summaryrefslogtreecommitdiff
path: root/lib/crypto/x86/blake2s-glue.c
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2025-08-05 11:15:34 +0200
committerIngo Molnar <mingo@kernel.org>2025-08-05 11:15:34 +0200
commita53d0cf7f1cb3182ad533ff5cacfa5fd29c419ad (patch)
tree59bd9bad63a1460a6079162fca98ea47f5a81679 /lib/crypto/x86/blake2s-glue.c
parented845c363d8c93eeaad4ce48bb7d5f81b6a75b61 (diff)
parent352af6a011d586ff042db4b2d1f7421875eb8a14 (diff)
Merge commit 'linus' into core/bugs, to resolve conflicts
Resolve conflicts with this commit that was developed in parallel during the merge window: 8c8efa93db68 ("x86/bug: Add ARCH_WARN_ASM macro for BUG/WARN asm code sharing with Rust") Conflicts: arch/riscv/include/asm/bug.h arch/x86/include/asm/bug.h Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'lib/crypto/x86/blake2s-glue.c')
-rw-r--r--lib/crypto/x86/blake2s-glue.c70
1 files changed, 70 insertions, 0 deletions
diff --git a/lib/crypto/x86/blake2s-glue.c b/lib/crypto/x86/blake2s-glue.c
new file mode 100644
index 000000000000..adc296cd17c9
--- /dev/null
+++ b/lib/crypto/x86/blake2s-glue.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <asm/cpufeature.h>
+#include <asm/fpu/api.h>
+#include <asm/processor.h>
+#include <asm/simd.h>
+#include <crypto/internal/blake2s.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/sizes.h>
+
+asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state,
+ const u8 *block, const size_t nblocks,
+ const u32 inc);
+asmlinkage void blake2s_compress_avx512(struct blake2s_state *state,
+ const u8 *block, const size_t nblocks,
+ const u32 inc);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512);
+
+void blake2s_compress(struct blake2s_state *state, const u8 *block,
+ size_t nblocks, const u32 inc)
+{
+ /* SIMD disables preemption, so relax after processing each page. */
+ BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8);
+
+ if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) {
+ blake2s_compress_generic(state, block, nblocks, inc);
+ return;
+ }
+
+ do {
+ const size_t blocks = min_t(size_t, nblocks,
+ SZ_4K / BLAKE2S_BLOCK_SIZE);
+
+ kernel_fpu_begin();
+ if (static_branch_likely(&blake2s_use_avx512))
+ blake2s_compress_avx512(state, block, blocks, inc);
+ else
+ blake2s_compress_ssse3(state, block, blocks, inc);
+ kernel_fpu_end();
+
+ nblocks -= blocks;
+ block += blocks * BLAKE2S_BLOCK_SIZE;
+ } while (nblocks);
+}
+EXPORT_SYMBOL(blake2s_compress);
+
+static int __init blake2s_mod_init(void)
+{
+ if (boot_cpu_has(X86_FEATURE_SSSE3))
+ static_branch_enable(&blake2s_use_ssse3);
+
+ if (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))
+ static_branch_enable(&blake2s_use_avx512);
+
+ return 0;
+}
+
+subsys_initcall(blake2s_mod_init);