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>

1 files changed, 80 insertions, 0 deletions

diff --git a/lib/crypto/x86/sha256.c b/lib/crypto/x86/sha256.c
new file mode 100644
index 000000000000..80380f8fdcee
--- /dev/null
+++ b/lib/crypto/x86/sha256.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 optimized for x86_64
+ *
+ * Copyright 2025 Google LLC
+ */
+#include <asm/fpu/api.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/static_call.h>
+
+asmlinkage void sha256_transform_ssse3(u32 state[SHA256_STATE_WORDS],
+				       const u8 *data, size_t nblocks);
+asmlinkage void sha256_transform_avx(u32 state[SHA256_STATE_WORDS],
+				     const u8 *data, size_t nblocks);
+asmlinkage void sha256_transform_rorx(u32 state[SHA256_STATE_WORDS],
+				      const u8 *data, size_t nblocks);
+asmlinkage void sha256_ni_transform(u32 state[SHA256_STATE_WORDS],
+				    const u8 *data, size_t nblocks);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_sha256_x86);
+
+DEFINE_STATIC_CALL(sha256_blocks_x86, sha256_transform_ssse3);
+
+void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	if (static_branch_likely(&have_sha256_x86)) {
+		kernel_fpu_begin();
+		static_call(sha256_blocks_x86)(state, data, nblocks);
+		kernel_fpu_end();
+	} else {
+		sha256_blocks_generic(state, data, nblocks);
+	}
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_simd);
+
+void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+			const u8 *data, size_t nblocks)
+{
+	sha256_blocks_generic(state, data, nblocks);
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+
+bool sha256_is_arch_optimized(void)
+{
+	return static_key_enabled(&have_sha256_x86);
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_x86_mod_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_SHA_NI)) {
+		static_call_update(sha256_blocks_x86, sha256_ni_transform);
+	} else if (cpu_has_xfeatures(XFEATURE_MASK_SSE |
+				     XFEATURE_MASK_YMM, NULL) &&
+		   boot_cpu_has(X86_FEATURE_AVX)) {
+		if (boot_cpu_has(X86_FEATURE_AVX2) &&
+		    boot_cpu_has(X86_FEATURE_BMI2))
+			static_call_update(sha256_blocks_x86,
+					   sha256_transform_rorx);
+		else
+			static_call_update(sha256_blocks_x86,
+					   sha256_transform_avx);
+	} else if (!boot_cpu_has(X86_FEATURE_SSSE3)) {
+		return 0;
+	}
+	static_branch_enable(&have_sha256_x86);
+	return 0;
+}
+subsys_initcall(sha256_x86_mod_init);
+
+static void __exit sha256_x86_mod_exit(void)
+{
+}
+module_exit(sha256_x86_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 optimized for x86_64");