/21] crypto/arm64: aes-gcm " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 13/21] crypto/arm64: nhpoly1305 " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 14/21] crypto/arm64: polyval " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 15/21] crypto/arm64: sha3 " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 16/21] crypto/arm64: sm3 " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 17/21] crypto/arm64: sm4 " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 18/21] arm64/xorblocks: " Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 19/21] net/mlx5: Switch to more abstract scoped ksimd guard API on arm64 Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 20/21] arm64/fpu: Enforce task-context only for generic kernel mode FPU Ard Biesheuvel
2025-10-08 15:45 ` [PATCH v3 21/21] arm64/fpsimd: Allocate kernel mode FP/SIMD buffers on the stack Ard Biesheuvel
2025-10-17 17:12 ` Eric Biggers
2025-10-17 17:07 ` [PATCH v3 00/21] arm64: Move kernel mode FPSIMD buffer to " Eric Biggers
2025-10-21 9:23 ` Ard Biesheuvel
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20251008154533.3089255-32-ardb+git@google.com \
--to=ardb+git@google.com \
--cc=ardb@kernel.org \
--cc=ebiggers@kernel.org \
--cc=herbert@gondor.apana.org.au \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.