1 files changed, 103 insertions, 81 deletions

diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 388f95a4ec24..a94e30b6f941 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -7,7 +7,7 @@
  */
 
 #include <crypto/algapi.h>
-#include <crypto/chacha.h>
+#include <crypto/internal/chacha.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
@@ -21,24 +21,24 @@ asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
 asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
 					unsigned int len, int nrounds);
 asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds);
-#ifdef CONFIG_AS_AVX2
+
 asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
 asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
 asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
 				       unsigned int len, int nrounds);
-static bool chacha_use_avx2;
-#ifdef CONFIG_AS_AVX512
+
 asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
 asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
 asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
 					   unsigned int len, int nrounds);
-static bool chacha_use_avx512vl;
-#endif
-#endif
+
+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)
 {
@@ -49,9 +49,8 @@ static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
 static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			  unsigned int bytes, int nrounds)
 {
-#ifdef CONFIG_AS_AVX2
-#ifdef CONFIG_AS_AVX512
-	if (chacha_use_avx512vl) {
+	if (IS_ENABLED(CONFIG_AS_AVX512) &&
+	    static_branch_likely(&chacha_use_avx512vl)) {
 		while (bytes >= CHACHA_BLOCK_SIZE * 8) {
 			chacha_8block_xor_avx512vl(state, dst, src, bytes,
 						   nrounds);
@@ -79,8 +78,9 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			return;
 		}
 	}
-#endif
-	if (chacha_use_avx2) {
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    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;
@@ -104,7 +104,7 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 			return;
 		}
 	}
-#endif
+
 	while (bytes >= CHACHA_BLOCK_SIZE * 4) {
 		chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
 		bytes -= CHACHA_BLOCK_SIZE * 4;
@@ -123,37 +123,76 @@ static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
 	}
 }
 
-static int chacha_simd_stream_xor(struct skcipher_walk *walk,
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
+		hchacha_block_generic(state, stream, nrounds);
+	} else {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, stream, nrounds);
+		kernel_fpu_end();
+	}
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+		       int nrounds)
+{
+	state = PTR_ALIGN(state, CHACHA_STATE_ALIGN);
+
+	if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
+	    bytes <= CHACHA_BLOCK_SIZE)
+		return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+	kernel_fpu_begin();
+	chacha_dosimd(state, dst, src, bytes, nrounds);
+	kernel_fpu_end();
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_simd_stream_xor(struct skcipher_request *req,
 				  const struct chacha_ctx *ctx, const u8 *iv)
 {
 	u32 *state, state_buf[16 + 2] __aligned(8);
-	int next_yield = 4096; /* bytes until next FPU yield */
-	int err = 0;
+	struct skcipher_walk walk;
+	int err;
+
+	err = skcipher_walk_virt(&walk, req, false);
 
 	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
 	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
 
-	crypto_chacha_init(state, ctx, iv);
-
-	while (walk->nbytes > 0) {
-		unsigned int nbytes = walk->nbytes;
+	chacha_init_generic(state, ctx->key, iv);
 
-		if (nbytes < walk->total) {
-			nbytes = round_down(nbytes, walk->stride);
-			next_yield -= nbytes;
-		}
+	while (walk.nbytes > 0) {
+		unsigned int nbytes = walk.nbytes;
 
-		chacha_dosimd(state, walk->dst.virt.addr, walk->src.virt.addr,
-			      nbytes, ctx->nrounds);
+		if (nbytes < walk.total)
+			nbytes = round_down(nbytes, walk.stride);
 
-		if (next_yield <= 0) {
-			/* temporarily allow preemption */
-			kernel_fpu_end();
+		if (!static_branch_likely(&chacha_use_simd) ||
+		    !crypto_simd_usable()) {
+			chacha_crypt_generic(state, walk.dst.virt.addr,
+					     walk.src.virt.addr, nbytes,
+					     ctx->nrounds);
+		} else {
 			kernel_fpu_begin();
-			next_yield = 4096;
+			chacha_dosimd(state, walk.dst.virt.addr,
+				      walk.src.virt.addr, nbytes,
+				      ctx->nrounds);
+			kernel_fpu_end();
 		}
-
-		err = skcipher_walk_done(walk, walk->nbytes - nbytes);
+		err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
 	}
 
 	return err;
@@ -163,55 +202,34 @@ static int chacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_chacha_crypt(req);
 
-	err = skcipher_walk_virt(&walk, req, true);
-	if (err)
-		return err;
-
-	kernel_fpu_begin();
-	err = chacha_simd_stream_xor(&walk, ctx, req->iv);
-	kernel_fpu_end();
-	return err;
+	return chacha_simd_stream_xor(req, ctx, req->iv);
 }
 
 static int xchacha_simd(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-	struct skcipher_walk walk;
-	struct chacha_ctx subctx;
 	u32 *state, state_buf[16 + 2] __aligned(8);
+	struct chacha_ctx subctx;
 	u8 real_iv[16];
-	int err;
-
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
-		return crypto_xchacha_crypt(req);
-
-	err = skcipher_walk_virt(&walk, req, true);
-	if (err)
-		return err;
 
 	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
 	state = PTR_ALIGN(state_buf + 0, CHACHA_STATE_ALIGN);
-	crypto_chacha_init(state, ctx, req->iv);
-
-	kernel_fpu_begin();
-
-	hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+	chacha_init_generic(state, ctx->key, req->iv);
+
+	if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
+		kernel_fpu_begin();
+		hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
+		kernel_fpu_end();
+	} else {
+		hchacha_block_generic(state, subctx.key, ctx->nrounds);
+	}
 	subctx.nrounds = ctx->nrounds;
 
 	memcpy(&real_iv[0], req->iv + 24, 8);
 	memcpy(&real_iv[8], req->iv + 16, 8);
-	err = chacha_simd_stream_xor(&walk, &subctx, real_iv);
-
-	kernel_fpu_end();
-
-	return err;
+	return chacha_simd_stream_xor(req, &subctx, real_iv);
 }
 
 static struct skcipher_alg algs[] = {
@@ -227,7 +245,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= CHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= chacha_simd,
 		.decrypt		= chacha_simd,
 	}, {
@@ -242,7 +260,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha20_setkey,
+		.setkey			= chacha20_setkey,
 		.encrypt		= xchacha_simd,
 		.decrypt		= xchacha_simd,
 	}, {
@@ -257,7 +275,7 @@ static struct skcipher_alg algs[] = {
 		.max_keysize		= CHACHA_KEY_SIZE,
 		.ivsize			= XCHACHA_IV_SIZE,
 		.chunksize		= CHACHA_BLOCK_SIZE,
-		.setkey			= crypto_chacha12_setkey,
+		.setkey			= chacha12_setkey,
 		.encrypt		= xchacha_simd,
 		.decrypt		= xchacha_simd,
 	},
@@ -266,24 +284,28 @@ static struct skcipher_alg algs[] = {
 static int __init chacha_simd_mod_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_SSSE3))
-		return -ENODEV;
-
-#ifdef CONFIG_AS_AVX2
-	chacha_use_avx2 = boot_cpu_has(X86_FEATURE_AVX) &&
-			  boot_cpu_has(X86_FEATURE_AVX2) &&
-			  cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL);
-#ifdef CONFIG_AS_AVX512
-	chacha_use_avx512vl = chacha_use_avx2 &&
-			      boot_cpu_has(X86_FEATURE_AVX512VL) &&
-			      boot_cpu_has(X86_FEATURE_AVX512BW); /* kmovq */
-#endif
-#endif
+		return 0;
+
+	static_branch_enable(&chacha_use_simd);
+
+	if (IS_ENABLED(CONFIG_AS_AVX2) &&
+	    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 (IS_ENABLED(CONFIG_AS_AVX512) &&
+		    boot_cpu_has(X86_FEATURE_AVX512VL) &&
+		    boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
+			static_branch_enable(&chacha_use_avx512vl);
+	}
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 static void __exit chacha_simd_mod_fini(void)
 {
-	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+	if (boot_cpu_has(X86_FEATURE_SSSE3))
+		crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
 module_init(chacha_simd_mod_init);