diff options
Diffstat (limited to 'arch/riscv')
50 files changed, 148 insertions, 1769 deletions
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 36061f4732b7..5352932badd8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -24,9 +24,6 @@ config RISCV select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_BINFMT_FLAT - select ARCH_HAS_CRC32 if RISCV_ISA_ZBC - select ARCH_HAS_CRC64 if 64BIT && RISCV_ISA_ZBC - select ARCH_HAS_CRC_T10DIF if RISCV_ISA_ZBC select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEBUG_VM_PGTABLE @@ -63,7 +60,8 @@ config RISCV select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW - select ARCH_SUPPORTS_CFI_CLANG + # clang >= 17: https://github.com/llvm/llvm-project/commit/62fa708ceb027713b386c7e0efda994f8bdc27e2 + select ARCH_SUPPORTS_CFI_CLANG if CLANG_VERSION >= 170000 select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE select ARCH_SUPPORTS_HUGETLBFS if MMU @@ -97,6 +95,7 @@ config RISCV select CLONE_BACKWARDS select COMMON_CLK select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND + select DYNAMIC_FTRACE if FUNCTION_TRACER select EDAC_SUPPORT select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE @@ -135,13 +134,13 @@ config RISCV select HAVE_ARCH_KASAN if MMU && 64BIT select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT select HAVE_ARCH_KFENCE if MMU && 64BIT + select HAVE_ARCH_KSTACK_ERASE select HAVE_ARCH_KGDB if !XIP_KERNEL select HAVE_ARCH_KGDB_QXFER_PKT select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET select HAVE_ARCH_SECCOMP_FILTER - select HAVE_ARCH_STACKLEAK select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU @@ -161,7 +160,7 @@ config RISCV select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_FUNCTION_GRAPH_FREGS - select HAVE_FUNCTION_TRACER if !XIP_KERNEL + select HAVE_FUNCTION_TRACER if !XIP_KERNEL && HAVE_DYNAMIC_FTRACE select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 900a50526d77..06731b8c7bc3 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -49,32 +49,28 @@ compatible = "pwm-leds"; led-d1 { - pwms = <&pwm0 0 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 0 7812500 0>; color = <LED_COLOR_ID_GREEN>; max-brightness = <255>; label = "d1"; }; led-d2 { - pwms = <&pwm0 1 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 1 7812500 0>; color = <LED_COLOR_ID_GREEN>; max-brightness = <255>; label = "d2"; }; led-d3 { - pwms = <&pwm0 2 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 2 7812500 0>; color = <LED_COLOR_ID_GREEN>; max-brightness = <255>; label = "d3"; }; led-d4 { - pwms = <&pwm0 3 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 3 7812500 0>; color = <LED_COLOR_ID_GREEN>; max-brightness = <255>; label = "d4"; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index 72b87b08ab44..03ce2cee4e97 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -51,8 +51,7 @@ compatible = "pwm-leds"; led-d12 { - pwms = <&pwm0 0 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 0 7812500 0>; color = <LED_COLOR_ID_GREEN>; max-brightness = <255>; label = "d12"; @@ -68,20 +67,17 @@ label = "d2"; led-red { - pwms = <&pwm0 2 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 2 7812500 0>; color = <LED_COLOR_ID_RED>; }; led-green { - pwms = <&pwm0 1 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 1 7812500 0>; color = <LED_COLOR_ID_GREEN>; }; led-blue { - pwms = <&pwm0 3 7812500 PWM_POLARITY_INVERTED>; - active-low; + pwms = <&pwm0 3 7812500 0>; color = <LED_COLOR_ID_BLUE>; }; }; diff --git a/arch/riscv/crypto/Kconfig b/arch/riscv/crypto/Kconfig index cd9b776602f8..a75d6325607b 100644 --- a/arch/riscv/crypto/Kconfig +++ b/arch/riscv/crypto/Kconfig @@ -28,17 +28,6 @@ config CRYPTO_GHASH_RISCV64 Architecture: riscv64 using: - Zvkg 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 - select CRYPTO_SHA512 - help - SHA-384 and SHA-512 secure hash algorithm (FIPS 180) - - Architecture: riscv64 using: - - Zvknhb vector crypto extension - - Zvkb vector crypto extension - config CRYPTO_SM3_RISCV64 tristate "Hash functions: SM3 (ShangMi 3)" depends on 64BIT && RISCV_ISA_V && TOOLCHAIN_HAS_VECTOR_CRYPTO diff --git a/arch/riscv/crypto/Makefile b/arch/riscv/crypto/Makefile index e10e8257734e..183495a95cc0 100644 --- a/arch/riscv/crypto/Makefile +++ b/arch/riscv/crypto/Makefile @@ -7,9 +7,6 @@ aes-riscv64-y := aes-riscv64-glue.o aes-riscv64-zvkned.o \ obj-$(CONFIG_CRYPTO_GHASH_RISCV64) += ghash-riscv64.o ghash-riscv64-y := ghash-riscv64-glue.o ghash-riscv64-zvkg.o -obj-$(CONFIG_CRYPTO_SHA512_RISCV64) += sha512-riscv64.o -sha512-riscv64-y := sha512-riscv64-glue.o sha512-riscv64-zvknhb-zvkb.o - obj-$(CONFIG_CRYPTO_SM3_RISCV64) += sm3-riscv64.o sm3-riscv64-y := sm3-riscv64-glue.o sm3-riscv64-zvksh-zvkb.o diff --git a/arch/riscv/crypto/sha512-riscv64-glue.c b/arch/riscv/crypto/sha512-riscv64-glue.c deleted file mode 100644 index 4634fca78ae2..000000000000 --- a/arch/riscv/crypto/sha512-riscv64-glue.c +++ /dev/null @@ -1,124 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * SHA-512 and SHA-384 using the RISC-V vector crypto extensions - * - * Copyright (C) 2023 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/sha512_base.h> -#include <linux/kernel.h> -#include <linux/module.h> - -/* - * Note: the asm function only uses the 'state' field of struct sha512_state. - * It is assumed to be the first field. - */ -asmlinkage void sha512_transform_zvknhb_zvkb( - struct sha512_state *state, const u8 *data, int num_blocks); - -static void sha512_block(struct sha512_state *state, const u8 *data, - int num_blocks) -{ - /* - * Ensure struct sha512_state begins directly with the SHA-512 - * 512-bit internal state, as this is what the asm function expects. - */ - BUILD_BUG_ON(offsetof(struct sha512_state, state) != 0); - - if (crypto_simd_usable()) { - kernel_vector_begin(); - sha512_transform_zvknhb_zvkb(state, data, num_blocks); - kernel_vector_end(); - } else { - sha512_generic_block_fn(state, data, num_blocks); - } -} - -static int riscv64_sha512_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - return sha512_base_do_update_blocks(desc, data, len, sha512_block); -} - -static int riscv64_sha512_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *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, - unsigned int len, u8 *out) -{ - return sha512_base_init(desc) ?: - riscv64_sha512_finup(desc, data, len, out); -} - -static struct shash_alg riscv64_sha512_algs[] = { - { - .init = sha512_base_init, - .update = riscv64_sha512_update, - .finup = riscv64_sha512_finup, - .digest = riscv64_sha512_digest, - .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, - }, - }, { - .init = sha384_base_init, - .update = riscv64_sha512_update, - .finup = riscv64_sha512_finup, - .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, - }, - }, -}; - -static int __init riscv64_sha512_mod_init(void) -{ - if (riscv_isa_extension_available(NULL, ZVKNHB) && - riscv_isa_extension_available(NULL, ZVKB) && - riscv_vector_vlen() >= 128) - return crypto_register_shashes(riscv64_sha512_algs, - ARRAY_SIZE(riscv64_sha512_algs)); - - return -ENODEV; -} - -static void __exit riscv64_sha512_mod_exit(void) -{ - crypto_unregister_shashes(riscv64_sha512_algs, - ARRAY_SIZE(riscv64_sha512_algs)); -} - -module_init(riscv64_sha512_mod_init); -module_exit(riscv64_sha512_mod_exit); - -MODULE_DESCRIPTION("SHA-512 (RISC-V accelerated)"); -MODULE_AUTHOR("Heiko Stuebner <heiko.stuebner@vrull.eu>"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS_CRYPTO("sha512"); -MODULE_ALIAS_CRYPTO("sha384"); diff --git a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S b/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S deleted file mode 100644 index 89f4a10d12dd..000000000000 --- a/arch/riscv/crypto/sha512-riscv64-zvknhb-zvkb.S +++ /dev/null @@ -1,203 +0,0 @@ -/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ -// -// This file is dual-licensed, meaning that you can use it under your -// choice of either of the following two licenses: -// -// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. -// -// Licensed under the Apache License 2.0 (the "License"). You can obtain -// a copy in the file LICENSE in the source distribution or at -// https://www.openssl.org/source/license.html -// -// or -// -// Copyright (c) 2023, Christoph Müllner <christoph.muellner@vrull.eu> -// Copyright (c) 2023, Phoebe Chen <phoebe.chen@sifive.com> -// Copyright 2024 Google LLC -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions -// are met: -// 1. Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// 2. Redistributions in binary form must reproduce the above copyright -// notice, this list of conditions and the following disclaimer in the -// documentation and/or other materials provided with the distribution. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -// The generated code of this file depends on the following RISC-V extensions: -// - RV64I -// - RISC-V Vector ('V') with VLEN >= 128 -// - RISC-V Vector SHA-2 Secure Hash extension ('Zvknhb') -// - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') - -#include <linux/linkage.h> - -.text -.option arch, +zvknhb, +zvkb - -#define STATEP a0 -#define DATA a1 -#define NUM_BLOCKS a2 - -#define STATEP_C a3 -#define K a4 - -#define MASK v0 -#define INDICES v1 -#define W0 v10 // LMUL=2 -#define W1 v12 // LMUL=2 -#define W2 v14 // LMUL=2 -#define W3 v16 // LMUL=2 -#define VTMP v20 // LMUL=2 -#define FEBA v22 // LMUL=2 -#define HGDC v24 // LMUL=2 -#define PREV_FEBA v26 // LMUL=2 -#define PREV_HGDC v28 // LMUL=2 - -// Do 4 rounds of SHA-512. w0 contains the current 4 message schedule words. -// -// If not all the message schedule words have been computed yet, then this also -// computes 4 more message schedule words. w1-w3 contain the next 3 groups of 4 -// message schedule words; this macro computes the group after w3 and writes it -// to w0. This means that the next (w0, w1, w2, w3) is the current (w1, w2, w3, -// w0), so the caller must cycle through the registers accordingly. -.macro sha512_4rounds last, w0, w1, w2, w3 - vle64.v VTMP, (K) - addi K, K, 32 - vadd.vv VTMP, VTMP, \w0 - vsha2cl.vv HGDC, FEBA, VTMP - vsha2ch.vv FEBA, HGDC, VTMP -.if !\last - vmerge.vvm VTMP, \w2, \w1, MASK - vsha2ms.vv \w0, VTMP, \w3 -.endif -.endm - -.macro sha512_16rounds last - sha512_4rounds \last, W0, W1, W2, W3 - sha512_4rounds \last, W1, W2, W3, W0 - sha512_4rounds \last, W2, W3, W0, W1 - sha512_4rounds \last, W3, W0, W1, W2 -.endm - -// void sha512_transform_zvknhb_zvkb(u64 state[8], const u8 *data, -// int num_blocks); -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. - vsetivli zero, 1, e8, m1, ta, ma - vmv.v.i MASK, 0x01 - - // Load the state. The state is stored as {a,b,c,d,e,f,g,h}, but we - // need {f,e,b,a},{h,g,d,c}. The dst vtype is e64m2 and the index vtype - // is e8mf4. We use index-load with the i8 indices {40, 32, 8, 0}, - // loaded using the 32-bit little endian value 0x00082028. - li t0, 0x00082028 - vsetivli zero, 1, e32, m1, ta, ma - vmv.v.x INDICES, t0 - addi STATEP_C, STATEP, 16 - vsetivli zero, 4, e64, m2, ta, ma - vluxei8.v FEBA, (STATEP), INDICES - vluxei8.v HGDC, (STATEP_C), INDICES - -.Lnext_block: - la K, K512 - addi NUM_BLOCKS, NUM_BLOCKS, -1 - - // Save the previous state, as it's needed later. - vmv.v.v PREV_FEBA, FEBA - vmv.v.v PREV_HGDC, HGDC - - // Load the next 1024-bit message block and endian-swap each 64-bit word - vle64.v W0, (DATA) - vrev8.v W0, W0 - addi DATA, DATA, 32 - vle64.v W1, (DATA) - vrev8.v W1, W1 - addi DATA, DATA, 32 - vle64.v W2, (DATA) - vrev8.v W2, W2 - addi DATA, DATA, 32 - vle64.v W3, (DATA) - vrev8.v W3, W3 - addi DATA, DATA, 32 - - // Do the 80 rounds of SHA-512. - sha512_16rounds 0 - sha512_16rounds 0 - sha512_16rounds 0 - sha512_16rounds 0 - sha512_16rounds 1 - - // Add the previous state. - vadd.vv FEBA, FEBA, PREV_FEBA - vadd.vv HGDC, HGDC, PREV_HGDC - - // Repeat if more blocks remain. - bnez NUM_BLOCKS, .Lnext_block - - // Store the new state and return. - vsuxei8.v FEBA, (STATEP), INDICES - vsuxei8.v HGDC, (STATEP_C), INDICES - ret -SYM_FUNC_END(sha512_transform_zvknhb_zvkb) - -.section ".rodata" -.p2align 3 -.type K512, @object -K512: - .dword 0x428a2f98d728ae22, 0x7137449123ef65cd - .dword 0xb5c0fbcfec4d3b2f, 0xe9b5dba58189dbbc - .dword 0x3956c25bf348b538, 0x59f111f1b605d019 - .dword 0x923f82a4af194f9b, 0xab1c5ed5da6d8118 - .dword 0xd807aa98a3030242, 0x12835b0145706fbe - .dword 0x243185be4ee4b28c, 0x550c7dc3d5ffb4e2 - .dword 0x72be5d74f27b896f, 0x80deb1fe3b1696b1 - .dword 0x9bdc06a725c71235, 0xc19bf174cf692694 - .dword 0xe49b69c19ef14ad2, 0xefbe4786384f25e3 - .dword 0x0fc19dc68b8cd5b5, 0x240ca1cc77ac9c65 - .dword 0x2de92c6f592b0275, 0x4a7484aa6ea6e483 - .dword 0x5cb0a9dcbd41fbd4, 0x76f988da831153b5 - .dword 0x983e5152ee66dfab, 0xa831c66d2db43210 - .dword 0xb00327c898fb213f, 0xbf597fc7beef0ee4 - .dword 0xc6e00bf33da88fc2, 0xd5a79147930aa725 - .dword 0x06ca6351e003826f, 0x142929670a0e6e70 - .dword 0x27b70a8546d22ffc, 0x2e1b21385c26c926 - .dword 0x4d2c6dfc5ac42aed, 0x53380d139d95b3df - .dword 0x650a73548baf63de, 0x766a0abb3c77b2a8 - .dword 0x81c2c92e47edaee6, 0x92722c851482353b - .dword 0xa2bfe8a14cf10364, 0xa81a664bbc423001 - .dword 0xc24b8b70d0f89791, 0xc76c51a30654be30 - .dword 0xd192e819d6ef5218, 0xd69906245565a910 - .dword 0xf40e35855771202a, 0x106aa07032bbd1b8 - .dword 0x19a4c116b8d2d0c8, 0x1e376c085141ab53 - .dword 0x2748774cdf8eeb99, 0x34b0bcb5e19b48a8 - .dword 0x391c0cb3c5c95a63, 0x4ed8aa4ae3418acb - .dword 0x5b9cca4f7763e373, 0x682e6ff3d6b2b8a3 - .dword 0x748f82ee5defb2fc, 0x78a5636f43172f60 - .dword 0x84c87814a1f0ab72, 0x8cc702081a6439ec - .dword 0x90befffa23631e28, 0xa4506cebde82bde9 - .dword 0xbef9a3f7b2c67915, 0xc67178f2e372532b - .dword 0xca273eceea26619c, 0xd186b8c721c0c207 - .dword 0xeada7dd6cde0eb1e, 0xf57d4f7fee6ed178 - .dword 0x06f067aa72176fba, 0x0a637dc5a2c898a6 - .dword 0x113f9804bef90dae, 0x1b710b35131c471b - .dword 0x28db77f523047d84, 0x32caab7b40c72493 - .dword 0x3c9ebe0a15c9bebc, 0x431d67c49c100d4c - .dword 0x4cc5d4becb3e42b6, 0x597f299cfc657e2a - .dword 0x5fcb6fab3ad6faec, 0x6c44198c4a475817 -.size K512, . - K512 diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h index 3b643b9efc07..5acce285e56e 100644 --- a/arch/riscv/include/asm/kvm_aia.h +++ b/arch/riscv/include/asm/kvm_aia.h @@ -87,6 +87,9 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available); extern struct kvm_device_ops kvm_riscv_aia_device_ops; +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu); @@ -161,7 +164,6 @@ void kvm_riscv_aia_destroy_vm(struct kvm *kvm); int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner, void __iomem **hgei_va, phys_addr_t *hgei_pa); void kvm_riscv_aia_free_hgei(int cpu, int hgei); -void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable); void kvm_riscv_aia_enable(void); void kvm_riscv_aia_disable(void); diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 85cfebc32e4c..bcbf8b1ec115 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -306,6 +306,9 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; } +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} + #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 438ce7df24c3..5bd5aae60d53 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -1075,7 +1075,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) */ #ifdef CONFIG_64BIT #define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) -#define TASK_SIZE_MAX LONG_MAX #ifdef CONFIG_COMPAT #define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h index 451fd76b8811..d766e2b9e6df 100644 --- a/arch/riscv/include/asm/runtime-const.h +++ b/arch/riscv/include/asm/runtime-const.h @@ -206,7 +206,7 @@ static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, u addi_insn_mask &= 0x07fff; } - if (lower_immediate & 0x00000fff) { + if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) { /* replace upper 12 bits of addi with lower 12 bits of val */ addi_insn &= addi_insn_mask; addi_insn |= (lower_immediate & 0x00000fff) << 20; diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index d472da4450e6..b88a6218b7f2 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -127,6 +127,7 @@ do { \ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT #define __get_user_8(x, ptr, label) \ +do { \ u32 __user *__ptr = (u32 __user *)(ptr); \ u32 __lo, __hi; \ asm_goto_output( \ @@ -141,7 +142,7 @@ do { \ : : label); \ (x) = (__typeof__(x))((__typeof__((x) - (x)))( \ (((u64)__hi << 32) | __lo))); \ - +} while (0) #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ #define __get_user_8(x, ptr, label) \ do { \ @@ -310,8 +311,8 @@ do { \ do { \ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ - __inttype(x) val = (__inttype(x))x; \ - if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \ + __inttype(x) ___val = (__inttype(x))x; \ + if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \ goto label; \ break; \ } \ diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h index 8dc92441702a..c6d66895c1f5 100644 --- a/arch/riscv/include/asm/vdso/getrandom.h +++ b/arch/riscv/include/asm/vdso/getrandom.h @@ -18,7 +18,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns register unsigned int flags asm("a2") = _flags; asm volatile ("ecall\n" - : "+r" (ret) + : "=r" (ret) : "r" (nr), "r" (buffer), "r" (len), "r" (flags) : "memory"); diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index 45c9b426fcc5..b61786d43c20 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -205,11 +205,11 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, THEAD_VSETVLI_T4X0E8M8D1 THEAD_VSB_V_V0T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V8T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V16T0 "add t0, t0, t4\n\t" - THEAD_VSB_V_V0T0 + THEAD_VSB_V_V24T0 : : "r" (datap) : "memory", "t0", "t4"); } else { asm volatile ( @@ -241,11 +241,11 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_ THEAD_VSETVLI_T4X0E8M8D1 THEAD_VLB_V_V0T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V8T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V16T0 "add t0, t0, t4\n\t" - THEAD_VLB_V_V0T0 + THEAD_VLB_V_V24T0 : : "r" (datap) : "memory", "t0", "t4"); } else { asm volatile ( diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c index e6fbaaf54956..87d655944803 100644 --- a/arch/riscv/kernel/cpu_ops_sbi.c +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -18,10 +18,10 @@ const struct cpu_operations cpu_ops_sbi; /* * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can - * be invoked from multiple threads in parallel. Define a per cpu data + * be invoked from multiple threads in parallel. Define an array of boot data * to handle that. */ -static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data); +static struct sbi_hart_boot_data boot_data[NR_CPUS]; static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr, unsigned long priv) @@ -67,7 +67,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle) unsigned long boot_addr = __pa_symbol(secondary_start_sbi); unsigned long hartid = cpuid_to_hartid_map(cpuid); unsigned long hsm_data; - struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid); + struct sbi_hart_boot_data *bdata = &boot_data[cpuid]; /* Make sure tidle is updated */ smp_mb(); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 75656afa2d6b..3a0ec6fd5956 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -220,7 +220,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) #endif bnez s0, 1f -#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#ifdef CONFIG_KSTACK_ERASE call stackleak_erase_on_task_stack #endif diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 4c6c24380cfd..8d18d6727f0f 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -14,6 +14,18 @@ #include <asm/text-patching.h> #ifdef CONFIG_DYNAMIC_FTRACE +void ftrace_arch_code_modify_prepare(void) + __acquires(&text_mutex) +{ + mutex_lock(&text_mutex); +} + +void ftrace_arch_code_modify_post_process(void) + __releases(&text_mutex) +{ + mutex_unlock(&text_mutex); +} + unsigned long ftrace_call_adjust(unsigned long addr) { if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) @@ -29,10 +41,8 @@ unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) void arch_ftrace_update_code(int command) { - mutex_lock(&text_mutex); command |= FTRACE_MAY_SLEEP; ftrace_modify_all_code(command); - mutex_unlock(&text_mutex); flush_icache_all(); } @@ -149,6 +159,8 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) unsigned int nops[2], offset; int ret; + guard(mutex)(&text_mutex); + ret = ftrace_rec_set_nop_ops(rec); if (ret) return ret; @@ -157,9 +169,7 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) nops[0] = to_auipc_t0(offset); nops[1] = RISCV_INSN_NOP4; - mutex_lock(&text_mutex); ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE); - mutex_unlock(&text_mutex); return ret; } diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile index 81d69d45c06c..7dd15be69c90 100644 --- a/arch/riscv/kernel/pi/Makefile +++ b/arch/riscv/kernel/pi/Makefile @@ -2,7 +2,7 @@ # This file was copied from arm64/kernel/pi/Makefile. KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ - -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_STACKLEAK_PLUGIN) \ + -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_KSTACK_ERASE) \ $(call cc-option,-mbranch-protection=none) \ -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \ -include $(srctree)/include/linux/hidden.h \ diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index ea67e9fb7a58..8e86305831ea 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -186,7 +186,7 @@ static int tagged_addr_ctrl_set(struct task_struct *target, static const struct user_regset riscv_user_regset[] = { [REGSET_X] = { - .core_note_type = NT_PRSTATUS, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(elf_greg_t), .align = sizeof(elf_greg_t), @@ -195,7 +195,7 @@ static const struct user_regset riscv_user_regset[] = { }, #ifdef CONFIG_FPU [REGSET_F] = { - .core_note_type = NT_PRFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG, .size = sizeof(elf_fpreg_t), .align = sizeof(elf_fpreg_t), @@ -205,7 +205,7 @@ static const struct user_regset riscv_user_regset[] = { #endif #ifdef CONFIG_RISCV_ISA_V [REGSET_V] = { - .core_note_type = NT_RISCV_VECTOR, + USER_REGSET_NOTE_TYPE(RISCV_VECTOR), .align = 16, .n = ((32 * RISCV_MAX_VLENB) + sizeof(struct __riscv_v_regset_state)) / sizeof(__u32), @@ -216,7 +216,7 @@ static const struct user_regset riscv_user_regset[] = { #endif #ifdef CONFIG_RISCV_ISA_SUPM [REGSET_TAGGED_ADDR_CTRL] = { - .core_note_type = NT_RISCV_TAGGED_ADDR_CTRL, + USER_REGSET_NOTE_TYPE(RISCV_TAGGED_ADDR_CTRL), .n = 1, .size = sizeof(long), .align = sizeof(long), @@ -380,7 +380,7 @@ static int compat_riscv_gpr_set(struct task_struct *target, static const struct user_regset compat_riscv_user_regset[] = { [REGSET_X] = { - .core_note_type = NT_PRSTATUS, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), @@ -389,7 +389,7 @@ static const struct user_regset compat_riscv_user_regset[] = { }, #ifdef CONFIG_FPU [REGSET_F] = { - .core_note_type = NT_PRFPREG, + USER_REGSET_NOTE_TYPE(PRFPREG), .n = ELF_NFPREG, .size = sizeof(elf_fpreg_t), .align = sizeof(elf_fpreg_t), diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f7c9a1caa83e..14888e5ea19a 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -50,6 +50,7 @@ atomic_t hart_lottery __section(".sdata") #endif ; unsigned long boot_cpu_hartid; +EXPORT_SYMBOL_GPL(boot_cpu_hartid); /* * Place kernel memory regions on the resource tree so that diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 9c83848797a7..80230de167de 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -6,6 +6,7 @@ #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/irqflags.h> #include <linux/randomize_kstack.h> #include <linux/sched.h> #include <linux/sched/debug.h> @@ -151,7 +152,9 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ { \ if (user_mode(regs)) { \ irqentry_enter_from_user_mode(regs); \ + local_irq_enable(); \ do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + local_irq_disable(); \ irqentry_exit_to_user_mode(regs); \ } else { \ irqentry_state_t state = irqentry_nmi_enter(regs); \ @@ -173,17 +176,14 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); - local_irq_enable(); handled = riscv_v_first_use_handler(regs); - - local_irq_disable(); - if (!handled) do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, "Oops - illegal instruction"); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); @@ -308,9 +308,11 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) { if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); + local_irq_enable(); handle_break(regs); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index dd8e4af6583f..f760e4fcc052 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -454,14 +454,14 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs) val.data_u64 = 0; if (user_mode(regs)) { - if (copy_from_user_nofault(&val, (u8 __user *)addr, len)) + if (copy_from_user(&val, (u8 __user *)addr, len)) return -1; } else { memcpy(&val, (u8 *)addr, len); } if (!fp) - SET_RD(insn, regs, val.data_ulong << shift >> shift); + SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift); else if (len == 8) set_f64_rd(insn, regs, val.data_u64); else @@ -555,7 +555,7 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs) return -EOPNOTSUPP; if (user_mode(regs)) { - if (copy_to_user_nofault((u8 __user *)addr, &val, len)) + if (copy_to_user((u8 __user *)addr, &val, len)) return -1; } else { memcpy((u8 *)addr, &val, len); diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index 7c15b0f4ee3b..c29ef12a63bb 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -30,7 +30,7 @@ SECTIONS *(.data .data.* .gnu.linkonce.d.*) *(.dynbss) *(.bss .bss.* .gnu.linkonce.b.*) - } + } :text .note : { *(.note.*) } :text :note diff --git a/arch/riscv/kernel/vendor_extensions/sifive.c b/arch/riscv/kernel/vendor_extensions/sifive.c index 1411337dc1e6..8fcf67e8c07f 100644 --- a/arch/riscv/kernel/vendor_extensions/sifive.c +++ b/arch/riscv/kernel/vendor_extensions/sifive.c @@ -8,7 +8,7 @@ #include <linux/types.h> /* All SiFive vendor extensions supported in Linux */ -const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { __RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF), __RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ), __RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD), diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index 19afd1f23537..dad318185660 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -30,28 +30,6 @@ unsigned int kvm_riscv_aia_nr_hgei; unsigned int kvm_riscv_aia_max_ids; DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available); -static int aia_find_hgei(struct kvm_vcpu *owner) -{ - int i, hgei; - unsigned long flags; - struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei); - - raw_spin_lock_irqsave(&hgctrl->lock, flags); - - hgei = -1; - for (i = 1; i <= kvm_riscv_aia_nr_hgei; i++) { - if (hgctrl->owners[i] == owner) { - hgei = i; - break; - } - } - - raw_spin_unlock_irqrestore(&hgctrl->lock, flags); - - put_cpu_ptr(&aia_hgei); - return hgei; -} - static inline unsigned long aia_hvictl_value(bool ext_irq_pending) { unsigned long hvictl; @@ -95,7 +73,6 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { - int hgei; unsigned long seip; if (!kvm_riscv_aia_available()) @@ -114,11 +91,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip) return false; - hgei = aia_find_hgei(vcpu); - if (hgei > 0) - return !!(ncsr_read(CSR_HGEIP) & BIT(hgei)); - - return false; + return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu); } void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) @@ -164,6 +137,9 @@ void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) csr_write(CSR_HVIPRIO2H, csr->hviprio2h); #endif } + + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu); } void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) @@ -174,6 +150,9 @@ void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) if (!kvm_riscv_aia_available()) return; + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_put(vcpu); + if (kvm_riscv_nacl_available()) { nsh = nacl_shmem(); csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT); @@ -472,22 +451,6 @@ void kvm_riscv_aia_free_hgei(int cpu, int hgei) raw_spin_unlock_irqrestore(&hgctrl->lock, flags); } -void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable) -{ - int hgei; - - if (!kvm_riscv_aia_available()) - return; - - hgei = aia_find_hgei(owner); - if (hgei > 0) { - if (enable) - csr_set(CSR_HGEIE, BIT(hgei)); - else - csr_clear(CSR_HGEIE, BIT(hgei)); - } -} - static irqreturn_t hgei_interrupt(int irq, void *dev_id) { int i; diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 29ef9c2133a9..2ff865943ebb 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -676,6 +676,48 @@ static void imsic_swfile_update(struct kvm_vcpu *vcpu, imsic_swfile_extirq_update(vcpu); } +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + bool ret = false; + + /* + * The IMSIC SW-file directly injects interrupt via hvip so + * only check for interrupt when IMSIC VS-file is being used. + */ + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) + ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + read_unlock_irqrestore(&imsic->vsfile_lock, flags); + + return ret; +} + +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu) +{ + /* + * No need to explicitly clear HGEIE CSR bits because the + * hgei interrupt handler (aka hgei_interrupt()) will always + * clear it for us. + */ +} + +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + + if (!kvm_vcpu_is_blocking(vcpu)) + return; + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) + csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei)); + read_unlock_irqrestore(&imsic->vsfile_lock, flags); +} + void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu) { unsigned long flags; @@ -781,6 +823,9 @@ int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu) * producers to the new IMSIC VS-file. */ + /* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */ + csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei)); + /* Zero-out new IMSIC VS-file */ imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index e0a01af426ff..0462863206ca 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -207,16 +207,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) return kvm_riscv_vcpu_timer_pending(vcpu); } -void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) -{ - kvm_riscv_aia_wakeon_hgei(vcpu, true); -} - -void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) -{ - kvm_riscv_aia_wakeon_hgei(vcpu, false); -} - int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) && diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c index 5fbf3f94f1e8..b17fad091bab 100644 --- a/arch/riscv/kvm/vcpu_sbi_replace.c +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -103,7 +103,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: - if (cp->a2 == 0 && cp->a3 == 0) + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask); else kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, @@ -111,7 +111,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: - if (cp->a2 == 0 && cp->a3 == 0) + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, hbase, hmask, cp->a4); else @@ -127,9 +127,9 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID: /* * Until nested virtualization is implemented, the - * SBI HFENCE calls should be treated as NOPs + * SBI HFENCE calls should return not supported + * hence fallthrough. */ - break; default: retdata->err_val = SBI_ERR_NOT_SUPPORTED; } diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c index ff672fa71fcc..85a7262115e1 100644 --- a/arch/riscv/kvm/vcpu_timer.c +++ b/arch/riscv/kvm/vcpu_timer.c @@ -345,8 +345,24 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu) /* * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync() * upon every VM exit so no need to save here. + * + * If VS-timer expires when no VCPU running on a host CPU then + * WFI executed by such host CPU will be effective NOP resulting + * in no power savings. This is because as-per RISC-V Privileged + * specificaiton: "WFI is also required to resume execution for + * locally enabled interrupts pending at any privilege level, + * regardless of the global interrupt enable at each privilege + * level." + * + * To address the above issue, vstimecmp CSR must be set to -1UL + * over here when VCPU is scheduled-out or exits to user space. */ + csr_write(CSR_VSTIMECMP, -1UL); +#if defined(CONFIG_32BIT) + csr_write(CSR_VSTIMECMPH, -1UL); +#endif + /* timer should be enabled for the remaining operations */ if (unlikely(!t->init_done)) return; diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 0baec92d2f55..bbc031124974 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += crypto/ lib-y += delay.o lib-y += memcpy.o lib-y += memset.o @@ -16,12 +15,6 @@ endif lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o -obj-$(CONFIG_CRC32_ARCH) += crc32-riscv.o -crc32-riscv-y := crc32.o crc32_msb.o crc32_lsb.o -obj-$(CONFIG_CRC64_ARCH) += crc64-riscv.o -crc64-riscv-y := crc64.o crc64_msb.o crc64_lsb.o -obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-riscv.o -crc-t10dif-riscv-y := crc-t10dif.o crc16_msb.o obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o lib-$(CONFIG_RISCV_ISA_V) += xor.o lib-$(CONFIG_RISCV_ISA_V) += riscv_v_helpers.o diff --git a/arch/riscv/lib/crc-clmul-consts.h b/arch/riscv/lib/crc-clmul-consts.h deleted file mode 100644 index 8d73449235ef..000000000000 --- a/arch/riscv/lib/crc-clmul-consts.h +++ /dev/null @@ -1,122 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * CRC constants generated by: - * - * ./scripts/gen-crc-consts.py riscv_clmul crc16_msb_0x8bb7,crc32_msb_0x04c11db7,crc32_lsb_0xedb88320,crc32_lsb_0x82f63b78,crc64_msb_0x42f0e1eba9ea3693,crc64_lsb_0x9a6c9329ac4bc9b5 - * - * Do not edit manually. - */ - -struct crc_clmul_consts { - unsigned long fold_across_2_longs_const_hi; - unsigned long fold_across_2_longs_const_lo; - unsigned long barrett_reduction_const_1; - unsigned long barrett_reduction_const_2; -}; - -/* - * Constants generated for most-significant-bit-first CRC-16 using - * G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0 - */ -static const struct crc_clmul_consts crc16_msb_0x8bb7_consts __maybe_unused = { -#ifdef CONFIG_64BIT - .fold_across_2_longs_const_hi = 0x0000000000001faa, /* x^192 mod G */ - .fold_across_2_longs_const_lo = 0x000000000000a010, /* x^128 mod G */ - .barrett_reduction_const_1 = 0xfb2d2bfc0e99d245, /* floor(x^79 / G) */ - .barrett_reduction_const_2 = 0x0000000000008bb7, /* G - x^16 */ -#else - .fold_across_2_longs_const_hi = 0x00005890, /* x^96 mod G */ - .fold_across_2_longs_const_lo = 0x0000f249, /* x^64 mod G */ - .barrett_reduction_const_1 = 0xfb2d2bfc, /* floor(x^47 / G) */ - .barrett_reduction_const_2 = 0x00008bb7, /* G - x^16 */ -#endif -}; - -/* - * Constants generated for most-significant-bit-first CRC-32 using - * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 + - * x^5 + x^4 + x^2 + x^1 + x^0 - */ -static const struct crc_clmul_consts crc32_msb_0x04c11db7_consts __maybe_unused = { -#ifdef CONFIG_64BIT - .fold_across_2_longs_const_hi = 0x00000000c5b9cd4c, /* x^192 mod G */ - .fold_across_2_longs_const_lo = 0x00000000e8a45605, /* x^128 mod G */ - .barrett_reduction_const_1 = 0x826880efa40da72d, /* floor(x^95 / G) */ - .barrett_reduction_const_2 = 0x0000000004c11db7, /* G - x^32 */ -#else - .fold_across_2_longs_const_hi = 0xf200aa66, /* x^96 mod G */ - .fold_across_2_longs_const_lo = 0x490d678d, /* x^64 mod G */ - .barrett_reduction_const_1 = 0x826880ef, /* floor(x^63 / G) */ - .barrett_reduction_const_2 = 0x04c11db7, /* G - x^32 */ -#endif -}; - -/* - * Constants generated for least-significant-bit-first CRC-32 using - * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 + - * x^5 + x^4 + x^2 + x^1 + x^0 - */ -static const struct crc_clmul_consts crc32_lsb_0xedb88320_consts __maybe_unused = { -#ifdef CONFIG_64BIT - .fold_across_2_longs_const_hi = 0x65673b4600000000, /* x^191 mod G */ - .fold_across_2_longs_const_lo = 0x9ba54c6f00000000, /* x^127 mod G */ - .barrett_reduction_const_1 = 0xb4e5b025f7011641, /* floor(x^95 / G) */ - .barrett_reduction_const_2 = 0x00000000edb88320, /* (G - x^32) * x^32 */ -#else - .fold_across_2_longs_const_hi = 0xccaa009e, /* x^95 mod G */ - .fold_across_2_longs_const_lo = 0xb8bc6765, /* x^63 mod G */ - .barrett_reduction_const_1 = 0xf7011641, /* floor(x^63 / G) */ - .barrett_reduction_const_2 = 0xedb88320, /* (G - x^32) * x^0 */ -#endif -}; - -/* - * Constants generated for least-significant-bit-first CRC-32 using - * G(x) = x^32 + x^28 + x^27 + x^26 + x^25 + x^23 + x^22 + x^20 + x^19 + x^18 + - * x^14 + x^13 + x^11 + x^10 + x^9 + x^8 + x^6 + x^0 - */ -static const struct crc_clmul_consts crc32_lsb_0x82f63b78_consts __maybe_unused = { -#ifdef CONFIG_64BIT - .fold_across_2_longs_const_hi = 0x3743f7bd00000000, /* x^191 mod G */ - .fold_across_2_longs_const_lo = 0x3171d43000000000, /* x^127 mod G */ - .barrett_reduction_const_1 = 0x4869ec38dea713f1, /* floor(x^95 / G) */ - .barrett_reduction_const_2 = 0x0000000082f63b78, /* (G - x^32) * x^32 */ -#else - .fold_across_2_longs_const_hi = 0x493c7d27, /* x^95 mod G */ - .fold_across_2_longs_const_lo = 0xdd45aab8, /* x^63 mod G */ - .barrett_reduction_const_1 = 0xdea713f1, /* floor(x^63 / G) */ - .barrett_reduction_const_2 = 0x82f63b78, /* (G - x^32) * x^0 */ -#endif -}; - -/* - * Constants generated for most-significant-bit-first CRC-64 using - * G(x) = x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 + - * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 + - * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 + - * x^7 + x^4 + x^1 + x^0 - */ -#ifdef CONFIG_64BIT -static const struct crc_clmul_consts crc64_msb_0x42f0e1eba9ea3693_consts __maybe_unused = { - .fold_across_2_longs_const_hi = 0x4eb938a7d257740e, /* x^192 mod G */ - .fold_across_2_longs_const_lo = 0x05f5c3c7eb52fab6, /* x^128 mod G */ - .barrett_reduction_const_1 = 0xabc694e836627c39, /* floor(x^127 / G) */ - .barrett_reduction_const_2 = 0x42f0e1eba9ea3693, /* G - x^64 */ -}; -#endif - -/* - * Constants generated for least-significant-bit-first CRC-64 using - * G(x) = x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + - * x^47 + x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + - * x^26 + x^23 + x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + - * x^4 + x^3 + x^0 - */ -#ifdef CONFIG_64BIT -static const struct crc_clmul_consts crc64_lsb_0x9a6c9329ac4bc9b5_consts __maybe_unused = { - .fold_across_2_longs_const_hi = 0xeadc41fd2ba3d420, /* x^191 mod G */ - .fold_across_2_longs_const_lo = 0x21e9761e252621ac, /* x^127 mod G */ - .barrett_reduction_const_1 = 0x27ecfa329aef9f77, /* floor(x^127 / G) */ - .barrett_reduction_const_2 = 0x9a6c9329ac4bc9b5, /* (G - x^64) * x^0 */ -}; -#endif diff --git a/arch/riscv/lib/crc-clmul-template.h b/arch/riscv/lib/crc-clmul-template.h deleted file mode 100644 index 77187e7f1762..000000000000 --- a/arch/riscv/lib/crc-clmul-template.h +++ /dev/null @@ -1,265 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* Copyright 2025 Google LLC */ - -/* - * This file is a "template" that generates a CRC function optimized using the - * RISC-V Zbc (scalar carryless multiplication) extension. The includer of this - * file must define the following parameters to specify the type of CRC: - * - * crc_t: the data type of the CRC, e.g. u32 for a 32-bit CRC - * LSB_CRC: 0 for a msb (most-significant-bit) first CRC, i.e. natural - * mapping between bits and polynomial coefficients - * 1 for a lsb (least-significant-bit) first CRC, i.e. reflected - * mapping between bits and polynomial coefficients - */ - -#include <asm/byteorder.h> -#include <linux/minmax.h> - -#define CRC_BITS (8 * sizeof(crc_t)) /* a.k.a. 'n' */ - -static inline unsigned long clmul(unsigned long a, unsigned long b) -{ - unsigned long res; - - asm(".option push\n" - ".option arch,+zbc\n" - "clmul %0, %1, %2\n" - ".option pop\n" - : "=r" (res) : "r" (a), "r" (b)); - return res; -} - -static inline unsigned long clmulh(unsigned long a, unsigned long b) -{ - unsigned long res; - - asm(".option push\n" - ".option arch,+zbc\n" - "clmulh %0, %1, %2\n" - ".option pop\n" - : "=r" (res) : "r" (a), "r" (b)); - return res; -} - -static inline unsigned long clmulr(unsigned long a, unsigned long b) -{ - unsigned long res; - - asm(".option push\n" - ".option arch,+zbc\n" - "clmulr %0, %1, %2\n" - ".option pop\n" - : "=r" (res) : "r" (a), "r" (b)); - return res; -} - -/* - * crc_load_long() loads one "unsigned long" of aligned data bytes, producing a - * polynomial whose bit order matches the CRC's bit order. - */ -#ifdef CONFIG_64BIT -# if LSB_CRC -# define crc_load_long(x) le64_to_cpup(x) -# else -# define crc_load_long(x) be64_to_cpup(x) -# endif -#else -# if LSB_CRC -# define crc_load_long(x) le32_to_cpup(x) -# else -# define crc_load_long(x) be32_to_cpup(x) -# endif -#endif - -/* XOR @crc into the end of @msgpoly that represents the high-order terms. */ -static inline unsigned long -crc_clmul_prep(crc_t crc, unsigned long msgpoly) -{ -#if LSB_CRC - return msgpoly ^ crc; -#else - return msgpoly ^ ((unsigned long)crc << (BITS_PER_LONG - CRC_BITS)); -#endif -} - -/* - * Multiply the long-sized @msgpoly by x^n (a.k.a. x^CRC_BITS) and reduce it - * modulo the generator polynomial G. This gives the CRC of @msgpoly. - */ -static inline crc_t -crc_clmul_long(unsigned long msgpoly, const struct crc_clmul_consts *consts) -{ - unsigned long tmp; - - /* - * First step of Barrett reduction with integrated multiplication by - * x^n: calculate floor((msgpoly * x^n) / G). This is the value by - * which G needs to be multiplied to cancel out the x^n and higher terms - * of msgpoly * x^n. Do it using the following formula: - * - * msb-first: - * floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G)) / x^(BITS_PER_LONG-1)) - * lsb-first: - * floor((msgpoly * floor(x^(BITS_PER_LONG-1+n) / G) * x) / x^BITS_PER_LONG) - * - * barrett_reduction_const_1 contains floor(x^(BITS_PER_LONG-1+n) / G), - * which fits a long exactly. Using any lower power of x there would - * not carry enough precision through the calculation, while using any - * higher power of x would require extra instructions to handle a wider - * multiplication. In the msb-first case, using this power of x results - * in needing a floored division by x^(BITS_PER_LONG-1), which matches - * what clmulr produces. In the lsb-first case, a factor of x gets - * implicitly introduced by each carryless multiplication (shown as - * '* x' above), and the floored division instead needs to be by - * x^BITS_PER_LONG which matches what clmul produces. - */ -#if LSB_CRC - tmp = clmul(msgpoly, consts->barrett_reduction_const_1); -#else - tmp = clmulr(msgpoly, consts->barrett_reduction_const_1); -#endif - - /* - * Second step of Barrett reduction: - * - * crc := (msgpoly * x^n) + (G * floor((msgpoly * x^n) / G)) - * - * This reduces (msgpoly * x^n) modulo G by adding the appropriate - * multiple of G to it. The result uses only the x^0..x^(n-1) terms. - * HOWEVER, since the unreduced value (msgpoly * x^n) is zero in those - * terms in the first place, it is more efficient to do the equivalent: - * - * crc := ((G - x^n) * floor((msgpoly * x^n) / G)) mod x^n - * - * In the lsb-first case further modify it to the following which avoids - * a shift, as the crc ends up in the physically low n bits from clmulr: - * - * product := ((G - x^n) * x^(BITS_PER_LONG - n)) * floor((msgpoly * x^n) / G) * x - * crc := floor(product / x^(BITS_PER_LONG + 1 - n)) mod x^n - * - * barrett_reduction_const_2 contains the constant multiplier (G - x^n) - * or (G - x^n) * x^(BITS_PER_LONG - n) from the formulas above. The - * cast of the result to crc_t is essential, as it applies the mod x^n! - */ -#if LSB_CRC - return clmulr(tmp, consts->barrett_reduction_const_2); -#else - return clmul(tmp, consts->barrett_reduction_const_2); -#endif -} - -/* Update @crc with the data from @msgpoly. */ -static inline crc_t -crc_clmul_update_long(crc_t crc, unsigned long msgpoly, - const struct crc_clmul_consts *consts) -{ - return crc_clmul_long(crc_clmul_prep(crc, msgpoly), consts); -} - -/* Update @crc with 1 <= @len < sizeof(unsigned long) bytes of data. */ -static inline crc_t -crc_clmul_update_partial(crc_t crc, const u8 *p, size_t len, - const struct crc_clmul_consts *consts) -{ - unsigned long msgpoly; - size_t i; - -#if LSB_CRC - msgpoly = (unsigned long)p[0] << (BITS_PER_LONG - 8); - for (i = 1; i < len; i++) - msgpoly = (msgpoly >> 8) ^ ((unsigned long)p[i] << (BITS_PER_LONG - 8)); -#else - msgpoly = p[0]; - for (i = 1; i < len; i++) - msgpoly = (msgpoly << 8) ^ p[i]; -#endif - - if (len >= sizeof(crc_t)) { - #if LSB_CRC - msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len); - #else - msgpoly ^= (unsigned long)crc << (8*len - CRC_BITS); - #endif - return crc_clmul_long(msgpoly, consts); - } -#if LSB_CRC - msgpoly ^= (unsigned long)crc << (BITS_PER_LONG - 8*len); - return crc_clmul_long(msgpoly, consts) ^ (crc >> (8*len)); -#else - msgpoly ^= crc >> (CRC_BITS - 8*len); - return crc_clmul_long(msgpoly, consts) ^ (crc << (8*len)); -#endif -} - -static inline crc_t -crc_clmul(crc_t crc, const void *p, size_t len, - const struct crc_clmul_consts *consts) -{ - size_t align; - - /* This implementation assumes that the CRC fits in an unsigned long. */ - BUILD_BUG_ON(sizeof(crc_t) > sizeof(unsigned long)); - - /* If the buffer is not long-aligned, align it. */ - align = (unsigned long)p % sizeof(unsigned long); - if (align && len) { - align = min(sizeof(unsigned long) - align, len); - crc = crc_clmul_update_partial(crc, p, align, consts); - p += align; - len -= align; - } - - if (len >= 4 * sizeof(unsigned long)) { - unsigned long m0, m1; - - m0 = crc_clmul_prep(crc, crc_load_long(p)); - m1 = crc_load_long(p + sizeof(unsigned long)); - p += 2 * sizeof(unsigned long); - len -= 2 * sizeof(unsigned long); - /* - * Main loop. Each iteration starts with a message polynomial - * (x^BITS_PER_LONG)*m0 + m1, then logically extends it by two - * more longs of data to form x^(3*BITS_PER_LONG)*m0 + - * x^(2*BITS_PER_LONG)*m1 + x^BITS_PER_LONG*m2 + m3, then - * "folds" that back into a congruent (modulo G) value that uses - * just m0 and m1 again. This is done by multiplying m0 by the - * precomputed constant (x^(3*BITS_PER_LONG) mod G) and m1 by - * the precomputed constant (x^(2*BITS_PER_LONG) mod G), then - * adding the results to m2 and m3 as appropriate. Each such - * multiplication produces a result twice the length of a long, - * which in RISC-V is two instructions clmul and clmulh. - * - * This could be changed to fold across more than 2 longs at a - * time if there is a CPU that can take advantage of it. - */ - do { - unsigned long p0, p1, p2, p3; - - p0 = clmulh(m0, consts->fold_across_2_longs_const_hi); - p1 = clmul(m0, consts->fold_across_2_longs_const_hi); - p2 = clmulh(m1, consts->fold_across_2_longs_const_lo); - p3 = clmul(m1, consts->fold_across_2_longs_const_lo); - m0 = (LSB_CRC ? p1 ^ p3 : p0 ^ p2) ^ crc_load_long(p); - m1 = (LSB_CRC ? p0 ^ p2 : p1 ^ p3) ^ - crc_load_long(p + sizeof(unsigned long)); - - p += 2 * sizeof(unsigned long); - len -= 2 * sizeof(unsigned long); - } while (len >= 2 * sizeof(unsigned long)); - - crc = crc_clmul_long(m0, consts); - crc = crc_clmul_update_long(crc, m1, consts); - } - - while (len >= sizeof(unsigned long)) { - crc = crc_clmul_update_long(crc, crc_load_long(p), consts); - p += sizeof(unsigned long); - len -= sizeof(unsigned long); - } - - if (len) - crc = crc_clmul_update_partial(crc, p, len, consts); - - return crc; -} diff --git a/arch/riscv/lib/crc-clmul.h b/arch/riscv/lib/crc-clmul.h deleted file mode 100644 index dd1736245815..000000000000 --- a/arch/riscv/lib/crc-clmul.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* Copyright 2025 Google LLC */ - -#ifndef _RISCV_CRC_CLMUL_H -#define _RISCV_CRC_CLMUL_H - -#include <linux/types.h> -#include "crc-clmul-consts.h" - -u16 crc16_msb_clmul(u16 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts); -u32 crc32_msb_clmul(u32 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts); -u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts); -#ifdef CONFIG_64BIT -u64 crc64_msb_clmul(u64 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts); -u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts); -#endif - -#endif /* _RISCV_CRC_CLMUL_H */ diff --git a/arch/riscv/lib/crc-t10dif.c b/arch/riscv/lib/crc-t10dif.c deleted file mode 100644 index e6b0051ccd86..000000000000 --- a/arch/riscv/lib/crc-t10dif.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized CRC-T10DIF function - * - * Copyright 2025 Google LLC - */ - -#include <asm/hwcap.h> -#include <asm/alternative-macros.h> -#include <linux/crc-t10dif.h> -#include <linux/module.h> - -#include "crc-clmul.h" - -u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return crc16_msb_clmul(crc, p, len, &crc16_msb_0x8bb7_consts); - return crc_t10dif_generic(crc, p, len); -} -EXPORT_SYMBOL(crc_t10dif_arch); - -MODULE_DESCRIPTION("RISC-V optimized CRC-T10DIF function"); -MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc16_msb.c b/arch/riscv/lib/crc16_msb.c deleted file mode 100644 index 554d295e95f5..000000000000 --- a/arch/riscv/lib/crc16_msb.c +++ /dev/null @@ -1,18 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized most-significant-bit-first CRC16 - * - * Copyright 2025 Google LLC - */ - -#include "crc-clmul.h" - -typedef u16 crc_t; -#define LSB_CRC 0 -#include "crc-clmul-template.h" - -u16 crc16_msb_clmul(u16 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts) -{ - return crc_clmul(crc, p, len, consts); -} diff --git a/arch/riscv/lib/crc32.c b/arch/riscv/lib/crc32.c deleted file mode 100644 index a3188b7d9c40..000000000000 --- a/arch/riscv/lib/crc32.c +++ /dev/null @@ -1,53 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized CRC32 functions - * - * Copyright 2025 Google LLC - */ - -#include <asm/hwcap.h> -#include <asm/alternative-macros.h> -#include <linux/crc32.h> -#include <linux/module.h> - -#include "crc-clmul.h" - -u32 crc32_le_arch(u32 crc, const u8 *p, size_t len) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return crc32_lsb_clmul(crc, p, len, - &crc32_lsb_0xedb88320_consts); - return crc32_le_base(crc, p, len); -} -EXPORT_SYMBOL(crc32_le_arch); - -u32 crc32_be_arch(u32 crc, const u8 *p, size_t len) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return crc32_msb_clmul(crc, p, len, - &crc32_msb_0x04c11db7_consts); - return crc32_be_base(crc, p, len); -} -EXPORT_SYMBOL(crc32_be_arch); - -u32 crc32c_arch(u32 crc, const u8 *p, size_t len) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return crc32_lsb_clmul(crc, p, len, - &crc32_lsb_0x82f63b78_consts); - return crc32c_base(crc, p, len); -} -EXPORT_SYMBOL(crc32c_arch); - -u32 crc32_optimizations(void) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return CRC32_LE_OPTIMIZATION | - CRC32_BE_OPTIMIZATION | - CRC32C_OPTIMIZATION; - return 0; -} -EXPORT_SYMBOL(crc32_optimizations); - -MODULE_DESCRIPTION("RISC-V optimized CRC32 functions"); -MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc32_lsb.c b/arch/riscv/lib/crc32_lsb.c deleted file mode 100644 index 72fd67e7470c..000000000000 --- a/arch/riscv/lib/crc32_lsb.c +++ /dev/null @@ -1,18 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized least-significant-bit-first CRC32 - * - * Copyright 2025 Google LLC - */ - -#include "crc-clmul.h" - -typedef u32 crc_t; -#define LSB_CRC 1 -#include "crc-clmul-template.h" - -u32 crc32_lsb_clmul(u32 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts) -{ - return crc_clmul(crc, p, len, consts); -} diff --git a/arch/riscv/lib/crc32_msb.c b/arch/riscv/lib/crc32_msb.c deleted file mode 100644 index fdbeaccc369f..000000000000 --- a/arch/riscv/lib/crc32_msb.c +++ /dev/null @@ -1,18 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized most-significant-bit-first CRC32 - * - * Copyright 2025 Google LLC - */ - -#include "crc-clmul.h" - -typedef u32 crc_t; -#define LSB_CRC 0 -#include "crc-clmul-template.h" - -u32 crc32_msb_clmul(u32 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts) -{ - return crc_clmul(crc, p, len, consts); -} diff --git a/arch/riscv/lib/crc64.c b/arch/riscv/lib/crc64.c deleted file mode 100644 index f0015a27836a..000000000000 --- a/arch/riscv/lib/crc64.c +++ /dev/null @@ -1,34 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized CRC64 functions - * - * Copyright 2025 Google LLC - */ - -#include <asm/hwcap.h> -#include <asm/alternative-macros.h> -#include <linux/crc64.h> -#include <linux/module.h> - -#include "crc-clmul.h" - -u64 crc64_be_arch(u64 crc, const u8 *p, size_t len) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return crc64_msb_clmul(crc, p, len, - &crc64_msb_0x42f0e1eba9ea3693_consts); - return crc64_be_generic(crc, p, len); -} -EXPORT_SYMBOL(crc64_be_arch); - -u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len) -{ - if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBC)) - return crc64_lsb_clmul(crc, p, len, - &crc64_lsb_0x9a6c9329ac4bc9b5_consts); - return crc64_nvme_generic(crc, p, len); -} -EXPORT_SYMBOL(crc64_nvme_arch); - -MODULE_DESCRIPTION("RISC-V optimized CRC64 functions"); -MODULE_LICENSE("GPL"); diff --git a/arch/riscv/lib/crc64_lsb.c b/arch/riscv/lib/crc64_lsb.c deleted file mode 100644 index c5371bb85d90..000000000000 --- a/arch/riscv/lib/crc64_lsb.c +++ /dev/null @@ -1,18 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized least-significant-bit-first CRC64 - * - * Copyright 2025 Google LLC - */ - -#include "crc-clmul.h" - -typedef u64 crc_t; -#define LSB_CRC 1 -#include "crc-clmul-template.h" - -u64 crc64_lsb_clmul(u64 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts) -{ - return crc_clmul(crc, p, len, consts); -} diff --git a/arch/riscv/lib/crc64_msb.c b/arch/riscv/lib/crc64_msb.c deleted file mode 100644 index 1925d1dbe225..000000000000 --- a/arch/riscv/lib/crc64_msb.c +++ /dev/null @@ -1,18 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RISC-V optimized most-significant-bit-first CRC64 - * - * Copyright 2025 Google LLC - */ - -#include "crc-clmul.h" - -typedef u64 crc_t; -#define LSB_CRC 0 -#include "crc-clmul-template.h" - -u64 crc64_msb_clmul(u64 crc, const void *p, size_t len, - const struct crc_clmul_consts *consts) -{ - return crc_clmul(crc, p, len, consts); -} diff --git a/arch/riscv/lib/crypto/Kconfig b/arch/riscv/lib/crypto/Kconfig deleted file mode 100644 index 47c99ea97ce2..000000000000 --- a/arch/riscv/lib/crypto/Kconfig +++ /dev/null @@ -1,16 +0,0 @@ -# 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 deleted file mode 100644 index b7cb877a2c07..000000000000 --- a/arch/riscv/lib/crypto/Makefile +++ /dev/null @@ -1,7 +0,0 @@ -# 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 deleted file mode 100644 index 8c3f11d79be3..000000000000 --- a/arch/riscv/lib/crypto/chacha-riscv64-glue.c +++ /dev/null @@ -1,75 +0,0 @@ -// 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/lib/crypto/chacha-riscv64-zvkb.S b/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S deleted file mode 100644 index b777d0b4e379..000000000000 --- a/arch/riscv/lib/crypto/chacha-riscv64-zvkb.S +++ /dev/null @@ -1,297 +0,0 @@ -/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ -// -// This file is dual-licensed, meaning that you can use it under your -// choice of either of the following two licenses: -// -// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. -// -// Licensed under the Apache License 2.0 (the "License"). You can obtain -// a copy in the file LICENSE in the source distribution or at -// https://www.openssl.org/source/license.html -// -// or -// -// Copyright (c) 2023, Jerry Shih <jerry.shih@sifive.com> -// Copyright 2024 Google LLC -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions -// are met: -// 1. Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// 2. Redistributions in binary form must reproduce the above copyright -// notice, this list of conditions and the following disclaimer in the -// documentation and/or other materials provided with the distribution. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -// The generated code of this file depends on the following RISC-V extensions: -// - RV64I -// - RISC-V Vector ('V') with VLEN >= 128 -// - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') - -#include <linux/linkage.h> - -.text -.option arch, +zvkb - -#define STATEP a0 -#define INP a1 -#define OUTP a2 -#define NBLOCKS a3 -#define NROUNDS a4 - -#define CONSTS0 a5 -#define CONSTS1 a6 -#define CONSTS2 a7 -#define CONSTS3 t0 -#define TMP t1 -#define VL t2 -#define STRIDE t3 -#define ROUND_CTR t4 -#define KEY0 s0 -#define KEY1 s1 -#define KEY2 s2 -#define KEY3 s3 -#define KEY4 s4 -#define KEY5 s5 -#define KEY6 s6 -#define KEY7 s7 -#define COUNTER s8 -#define NONCE0 s9 -#define NONCE1 s10 -#define NONCE2 s11 - -.macro chacha_round a0, b0, c0, d0, a1, b1, c1, d1, \ - a2, b2, c2, d2, a3, b3, c3, d3 - // a += b; d ^= a; d = rol(d, 16); - vadd.vv \a0, \a0, \b0 - vadd.vv \a1, \a1, \b1 - vadd.vv \a2, \a2, \b2 - vadd.vv \a3, \a3, \b3 - vxor.vv \d0, \d0, \a0 - vxor.vv \d1, \d1, \a1 - vxor.vv \d2, \d2, \a2 - vxor.vv \d3, \d3, \a3 - vror.vi \d0, \d0, 32 - 16 - vror.vi \d1, \d1, 32 - 16 - vror.vi \d2, \d2, 32 - 16 - vror.vi \d3, \d3, 32 - 16 - - // c += d; b ^= c; b = rol(b, 12); - vadd.vv \c0, \c0, \d0 - vadd.vv \c1, \c1, \d1 - vadd.vv \c2, \c2, \d2 - vadd.vv \c3, \c3, \d3 - vxor.vv \b0, \b0, \c0 - vxor.vv \b1, \b1, \c1 - vxor.vv \b2, \b2, \c2 - vxor.vv \b3, \b3, \c3 - vror.vi \b0, \b0, 32 - 12 - vror.vi \b1, \b1, 32 - 12 - vror.vi \b2, \b2, 32 - 12 - vror.vi \b3, \b3, 32 - 12 - - // a += b; d ^= a; d = rol(d, 8); - vadd.vv \a0, \a0, \b0 - vadd.vv \a1, \a1, \b1 - vadd.vv \a2, \a2, \b2 - vadd.vv \a3, \a3, \b3 - vxor.vv \d0, \d0, \a0 - vxor.vv \d1, \d1, \a1 - vxor.vv \d2, \d2, \a2 - vxor.vv \d3, \d3, \a3 - vror.vi \d0, \d0, 32 - 8 - vror.vi \d1, \d1, 32 - 8 - vror.vi \d2, \d2, 32 - 8 - vror.vi \d3, \d3, 32 - 8 - - // c += d; b ^= c; b = rol(b, 7); - vadd.vv \c0, \c0, \d0 - vadd.vv \c1, \c1, \d1 - vadd.vv \c2, \c2, \d2 - vadd.vv \c3, \c3, \d3 - vxor.vv \b0, \b0, \c0 - vxor.vv \b1, \b1, \c1 - vxor.vv \b2, \b2, \c2 - vxor.vv \b3, \b3, \c3 - vror.vi \b0, \b0, 32 - 7 - vror.vi \b1, \b1, 32 - 7 - vror.vi \b2, \b2, 32 - 7 - vror.vi \b3, \b3, 32 - 7 -.endm - -// void chacha_zvkb(struct chacha_state *state, const u8 *in, u8 *out, -// size_t nblocks, int nrounds); -// -// |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) - sd s2, 16(sp) - sd s3, 24(sp) - sd s4, 32(sp) - sd s5, 40(sp) - sd s6, 48(sp) - sd s7, 56(sp) - sd s8, 64(sp) - sd s9, 72(sp) - sd s10, 80(sp) - sd s11, 88(sp) - - li STRIDE, 64 - - // Set up the initial state matrix in scalar registers. - 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, 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. - // Note that only the counter word, at index 12, differs across blocks. - vmv.v.x v0, CONSTS0 - vmv.v.x v1, CONSTS1 - vmv.v.x v2, CONSTS2 - vmv.v.x v3, CONSTS3 - vmv.v.x v4, KEY0 - vmv.v.x v5, KEY1 - vmv.v.x v6, KEY2 - vmv.v.x v7, KEY3 - vmv.v.x v8, KEY4 - vmv.v.x v9, KEY5 - vmv.v.x v10, KEY6 - vmv.v.x v11, KEY7 - vid.v v12 - vadd.vx v12, v12, COUNTER - vmv.v.x v13, NONCE0 - vmv.v.x v14, NONCE1 - vmv.v.x v15, NONCE2 - - // Load the first half of the input data for each block into v16-v23. - // v{16+i} holds the i'th 32-bit word for all blocks. - vlsseg8e32.v v16, (INP), STRIDE - - mv ROUND_CTR, NROUNDS -.Lnext_doubleround: - 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 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. - addi TMP, INP, 32 - vlsseg8e32.v v24, (TMP), STRIDE - - // Finalize the first half of the keystream for each block. - vadd.vx v0, v0, CONSTS0 - vadd.vx v1, v1, CONSTS1 - vadd.vx v2, v2, CONSTS2 - vadd.vx v3, v3, CONSTS3 - vadd.vx v4, v4, KEY0 - vadd.vx v5, v5, KEY1 - vadd.vx v6, v6, KEY2 - vadd.vx v7, v7, KEY3 - - // Encrypt/decrypt the first half of the data for each block. - vxor.vv v16, v16, v0 - vxor.vv v17, v17, v1 - vxor.vv v18, v18, v2 - vxor.vv v19, v19, v3 - vxor.vv v20, v20, v4 - vxor.vv v21, v21, v5 - vxor.vv v22, v22, v6 - vxor.vv v23, v23, v7 - - // Store the first half of the output data for each block. - vssseg8e32.v v16, (OUTP), STRIDE - - // Finalize the second half of the keystream for each block. - vadd.vx v8, v8, KEY4 - vadd.vx v9, v9, KEY5 - vadd.vx v10, v10, KEY6 - vadd.vx v11, v11, KEY7 - vid.v v0 - vadd.vx v12, v12, COUNTER - vadd.vx v13, v13, NONCE0 - vadd.vx v14, v14, NONCE1 - vadd.vx v15, v15, NONCE2 - vadd.vv v12, v12, v0 - - // Encrypt/decrypt the second half of the data for each block. - vxor.vv v24, v24, v8 - vxor.vv v25, v25, v9 - vxor.vv v26, v26, v10 - vxor.vv v27, v27, v11 - vxor.vv v29, v29, v13 - vxor.vv v28, v28, v12 - vxor.vv v30, v30, v14 - vxor.vv v31, v31, v15 - - // Store the second half of the output data for each block. - addi TMP, OUTP, 32 - vssseg8e32.v v24, (TMP), STRIDE - - // 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 NBLOCKS, NBLOCKS, VL - slli TMP, VL, 6 - add OUTP, OUTP, TMP - add INP, INP, TMP - bnez NBLOCKS, .Lblock_loop - - sw COUNTER, 48(STATEP) - ld s0, 0(sp) - ld s1, 8(sp) - ld s2, 16(sp) - ld s3, 24(sp) - ld s4, 32(sp) - ld s5, 40(sp) - ld s6, 48(sp) - ld s7, 56(sp) - ld s8, 64(sp) - ld s9, 72(sp) - ld s10, 80(sp) - ld s11, 88(sp) - addi sp, sp, 96 - ret -SYM_FUNC_END(chacha_zvkb) diff --git a/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S b/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S deleted file mode 100644 index fad501ad0617..000000000000 --- a/arch/riscv/lib/crypto/sha256-riscv64-zvknha_or_zvknhb-zvkb.S +++ /dev/null @@ -1,225 +0,0 @@ -/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ -// -// This file is dual-licensed, meaning that you can use it under your -// choice of either of the following two licenses: -// -// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. -// -// Licensed under the Apache License 2.0 (the "License"). You can obtain -// a copy in the file LICENSE in the source distribution or at -// https://www.openssl.org/source/license.html -// -// or -// -// Copyright (c) 2023, Christoph Müllner <christoph.muellner@vrull.eu> -// Copyright (c) 2023, Phoebe Chen <phoebe.chen@sifive.com> -// Copyright 2024 Google LLC -// All rights reserved. -// -// Redistribution and use in source and binary forms, with or without -// modification, are permitted provided that the following conditions -// are met: -// 1. Redistributions of source code must retain the above copyright -// notice, this list of conditions and the following disclaimer. -// 2. Redistributions in binary form must reproduce the above copyright -// notice, this list of conditions and the following disclaimer in the -// documentation and/or other materials provided with the distribution. -// -// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS -// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT -// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR -// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT -// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, -// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT -// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, -// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY -// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT -// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE -// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - -// The generated code of this file depends on the following RISC-V extensions: -// - RV64I -// - RISC-V Vector ('V') with VLEN >= 128 -// - RISC-V Vector SHA-2 Secure Hash extension ('Zvknha' or 'Zvknhb') -// - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') - -#include <linux/linkage.h> - -.text -.option arch, +zvknha, +zvkb - -#define STATEP a0 -#define DATA a1 -#define NUM_BLOCKS a2 - -#define STATEP_C a3 - -#define MASK v0 -#define INDICES v1 -#define W0 v2 -#define W1 v3 -#define W2 v4 -#define W3 v5 -#define VTMP v6 -#define FEBA v7 -#define HGDC v8 -#define K0 v10 -#define K1 v11 -#define K2 v12 -#define K3 v13 -#define K4 v14 -#define K5 v15 -#define K6 v16 -#define K7 v17 -#define K8 v18 -#define K9 v19 -#define K10 v20 -#define K11 v21 -#define K12 v22 -#define K13 v23 -#define K14 v24 -#define K15 v25 -#define PREV_FEBA v26 -#define PREV_HGDC v27 - -// Do 4 rounds of SHA-256. w0 contains the current 4 message schedule words. -// -// If not all the message schedule words have been computed yet, then this also -// computes 4 more message schedule words. w1-w3 contain the next 3 groups of 4 -// message schedule words; this macro computes the group after w3 and writes it -// to w0. This means that the next (w0, w1, w2, w3) is the current (w1, w2, w3, -// w0), so the caller must cycle through the registers accordingly. -.macro sha256_4rounds last, k, w0, w1, w2, w3 - vadd.vv VTMP, \k, \w0 - vsha2cl.vv HGDC, FEBA, VTMP - vsha2ch.vv FEBA, HGDC, VTMP -.if !\last - vmerge.vvm VTMP, \w2, \w1, MASK - vsha2ms.vv \w0, VTMP, \w3 -.endif -.endm - -.macro sha256_16rounds last, k0, k1, k2, k3 - sha256_4rounds \last, \k0, W0, W1, W2, W3 - sha256_4rounds \last, \k1, W1, W2, W3, W0 - sha256_4rounds \last, \k2, W2, W3, W0, W1 - sha256_4rounds \last, \k3, W3, W0, W1, W2 -.endm - -// 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 - la t0, K256 - vle32.v K0, (t0) - addi t0, t0, 16 - vle32.v K1, (t0) - addi t0, t0, 16 - vle32.v K2, (t0) - addi t0, t0, 16 - vle32.v K3, (t0) - addi t0, t0, 16 - vle32.v K4, (t0) - addi t0, t0, 16 - vle32.v K5, (t0) - addi t0, t0, 16 - vle32.v K6, (t0) - addi t0, t0, 16 - vle32.v K7, (t0) - addi t0, t0, 16 - vle32.v K8, (t0) - addi t0, t0, 16 - vle32.v K9, (t0) - addi t0, t0, 16 - vle32.v K10, (t0) - addi t0, t0, 16 - vle32.v K11, (t0) - addi t0, t0, 16 - vle32.v K12, (t0) - addi t0, t0, 16 - vle32.v K13, (t0) - addi t0, t0, 16 - vle32.v K14, (t0) - addi t0, t0, 16 - vle32.v K15, (t0) - - // 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. - vsetivli zero, 1, e8, m1, ta, ma - vmv.v.i MASK, 0x01 - - // Load the state. The state is stored as {a,b,c,d,e,f,g,h}, but we - // need {f,e,b,a},{h,g,d,c}. The dst vtype is e32m1 and the index vtype - // is e8mf4. We use index-load with the i8 indices {20, 16, 4, 0}, - // loaded using the 32-bit little endian value 0x00041014. - li t0, 0x00041014 - vsetivli zero, 1, e32, m1, ta, ma - vmv.v.x INDICES, t0 - addi STATEP_C, STATEP, 8 - vsetivli zero, 4, e32, m1, ta, ma - vluxei8.v FEBA, (STATEP), INDICES - vluxei8.v HGDC, (STATEP_C), INDICES - -.Lnext_block: - addi NUM_BLOCKS, NUM_BLOCKS, -1 - - // Save the previous state, as it's needed later. - vmv.v.v PREV_FEBA, FEBA - vmv.v.v PREV_HGDC, HGDC - - // Load the next 512-bit message block and endian-swap each 32-bit word. - vle32.v W0, (DATA) - vrev8.v W0, W0 - addi DATA, DATA, 16 - vle32.v W1, (DATA) - vrev8.v W1, W1 - addi DATA, DATA, 16 - vle32.v W2, (DATA) - vrev8.v W2, W2 - addi DATA, DATA, 16 - vle32.v W3, (DATA) - vrev8.v W3, W3 - addi DATA, DATA, 16 - - // Do the 64 rounds of SHA-256. - sha256_16rounds 0, K0, K1, K2, K3 - sha256_16rounds 0, K4, K5, K6, K7 - sha256_16rounds 0, K8, K9, K10, K11 - sha256_16rounds 1, K12, K13, K14, K15 - - // Add the previous state. - vadd.vv FEBA, FEBA, PREV_FEBA - vadd.vv HGDC, HGDC, PREV_HGDC - - // Repeat if more blocks remain. - bnez NUM_BLOCKS, .Lnext_block - - // Store the new state and return. - vsuxei8.v FEBA, (STATEP), INDICES - vsuxei8.v HGDC, (STATEP_C), INDICES - ret -SYM_FUNC_END(sha256_transform_zvknha_or_zvknhb_zvkb) - -.section ".rodata" -.p2align 2 -.type K256, @object -K256: - .word 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5 - .word 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5 - .word 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3 - .word 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174 - .word 0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc - .word 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da - .word 0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7 - .word 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967 - .word 0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13 - .word 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85 - .word 0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3 - .word 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070 - .word 0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5 - .word 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3 - .word 0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208 - .word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 -.size K256, . - K256 diff --git a/arch/riscv/lib/crypto/sha256.c b/arch/riscv/lib/crypto/sha256.c deleted file mode 100644 index 71808397dff4..000000000000 --- a/arch/riscv/lib/crypto/sha256.c +++ /dev/null @@ -1,67 +0,0 @@ -// 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/purgatory/Makefile b/arch/riscv/purgatory/Makefile index fb9c917c9b45..240592e3f5c2 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -53,7 +53,7 @@ targets += purgatory.ro purgatory.chk PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel PURGATORY_CFLAGS := -mcmodel=medany -ffreestanding -fno-zero-initialized-in-bss -PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING +PURGATORY_CFLAGS += $(DISABLE_KSTACK_ERASE) -DDISABLE_BRANCH_PROFILING PURGATORY_CFLAGS += -fno-stack-protector -g0 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That diff --git a/arch/riscv/purgatory/purgatory.c b/arch/riscv/purgatory/purgatory.c index 80596ab5fb62..bbd5cfa4d741 100644 --- a/arch/riscv/purgatory/purgatory.c +++ b/arch/riscv/purgatory/purgatory.c @@ -20,14 +20,14 @@ struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(".kex static int verify_sha256_digest(void) { struct kexec_sha_region *ptr, *end; - struct sha256_state ss; + struct sha256_ctx sctx; u8 digest[SHA256_DIGEST_SIZE]; - sha256_init(&ss); + sha256_init(&sctx); end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); for (ptr = purgatory_sha_regions; ptr < end; ptr++) - sha256_update(&ss, (uint8_t *)(ptr->start), ptr->len); - sha256_final(&ss, digest); + sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len); + sha256_final(&sctx, digest); if (memcmp(digest, purgatory_sha256_digest, sizeof(digest)) != 0) return 1; return 0; diff --git a/arch/riscv/tools/relocs_check.sh b/arch/riscv/tools/relocs_check.sh index baeb2e7b2290..742993e6a8cb 100755 --- a/arch/riscv/tools/relocs_check.sh +++ b/arch/riscv/tools/relocs_check.sh @@ -14,7 +14,9 @@ bad_relocs=$( ${srctree}/scripts/relocs_check.sh "$@" | # These relocations are okay # R_RISCV_RELATIVE - grep -F -w -v 'R_RISCV_RELATIVE' + # R_RISCV_NONE + grep -F -w -v 'R_RISCV_RELATIVE +R_RISCV_NONE' ) if [ -z "$bad_relocs" ]; then |