diff options
Diffstat (limited to 'arch/riscv')
35 files changed, 654 insertions, 599 deletions
diff --git a/arch/riscv/crypto/Kconfig b/arch/riscv/crypto/Kconfig index c67095a3d669..cd9b776602f8 100644 --- a/arch/riscv/crypto/Kconfig +++ b/arch/riscv/crypto/Kconfig @@ -18,16 +18,6 @@ config CRYPTO_AES_RISCV64 - Zvkb vector crypto extension (CTR) - Zvkg vector crypto extension (XTS) -config CRYPTO_CHACHA_RISCV64 - tristate "Ciphers: ChaCha" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO - select CRYPTO_SKCIPHER - help - Length-preserving ciphers: ChaCha20 stream cipher algorithm - - Architecture: riscv64 using: - - Zvkb vector crypto extension - config CRYPTO_GHASH_RISCV64 tristate "Hash functions: GHASH" depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO @@ -38,17 +28,6 @@ config CRYPTO_GHASH_RISCV64 Architecture: riscv64 using: - Zvkg vector crypto extension -config CRYPTO_SHA256_RISCV64 - tristate "Hash functions: SHA-224 and SHA-256" - depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO - select CRYPTO_SHA256 - help - SHA-224 and SHA-256 secure hash algorithm (FIPS 180) - - Architecture: riscv64 using: - - Zvknha or Zvknhb vector crypto extensions - - Zvkb vector crypto extension - config CRYPTO_SHA512_RISCV64 tristate "Hash functions: SHA-384 and SHA-512" depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO @@ -64,7 +43,7 @@ config CRYPTO_SM3_RISCV64 tristate "Hash functions: SM3 (ShangMi 3)" depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO select CRYPTO_HASH - select CRYPTO_SM3 + select CRYPTO_LIB_SM3 help SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012) diff --git a/arch/riscv/crypto/Makefile b/arch/riscv/crypto/Makefile index 247c7bc7288c..e10e8257734e 100644 --- a/arch/riscv/crypto/Makefile +++ b/arch/riscv/crypto/Makefile @@ -4,15 +4,9 @@ obj-$(CONFIG_CRYPTO_AES_RISCV64) += aes-riscv64.o aes-riscv64-y := aes-riscv64-glue.o aes-riscv64-zvkned.o \ aes-riscv64-zvkned-zvbb-zvkg.o aes-riscv64-zvkned-zvkb.o -obj-$(CONFIG_CRYPTO_CHACHA_RISCV64) += chacha-riscv64.o -chacha-riscv64-y := chacha-riscv64-glue.o chacha-riscv64-zvkb.o - obj-$(CONFIG_CRYPTO_GHASH_RISCV64) += ghash-riscv64.o ghash-riscv64-y := ghash-riscv64-glue.o ghash-riscv64-zvkg.o -obj-$(CONFIG_CRYPTO_SHA256_RISCV64) += sha256-riscv64.o -sha256-riscv64-y := sha256-riscv64-glue.o sha256-riscv64-zvknha_or_zvknhb-zvkb.o - obj-$(CONFIG_CRYPTO_SHA512_RISCV64) += sha512-riscv64.o sha512-riscv64-y := sha512-riscv64-glue.o sha512-riscv64-zvknhb-zvkb.o diff --git a/arch/riscv/crypto/chacha-riscv64-glue.c b/arch/riscv/crypto/chacha-riscv64-glue.c deleted file mode 100644 index 10b46f36375a..000000000000 --- a/arch/riscv/crypto/chacha-riscv64-glue.c +++ /dev/null @@ -1,101 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * ChaCha20 using the RISC-V vector crypto extensions - * - * Copyright (C) 2023 SiFive, Inc. - * Author: Jerry Shih <jerry.shih@sifive.com> - */ - -#include <asm/simd.h> -#include <asm/vector.h> -#include <crypto/internal/chacha.h> -#include <crypto/internal/skcipher.h> -#include <linux/linkage.h> -#include <linux/module.h> - -asmlinkage void chacha20_zvkb(const u32 key[8], const u8 *in, u8 *out, - size_t len, const u32 iv[4]); - -static int riscv64_chacha20_crypt(struct skcipher_request *req) -{ - u32 iv[CHACHA_IV_SIZE / sizeof(u32)]; - u8 block_buffer[CHACHA_BLOCK_SIZE]; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - const struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - unsigned int tail_bytes; - int err; - - iv[0] = get_unaligned_le32(req->iv); - iv[1] = get_unaligned_le32(req->iv + 4); - iv[2] = get_unaligned_le32(req->iv + 8); - iv[3] = get_unaligned_le32(req->iv + 12); - - err = skcipher_walk_virt(&walk, req, false); - while (walk.nbytes) { - nbytes = walk.nbytes & ~(CHACHA_BLOCK_SIZE - 1); - tail_bytes = walk.nbytes & (CHACHA_BLOCK_SIZE - 1); - kernel_vector_begin(); - if (nbytes) { - chacha20_zvkb(ctx->key, walk.src.virt.addr, - walk.dst.virt.addr, nbytes, iv); - iv[0] += nbytes / CHACHA_BLOCK_SIZE; - } - if (walk.nbytes == walk.total && tail_bytes > 0) { - memcpy(block_buffer, walk.src.virt.addr + nbytes, - tail_bytes); - chacha20_zvkb(ctx->key, block_buffer, block_buffer, - CHACHA_BLOCK_SIZE, iv); - memcpy(walk.dst.virt.addr + nbytes, block_buffer, - tail_bytes); - tail_bytes = 0; - } - kernel_vector_end(); - - err = skcipher_walk_done(&walk, tail_bytes); - } - - return err; -} - -static struct skcipher_alg riscv64_chacha_alg = { - .setkey = chacha20_setkey, - .encrypt = riscv64_chacha20_crypt, - .decrypt = riscv64_chacha20_crypt, - .min_keysize = CHACHA_KEY_SIZE, - .max_keysize = CHACHA_KEY_SIZE, - .ivsize = CHACHA_IV_SIZE, - .chunksize = CHACHA_BLOCK_SIZE, - .walksize = 4 * CHACHA_BLOCK_SIZE, - .base = { - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct chacha_ctx), - .cra_priority = 300, - .cra_name = "chacha20", - .cra_driver_name = "chacha20-riscv64-zvkb", - .cra_module = THIS_MODULE, - }, -}; - -static int __init riscv64_chacha_mod_init(void) -{ - if (riscv_isa_extension_available(NULL, ZVKB) && - riscv_vector_vlen() >= 128) - return crypto_register_skcipher(&riscv64_chacha_alg); - - return -ENODEV; -} - -static void __exit riscv64_chacha_mod_exit(void) -{ - crypto_unregister_skcipher(&riscv64_chacha_alg); -} - -module_init(riscv64_chacha_mod_init); -module_exit(riscv64_chacha_mod_exit); - -MODULE_DESCRIPTION("ChaCha20 (RISC-V accelerated)"); -MODULE_AUTHOR("Jerry Shih <jerry.shih@sifive.com>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("chacha20"); diff --git a/arch/riscv/crypto/ghash-riscv64-glue.c b/arch/riscv/crypto/ghash-riscv64-glue.c index 312e7891fd0a..d86073d25387 100644 --- a/arch/riscv/crypto/ghash-riscv64-glue.c +++ b/arch/riscv/crypto/ghash-riscv64-glue.c @@ -11,11 +11,16 @@ #include <asm/simd.h> #include <asm/vector.h> +#include <crypto/b128ops.h> +#include <crypto/gf128mul.h> #include <crypto/ghash.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> -#include <linux/linkage.h> +#include <crypto/utils.h> +#include <linux/errno.h> +#include <linux/kernel.h> #include <linux/module.h> +#include <linux/string.h> asmlinkage void ghash_zvkg(be128 *accumulator, const be128 *key, const u8 *data, size_t len); @@ -26,8 +31,6 @@ struct riscv64_ghash_tfm_ctx { struct riscv64_ghash_desc_ctx { be128 accumulator; - u8 buffer[GHASH_BLOCK_SIZE]; - u32 bytes; }; static int riscv64_ghash_setkey(struct crypto_shash *tfm, const u8 *key, @@ -78,50 +81,24 @@ static int riscv64_ghash_update(struct shash_desc *desc, const u8 *src, { const struct riscv64_ghash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct riscv64_ghash_desc_ctx *dctx = shash_desc_ctx(desc); - unsigned int len; - - if (dctx->bytes) { - if (dctx->bytes + srclen < GHASH_BLOCK_SIZE) { - memcpy(dctx->buffer + dctx->bytes, src, srclen); - dctx->bytes += srclen; - return 0; - } - memcpy(dctx->buffer + dctx->bytes, src, - GHASH_BLOCK_SIZE - dctx->bytes); - riscv64_ghash_blocks(tctx, dctx, dctx->buffer, - GHASH_BLOCK_SIZE); - src += GHASH_BLOCK_SIZE - dctx->bytes; - srclen -= GHASH_BLOCK_SIZE - dctx->bytes; - dctx->bytes = 0; - } - - len = round_down(srclen, GHASH_BLOCK_SIZE); - if (len) { - riscv64_ghash_blocks(tctx, dctx, src, len); - src += len; - srclen -= len; - } - if (srclen) { - memcpy(dctx->buffer, src, srclen); - dctx->bytes = srclen; - } - - return 0; + riscv64_ghash_blocks(tctx, dctx, src, + round_down(srclen, GHASH_BLOCK_SIZE)); + return srclen - round_down(srclen, GHASH_BLOCK_SIZE); } -static int riscv64_ghash_final(struct shash_desc *desc, u8 *out) +static int riscv64_ghash_finup(struct shash_desc *desc, const u8 *src, + unsigned int len, u8 *out) { const struct riscv64_ghash_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm); struct riscv64_ghash_desc_ctx *dctx = shash_desc_ctx(desc); - int i; - if (dctx->bytes) { - for (i = dctx->bytes; i < GHASH_BLOCK_SIZE; i++) - dctx->buffer[i] = 0; + if (len) { + u8 buf[GHASH_BLOCK_SIZE] = {}; - riscv64_ghash_blocks(tctx, dctx, dctx->buffer, - GHASH_BLOCK_SIZE); + memcpy(buf, src, len); + riscv64_ghash_blocks(tctx, dctx, buf, GHASH_BLOCK_SIZE); + memzero_explicit(buf, sizeof(buf)); } memcpy(out, &dctx->accumulator, GHASH_DIGEST_SIZE); @@ -131,7 +108,7 @@ static int riscv64_ghash_final(struct shash_desc *desc, u8 *out) static struct shash_alg riscv64_ghash_alg = { .init = riscv64_ghash_init, .update = riscv64_ghash_update, - .final = riscv64_ghash_final, + .finup = riscv64_ghash_finup, .setkey = riscv64_ghash_setkey, .descsize = sizeof(struct riscv64_ghash_desc_ctx), .digestsize = GHASH_DIGEST_SIZE, @@ -139,6 +116,7 @@ static struct shash_alg riscv64_ghash_alg = { .cra_blocksize = GHASH_BLOCK_SIZE, .cra_ctxsize = sizeof(struct riscv64_ghash_tfm_ctx), .cra_priority = 300, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY, .cra_name = "ghash", .cra_driver_name = "ghash-riscv64-zvkg", .cra_module = THIS_MODULE, diff --git a/arch/riscv/crypto/sha256-riscv64-glue.c b/arch/riscv/crypto/sha256-riscv64-glue.c deleted file mode 100644 index 71e051e40a64..000000000000 --- a/arch/riscv/crypto/sha256-riscv64-glue.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * SHA-256 and SHA-224 using the RISC-V vector crypto extensions - * - * Copyright (C) 2022 VRULL GmbH - * Author: Heiko Stuebner <heiko.stuebner@vrull.eu> - * - * Copyright (C) 2023 SiFive, Inc. - * Author: Jerry Shih <jerry.shih@sifive.com> - */ - -#include <asm/simd.h> -#include <asm/vector.h> -#include <crypto/internal/hash.h> -#include <crypto/internal/simd.h> -#include <crypto/sha256_base.h> -#include <linux/linkage.h> -#include <linux/module.h> - -/* - * Note: the asm function only uses the 'state' field of struct sha256_state. - * It is assumed to be the first field. - */ -asmlinkage void sha256_transform_zvknha_or_zvknhb_zvkb( - struct sha256_state *state, const u8 *data, int num_blocks); - -static int riscv64_sha256_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - /* - * Ensure struct sha256_state begins directly with the SHA-256 - * 256-bit internal state, as this is what the asm function expects. - */ - BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); - - if (crypto_simd_usable()) { - kernel_vector_begin(); - sha256_base_do_update(desc, data, len, - sha256_transform_zvknha_or_zvknhb_zvkb); - kernel_vector_end(); - } else { - crypto_sha256_update(desc, data, len); - } - return 0; -} - -static int riscv64_sha256_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - if (crypto_simd_usable()) { - kernel_vector_begin(); - if (len) - sha256_base_do_update( - desc, data, len, - sha256_transform_zvknha_or_zvknhb_zvkb); - sha256_base_do_finalize( - desc, sha256_transform_zvknha_or_zvknhb_zvkb); - kernel_vector_end(); - - return sha256_base_finish(desc, out); - } - - return crypto_sha256_finup(desc, data, len, out); -} - -static int riscv64_sha256_final(struct shash_desc *desc, u8 *out) -{ - return riscv64_sha256_finup(desc, NULL, 0, out); -} - -static int riscv64_sha256_digest(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) -{ - return sha256_base_init(desc) ?: - riscv64_sha256_finup(desc, data, len, out); -} - -static struct shash_alg riscv64_sha256_algs[] = { - { - .init = sha256_base_init, - .update = riscv64_sha256_update, - .final = riscv64_sha256_final, - .finup = riscv64_sha256_finup, - .digest = riscv64_sha256_digest, - .descsize = sizeof(struct sha256_state), - .digestsize = SHA256_DIGEST_SIZE, - .base = { - .cra_blocksize = SHA256_BLOCK_SIZE, - .cra_priority = 300, - .cra_name = "sha256", - .cra_driver_name = "sha256-riscv64-zvknha_or_zvknhb-zvkb", - .cra_module = THIS_MODULE, - }, - }, { - .init = sha224_base_init, - .update = riscv64_sha256_update, - .final = riscv64_sha256_final, - .finup = riscv64_sha256_finup, - .descsize = sizeof(struct sha256_state), - .digestsize = SHA224_DIGEST_SIZE, - .base = { - .cra_blocksize = SHA224_BLOCK_SIZE, - .cra_priority = 300, - .cra_name = "sha224", - .cra_driver_name = "sha224-riscv64-zvknha_or_zvknhb-zvkb", - .cra_module = THIS_MODULE, - }, - }, -}; - -static int __init riscv64_sha256_mod_init(void) -{ - /* Both zvknha and zvknhb provide the SHA-256 instructions. */ - if ((riscv_isa_extension_available(NULL, ZVKNHA) || - riscv_isa_extension_available(NULL, ZVKNHB)) && - riscv_isa_extension_available(NULL, ZVKB) && - riscv_vector_vlen() >= 128) - return crypto_register_shashes(riscv64_sha256_algs, - ARRAY_SIZE(riscv64_sha256_algs)); - - return -ENODEV; -} - -static void __exit riscv64_sha256_mod_exit(void) -{ - crypto_unregister_shashes(riscv64_sha256_algs, - ARRAY_SIZE(riscv64_sha256_algs)); -} - -module_init(riscv64_sha256_mod_init); -module_exit(riscv64_sha256_mod_exit); - -MODULE_DESCRIPTION("SHA-256 (RISC-V accelerated)"); -MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("sha256"); -MODULE_ALIAS_CRYPTO("sha224"); diff --git a/arch/riscv/crypto/sha512-riscv64-glue.c b/arch/riscv/crypto/sha512-riscv64-glue.c index 43b56a08aeb5..4634fca78ae2 100644 --- a/arch/riscv/crypto/sha512-riscv64-glue.c +++ b/arch/riscv/crypto/sha512-riscv64-glue.c @@ -14,7 +14,7 @@ #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> #include <crypto/sha512_base.h> -#include <linux/linkage.h> +#include <linux/kernel.h> #include <linux/module.h> /* @@ -24,8 +24,8 @@ asmlinkage void sha512_transform_zvknhb_zvkb( struct sha512_state *state, const u8 *data, int num_blocks); -static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static void sha512_block(struct sha512_state *state, const u8 *data, + int num_blocks) { /* * Ensure struct sha512_state begins directly with the SHA-512 @@ -35,35 +35,24 @@ static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data, if (crypto_simd_usable()) { kernel_vector_begin(); - sha512_base_do_update(desc, data, len, - sha512_transform_zvknhb_zvkb); + sha512_transform_zvknhb_zvkb(state, data, num_blocks); kernel_vector_end(); } else { - crypto_sha512_update(desc, data, len); + sha512_generic_block_fn(state, data, num_blocks); } - return 0; } -static int riscv64_sha512_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - if (crypto_simd_usable()) { - kernel_vector_begin(); - if (len) - sha512_base_do_update(desc, data, len, - sha512_transform_zvknhb_zvkb); - sha512_base_do_finalize(desc, sha512_transform_zvknhb_zvkb); - kernel_vector_end(); - - return sha512_base_finish(desc, out); - } - - return crypto_sha512_finup(desc, data, len, out); + return sha512_base_do_update_blocks(desc, data, len, sha512_block); } -static int riscv64_sha512_final(struct shash_desc *desc, u8 *out) +static int riscv64_sha512_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - return riscv64_sha512_finup(desc, NULL, 0, out); + sha512_base_do_finup(desc, data, len, sha512_block); + return sha512_base_finish(desc, out); } static int riscv64_sha512_digest(struct shash_desc *desc, const u8 *data, @@ -77,14 +66,15 @@ static struct shash_alg riscv64_sha512_algs[] = { { .init = sha512_base_init, .update = riscv64_sha512_update, - .final = riscv64_sha512_final, .finup = riscv64_sha512_finup, .digest = riscv64_sha512_digest, - .descsize = sizeof(struct sha512_state), + .descsize = SHA512_STATE_SIZE, .digestsize = SHA512_DIGEST_SIZE, .base = { .cra_blocksize = SHA512_BLOCK_SIZE, .cra_priority = 300, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | + CRYPTO_AHASH_ALG_FINUP_MAX, .cra_name = "sha512", .cra_driver_name = "sha512-riscv64-zvknhb-zvkb", .cra_module = THIS_MODULE, @@ -92,13 +82,14 @@ static struct shash_alg riscv64_sha512_algs[] = { }, { .init = sha384_base_init, .update = riscv64_sha512_update, - .final = riscv64_sha512_final, .finup = riscv64_sha512_finup, - .descsize = sizeof(struct sha512_state), + .descsize = SHA512_STATE_SIZE, .digestsize = SHA384_DIGEST_SIZE, .base = { .cra_blocksize = SHA384_BLOCK_SIZE, .cra_priority = 300, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | + CRYPTO_AHASH_ALG_FINUP_MAX, .cra_name = "sha384", .cra_driver_name = "sha384-riscv64-zvknhb-zvkb", .cra_module = THIS_MODULE, diff --git a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S b/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S index 3a9ae210f915..89f4a10d12dd 100644 --- a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S +++ b/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S @@ -43,7 +43,7 @@ // - RISC-V Vector SHA-2 Secure Hash extension ('Zvknhb') // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') -#include <linux/cfi_types.h> +#include <linux/linkage.h> .text .option arch, +zvknhb, +zvkb @@ -95,7 +95,7 @@ // void sha512_transform_zvknhb_zvkb(u64 state[8], const u8 *data, // int num_blocks); -SYM_TYPED_FUNC_START(sha512_transform_zvknhb_zvkb) +SYM_FUNC_START(sha512_transform_zvknhb_zvkb) // Setup mask for the vmerge to replace the first word (idx==0) in // message scheduling. There are 4 words, so an 8-bit mask suffices. diff --git a/arch/riscv/crypto/sm3-riscv64-glue.c b/arch/riscv/crypto/sm3-riscv64-glue.c index e1737a970c7c..abdfe4a63a27 100644 --- a/arch/riscv/crypto/sm3-riscv64-glue.c +++ b/arch/riscv/crypto/sm3-riscv64-glue.c @@ -13,8 +13,9 @@ #include <asm/vector.h> #include <crypto/internal/hash.h> #include <crypto/internal/simd.h> +#include <crypto/sm3.h> #include <crypto/sm3_base.h> -#include <linux/linkage.h> +#include <linux/kernel.h> #include <linux/module.h> /* @@ -24,8 +25,8 @@ asmlinkage void sm3_transform_zvksh_zvkb( struct sm3_state *state, const u8 *data, int num_blocks); -static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static void sm3_block(struct sm3_state *state, const u8 *data, + int num_blocks) { /* * Ensure struct sm3_state begins directly with the SM3 @@ -35,52 +36,36 @@ static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data, if (crypto_simd_usable()) { kernel_vector_begin(); - sm3_base_do_update(desc, data, len, sm3_transform_zvksh_zvkb); + sm3_transform_zvksh_zvkb(state, data, num_blocks); kernel_vector_end(); } else { - sm3_update(shash_desc_ctx(desc), data, len); + sm3_block_generic(state, data, num_blocks); } - return 0; } -static int riscv64_sm3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int riscv64_sm3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - struct sm3_state *ctx; - - if (crypto_simd_usable()) { - kernel_vector_begin(); - if (len) - sm3_base_do_update(desc, data, len, - sm3_transform_zvksh_zvkb); - sm3_base_do_finalize(desc, sm3_transform_zvksh_zvkb); - kernel_vector_end(); - - return sm3_base_finish(desc, out); - } - - ctx = shash_desc_ctx(desc); - if (len) - sm3_update(ctx, data, len); - sm3_final(ctx, out); - - return 0; + return sm3_base_do_update_blocks(desc, data, len, sm3_block); } -static int riscv64_sm3_final(struct shash_desc *desc, u8 *out) +static int riscv64_sm3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - return riscv64_sm3_finup(desc, NULL, 0, out); + sm3_base_do_finup(desc, data, len, sm3_block); + return sm3_base_finish(desc, out); } static struct shash_alg riscv64_sm3_alg = { .init = sm3_base_init, .update = riscv64_sm3_update, - .final = riscv64_sm3_final, .finup = riscv64_sm3_finup, - .descsize = sizeof(struct sm3_state), + .descsize = SM3_STATE_SIZE, .digestsize = SM3_DIGEST_SIZE, .base = { .cra_blocksize = SM3_BLOCK_SIZE, + .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY | + CRYPTO_AHASH_ALG_FINUP_MAX, .cra_priority = 300, .cra_name = "sm3", .cra_driver_name = "sm3-riscv64-zvksh-zvkb", diff --git a/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S b/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S index a2b65d961c04..4fe754846f65 100644 --- a/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S +++ b/arch/riscv/crypto/sm3-riscv64-zvksh-zvkb.S @@ -43,7 +43,7 @@ // - RISC-V Vector SM3 Secure Hash extension ('Zvksh') // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') -#include <linux/cfi_types.h> +#include <linux/linkage.h> .text .option arch, +zvksh, +zvkb @@ -81,7 +81,7 @@ .endm // void sm3_transform_zvksh_zvkb(u32 state[8], const u8 *data, int num_blocks); -SYM_TYPED_FUNC_START(sm3_transform_zvksh_zvkb) +SYM_FUNC_START(sm3_transform_zvksh_zvkb) // Load the state and endian-swap each 32-bit word. vsetivli zero, 8, e32, m2, ta, ma diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index cd627ec289f1..bfc8ea5f9319 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -52,6 +52,8 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs); +asmlinkage void ret_from_fork_user(struct pt_regs *regs); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h index 1f37b600ca47..3b643b9efc07 100644 --- a/arch/riscv/include/asm/kvm_aia.h +++ b/arch/riscv/include/asm/kvm_aia.h @@ -63,9 +63,6 @@ struct kvm_vcpu_aia { /* CPU AIA CSR context of Guest VCPU */ struct kvm_vcpu_aia_csr guest_csr; - /* CPU AIA CSR context upon Guest VCPU reset */ - struct kvm_vcpu_aia_csr guest_reset_csr; - /* Guest physical address of IMSIC for this VCPU */ gpa_t imsic_addr; diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 0e9c2fab6378..85cfebc32e4c 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -119,6 +119,9 @@ struct kvm_arch { /* AIA Guest/VM context */ struct kvm_aia aia; + + /* KVM_CAP_RISCV_MP_STATE_RESET */ + bool mp_state_reset; }; struct kvm_cpu_trap { @@ -193,6 +196,12 @@ struct kvm_vcpu_smstateen_csr { unsigned long sstateen0; }; +struct kvm_vcpu_reset_state { + spinlock_t lock; + unsigned long pc; + unsigned long a1; +}; + struct kvm_vcpu_arch { /* VCPU ran at least once */ bool ran_atleast_once; @@ -227,12 +236,8 @@ struct kvm_vcpu_arch { /* CPU Smstateen CSR context of Guest VCPU */ struct kvm_vcpu_smstateen_csr smstateen_csr; - /* CPU context upon Guest VCPU reset */ - struct kvm_cpu_context guest_reset_context; - spinlock_t reset_cntx_lock; - - /* CPU CSR context upon Guest VCPU reset */ - struct kvm_vcpu_csr guest_reset_csr; + /* CPU reset state of Guest VCPU */ + struct kvm_vcpu_reset_state reset_state; /* * VCPU interrupts diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index 4ed6203cdd30..439ab2b3534f 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -55,6 +55,9 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type, u64 flags); +void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, + unsigned long pc, unsigned long a1); +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h index 27f5bccdd8b0..57a798a4cb0d 100644 --- a/arch/riscv/include/asm/kvm_vcpu_vector.h +++ b/arch/riscv/include/asm/kvm_vcpu_vector.h @@ -33,8 +33,7 @@ void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, unsigned long *isa); void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx); void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx); -int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx); +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu); #else @@ -62,8 +61,7 @@ static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cn { } -static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx) +static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu) { return 0; } diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 33a5a9f2a0d4..0fb338000c6d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -319,17 +319,21 @@ SYM_CODE_END(handle_kernel_stack_overflow) ASM_NOKPROBE(handle_kernel_stack_overflow) #endif -SYM_CODE_START(ret_from_fork) +SYM_CODE_START(ret_from_fork_kernel_asm) + call schedule_tail + move a0, s1 /* fn_arg */ + move a1, s0 /* fn */ + move a2, sp /* pt_regs */ + call ret_from_fork_kernel + j ret_from_exception +SYM_CODE_END(ret_from_fork_kernel_asm) + +SYM_CODE_START(ret_from_fork_user_asm) call schedule_tail - beqz s0, 1f /* not from kernel thread */ - /* Call fn(arg) */ - move a0, s1 - jalr s0 -1: move a0, sp /* pt_regs */ - call syscall_exit_to_user_mode + call ret_from_fork_user j ret_from_exception -SYM_CODE_END(ret_from_fork) +SYM_CODE_END(ret_from_fork_user_asm) #ifdef CONFIG_IRQ_STACKS /* diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 356d5397b2a2..bdf3352acf4c 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -131,6 +131,12 @@ secondary_start_sbi: csrw CSR_IE, zero csrw CSR_IP, zero +#ifndef CONFIG_RISCV_M_MODE + /* Enable time CSR */ + li t0, 0x2 + csrw CSR_SCOUNTEREN, t0 +#endif + /* Load the global pointer */ load_global_pointer @@ -226,6 +232,10 @@ SYM_CODE_START(_start_kernel) * to hand it to us. */ csrr a0, CSR_MHARTID +#else + /* Enable time CSR */ + li t0, 0x2 + csrw CSR_SCOUNTEREN, t0 #endif /* CONFIG_RISCV_M_MODE */ /* Load the global pointer */ diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 15d8f75902f8..bbf7ec6a75c0 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -17,7 +17,9 @@ #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/personality.h> +#include <linux/entry-common.h> +#include <asm/asm-prototypes.h> #include <asm/unistd.h> #include <asm/processor.h> #include <asm/csr.h> @@ -36,7 +38,8 @@ unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); #endif -extern asmlinkage void ret_from_fork(void); +extern asmlinkage void ret_from_fork_kernel_asm(void); +extern asmlinkage void ret_from_fork_user_asm(void); void noinstr arch_cpu_idle(void) { @@ -206,6 +209,18 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs) +{ + fn(fn_arg); + + syscall_exit_to_user_mode(regs); +} + +asmlinkage void ret_from_fork_user(struct pt_regs *regs) +{ + syscall_exit_to_user_mode(regs); +} + int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; @@ -228,6 +243,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.s[0] = (unsigned long)args->fn; p->thread.s[1] = (unsigned long)args->fn_arg; + p->thread.ra = (unsigned long)ret_from_fork_kernel_asm; } else { *childregs = *(current_pt_regs()); /* Turn off status.VS */ @@ -237,12 +253,11 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) if (clone_flags & CLONE_SETTLS) childregs->tp = tls; childregs->a0 = 0; /* Return value of fork() */ - p->thread.s[0] = 0; + p->thread.ra = (unsigned long)ret_from_fork_user_asm; } p->thread.riscv_v_flags = 0; if (has_vector() || has_xtheadvector()) riscv_v_thread_alloc(p); - p->thread.ra = (unsigned long)ret_from_fork; p->thread.sp = (unsigned long)childregs; /* kernel sp */ return 0; } diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index 0c3cbb0915ff..704c2899197e 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -18,7 +18,7 @@ menuconfig VIRTUALIZATION if VIRTUALIZATION config KVM - tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)" + tristate "Kernel-based Virtual Machine (KVM) support" depends on RISCV_SBI && MMU select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQ_ROUTING diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c index 39cd26af5a69..43e472ff3e1a 100644 --- a/arch/riscv/kvm/aia_device.c +++ b/arch/riscv/kvm/aia_device.c @@ -526,12 +526,10 @@ int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu) void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu) { struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; - struct kvm_vcpu_aia_csr *reset_csr = - &vcpu->arch.aia_context.guest_reset_csr; if (!kvm_riscv_aia_available()) return; - memcpy(csr, reset_csr, sizeof(*csr)); + memset(csr, 0, sizeof(*csr)); /* Proceed only if AIA was initialized successfully */ if (!kvm_riscv_aia_initialized(vcpu->kvm)) diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 02635bac91f1..e0a01af426ff 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -51,12 +51,33 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { sizeof(kvm_vcpu_stats_desc), }; -static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) +static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu, + bool kvm_sbi_reset) { struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; - struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; - struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context; + void *vector_datap = cntx->vector.datap; + + memset(cntx, 0, sizeof(*cntx)); + memset(csr, 0, sizeof(*csr)); + memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr)); + + /* Restore datap as it's not a part of the guest context. */ + cntx->vector.datap = vector_datap; + + if (kvm_sbi_reset) + kvm_riscv_vcpu_sbi_load_reset_state(vcpu); + + /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ + cntx->sstatus = SR_SPP | SR_SPIE; + + cntx->hstatus |= HSTATUS_VTW; + cntx->hstatus |= HSTATUS_SPVP; + cntx->hstatus |= HSTATUS_SPV; +} + +static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) +{ bool loaded; /** @@ -71,13 +92,7 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.last_exit_cpu = -1; - memcpy(csr, reset_csr, sizeof(*csr)); - - spin_lock(&vcpu->arch.reset_cntx_lock); - memcpy(cntx, reset_cntx, sizeof(*cntx)); - spin_unlock(&vcpu->arch.reset_cntx_lock); - - memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr)); + kvm_riscv_vcpu_context_reset(vcpu, kvm_sbi_reset); kvm_riscv_vcpu_fp_reset(vcpu); @@ -112,8 +127,6 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { int rc; - struct kvm_cpu_context *cntx; - struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; spin_lock_init(&vcpu->arch.mp_state_lock); @@ -133,24 +146,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Setup VCPU hfence queue */ spin_lock_init(&vcpu->arch.hfence_lock); - /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ - spin_lock_init(&vcpu->arch.reset_cntx_lock); + spin_lock_init(&vcpu->arch.reset_state.lock); - spin_lock(&vcpu->arch.reset_cntx_lock); - cntx = &vcpu->arch.guest_reset_context; - cntx->sstatus = SR_SPP | SR_SPIE; - cntx->hstatus = 0; - cntx->hstatus |= HSTATUS_VTW; - cntx->hstatus |= HSTATUS_SPVP; - cntx->hstatus |= HSTATUS_SPV; - spin_unlock(&vcpu->arch.reset_cntx_lock); - - if (kvm_riscv_vcpu_alloc_vector_context(vcpu, cntx)) + if (kvm_riscv_vcpu_alloc_vector_context(vcpu)) return -ENOMEM; - /* By default, make CY, TM, and IR counters accessible in VU mode */ - reset_csr->scounteren = 0x7; - /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); @@ -169,7 +169,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_sbi_init(vcpu); /* Reset VCPU */ - kvm_riscv_reset_vcpu(vcpu); + kvm_riscv_reset_vcpu(vcpu, false); return 0; } @@ -518,6 +518,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, case KVM_MP_STATE_STOPPED: __kvm_riscv_vcpu_power_off(vcpu); break; + case KVM_MP_STATE_INIT_RECEIVED: + if (vcpu->kvm->arch.mp_state_reset) + kvm_riscv_reset_vcpu(vcpu, false); + else + ret = -EINVAL; + break; default: ret = -EINVAL; } @@ -706,7 +712,7 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) - kvm_riscv_reset_vcpu(vcpu); + kvm_riscv_reset_vcpu(vcpu, true); if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu)) kvm_riscv_gstage_update_hgatp(vcpu); diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index d1c83a77735e..6e09b518a5d1 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -143,9 +143,9 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, struct kvm_vcpu *tmp; kvm_for_each_vcpu(i, tmp, vcpu->kvm) { - spin_lock(&vcpu->arch.mp_state_lock); + spin_lock(&tmp->arch.mp_state_lock); WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); - spin_unlock(&vcpu->arch.mp_state_lock); + spin_unlock(&tmp->arch.mp_state_lock); } kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); @@ -156,6 +156,34 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, run->exit_reason = KVM_EXIT_SYSTEM_EVENT; } +void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, + unsigned long pc, unsigned long a1) +{ + spin_lock(&vcpu->arch.reset_state.lock); + vcpu->arch.reset_state.pc = pc; + vcpu->arch.reset_state.a1 = a1; + spin_unlock(&vcpu->arch.reset_state.lock); + + kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); +} + +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + struct kvm_vcpu_reset_state *reset_state = &vcpu->arch.reset_state; + + cntx->a0 = vcpu->vcpu_id; + + spin_lock(&vcpu->arch.reset_state.lock); + cntx->sepc = reset_state->pc; + cntx->a1 = reset_state->a1; + spin_unlock(&vcpu->arch.reset_state.lock); + + cntx->sstatus &= ~SR_SIE; + csr->vsatp = 0; +} + int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c index 3070bb31745d..f26207f84bab 100644 --- a/arch/riscv/kvm/vcpu_sbi_hsm.c +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -15,7 +15,6 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) { - struct kvm_cpu_context *reset_cntx; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; struct kvm_vcpu *target_vcpu; unsigned long target_vcpuid = cp->a0; @@ -32,17 +31,7 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) goto out; } - spin_lock(&target_vcpu->arch.reset_cntx_lock); - reset_cntx = &target_vcpu->arch.guest_reset_context; - /* start address */ - reset_cntx->sepc = cp->a1; - /* target vcpu id to start */ - reset_cntx->a0 = target_vcpuid; - /* private data passed from kernel */ - reset_cntx->a1 = cp->a2; - spin_unlock(&target_vcpu->arch.reset_cntx_lock); - - kvm_make_request(KVM_REQ_VCPU_RESET, target_vcpu); + kvm_riscv_vcpu_sbi_request_reset(target_vcpu, cp->a1, cp->a2); __kvm_riscv_vcpu_power_on(target_vcpu); diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c index bc0ebba89003..359be90b0fc5 100644 --- a/arch/riscv/kvm/vcpu_sbi_system.c +++ b/arch/riscv/kvm/vcpu_sbi_system.c @@ -13,7 +13,6 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_vcpu_sbi_return *retdata) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; - struct kvm_cpu_context *reset_cntx; unsigned long funcid = cp->a6; unsigned long hva, i; struct kvm_vcpu *tmp; @@ -45,14 +44,7 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, } } - spin_lock(&vcpu->arch.reset_cntx_lock); - reset_cntx = &vcpu->arch.guest_reset_context; - reset_cntx->sepc = cp->a1; - reset_cntx->a0 = vcpu->vcpu_id; - reset_cntx->a1 = cp->a2; - spin_unlock(&vcpu->arch.reset_cntx_lock); - - kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); + kvm_riscv_vcpu_sbi_request_reset(vcpu, cp->a1, cp->a2); /* userspace provides the suspend implementation */ kvm_riscv_vcpu_sbi_forward(vcpu, run); diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c index d92d1348045c..a5f88cb717f3 100644 --- a/arch/riscv/kvm/vcpu_vector.c +++ b/arch/riscv/kvm/vcpu_vector.c @@ -22,6 +22,9 @@ void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu) struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; cntx->sstatus &= ~SR_VS; + + cntx->vector.vlenb = riscv_v_vsize / 32; + if (riscv_isa_extension_available(isa, v)) { cntx->sstatus |= SR_VS_INITIAL; WARN_ON(!cntx->vector.datap); @@ -70,13 +73,11 @@ void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx) __kvm_riscv_vector_restore(cntx); } -int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, - struct kvm_cpu_context *cntx) +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu) { - cntx->vector.datap = kmalloc(riscv_v_vsize, GFP_KERNEL); - if (!cntx->vector.datap) + vcpu->arch.guest_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL); + if (!vcpu->arch.guest_context.vector.datap) return -ENOMEM; - cntx->vector.vlenb = riscv_v_vsize / 32; vcpu->arch.host_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL); if (!vcpu->arch.host_context.vector.datap) @@ -87,7 +88,7 @@ int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu, void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu) { - kfree(vcpu->arch.guest_reset_context.vector.datap); + kfree(vcpu->arch.guest_context.vector.datap); kfree(vcpu->arch.host_context.vector.datap); } #endif diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 7396b8654f45..b27ec8f96697 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -209,6 +209,19 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) return r; } +int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) +{ + switch (cap->cap) { + case KVM_CAP_RISCV_MP_STATE_RESET: + if (cap->flags) + return -EINVAL; + kvm->arch.mp_state_reset = true; + return 0; + default: + return -EINVAL; + } +} + int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -EINVAL; diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index b1c46153606a..0baec92d2f55 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +obj-y += crypto/ lib-y += delay.o lib-y += memcpy.o lib-y += memset.o diff --git a/arch/riscv/lib/crypto/Kconfig b/arch/riscv/lib/crypto/Kconfig new file mode 100644 index 000000000000..47c99ea97ce2 --- /dev/null +++ b/arch/riscv/lib/crypto/Kconfig @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config CRYPTO_CHACHA_RISCV64 + tristate + depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + default CRYPTO_LIB_CHACHA + select CRYPTO_ARCH_HAVE_LIB_CHACHA + select CRYPTO_LIB_CHACHA_GENERIC + +config CRYPTO_SHA256_RISCV64 + tristate + depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO + default CRYPTO_LIB_SHA256 + select CRYPTO_ARCH_HAVE_LIB_SHA256 + select CRYPTO_ARCH_HAVE_LIB_SHA256_SIMD + select CRYPTO_LIB_SHA256_GENERIC diff --git a/arch/riscv/lib/crypto/Makefile b/arch/riscv/lib/crypto/Makefile new file mode 100644 index 000000000000..b7cb877a2c07 --- /dev/null +++ b/arch/riscv/lib/crypto/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_CRYPTO_CHACHA_RISCV64) += chacha-riscv64.o +chacha-riscv64-y := chacha-riscv64-glue.o chacha-riscv64-zvkb.o + +obj-$(CONFIG_CRYPTO_SHA256_RISCV64) += sha256-riscv64.o +sha256-riscv64-y := sha256.o sha256-riscv64-zvknha_or_zvknhb-zvkb.o diff --git a/arch/riscv/lib/crypto/chacha-riscv64-glue.c b/arch/riscv/lib/crypto/chacha-riscv64-glue.c new file mode 100644 index 000000000000..8c3f11d79be3 --- /dev/null +++ b/arch/riscv/lib/crypto/chacha-riscv64-glue.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ChaCha stream cipher (RISC-V optimized) + * + * Copyright (C) 2023 SiFive, Inc. + * Author: Jerry Shih <jerry.shih@sifive.com> + */ + +#include <asm/simd.h> +#include <asm/vector.h> +#include <crypto/chacha.h> +#include <crypto/internal/simd.h> +#include <linux/linkage.h> +#include <linux/module.h> + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(use_zvkb); + +asmlinkage void chacha_zvkb(struct chacha_state *state, const u8 *in, u8 *out, + size_t nblocks, int nrounds); + +void hchacha_block_arch(const struct chacha_state *state, + u32 out[HCHACHA_OUT_WORDS], int nrounds) +{ + hchacha_block_generic(state, out, nrounds); +} +EXPORT_SYMBOL(hchacha_block_arch); + +void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src, + unsigned int bytes, int nrounds) +{ + u8 block_buffer[CHACHA_BLOCK_SIZE]; + unsigned int full_blocks = bytes / CHACHA_BLOCK_SIZE; + unsigned int tail_bytes = bytes % CHACHA_BLOCK_SIZE; + + if (!static_branch_likely(&use_zvkb) || !crypto_simd_usable()) + return chacha_crypt_generic(state, dst, src, bytes, nrounds); + + kernel_vector_begin(); + if (full_blocks) { + chacha_zvkb(state, src, dst, full_blocks, nrounds); + src += full_blocks * CHACHA_BLOCK_SIZE; + dst += full_blocks * CHACHA_BLOCK_SIZE; + } + if (tail_bytes) { + memcpy(block_buffer, src, tail_bytes); + chacha_zvkb(state, block_buffer, block_buffer, 1, nrounds); + memcpy(dst, block_buffer, tail_bytes); + } + kernel_vector_end(); +} +EXPORT_SYMBOL(chacha_crypt_arch); + +bool chacha_is_arch_optimized(void) +{ + return static_key_enabled(&use_zvkb); +} +EXPORT_SYMBOL(chacha_is_arch_optimized); + +static int __init riscv64_chacha_mod_init(void) +{ + if (riscv_isa_extension_available(NULL, ZVKB) && + riscv_vector_vlen() >= 128) + static_branch_enable(&use_zvkb); + return 0; +} +subsys_initcall(riscv64_chacha_mod_init); + +static void __exit riscv64_chacha_mod_exit(void) +{ +} +module_exit(riscv64_chacha_mod_exit); + +MODULE_DESCRIPTION("ChaCha stream cipher (RISC-V optimized)"); +MODULE_AUTHOR("Jerry Shih <jerry.shih@sifive.com>"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/crypto/chacha-riscv64-zvkb.S b/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S index bf057737ac69..b777d0b4e379 100644 --- a/arch/riscv/crypto/chacha-riscv64-zvkb.S +++ b/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S @@ -46,11 +46,11 @@ .text .option arch, +zvkb -#define KEYP a0 +#define STATEP a0 #define INP a1 #define OUTP a2 -#define LEN a3 -#define IVP a4 +#define NBLOCKS a3 +#define NROUNDS a4 #define CONSTS0 a5 #define CONSTS1 a6 @@ -59,7 +59,7 @@ #define TMP t1 #define VL t2 #define STRIDE t3 -#define NROUNDS t4 +#define ROUND_CTR t4 #define KEY0 s0 #define KEY1 s1 #define KEY2 s2 @@ -132,14 +132,16 @@ vror.vi \b3, \b3, 32 - 7 .endm -// void chacha20_zvkb(const u32 key[8], const u8 *in, u8 *out, size_t len, -// const u32 iv[4]); +// void chacha_zvkb(struct chacha_state *state, const u8 *in, u8 *out, +// size_t nblocks, int nrounds); // -// |len| must be nonzero and a multiple of 64 (CHACHA_BLOCK_SIZE). -// The counter is treated as 32-bit, following the RFC7539 convention. -SYM_FUNC_START(chacha20_zvkb) - srli LEN, LEN, 6 // Bytes to blocks - +// |nblocks| is the number of 64-byte blocks to process, and must be nonzero. +// +// |state| gives the ChaCha state matrix, including the 32-bit counter in +// state->x[12] following the RFC7539 convention; note that this differs from +// the original Salsa20 paper which uses a 64-bit counter in state->x[12..13]. +// The updated 32-bit counter is written back to state->x[12] before returning. +SYM_FUNC_START(chacha_zvkb) addi sp, sp, -96 sd s0, 0(sp) sd s1, 8(sp) @@ -157,26 +159,26 @@ SYM_FUNC_START(chacha20_zvkb) li STRIDE, 64 // Set up the initial state matrix in scalar registers. - li CONSTS0, 0x61707865 // "expa" little endian - li CONSTS1, 0x3320646e // "nd 3" little endian - li CONSTS2, 0x79622d32 // "2-by" little endian - li CONSTS3, 0x6b206574 // "te k" little endian - lw KEY0, 0(KEYP) - lw KEY1, 4(KEYP) - lw KEY2, 8(KEYP) - lw KEY3, 12(KEYP) - lw KEY4, 16(KEYP) - lw KEY5, 20(KEYP) - lw KEY6, 24(KEYP) - lw KEY7, 28(KEYP) - lw COUNTER, 0(IVP) - lw NONCE0, 4(IVP) - lw NONCE1, 8(IVP) - lw NONCE2, 12(IVP) + lw CONSTS0, 0(STATEP) + lw CONSTS1, 4(STATEP) + lw CONSTS2, 8(STATEP) + lw CONSTS3, 12(STATEP) + lw KEY0, 16(STATEP) + lw KEY1, 20(STATEP) + lw KEY2, 24(STATEP) + lw KEY3, 28(STATEP) + lw KEY4, 32(STATEP) + lw KEY5, 36(STATEP) + lw KEY6, 40(STATEP) + lw KEY7, 44(STATEP) + lw COUNTER, 48(STATEP) + lw NONCE0, 52(STATEP) + lw NONCE1, 56(STATEP) + lw NONCE2, 60(STATEP) .Lblock_loop: // Set vl to the number of blocks to process in this iteration. - vsetvli VL, LEN, e32, m1, ta, ma + vsetvli VL, NBLOCKS, e32, m1, ta, ma // Set up the initial state matrix for the next VL blocks in v0-v15. // v{i} holds the i'th 32-bit word of the state matrix for all blocks. @@ -203,16 +205,16 @@ SYM_FUNC_START(chacha20_zvkb) // v{16+i} holds the i'th 32-bit word for all blocks. vlsseg8e32.v v16, (INP), STRIDE - li NROUNDS, 20 + mv ROUND_CTR, NROUNDS .Lnext_doubleround: - addi NROUNDS, NROUNDS, -2 + addi ROUND_CTR, ROUND_CTR, -2 // column round chacha_round v0, v4, v8, v12, v1, v5, v9, v13, \ v2, v6, v10, v14, v3, v7, v11, v15 // diagonal round chacha_round v0, v5, v10, v15, v1, v6, v11, v12, \ v2, v7, v8, v13, v3, v4, v9, v14 - bnez NROUNDS, .Lnext_doubleround + bnez ROUND_CTR, .Lnext_doubleround // Load the second half of the input data for each block into v24-v31. // v{24+i} holds the {8+i}'th 32-bit word for all blocks. @@ -271,12 +273,13 @@ SYM_FUNC_START(chacha20_zvkb) // Update the counter, the remaining number of blocks, and the input and // output pointers according to the number of blocks processed (VL). add COUNTER, COUNTER, VL - sub LEN, LEN, VL + sub NBLOCKS, NBLOCKS, VL slli TMP, VL, 6 add OUTP, OUTP, TMP add INP, INP, TMP - bnez LEN, .Lblock_loop + bnez NBLOCKS, .Lblock_loop + sw COUNTER, 48(STATEP) ld s0, 0(sp) ld s1, 8(sp) ld s2, 16(sp) @@ -291,4 +294,4 @@ SYM_FUNC_START(chacha20_zvkb) ld s11, 88(sp) addi sp, sp, 96 ret -SYM_FUNC_END(chacha20_zvkb) +SYM_FUNC_END(chacha_zvkb) diff --git a/arch/riscv/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S b/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S index 8ebcc17de4dc..fad501ad0617 100644 --- a/arch/riscv/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S +++ b/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S @@ -43,7 +43,7 @@ // - RISC-V Vector SHA-2 Secure Hash extension ('Zvknha' or 'Zvknhb') // - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') -#include <linux/cfi_types.h> +#include <linux/linkage.h> .text .option arch, +zvknha, +zvkb @@ -106,9 +106,9 @@ sha256_4rounds \last, \k3, W3, W0, W1, W2 .endm -// void sha256_transform_zvknha_or_zvknhb_zvkb(u32 state[8], const u8 *data, -// int num_blocks); -SYM_TYPED_FUNC_START(sha256_transform_zvknha_or_zvknhb_zvkb) +// void sha256_transform_zvknha_or_zvknhb_zvkb(u32 state[SHA256_STATE_WORDS], +// const u8 *data, size_t nblocks); +SYM_FUNC_START(sha256_transform_zvknha_or_zvknhb_zvkb) // Load the round constants into K0-K15. vsetivli zero, 4, e32, m1, ta, ma diff --git a/arch/riscv/lib/crypto/sha256.c b/arch/riscv/lib/crypto/sha256.c new file mode 100644 index 000000000000..71808397dff4 --- /dev/null +++ b/arch/riscv/lib/crypto/sha256.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * SHA-256 (RISC-V accelerated) + * + * Copyright (C) 2022 VRULL GmbH + * Author: Heiko Stuebner <heiko.stuebner@vrull.eu> + * + * Copyright (C) 2023 SiFive, Inc. + * Author: Jerry Shih <jerry.shih@sifive.com> + */ + +#include <asm/vector.h> +#include <crypto/internal/sha2.h> +#include <linux/kernel.h> +#include <linux/module.h> + +asmlinkage void sha256_transform_zvknha_or_zvknhb_zvkb( + u32 state[SHA256_STATE_WORDS], const u8 *data, size_t nblocks); + +static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_extensions); + +void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS], + const u8 *data, size_t nblocks) +{ + if (static_branch_likely(&have_extensions)) { + kernel_vector_begin(); + sha256_transform_zvknha_or_zvknhb_zvkb(state, data, nblocks); + kernel_vector_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_extensions); +} +EXPORT_SYMBOL_GPL(sha256_is_arch_optimized); + +static int __init riscv64_sha256_mod_init(void) +{ + /* Both zvknha and zvknhb provide the SHA-256 instructions. */ + if ((riscv_isa_extension_available(NULL, ZVKNHA) || + riscv_isa_extension_available(NULL, ZVKNHB)) && + riscv_isa_extension_available(NULL, ZVKB) && + riscv_vector_vlen() >= 128) + static_branch_enable(&have_extensions); + return 0; +} +subsys_initcall(riscv64_sha256_mod_init); + +static void __exit riscv64_sha256_mod_exit(void) +{ +} +module_exit(riscv64_sha256_mod_exit); + +MODULE_DESCRIPTION("SHA-256 (RISC-V accelerated)"); +MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>"); +MODULE_LICENSE("GPL"); diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index 1d1c78d4cff1..e7b032dfd17f 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -608,6 +608,21 @@ static inline u32 rv_fence(u8 pred, u8 succ) return rv_i_insn(imm11_0, 0, 0, 0, 0xf); } +static inline void emit_fence_r_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x2, 0x3), ctx); +} + +static inline void emit_fence_rw_w(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x1), ctx); +} + +static inline void emit_fence_rw_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x3), ctx); +} + static inline u32 rv_nop(void) { return rv_i_insn(0, 0, 0, 0, 0x13); diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index ca60db75199d..10e01ff06312 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -473,11 +473,212 @@ static inline void emit_kcfi(u32 hash, struct rv_jit_context *ctx) emit(hash, ctx); } -static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, - struct rv_jit_context *ctx) +static int emit_load_8(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lb(rd, off, rs), ctx); + else + emit(rv_lbu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lb(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_16(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lh(rd, off, rs), ctx); + else + emit(rv_lhu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lh(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_32(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lw(rd, off, rs), ctx); + else + emit(rv_lwu(rd, off, rs), ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + if (sign_ext) + emit(rv_lw(rd, 0, RV_REG_T1), ctx); + else + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + return ctx->ninsns - insns_start; +} + +static int emit_load_64(bool sign_ext, u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + int insns_start; + + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_ld(rd, off, rs, ctx); + return ctx->ninsns - insns_start; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + emit_ld(rd, 0, RV_REG_T1, ctx); + return ctx->ninsns - insns_start; +} + +static void emit_store_8(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit(rv_sb(rd, off, rs), ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit(rv_sb(RV_REG_T1, 0, rs), ctx); +} + +static void emit_store_16(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit(rv_sh(rd, off, rs), ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit(rv_sh(RV_REG_T1, 0, rs), ctx); +} + +static void emit_store_32(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit_sw(rd, off, rs, ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit_sw(RV_REG_T1, 0, rs, ctx); +} + +static void emit_store_64(u8 rd, s32 off, u8 rs, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + emit_sd(rd, off, rs, ctx); + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + emit_sd(RV_REG_T1, 0, rs, ctx); +} + +static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) +{ + u8 code = insn->code; + s32 imm = insn->imm; + s16 off = insn->off; + + switch (imm) { + /* dst_reg = load_acquire(src_reg + off16) */ + case BPF_LOAD_ACQ: + switch (BPF_SIZE(code)) { + case BPF_B: + emit_load_8(false, rd, off, rs, ctx); + break; + case BPF_H: + emit_load_16(false, rd, off, rs, ctx); + break; + case BPF_W: + emit_load_32(false, rd, off, rs, ctx); + break; + case BPF_DW: + emit_load_64(false, rd, off, rs, ctx); + break; + } + emit_fence_r_rw(ctx); + + /* If our next insn is a redundant zext, return 1 to tell + * build_body() to skip it. + */ + if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1])) + return 1; + break; + /* store_release(dst_reg + off16, src_reg) */ + case BPF_STORE_REL: + emit_fence_rw_w(ctx); + switch (BPF_SIZE(code)) { + case BPF_B: + emit_store_8(rd, off, rs, ctx); + break; + case BPF_H: + emit_store_16(rd, off, rs, ctx); + break; + case BPF_W: + emit_store_32(rd, off, rs, ctx); + break; + case BPF_DW: + emit_store_64(rd, off, rs, ctx); + break; + } + break; + default: + pr_err_once("bpf-jit: invalid atomic load/store opcode %02x\n", imm); + return -EINVAL; + } + + return 0; +} + +static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) { - u8 r0; + u8 r0, code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; int jmp_offset; + bool is64; + + if (BPF_SIZE(code) != BPF_W && BPF_SIZE(code) != BPF_DW) { + pr_err_once("bpf-jit: 1- and 2-byte RMW atomics are not supported\n"); + return -EINVAL; + } + is64 = BPF_SIZE(code) == BPF_DW; if (off) { if (is_12b_int(off)) { @@ -554,9 +755,14 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx); jmp_offset = ninsns_rvoff(-6); emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx); - emit(rv_fence(0x3, 0x3), ctx); + emit_fence_rw_rw(ctx); break; + default: + pr_err_once("bpf-jit: invalid atomic RMW opcode %02x\n", imm); + return -EINVAL; } + + return 0; } #define BPF_FIXUP_OFFSET_MASK GENMASK(26, 0) @@ -1650,8 +1856,8 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, case BPF_LDX | BPF_PROBE_MEM32 | BPF_W: case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW: { - int insn_len, insns_start; bool sign_ext; + int insn_len; sign_ext = BPF_MODE(insn->code) == BPF_MEMSX || BPF_MODE(insn->code) == BPF_PROBE_MEMSX; @@ -1663,78 +1869,16 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, switch (BPF_SIZE(code)) { case BPF_B: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lb(rd, off, rs), ctx); - else - emit(rv_lbu(rd, off, rs), ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lb(rd, 0, RV_REG_T1), ctx); - else - emit(rv_lbu(rd, 0, RV_REG_T1), ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_8(sign_ext, rd, off, rs, ctx); break; case BPF_H: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lh(rd, off, rs), ctx); - else - emit(rv_lhu(rd, off, rs), ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lh(rd, 0, RV_REG_T1), ctx); - else - emit(rv_lhu(rd, 0, RV_REG_T1), ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_16(sign_ext, rd, off, rs, ctx); break; case BPF_W: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lw(rd, off, rs), ctx); - else - emit(rv_lwu(rd, off, rs), ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - if (sign_ext) - emit(rv_lw(rd, 0, RV_REG_T1), ctx); - else - emit(rv_lwu(rd, 0, RV_REG_T1), ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_32(sign_ext, rd, off, rs, ctx); break; case BPF_DW: - if (is_12b_int(off)) { - insns_start = ctx->ninsns; - emit_ld(rd, off, rs, ctx); - insn_len = ctx->ninsns - insns_start; - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - insns_start = ctx->ninsns; - emit_ld(rd, 0, RV_REG_T1, ctx); - insn_len = ctx->ninsns - insns_start; + insn_len = emit_load_64(sign_ext, rd, off, rs, ctx); break; } @@ -1879,49 +2023,27 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, /* STX: *(size *)(dst + off) = src */ case BPF_STX | BPF_MEM | BPF_B: - if (is_12b_int(off)) { - emit(rv_sb(rd, off, rs), ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit(rv_sb(RV_REG_T1, 0, rs), ctx); + emit_store_8(rd, off, rs, ctx); break; case BPF_STX | BPF_MEM | BPF_H: - if (is_12b_int(off)) { - emit(rv_sh(rd, off, rs), ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit(rv_sh(RV_REG_T1, 0, rs), ctx); + emit_store_16(rd, off, rs, ctx); break; case BPF_STX | BPF_MEM | BPF_W: - if (is_12b_int(off)) { - emit_sw(rd, off, rs, ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit_sw(RV_REG_T1, 0, rs, ctx); + emit_store_32(rd, off, rs, ctx); break; case BPF_STX | BPF_MEM | BPF_DW: - if (is_12b_int(off)) { - emit_sd(rd, off, rs, ctx); - break; - } - - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); - emit_sd(RV_REG_T1, 0, rs, ctx); + emit_store_64(rd, off, rs, ctx); break; + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: case BPF_STX | BPF_ATOMIC | BPF_W: case BPF_STX | BPF_ATOMIC | BPF_DW: - emit_atomic(rd, rs, off, imm, - BPF_SIZE(code) == BPF_DW, ctx); + if (bpf_atomic_is_load_store(insn)) + ret = emit_atomic_ld_st(rd, rs, insn, ctx); + else + ret = emit_atomic_rmw(rd, rs, insn, ctx); + if (ret) + return ret; break; case BPF_STX | BPF_PROBE_MEM32 | BPF_B: diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index f8cd2f70a7fb..f6ca5cfa6b2f 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -26,9 +26,8 @@ static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) int ret; ret = bpf_jit_emit_insn(insn, ctx, extra_pass); - /* BPF_LD | BPF_IMM | BPF_DW: skip the next instruction. */ if (ret > 0) - i++; + i++; /* skip the next instruction */ if (offset) offset[i] = ctx->ninsns; if (ret < 0) |