summaryrefslogtreecommitdiff
path: root/arch/x86/lib/crypto/chacha_glue.c
diff options
context:
space:
mode:
authorEric Biggers <ebiggers@kernel.org>2025-06-19 12:19:07 -0700
committerEric Biggers <ebiggers@kernel.org>2025-06-30 09:26:20 -0700
commit74750aa78de33794aa9ab55de15da04bd41d1ac8 (patch)
treece3498ed648b95176cff53bc3dd48f96b6575c29 /arch/x86/lib/crypto/chacha_glue.c
parenta32e93e10067d19dec302220a9124a21573e7e7e (diff)
lib/crypto: x86: Move arch/x86/lib/crypto/ into lib/crypto/
Move the contents of arch/x86/lib/crypto/ into lib/crypto/x86/. The new code organization makes a lot more sense for how this code actually works and is developed. In particular, it makes it possible to build each algorithm as a single module, with better inlining and dead code elimination. For a more detailed explanation, see the patchset which did this for the CRC library code: https://lore.kernel.org/r/20250607200454.73587-1-ebiggers@kernel.org/. Also see the patchset which did this for SHA-512: https://lore.kernel.org/linux-crypto/20250616014019.415791-1-ebiggers@kernel.org/ This is just a preparatory commit, which does the move to get the files into their new location but keeps them building the same way as before. Later commits will make the actual improvements to the way the arch-optimized code is integrated for each algorithm. Add a gitignore entry for the removed directory arch/x86/lib/crypto/ so that people don't accidentally commit leftover generated files. Acked-by: Ard Biesheuvel <ardb@kernel.org> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Sohil Mehta <sohil.mehta@intel.com> Link: https://lore.kernel.org/r/20250619191908.134235-9-ebiggers@kernel.org Signed-off-by: Eric Biggers <ebiggers@kernel.org>
Diffstat (limited to 'arch/x86/lib/crypto/chacha_glue.c')
-rw-r--r--arch/x86/lib/crypto/chacha_glue.c196
1 files changed, 0 insertions, 196 deletions
diff --git a/arch/x86/lib/crypto/chacha_glue.c b/arch/x86/lib/crypto/chacha_glue.c
deleted file mode 100644
index 10b2c945f541..000000000000
--- a/arch/x86/lib/crypto/chacha_glue.c
+++ /dev/null
@@ -1,196 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * ChaCha and HChaCha functions (x86_64 optimized)
- *
- * Copyright (C) 2015 Martin Willi
- */
-
-#include <asm/simd.h>
-#include <crypto/chacha.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-
-asmlinkage void chacha_block_xor_ssse3(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_ssse3(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void hchacha_block_ssse3(const struct chacha_state *state,
- u32 out[HCHACHA_OUT_WORDS], int nrounds);
-
-asmlinkage void chacha_2block_xor_avx2(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_avx2(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_8block_xor_avx2(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-
-asmlinkage void chacha_2block_xor_avx512vl(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_avx512vl(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_8block_xor_avx512vl(const struct chacha_state *state,
- u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
-
-static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
-{
- len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
- return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
-}
-
-static void chacha_dosimd(struct chacha_state *state, u8 *dst, const u8 *src,
- unsigned int bytes, int nrounds)
-{
- if (static_branch_likely(&chacha_use_avx512vl)) {
- while (bytes >= CHACHA_BLOCK_SIZE * 8) {
- chacha_8block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- bytes -= CHACHA_BLOCK_SIZE * 8;
- src += CHACHA_BLOCK_SIZE * 8;
- dst += CHACHA_BLOCK_SIZE * 8;
- state->x[12] += 8;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 4) {
- chacha_8block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- state->x[12] += chacha_advance(bytes, 8);
- return;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 2) {
- chacha_4block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- state->x[12] += chacha_advance(bytes, 4);
- return;
- }
- if (bytes) {
- chacha_2block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- state->x[12] += chacha_advance(bytes, 2);
- return;
- }
- }
-
- if (static_branch_likely(&chacha_use_avx2)) {
- while (bytes >= CHACHA_BLOCK_SIZE * 8) {
- chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
- bytes -= CHACHA_BLOCK_SIZE * 8;
- src += CHACHA_BLOCK_SIZE * 8;
- dst += CHACHA_BLOCK_SIZE * 8;
- state->x[12] += 8;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 4) {
- chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
- state->x[12] += chacha_advance(bytes, 8);
- return;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 2) {
- chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
- state->x[12] += chacha_advance(bytes, 4);
- return;
- }
- if (bytes > CHACHA_BLOCK_SIZE) {
- chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
- state->x[12] += chacha_advance(bytes, 2);
- return;
- }
- }
-
- while (bytes >= CHACHA_BLOCK_SIZE * 4) {
- chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
- bytes -= CHACHA_BLOCK_SIZE * 4;
- src += CHACHA_BLOCK_SIZE * 4;
- dst += CHACHA_BLOCK_SIZE * 4;
- state->x[12] += 4;
- }
- if (bytes > CHACHA_BLOCK_SIZE) {
- chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
- state->x[12] += chacha_advance(bytes, 4);
- return;
- }
- if (bytes) {
- chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
- state->x[12]++;
- }
-}
-
-void hchacha_block_arch(const struct chacha_state *state,
- u32 out[HCHACHA_OUT_WORDS], int nrounds)
-{
- if (!static_branch_likely(&chacha_use_simd)) {
- hchacha_block_generic(state, out, nrounds);
- } else {
- kernel_fpu_begin();
- hchacha_block_ssse3(state, out, nrounds);
- kernel_fpu_end();
- }
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
- unsigned int bytes, int nrounds)
-{
- if (!static_branch_likely(&chacha_use_simd) ||
- bytes <= CHACHA_BLOCK_SIZE)
- return chacha_crypt_generic(state, dst, src, bytes, nrounds);
-
- do {
- unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
-
- kernel_fpu_begin();
- chacha_dosimd(state, dst, src, todo, nrounds);
- kernel_fpu_end();
-
- bytes -= todo;
- src += todo;
- dst += todo;
- } while (bytes);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-bool chacha_is_arch_optimized(void)
-{
- return static_key_enabled(&chacha_use_simd);
-}
-EXPORT_SYMBOL(chacha_is_arch_optimized);
-
-static int __init chacha_simd_mod_init(void)
-{
- if (!boot_cpu_has(X86_FEATURE_SSSE3))
- return 0;
-
- static_branch_enable(&chacha_use_simd);
-
- if (boot_cpu_has(X86_FEATURE_AVX) &&
- boot_cpu_has(X86_FEATURE_AVX2) &&
- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
- static_branch_enable(&chacha_use_avx2);
-
- if (boot_cpu_has(X86_FEATURE_AVX512VL) &&
- boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
- static_branch_enable(&chacha_use_avx512vl);
- }
- return 0;
-}
-subsys_initcall(chacha_simd_mod_init);
-
-static void __exit chacha_simd_mod_exit(void)
-{
-}
-module_exit(chacha_simd_mod_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
-MODULE_DESCRIPTION("ChaCha and HChaCha functions (x86_64 optimized)");