aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/src/crypto/zinc/chacha20/chacha20-x86_64-glue.c
diff options
context:
space:
mode:
authorJason A. Donenfeld <Jason@zx2c4.com>2018-10-05 23:20:40 +0200
committerJason A. Donenfeld <Jason@zx2c4.com>2018-10-06 01:03:16 +0200
commitad5e42105059b23545b6958b3d8d4a65e7c78f01 (patch)
tree2aaad03f36ba8c27c051ffeb6272d4f9c851c693 /src/crypto/zinc/chacha20/chacha20-x86_64-glue.c
parentallowedips: remove ifdefs in favor of IS_ENABLED (diff)
downloadwireguard-monolithic-historical-ad5e42105059b23545b6958b3d8d4a65e7c78f01.tar.xz
wireguard-monolithic-historical-ad5e42105059b23545b6958b3d8d4a65e7c78f01.zip
global: rename include'd C files to be .c
This is done by 259 other files in the kernel tree: linux $ rg '#include.*\.c' -l | wc -l 259 Suggested-by: Sultan Alsawaf <sultanxda@gmail.com>
Diffstat (limited to 'src/crypto/zinc/chacha20/chacha20-x86_64-glue.c')
-rw-r--r--src/crypto/zinc/chacha20/chacha20-x86_64-glue.c102
1 files changed, 102 insertions, 0 deletions
diff --git a/src/crypto/zinc/chacha20/chacha20-x86_64-glue.c b/src/crypto/zinc/chacha20/chacha20-x86_64-glue.c
new file mode 100644
index 0000000..b89d5e1
--- /dev/null
+++ b/src/crypto/zinc/chacha20/chacha20-x86_64-glue.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <asm/fpu/api.h>
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/intel-family.h>
+
+asmlinkage void hchacha20_ssse3(u32 *derived_key, const u8 *nonce,
+ const u8 *key);
+asmlinkage void chacha20_ssse3(u8 *out, const u8 *in, const size_t len,
+ const u32 key[8], const u32 counter[4]);
+asmlinkage void chacha20_avx2(u8 *out, const u8 *in, const size_t len,
+ const u32 key[8], const u32 counter[4]);
+asmlinkage void chacha20_avx512(u8 *out, const u8 *in, const size_t len,
+ const u32 key[8], const u32 counter[4]);
+asmlinkage void chacha20_avx512vl(u8 *out, const u8 *in, const size_t len,
+ const u32 key[8], const u32 counter[4]);
+
+static bool chacha20_use_ssse3 __ro_after_init;
+static bool chacha20_use_avx2 __ro_after_init;
+static bool chacha20_use_avx512 __ro_after_init;
+static bool chacha20_use_avx512vl __ro_after_init;
+
+static void __init chacha20_fpu_init(void)
+{
+ chacha20_use_ssse3 = boot_cpu_has(X86_FEATURE_SSSE3);
+ chacha20_use_avx2 =
+ boot_cpu_has(X86_FEATURE_AVX) &&
+ boot_cpu_has(X86_FEATURE_AVX2) &&
+ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
+#ifndef COMPAT_CANNOT_USE_AVX512
+ chacha20_use_avx512 =
+ boot_cpu_has(X86_FEATURE_AVX) &&
+ boot_cpu_has(X86_FEATURE_AVX2) &&
+ boot_cpu_has(X86_FEATURE_AVX512F) &&
+ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
+ XFEATURE_MASK_AVX512, NULL) &&
+ /* Skylake downclocks unacceptably much when using zmm. */
+ boot_cpu_data.x86_model != INTEL_FAM6_SKYLAKE_X;
+ chacha20_use_avx512vl =
+ boot_cpu_has(X86_FEATURE_AVX) &&
+ boot_cpu_has(X86_FEATURE_AVX2) &&
+ boot_cpu_has(X86_FEATURE_AVX512F) &&
+ boot_cpu_has(X86_FEATURE_AVX512VL) &&
+ cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
+ XFEATURE_MASK_AVX512, NULL);
+#endif
+}
+
+static inline bool chacha20_arch(struct chacha20_ctx *ctx, u8 *dst,
+ const u8 *src, size_t len,
+ simd_context_t *simd_context)
+{
+ /* SIMD disables preemption, so relax after processing each page. */
+ BUILD_BUG_ON(PAGE_SIZE < CHACHA20_BLOCK_SIZE ||
+ PAGE_SIZE % CHACHA20_BLOCK_SIZE);
+
+ if (!IS_ENABLED(CONFIG_AS_SSSE3) || !chacha20_use_ssse3 ||
+ len <= CHACHA20_BLOCK_SIZE || !simd_use(simd_context))
+ return false;
+
+ for (;;) {
+ const size_t bytes = min_t(size_t, len, PAGE_SIZE);
+
+ if (IS_ENABLED(CONFIG_AS_AVX512) && chacha20_use_avx512 &&
+ len >= CHACHA20_BLOCK_SIZE * 8)
+ chacha20_avx512(dst, src, bytes, ctx->key, ctx->counter);
+ else if (IS_ENABLED(CONFIG_AS_AVX512) && chacha20_use_avx512vl &&
+ len >= CHACHA20_BLOCK_SIZE * 4)
+ chacha20_avx512vl(dst, src, bytes, ctx->key, ctx->counter);
+ else if (IS_ENABLED(CONFIG_AS_AVX2) && chacha20_use_avx2 &&
+ len >= CHACHA20_BLOCK_SIZE * 4)
+ chacha20_avx2(dst, src, bytes, ctx->key, ctx->counter);
+ else
+ chacha20_ssse3(dst, src, bytes, ctx->key, ctx->counter);
+ ctx->counter[0] += (bytes + 63) / 64;
+ len -= bytes;
+ if (!len)
+ break;
+ dst += bytes;
+ src += bytes;
+ simd_relax(simd_context);
+ }
+
+ return true;
+}
+
+static inline bool hchacha20_arch(u32 derived_key[CHACHA20_KEY_WORDS],
+ const u8 nonce[HCHACHA20_NONCE_SIZE],
+ const u8 key[HCHACHA20_KEY_SIZE],
+ simd_context_t *simd_context)
+{
+ if (IS_ENABLED(CONFIG_AS_SSSE3) && chacha20_use_ssse3 &&
+ simd_use(simd_context)) {
+ hchacha20_ssse3(derived_key, nonce, key);
+ return true;
+ }
+ return false;
+}